Validation of psoriatic arthritis diagnoses in electronic medical records using natural language processing

PubMed Central

Cai, Tianxi; Karlson, Elizabeth W.

2013-01-01

Objectives To test whether data extracted from full text patient visit notes from an electronic medical record (EMR) would improve the classification of PsA compared to an algorithm based on codified data. Methods From the > 1,350,000 adults in a large academic EMR, all 2318 patients with a billing code for PsA were extracted and 550 were randomly selected for chart review and algorithm training. Using codified data and phrases extracted from narrative data using natural language processing, 31 predictors were extracted and three random forest algorithms trained using coded, narrative, and combined predictors. The receiver operator curve (ROC) was used to identify the optimal algorithm and a cut point was chosen to achieve the maximum sensitivity possible at a 90% positive predictive value (PPV). The algorithm was then used to classify the remaining 1768 charts and finally validated in a random sample of 300 cases predicted to have PsA. Results The PPV of a single PsA code was 57% (95%CI 55%–58%). Using a combination of coded data and NLP the random forest algorithm reached a PPV of 90% (95%CI 86%–93%) at sensitivity of 87% (95% CI 83% – 91%) in the training data. The PPV was 93% (95%CI 89%–96%) in the validation set. Adding NLP predictors to codified data increased the area under the ROC (p < 0.001). Conclusions Using NLP with text notes from electronic medical records improved the performance of the prediction algorithm significantly. Random forests were a useful tool to accurately classify psoriatic arthritis cases to enable epidemiological research. PMID:20701955

The Past, Present and Future of the Meteorological Phenomena Identification Near the Ground (mPING) Project

NASA Astrophysics Data System (ADS)

Elmore, K. L.

2016-12-01

The Metorological Phenomemna Identification NeartheGround (mPING) project is an example of a crowd-sourced, citizen science effort to gather data of sufficeint quality and quantity needed by new post processing methods that use machine learning. Transportation and infrastructure are particularly sensitive to precipitation type in winter weather. We extract attributes from operational numerical forecast models and use them in a random forest to generate forecast winter precipitation types. We find that random forests applied to forecast soundings are effective at generating skillful forecasts of surface ptype with consideralbly more skill than the current algorithms, especuially for ice pellets and freezing rain. We also find that three very different forecast models yuield similar overall results, showing that random forests are able to extract essentially equivalent information from different forecast models. We also show that the random forest for each model, and each profile type is unique to the particular forecast model and that the random forests developed using a particular model suffer significant degradation when given attributes derived from a different model. This implies that no single algorithm can perform well across all forecast models. Clearly, random forests extract information unavailable to "physically based" methods because the physical information in the models does not appear as we expect. One intersting result is that results from the classic "warm nose" sounding profile are, by far, the most sensitive to the particular forecast model, but this profile is also the one for which random forests are most skillful. Finally, a method for calibrarting probabilties for each different ptype using multinomial logistic regression is shown.

Do bioclimate variables improve performance of climate envelope models?

USGS Publications Warehouse

Watling, James I.; Romañach, Stephanie S.; Bucklin, David N.; Speroterra, Carolina; Brandt, Laura A.; Pearlstine, Leonard G.; Mazzotti, Frank J.

2012-01-01

Climate envelope models are widely used to forecast potential effects of climate change on species distributions. A key issue in climate envelope modeling is the selection of predictor variables that most directly influence species. To determine whether model performance and spatial predictions were related to the selection of predictor variables, we compared models using bioclimate variables with models constructed from monthly climate data for twelve terrestrial vertebrate species in the southeastern USA using two different algorithms (random forests or generalized linear models), and two model selection techniques (using uncorrelated predictors or a subset of user-defined biologically relevant predictor variables). There were no differences in performance between models created with bioclimate or monthly variables, but one metric of model performance was significantly greater using the random forest algorithm compared with generalized linear models. Spatial predictions between maps using bioclimate and monthly variables were very consistent using the random forest algorithm with uncorrelated predictors, whereas we observed greater variability in predictions using generalized linear models.

CW-SSIM kernel based random forest for image classification

NASA Astrophysics Data System (ADS)

Fan, Guangzhe; Wang, Zhou; Wang, Jiheng

2010-07-01

Complex wavelet structural similarity (CW-SSIM) index has been proposed as a powerful image similarity metric that is robust to translation, scaling and rotation of images, but how to employ it in image classification applications has not been deeply investigated. In this paper, we incorporate CW-SSIM as a kernel function into a random forest learning algorithm. This leads to a novel image classification approach that does not require a feature extraction or dimension reduction stage at the front end. We use hand-written digit recognition as an example to demonstrate our algorithm. We compare the performance of the proposed approach with random forest learning based on other kernels, including the widely adopted Gaussian and the inner product kernels. Empirical evidences show that the proposed method is superior in its classification power. We also compared our proposed approach with the direct random forest method without kernel and the popular kernel-learning method support vector machine. Our test results based on both simulated and realworld data suggest that the proposed approach works superior to traditional methods without the feature selection procedure.

Random Forest Application for NEXRAD Radar Data Quality Control

NASA Astrophysics Data System (ADS)

Keem, M.; Seo, B. C.; Krajewski, W. F.

2017-12-01

Identification and elimination of non-meteorological radar echoes (e.g., returns from ground, wind turbines, and biological targets) are the basic data quality control steps before radar data use in quantitative applications (e.g., precipitation estimation). Although WSR-88Ds' recent upgrade to dual-polarization has enhanced this quality control and echo classification, there are still challenges to detect some non-meteorological echoes that show precipitation-like characteristics (e.g., wind turbine or anomalous propagation clutter embedded in rain). With this in mind, a new quality control method using Random Forest is proposed in this study. This classification algorithm is known to produce reliable results with less uncertainty. The method introduces randomness into sampling and feature selections and integrates consequent multiple decision trees. The multidimensional structure of the trees can characterize the statistical interactions of involved multiple features in complex situations. The authors explore the performance of Random Forest method for NEXRAD radar data quality control. Training datasets are selected using several clear cases of precipitation and non-precipitation (but with some non-meteorological echoes). The model is structured using available candidate features (from the NEXRAD data) such as horizontal reflectivity, differential reflectivity, differential phase shift, copolar correlation coefficient, and their horizontal textures (e.g., local standard deviation). The influence of each feature on classification results are quantified by variable importance measures that are automatically estimated by the Random Forest algorithm. Therefore, the number and types of features in the final forest can be examined based on the classification accuracy. The authors demonstrate the capability of the proposed approach using several cases ranging from distinct to complex rain/no-rain events and compare the performance with the existing algorithms (e.g., MRMS). They also discuss operational feasibility based on the observed strength and weakness of the method.

The Efficiency of Random Forest Method for Shoreline Extraction from LANDSAT-8 and GOKTURK-2 Imageries

NASA Astrophysics Data System (ADS)

Bayram, B.; Erdem, F.; Akpinar, B.; Ince, A. K.; Bozkurt, S.; Catal Reis, H.; Seker, D. Z.

2017-11-01

Coastal monitoring plays a vital role in environmental planning and hazard management related issues. Since shorelines are fundamental data for environment management, disaster management, coastal erosion studies, modelling of sediment transport and coastal morphodynamics, various techniques have been developed to extract shorelines. Random Forest is one of these techniques which is used in this study for shoreline extraction.. This algorithm is a machine learning method based on decision trees. Decision trees analyse classes of training data creates rules for classification. In this study, Terkos region has been chosen for the proposed method within the scope of "TUBITAK Project (Project No: 115Y718) titled "Integration of Unmanned Aerial Vehicles for Sustainable Coastal Zone Monitoring Model - Three-Dimensional Automatic Coastline Extraction and Analysis: Istanbul-Terkos Example". Random Forest algorithm has been implemented to extract the shoreline of the Black Sea where near the lake from LANDSAT-8 and GOKTURK-2 satellite imageries taken in 2015. The MATLAB environment was used for classification. To obtain land and water-body classes, the Random Forest method has been applied to NIR bands of LANDSAT-8 (5th band) and GOKTURK-2 (4th band) imageries. Each image has been digitized manually and shorelines obtained for accuracy assessment. According to accuracy assessment results, Random Forest method is efficient for both medium and high resolution images for shoreline extraction studies.

Underwater image enhancement through depth estimation based on random forest

NASA Astrophysics Data System (ADS)

Tai, Shen-Chuan; Tsai, Ting-Chou; Huang, Jyun-Han

2017-11-01

Light absorption and scattering in underwater environments can result in low-contrast images with a distinct color cast. This paper proposes a systematic framework for the enhancement of underwater images. Light transmission is estimated using the random forest algorithm. RGB values, luminance, color difference, blurriness, and the dark channel are treated as features in training and estimation. Transmission is calculated using an ensemble machine learning algorithm to deal with a variety of conditions encountered in underwater environments. A color compensation and contrast enhancement algorithm based on depth information was also developed with the aim of improving the visual quality of underwater images. Experimental results demonstrate that the proposed scheme outperforms existing methods with regard to subjective visual quality as well as objective measurements.

A Robust Random Forest-Based Approach for Heart Rate Monitoring Using Photoplethysmography Signal Contaminated by Intense Motion Artifacts.

PubMed

Ye, Yalan; He, Wenwen; Cheng, Yunfei; Huang, Wenxia; Zhang, Zhilin

2017-02-16

The estimation of heart rate (HR) based on wearable devices is of interest in fitness. Photoplethysmography (PPG) is a promising approach to estimate HR due to low cost; however, it is easily corrupted by motion artifacts (MA). In this work, a robust approach based on random forest is proposed for accurately estimating HR from the photoplethysmography signal contaminated by intense motion artifacts, consisting of two stages. Stage 1 proposes a hybrid method to effectively remove MA with a low computation complexity, where two MA removal algorithms are combined by an accurate binary decision algorithm whose aim is to decide whether or not to adopt the second MA removal algorithm. Stage 2 proposes a random forest-based spectral peak-tracking algorithm, whose aim is to locate the spectral peak corresponding to HR, formulating the problem of spectral peak tracking into a pattern classification problem. Experiments on the PPG datasets including 22 subjects used in the 2015 IEEE Signal Processing Cup showed that the proposed approach achieved the average absolute error of 1.65 beats per minute (BPM) on the 22 PPG datasets. Compared to state-of-the-art approaches, the proposed approach has better accuracy and robustness to intense motion artifacts, indicating its potential use in wearable sensors for health monitoring and fitness tracking.

Predicting Coastal Flood Severity using Random Forest Algorithm

NASA Astrophysics Data System (ADS)

Sadler, J. M.; Goodall, J. L.; Morsy, M. M.; Spencer, K.

2017-12-01

Coastal floods have become more common recently and are predicted to further increase in frequency and severity due to sea level rise. Predicting floods in coastal cities can be difficult due to the number of environmental and geographic factors which can influence flooding events. Built stormwater infrastructure and irregular urban landscapes add further complexity. This paper demonstrates the use of machine learning algorithms in predicting street flood occurrence in an urban coastal setting. The model is trained and evaluated using data from Norfolk, Virginia USA from September 2010 - October 2016. Rainfall, tide levels, water table levels, and wind conditions are used as input variables. Street flooding reports made by city workers after named and unnamed storm events, ranging from 1-159 reports per event, are the model output. Results show that Random Forest provides predictive power in estimating the number of flood occurrences given a set of environmental conditions with an out-of-bag root mean squared error of 4.3 flood reports and a mean absolute error of 0.82 flood reports. The Random Forest algorithm performed much better than Poisson regression. From the Random Forest model, total daily rainfall was by far the most important factor in flood occurrence prediction, followed by daily low tide and daily higher high tide. The model demonstrated here could be used to predict flood severity based on forecast rainfall and tide conditions and could be further enhanced using more complete street flooding data for model training.

Identification of Genes Involved in Breast Cancer Metastasis by Integrating Protein-Protein Interaction Information with Expression Data.

PubMed

Tian, Xin; Xin, Mingyuan; Luo, Jian; Liu, Mingyao; Jiang, Zhenran

2017-02-01

The selection of relevant genes for breast cancer metastasis is critical for the treatment and prognosis of cancer patients. Although much effort has been devoted to the gene selection procedures by use of different statistical analysis methods or computational techniques, the interpretation of the variables in the resulting survival models has been limited so far. This article proposes a new Random Forest (RF)-based algorithm to identify important variables highly related with breast cancer metastasis, which is based on the important scores of two variable selection algorithms, including the mean decrease Gini (MDG) criteria of Random Forest and the GeneRank algorithm with protein-protein interaction (PPI) information. The new gene selection algorithm can be called PPIRF. The improved prediction accuracy fully illustrated the reliability and high interpretability of gene list selected by the PPIRF approach.

Predicting CD4 count changes among patients on antiretroviral treatment: Application of data mining techniques.

PubMed

Kebede, Mihiretu; Zegeye, Desalegn Tigabu; Zeleke, Berihun Megabiaw

2017-12-01

To monitor the progress of therapy and disease progression, periodic CD4 counts are required throughout the course of HIV/AIDS care and support. The demand for CD4 count measurement is increasing as ART programs expand over the last decade. This study aimed to predict CD4 count changes and to identify the predictors of CD4 count changes among patients on ART. A cross-sectional study was conducted at the University of Gondar Hospital from 3,104 adult patients on ART with CD4 counts measured at least twice (baseline and most recent). Data were retrieved from the HIV care clinic electronic database and patients` charts. Descriptive data were analyzed by SPSS version 20. Cross-Industry Standard Process for Data Mining (CRISP-DM) methodology was followed to undertake the study. WEKA version 3.8 was used to conduct a predictive data mining. Before building the predictive data mining models, information gain values and correlation-based Feature Selection methods were used for attribute selection. Variables were ranked according to their relevance based on their information gain values. J48, Neural Network, and Random Forest algorithms were experimented to assess model accuracies. The median duration of ART was 191.5 weeks. The mean CD4 count change was 243 (SD 191.14) cells per microliter. Overall, 2427 (78.2%) patients had their CD4 counts increased by at least 100 cells per microliter, while 4% had a decline from the baseline CD4 value. Baseline variables including age, educational status, CD8 count, ART regimen, and hemoglobin levels predicted CD4 count changes with predictive accuracies of J48, Neural Network, and Random Forest being 87.1%, 83.5%, and 99.8%, respectively. Random Forest algorithm had a superior performance accuracy level than both J48 and Artificial Neural Network. The precision, sensitivity and recall values of Random Forest were also more than 99%. Nearly accurate prediction results were obtained using Random Forest algorithm. This algorithm could be used in a low-resource setting to build a web-based prediction model for CD4 count changes. Copyright © 2017 Elsevier B.V. All rights reserved.

3D Forest: An application for descriptions of three-dimensional forest structures using terrestrial LiDAR

PubMed Central

Krůček, Martin; Vrška, Tomáš; Král, Kamil

2017-01-01

Terrestrial laser scanning is a powerful technology for capturing the three-dimensional structure of forests with a high level of detail and accuracy. Over the last decade, many algorithms have been developed to extract various tree parameters from terrestrial laser scanning data. Here we present 3D Forest, an open-source non-platform-specific software application with an easy-to-use graphical user interface with the compilation of algorithms focused on the forest environment and extraction of tree parameters. The current version (0.42) extracts important parameters of forest structure from the terrestrial laser scanning data, such as stem positions (X, Y, Z), tree heights, diameters at breast height (DBH), as well as more advanced parameters such as tree planar projections, stem profiles or detailed crown parameters including convex and concave crown surface and volume. Moreover, 3D Forest provides quantitative measures of between-crown interactions and their real arrangement in 3D space. 3D Forest also includes an original algorithm of automatic tree segmentation and crown segmentation. Comparison with field data measurements showed no significant difference in measuring DBH or tree height using 3D Forest, although for DBH only the Randomized Hough Transform algorithm proved to be sufficiently resistant to noise and provided results comparable to traditional field measurements. PMID:28472167

Random forests ensemble classifier trained with data resampling strategy to improve cardiac arrhythmia diagnosis.

PubMed

Ozçift, Akin

2011-05-01

Supervised classification algorithms are commonly used in the designing of computer-aided diagnosis systems. In this study, we present a resampling strategy based Random Forests (RF) ensemble classifier to improve diagnosis of cardiac arrhythmia. Random forests is an ensemble classifier that consists of many decision trees and outputs the class that is the mode of the class's output by individual trees. In this way, an RF ensemble classifier performs better than a single tree from classification performance point of view. In general, multiclass datasets having unbalanced distribution of sample sizes are difficult to analyze in terms of class discrimination. Cardiac arrhythmia is such a dataset that has multiple classes with small sample sizes and it is therefore adequate to test our resampling based training strategy. The dataset contains 452 samples in fourteen types of arrhythmias and eleven of these classes have sample sizes less than 15. Our diagnosis strategy consists of two parts: (i) a correlation based feature selection algorithm is used to select relevant features from cardiac arrhythmia dataset. (ii) RF machine learning algorithm is used to evaluate the performance of selected features with and without simple random sampling to evaluate the efficiency of proposed training strategy. The resultant accuracy of the classifier is found to be 90.0% and this is a quite high diagnosis performance for cardiac arrhythmia. Furthermore, three case studies, i.e., thyroid, cardiotocography and audiology, are used to benchmark the effectiveness of the proposed method. The results of experiments demonstrated the efficiency of random sampling strategy in training RF ensemble classification algorithm. Copyright © 2011 Elsevier Ltd. All rights reserved.

Combined rule extraction and feature elimination in supervised classification.

PubMed

Liu, Sheng; Patel, Ronak Y; Daga, Pankaj R; Liu, Haining; Fu, Gang; Doerksen, Robert J; Chen, Yixin; Wilkins, Dawn E

2012-09-01

There are a vast number of biology related research problems involving a combination of multiple sources of data to achieve a better understanding of the underlying problems. It is important to select and interpret the most important information from these sources. Thus it will be beneficial to have a good algorithm to simultaneously extract rules and select features for better interpretation of the predictive model. We propose an efficient algorithm, Combined Rule Extraction and Feature Elimination (CRF), based on 1-norm regularized random forests. CRF simultaneously extracts a small number of rules generated by random forests and selects important features. We applied CRF to several drug activity prediction and microarray data sets. CRF is capable of producing performance comparable with state-of-the-art prediction algorithms using a small number of decision rules. Some of the decision rules are biologically significant.

Characterizing stand-level forest canopy cover and height using Landsat time series, samples of airborne LiDAR, and the Random Forest algorithm

NASA Astrophysics Data System (ADS)

Ahmed, Oumer S.; Franklin, Steven E.; Wulder, Michael A.; White, Joanne C.

2015-03-01

Many forest management activities, including the development of forest inventories, require spatially detailed forest canopy cover and height data. Among the various remote sensing technologies, LiDAR (Light Detection and Ranging) offers the most accurate and consistent means for obtaining reliable canopy structure measurements. A potential solution to reduce the cost of LiDAR data, is to integrate transects (samples) of LiDAR data with frequently acquired and spatially comprehensive optical remotely sensed data. Although multiple regression is commonly used for such modeling, often it does not fully capture the complex relationships between forest structure variables. This study investigates the potential of Random Forest (RF), a machine learning technique, to estimate LiDAR measured canopy structure using a time series of Landsat imagery. The study is implemented over a 2600 ha area of industrially managed coastal temperate forests on Vancouver Island, British Columbia, Canada. We implemented a trajectory-based approach to time series analysis that generates time since disturbance (TSD) and disturbance intensity information for each pixel and we used this information to stratify the forest land base into two strata: mature forests and young forests. Canopy cover and height for three forest classes (i.e. mature, young and mature and young (combined)) were modeled separately using multiple regression and Random Forest (RF) techniques. For all forest classes, the RF models provided improved estimates relative to the multiple regression models. The lowest validation error was obtained for the mature forest strata in a RF model (R2 = 0.88, RMSE = 2.39 m and bias = -0.16 for canopy height; R2 = 0.72, RMSE = 0.068% and bias = -0.0049 for canopy cover). This study demonstrates the value of using disturbance and successional history to inform estimates of canopy structure and obtain improved estimates of forest canopy cover and height using the RF algorithm.

Toward Improving Electrocardiogram (ECG) Biometric Verification using Mobile Sensors: A Two-Stage Classifier Approach

PubMed Central

Tan, Robin; Perkowski, Marek

2017-01-01

Electrocardiogram (ECG) signals sensed from mobile devices pertain the potential for biometric identity recognition applicable in remote access control systems where enhanced data security is demanding. In this study, we propose a new algorithm that consists of a two-stage classifier combining random forest and wavelet distance measure through a probabilistic threshold schema, to improve the effectiveness and robustness of a biometric recognition system using ECG data acquired from a biosensor integrated into mobile devices. The proposed algorithm is evaluated using a mixed dataset from 184 subjects under different health conditions. The proposed two-stage classifier achieves a total of 99.52% subject verification accuracy, better than the 98.33% accuracy from random forest alone and 96.31% accuracy from wavelet distance measure algorithm alone. These results demonstrate the superiority of the proposed algorithm for biometric identification, hence supporting its practicality in areas such as cloud data security, cyber-security or remote healthcare systems. PMID:28230745

Toward Improving Electrocardiogram (ECG) Biometric Verification using Mobile Sensors: A Two-Stage Classifier Approach.

PubMed

Tan, Robin; Perkowski, Marek

2017-02-20

Electrocardiogram (ECG) signals sensed from mobile devices pertain the potential for biometric identity recognition applicable in remote access control systems where enhanced data security is demanding. In this study, we propose a new algorithm that consists of a two-stage classifier combining random forest and wavelet distance measure through a probabilistic threshold schema, to improve the effectiveness and robustness of a biometric recognition system using ECG data acquired from a biosensor integrated into mobile devices. The proposed algorithm is evaluated using a mixed dataset from 184 subjects under different health conditions. The proposed two-stage classifier achieves a total of 99.52% subject verification accuracy, better than the 98.33% accuracy from random forest alone and 96.31% accuracy from wavelet distance measure algorithm alone. These results demonstrate the superiority of the proposed algorithm for biometric identification, hence supporting its practicality in areas such as cloud data security, cyber-security or remote healthcare systems.

Introducing two Random Forest based methods for cloud detection in remote sensing images

NASA Astrophysics Data System (ADS)

Ghasemian, Nafiseh; Akhoondzadeh, Mehdi

2018-07-01

Cloud detection is a necessary phase in satellite images processing to retrieve the atmospheric and lithospheric parameters. Currently, some cloud detection methods based on Random Forest (RF) model have been proposed but they do not consider both spectral and textural characteristics of the image. Furthermore, they have not been tested in the presence of snow/ice. In this paper, we introduce two RF based algorithms, Feature Level Fusion Random Forest (FLFRF) and Decision Level Fusion Random Forest (DLFRF) to incorporate visible, infrared (IR) and thermal spectral and textural features (FLFRF) including Gray Level Co-occurrence Matrix (GLCM) and Robust Extended Local Binary Pattern (RELBP_CI) or visible, IR and thermal classifiers (DLFRF) for highly accurate cloud detection on remote sensing images. FLFRF first fuses visible, IR and thermal features. Thereafter, it uses the RF model to classify pixels to cloud, snow/ice and background or thick cloud, thin cloud and background. DLFRF considers visible, IR and thermal features (both spectral and textural) separately and inserts each set of features to RF model. Then, it holds vote matrix of each run of the model. Finally, it fuses the classifiers using the majority vote method. To demonstrate the effectiveness of the proposed algorithms, 10 Terra MODIS and 15 Landsat 8 OLI/TIRS images with different spatial resolutions are used in this paper. Quantitative analyses are based on manually selected ground truth data. Results show that after adding RELBP_CI to input feature set cloud detection accuracy improves. Also, the average cloud kappa values of FLFRF and DLFRF on MODIS images (1 and 0.99) are higher than other machine learning methods, Linear Discriminate Analysis (LDA), Classification And Regression Tree (CART), K Nearest Neighbor (KNN) and Support Vector Machine (SVM) (0.96). The average snow/ice kappa values of FLFRF and DLFRF on MODIS images (1 and 0.85) are higher than other traditional methods. The quantitative values on Landsat 8 images show similar trend. Consequently, while SVM and K-nearest neighbor show overestimation in predicting cloud and snow/ice pixels, our Random Forest (RF) based models can achieve higher cloud, snow/ice kappa values on MODIS and thin cloud, thick cloud and snow/ice kappa values on Landsat 8 images. Our algorithms predict both thin and thick cloud on Landsat 8 images while the existing cloud detection algorithm, Fmask cannot discriminate them. Compared to the state-of-the-art methods, our algorithms have acquired higher average cloud and snow/ice kappa values for different spatial resolutions.

Optimal Symmetric Multimodal Templates and Concatenated Random Forests for Supervised Brain Tumor Segmentation (Simplified) with ANTsR.

PubMed

Tustison, Nicholas J; Shrinidhi, K L; Wintermark, Max; Durst, Christopher R; Kandel, Benjamin M; Gee, James C; Grossman, Murray C; Avants, Brian B

2015-04-01

Segmenting and quantifying gliomas from MRI is an important task for diagnosis, planning intervention, and for tracking tumor changes over time. However, this task is complicated by the lack of prior knowledge concerning tumor location, spatial extent, shape, possible displacement of normal tissue, and intensity signature. To accommodate such complications, we introduce a framework for supervised segmentation based on multiple modality intensity, geometry, and asymmetry feature sets. These features drive a supervised whole-brain and tumor segmentation approach based on random forest-derived probabilities. The asymmetry-related features (based on optimal symmetric multimodal templates) demonstrate excellent discriminative properties within this framework. We also gain performance by generating probability maps from random forest models and using these maps for a refining Markov random field regularized probabilistic segmentation. This strategy allows us to interface the supervised learning capabilities of the random forest model with regularized probabilistic segmentation using the recently developed ANTsR package--a comprehensive statistical and visualization interface between the popular Advanced Normalization Tools (ANTs) and the R statistical project. The reported algorithmic framework was the top-performing entry in the MICCAI 2013 Multimodal Brain Tumor Segmentation challenge. The challenge data were widely varying consisting of both high-grade and low-grade glioma tumor four-modality MRI from five different institutions. Average Dice overlap measures for the final algorithmic assessment were 0.87, 0.78, and 0.74 for "complete", "core", and "enhanced" tumor components, respectively.

Comparison of Random Forest and Parametric Imputation Models for Imputing Missing Data Using MICE: A CALIBER Study

PubMed Central

Shah, Anoop D.; Bartlett, Jonathan W.; Carpenter, James; Nicholas, Owen; Hemingway, Harry

2014-01-01

Multivariate imputation by chained equations (MICE) is commonly used for imputing missing data in epidemiologic research. The “true” imputation model may contain nonlinearities which are not included in default imputation models. Random forest imputation is a machine learning technique which can accommodate nonlinearities and interactions and does not require a particular regression model to be specified. We compared parametric MICE with a random forest-based MICE algorithm in 2 simulation studies. The first study used 1,000 random samples of 2,000 persons drawn from the 10,128 stable angina patients in the CALIBER database (Cardiovascular Disease Research using Linked Bespoke Studies and Electronic Records; 2001–2010) with complete data on all covariates. Variables were artificially made “missing at random,” and the bias and efficiency of parameter estimates obtained using different imputation methods were compared. Both MICE methods produced unbiased estimates of (log) hazard ratios, but random forest was more efficient and produced narrower confidence intervals. The second study used simulated data in which the partially observed variable depended on the fully observed variables in a nonlinear way. Parameter estimates were less biased using random forest MICE, and confidence interval coverage was better. This suggests that random forest imputation may be useful for imputing complex epidemiologic data sets in which some patients have missing data. PMID:24589914

Comparison of random forest and parametric imputation models for imputing missing data using MICE: a CALIBER study.

PubMed

Shah, Anoop D; Bartlett, Jonathan W; Carpenter, James; Nicholas, Owen; Hemingway, Harry

2014-03-15

Multivariate imputation by chained equations (MICE) is commonly used for imputing missing data in epidemiologic research. The "true" imputation model may contain nonlinearities which are not included in default imputation models. Random forest imputation is a machine learning technique which can accommodate nonlinearities and interactions and does not require a particular regression model to be specified. We compared parametric MICE with a random forest-based MICE algorithm in 2 simulation studies. The first study used 1,000 random samples of 2,000 persons drawn from the 10,128 stable angina patients in the CALIBER database (Cardiovascular Disease Research using Linked Bespoke Studies and Electronic Records; 2001-2010) with complete data on all covariates. Variables were artificially made "missing at random," and the bias and efficiency of parameter estimates obtained using different imputation methods were compared. Both MICE methods produced unbiased estimates of (log) hazard ratios, but random forest was more efficient and produced narrower confidence intervals. The second study used simulated data in which the partially observed variable depended on the fully observed variables in a nonlinear way. Parameter estimates were less biased using random forest MICE, and confidence interval coverage was better. This suggests that random forest imputation may be useful for imputing complex epidemiologic data sets in which some patients have missing data.

Random Forest Algorithm for the Classification of Neuroimaging Data in Alzheimer's Disease: A Systematic Review.

PubMed

Sarica, Alessia; Cerasa, Antonio; Quattrone, Aldo

2017-01-01

Objective: Machine learning classification has been the most important computational development in the last years to satisfy the primary need of clinicians for automatic early diagnosis and prognosis. Nowadays, Random Forest (RF) algorithm has been successfully applied for reducing high dimensional and multi-source data in many scientific realms. Our aim was to explore the state of the art of the application of RF on single and multi-modal neuroimaging data for the prediction of Alzheimer's disease. Methods: A systematic review following PRISMA guidelines was conducted on this field of study. In particular, we constructed an advanced query using boolean operators as follows: ("random forest" OR "random forests") AND neuroimaging AND ("alzheimer's disease" OR alzheimer's OR alzheimer) AND (prediction OR classification) . The query was then searched in four well-known scientific databases: Pubmed, Scopus, Google Scholar and Web of Science. Results: Twelve articles-published between the 2007 and 2017-have been included in this systematic review after a quantitative and qualitative selection. The lesson learnt from these works suggest that when RF was applied on multi-modal data for prediction of Alzheimer's disease (AD) conversion from the Mild Cognitive Impairment (MCI), it produces one of the best accuracies to date. Moreover, the RF has important advantages in terms of robustness to overfitting, ability to handle highly non-linear data, stability in the presence of outliers and opportunity for efficient parallel processing mainly when applied on multi-modality neuroimaging data, such as, MRI morphometric, diffusion tensor imaging, and PET images. Conclusions: We discussed the strengths of RF, considering also possible limitations and by encouraging further studies on the comparisons of this algorithm with other commonly used classification approaches, particularly in the early prediction of the progression from MCI to AD.

Learning accurate and interpretable models based on regularized random forests regression

PubMed Central

2014-01-01

Background Many biology related research works combine data from multiple sources in an effort to understand the underlying problems. It is important to find and interpret the most important information from these sources. Thus it will be beneficial to have an effective algorithm that can simultaneously extract decision rules and select critical features for good interpretation while preserving the prediction performance. Methods In this study, we focus on regression problems for biological data where target outcomes are continuous. In general, models constructed from linear regression approaches are relatively easy to interpret. However, many practical biological applications are nonlinear in essence where we can hardly find a direct linear relationship between input and output. Nonlinear regression techniques can reveal nonlinear relationship of data, but are generally hard for human to interpret. We propose a rule based regression algorithm that uses 1-norm regularized random forests. The proposed approach simultaneously extracts a small number of rules from generated random forests and eliminates unimportant features. Results We tested the approach on some biological data sets. The proposed approach is able to construct a significantly smaller set of regression rules using a subset of attributes while achieving prediction performance comparable to that of random forests regression. Conclusion It demonstrates high potential in aiding prediction and interpretation of nonlinear relationships of the subject being studied. PMID:25350120

Intelligent Fault Diagnosis of HVCB with Feature Space Optimization-Based Random Forest

PubMed Central

Ma, Suliang; Wu, Jianwen; Wang, Yuhao; Jia, Bowen; Jiang, Yuan

2018-01-01

Mechanical faults of high-voltage circuit breakers (HVCBs) always happen over long-term operation, so extracting the fault features and identifying the fault type have become a key issue for ensuring the security and reliability of power supply. Based on wavelet packet decomposition technology and random forest algorithm, an effective identification system was developed in this paper. First, compared with the incomplete description of Shannon entropy, the wavelet packet time-frequency energy rate (WTFER) was adopted as the input vector for the classifier model in the feature selection procedure. Then, a random forest classifier was used to diagnose the HVCB fault, assess the importance of the feature variable and optimize the feature space. Finally, the approach was verified based on actual HVCB vibration signals by considering six typical fault classes. The comparative experiment results show that the classification accuracy of the proposed method with the origin feature space reached 93.33% and reached up to 95.56% with optimized input feature vector of classifier. This indicates that feature optimization procedure is successful, and the proposed diagnosis algorithm has higher efficiency and robustness than traditional methods. PMID:29659548

RAQ–A Random Forest Approach for Predicting Air Quality in Urban Sensing Systems

PubMed Central

Yu, Ruiyun; Yang, Yu; Yang, Leyou; Han, Guangjie; Move, Oguti Ann

2016-01-01

Air quality information such as the concentration of PM2.5 is of great significance for human health and city management. It affects the way of traveling, urban planning, government policies and so on. However, in major cities there is typically only a limited number of air quality monitoring stations. In the meantime, air quality varies in the urban areas and there can be large differences, even between closely neighboring regions. In this paper, a random forest approach for predicting air quality (RAQ) is proposed for urban sensing systems. The data generated by urban sensing includes meteorology data, road information, real-time traffic status and point of interest (POI) distribution. The random forest algorithm is exploited for data training and prediction. The performance of RAQ is evaluated with real city data. Compared with three other algorithms, this approach achieves better prediction precision. Exciting results are observed from the experiments that the air quality can be inferred with amazingly high accuracy from the data which are obtained from urban sensing. PMID:26761008

GPURFSCREEN: a GPU based virtual screening tool using random forest classifier.

PubMed

Jayaraj, P B; Ajay, Mathias K; Nufail, M; Gopakumar, G; Jaleel, U C A

2016-01-01

In-silico methods are an integral part of modern drug discovery paradigm. Virtual screening, an in-silico method, is used to refine data models and reduce the chemical space on which wet lab experiments need to be performed. Virtual screening of a ligand data model requires large scale computations, making it a highly time consuming task. This process can be speeded up by implementing parallelized algorithms on a Graphical Processing Unit (GPU). Random Forest is a robust classification algorithm that can be employed in the virtual screening. A ligand based virtual screening tool (GPURFSCREEN) that uses random forests on GPU systems has been proposed and evaluated in this paper. This tool produces optimized results at a lower execution time for large bioassay data sets. The quality of results produced by our tool on GPU is same as that on a regular serial environment. Considering the magnitude of data to be screened, the parallelized virtual screening has a significantly lower running time at high throughput. The proposed parallel tool outperforms its serial counterpart by successfully screening billions of molecules in training and prediction phases.

Exploring prediction uncertainty of spatial data in geostatistical and machine learning Approaches

NASA Astrophysics Data System (ADS)

Klump, J. F.; Fouedjio, F.

2017-12-01

Geostatistical methods such as kriging with external drift as well as machine learning techniques such as quantile regression forest have been intensively used for modelling spatial data. In addition to providing predictions for target variables, both approaches are able to deliver a quantification of the uncertainty associated with the prediction at a target location. Geostatistical approaches are, by essence, adequate for providing such prediction uncertainties and their behaviour is well understood. However, they often require significant data pre-processing and rely on assumptions that are rarely met in practice. Machine learning algorithms such as random forest regression, on the other hand, require less data pre-processing and are non-parametric. This makes the application of machine learning algorithms to geostatistical problems an attractive proposition. The objective of this study is to compare kriging with external drift and quantile regression forest with respect to their ability to deliver reliable prediction uncertainties of spatial data. In our comparison we use both simulated and real world datasets. Apart from classical performance indicators, comparisons make use of accuracy plots, probability interval width plots, and the visual examinations of the uncertainty maps provided by the two approaches. By comparing random forest regression to kriging we found that both methods produced comparable maps of estimated values for our variables of interest. However, the measure of uncertainty provided by random forest seems to be quite different to the measure of uncertainty provided by kriging. In particular, the lack of spatial context can give misleading results in areas without ground truth data. These preliminary results raise questions about assessing the risks associated with decisions based on the predictions from geostatistical and machine learning algorithms in a spatial context, e.g. mineral exploration.

Mapping forested wetlands in the Great Zhan River Basin through integrating optical, radar, and topographical data classification techniques.

PubMed

Na, X D; Zang, S Y; Wu, C S; Li, W L

2015-11-01

Knowledge of the spatial extent of forested wetlands is essential to many studies including wetland functioning assessment, greenhouse gas flux estimation, and wildlife suitable habitat identification. For discriminating forested wetlands from their adjacent land cover types, researchers have resorted to image analysis techniques applied to numerous remotely sensed data. While with some success, there is still no consensus on the optimal approaches for mapping forested wetlands. To address this problem, we examined two machine learning approaches, random forest (RF) and K-nearest neighbor (KNN) algorithms, and applied these two approaches to the framework of pixel-based and object-based classifications. The RF and KNN algorithms were constructed using predictors derived from Landsat 8 imagery, Radarsat-2 advanced synthetic aperture radar (SAR), and topographical indices. The results show that the objected-based classifications performed better than per-pixel classifications using the same algorithm (RF) in terms of overall accuracy and the difference of their kappa coefficients are statistically significant (p<0.01). There were noticeably omissions for forested and herbaceous wetlands based on the per-pixel classifications using the RF algorithm. As for the object-based image analysis, there were also statistically significant differences (p<0.01) of Kappa coefficient between results performed based on RF and KNN algorithms. The object-based classification using RF provided a more visually adequate distribution of interested land cover types, while the object classifications based on the KNN algorithm showed noticeably commissions for forested wetlands and omissions for agriculture land. This research proves that the object-based classification with RF using optical, radar, and topographical data improved the mapping accuracy of land covers and provided a feasible approach to discriminate the forested wetlands from the other land cover types in forestry area.

Modification of the random forest algorithm to avoid statistical dependence problems when classifying remote sensing imagery

NASA Astrophysics Data System (ADS)

Cánovas-García, Fulgencio; Alonso-Sarría, Francisco; Gomariz-Castillo, Francisco; Oñate-Valdivieso, Fernando

2017-06-01

Random forest is a classification technique widely used in remote sensing. One of its advantages is that it produces an estimation of classification accuracy based on the so called out-of-bag cross-validation method. It is usually assumed that such estimation is not biased and may be used instead of validation based on an external data-set or a cross-validation external to the algorithm. In this paper we show that this is not necessarily the case when classifying remote sensing imagery using training areas with several pixels or objects. According to our results, out-of-bag cross-validation clearly overestimates accuracy, both overall and per class. The reason is that, in a training patch, pixels or objects are not independent (from a statistical point of view) of each other; however, they are split by bootstrapping into in-bag and out-of-bag as if they were really independent. We believe that putting whole patch, rather than pixels/objects, in one or the other set would produce a less biased out-of-bag cross-validation. To deal with the problem, we propose a modification of the random forest algorithm to split training patches instead of the pixels (or objects) that compose them. This modified algorithm does not overestimate accuracy and has no lower predictive capability than the original. When its results are validated with an external data-set, the accuracy is not different from that obtained with the original algorithm. We analysed three remote sensing images with different classification approaches (pixel and object based); in the three cases reported, the modification we propose produces a less biased accuracy estimation.

RS-Forest: A Rapid Density Estimator for Streaming Anomaly Detection.

PubMed

Wu, Ke; Zhang, Kun; Fan, Wei; Edwards, Andrea; Yu, Philip S

Anomaly detection in streaming data is of high interest in numerous application domains. In this paper, we propose a novel one-class semi-supervised algorithm to detect anomalies in streaming data. Underlying the algorithm is a fast and accurate density estimator implemented by multiple fully randomized space trees (RS-Trees), named RS-Forest. The piecewise constant density estimate of each RS-tree is defined on the tree node into which an instance falls. Each incoming instance in a data stream is scored by the density estimates averaged over all trees in the forest. Two strategies, statistical attribute range estimation of high probability guarantee and dual node profiles for rapid model update, are seamlessly integrated into RS-Forest to systematically address the ever-evolving nature of data streams. We derive the theoretical upper bound for the proposed algorithm and analyze its asymptotic properties via bias-variance decomposition. Empirical comparisons to the state-of-the-art methods on multiple benchmark datasets demonstrate that the proposed method features high detection rate, fast response, and insensitivity to most of the parameter settings. Algorithm implementations and datasets are available upon request.

RS-Forest: A Rapid Density Estimator for Streaming Anomaly Detection

PubMed Central

Wu, Ke; Zhang, Kun; Fan, Wei; Edwards, Andrea; Yu, Philip S.

2015-01-01

Anomaly detection in streaming data is of high interest in numerous application domains. In this paper, we propose a novel one-class semi-supervised algorithm to detect anomalies in streaming data. Underlying the algorithm is a fast and accurate density estimator implemented by multiple fully randomized space trees (RS-Trees), named RS-Forest. The piecewise constant density estimate of each RS-tree is defined on the tree node into which an instance falls. Each incoming instance in a data stream is scored by the density estimates averaged over all trees in the forest. Two strategies, statistical attribute range estimation of high probability guarantee and dual node profiles for rapid model update, are seamlessly integrated into RS-Forest to systematically address the ever-evolving nature of data streams. We derive the theoretical upper bound for the proposed algorithm and analyze its asymptotic properties via bias-variance decomposition. Empirical comparisons to the state-of-the-art methods on multiple benchmark datasets demonstrate that the proposed method features high detection rate, fast response, and insensitivity to most of the parameter settings. Algorithm implementations and datasets are available upon request. PMID:25685112

Mortality risk score prediction in an elderly population using machine learning.

PubMed

Rose, Sherri

2013-03-01

Standard practice for prediction often relies on parametric regression methods. Interesting new methods from the machine learning literature have been introduced in epidemiologic studies, such as random forest and neural networks. However, a priori, an investigator will not know which algorithm to select and may wish to try several. Here I apply the super learner, an ensembling machine learning approach that combines multiple algorithms into a single algorithm and returns a prediction function with the best cross-validated mean squared error. Super learning is a generalization of stacking methods. I used super learning in the Study of Physical Performance and Age-Related Changes in Sonomans (SPPARCS) to predict death among 2,066 residents of Sonoma, California, aged 54 years or more during the period 1993-1999. The super learner for predicting death (risk score) improved upon all single algorithms in the collection of algorithms, although its performance was similar to that of several algorithms. Super learner outperformed the worst algorithm (neural networks) by 44% with respect to estimated cross-validated mean squared error and had an R2 value of 0.201. The improvement of super learner over random forest with respect to R2 was approximately 2-fold. Alternatives for risk score prediction include the super learner, which can provide improved performance.

Predicting temperate forest stand types using only structural profiles from discrete return airborne lidar

NASA Astrophysics Data System (ADS)

Fedrigo, Melissa; Newnham, Glenn J.; Coops, Nicholas C.; Culvenor, Darius S.; Bolton, Douglas K.; Nitschke, Craig R.

2018-02-01

Light detection and ranging (lidar) data have been increasingly used for forest classification due to its ability to penetrate the forest canopy and provide detail about the structure of the lower strata. In this study we demonstrate forest classification approaches using airborne lidar data as inputs to random forest and linear unmixing classification algorithms. Our results demonstrated that both random forest and linear unmixing models identified a distribution of rainforest and eucalypt stands that was comparable to existing ecological vegetation class (EVC) maps based primarily on manual interpretation of high resolution aerial imagery. Rainforest stands were also identified in the region that have not previously been identified in the EVC maps. The transition between stand types was better characterised by the random forest modelling approach. In contrast, the linear unmixing model placed greater emphasis on field plots selected as endmembers which may not have captured the variability in stand structure within a single stand type. The random forest model had the highest overall accuracy (84%) and Cohen's kappa coefficient (0.62). However, the classification accuracy was only marginally better than linear unmixing. The random forest model was applied to a region in the Central Highlands of south-eastern Australia to produce maps of stand type probability, including areas of transition (the 'ecotone') between rainforest and eucalypt forest. The resulting map provided a detailed delineation of forest classes, which specifically recognised the coalescing of stand types at the landscape scale. This represents a key step towards mapping the structural and spatial complexity of these ecosystems, which is important for both their management and conservation.

Effective search for stable segregation configurations at grain boundaries with data-mining techniques

NASA Astrophysics Data System (ADS)

Kiyohara, Shin; Mizoguchi, Teruyasu

2018-03-01

Grain boundary segregation of dopants plays a crucial role in materials properties. To investigate the dopant segregation behavior at the grain boundary, an enormous number of combinations have to be considered in the segregation of multiple dopants at the complex grain boundary structures. Here, two data mining techniques, the random-forests regression and the genetic algorithm, were applied to determine stable segregation sites at grain boundaries efficiently. Using the random-forests method, a predictive model was constructed from 2% of the segregation configurations and it has been shown that this model could determine the stable segregation configurations. Furthermore, the genetic algorithm also successfully determined the most stable segregation configuration with great efficiency. We demonstrate that these approaches are quite effective to investigate the dopant segregation behaviors at grain boundaries.

Spatio-temporal Change Patterns of Tropical Forests from 2000 to 2014 Using MOD09A1 Dataset

NASA Astrophysics Data System (ADS)

Qin, Y.; Xiao, X.; Dong, J.

2016-12-01

Large-scale deforestation and forest degradation in the tropical region have resulted in extensive carbon emissions and biodiversity loss. However, restricted by the availability of good-quality observations, large uncertainty exists in mapping the spatial distribution of forests and their spatio-temporal changes. In this study, we proposed a pixel- and phenology-based algorithm to identify and map annual tropical forests from 2000 to 2014, using the 8-day, 500-m MOD09A1 (v005) product, under the support of Google cloud computing (Google Earth Engine). A temporal filter was applied to reduce the random noises and to identify the spatio-temporal changes of forests. We then built up a confusion matrix and assessed the accuracy of the annual forest maps based on the ground reference interpreted from high spatial resolution images in Google Earth. The resultant forest maps showed the consistent forest/non-forest, forest loss, and forest gain in the pan-tropical zone during 2000 - 2014. The proposed algorithm showed the potential for tropical forest mapping and the resultant forest maps are important for the estimation of carbon emission and biodiversity loss.

Patterns among the ashes: Exploring the relationship between landscape pattern and the emerald ash borer

Treesearch

Susan J. Crocker; Dacia M. Meneguzzo; Greg C. Liknes

2010-01-01

Landscape metrics, including host abundance and population density, were calculated using forest inventory and land cover data to assess the relationship between landscape pattern and the presence or absence of the emerald ash borer (EAB) (Agrilus planipennis Fairmaire). The Random Forests classification algorithm in the R statistical environment was...

Automatic segmentation of psoriasis lesions

NASA Astrophysics Data System (ADS)

Ning, Yang; Shi, Chenbo; Wang, Li; Shu, Chang

2014-10-01

The automatic segmentation of psoriatic lesions is widely researched these years. It is an important step in Computer-aid methods of calculating PASI for estimation of lesions. Currently those algorithms can only handle single erythema or only deal with scaling segmentation. In practice, scaling and erythema are often mixed together. In order to get the segmentation of lesions area - this paper proposes an algorithm based on Random forests with color and texture features. The algorithm has three steps. The first step, the polarized light is applied based on the skin's Tyndall-effect in the imaging to eliminate the reflection and Lab color space are used for fitting the human perception. The second step, sliding window and its sub windows are used to get textural feature and color feature. In this step, a feature of image roughness has been defined, so that scaling can be easily separated from normal skin. In the end, Random forests will be used to ensure the generalization ability of the algorithm. This algorithm can give reliable segmentation results even the image has different lighting conditions, skin types. In the data set offered by Union Hospital, more than 90% images can be segmented accurately.

Disaggregating census data for population mapping using random forests with remotely-sensed and ancillary data.

PubMed

Stevens, Forrest R; Gaughan, Andrea E; Linard, Catherine; Tatem, Andrew J

2015-01-01

High resolution, contemporary data on human population distributions are vital for measuring impacts of population growth, monitoring human-environment interactions and for planning and policy development. Many methods are used to disaggregate census data and predict population densities for finer scale, gridded population data sets. We present a new semi-automated dasymetric modeling approach that incorporates detailed census and ancillary data in a flexible, "Random Forest" estimation technique. We outline the combination of widely available, remotely-sensed and geospatial data that contribute to the modeled dasymetric weights and then use the Random Forest model to generate a gridded prediction of population density at ~100 m spatial resolution. This prediction layer is then used as the weighting surface to perform dasymetric redistribution of the census counts at a country level. As a case study we compare the new algorithm and its products for three countries (Vietnam, Cambodia, and Kenya) with other common gridded population data production methodologies. We discuss the advantages of the new method and increases over the accuracy and flexibility of those previous approaches. Finally, we outline how this algorithm will be extended to provide freely-available gridded population data sets for Africa, Asia and Latin America.

Analysis of landslide hazard area in Ludian earthquake based on Random Forests

NASA Astrophysics Data System (ADS)

Xie, J.-C.; Liu, R.; Li, H.-W.; Lai, Z.-L.

2015-04-01

With the development of machine learning theory, more and more algorithms are evaluated for seismic landslides. After the Ludian earthquake, the research team combine with the special geological structure in Ludian area and the seismic filed exploration results, selecting SLOPE(PODU); River distance(HL); Fault distance(DC); Seismic Intensity(LD) and Digital Elevation Model(DEM), the normalized difference vegetation index(NDVI) which based on remote sensing images as evaluation factors. But the relationships among these factors are fuzzy, there also exists heavy noise and high-dimensional, we introduce the random forest algorithm to tolerate these difficulties and get the evaluation result of Ludian landslide areas, in order to verify the accuracy of the result, using the ROC graphs for the result evaluation standard, AUC covers an area of 0.918, meanwhile, the random forest's generalization error rate decreases with the increase of the classification tree to the ideal 0.08 by using Out Of Bag(OOB) Estimation. Studying the final landslides inversion results, paper comes to a statistical conclusion that near 80% of the whole landslides and dilapidations are in areas with high susceptibility and moderate susceptibility, showing the forecast results are reasonable and adopted.

Hierarchical Bayesian spatial models for predicting multiple forest variables using waveform LiDAR, hyperspectral imagery, and large inventory datasets

USGS Publications Warehouse

Finley, Andrew O.; Banerjee, Sudipto; Cook, Bruce D.; Bradford, John B.

2013-01-01

In this paper we detail a multivariate spatial regression model that couples LiDAR, hyperspectral and forest inventory data to predict forest outcome variables at a high spatial resolution. The proposed model is used to analyze forest inventory data collected on the US Forest Service Penobscot Experimental Forest (PEF), ME, USA. In addition to helping meet the regression model's assumptions, results from the PEF analysis suggest that the addition of multivariate spatial random effects improves model fit and predictive ability, compared with two commonly applied modeling approaches. This improvement results from explicitly modeling the covariation among forest outcome variables and spatial dependence among observations through the random effects. Direct application of such multivariate models to even moderately large datasets is often computationally infeasible because of cubic order matrix algorithms involved in estimation. We apply a spatial dimension reduction technique to help overcome this computational hurdle without sacrificing richness in modeling.

Comparison of the Predictive Performance and Interpretability of Random Forest and Linear Models on Benchmark Data Sets.

PubMed

Marchese Robinson, Richard L; Palczewska, Anna; Palczewski, Jan; Kidley, Nathan

2017-08-28

The ability to interpret the predictions made by quantitative structure-activity relationships (QSARs) offers a number of advantages. While QSARs built using nonlinear modeling approaches, such as the popular Random Forest algorithm, might sometimes be more predictive than those built using linear modeling approaches, their predictions have been perceived as difficult to interpret. However, a growing number of approaches have been proposed for interpreting nonlinear QSAR models in general and Random Forest in particular. In the current work, we compare the performance of Random Forest to those of two widely used linear modeling approaches: linear Support Vector Machines (SVMs) (or Support Vector Regression (SVR)) and partial least-squares (PLS). We compare their performance in terms of their predictivity as well as the chemical interpretability of the predictions using novel scoring schemes for assessing heat map images of substructural contributions. We critically assess different approaches for interpreting Random Forest models as well as for obtaining predictions from the forest. We assess the models on a large number of widely employed public-domain benchmark data sets corresponding to regression and binary classification problems of relevance to hit identification and toxicology. We conclude that Random Forest typically yields comparable or possibly better predictive performance than the linear modeling approaches and that its predictions may also be interpreted in a chemically and biologically meaningful way. In contrast to earlier work looking at interpretation of nonlinear QSAR models, we directly compare two methodologically distinct approaches for interpreting Random Forest models. The approaches for interpreting Random Forest assessed in our article were implemented using open-source programs that we have made available to the community. These programs are the rfFC package ( https://r-forge.r-project.org/R/?group_id=1725 ) for the R statistical programming language and the Python program HeatMapWrapper [ https://doi.org/10.5281/zenodo.495163 ] for heat map generation.

Ecological impacts and management strategies for western larch in the face of climate-change

Treesearch

Gerald E. Rehfeldt; Barry C. Jaquish

2010-01-01

Approximately 185,000 forest inventory and ecological plots from both USA and Canada were used to predict the contemporary distribution of western larch (Larix occidentalis Nutt.) from climate variables. The random forests algorithm, using an 8-variable model, produced an overall error rate of about 2.9 %, nearly all of which consisted of predicting presence at...

Prediction of Baseflow Index of Catchments using Machine Learning Algorithms

NASA Astrophysics Data System (ADS)

Yadav, B.; Hatfield, K.

2017-12-01

We present the results of eight machine learning techniques for predicting the baseflow index (BFI) of ungauged basins using a surrogate of catchment scale climate and physiographic data. The tested algorithms include ordinary least squares, ridge regression, least absolute shrinkage and selection operator (lasso), elasticnet, support vector machine, gradient boosted regression trees, random forests, and extremely randomized trees. Our work seeks to identify the dominant controls of BFI that can be readily obtained from ancillary geospatial databases and remote sensing measurements, such that the developed techniques can be extended to ungauged catchments. More than 800 gauged catchments spanning the continental United States were selected to develop the general methodology. The BFI calculation was based on the baseflow separated from daily streamflow hydrograph using HYSEP filter. The surrogate catchment attributes were compiled from multiple sources including digital elevation model, soil, landuse, climate data, other publicly available ancillary and geospatial data. 80% catchments were used to train the ML algorithms, and the remaining 20% of the catchments were used as an independent test set to measure the generalization performance of fitted models. A k-fold cross-validation using exhaustive grid search was used to fit the hyperparameters of each model. Initial model development was based on 19 independent variables, but after variable selection and feature ranking, we generated revised sparse models of BFI prediction that are based on only six catchment attributes. These key predictive variables selected after the careful evaluation of bias-variance tradeoff include average catchment elevation, slope, fraction of sand, permeability, temperature, and precipitation. The most promising algorithms exceeding an accuracy score (r-square) of 0.7 on test data include support vector machine, gradient boosted regression trees, random forests, and extremely randomized trees. Considering both the accuracy and the computational complexity of these algorithms, we identify the extremely randomized trees as the best performing algorithm for BFI prediction in ungauged basins.

Fire detection system using random forest classification for image sequences of complex background

NASA Astrophysics Data System (ADS)

Kim, Onecue; Kang, Dong-Joong

2013-06-01

We present a fire alarm system based on image processing that detects fire accidents in various environments. To reduce false alarms that frequently appeared in earlier systems, we combined image features including color, motion, and blinking information. We specifically define the color conditions of fires in hue, saturation and value, and RGB color space. Fire features are represented as intensity variation, color mean and variance, motion, and image differences. Moreover, blinking fire features are modeled by using crossing patches. We propose an algorithm that classifies patches into fire or nonfire areas by using random forest supervised learning. We design an embedded surveillance device made with acrylonitrile butadiene styrene housing for stable fire detection in outdoor environments. The experimental results show that our algorithm works robustly in complex environments and is able to detect fires in real time.

Gray level co-occurrence and random forest algorithm-based gender determination with maxillary tooth plaster images.

PubMed

Akkoç, Betül; Arslan, Ahmet; Kök, Hatice

2016-06-01

Gender is one of the intrinsic properties of identity, with performance enhancement reducing the cluster when a search is performed. Teeth have durable and resistant structure, and as such are important sources of identification in disasters (accident, fire, etc.). In this study, gender determination is accomplished by maxillary tooth plaster models of 40 people (20 males and 20 females). The images of tooth plaster models are taken with a lighting mechanism set-up. A gray level co-occurrence matrix of the image with segmentation is formed and classified via a Random Forest (RF) algorithm by extracting pertinent features of the matrix. Automatic gender determination has a 90% success rate, with an applicable system to determine gender from maxillary tooth plaster images. Copyright © 2016 Elsevier Ltd. All rights reserved.

Detecting targets hidden in random forests

NASA Astrophysics Data System (ADS)

Kouritzin, Michael A.; Luo, Dandan; Newton, Fraser; Wu, Biao

2009-05-01

Military tanks, cargo or troop carriers, missile carriers or rocket launchers often hide themselves from detection in the forests. This plagues the detection problem of locating these hidden targets. An electro-optic camera mounted on a surveillance aircraft or unmanned aerial vehicle is used to capture the images of the forests with possible hidden targets, e.g., rocket launchers. We consider random forests of longitudinal and latitudinal correlations. Specifically, foliage coverage is encoded with a binary representation (i.e., foliage or no foliage), and is correlated in adjacent regions. We address the detection problem of camouflaged targets hidden in random forests by building memory into the observations. In particular, we propose an efficient algorithm to generate random forests, ground, and camouflage of hidden targets with two dimensional correlations. The observations are a sequence of snapshots consisting of foliage-obscured ground or target. Theoretically, detection is possible because there are subtle differences in the correlations of the ground and camouflage of the rocket launcher. However, these differences are well beyond human perception. To detect the presence of hidden targets automatically, we develop a Markov representation for these sequences and modify the classical filtering equations to allow the Markov chain observation. Particle filters are used to estimate the position of the targets in combination with a novel random weighting technique. Furthermore, we give positive proof-of-concept simulations.

Applications of random forest feature selection for fine-scale genetic population assignment.

PubMed

Sylvester, Emma V A; Bentzen, Paul; Bradbury, Ian R; Clément, Marie; Pearce, Jon; Horne, John; Beiko, Robert G

2018-02-01

Genetic population assignment used to inform wildlife management and conservation efforts requires panels of highly informative genetic markers and sensitive assignment tests. We explored the utility of machine-learning algorithms (random forest, regularized random forest and guided regularized random forest) compared with F ST ranking for selection of single nucleotide polymorphisms (SNP) for fine-scale population assignment. We applied these methods to an unpublished SNP data set for Atlantic salmon ( Salmo salar ) and a published SNP data set for Alaskan Chinook salmon ( Oncorhynchus tshawytscha ). In each species, we identified the minimum panel size required to obtain a self-assignment accuracy of at least 90% using each method to create panels of 50-700 markers Panels of SNPs identified using random forest-based methods performed up to 7.8 and 11.2 percentage points better than F ST -selected panels of similar size for the Atlantic salmon and Chinook salmon data, respectively. Self-assignment accuracy ≥90% was obtained with panels of 670 and 384 SNPs for each data set, respectively, a level of accuracy never reached for these species using F ST -selected panels. Our results demonstrate a role for machine-learning approaches in marker selection across large genomic data sets to improve assignment for management and conservation of exploited populations.

A Hybrid Color Space for Skin Detection Using Genetic Algorithm Heuristic Search and Principal Component Analysis Technique

PubMed Central

2015-01-01

Color is one of the most prominent features of an image and used in many skin and face detection applications. Color space transformation is widely used by researchers to improve face and skin detection performance. Despite the substantial research efforts in this area, choosing a proper color space in terms of skin and face classification performance which can address issues like illumination variations, various camera characteristics and diversity in skin color tones has remained an open issue. This research proposes a new three-dimensional hybrid color space termed SKN by employing the Genetic Algorithm heuristic and Principal Component Analysis to find the optimal representation of human skin color in over seventeen existing color spaces. Genetic Algorithm heuristic is used to find the optimal color component combination setup in terms of skin detection accuracy while the Principal Component Analysis projects the optimal Genetic Algorithm solution to a less complex dimension. Pixel wise skin detection was used to evaluate the performance of the proposed color space. We have employed four classifiers including Random Forest, Naïve Bayes, Support Vector Machine and Multilayer Perceptron in order to generate the human skin color predictive model. The proposed color space was compared to some existing color spaces and shows superior results in terms of pixel-wise skin detection accuracy. Experimental results show that by using Random Forest classifier, the proposed SKN color space obtained an average F-score and True Positive Rate of 0.953 and False Positive Rate of 0.0482 which outperformed the existing color spaces in terms of pixel wise skin detection accuracy. The results also indicate that among the classifiers used in this study, Random Forest is the most suitable classifier for pixel wise skin detection applications. PMID:26267377

Validating predictions from climate envelope models

USGS Publications Warehouse

Watling, J.; Bucklin, D.; Speroterra, C.; Brandt, L.; Cabal, C.; Romañach, Stephanie S.; Mazzotti, Frank J.

2013-01-01

Climate envelope models are a potentially important conservation tool, but their ability to accurately forecast species’ distributional shifts using independent survey data has not been fully evaluated. We created climate envelope models for 12 species of North American breeding birds previously shown to have experienced poleward range shifts. For each species, we evaluated three different approaches to climate envelope modeling that differed in the way they treated climate-induced range expansion and contraction, using random forests and maximum entropy modeling algorithms. All models were calibrated using occurrence data from 1967–1971 (t1) and evaluated using occurrence data from 1998–2002 (t2). Model sensitivity (the ability to correctly classify species presences) was greater using the maximum entropy algorithm than the random forest algorithm. Although sensitivity did not differ significantly among approaches, for many species, sensitivity was maximized using a hybrid approach that assumed range expansion, but not contraction, in t2. Species for which the hybrid approach resulted in the greatest improvement in sensitivity have been reported from more land cover types than species for which there was little difference in sensitivity between hybrid and dynamic approaches, suggesting that habitat generalists may be buffered somewhat against climate-induced range contractions. Specificity (the ability to correctly classify species absences) was maximized using the random forest algorithm and was lowest using the hybrid approach. Overall, our results suggest cautious optimism for the use of climate envelope models to forecast range shifts, but also underscore the importance of considering non-climate drivers of species range limits. The use of alternative climate envelope models that make different assumptions about range expansion and contraction is a new and potentially useful way to help inform our understanding of climate change effects on species.

How random is the random forest? Random forest algorithm on the service of structural imaging biomarkers for Alzheimer's disease: from Alzheimer's disease neuroimaging initiative (ADNI) database.

PubMed

Dimitriadis, Stavros I; Liparas, Dimitris

2018-06-01

Neuroinformatics is a fascinating research field that applies computational models and analytical tools to high dimensional experimental neuroscience data for a better understanding of how the brain functions or dysfunctions in brain diseases. Neuroinformaticians work in the intersection of neuroscience and informatics supporting the integration of various sub-disciplines (behavioural neuroscience, genetics, cognitive psychology, etc.) working on brain research. Neuroinformaticians are the pathway of information exchange between informaticians and clinicians for a better understanding of the outcome of computational models and the clinical interpretation of the analysis. Machine learning is one of the most significant computational developments in the last decade giving tools to neuroinformaticians and finally to radiologists and clinicians for an automatic and early diagnosis-prognosis of a brain disease. Random forest (RF) algorithm has been successfully applied to high-dimensional neuroimaging data for feature reduction and also has been applied to classify the clinical label of a subject using single or multi-modal neuroimaging datasets. Our aim was to review the studies where RF was applied to correctly predict the Alzheimer's disease (AD), the conversion from mild cognitive impairment (MCI) and its robustness to overfitting, outliers and handling of non-linear data. Finally, we described our RF-based model that gave us the 1 st position in an international challenge for automated prediction of MCI from MRI data.

Improvement of Forest Height Retrieval By Integration of Dual-Baseline PolInSAR Data And External DEM Data

NASA Astrophysics Data System (ADS)

Xie, Q.; Wang, C.; Zhu, J.; Fu, H.; Wang, C.

2015-06-01

In recent years, a lot of studies have shown that polarimetric synthetic aperture radar interferometry (PolInSAR) is a powerful technique for forest height mapping and monitoring. However, few researches address the problem of terrain slope effect, which will be one of the major limitations for forest height inversion in mountain forest area. In this paper, we present a novel forest height retrieval algorithm by integration of dual-baseline PolInSAR data and external DEM data. For the first time, we successfully expand the S-RVoG (Sloped-Random Volume over Ground) model for forest parameters inversion into the case of dual-baseline PolInSAR configuration. In this case, the proposed method not only corrects terrain slope variation effect efficiently, but also involves more observations to improve the accuracy of parameters inversion. In order to demonstrate the performance of the inversion algorithm, a set of quad-pol images acquired at the P-band in interferometric repeat-pass mode by the German Aerospace Center (DLR) with the Experimental SAR (E-SAR) system, in the frame of the BioSAR2008 campaign, has been used for the retrieval of forest height over Krycklan boreal forest in northern Sweden. At the same time, a high accuracy external DEM in the experimental area has been collected for computing terrain slope information, which subsequently is used as an inputting parameter in the S-RVoG model. Finally, in-situ ground truth heights in stand-level have been collected to validate the inversion result. The preliminary results show that the proposed inversion algorithm promises to provide much more accurate estimation of forest height than traditional dualbaseline inversion algorithms.

Canopy Height and Vertical Structure from Multibaseline Polarimetric InSAR: First Results of the 2016 NASA/ESA AfriSAR Campaign

NASA Astrophysics Data System (ADS)

Lavalle, M.; Hensley, S.; Lou, Y.; Saatchi, S. S.; Pinto, N.; Simard, M.; Fatoyinbo, T. E.; Duncanson, L.; Dubayah, R.; Hofton, M. A.; Blair, J. B.; Armston, J.

2016-12-01

In this paper we explore the derivation of canopy height and vertical structure from polarimetric-interferometric SAR (PolInSAR) data collected during the 2016 AfriSAR campaign in Gabon. AfriSAR is a joint effort between NASA and ESA to acquire multi-baseline L- and P-band radar data, lidar data and field data over tropical forests and savannah sites to support calibration, validation and algorithm development in preparation for the NISAR, GEDI and BIOMASS missions. Here we focus on the L-band UAVSAR dataset acquired over the Lope National Park in Central Gabon to demonstrate mapping of canopy height and vertical structure using PolInSAR and tomographic techniques. The Lope site features a natural gradient of forest biomass from the forest-savanna boundary (< 100 Mg/ha) to dense undisturbed humid tropical forests (> 400 Mg/ha). Our dataset includes 9 long-baseline, full-polarimetric UAVSAR acquisitions along with field and lidar data from the Laser Vegetation Ice Sensor (LVIS). We first present a brief theoretical background of the PolInSAR and tomographic techniques. We then show the results of our PolInSAR algorithms to create maps of canopy height generated via inversion of the random-volume-over-ground (RVOG) and random-motion-over-ground (RVoG) models. In our approach multiple interferometric baselines are merged incoherently to maximize the interferometric sensitivity over a broad range of tree heights. Finally we show how traditional tomographic algorithms are used for the retrieval of the full vertical canopy profile. We compare our results from the different PolInSAR/tomographic algorithms to validation data derived from lidar and field data.

Identifying Active Travel Behaviors in Challenging Environments Using GPS, Accelerometers, and Machine Learning Algorithms.

PubMed

Ellis, Katherine; Godbole, Suneeta; Marshall, Simon; Lanckriet, Gert; Staudenmayer, John; Kerr, Jacqueline

2014-01-01

Active travel is an important area in physical activity research, but objective measurement of active travel is still difficult. Automated methods to measure travel behaviors will improve research in this area. In this paper, we present a supervised machine learning method for transportation mode prediction from global positioning system (GPS) and accelerometer data. We collected a dataset of about 150 h of GPS and accelerometer data from two research assistants following a protocol of prescribed trips consisting of five activities: bicycling, riding in a vehicle, walking, sitting, and standing. We extracted 49 features from 1-min windows of this data. We compared the performance of several machine learning algorithms and chose a random forest algorithm to classify the transportation mode. We used a moving average output filter to smooth the output predictions over time. The random forest algorithm achieved 89.8% cross-validated accuracy on this dataset. Adding the moving average filter to smooth output predictions increased the cross-validated accuracy to 91.9%. Machine learning methods are a viable approach for automating measurement of active travel, particularly for measuring travel activities that traditional accelerometer data processing methods misclassify, such as bicycling and vehicle travel.

Comparative genetic responses to climate for the varieties of Pinus ponderosa and Pseudotsuga menziesii: realized climate niches

Treesearch

Gerald E. Rehfeldt; Barry C. Jaquish; Javier Lopez-Upton; Cuauhtemoc Saenz-Romero; J. Bradley St Clair; Laura P. Leites; Dennis G. Joyce

2014-01-01

The Random Forests classification algorithm was used to predict the occurrence of the realized climate niche for two sub-specific varieties of Pinus ponderosa and three varieties of Pseudotsuga menziesii from presence-absence data in forest inventory ground plots. Analyses were based on ca. 271,000 observations for P. ponderosa and ca. 426,000 observations for P....

Random forest feature selection approach for image segmentation

NASA Astrophysics Data System (ADS)

Lefkovits, László; Lefkovits, Szidónia; Emerich, Simina; Vaida, Mircea Florin

2017-03-01

In the field of image segmentation, discriminative models have shown promising performance. Generally, every such model begins with the extraction of numerous features from annotated images. Most authors create their discriminative model by using many features without using any selection criteria. A more reliable model can be built by using a framework that selects the important variables, from the point of view of the classification, and eliminates the unimportant once. In this article we present a framework for feature selection and data dimensionality reduction. The methodology is built around the random forest (RF) algorithm and its variable importance evaluation. In order to deal with datasets so large as to be practically unmanageable, we propose an algorithm based on RF that reduces the dimension of the database by eliminating irrelevant features. Furthermore, this framework is applied to optimize our discriminative model for brain tumor segmentation.

Feature combination networks for the interpretation of statistical machine learning models: application to Ames mutagenicity.

PubMed

Webb, Samuel J; Hanser, Thierry; Howlin, Brendan; Krause, Paul; Vessey, Jonathan D

2014-03-25

A new algorithm has been developed to enable the interpretation of black box models. The developed algorithm is agnostic to learning algorithm and open to all structural based descriptors such as fragments, keys and hashed fingerprints. The algorithm has provided meaningful interpretation of Ames mutagenicity predictions from both random forest and support vector machine models built on a variety of structural fingerprints.A fragmentation algorithm is utilised to investigate the model's behaviour on specific substructures present in the query. An output is formulated summarising causes of activation and deactivation. The algorithm is able to identify multiple causes of activation or deactivation in addition to identifying localised deactivations where the prediction for the query is active overall. No loss in performance is seen as there is no change in the prediction; the interpretation is produced directly on the model's behaviour for the specific query. Models have been built using multiple learning algorithms including support vector machine and random forest. The models were built on public Ames mutagenicity data and a variety of fingerprint descriptors were used. These models produced a good performance in both internal and external validation with accuracies around 82%. The models were used to evaluate the interpretation algorithm. Interpretation was revealed that links closely with understood mechanisms for Ames mutagenicity. This methodology allows for a greater utilisation of the predictions made by black box models and can expedite further study based on the output for a (quantitative) structure activity model. Additionally the algorithm could be utilised for chemical dataset investigation and knowledge extraction/human SAR development.

D Semantic Labeling of ALS Data Based on Domain Adaption by Transferring and Fusing Random Forest Models

NASA Astrophysics Data System (ADS)

Wu, J.; Yao, W.; Zhang, J.; Li, Y.

2018-04-01

Labeling 3D point cloud data with traditional supervised learning methods requires considerable labelled samples, the collection of which is cost and time expensive. This work focuses on adopting domain adaption concept to transfer existing trained random forest classifiers (based on source domain) to new data scenes (target domain), which aims at reducing the dependence of accurate 3D semantic labeling in point clouds on training samples from the new data scene. Firstly, two random forest classifiers were firstly trained with existing samples previously collected for other data. They were different from each other by using two different decision tree construction algorithms: C4.5 with information gain ratio and CART with Gini index. Secondly, four random forest classifiers adapted to the target domain are derived through transferring each tree in the source random forest models with two types of operations: structure expansion and reduction-SER and structure transfer-STRUT. Finally, points in target domain are labelled by fusing the four newly derived random forest classifiers using weights of evidence based fusion model. To validate our method, experimental analysis was conducted using 3 datasets: one is used as the source domain data (Vaihingen data for 3D Semantic Labelling); another two are used as the target domain data from two cities in China (Jinmen city and Dunhuang city). Overall accuracies of 85.5 % and 83.3 % for 3D labelling were achieved for Jinmen city and Dunhuang city data respectively, with only 1/3 newly labelled samples compared to the cases without domain adaption.

Empirical study of seven data mining algorithms on different characteristics of datasets for biomedical classification applications.

PubMed

Zhang, Yiyan; Xin, Yi; Li, Qin; Ma, Jianshe; Li, Shuai; Lv, Xiaodan; Lv, Weiqi

2017-11-02

Various kinds of data mining algorithms are continuously raised with the development of related disciplines. The applicable scopes and their performances of these algorithms are different. Hence, finding a suitable algorithm for a dataset is becoming an important emphasis for biomedical researchers to solve practical problems promptly. In this paper, seven kinds of sophisticated active algorithms, namely, C4.5, support vector machine, AdaBoost, k-nearest neighbor, naïve Bayes, random forest, and logistic regression, were selected as the research objects. The seven algorithms were applied to the 12 top-click UCI public datasets with the task of classification, and their performances were compared through induction and analysis. The sample size, number of attributes, number of missing values, and the sample size of each class, correlation coefficients between variables, class entropy of task variable, and the ratio of the sample size of the largest class to the least class were calculated to character the 12 research datasets. The two ensemble algorithms reach high accuracy of classification on most datasets. Moreover, random forest performs better than AdaBoost on the unbalanced dataset of the multi-class task. Simple algorithms, such as the naïve Bayes and logistic regression model are suitable for a small dataset with high correlation between the task and other non-task attribute variables. K-nearest neighbor and C4.5 decision tree algorithms perform well on binary- and multi-class task datasets. Support vector machine is more adept on the balanced small dataset of the binary-class task. No algorithm can maintain the best performance in all datasets. The applicability of the seven data mining algorithms on the datasets with different characteristics was summarized to provide a reference for biomedical researchers or beginners in different fields.

SU-C-207B-05: Tissue Segmentation of Computed Tomography Images Using a Random Forest Algorithm: A Feasibility Study

DOE Office of Scientific and Technical Information (OSTI.GOV)

Polan, D; Brady, S; Kaufman, R

2016-06-15

Purpose: Develop an automated Random Forest algorithm for tissue segmentation of CT examinations. Methods: Seven materials were classified for segmentation: background, lung/internal gas, fat, muscle, solid organ parenchyma, blood/contrast, and bone using Matlab and the Trainable Weka Segmentation (TWS) plugin of FIJI. The following classifier feature filters of TWS were investigated: minimum, maximum, mean, and variance each evaluated over a pixel radius of 2n, (n = 0–4). Also noise reduction and edge preserving filters, Gaussian, bilateral, Kuwahara, and anisotropic diffusion, were evaluated. The algorithm used 200 trees with 2 features per node. A training data set was established using anmore » anonymized patient’s (male, 20 yr, 72 kg) chest-abdomen-pelvis CT examination. To establish segmentation ground truth, the training data were manually segmented using Eclipse planning software, and an intra-observer reproducibility test was conducted. Six additional patient data sets were segmented based on classifier data generated from the training data. Accuracy of segmentation was determined by calculating the Dice similarity coefficient (DSC) between manual and auto segmented images. Results: The optimized autosegmentation algorithm resulted in 16 features calculated using maximum, mean, variance, and Gaussian blur filters with kernel radii of 1, 2, and 4 pixels, in addition to the original CT number, and Kuwahara filter (linear kernel of 19 pixels). Ground truth had a DSC of 0.94 (range: 0.90–0.99) for adult and 0.92 (range: 0.85–0.99) for pediatric data sets across all seven segmentation classes. The automated algorithm produced segmentation with an average DSC of 0.85 ± 0.04 (range: 0.81–1.00) for the adult patients, and 0.86 ± 0.03 (range: 0.80–0.99) for the pediatric patients. Conclusion: The TWS Random Forest auto-segmentation algorithm was optimized for CT environment, and able to segment seven material classes over a range of body habitus and CT protocol parameters with an average DSC of 0.86 ± 0.04 (range: 0.80–0.99).« less

Subtyping cognitive profiles in Autism Spectrum Disorder using a Functional Random Forest algorithm.

PubMed

Feczko, E; Balba, N M; Miranda-Dominguez, O; Cordova, M; Karalunas, S L; Irwin, L; Demeter, D V; Hill, A P; Langhorst, B H; Grieser Painter, J; Van Santen, J; Fombonne, E J; Nigg, J T; Fair, D A

2018-05-15

DSM-5 Autism Spectrum Disorder (ASD) comprises a set of neurodevelopmental disorders characterized by deficits in social communication and interaction and repetitive behaviors or restricted interests, and may both affect and be affected by multiple cognitive mechanisms. This study attempts to identify and characterize cognitive subtypes within the ASD population using our Functional Random Forest (FRF) machine learning classification model. This model trained a traditional random forest model on measures from seven tasks that reflect multiple levels of information processing. 47 ASD diagnosed and 58 typically developing (TD) children between the ages of 9 and 13 participated in this study. Our RF model was 72.7% accurate, with 80.7% specificity and 63.1% sensitivity. Using the random forest model, the FRF then measures the proximity of each subject to every other subject, generating a distance matrix between participants. This matrix is then used in a community detection algorithm to identify subgroups within the ASD and TD groups, and revealed 3 ASD and 4 TD putative subgroups with unique behavioral profiles. We then examined differences in functional brain systems between diagnostic groups and putative subgroups using resting-state functional connectivity magnetic resonance imaging (rsfcMRI). Chi-square tests revealed a significantly greater number of between group differences (p < .05) within the cingulo-opercular, visual, and default systems as well as differences in inter-system connections in the somato-motor, dorsal attention, and subcortical systems. Many of these differences were primarily driven by specific subgroups suggesting that our method could potentially parse the variation in brain mechanisms affected by ASD. Copyright © 2017. Published by Elsevier Inc.

Remote sensing leaf water stress in coffee (Coffea arabica) using secondary effects of water absorption and random forests

NASA Astrophysics Data System (ADS)

Chemura, Abel; Mutanga, Onisimo; Dube, Timothy

2017-08-01

Water management is an important component in agriculture, particularly for perennial tree crops such as coffee. Proper detection and monitoring of water stress therefore plays an important role not only in mitigating the associated adverse impacts on crop growth and productivity but also in reducing expensive and environmentally unsustainable irrigation practices. Current methods for water stress detection in coffee production mainly involve monitoring plant physiological characteristics and soil conditions. In this study, we tested the ability of selected wavebands in the VIS/NIR range to predict plant water content (PWC) in coffee using the random forest algorithm. An experiment was set up such that coffee plants were exposed to different levels of water stress and reflectance and plant water content measured. In selecting appropriate parameters, cross-correlation identified 11 wavebands, reflectance difference identified 16 and reflectance sensitivity identified 22 variables related to PWC. Only three wavebands (485 nm, 670 nm and 885 nm) were identified by at least two methods as significant. The selected wavebands were trained (n = 36) and tested on independent data (n = 24) after being integrated into the random forest algorithm to predict coffee PWC. The results showed that the reflectance sensitivity selected bands performed the best in water stress detection (r = 0.87, RMSE = 4.91% and pBias = 0.9%), when compared to reflectance difference (r = 0.79, RMSE = 6.19 and pBias = 2.5%) and cross-correlation selected wavebands (r = 0.75, RMSE = 6.52 and pBias = 1.6). These results indicate that it is possible to reliably predict PWC using wavebands in the VIS/NIR range that correspond with many of the available multispectral scanners using random forests and further research at field and landscape scale is required to operationalize these findings.

Comparing ensemble learning methods based on decision tree classifiers for protein fold recognition.

PubMed

Bardsiri, Mahshid Khatibi; Eftekhari, Mahdi

2014-01-01

In this paper, some methods for ensemble learning of protein fold recognition based on a decision tree (DT) are compared and contrasted against each other over three datasets taken from the literature. According to previously reported studies, the features of the datasets are divided into some groups. Then, for each of these groups, three ensemble classifiers, namely, random forest, rotation forest and AdaBoost.M1 are employed. Also, some fusion methods are introduced for combining the ensemble classifiers obtained in the previous step. After this step, three classifiers are produced based on the combination of classifiers of types random forest, rotation forest and AdaBoost.M1. Finally, the three different classifiers achieved are combined to make an overall classifier. Experimental results show that the overall classifier obtained by the genetic algorithm (GA) weighting fusion method, is the best one in comparison to previously applied methods in terms of classification accuracy.

Decision tree modeling using R.

PubMed

Zhang, Zhongheng

2016-08-01

In machine learning field, decision tree learner is powerful and easy to interpret. It employs recursive binary partitioning algorithm that splits the sample in partitioning variable with the strongest association with the response variable. The process continues until some stopping criteria are met. In the example I focus on conditional inference tree, which incorporates tree-structured regression models into conditional inference procedures. While growing a single tree is subject to small changes in the training data, random forests procedure is introduced to address this problem. The sources of diversity for random forests come from the random sampling and restricted set of input variables to be selected. Finally, I introduce R functions to perform model based recursive partitioning. This method incorporates recursive partitioning into conventional parametric model building.

Multisource passive acoustic tracking: an application of random finite set data fusion

NASA Astrophysics Data System (ADS)

Ali, Andreas M.; Hudson, Ralph E.; Lorenzelli, Flavio; Yao, Kung

2010-04-01

Multisource passive acoustic tracking is useful in animal bio-behavioral study by replacing or enhancing human involvement during and after field data collection. Multiple simultaneous vocalizations are a common occurrence in a forest or a jungle, where many species are encountered. Given a set of nodes that are capable of producing multiple direction-of-arrivals (DOAs), such data needs to be combined into meaningful estimates. Random Finite Set provides the mathematical probabilistic model, which is suitable for analysis and optimal estimation algorithm synthesis. Then the proposed algorithm has been verified using a simulation and a controlled test experiment.

Object based image analysis for the classification of the growth stages of Avocado crop, in Michoacán State, Mexico

NASA Astrophysics Data System (ADS)

Gao, Yan; Marpu, Prashanth; Morales Manila, Luis M.

2014-11-01

This paper assesses the suitability of 8-band Worldview-2 (WV2) satellite data and object-based random forest algorithm for the classification of avocado growth stages in Mexico. We tested both pixel-based with minimum distance (MD) and maximum likelihood (MLC) and object-based with Random Forest (RF) algorithm for this task. Training samples and verification data were selected by visual interpreting the WV2 images for seven thematic classes: fully grown, middle stage, and early stage of avocado crops, bare land, two types of natural forests, and water body. To examine the contribution of the four new spectral bands of WV2 sensor, all the tested classifications were carried out with and without the four new spectral bands. Classification accuracy assessment results show that object-based classification with RF algorithm obtained higher overall higher accuracy (93.06%) than pixel-based MD (69.37%) and MLC (64.03%) method. For both pixel-based and object-based methods, the classifications with the four new spectral bands (overall accuracy obtained higher accuracy than those without: overall accuracy of object-based RF classification with vs without: 93.06% vs 83.59%, pixel-based MD: 69.37% vs 67.2%, pixel-based MLC: 64.03% vs 36.05%, suggesting that the four new spectral bands in WV2 sensor contributed to the increase of the classification accuracy.

On the classification techniques in data mining for microarray data classification

NASA Astrophysics Data System (ADS)

Aydadenta, Husna; Adiwijaya

2018-03-01

Cancer is one of the deadly diseases, according to data from WHO by 2015 there are 8.8 million more deaths caused by cancer, and this will increase every year if not resolved earlier. Microarray data has become one of the most popular cancer-identification studies in the field of health, since microarray data can be used to look at levels of gene expression in certain cell samples that serve to analyze thousands of genes simultaneously. By using data mining technique, we can classify the sample of microarray data thus it can be identified with cancer or not. In this paper we will discuss some research using some data mining techniques using microarray data, such as Support Vector Machine (SVM), Artificial Neural Network (ANN), Naive Bayes, k-Nearest Neighbor (kNN), and C4.5, and simulation of Random Forest algorithm with technique of reduction dimension using Relief. The result of this paper show performance measure (accuracy) from classification algorithm (SVM, ANN, Naive Bayes, kNN, C4.5, and Random Forets).The results in this paper show the accuracy of Random Forest algorithm higher than other classification algorithms (Support Vector Machine (SVM), Artificial Neural Network (ANN), Naive Bayes, k-Nearest Neighbor (kNN), and C4.5). It is hoped that this paper can provide some information about the speed, accuracy, performance and computational cost generated from each Data Mining Classification Technique based on microarray data.

Linear Subpixel Learning Algorithm for Land Cover Classification from WELD using High Performance Computing

NASA Technical Reports Server (NTRS)

Kumar, Uttam; Nemani, Ramakrishna R.; Ganguly, Sangram; Kalia, Subodh; Michaelis, Andrew

2017-01-01

In this work, we use a Fully Constrained Least Squares Subpixel Learning Algorithm to unmix global WELD (Web Enabled Landsat Data) to obtain fractions or abundances of substrate (S), vegetation (V) and dark objects (D) classes. Because of the sheer nature of data and compute needs, we leveraged the NASA Earth Exchange (NEX) high performance computing architecture to optimize and scale our algorithm for large-scale processing. Subsequently, the S-V-D abundance maps were characterized into 4 classes namely, forest, farmland, water and urban areas (with NPP-VIIRS-national polar orbiting partnership visible infrared imaging radiometer suite nighttime lights data) over California, USA using Random Forest classifier. Validation of these land cover maps with NLCD (National Land Cover Database) 2011 products and NAFD (North American Forest Dynamics) static forest cover maps showed that an overall classification accuracy of over 91 percent was achieved, which is a 6 percent improvement in unmixing based classification relative to per-pixel-based classification. As such, abundance maps continue to offer an useful alternative to high-spatial resolution data derived classification maps for forest inventory analysis, multi-class mapping for eco-climatic models and applications, fast multi-temporal trend analysis and for societal and policy-relevant applications needed at the watershed scale.

Linear Subpixel Learning Algorithm for Land Cover Classification from WELD using High Performance Computing

NASA Astrophysics Data System (ADS)

Ganguly, S.; Kumar, U.; Nemani, R. R.; Kalia, S.; Michaelis, A.

2017-12-01

In this work, we use a Fully Constrained Least Squares Subpixel Learning Algorithm to unmix global WELD (Web Enabled Landsat Data) to obtain fractions or abundances of substrate (S), vegetation (V) and dark objects (D) classes. Because of the sheer nature of data and compute needs, we leveraged the NASA Earth Exchange (NEX) high performance computing architecture to optimize and scale our algorithm for large-scale processing. Subsequently, the S-V-D abundance maps were characterized into 4 classes namely, forest, farmland, water and urban areas (with NPP-VIIRS - national polar orbiting partnership visible infrared imaging radiometer suite nighttime lights data) over California, USA using Random Forest classifier. Validation of these land cover maps with NLCD (National Land Cover Database) 2011 products and NAFD (North American Forest Dynamics) static forest cover maps showed that an overall classification accuracy of over 91% was achieved, which is a 6% improvement in unmixing based classification relative to per-pixel based classification. As such, abundance maps continue to offer an useful alternative to high-spatial resolution data derived classification maps for forest inventory analysis, multi-class mapping for eco-climatic models and applications, fast multi-temporal trend analysis and for societal and policy-relevant applications needed at the watershed scale.

Quantifying Biomass from Point Clouds by Connecting Representations of Ecosystem Structure

NASA Astrophysics Data System (ADS)

Hendryx, S. M.; Barron-Gafford, G.

2017-12-01

Quantifying terrestrial ecosystem biomass is an essential part of monitoring carbon stocks and fluxes within the global carbon cycle and optimizing natural resource management. Point cloud data such as from lidar and structure from motion can be effective for quantifying biomass over large areas, but significant challenges remain in developing effective models that allow for such predictions. Inference models that estimate biomass from point clouds are established in many environments, yet, are often scale-dependent, needing to be fitted and applied at the same spatial scale and grid size at which they were developed. Furthermore, training such models typically requires large in situ datasets that are often prohibitively costly or time-consuming to obtain. We present here a scale- and sensor-invariant framework for efficiently estimating biomass from point clouds. Central to this framework, we present a new algorithm, assignPointsToExistingClusters, that has been developed for finding matches between in situ data and clusters in remotely-sensed point clouds. The algorithm can be used for assessing canopy segmentation accuracy and for training and validating machine learning models for predicting biophysical variables. We demonstrate the algorithm's efficacy by using it to train a random forest model of above ground biomass in a shrubland environment in Southern Arizona. We show that by learning a nonlinear function to estimate biomass from segmented canopy features we can reduce error, especially in the presence of inaccurate clusterings, when compared to a traditional, deterministic technique to estimate biomass from remotely measured canopies. Our random forest on cluster features model extends established methods of training random forest regressions to predict biomass of subplots but requires significantly less training data and is scale invariant. The random forest on cluster features model reduced mean absolute error, when evaluated on all test data in leave one out cross validation, by 40.6% from deterministic mesquite allometry and 35.9% from the inferred ecosystem-state allometric function. Our framework should allow for the inference of biomass more efficiently than common subplot methods and more accurately than individual tree segmentation methods in densely vegetated environments.

Integration of spectral, spatial and morphometric data into lithological mapping: A comparison of different Machine Learning Algorithms in the Kurdistan Region, NE Iraq

NASA Astrophysics Data System (ADS)

Othman, Arsalan A.; Gloaguen, Richard

2017-09-01

Lithological mapping in mountainous regions is often impeded by limited accessibility due to relief. This study aims to evaluate (1) the performance of different supervised classification approaches using remote sensing data and (2) the use of additional information such as geomorphology. We exemplify the methodology in the Bardi-Zard area in NE Iraq, a part of the Zagros Fold - Thrust Belt, known for its chromite deposits. We highlighted the improvement of remote sensing geological classification by integrating geomorphic features and spatial information in the classification scheme. We performed a Maximum Likelihood (ML) classification method besides two Machine Learning Algorithms (MLA): Support Vector Machine (SVM) and Random Forest (RF) to allow the joint use of geomorphic features, Band Ratio (BR), Principal Component Analysis (PCA), spatial information (spatial coordinates) and multispectral data of the Advanced Space-borne Thermal Emission and Reflection radiometer (ASTER) satellite. The RF algorithm showed reliable results and discriminated serpentinite, talus and terrace deposits, red argillites with conglomerates and limestone, limy conglomerates and limestone conglomerates, tuffites interbedded with basic lavas, limestone and Metamorphosed limestone and reddish green shales. The best overall accuracy (∼80%) was achieved by Random Forest (RF) algorithms in the majority of the sixteen tested combination datasets.

Identifying Active Travel Behaviors in Challenging Environments Using GPS, Accelerometers, and Machine Learning Algorithms

PubMed Central

Ellis, Katherine; Godbole, Suneeta; Marshall, Simon; Lanckriet, Gert; Staudenmayer, John; Kerr, Jacqueline

2014-01-01

Background: Active travel is an important area in physical activity research, but objective measurement of active travel is still difficult. Automated methods to measure travel behaviors will improve research in this area. In this paper, we present a supervised machine learning method for transportation mode prediction from global positioning system (GPS) and accelerometer data. Methods: We collected a dataset of about 150 h of GPS and accelerometer data from two research assistants following a protocol of prescribed trips consisting of five activities: bicycling, riding in a vehicle, walking, sitting, and standing. We extracted 49 features from 1-min windows of this data. We compared the performance of several machine learning algorithms and chose a random forest algorithm to classify the transportation mode. We used a moving average output filter to smooth the output predictions over time. Results: The random forest algorithm achieved 89.8% cross-validated accuracy on this dataset. Adding the moving average filter to smooth output predictions increased the cross-validated accuracy to 91.9%. Conclusion: Machine learning methods are a viable approach for automating measurement of active travel, particularly for measuring travel activities that traditional accelerometer data processing methods misclassify, such as bicycling and vehicle travel. PMID:24795875

Classification of large-sized hyperspectral imagery using fast machine learning algorithms

NASA Astrophysics Data System (ADS)

Xia, Junshi; Yokoya, Naoto; Iwasaki, Akira

2017-07-01

We present a framework of fast machine learning algorithms in the context of large-sized hyperspectral images classification from the theoretical to a practical viewpoint. In particular, we assess the performance of random forest (RF), rotation forest (RoF), and extreme learning machine (ELM) and the ensembles of RF and ELM. These classifiers are applied to two large-sized hyperspectral images and compared to the support vector machines. To give the quantitative analysis, we pay attention to comparing these methods when working with high input dimensions and a limited/sufficient training set. Moreover, other important issues such as the computational cost and robustness against the noise are also discussed.

Evaluating data mining algorithms using molecular dynamics trajectories.

PubMed

Tatsis, Vasileios A; Tjortjis, Christos; Tzirakis, Panagiotis

2013-01-01

Molecular dynamics simulations provide a sample of a molecule's conformational space. Experiments on the mus time scale, resulting in large amounts of data, are nowadays routine. Data mining techniques such as classification provide a way to analyse such data. In this work, we evaluate and compare several classification algorithms using three data sets which resulted from computer simulations, of a potential enzyme mimetic biomolecule. We evaluated 65 classifiers available in the well-known data mining toolkit Weka, using 'classification' errors to assess algorithmic performance. Results suggest that: (i) 'meta' classifiers perform better than the other groups, when applied to molecular dynamics data sets; (ii) Random Forest and Rotation Forest are the best classifiers for all three data sets; and (iii) classification via clustering yields the highest classification error. Our findings are consistent with bibliographic evidence, suggesting a 'roadmap' for dealing with such data.

Assessment of various supervised learning algorithms using different performance metrics

NASA Astrophysics Data System (ADS)

Susheel Kumar, S. M.; Laxkar, Deepak; Adhikari, Sourav; Vijayarajan, V.

2017-11-01

Our work brings out comparison based on the performance of supervised machine learning algorithms on a binary classification task. The supervised machine learning algorithms which are taken into consideration in the following work are namely Support Vector Machine(SVM), Decision Tree(DT), K Nearest Neighbour (KNN), Naïve Bayes(NB) and Random Forest(RF). This paper mostly focuses on comparing the performance of above mentioned algorithms on one binary classification task by analysing the Metrics such as Accuracy, F-Measure, G-Measure, Precision, Misclassification Rate, False Positive Rate, True Positive Rate, Specificity, Prevalence.

Application of XGBoost algorithm in hourly PM2.5 concentration prediction

NASA Astrophysics Data System (ADS)

Pan, Bingyue

2018-02-01

In view of prediction techniques of hourly PM2.5 concentration in China, this paper applied the XGBoost(Extreme Gradient Boosting) algorithm to predict hourly PM2.5 concentration. The monitoring data of air quality in Tianjin city was analyzed by using XGBoost algorithm. The prediction performance of the XGBoost method is evaluated by comparing observed and predicted PM2.5 concentration using three measures of forecast accuracy. The XGBoost method is also compared with the random forest algorithm, multiple linear regression, decision tree regression and support vector machines for regression models using computational results. The results demonstrate that the XGBoost algorithm outperforms other data mining methods.

Recursive random forest algorithm for constructing multilayered hierarchical gene regulatory networks that govern biological pathways.

PubMed

Deng, Wenping; Zhang, Kui; Busov, Victor; Wei, Hairong

2017-01-01

Present knowledge indicates a multilayered hierarchical gene regulatory network (ML-hGRN) often operates above a biological pathway. Although the ML-hGRN is very important for understanding how a pathway is regulated, there is almost no computational algorithm for directly constructing ML-hGRNs. A backward elimination random forest (BWERF) algorithm was developed for constructing the ML-hGRN operating above a biological pathway. For each pathway gene, the BWERF used a random forest model to calculate the importance values of all transcription factors (TFs) to this pathway gene recursively with a portion (e.g. 1/10) of least important TFs being excluded in each round of modeling, during which, the importance values of all TFs to the pathway gene were updated and ranked until only one TF was remained in the list. The above procedure, termed BWERF. After that, the importance values of a TF to all pathway genes were aggregated and fitted to a Gaussian mixture model to determine the TF retention for the regulatory layer immediately above the pathway layer. The acquired TFs at the secondary layer were then set to be the new bottom layer to infer the next upper layer, and this process was repeated until a ML-hGRN with the expected layers was obtained. BWERF improved the accuracy for constructing ML-hGRNs because it used backward elimination to exclude the noise genes, and aggregated the individual importance values for determining the TFs retention. We validated the BWERF by using it for constructing ML-hGRNs operating above mouse pluripotency maintenance pathway and Arabidopsis lignocellulosic pathway. Compared to GENIE3, BWERF showed an improvement in recognizing authentic TFs regulating a pathway. Compared to the bottom-up Gaussian graphical model algorithm we developed for constructing ML-hGRNs, the BWERF can construct ML-hGRNs with significantly reduced edges that enable biologists to choose the implicit edges for experimental validation.

Combined use of two supervised learning algorithms to model sea turtle behaviours from tri-axial acceleration data.

PubMed

Jeantet, L; Dell'Amico, F; Forin-Wiart, M-A; Coutant, M; Bonola, M; Etienne, D; Gresser, J; Regis, S; Lecerf, N; Lefebvre, F; de Thoisy, B; Le Maho, Y; Brucker, M; Châtelain, N; Laesser, R; Crenner, F; Handrich, Y; Wilson, R; Chevallier, D

2018-05-23

Accelerometers are becoming ever more important sensors in animal-attached technology, providing data that allow determination of body posture and movement and thereby helping to elucidate behaviour in animals that are difficult to observe. We sought to validate the identification of sea turtle behaviours from accelerometer signals by deploying tags on the carapace of a juvenile loggerhead ( Caretta caretta ), an adult hawksbill ( Eretmochelys imbricata ) and an adult green turtle ( Chelonia mydas ) at Aquarium La Rochelle, France. We recorded tri-axial acceleration at 50 Hz for each species for a full day while two fixed cameras recorded their behaviours. We identified behaviours from the acceleration data using two different supervised learning algorithms, Random Forest and Classification And Regression Tree (CART), treating the data from the adult animals as separate from the juvenile data. We achieved a global accuracy of 81.30% for the adult hawksbill and green turtle CART model and 71.63% for the juvenile loggerhead, identifying 10 and 12 different behaviours, respectively. Equivalent figures were 86.96% for the adult hawksbill and green turtle Random Forest model and 79.49% for the juvenile loggerhead, for the same behaviours. The use of Random Forest combined with CART algorithms allowed us to understand the decision rules implicated in behaviour discrimination, and thus remove or group together some 'confused' or under--represented behaviours in order to get the most accurate models. This study is the first to validate accelerometer data to identify turtle behaviours and the approach can now be tested on other captive sea turtle species. © 2018. Published by The Company of Biologists Ltd.

Genome analysis of Legionella pneumophila strains using a mixed-genome microarray.

PubMed

Euser, Sjoerd M; Nagelkerke, Nico J; Schuren, Frank; Jansen, Ruud; Den Boer, Jeroen W

2012-01-01

Legionella, the causative agent for Legionnaires' disease, is ubiquitous in both natural and man-made aquatic environments. The distribution of Legionella genotypes within clinical strains is significantly different from that found in environmental strains. Developing novel genotypic methods that offer the ability to distinguish clinical from environmental strains could help to focus on more relevant (virulent) Legionella species in control efforts. Mixed-genome microarray data can be used to perform a comparative-genome analysis of strain collections, and advanced statistical approaches, such as the Random Forest algorithm are available to process these data. Microarray analysis was performed on a collection of 222 Legionella pneumophila strains, which included patient-derived strains from notified cases in The Netherlands in the period 2002-2006 and the environmental strains that were collected during the source investigation for those patients within the Dutch National Legionella Outbreak Detection Programme. The Random Forest algorithm combined with a logistic regression model was used to select predictive markers and to construct a predictive model that could discriminate between strains from different origin: clinical or environmental. Four genetic markers were selected that correctly predicted 96% of the clinical strains and 66% of the environmental strains collected within the Dutch National Legionella Outbreak Detection Programme. The Random Forest algorithm is well suited for the development of prediction models that use mixed-genome microarray data to discriminate between Legionella strains from different origin. The identification of these predictive genetic markers could offer the possibility to identify virulence factors within the Legionella genome, which in the future may be implemented in the daily practice of controlling Legionella in the public health environment.

Ensemble Feature Learning of Genomic Data Using Support Vector Machine

PubMed Central

Anaissi, Ali; Goyal, Madhu; Catchpoole, Daniel R.; Braytee, Ali; Kennedy, Paul J.

2016-01-01

The identification of a subset of genes having the ability to capture the necessary information to distinguish classes of patients is crucial in bioinformatics applications. Ensemble and bagging methods have been shown to work effectively in the process of gene selection and classification. Testament to that is random forest which combines random decision trees with bagging to improve overall feature selection and classification accuracy. Surprisingly, the adoption of these methods in support vector machines has only recently received attention but mostly on classification not gene selection. This paper introduces an ensemble SVM-Recursive Feature Elimination (ESVM-RFE) for gene selection that follows the concepts of ensemble and bagging used in random forest but adopts the backward elimination strategy which is the rationale of RFE algorithm. The rationale behind this is, building ensemble SVM models using randomly drawn bootstrap samples from the training set, will produce different feature rankings which will be subsequently aggregated as one feature ranking. As a result, the decision for elimination of features is based upon the ranking of multiple SVM models instead of choosing one particular model. Moreover, this approach will address the problem of imbalanced datasets by constructing a nearly balanced bootstrap sample. Our experiments show that ESVM-RFE for gene selection substantially increased the classification performance on five microarray datasets compared to state-of-the-art methods. Experiments on the childhood leukaemia dataset show that an average 9% better accuracy is achieved by ESVM-RFE over SVM-RFE, and 5% over random forest based approach. The selected genes by the ESVM-RFE algorithm were further explored with Singular Value Decomposition (SVD) which reveals significant clusters with the selected data. PMID:27304923

Epidermis area detection for immunofluorescence microscopy

NASA Astrophysics Data System (ADS)

Dovganich, Andrey; Krylov, Andrey; Nasonov, Andrey; Makhneva, Natalia

2018-04-01

We propose a novel image segmentation method for immunofluorescence microscopy images of skin tissue for the diagnosis of various skin diseases. The segmentation is based on machine learning algorithms. The feature vector is filled by three groups of features: statistical features, Laws' texture energy measures and local binary patterns. The images are preprocessed for better learning. Different machine learning algorithms have been used and the best results have been obtained with random forest algorithm. We use the proposed method to detect the epidermis region as a part of pemphigus diagnosis system.

Developing a Learning Algorithm-Generated Empirical Relaxer

DOE Office of Scientific and Technical Information (OSTI.GOV)

Mitchell, Wayne; Kallman, Josh; Toreja, Allen

2016-03-30

One of the main difficulties when running Arbitrary Lagrangian-Eulerian (ALE) simulations is determining how much to relax the mesh during the Eulerian step. This determination is currently made by the user on a simulation-by-simulation basis. We present a Learning Algorithm-Generated Empirical Relaxer (LAGER) which uses a regressive random forest algorithm to automate this decision process. We also demonstrate that LAGER successfully relaxes a variety of test problems, maintains simulation accuracy, and has the potential to significantly decrease both the person-hours and computational hours needed to run a successful ALE simulation.

Automatic detection of atrial fibrillation in cardiac vibration signals.

PubMed

Brueser, C; Diesel, J; Zink, M D H; Winter, S; Schauerte, P; Leonhardt, S

2013-01-01

We present a study on the feasibility of the automatic detection of atrial fibrillation (AF) from cardiac vibration signals (ballistocardiograms/BCGs) recorded by unobtrusive bedmounted sensors. The proposed system is intended as a screening and monitoring tool in home-healthcare applications and not as a replacement for ECG-based methods used in clinical environments. Based on BCG data recorded in a study with 10 AF patients, we evaluate and rank seven popular machine learning algorithms (naive Bayes, linear and quadratic discriminant analysis, support vector machines, random forests as well as bagged and boosted trees) for their performance in separating 30 s long BCG epochs into one of three classes: sinus rhythm, atrial fibrillation, and artifact. For each algorithm, feature subsets of a set of statistical time-frequency-domain and time-domain features were selected based on the mutual information between features and class labels as well as first- and second-order interactions among features. The classifiers were evaluated on a set of 856 epochs by means of 10-fold cross-validation. The best algorithm (random forests) achieved a Matthews correlation coefficient, mean sensitivity, and mean specificity of 0.921, 0.938, and 0.982, respectively.

Optimizing classification performance in an object-based very-high-resolution land use-land cover urban application

NASA Astrophysics Data System (ADS)

Georganos, Stefanos; Grippa, Tais; Vanhuysse, Sabine; Lennert, Moritz; Shimoni, Michal; Wolff, Eléonore

2017-10-01

This study evaluates the impact of three Feature Selection (FS) algorithms in an Object Based Image Analysis (OBIA) framework for Very-High-Resolution (VHR) Land Use-Land Cover (LULC) classification. The three selected FS algorithms, Correlation Based Selection (CFS), Mean Decrease in Accuracy (MDA) and Random Forest (RF) based Recursive Feature Elimination (RFE), were tested on Support Vector Machine (SVM), K-Nearest Neighbor, and Random Forest (RF) classifiers. The results demonstrate that the accuracy of SVM and KNN classifiers are the most sensitive to FS. The RF appeared to be more robust to high dimensionality, although a significant increase in accuracy was found by using the RFE method. In terms of classification accuracy, SVM performed the best using FS, followed by RF and KNN. Finally, only a small number of features is needed to achieve the highest performance using each classifier. This study emphasizes the benefits of rigorous FS for maximizing performance, as well as for minimizing model complexity and interpretation.

Classification of acoustic emission signals using wavelets and Random Forests : Application to localized corrosion

NASA Astrophysics Data System (ADS)

Morizet, N.; Godin, N.; Tang, J.; Maillet, E.; Fregonese, M.; Normand, B.

2016-03-01

This paper aims to propose a novel approach to classify acoustic emission (AE) signals deriving from corrosion experiments, even if embedded into a noisy environment. To validate this new methodology, synthetic data are first used throughout an in-depth analysis, comparing Random Forests (RF) to the k-Nearest Neighbor (k-NN) algorithm. Moreover, a new evaluation tool called the alter-class matrix (ACM) is introduced to simulate different degrees of uncertainty on labeled data for supervised classification. Then, tests on real cases involving noise and crevice corrosion are conducted, by preprocessing the waveforms including wavelet denoising and extracting a rich set of features as input of the RF algorithm. To this end, a software called RF-CAM has been developed. Results show that this approach is very efficient on ground truth data and is also very promising on real data, especially for its reliability, performance and speed, which are serious criteria for the chemical industry.

An integrated classifier for computer-aided diagnosis of colorectal polyps based on random forest and location index strategies

NASA Astrophysics Data System (ADS)

Hu, Yifan; Han, Hao; Zhu, Wei; Li, Lihong; Pickhardt, Perry J.; Liang, Zhengrong

2016-03-01

Feature classification plays an important role in differentiation or computer-aided diagnosis (CADx) of suspicious lesions. As a widely used ensemble learning algorithm for classification, random forest (RF) has a distinguished performance for CADx. Our recent study has shown that the location index (LI), which is derived from the well-known kNN (k nearest neighbor) and wkNN (weighted k nearest neighbor) classifier [1], has also a distinguished role in the classification for CADx. Therefore, in this paper, based on the property that the LI will achieve a very high accuracy, we design an algorithm to integrate the LI into RF for improved or higher value of AUC (area under the curve of receiver operating characteristics -- ROC). Experiments were performed by the use of a database of 153 lesions (polyps), including 116 neoplastic lesions and 37 hyperplastic lesions, with comparison to the existing classifiers of RF and wkNN, respectively. A noticeable gain by the proposed integrated classifier was quantified by the AUC measure.

Unbiased feature selection in learning random forests for high-dimensional data.

PubMed

Nguyen, Thanh-Tung; Huang, Joshua Zhexue; Nguyen, Thuy Thi

2015-01-01

Random forests (RFs) have been widely used as a powerful classification method. However, with the randomization in both bagging samples and feature selection, the trees in the forest tend to select uninformative features for node splitting. This makes RFs have poor accuracy when working with high-dimensional data. Besides that, RFs have bias in the feature selection process where multivalued features are favored. Aiming at debiasing feature selection in RFs, we propose a new RF algorithm, called xRF, to select good features in learning RFs for high-dimensional data. We first remove the uninformative features using p-value assessment, and the subset of unbiased features is then selected based on some statistical measures. This feature subset is then partitioned into two subsets. A feature weighting sampling technique is used to sample features from these two subsets for building trees. This approach enables one to generate more accurate trees, while allowing one to reduce dimensionality and the amount of data needed for learning RFs. An extensive set of experiments has been conducted on 47 high-dimensional real-world datasets including image datasets. The experimental results have shown that RFs with the proposed approach outperformed the existing random forests in increasing the accuracy and the AUC measures.

A random forest learning assisted "divide and conquer" approach for peptide conformation search.

PubMed

Chen, Xin; Yang, Bing; Lin, Zijing

2018-06-11

Computational determination of peptide conformations is challenging as it is a problem of finding minima in a high-dimensional space. The "divide and conquer" approach is promising for reliably reducing the search space size. A random forest learning model is proposed here to expand the scope of applicability of the "divide and conquer" approach. A random forest classification algorithm is used to characterize the distributions of the backbone φ-ψ units ("words"). A random forest supervised learning model is developed to analyze the combinations of the φ-ψ units ("grammar"). It is found that amino acid residues may be grouped as equivalent "words", while the φ-ψ combinations in low-energy peptide conformations follow a distinct "grammar". The finding of equivalent words empowers the "divide and conquer" method with the flexibility of fragment substitution. The learnt grammar is used to improve the efficiency of the "divide and conquer" method by removing unfavorable φ-ψ combinations without the need of dedicated human effort. The machine learning assisted search method is illustrated by efficiently searching the conformations of GGG/AAA/GGGG/AAAA/GGGGG through assembling the structures of GFG/GFGG. Moreover, the computational cost of the new method is shown to increase rather slowly with the peptide length.

Image matching as a data source for forest inventory - Comparison of Semi-Global Matching and Next-Generation Automatic Terrain Extraction algorithms in a typical managed boreal forest environment

NASA Astrophysics Data System (ADS)

Kukkonen, M.; Maltamo, M.; Packalen, P.

2017-08-01

Image matching is emerging as a compelling alternative to airborne laser scanning (ALS) as a data source for forest inventory and management. There is currently an open discussion in the forest inventory community about whether, and to what extent, the new method can be applied to practical inventory campaigns. This paper aims to contribute to this discussion by comparing two different image matching algorithms (Semi-Global Matching [SGM] and Next-Generation Automatic Terrain Extraction [NGATE]) and ALS in a typical managed boreal forest environment in southern Finland. Spectral features from unrectified aerial images were included in the modeling and the potential of image matching in areas without a high resolution digital terrain model (DTM) was also explored. Plot level predictions for total volume, stem number, basal area, height of basal area median tree and diameter of basal area median tree were modeled using an area-based approach. Plot level dominant tree species were predicted using a random forest algorithm, also using an area-based approach. The statistical difference between the error rates from different datasets was evaluated using a bootstrap method. Results showed that ALS outperformed image matching with every forest attribute, even when a high resolution DTM was used for height normalization and spectral information from images was included. Dominant tree species classification with image matching achieved accuracy levels similar to ALS regardless of the resolution of the DTM when spectral metrics were used. Neither of the image matching algorithms consistently outperformed the other, but there were noticeably different error rates depending on the parameter configuration, spectral band, resolution of DTM, or response variable. This study showed that image matching provides reasonable point cloud data for forest inventory purposes, especially when a high resolution DTM is available and information from the understory is redundant.

Performance of thigh-mounted triaxial accelerometer algorithms in objective quantification of sedentary behaviour and physical activity in older adults

PubMed Central

Verschueren, Sabine M. P.; Degens, Hans; Morse, Christopher I.; Onambélé, Gladys L.

2017-01-01

Accurate monitoring of sedentary behaviour and physical activity is key to investigate their exact role in healthy ageing. To date, accelerometers using cut-off point models are most preferred for this, however, machine learning seems a highly promising future alternative. Hence, the current study compared between cut-off point and machine learning algorithms, for optimal quantification of sedentary behaviour and physical activity intensities in the elderly. Thus, in a heterogeneous sample of forty participants (aged ≥60 years, 50% female) energy expenditure during laboratory-based activities (ranging from sedentary behaviour through to moderate-to-vigorous physical activity) was estimated by indirect calorimetry, whilst wearing triaxial thigh-mounted accelerometers. Three cut-off point algorithms and a Random Forest machine learning model were developed and cross-validated using the collected data. Detailed analyses were performed to check algorithm robustness, and examine and benchmark both overall and participant-specific balanced accuracies. This revealed that the four models can at least be used to confidently monitor sedentary behaviour and moderate-to-vigorous physical activity. Nevertheless, the machine learning algorithm outperformed the cut-off point models by being robust for all individual’s physiological and non-physiological characteristics and showing more performance of an acceptable level over the whole range of physical activity intensities. Therefore, we propose that Random Forest machine learning may be optimal for objective assessment of sedentary behaviour and physical activity in older adults using thigh-mounted triaxial accelerometry. PMID:29155839

Performance of thigh-mounted triaxial accelerometer algorithms in objective quantification of sedentary behaviour and physical activity in older adults.

PubMed

Wullems, Jorgen A; Verschueren, Sabine M P; Degens, Hans; Morse, Christopher I; Onambélé, Gladys L

2017-01-01

Accurate monitoring of sedentary behaviour and physical activity is key to investigate their exact role in healthy ageing. To date, accelerometers using cut-off point models are most preferred for this, however, machine learning seems a highly promising future alternative. Hence, the current study compared between cut-off point and machine learning algorithms, for optimal quantification of sedentary behaviour and physical activity intensities in the elderly. Thus, in a heterogeneous sample of forty participants (aged ≥60 years, 50% female) energy expenditure during laboratory-based activities (ranging from sedentary behaviour through to moderate-to-vigorous physical activity) was estimated by indirect calorimetry, whilst wearing triaxial thigh-mounted accelerometers. Three cut-off point algorithms and a Random Forest machine learning model were developed and cross-validated using the collected data. Detailed analyses were performed to check algorithm robustness, and examine and benchmark both overall and participant-specific balanced accuracies. This revealed that the four models can at least be used to confidently monitor sedentary behaviour and moderate-to-vigorous physical activity. Nevertheless, the machine learning algorithm outperformed the cut-off point models by being robust for all individual's physiological and non-physiological characteristics and showing more performance of an acceptable level over the whole range of physical activity intensities. Therefore, we propose that Random Forest machine learning may be optimal for objective assessment of sedentary behaviour and physical activity in older adults using thigh-mounted triaxial accelerometry.

Automated segmentation of thyroid gland on CT images with multi-atlas label fusion and random classification forest

NASA Astrophysics Data System (ADS)

Liu, Jiamin; Chang, Kevin; Kim, Lauren; Turkbey, Evrim; Lu, Le; Yao, Jianhua; Summers, Ronald

2015-03-01

The thyroid gland plays an important role in clinical practice, especially for radiation therapy treatment planning. For patients with head and neck cancer, radiation therapy requires a precise delineation of the thyroid gland to be spared on the pre-treatment planning CT images to avoid thyroid dysfunction. In the current clinical workflow, the thyroid gland is normally manually delineated by radiologists or radiation oncologists, which is time consuming and error prone. Therefore, a system for automated segmentation of the thyroid is desirable. However, automated segmentation of the thyroid is challenging because the thyroid is inhomogeneous and surrounded by structures that have similar intensities. In this work, the thyroid gland segmentation is initially estimated by multi-atlas label fusion algorithm. The segmentation is refined by supervised statistical learning based voxel labeling with a random forest algorithm. Multiatlas label fusion (MALF) transfers expert-labeled thyroids from atlases to a target image using deformable registration. Errors produced by label transfer are reduced by label fusion that combines the results produced by all atlases into a consensus solution. Then, random forest (RF) employs an ensemble of decision trees that are trained on labeled thyroids to recognize features. The trained forest classifier is then applied to the thyroid estimated from the MALF by voxel scanning to assign the class-conditional probability. Voxels from the expert-labeled thyroids in CT volumes are treated as positive classes; background non-thyroid voxels as negatives. We applied this automated thyroid segmentation system to CT scans of 20 patients. The results showed that the MALF achieved an overall 0.75 Dice Similarity Coefficient (DSC) and the RF classification further improved the DSC to 0.81.

Does Sentinel multi sensor data offer synergy in Improving Accuracy of Aboveground Biomass Estimate of Dense Tropical Forest? - Utility of Decision Tree Based Machine Learning Algorithms

NASA Astrophysics Data System (ADS)

Ghosh, S. M.; Behera, M. D.

2017-12-01

Forest aboveground biomass (AGB) is an important factor for preparation of global policy making decisions to tackle the impact of climate change. Several previous studies has concluded that remote sensing methods are more suitable for estimating forest biomass on regional scale. Among all available remote sensing data and methods, Synthetic Aperture Radar (SAR) data in combination with decision tree based machine learning algorithms has shown better promise in estimating higher biomass values. There aren't many studies done for biomass estimation of dense Indian tropical forests with high biomass density. In this study aboveground biomass was estimated for two major tree species, Sal (Shorea robusta) and Teak (Tectona grandis), of Katerniaghat Wildlife Sanctuary, a tropical forest situated in northern India. Biomass was estimated by combining C-band SAR data from Sentinel-1A satellite, vegetation indices produced using Sentinel-2A data and ground inventory plots. Along with SAR backscatter value, SAR texture images were also used as input as earlier studies had found that image texture has a correlation with vegetation biomass. Decision tree based nonlinear machine learning algorithms were used in place of parametric regression models for establishing relationship between fields measured values and remotely sensed parameters. Using random forest model with a combination of vegetation indices with SAR backscatter as predictor variables shows best result for Sal forest, with a coefficient of determination value of 0.71 and a RMSE value of 105.027 t/ha. In teak forest also best result can be found in the same combination but for stochastic gradient boosted model with a coefficient of determination value of 0.6 and a RMSE value of 79.45 t/ha. These results are mostly better than the results of other studies done for similar kind of forests. This study shows that Sentinel series satellite data has exceptional capabilities in estimating dense forest AGB and machine learning algorithms are better means to do so than parametric regression models.

Random Forest-Based Approach for Maximum Power Point Tracking of Photovoltaic Systems Operating under Actual Environmental Conditions.

PubMed

Shareef, Hussain; Mutlag, Ammar Hussein; Mohamed, Azah

2017-01-01

Many maximum power point tracking (MPPT) algorithms have been developed in recent years to maximize the produced PV energy. These algorithms are not sufficiently robust because of fast-changing environmental conditions, efficiency, accuracy at steady-state value, and dynamics of the tracking algorithm. Thus, this paper proposes a new random forest (RF) model to improve MPPT performance. The RF model has the ability to capture the nonlinear association of patterns between predictors, such as irradiance and temperature, to determine accurate maximum power point. A RF-based tracker is designed for 25 SolarTIFSTF-120P6 PV modules, with the capacity of 3 kW peak using two high-speed sensors. For this purpose, a complete PV system is modeled using 300,000 data samples and simulated using the MATLAB/SIMULINK package. The proposed RF-based MPPT is then tested under actual environmental conditions for 24 days to validate the accuracy and dynamic response. The response of the RF-based MPPT model is also compared with that of the artificial neural network and adaptive neurofuzzy inference system algorithms for further validation. The results show that the proposed MPPT technique gives significant improvement compared with that of other techniques. In addition, the RF model passes the Bland-Altman test, with more than 95 percent acceptability.

Random Forest-Based Approach for Maximum Power Point Tracking of Photovoltaic Systems Operating under Actual Environmental Conditions

PubMed Central

Shareef, Hussain; Mohamed, Azah

2017-01-01

Many maximum power point tracking (MPPT) algorithms have been developed in recent years to maximize the produced PV energy. These algorithms are not sufficiently robust because of fast-changing environmental conditions, efficiency, accuracy at steady-state value, and dynamics of the tracking algorithm. Thus, this paper proposes a new random forest (RF) model to improve MPPT performance. The RF model has the ability to capture the nonlinear association of patterns between predictors, such as irradiance and temperature, to determine accurate maximum power point. A RF-based tracker is designed for 25 SolarTIFSTF-120P6 PV modules, with the capacity of 3 kW peak using two high-speed sensors. For this purpose, a complete PV system is modeled using 300,000 data samples and simulated using the MATLAB/SIMULINK package. The proposed RF-based MPPT is then tested under actual environmental conditions for 24 days to validate the accuracy and dynamic response. The response of the RF-based MPPT model is also compared with that of the artificial neural network and adaptive neurofuzzy inference system algorithms for further validation. The results show that the proposed MPPT technique gives significant improvement compared with that of other techniques. In addition, the RF model passes the Bland–Altman test, with more than 95 percent acceptability. PMID:28702051

Modified Bat Algorithm for Feature Selection with the Wisconsin Diagnosis Breast Cancer (WDBC) Dataset

PubMed

Jeyasingh, Suganthi; Veluchamy, Malathi

2017-05-01

Early diagnosis of breast cancer is essential to save lives of patients. Usually, medical datasets include a large variety of data that can lead to confusion during diagnosis. The Knowledge Discovery on Database (KDD) process helps to improve efficiency. It requires elimination of inappropriate and repeated data from the dataset before final diagnosis. This can be done using any of the feature selection algorithms available in data mining. Feature selection is considered as a vital step to increase the classification accuracy. This paper proposes a Modified Bat Algorithm (MBA) for feature selection to eliminate irrelevant features from an original dataset. The Bat algorithm was modified using simple random sampling to select the random instances from the dataset. Ranking was with the global best features to recognize the predominant features available in the dataset. The selected features are used to train a Random Forest (RF) classification algorithm. The MBA feature selection algorithm enhanced the classification accuracy of RF in identifying the occurrence of breast cancer. The Wisconsin Diagnosis Breast Cancer Dataset (WDBC) was used for estimating the performance analysis of the proposed MBA feature selection algorithm. The proposed algorithm achieved better performance in terms of Kappa statistic, Mathew’s Correlation Coefficient, Precision, F-measure, Recall, Mean Absolute Error (MAE), Root Mean Square Error (RMSE), Relative Absolute Error (RAE) and Root Relative Squared Error (RRSE). Creative Commons Attribution License

Stable Atlas-based Mapped Prior (STAMP) machine-learning segmentation for multicenter large-scale MRI data.

PubMed

Kim, Eun Young; Magnotta, Vincent A; Liu, Dawei; Johnson, Hans J

2014-09-01

Machine learning (ML)-based segmentation methods are a common technique in the medical image processing field. In spite of numerous research groups that have investigated ML-based segmentation frameworks, there remains unanswered aspects of performance variability for the choice of two key components: ML algorithm and intensity normalization. This investigation reveals that the choice of those elements plays a major part in determining segmentation accuracy and generalizability. The approach we have used in this study aims to evaluate relative benefits of the two elements within a subcortical MRI segmentation framework. Experiments were conducted to contrast eight machine-learning algorithm configurations and 11 normalization strategies for our brain MR segmentation framework. For the intensity normalization, a Stable Atlas-based Mapped Prior (STAMP) was utilized to take better account of contrast along boundaries of structures. Comparing eight machine learning algorithms on down-sampled segmentation MR data, it was obvious that a significant improvement was obtained using ensemble-based ML algorithms (i.e., random forest) or ANN algorithms. Further investigation between these two algorithms also revealed that the random forest results provided exceptionally good agreement with manual delineations by experts. Additional experiments showed that the effect of STAMP-based intensity normalization also improved the robustness of segmentation for multicenter data sets. The constructed framework obtained good multicenter reliability and was successfully applied on a large multicenter MR data set (n>3000). Less than 10% of automated segmentations were recommended for minimal expert intervention. These results demonstrate the feasibility of using the ML-based segmentation tools for processing large amount of multicenter MR images. We demonstrated dramatically different result profiles in segmentation accuracy according to the choice of ML algorithm and intensity normalization chosen. Copyright © 2014 Elsevier Inc. All rights reserved.

Mapping Soil Properties of Africa at 250 m Resolution: Random Forests Significantly Improve Current Predictions

PubMed Central

Hengl, Tomislav; Heuvelink, Gerard B. M.; Kempen, Bas; Leenaars, Johan G. B.; Walsh, Markus G.; Shepherd, Keith D.; Sila, Andrew; MacMillan, Robert A.; Mendes de Jesus, Jorge; Tamene, Lulseged; Tondoh, Jérôme E.

2015-01-01

80% of arable land in Africa has low soil fertility and suffers from physical soil problems. Additionally, significant amounts of nutrients are lost every year due to unsustainable soil management practices. This is partially the result of insufficient use of soil management knowledge. To help bridge the soil information gap in Africa, the Africa Soil Information Service (AfSIS) project was established in 2008. Over the period 2008–2014, the AfSIS project compiled two point data sets: the Africa Soil Profiles (legacy) database and the AfSIS Sentinel Site database. These data sets contain over 28 thousand sampling locations and represent the most comprehensive soil sample data sets of the African continent to date. Utilizing these point data sets in combination with a large number of covariates, we have generated a series of spatial predictions of soil properties relevant to the agricultural management—organic carbon, pH, sand, silt and clay fractions, bulk density, cation-exchange capacity, total nitrogen, exchangeable acidity, Al content and exchangeable bases (Ca, K, Mg, Na). We specifically investigate differences between two predictive approaches: random forests and linear regression. Results of 5-fold cross-validation demonstrate that the random forests algorithm consistently outperforms the linear regression algorithm, with average decreases of 15–75% in Root Mean Squared Error (RMSE) across soil properties and depths. Fitting and running random forests models takes an order of magnitude more time and the modelling success is sensitive to artifacts in the input data, but as long as quality-controlled point data are provided, an increase in soil mapping accuracy can be expected. Results also indicate that globally predicted soil classes (USDA Soil Taxonomy, especially Alfisols and Mollisols) help improve continental scale soil property mapping, and are among the most important predictors. This indicates a promising potential for transferring pedological knowledge from data rich countries to countries with limited soil data. PMID:26110833

Mapping Soil Properties of Africa at 250 m Resolution: Random Forests Significantly Improve Current Predictions.

PubMed

Hengl, Tomislav; Heuvelink, Gerard B M; Kempen, Bas; Leenaars, Johan G B; Walsh, Markus G; Shepherd, Keith D; Sila, Andrew; MacMillan, Robert A; Mendes de Jesus, Jorge; Tamene, Lulseged; Tondoh, Jérôme E

2015-01-01

80% of arable land in Africa has low soil fertility and suffers from physical soil problems. Additionally, significant amounts of nutrients are lost every year due to unsustainable soil management practices. This is partially the result of insufficient use of soil management knowledge. To help bridge the soil information gap in Africa, the Africa Soil Information Service (AfSIS) project was established in 2008. Over the period 2008-2014, the AfSIS project compiled two point data sets: the Africa Soil Profiles (legacy) database and the AfSIS Sentinel Site database. These data sets contain over 28 thousand sampling locations and represent the most comprehensive soil sample data sets of the African continent to date. Utilizing these point data sets in combination with a large number of covariates, we have generated a series of spatial predictions of soil properties relevant to the agricultural management--organic carbon, pH, sand, silt and clay fractions, bulk density, cation-exchange capacity, total nitrogen, exchangeable acidity, Al content and exchangeable bases (Ca, K, Mg, Na). We specifically investigate differences between two predictive approaches: random forests and linear regression. Results of 5-fold cross-validation demonstrate that the random forests algorithm consistently outperforms the linear regression algorithm, with average decreases of 15-75% in Root Mean Squared Error (RMSE) across soil properties and depths. Fitting and running random forests models takes an order of magnitude more time and the modelling success is sensitive to artifacts in the input data, but as long as quality-controlled point data are provided, an increase in soil mapping accuracy can be expected. Results also indicate that globally predicted soil classes (USDA Soil Taxonomy, especially Alfisols and Mollisols) help improve continental scale soil property mapping, and are among the most important predictors. This indicates a promising potential for transferring pedological knowledge from data rich countries to countries with limited soil data.

Uncertainty in Random Forests: What does it mean in a spatial context?

NASA Astrophysics Data System (ADS)

Klump, Jens; Fouedjio, Francky

2017-04-01

Geochemical surveys are an important part of exploration for mineral resources and in environmental studies. The samples and chemical analyses are often laborious and difficult to obtain and therefore come at a high cost. As a consequence, these surveys are characterised by datasets with large numbers of variables but relatively few data points when compared to conventional big data problems. With more remote sensing platforms and sensor networks being deployed, large volumes of auxiliary data of the surveyed areas are becoming available. The use of these auxiliary data has the potential to improve the prediction of chemical element concentrations over the whole study area. Kriging is a well established geostatistical method for the prediction of spatial data but requires significant pre-processing and makes some basic assumptions about the underlying distribution of the data. Some machine learning algorithms, on the other hand, may require less data pre-processing and are non-parametric. In this study we used a dataset provided by Kirkwood et al. [1] to explore the potential use of Random Forest in geochemical mapping. We chose Random Forest because it is a well understood machine learning method and has the advantage that it provides us with a measure of uncertainty. By comparing Random Forest to Kriging we found that both methods produced comparable maps of estimated values for our variables of interest. Kriging outperformed Random Forest for variables of interest with relatively strong spatial correlation. The measure of uncertainty provided by Random Forest seems to be quite different to the measure of uncertainty provided by Kriging. In particular, the lack of spatial context can give misleading results in areas without ground truth data. In conclusion, our preliminary results show that the model driven approach in geostatistics gives us more reliable estimates for our target variables than Random Forest for variables with relatively strong spatial correlation. However, in cases of weak spatial correlation Random Forest, as a nonparametric method, may give the better results once we have a better understanding of the meaning of its uncertainty measures in a spatial context. References [1] Kirkwood, C., M. Cave, D. Beamish, S. Grebby, and A. Ferreira (2016), A machine learning approach to geochemical mapping, Journal of Geochemical Exploration, 163, 28-40, doi:10.1016/j.gexplo.2016.05.003.

Differential privacy-based evaporative cooling feature selection and classification with relief-F and random forests.

PubMed

Le, Trang T; Simmons, W Kyle; Misaki, Masaya; Bodurka, Jerzy; White, Bill C; Savitz, Jonathan; McKinney, Brett A

2017-09-15

Classification of individuals into disease or clinical categories from high-dimensional biological data with low prediction error is an important challenge of statistical learning in bioinformatics. Feature selection can improve classification accuracy but must be incorporated carefully into cross-validation to avoid overfitting. Recently, feature selection methods based on differential privacy, such as differentially private random forests and reusable holdout sets, have been proposed. However, for domains such as bioinformatics, where the number of features is much larger than the number of observations p≫n , these differential privacy methods are susceptible to overfitting. We introduce private Evaporative Cooling, a stochastic privacy-preserving machine learning algorithm that uses Relief-F for feature selection and random forest for privacy preserving classification that also prevents overfitting. We relate the privacy-preserving threshold mechanism to a thermodynamic Maxwell-Boltzmann distribution, where the temperature represents the privacy threshold. We use the thermal statistical physics concept of Evaporative Cooling of atomic gases to perform backward stepwise privacy-preserving feature selection. On simulated data with main effects and statistical interactions, we compare accuracies on holdout and validation sets for three privacy-preserving methods: the reusable holdout, reusable holdout with random forest, and private Evaporative Cooling, which uses Relief-F feature selection and random forest classification. In simulations where interactions exist between attributes, private Evaporative Cooling provides higher classification accuracy without overfitting based on an independent validation set. In simulations without interactions, thresholdout with random forest and private Evaporative Cooling give comparable accuracies. We also apply these privacy methods to human brain resting-state fMRI data from a study of major depressive disorder. Code available at http://insilico.utulsa.edu/software/privateEC . brett-mckinney@utulsa.edu. Supplementary data are available at Bioinformatics online. © The Author (2017). Published by Oxford University Press. All rights reserved. For Permissions, please email: journals.permissions@oup.com

Disruption prediction investigations using Machine Learning tools on DIII-D and Alcator C-Mod

DOE Office of Scientific and Technical Information (OSTI.GOV)

Rea, C.; Granetz, R. S.; Montes, K.

Using data-driven methodology, we exploit the time series of relevant plasma parameters for a large set of disrupted and non-disrupted discharges to develop a classification algorithm for detecting disruptive phases in shots that eventually disrupt. Comparing the same methodology on different devices is crucial in order to have information on the portability of the developed algorithm and the possible extrapolation to ITER. Therefore, we use data from two very different tokamaks, DIII-D and Alcator C-Mod. We then focus on a subset of disruption predictors, most of which are dimensionless and/or machine-independent parameters, coming from both plasma diagnostics and equilibrium reconstructions,more » such as the normalized plasma internal inductance ℓ and the n = 1 mode amplitude normalized to the toroidal magnetic field. Using such dimensionless indicators facilitates a more direct comparison between DIII-D and C-Mod. We then choose a shallow Machine Learning technique, called Random Forests, to explore the databases available for the two devices. We show results from the classification task, where we introduce a time dependency through the definition of class labels on the basis of the elapsed time before the disruption (i.e. ‘far from a disruption’ and ‘close to a disruption’). The performances of the different Random Forest classifiers are discussed in terms of several metrics, by showing the number of successfully detected samples, as well as the misclassifications. The overall model accuracies are above 97% when identifying a ‘far from disruption’ and a ‘disruptive’ phase for disrupted discharges. Nevertheless, the Forests are intrinsically different in their capability of predicting a disruptive behavior, with C-Mod predictions comparable to random guesses. Indeed, we show that C-Mod recall index, i.e. the sensitivity to a disruptive behavior, is as low as 0.47, while DIII-D recall is ~0.72. The portability of the developed algorithm is also tested across the two devices, by using DIII-D data for training the forests and C-Mod for testing and vice versa.« less

Disruption prediction investigations using Machine Learning tools on DIII-D and Alcator C-Mod

DOE PAGES

Rea, C.; Granetz, R. S.; Montes, K.; ...

2018-06-18

Using data-driven methodology, we exploit the time series of relevant plasma parameters for a large set of disrupted and non-disrupted discharges to develop a classification algorithm for detecting disruptive phases in shots that eventually disrupt. Comparing the same methodology on different devices is crucial in order to have information on the portability of the developed algorithm and the possible extrapolation to ITER. Therefore, we use data from two very different tokamaks, DIII-D and Alcator C-Mod. We then focus on a subset of disruption predictors, most of which are dimensionless and/or machine-independent parameters, coming from both plasma diagnostics and equilibrium reconstructions,more » such as the normalized plasma internal inductance ℓ and the n = 1 mode amplitude normalized to the toroidal magnetic field. Using such dimensionless indicators facilitates a more direct comparison between DIII-D and C-Mod. We then choose a shallow Machine Learning technique, called Random Forests, to explore the databases available for the two devices. We show results from the classification task, where we introduce a time dependency through the definition of class labels on the basis of the elapsed time before the disruption (i.e. ‘far from a disruption’ and ‘close to a disruption’). The performances of the different Random Forest classifiers are discussed in terms of several metrics, by showing the number of successfully detected samples, as well as the misclassifications. The overall model accuracies are above 97% when identifying a ‘far from disruption’ and a ‘disruptive’ phase for disrupted discharges. Nevertheless, the Forests are intrinsically different in their capability of predicting a disruptive behavior, with C-Mod predictions comparable to random guesses. Indeed, we show that C-Mod recall index, i.e. the sensitivity to a disruptive behavior, is as low as 0.47, while DIII-D recall is ~0.72. The portability of the developed algorithm is also tested across the two devices, by using DIII-D data for training the forests and C-Mod for testing and vice versa.« less

Faster Trees: Strategies for Accelerated Training and Prediction of Random Forests for Classification of Polsar Images

NASA Astrophysics Data System (ADS)

Hänsch, Ronny; Hellwich, Olaf

2018-04-01

Random Forests have continuously proven to be one of the most accurate, robust, as well as efficient methods for the supervised classification of images in general and polarimetric synthetic aperture radar data in particular. While the majority of previous work focus on improving classification accuracy, we aim for accelerating the training of the classifier as well as its usage during prediction while maintaining its accuracy. Unlike other approaches we mainly consider algorithmic changes to stay as much as possible independent of platform and programming language. The final model achieves an approximately 60 times faster training and a 500 times faster prediction, while the accuracy is only marginally decreased by roughly 1 %.

Ensemble Methods for Classification of Physical Activities from Wrist Accelerometry.

PubMed

Chowdhury, Alok Kumar; Tjondronegoro, Dian; Chandran, Vinod; Trost, Stewart G

2017-09-01

To investigate whether the use of ensemble learning algorithms improve physical activity recognition accuracy compared to the single classifier algorithms, and to compare the classification accuracy achieved by three conventional ensemble machine learning methods (bagging, boosting, random forest) and a custom ensemble model comprising four algorithms commonly used for activity recognition (binary decision tree, k nearest neighbor, support vector machine, and neural network). The study used three independent data sets that included wrist-worn accelerometer data. For each data set, a four-step classification framework consisting of data preprocessing, feature extraction, normalization and feature selection, and classifier training and testing was implemented. For the custom ensemble, decisions from the single classifiers were aggregated using three decision fusion methods: weighted majority vote, naïve Bayes combination, and behavior knowledge space combination. Classifiers were cross-validated using leave-one subject out cross-validation and compared on the basis of average F1 scores. In all three data sets, ensemble learning methods consistently outperformed the individual classifiers. Among the conventional ensemble methods, random forest models provided consistently high activity recognition; however, the custom ensemble model using weighted majority voting demonstrated the highest classification accuracy in two of the three data sets. Combining multiple individual classifiers using conventional or custom ensemble learning methods can improve activity recognition accuracy from wrist-worn accelerometer data.

RandomForest4Life: a Random Forest for predicting ALS disease progression.

PubMed

Hothorn, Torsten; Jung, Hans H

2014-09-01

We describe a method for predicting disease progression in amyotrophic lateral sclerosis (ALS) patients. The method was developed as a submission to the DREAM Phil Bowen ALS Prediction Prize4Life Challenge of summer 2012. Based on repeated patient examinations over a three- month period, we used a random forest algorithm to predict future disease progression. The procedure was set up and internally evaluated using data from 1197 ALS patients. External validation by an expert jury was based on undisclosed information of an additional 625 patients; all patient data were obtained from the PRO-ACT database. In terms of prediction accuracy, the approach described here ranked third best. Our interpretation of the prediction model confirmed previous reports suggesting that past disease progression is a strong predictor of future disease progression measured on the ALS functional rating scale (ALSFRS). We also found that larger variability in initial ALSFRS scores is linked to faster future disease progression. The results reported here furthermore suggested that approaches taking the multidimensionality of the ALSFRS into account promise some potential for improved ALS disease prediction.

PET-CT image fusion using random forest and à-trous wavelet transform.

PubMed

Seal, Ayan; Bhattacharjee, Debotosh; Nasipuri, Mita; Rodríguez-Esparragón, Dionisio; Menasalvas, Ernestina; Gonzalo-Martin, Consuelo

2018-03-01

New image fusion rules for multimodal medical images are proposed in this work. Image fusion rules are defined by random forest learning algorithm and a translation-invariant à-trous wavelet transform (AWT). The proposed method is threefold. First, source images are decomposed into approximation and detail coefficients using AWT. Second, random forest is used to choose pixels from the approximation and detail coefficients for forming the approximation and detail coefficients of the fused image. Lastly, inverse AWT is applied to reconstruct fused image. All experiments have been performed on 198 slices of both computed tomography and positron emission tomography images of a patient. A traditional fusion method based on Mallat wavelet transform has also been implemented on these slices. A new image fusion performance measure along with 4 existing measures has been presented, which helps to compare the performance of 2 pixel level fusion methods. The experimental results clearly indicate that the proposed method outperforms the traditional method in terms of visual and quantitative qualities and the new measure is meaningful. Copyright © 2017 John Wiley & Sons, Ltd.

Random Forest as a Predictive Analytics Alternative to Regression in Institutional Research

ERIC Educational Resources Information Center

He, Lingjun; Levine, Richard A.; Fan, Juanjuan; Beemer, Joshua; Stronach, Jeanne

2018-01-01

In institutional research, modern data mining approaches are seldom considered to address predictive analytics problems. The goal of this paper is to highlight the advantages of tree-based machine learning algorithms over classic (logistic) regression methods for data-informed decision making in higher education problems, and stress the success of…

Can machine-learning improve cardiovascular risk prediction using routine clinical data?

PubMed Central

Kai, Joe; Garibaldi, Jonathan M.; Qureshi, Nadeem

2017-01-01

Background Current approaches to predict cardiovascular risk fail to identify many people who would benefit from preventive treatment, while others receive unnecessary intervention. Machine-learning offers opportunity to improve accuracy by exploiting complex interactions between risk factors. We assessed whether machine-learning can improve cardiovascular risk prediction. Methods Prospective cohort study using routine clinical data of 378,256 patients from UK family practices, free from cardiovascular disease at outset. Four machine-learning algorithms (random forest, logistic regression, gradient boosting machines, neural networks) were compared to an established algorithm (American College of Cardiology guidelines) to predict first cardiovascular event over 10-years. Predictive accuracy was assessed by area under the ‘receiver operating curve’ (AUC); and sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV) to predict 7.5% cardiovascular risk (threshold for initiating statins). Findings 24,970 incident cardiovascular events (6.6%) occurred. Compared to the established risk prediction algorithm (AUC 0.728, 95% CI 0.723–0.735), machine-learning algorithms improved prediction: random forest +1.7% (AUC 0.745, 95% CI 0.739–0.750), logistic regression +3.2% (AUC 0.760, 95% CI 0.755–0.766), gradient boosting +3.3% (AUC 0.761, 95% CI 0.755–0.766), neural networks +3.6% (AUC 0.764, 95% CI 0.759–0.769). The highest achieving (neural networks) algorithm predicted 4,998/7,404 cases (sensitivity 67.5%, PPV 18.4%) and 53,458/75,585 non-cases (specificity 70.7%, NPV 95.7%), correctly predicting 355 (+7.6%) more patients who developed cardiovascular disease compared to the established algorithm. Conclusions Machine-learning significantly improves accuracy of cardiovascular risk prediction, increasing the number of patients identified who could benefit from preventive treatment, while avoiding unnecessary treatment of others. PMID:28376093

Can machine-learning improve cardiovascular risk prediction using routine clinical data?

PubMed

Weng, Stephen F; Reps, Jenna; Kai, Joe; Garibaldi, Jonathan M; Qureshi, Nadeem

2017-01-01

Current approaches to predict cardiovascular risk fail to identify many people who would benefit from preventive treatment, while others receive unnecessary intervention. Machine-learning offers opportunity to improve accuracy by exploiting complex interactions between risk factors. We assessed whether machine-learning can improve cardiovascular risk prediction. Prospective cohort study using routine clinical data of 378,256 patients from UK family practices, free from cardiovascular disease at outset. Four machine-learning algorithms (random forest, logistic regression, gradient boosting machines, neural networks) were compared to an established algorithm (American College of Cardiology guidelines) to predict first cardiovascular event over 10-years. Predictive accuracy was assessed by area under the 'receiver operating curve' (AUC); and sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV) to predict 7.5% cardiovascular risk (threshold for initiating statins). 24,970 incident cardiovascular events (6.6%) occurred. Compared to the established risk prediction algorithm (AUC 0.728, 95% CI 0.723-0.735), machine-learning algorithms improved prediction: random forest +1.7% (AUC 0.745, 95% CI 0.739-0.750), logistic regression +3.2% (AUC 0.760, 95% CI 0.755-0.766), gradient boosting +3.3% (AUC 0.761, 95% CI 0.755-0.766), neural networks +3.6% (AUC 0.764, 95% CI 0.759-0.769). The highest achieving (neural networks) algorithm predicted 4,998/7,404 cases (sensitivity 67.5%, PPV 18.4%) and 53,458/75,585 non-cases (specificity 70.7%, NPV 95.7%), correctly predicting 355 (+7.6%) more patients who developed cardiovascular disease compared to the established algorithm. Machine-learning significantly improves accuracy of cardiovascular risk prediction, increasing the number of patients identified who could benefit from preventive treatment, while avoiding unnecessary treatment of others.

Minimizing effects of methodological decisions on interpretation and prediction in species distribution studies: An example with background selection

USGS Publications Warehouse

Jarnevich, Catherine S.; Talbert, Marian; Morisette, Jeffrey T.; Aldridge, Cameron L.; Brown, Cynthia; Kumar, Sunil; Manier, Daniel; Talbert, Colin; Holcombe, Tracy R.

2017-01-01

Evaluating the conditions where a species can persist is an important question in ecology both to understand tolerances of organisms and to predict distributions across landscapes. Presence data combined with background or pseudo-absence locations are commonly used with species distribution modeling to develop these relationships. However, there is not a standard method to generate background or pseudo-absence locations, and method choice affects model outcomes. We evaluated combinations of both model algorithms (simple and complex generalized linear models, multivariate adaptive regression splines, Maxent, boosted regression trees, and random forest) and background methods (random, minimum convex polygon, and continuous and binary kernel density estimator (KDE)) to assess the sensitivity of model outcomes to choices made. We evaluated six questions related to model results, including five beyond the common comparison of model accuracy assessment metrics (biological interpretability of response curves, cross-validation robustness, independent data accuracy and robustness, and prediction consistency). For our case study with cheatgrass in the western US, random forest was least sensitive to background choice and the binary KDE method was least sensitive to model algorithm choice. While this outcome may not hold for other locations or species, the methods we used can be implemented to help determine appropriate methodologies for particular research questions.

Disaggregating Census Data for Population Mapping Using Random Forests with Remotely-Sensed and Ancillary Data

PubMed Central

Stevens, Forrest R.; Gaughan, Andrea E.; Linard, Catherine; Tatem, Andrew J.

2015-01-01

High resolution, contemporary data on human population distributions are vital for measuring impacts of population growth, monitoring human-environment interactions and for planning and policy development. Many methods are used to disaggregate census data and predict population densities for finer scale, gridded population data sets. We present a new semi-automated dasymetric modeling approach that incorporates detailed census and ancillary data in a flexible, “Random Forest” estimation technique. We outline the combination of widely available, remotely-sensed and geospatial data that contribute to the modeled dasymetric weights and then use the Random Forest model to generate a gridded prediction of population density at ~100 m spatial resolution. This prediction layer is then used as the weighting surface to perform dasymetric redistribution of the census counts at a country level. As a case study we compare the new algorithm and its products for three countries (Vietnam, Cambodia, and Kenya) with other common gridded population data production methodologies. We discuss the advantages of the new method and increases over the accuracy and flexibility of those previous approaches. Finally, we outline how this algorithm will be extended to provide freely-available gridded population data sets for Africa, Asia and Latin America. PMID:25689585

Patch forest: a hybrid framework of random forest and patch-based segmentation

NASA Astrophysics Data System (ADS)

Xie, Zhongliu; Gillies, Duncan

2016-03-01

The development of an accurate, robust and fast segmentation algorithm has long been a research focus in medical computer vision. State-of-the-art practices often involve non-rigidly registering a target image with a set of training atlases for label propagation over the target space to perform segmentation, a.k.a. multi-atlas label propagation (MALP). In recent years, the patch-based segmentation (PBS) framework has gained wide attention due to its advantage of relaxing the strict voxel-to-voxel correspondence to a series of pair-wise patch comparisons for contextual pattern matching. Despite a high accuracy reported in many scenarios, computational efficiency has consistently been a major obstacle for both approaches. Inspired by recent work on random forest, in this paper we propose a patch forest approach, which by equipping the conventional PBS with a fast patch search engine, is able to boost segmentation speed significantly while retaining an equal level of accuracy. In addition, a fast forest training mechanism is also proposed, with the use of a dynamic grid framework to efficiently approximate data compactness computation and a 3D integral image technique for fast box feature retrieval.

Unsupervised detection and removal of muscle artifacts from scalp EEG recordings using canonical correlation analysis, wavelets and random forests.

PubMed

Anastasiadou, Maria N; Christodoulakis, Manolis; Papathanasiou, Eleftherios S; Papacostas, Savvas S; Mitsis, Georgios D

2017-09-01

This paper proposes supervised and unsupervised algorithms for automatic muscle artifact detection and removal from long-term EEG recordings, which combine canonical correlation analysis (CCA) and wavelets with random forests (RF). The proposed algorithms first perform CCA and continuous wavelet transform of the canonical components to generate a number of features which include component autocorrelation values and wavelet coefficient magnitude values. A subset of the most important features is subsequently selected using RF and labelled observations (supervised case) or synthetic data constructed from the original observations (unsupervised case). The proposed algorithms are evaluated using realistic simulation data as well as 30min epochs of non-invasive EEG recordings obtained from ten patients with epilepsy. We assessed the performance of the proposed algorithms using classification performance and goodness-of-fit values for noisy and noise-free signal windows. In the simulation study, where the ground truth was known, the proposed algorithms yielded almost perfect performance. In the case of experimental data, where expert marking was performed, the results suggest that both the supervised and unsupervised algorithm versions were able to remove artifacts without affecting noise-free channels considerably, outperforming standard CCA, independent component analysis (ICA) and Lagged Auto-Mutual Information Clustering (LAMIC). The proposed algorithms achieved excellent performance for both simulation and experimental data. Importantly, for the first time to our knowledge, we were able to perform entirely unsupervised artifact removal, i.e. without using already marked noisy data segments, achieving performance that is comparable to the supervised case. Overall, the results suggest that the proposed algorithms yield significant future potential for improving EEG signal quality in research or clinical settings without the need for marking by expert neurophysiologists, EMG signal recording and user visual inspection. Copyright © 2017 International Federation of Clinical Neurophysiology. Published by Elsevier B.V. All rights reserved.

Automatic medical image annotation and keyword-based image retrieval using relevance feedback.

PubMed

Ko, Byoung Chul; Lee, JiHyeon; Nam, Jae-Yeal

2012-08-01

This paper presents novel multiple keywords annotation for medical images, keyword-based medical image retrieval, and relevance feedback method for image retrieval for enhancing image retrieval performance. For semantic keyword annotation, this study proposes a novel medical image classification method combining local wavelet-based center symmetric-local binary patterns with random forests. For keyword-based image retrieval, our retrieval system use the confidence score that is assigned to each annotated keyword by combining probabilities of random forests with predefined body relation graph. To overcome the limitation of keyword-based image retrieval, we combine our image retrieval system with relevance feedback mechanism based on visual feature and pattern classifier. Compared with other annotation and relevance feedback algorithms, the proposed method shows both improved annotation performance and accurate retrieval results.

Evaluating the Effectiveness of Flood Control Strategies in Contrasting Urban Watersheds and Implications for Houston's Future Flood Vulnerability

NASA Astrophysics Data System (ADS)

Ganguly, S.; Kumar, U.; Nemani, R. R.; Kalia, S.; Michaelis, A.

2016-12-01

In this work, we use a Fully Constrained Least Squares Subpixel Learning Algorithm to unmix global WELD (Web Enabled Landsat Data) to obtain fractions or abundances of substrate (S), vegetation (V) and dark objects (D) classes. Because of the sheer nature of data and compute needs, we leveraged the NASA Earth Exchange (NEX) high performance computing architecture to optimize and scale our algorithm for large-scale processing. Subsequently, the S-V-D abundance maps were characterized into 4 classes namely, forest, farmland, water and urban areas (with NPP-VIIRS - national polar orbiting partnership visible infrared imaging radiometer suite nighttime lights data) over California, USA using Random Forest classifier. Validation of these land cover maps with NLCD (National Land Cover Database) 2011 products and NAFD (North American Forest Dynamics) static forest cover maps showed that an overall classification accuracy of over 91% was achieved, which is a 6% improvement in unmixing based classification relative to per-pixel based classification. As such, abundance maps continue to offer an useful alternative to high-spatial resolution data derived classification maps for forest inventory analysis, multi-class mapping for eco-climatic models and applications, fast multi-temporal trend analysis and for societal and policy-relevant applications needed at the watershed scale.

Analysis of Machine Learning Techniques for Heart Failure Readmissions.

PubMed

Mortazavi, Bobak J; Downing, Nicholas S; Bucholz, Emily M; Dharmarajan, Kumar; Manhapra, Ajay; Li, Shu-Xia; Negahban, Sahand N; Krumholz, Harlan M

2016-11-01

The current ability to predict readmissions in patients with heart failure is modest at best. It is unclear whether machine learning techniques that address higher dimensional, nonlinear relationships among variables would enhance prediction. We sought to compare the effectiveness of several machine learning algorithms for predicting readmissions. Using data from the Telemonitoring to Improve Heart Failure Outcomes trial, we compared the effectiveness of random forests, boosting, random forests combined hierarchically with support vector machines or logistic regression (LR), and Poisson regression against traditional LR to predict 30- and 180-day all-cause readmissions and readmissions because of heart failure. We randomly selected 50% of patients for a derivation set, and a validation set comprised the remaining patients, validated using 100 bootstrapped iterations. We compared C statistics for discrimination and distributions of observed outcomes in risk deciles for predictive range. In 30-day all-cause readmission prediction, the best performing machine learning model, random forests, provided a 17.8% improvement over LR (mean C statistics, 0.628 and 0.533, respectively). For readmissions because of heart failure, boosting improved the C statistic by 24.9% over LR (mean C statistic 0.678 and 0.543, respectively). For 30-day all-cause readmission, the observed readmission rates in the lowest and highest deciles of predicted risk with random forests (7.8% and 26.2%, respectively) showed a much wider separation than LR (14.2% and 16.4%, respectively). Machine learning methods improved the prediction of readmission after hospitalization for heart failure compared with LR and provided the greatest predictive range in observed readmission rates. © 2016 American Heart Association, Inc.

Android Malware Classification Using K-Means Clustering Algorithm

NASA Astrophysics Data System (ADS)

Hamid, Isredza Rahmi A.; Syafiqah Khalid, Nur; Azma Abdullah, Nurul; Rahman, Nurul Hidayah Ab; Chai Wen, Chuah

2017-08-01

Malware was designed to gain access or damage a computer system without user notice. Besides, attacker exploits malware to commit crime or fraud. This paper proposed Android malware classification approach based on K-Means clustering algorithm. We evaluate the proposed model in terms of accuracy using machine learning algorithms. Two datasets were selected to demonstrate the practicing of K-Means clustering algorithms that are Virus Total and Malgenome dataset. We classify the Android malware into three clusters which are ransomware, scareware and goodware. Nine features were considered for each types of dataset such as Lock Detected, Text Detected, Text Score, Encryption Detected, Threat, Porn, Law, Copyright and Moneypak. We used IBM SPSS Statistic software for data classification and WEKA tools to evaluate the built cluster. The proposed K-Means clustering algorithm shows promising result with high accuracy when tested using Random Forest algorithm.

Foliar and woody materials discriminated using terrestrial LiDAR in a mixed natural forest

NASA Astrophysics Data System (ADS)

Zhu, Xi; Skidmore, Andrew K.; Darvishzadeh, Roshanak; Niemann, K. Olaf; Liu, Jing; Shi, Yifang; Wang, Tiejun

2018-02-01

Separation of foliar and woody materials using remotely sensed data is crucial for the accurate estimation of leaf area index (LAI) and woody biomass across forest stands. In this paper, we present a new method to accurately separate foliar and woody materials using terrestrial LiDAR point clouds obtained from ten test sites in a mixed forest in Bavarian Forest National Park, Germany. Firstly, we applied and compared an adaptive radius near-neighbor search algorithm with a fixed radius near-neighbor search method in order to obtain both radiometric and geometric features derived from terrestrial LiDAR point clouds. Secondly, we used a random forest machine learning algorithm to classify foliar and woody materials and examined the impact of understory and slope on the classification accuracy. An average overall accuracy of 84.4% (Kappa = 0.75) was achieved across all experimental plots. The adaptive radius near-neighbor search method outperformed the fixed radius near-neighbor search method. The classification accuracy was significantly higher when the combination of both radiometric and geometric features was utilized. The analysis showed that increasing slope and understory coverage had a significant negative effect on the overall classification accuracy. Our results suggest that the utilization of the adaptive radius near-neighbor search method coupling both radiometric and geometric features has the potential to accurately discriminate foliar and woody materials from terrestrial LiDAR data in a mixed natural forest.

Detection of dead standing Eucalyptus camaldulensis without tree delineation for managing biodiversity in native Australian forest

NASA Astrophysics Data System (ADS)

Miltiadou, Milto; Campbell, Neil D. F.; Gonzalez Aracil, Susana; Brown, Tony; Grant, Michael G.

2018-05-01

In Australia, many birds and arboreal animals use hollows for shelters, but studies predict shortage of hollows in near future. Aged dead trees are more likely to contain hollows and therefore automated detection of them plays a substantial role in preserving biodiversity and consequently maintaining a resilient ecosystem. For this purpose full-waveform LiDAR data were acquired from a native Eucalypt forest in Southern Australia. The structure of the forest significantly varies in terms of tree density, age and height. Additionally, Eucalyptus camaldulensis have multiple trunk splits making tree delineation very challenging. For that reason, this paper investigates automated detection of dead standing Eucalyptus camaldulensis without tree delineation. It also presents the new feature of the open source software DASOS, which extracts features for 3D object detection in voxelised FW LiDAR. A random forest classifier, a weighted-distance KNN algorithm and a seed growth algorithm are used to create a 2D probabilistic field and to then predict potential positions of dead trees. It is shown that tree health assessment is possible without tree delineation but since it is a new research directions there are many improvements to be made.

Benchmarking protein classification algorithms via supervised cross-validation.

PubMed

Kertész-Farkas, Attila; Dhir, Somdutta; Sonego, Paolo; Pacurar, Mircea; Netoteia, Sergiu; Nijveen, Harm; Kuzniar, Arnold; Leunissen, Jack A M; Kocsor, András; Pongor, Sándor

2008-04-24

Development and testing of protein classification algorithms are hampered by the fact that the protein universe is characterized by groups vastly different in the number of members, in average protein size, similarity within group, etc. Datasets based on traditional cross-validation (k-fold, leave-one-out, etc.) may not give reliable estimates on how an algorithm will generalize to novel, distantly related subtypes of the known protein classes. Supervised cross-validation, i.e., selection of test and train sets according to the known subtypes within a database has been successfully used earlier in conjunction with the SCOP database. Our goal was to extend this principle to other databases and to design standardized benchmark datasets for protein classification. Hierarchical classification trees of protein categories provide a simple and general framework for designing supervised cross-validation strategies for protein classification. Benchmark datasets can be designed at various levels of the concept hierarchy using a simple graph-theoretic distance. A combination of supervised and random sampling was selected to construct reduced size model datasets, suitable for algorithm comparison. Over 3000 new classification tasks were added to our recently established protein classification benchmark collection that currently includes protein sequence (including protein domains and entire proteins), protein structure and reading frame DNA sequence data. We carried out an extensive evaluation based on various machine-learning algorithms such as nearest neighbor, support vector machines, artificial neural networks, random forests and logistic regression, used in conjunction with comparison algorithms, BLAST, Smith-Waterman, Needleman-Wunsch, as well as 3D comparison methods DALI and PRIDE. The resulting datasets provide lower, and in our opinion more realistic estimates of the classifier performance than do random cross-validation schemes. A combination of supervised and random sampling was used to construct model datasets, suitable for algorithm comparison.

Machine Learning Algorithm Predicts Cardiac Resynchronization Therapy Outcomes: Lessons From the COMPANION Trial.

PubMed

Kalscheur, Matthew M; Kipp, Ryan T; Tattersall, Matthew C; Mei, Chaoqun; Buhr, Kevin A; DeMets, David L; Field, Michael E; Eckhardt, Lee L; Page, C David

2018-01-01

Cardiac resynchronization therapy (CRT) reduces morbidity and mortality in heart failure patients with reduced left ventricular function and intraventricular conduction delay. However, individual outcomes vary significantly. This study sought to use a machine learning algorithm to develop a model to predict outcomes after CRT. Models were developed with machine learning algorithms to predict all-cause mortality or heart failure hospitalization at 12 months post-CRT in the COMPANION trial (Comparison of Medical Therapy, Pacing, and Defibrillation in Heart Failure). The best performing model was developed with the random forest algorithm. The ability of this model to predict all-cause mortality or heart failure hospitalization and all-cause mortality alone was compared with discrimination obtained using a combination of bundle branch block morphology and QRS duration. In the 595 patients with CRT-defibrillator in the COMPANION trial, 105 deaths occurred (median follow-up, 15.7 months). The survival difference across subgroups differentiated by bundle branch block morphology and QRS duration did not reach significance ( P =0.08). The random forest model produced quartiles of patients with an 8-fold difference in survival between those with the highest and lowest predicted probability for events (hazard ratio, 7.96; P <0.0001). The model also discriminated the risk of the composite end point of all-cause mortality or heart failure hospitalization better than subgroups based on bundle branch block morphology and QRS duration. In the COMPANION trial, a machine learning algorithm produced a model that predicted clinical outcomes after CRT. Applied before device implant, this model may better differentiate outcomes over current clinical discriminators and improve shared decision-making with patients. © 2018 American Heart Association, Inc.

A new tool for supervised classification of satellite images available on web servers: Google Maps as a case study

NASA Astrophysics Data System (ADS)

García-Flores, Agustín.; Paz-Gallardo, Abel; Plaza, Antonio; Li, Jun

2016-10-01

This paper describes a new web platform dedicated to the classification of satellite images called Hypergim. The current implementation of this platform enables users to perform classification of satellite images from any part of the world thanks to the worldwide maps provided by Google Maps. To perform this classification, Hypergim uses unsupervised algorithms like Isodata and K-means. Here, we present an extension of the original platform in which we adapt Hypergim in order to use supervised algorithms to improve the classification results. This involves a significant modification of the user interface, providing the user with a way to obtain samples of classes present in the images to use in the training phase of the classification process. Another main goal of this development is to improve the runtime of the image classification process. To achieve this goal, we use a parallel implementation of the Random Forest classification algorithm. This implementation is a modification of the well-known CURFIL software package. The use of this type of algorithms to perform image classification is widespread today thanks to its precision and ease of training. The actual implementation of Random Forest was developed using CUDA platform, which enables us to exploit the potential of several models of NVIDIA graphics processing units using them to execute general purpose computing tasks as image classification algorithms. As well as CUDA, we use other parallel libraries as Intel Boost, taking advantage of the multithreading capabilities of modern CPUs. To ensure the best possible results, the platform is deployed in a cluster of commodity graphics processing units (GPUs), so that multiple users can use the tool in a concurrent way. The experimental results indicate that this new algorithm widely outperform the previous unsupervised algorithms implemented in Hypergim, both in runtime as well as precision of the actual classification of the images.

An assessment of the effectiveness of a random forest classifier for land-cover classification

NASA Astrophysics Data System (ADS)

Rodriguez-Galiano, V. F.; Ghimire, B.; Rogan, J.; Chica-Olmo, M.; Rigol-Sanchez, J. P.

2012-01-01

Land cover monitoring using remotely sensed data requires robust classification methods which allow for the accurate mapping of complex land cover and land use categories. Random forest (RF) is a powerful machine learning classifier that is relatively unknown in land remote sensing and has not been evaluated thoroughly by the remote sensing community compared to more conventional pattern recognition techniques. Key advantages of RF include: their non-parametric nature; high classification accuracy; and capability to determine variable importance. However, the split rules for classification are unknown, therefore RF can be considered to be black box type classifier. RF provides an algorithm for estimating missing values; and flexibility to perform several types of data analysis, including regression, classification, survival analysis, and unsupervised learning. In this paper, the performance of the RF classifier for land cover classification of a complex area is explored. Evaluation was based on several criteria: mapping accuracy, sensitivity to data set size and noise. Landsat-5 Thematic Mapper data captured in European spring and summer were used with auxiliary variables derived from a digital terrain model to classify 14 different land categories in the south of Spain. Results show that the RF algorithm yields accurate land cover classifications, with 92% overall accuracy and a Kappa index of 0.92. RF is robust to training data reduction and noise because significant differences in kappa values were only observed for data reduction and noise addition values greater than 50 and 20%, respectively. Additionally, variables that RF identified as most important for classifying land cover coincided with expectations. A McNemar test indicates an overall better performance of the random forest model over a single decision tree at the 0.00001 significance level.

Retinal layer segmentation of macular OCT images using boundary classification

PubMed Central

Lang, Andrew; Carass, Aaron; Hauser, Matthew; Sotirchos, Elias S.; Calabresi, Peter A.; Ying, Howard S.; Prince, Jerry L.

2013-01-01

Optical coherence tomography (OCT) has proven to be an essential imaging modality for ophthalmology and is proving to be very important in neurology. OCT enables high resolution imaging of the retina, both at the optic nerve head and the macula. Macular retinal layer thicknesses provide useful diagnostic information and have been shown to correlate well with measures of disease severity in several diseases. Since manual segmentation of these layers is time consuming and prone to bias, automatic segmentation methods are critical for full utilization of this technology. In this work, we build a random forest classifier to segment eight retinal layers in macular cube images acquired by OCT. The random forest classifier learns the boundary pixels between layers, producing an accurate probability map for each boundary, which is then processed to finalize the boundaries. Using this algorithm, we can accurately segment the entire retina contained in the macular cube to an accuracy of at least 4.3 microns for any of the nine boundaries. Experiments were carried out on both healthy and multiple sclerosis subjects, with no difference in the accuracy of our algorithm found between the groups. PMID:23847738

PPCM: Combing multiple classifiers to improve protein-protein interaction prediction

DOE PAGES

Yao, Jianzhuang; Guo, Hong; Yang, Xiaohan

2015-08-01

Determining protein-protein interaction (PPI) in biological systems is of considerable importance, and prediction of PPI has become a popular research area. Although different classifiers have been developed for PPI prediction, no single classifier seems to be able to predict PPI with high confidence. We postulated that by combining individual classifiers the accuracy of PPI prediction could be improved. We developed a method called protein-protein interaction prediction classifiers merger (PPCM), and this method combines output from two PPI prediction tools, GO2PPI and Phyloprof, using Random Forests algorithm. The performance of PPCM was tested by area under the curve (AUC) using anmore » assembled Gold Standard database that contains both positive and negative PPI pairs. Our AUC test showed that PPCM significantly improved the PPI prediction accuracy over the corresponding individual classifiers. We found that additional classifiers incorporated into PPCM could lead to further improvement in the PPI prediction accuracy. Furthermore, cross species PPCM could achieve competitive and even better prediction accuracy compared to the single species PPCM. This study established a robust pipeline for PPI prediction by integrating multiple classifiers using Random Forests algorithm. Ultimately, this pipeline will be useful for predicting PPI in nonmodel species.« less

Summer and winter habitat suitability of Marco Polo argali in southeastern Tajikistan: A modeling approach.

PubMed

Salas, Eric Ariel L; Valdez, Raul; Michel, Stefan

2017-11-01

We modeled summer and winter habitat suitability of Marco Polo argali in the Pamir Mountains in southeastern Tajikistan using these statistical algorithms: Generalized Linear Model, Random Forest, Boosted Regression Tree, Maxent, and Multivariate Adaptive Regression Splines. Using sheep occurrence data collected from 2009 to 2015 and a set of selected habitat predictors, we produced summer and winter habitat suitability maps and determined the important habitat suitability predictors for both seasons. Our results demonstrated that argali selected proximity to riparian areas and greenness as the two most relevant variables for summer, and the degree of slope (gentler slopes between 0° to 20°) and Landsat temperature band for winter. The terrain roughness was also among the most important variables in summer and winter models. Aspect was only significant for winter habitat, with argali preferring south-facing mountain slopes. We evaluated various measures of model performance such as the Area Under the Curve (AUC) and the True Skill Statistic (TSS). Comparing the five algorithms, the AUC scored highest for Boosted Regression Tree in summer (AUC = 0.94) and winter model runs (AUC = 0.94). In contrast, Random Forest underperformed in both model runs.

Predicting adaptive phenotypes from multilocus genotypes in Sitka spruce (Picea sitchensis) using random forest.

PubMed

Holliday, Jason A; Wang, Tongli; Aitken, Sally

2012-09-01

Climate is the primary driver of the distribution of tree species worldwide, and the potential for adaptive evolution will be an important factor determining the response of forests to anthropogenic climate change. Although association mapping has the potential to improve our understanding of the genomic underpinnings of climatically relevant traits, the utility of adaptive polymorphisms uncovered by such studies would be greatly enhanced by the development of integrated models that account for the phenotypic effects of multiple single-nucleotide polymorphisms (SNPs) and their interactions simultaneously. We previously reported the results of association mapping in the widespread conifer Sitka spruce (Picea sitchensis). In the current study we used the recursive partitioning algorithm 'Random Forest' to identify optimized combinations of SNPs to predict adaptive phenotypes. After adjusting for population structure, we were able to explain 37% and 30% of the phenotypic variation, respectively, in two locally adaptive traits--autumn budset timing and cold hardiness. For each trait, the leading five SNPs captured much of the phenotypic variation. To determine the role of epistasis in shaping these phenotypes, we also used a novel approach to quantify the strength and direction of pairwise interactions between SNPs and found such interactions to be common. Our results demonstrate the power of Random Forest to identify subsets of markers that are most important to climatic adaptation, and suggest that interactions among these loci may be widespread.

Intra-and-Inter Species Biomass Prediction in a Plantation Forest: Testing the Utility of High Spatial Resolution Spaceborne Multispectral RapidEye Sensor and Advanced Machine Learning Algorithms

PubMed Central

Dube, Timothy; Mutanga, Onisimo; Adam, Elhadi; Ismail, Riyad

2014-01-01

The quantification of aboveground biomass using remote sensing is critical for better understanding the role of forests in carbon sequestration and for informed sustainable management. Although remote sensing techniques have been proven useful in assessing forest biomass in general, more is required to investigate their capabilities in predicting intra-and-inter species biomass which are mainly characterised by non-linear relationships. In this study, we tested two machine learning algorithms, Stochastic Gradient Boosting (SGB) and Random Forest (RF) regression trees to predict intra-and-inter species biomass using high resolution RapidEye reflectance bands as well as the derived vegetation indices in a commercial plantation. The results showed that the SGB algorithm yielded the best performance for intra-and-inter species biomass prediction; using all the predictor variables as well as based on the most important selected variables. For example using the most important variables the algorithm produced an R2 of 0.80 and RMSE of 16.93 t·ha−1 for E. grandis; R2 of 0.79, RMSE of 17.27 t·ha−1 for P. taeda and R2 of 0.61, RMSE of 43.39 t·ha−1 for the combined species data sets. Comparatively, RF yielded plausible results only for E. dunii (R2 of 0.79; RMSE of 7.18 t·ha−1). We demonstrated that although the two statistical methods were able to predict biomass accurately, RF produced weaker results as compared to SGB when applied to combined species dataset. The result underscores the relevance of stochastic models in predicting biomass drawn from different species and genera using the new generation high resolution RapidEye sensor with strategically positioned bands. PMID:25140631

Comparison of classification algorithms for various methods of preprocessing radar images of the MSTAR base

NASA Astrophysics Data System (ADS)

Borodinov, A. A.; Myasnikov, V. V.

2018-04-01

The present work is devoted to comparing the accuracy of the known qualification algorithms in the task of recognizing local objects on radar images for various image preprocessing methods. Preprocessing involves speckle noise filtering and normalization of the object orientation in the image by the method of image moments and by a method based on the Hough transform. In comparison, the following classification algorithms are used: Decision tree; Support vector machine, AdaBoost, Random forest. The principal component analysis is used to reduce the dimension. The research is carried out on the objects from the base of radar images MSTAR. The paper presents the results of the conducted studies.

Recognition physical activities with optimal number of wearable sensors using data mining algorithms and deep belief network.

PubMed

Al-Fatlawi, Ali H; Fatlawi, Hayder K; Sai Ho Ling

2017-07-01

Daily physical activities monitoring is benefiting the health care field in several ways, in particular with the development of the wearable sensors. This paper adopts effective ways to calculate the optimal number of the necessary sensors and to build a reliable and a high accuracy monitoring system. Three data mining algorithms, namely Decision Tree, Random Forest and PART Algorithm, have been applied for the sensors selection process. Furthermore, the deep belief network (DBN) has been investigated to recognise 33 physical activities effectively. The results indicated that the proposed method is reliable with an overall accuracy of 96.52% and the number of sensors is minimised from nine to six sensors.

Enhancing Deep-Water Low-Resolution Gridded Bathymetry Using Single Image Super-Resolution

NASA Astrophysics Data System (ADS)

Elmore, P. A.; Nock, K.; Bonanno, D.; Smith, L.; Ferrini, V. L.; Petry, F. E.

2017-12-01

We present research to employ single-image super-resolution (SISR) algorithms to enhance knowledge of the seafloor using the 1-minute GEBCO 2014 grid when 100m grids from high-resolution sonar systems are available for training. Our numerical upscaling experiments of x15 upscaling of the GEBCO grid along three areas of the Eastern Pacific Ocean along mid-ocean ridge systems where we have these 100m gridded bathymetry data sets, which we accept as ground-truth. We show that four SISR algorithms can enhance this low-resolution knowledge of bathymetry versus bicubic or Spline-In-Tension algorithms through upscaling under these conditions: 1) rough topography is present in both training and testing areas and 2) the range of depths and features in the training area contains the range of depths in the enhancement area. We quantitatively judged successful SISR enhancement versus bicubic interpolation when Student's hypothesis testing show significant improvement of the root-mean squared error (RMSE) between upscaled bathymetry and 100m gridded ground-truth bathymetry at p < 0.05. In addition, we found evidence that random forest based SISR methods may provide more robust enhancements versus non-forest based SISR algorithms.

Recognizing pedestrian's unsafe behaviors in far-infrared imagery at night

NASA Astrophysics Data System (ADS)

Lee, Eun Ju; Ko, Byoung Chul; Nam, Jae-Yeal

2016-05-01

Pedestrian behavior recognition is important work for early accident prevention in advanced driver assistance system (ADAS). In particular, because most pedestrian-vehicle crashes are occurred from late of night to early of dawn, our study focus on recognizing unsafe behavior of pedestrians using thermal image captured from moving vehicle at night. For recognizing unsafe behavior, this study uses convolutional neural network (CNN) which shows high quality of recognition performance. However, because traditional CNN requires the very expensive training time and memory, we design the light CNN consisted of two convolutional layers and two subsampling layers for real-time processing of vehicle applications. In addition, we combine light CNN with boosted random forest (Boosted RF) classifier so that the output of CNN is not fully connected with the classifier but randomly connected with Boosted random forest. We named this CNN as randomly connected CNN (RC-CNN). The proposed method was successfully applied to the pedestrian unsafe behavior (PUB) dataset captured from far-infrared camera at night and its behavior recognition accuracy is confirmed to be higher than that of some algorithms related to CNNs, with a shorter processing time.

Bilayer segmentation of webcam videos using tree-based classifiers.

PubMed

Yin, Pei; Criminisi, Antonio; Winn, John; Essa, Irfan

2011-01-01

This paper presents an automatic segmentation algorithm for video frames captured by a (monocular) webcam that closely approximates depth segmentation from a stereo camera. The frames are segmented into foreground and background layers that comprise a subject (participant) and other objects and individuals. The algorithm produces correct segmentations even in the presence of large background motion with a nearly stationary foreground. This research makes three key contributions: First, we introduce a novel motion representation, referred to as "motons," inspired by research in object recognition. Second, we propose estimating the segmentation likelihood from the spatial context of motion. The estimation is efficiently learned by random forests. Third, we introduce a general taxonomy of tree-based classifiers that facilitates both theoretical and experimental comparisons of several known classification algorithms and generates new ones. In our bilayer segmentation algorithm, diverse visual cues such as motion, motion context, color, contrast, and spatial priors are fused by means of a conditional random field (CRF) model. Segmentation is then achieved by binary min-cut. Experiments on many sequences of our videochat application demonstrate that our algorithm, which requires no initialization, is effective in a variety of scenes, and the segmentation results are comparable to those obtained by stereo systems.

The feasibility of using a universal Random Forest model to map tree height across different locations and vegetation types

NASA Astrophysics Data System (ADS)

Su, Y.; Guo, Q.; Jin, S.; Gao, S.; Hu, T.; Liu, J.; Xue, B. L.

2017-12-01

Tree height is an important forest structure parameter for understanding forest ecosystem and improving the accuracy of global carbon stock quantification. Light detection and ranging (LiDAR) can provide accurate tree height measurements, but its use in large-scale tree height mapping is limited by the spatial availability. Random Forest (RF) has been one of the most commonly used algorithms for mapping large-scale tree height through the fusion of LiDAR and other remotely sensed datasets. However, how the variances in vegetation types, geolocations and spatial scales of different study sites influence the RF results is still a question that needs to be addressed. In this study, we selected 16 study sites across four vegetation types in United States (U.S.) fully covered by airborne LiDAR data, and the area of each site was 100 km2. The LiDAR-derived canopy height models (CHMs) were used as the ground truth to train the RF algorithm to predict canopy height from other remotely sensed variables, such as Landsat TM imagery, terrain information and climate surfaces. To address the abovementioned question, 22 models were run under different combinations of vegetation types, geolocations and spatial scales. The results show that the RF model trained at one specific location or vegetation type cannot be used to predict tree height in other locations or vegetation types. However, by training the RF model using samples from all locations and vegetation types, a universal model can be achieved for predicting canopy height across different locations and vegetation types. Moreover, the number of training samples and the targeted spatial resolution of the canopy height product have noticeable influence on the RF prediction accuracy.

Field evaluation of a random forest activity classifier for wrist-worn accelerometer data.

PubMed

Pavey, Toby G; Gilson, Nicholas D; Gomersall, Sjaan R; Clark, Bronwyn; Trost, Stewart G

2017-01-01

Wrist-worn accelerometers are convenient to wear and associated with greater wear-time compliance. Previous work has generally relied on choreographed activity trials to train and test classification models. However, validity in free-living contexts is starting to emerge. Study aims were: (1) train and test a random forest activity classifier for wrist accelerometer data; and (2) determine if models trained on laboratory data perform well under free-living conditions. Twenty-one participants (mean age=27.6±6.2) completed seven lab-based activity trials and a 24h free-living trial (N=16). Participants wore a GENEActiv monitor on the non-dominant wrist. Classification models recognising four activity classes (sedentary, stationary+, walking, and running) were trained using time and frequency domain features extracted from 10-s non-overlapping windows. Model performance was evaluated using leave-one-out-cross-validation. Models were implemented using the randomForest package within R. Classifier accuracy during the 24h free living trial was evaluated by calculating agreement with concurrently worn activPAL monitors. Overall classification accuracy for the random forest algorithm was 92.7%. Recognition accuracy for sedentary, stationary+, walking, and running was 80.1%, 95.7%, 91.7%, and 93.7%, respectively for the laboratory protocol. Agreement with the activPAL data (stepping vs. non-stepping) during the 24h free-living trial was excellent and, on average, exceeded 90%. The ICC for stepping time was 0.92 (95% CI=0.75-0.97). However, sensitivity and positive predictive values were modest. Mean bias was 10.3min/d (95% LOA=-46.0 to 25.4min/d). The random forest classifier for wrist accelerometer data yielded accurate group-level predictions under controlled conditions, but was less accurate at identifying stepping verse non-stepping behaviour in free living conditions Future studies should conduct more rigorous field-based evaluations using observation as a criterion measure. Copyright © 2016 Sports Medicine Australia. Published by Elsevier Ltd. All rights reserved.

Pigmented skin lesion detection using random forest and wavelet-based texture

NASA Astrophysics Data System (ADS)

Hu, Ping; Yang, Tie-jun

2016-10-01

The incidence of cutaneous malignant melanoma, a disease of worldwide distribution and is the deadliest form of skin cancer, has been rapidly increasing over the last few decades. Because advanced cutaneous melanoma is still incurable, early detection is an important step toward a reduction in mortality. Dermoscopy photographs are commonly used in melanoma diagnosis and can capture detailed features of a lesion. A great variability exists in the visual appearance of pigmented skin lesions. Therefore, in order to minimize the diagnostic errors that result from the difficulty and subjectivity of visual interpretation, an automatic detection approach is required. The objectives of this paper were to propose a hybrid method using random forest and Gabor wavelet transformation to accurately differentiate which part belong to lesion area and the other is not in a dermoscopy photographs and analyze segmentation accuracy. A random forest classifier consisting of a set of decision trees was used for classification. Gabor wavelets transformation are the mathematical model of visual cortical cells of mammalian brain and an image can be decomposed into multiple scales and multiple orientations by using it. The Gabor function has been recognized as a very useful tool in texture analysis, due to its optimal localization properties in both spatial and frequency domain. Texture features based on Gabor wavelets transformation are found by the Gabor filtered image. Experiment results indicate the following: (1) the proposed algorithm based on random forest outperformed the-state-of-the-art in pigmented skin lesions detection (2) and the inclusion of Gabor wavelet transformation based texture features improved segmentation accuracy significantly.

Prediction of aquatic toxicity mode of action using linear discriminant and random forest models.

PubMed

Martin, Todd M; Grulke, Christopher M; Young, Douglas M; Russom, Christine L; Wang, Nina Y; Jackson, Crystal R; Barron, Mace G

2013-09-23

The ability to determine the mode of action (MOA) for a diverse group of chemicals is a critical part of ecological risk assessment and chemical regulation. However, existing MOA assignment approaches in ecotoxicology have been limited to a relatively few MOAs, have high uncertainty, or rely on professional judgment. In this study, machine based learning algorithms (linear discriminant analysis and random forest) were used to develop models for assigning aquatic toxicity MOA. These methods were selected since they have been shown to be able to correlate diverse data sets and provide an indication of the most important descriptors. A data set of MOA assignments for 924 chemicals was developed using a combination of high confidence assignments, international consensus classifications, ASTER (ASessment Tools for the Evaluation of Risk) predictions, and weight of evidence professional judgment based an assessment of structure and literature information. The overall data set was randomly divided into a training set (75%) and a validation set (25%) and then used to develop linear discriminant analysis (LDA) and random forest (RF) MOA assignment models. The LDA and RF models had high internal concordance and specificity and were able to produce overall prediction accuracies ranging from 84.5 to 87.7% for the validation set. These results demonstrate that computational chemistry approaches can be used to determine the acute toxicity MOAs across a large range of structures and mechanisms.

Modelling above Ground Biomass of Mangrove Forest Using SENTINEL-1 Imagery

NASA Astrophysics Data System (ADS)

Labadisos Argamosa, Reginald Jay; Conferido Blanco, Ariel; Balidoy Baloloy, Alvin; Gumbao Candido, Christian; Lovern Caboboy Dumalag, John Bart; Carandang Dimapilis, Lee, , Lady; Camero Paringit, Enrico

2018-04-01

Many studies have been conducted in the estimation of forest above ground biomass (AGB) using features from synthetic aperture radar (SAR). Specifically, L-band ALOS/PALSAR (wavelength 23 cm) data is often used. However, few studies have been made on the use of shorter wavelengths (e.g., C-band, 3.75 cm to 7.5 cm) for forest mapping especially in tropical forests since higher attenuation is observed for volumetric objects where energy propagated is absorbed. This study aims to model AGB estimates of mangrove forest using information derived from Sentinel-1 C-band SAR data. Combinations of polarisations (VV, VH), its derivatives, grey level co-occurrence matrix (GLCM), and its principal components were used as features for modelling AGB. Five models were tested with varying combinations of features; a) sigma nought polarisations and its derivatives; b) GLCM textures; c) the first five principal components; d) combination of models a-c; and e) the identified important features by Random Forest variable importance algorithm. Random Forest was used as regressor to compute for the AGB estimates to avoid over fitting caused by the introduction of too many features in the model. Model e obtained the highest r2 of 0.79 and an RMSE of 0.44 Mg using only four features, namely, σ°VH GLCM variance, σ°VH GLCM contrast, PC1, and PC2. This study shows that Sentinel-1 C-band SAR data could be used to produce acceptable AGB estimates in mangrove forest to compensate for the unavailability of longer wavelength SAR.

Random forests on Hadoop for genome-wide association studies of multivariate neuroimaging phenotypes

PubMed Central

2013-01-01

Motivation Multivariate quantitative traits arise naturally in recent neuroimaging genetics studies, in which both structural and functional variability of the human brain is measured non-invasively through techniques such as magnetic resonance imaging (MRI). There is growing interest in detecting genetic variants associated with such multivariate traits, especially in genome-wide studies. Random forests (RFs) classifiers, which are ensembles of decision trees, are amongst the best performing machine learning algorithms and have been successfully employed for the prioritisation of genetic variants in case-control studies. RFs can also be applied to produce gene rankings in association studies with multivariate quantitative traits, and to estimate genetic similarities measures that are predictive of the trait. However, in studies involving hundreds of thousands of SNPs and high-dimensional traits, a very large ensemble of trees must be inferred from the data in order to obtain reliable rankings, which makes the application of these algorithms computationally prohibitive. Results We have developed a parallel version of the RF algorithm for regression and genetic similarity learning tasks in large-scale population genetic association studies involving multivariate traits, called PaRFR (Parallel Random Forest Regression). Our implementation takes advantage of the MapReduce programming model and is deployed on Hadoop, an open-source software framework that supports data-intensive distributed applications. Notable speed-ups are obtained by introducing a distance-based criterion for node splitting in the tree estimation process. PaRFR has been applied to a genome-wide association study on Alzheimer's disease (AD) in which the quantitative trait consists of a high-dimensional neuroimaging phenotype describing longitudinal changes in the human brain structure. PaRFR provides a ranking of SNPs associated to this trait, and produces pair-wise measures of genetic proximity that can be directly compared to pair-wise measures of phenotypic proximity. Several known AD-related variants have been identified, including APOE4 and TOMM40. We also present experimental evidence supporting the hypothesis of a linear relationship between the number of top-ranked mutated states, or frequent mutation patterns, and an indicator of disease severity. Availability The Java codes are freely available at http://www2.imperial.ac.uk/~gmontana. PMID:24564704

Random forests on Hadoop for genome-wide association studies of multivariate neuroimaging phenotypes.

PubMed

Wang, Yue; Goh, Wilson; Wong, Limsoon; Montana, Giovanni

2013-01-01

Multivariate quantitative traits arise naturally in recent neuroimaging genetics studies, in which both structural and functional variability of the human brain is measured non-invasively through techniques such as magnetic resonance imaging (MRI). There is growing interest in detecting genetic variants associated with such multivariate traits, especially in genome-wide studies. Random forests (RFs) classifiers, which are ensembles of decision trees, are amongst the best performing machine learning algorithms and have been successfully employed for the prioritisation of genetic variants in case-control studies. RFs can also be applied to produce gene rankings in association studies with multivariate quantitative traits, and to estimate genetic similarities measures that are predictive of the trait. However, in studies involving hundreds of thousands of SNPs and high-dimensional traits, a very large ensemble of trees must be inferred from the data in order to obtain reliable rankings, which makes the application of these algorithms computationally prohibitive. We have developed a parallel version of the RF algorithm for regression and genetic similarity learning tasks in large-scale population genetic association studies involving multivariate traits, called PaRFR (Parallel Random Forest Regression). Our implementation takes advantage of the MapReduce programming model and is deployed on Hadoop, an open-source software framework that supports data-intensive distributed applications. Notable speed-ups are obtained by introducing a distance-based criterion for node splitting in the tree estimation process. PaRFR has been applied to a genome-wide association study on Alzheimer's disease (AD) in which the quantitative trait consists of a high-dimensional neuroimaging phenotype describing longitudinal changes in the human brain structure. PaRFR provides a ranking of SNPs associated to this trait, and produces pair-wise measures of genetic proximity that can be directly compared to pair-wise measures of phenotypic proximity. Several known AD-related variants have been identified, including APOE4 and TOMM40. We also present experimental evidence supporting the hypothesis of a linear relationship between the number of top-ranked mutated states, or frequent mutation patterns, and an indicator of disease severity. The Java codes are freely available at http://www2.imperial.ac.uk/~gmontana.

Automated seismic detection of landslides at regional scales: a Random Forest based detection algorithm

NASA Astrophysics Data System (ADS)

Hibert, C.; Michéa, D.; Provost, F.; Malet, J. P.; Geertsema, M.

2017-12-01

Detection of landslide occurrences and measurement of their dynamics properties during run-out is a high research priority but a logistical and technical challenge. Seismology has started to help in several important ways. Taking advantage of the densification of global, regional and local networks of broadband seismic stations, recent advances now permit the seismic detection and location of landslides in near-real-time. This seismic detection could potentially greatly increase the spatio-temporal resolution at which we study landslides triggering, which is critical to better understand the influence of external forcings such as rainfalls and earthquakes. However, detecting automatically seismic signals generated by landslides still represents a challenge, especially for events with small mass. The low signal-to-noise ratio classically observed for landslide-generated seismic signals and the difficulty to discriminate these signals from those generated by regional earthquakes or anthropogenic and natural noises are some of the obstacles that have to be circumvented. We present a new method for automatically constructing instrumental landslide catalogues from continuous seismic data. We developed a robust and versatile solution, which can be implemented in any context where a seismic detection of landslides or other mass movements is relevant. The method is based on a spectral detection of the seismic signals and the identification of the sources with a Random Forest machine learning algorithm. The spectral detection allows detecting signals with low signal-to-noise ratio, while the Random Forest algorithm achieve a high rate of positive identification of the seismic signals generated by landslides and other seismic sources. The processing chain is implemented to work in a High Performance Computers centre which permits to explore years of continuous seismic data rapidly. We present here the preliminary results of the application of this processing chain for years of continuous seismic record by the Alaskan permanent seismic network and Hi-Climb trans-Himalayan seismic network. The processing chain we developed also opens the possibility for a near-real time seismic detection of landslides, in association with remote-sensing automated detection from Sentinel 2 images for example.

Automated seismic detection of landslides at regional scales: a Random Forest based detection algorithm for Alaska and the Himalaya.

NASA Astrophysics Data System (ADS)

Hibert, Clement; Malet, Jean-Philippe; Provost, Floriane; Michéa, David; Geertsema, Marten

2017-04-01

Detection of landslide occurrences and measurement of their dynamics properties during run-out is a high research priority but a logistical and technical challenge. Seismology has started to help in several important ways. Taking advantage of the densification of global, regional and local networks of broadband seismic stations, recent advances now permit the seismic detection and location of landslides in near-real-time. This seismic detection could potentially greatly increase the spatio-temporal resolution at which we study landslides triggering, which is critical to better understand the influence of external forcings such as rainfalls and earthquakes. However, detecting automatically seismic signals generated by landslides still represents a challenge, especially for events with volumes below one millions of cubic meters. The low signal-to-noise ratio classically observed for landslide-generated seismic signals and the difficulty to discriminate these signals from those generated by regional earthquakes or anthropogenic and natural noises are some of the obstacles that have to be circumvented. We present a new method for automatically constructing instrumental landslide catalogues from continuous seismic data. We developed a robust and versatile solution, which can be implemented in any context where a seismic detection of landslides or other mass movements is relevant. The method is based on a spectral detection of the seismic signals and the identification of the sources with a Random Forest algorithm. The spectral detection allows detecting signals with low signal-to-noise ratio, while the Random Forest algorithm achieve a high rate of positive identification of the seismic signals generated by landslides and other seismic sources. We present here the preliminary results of the application of this processing chain in two contexts: i) In Himalaya with the data acquired between 2002 and 2005 by the Hi-Climb network; ii) In Alaska using data recorded by the permanent regional network and the USArray, which is currently being deployed in this region. The landslide seismic catalogues are compared to geomorphological catalogues in terms of number of events and dates when possible.

Machine learning based brain tumour segmentation on limited data using local texture and abnormality.

PubMed

Bonte, Stijn; Goethals, Ingeborg; Van Holen, Roel

2018-05-07

Brain tumour segmentation in medical images is a very challenging task due to the large variety in tumour shape, position, appearance, scanning modalities and scanning parameters. Most existing segmentation algorithms use information from four different MRI-sequences, but since this is often not available, there is need for a method able to delineate the different tumour tissues based on a minimal amount of data. We present a novel approach using a Random Forests model combining voxelwise texture and abnormality features on a contrast-enhanced T1 and FLAIR MRI. We transform the two scans into 275 feature maps. A random forest model next calculates the probability to belong to 4 tumour classes or 5 normal classes. Afterwards, a dedicated voxel clustering algorithm provides the final tumour segmentation. We trained our method on the BraTS 2013 database and validated it on the larger BraTS 2017 dataset. We achieve median Dice scores of 40.9% (low-grade glioma) and 75.0% (high-grade glioma) to delineate the active tumour, and 68.4%/80.1% for the total abnormal region including edema. Our fully automated brain tumour segmentation algorithm is able to delineate contrast enhancing tissue and oedema with high accuracy based only on post-contrast T1-weighted and FLAIR MRI, whereas for non-enhancing tumour tissue and necrosis only moderate results are obtained. This makes the method especially suitable for high-grade glioma. Copyright © 2018 Elsevier Ltd. All rights reserved.

Mathematical models application for mapping soils spatial distribution on the example of the farm from the North of Udmurt Republic of Russia

NASA Astrophysics Data System (ADS)

Dokuchaev, P. M.; Meshalkina, J. L.; Yaroslavtsev, A. M.

2018-01-01

Comparative analysis of soils geospatial modeling using multinomial logistic regression, decision trees, random forest, regression trees and support vector machines algorithms was conducted. The visual interpretation of the digital maps obtained and their comparison with the existing map, as well as the quantitative assessment of the individual soil groups detection overall accuracy and of the models kappa showed that multiple logistic regression, support vector method, and random forest models application with spatial prediction of the conditional soil groups distribution can be reliably used for mapping of the study area. It has shown the most accurate detection for sod-podzolics soils (Phaeozems Albic) lightly eroded and moderately eroded soils. In second place, according to the mean overall accuracy of the prediction, there are sod-podzolics soils - non-eroded and warp one, as well as sod-gley soils (Umbrisols Gleyic) and alluvial soils (Fluvisols Dystric, Umbric). Heavy eroded sod-podzolics and gray forest soils (Phaeozems Albic) were detected by methods of automatic classification worst of all.

Improving the Spatial Prediction of Soil Organic Carbon Stocks in a Complex Tropical Mountain Landscape by Methodological Specifications in Machine Learning Approaches.

PubMed

Ließ, Mareike; Schmidt, Johannes; Glaser, Bruno

2016-01-01

Tropical forests are significant carbon sinks and their soils' carbon storage potential is immense. However, little is known about the soil organic carbon (SOC) stocks of tropical mountain areas whose complex soil-landscape and difficult accessibility pose a challenge to spatial analysis. The choice of methodology for spatial prediction is of high importance to improve the expected poor model results in case of low predictor-response correlations. Four aspects were considered to improve model performance in predicting SOC stocks of the organic layer of a tropical mountain forest landscape: Different spatial predictor settings, predictor selection strategies, various machine learning algorithms and model tuning. Five machine learning algorithms: random forests, artificial neural networks, multivariate adaptive regression splines, boosted regression trees and support vector machines were trained and tuned to predict SOC stocks from predictors derived from a digital elevation model and satellite image. Topographical predictors were calculated with a GIS search radius of 45 to 615 m. Finally, three predictor selection strategies were applied to the total set of 236 predictors. All machine learning algorithms-including the model tuning and predictor selection-were compared via five repetitions of a tenfold cross-validation. The boosted regression tree algorithm resulted in the overall best model. SOC stocks ranged between 0.2 to 17.7 kg m-2, displaying a huge variability with diffuse insolation and curvatures of different scale guiding the spatial pattern. Predictor selection and model tuning improved the models' predictive performance in all five machine learning algorithms. The rather low number of selected predictors favours forward compared to backward selection procedures. Choosing predictors due to their indiviual performance was vanquished by the two procedures which accounted for predictor interaction.

Sequential Monte Carlo tracking of the marginal artery by multiple cue fusion and random forest regression.

PubMed

Cherry, Kevin M; Peplinski, Brandon; Kim, Lauren; Wang, Shijun; Lu, Le; Zhang, Weidong; Liu, Jianfei; Wei, Zhuoshi; Summers, Ronald M

2015-01-01

Given the potential importance of marginal artery localization in automated registration in computed tomography colonography (CTC), we have devised a semi-automated method of marginal vessel detection employing sequential Monte Carlo tracking (also known as particle filtering tracking) by multiple cue fusion based on intensity, vesselness, organ detection, and minimum spanning tree information for poorly enhanced vessel segments. We then employed a random forest algorithm for intelligent cue fusion and decision making which achieved high sensitivity and robustness. After applying a vessel pruning procedure to the tracking results, we achieved statistically significantly improved precision compared to a baseline Hessian detection method (2.7% versus 75.2%, p<0.001). This method also showed statistically significantly improved recall rate compared to a 2-cue baseline method using fewer vessel cues (30.7% versus 67.7%, p<0.001). These results demonstrate that marginal artery localization on CTC is feasible by combining a discriminative classifier (i.e., random forest) with a sequential Monte Carlo tracking mechanism. In so doing, we present the effective application of an anatomical probability map to vessel pruning as well as a supplementary spatial coordinate system for colonic segmentation and registration when this task has been confounded by colon lumen collapse. Published by Elsevier B.V.

Groundwater potential mapping using C5.0, random forest, and multivariate adaptive regression spline models in GIS.

PubMed

Golkarian, Ali; Naghibi, Seyed Amir; Kalantar, Bahareh; Pradhan, Biswajeet

2018-02-17

Ever increasing demand for water resources for different purposes makes it essential to have better understanding and knowledge about water resources. As known, groundwater resources are one of the main water resources especially in countries with arid climatic condition. Thus, this study seeks to provide groundwater potential maps (GPMs) employing new algorithms. Accordingly, this study aims to validate the performance of C5.0, random forest (RF), and multivariate adaptive regression splines (MARS) algorithms for generating GPMs in the eastern part of Mashhad Plain, Iran. For this purpose, a dataset was produced consisting of spring locations as indicator and groundwater-conditioning factors (GCFs) as input. In this research, 13 GCFs were selected including altitude, slope aspect, slope angle, plan curvature, profile curvature, topographic wetness index (TWI), slope length, distance from rivers and faults, rivers and faults density, land use, and lithology. The mentioned dataset was divided into two classes of training and validation with 70 and 30% of the springs, respectively. Then, C5.0, RF, and MARS algorithms were employed using R statistical software, and the final values were transformed into GPMs. Finally, two evaluation criteria including Kappa and area under receiver operating characteristics curve (AUC-ROC) were calculated. According to the findings of this research, MARS had the best performance with AUC-ROC of 84.2%, followed by RF and C5.0 algorithms with AUC-ROC values of 79.7 and 77.3%, respectively. The results indicated that AUC-ROC values for the employed models are more than 70% which shows their acceptable performance. As a conclusion, the produced methodology could be used in other geographical areas. GPMs could be used by water resource managers and related organizations to accelerate and facilitate water resource exploitation.

Automated diagnoses of attention deficit hyperactive disorder using magnetic resonance imaging.

PubMed

Eloyan, Ani; Muschelli, John; Nebel, Mary Beth; Liu, Han; Han, Fang; Zhao, Tuo; Barber, Anita D; Joel, Suresh; Pekar, James J; Mostofsky, Stewart H; Caffo, Brian

2012-01-01

Successful automated diagnoses of attention deficit hyperactive disorder (ADHD) using imaging and functional biomarkers would have fundamental consequences on the public health impact of the disease. In this work, we show results on the predictability of ADHD using imaging biomarkers and discuss the scientific and diagnostic impacts of the research. We created a prediction model using the landmark ADHD 200 data set focusing on resting state functional connectivity (rs-fc) and structural brain imaging. We predicted ADHD status and subtype, obtained by behavioral examination, using imaging data, intelligence quotients and other covariates. The novel contributions of this manuscript include a thorough exploration of prediction and image feature extraction methodology on this form of data, including the use of singular value decompositions (SVDs), CUR decompositions, random forest, gradient boosting, bagging, voxel-based morphometry, and support vector machines as well as important insights into the value, and potentially lack thereof, of imaging biomarkers of disease. The key results include the CUR-based decomposition of the rs-fc-fMRI along with gradient boosting and the prediction algorithm based on a motor network parcellation and random forest algorithm. We conjecture that the CUR decomposition is largely diagnosing common population directions of head motion. Of note, a byproduct of this research is a potential automated method for detecting subtle in-scanner motion. The final prediction algorithm, a weighted combination of several algorithms, had an external test set specificity of 94% with sensitivity of 21%. The most promising imaging biomarker was a correlation graph from a motor network parcellation. In summary, we have undertaken a large-scale statistical exploratory prediction exercise on the unique ADHD 200 data set. The exercise produced several potential leads for future scientific exploration of the neurological basis of ADHD.

Automated diagnoses of attention deficit hyperactive disorder using magnetic resonance imaging

PubMed Central

Eloyan, Ani; Muschelli, John; Nebel, Mary Beth; Liu, Han; Han, Fang; Zhao, Tuo; Barber, Anita D.; Joel, Suresh; Pekar, James J.; Mostofsky, Stewart H.; Caffo, Brian

2012-01-01

Successful automated diagnoses of attention deficit hyperactive disorder (ADHD) using imaging and functional biomarkers would have fundamental consequences on the public health impact of the disease. In this work, we show results on the predictability of ADHD using imaging biomarkers and discuss the scientific and diagnostic impacts of the research. We created a prediction model using the landmark ADHD 200 data set focusing on resting state functional connectivity (rs-fc) and structural brain imaging. We predicted ADHD status and subtype, obtained by behavioral examination, using imaging data, intelligence quotients and other covariates. The novel contributions of this manuscript include a thorough exploration of prediction and image feature extraction methodology on this form of data, including the use of singular value decompositions (SVDs), CUR decompositions, random forest, gradient boosting, bagging, voxel-based morphometry, and support vector machines as well as important insights into the value, and potentially lack thereof, of imaging biomarkers of disease. The key results include the CUR-based decomposition of the rs-fc-fMRI along with gradient boosting and the prediction algorithm based on a motor network parcellation and random forest algorithm. We conjecture that the CUR decomposition is largely diagnosing common population directions of head motion. Of note, a byproduct of this research is a potential automated method for detecting subtle in-scanner motion. The final prediction algorithm, a weighted combination of several algorithms, had an external test set specificity of 94% with sensitivity of 21%. The most promising imaging biomarker was a correlation graph from a motor network parcellation. In summary, we have undertaken a large-scale statistical exploratory prediction exercise on the unique ADHD 200 data set. The exercise produced several potential leads for future scientific exploration of the neurological basis of ADHD. PMID:22969709

Machine learning methods for the classification of gliomas: Initial results using features extracted from MR spectroscopy.

PubMed

Ranjith, G; Parvathy, R; Vikas, V; Chandrasekharan, Kesavadas; Nair, Suresh

2015-04-01

With the advent of new imaging modalities, radiologists are faced with handling increasing volumes of data for diagnosis and treatment planning. The use of automated and intelligent systems is becoming essential in such a scenario. Machine learning, a branch of artificial intelligence, is increasingly being used in medical image analysis applications such as image segmentation, registration and computer-aided diagnosis and detection. Histopathological analysis is currently the gold standard for classification of brain tumors. The use of machine learning algorithms along with extraction of relevant features from magnetic resonance imaging (MRI) holds promise of replacing conventional invasive methods of tumor classification. The aim of the study is to classify gliomas into benign and malignant types using MRI data. Retrospective data from 28 patients who were diagnosed with glioma were used for the analysis. WHO Grade II (low-grade astrocytoma) was classified as benign while Grade III (anaplastic astrocytoma) and Grade IV (glioblastoma multiforme) were classified as malignant. Features were extracted from MR spectroscopy. The classification was done using four machine learning algorithms: multilayer perceptrons, support vector machine, random forest and locally weighted learning. Three of the four machine learning algorithms gave an area under ROC curve in excess of 0.80. Random forest gave the best performance in terms of AUC (0.911) while sensitivity was best for locally weighted learning (86.1%). The performance of different machine learning algorithms in the classification of gliomas is promising. An even better performance may be expected by integrating features extracted from other MR sequences. © The Author(s) 2015 Reprints and permissions: sagepub.co.uk/journalsPermissions.nav.

How similar are forest disturbance maps derived from different Landsat time series algorithms?

Treesearch

Warren B. Cohen; Sean P. Healey; Zhiqiang Yang; Stephen V. Stehman; C. Kenneth Brewer; Evan B. Brooks; Noel Gorelick; Chengqaun Huang; M. Joseph Hughes; Robert E. Kennedy; Thomas R. Loveland; Gretchen G. Moisen; Todd A. Schroeder; James E. Vogelmann; Curtis E. Woodcock; Limin Yang; Zhe Zhu

2017-01-01

Disturbance is a critical ecological process in forested systems, and disturbance maps are important for understanding forest dynamics. Landsat data are a key remote sensing dataset for monitoring forest disturbance and there recently has been major growth in the development of disturbance mapping algorithms. Many of these algorithms take advantage of the high temporal...

An application of quantile random forests for predictive mapping of forest attributes

Treesearch

E.A. Freeman; G.G. Moisen

2015-01-01

Increasingly, random forest models are used in predictive mapping of forest attributes. Traditional random forests output the mean prediction from the random trees. Quantile regression forests (QRF) is an extension of random forests developed by Nicolai Meinshausen that provides non-parametric estimates of the median predicted value as well as prediction quantiles. It...

Automatic detection of freezing of gait events in patients with Parkinson's disease.

PubMed

Tripoliti, Evanthia E; Tzallas, Alexandros T; Tsipouras, Markos G; Rigas, George; Bougia, Panagiota; Leontiou, Michael; Konitsiotis, Spiros; Chondrogiorgi, Maria; Tsouli, Sofia; Fotiadis, Dimitrios I

2013-04-01

The aim of this study is to detect freezing of gait (FoG) events in patients suffering from Parkinson's disease (PD) using signals received from wearable sensors (six accelerometers and two gyroscopes) placed on the patients' body. For this purpose, an automated methodology has been developed which consists of four stages. In the first stage, missing values due to signal loss or degradation are replaced and then (second stage) low frequency components of the raw signal are removed. In the third stage, the entropy of the raw signal is calculated. Finally (fourth stage), four classification algorithms have been tested (Naïve Bayes, Random Forests, Decision Trees and Random Tree) in order to detect the FoG events. The methodology has been evaluated using several different configurations of sensors in order to conclude to the set of sensors which can produce optimal FoG episode detection. Signals recorded from five healthy subjects, five patients with PD who presented the symptom of FoG and six patients who suffered from PD but they do not present FoG events. The signals included 93 FoG events with 405.6s total duration. The results indicate that the proposed methodology is able to detect FoG events with 81.94% sensitivity, 98.74% specificity, 96.11% accuracy and 98.6% area under curve (AUC) using the signals from all sensors and the Random Forests classification algorithm. Copyright © 2012 Elsevier Ireland Ltd. All rights reserved.

Use of Hundreds of Electrocardiograhpic Biomarkers for Prediction of Mortality in Post-Menopausal Women: The Women’s Health Initiative

PubMed Central

Gorodeski, Eiran Z.; Ishwaran, Hemant; Kogalur, Udaya B.; Blackstone, Eugene H.; Hsich, Eileen; Zhang, Zhu-ming; Vitolins, Mara Z.; Manson, JoAnn E.; Curb, J. David; Martin, Lisa W.; Prineas, Ronald J.; Lauer, Michael S.

2013-01-01

Background Simultaneous contribution of hundreds of electrocardiographic biomarkers to prediction of long-term mortality in post-menopausal women with clinically normal resting electrocardiograms (ECGs) is unknown. Methods and Results We analyzed ECGs and all-cause mortality in 33,144 women enrolled in Women’s Health Initiative trials, who were without baseline cardiovascular disease or cancer, and had normal ECGs by Minnesota and Novacode criteria. Four hundred and seventy seven ECG biomarkers, encompassing global and individual ECG findings, were measured using computer algorithms. During a median follow-up of 8.1 years (range for survivors 0.5–11.2 years), 1,229 women died. For analyses cohort was randomly split into derivation (n=22,096, deaths=819) and validation (n=11,048, deaths=410) subsets. ECG biomarkers, demographic, and clinical characteristics were simultaneously analyzed using both traditional Cox regression and Random Survival Forest (RSF), a novel algorithmic machine-learning approach. Regression modeling failed to converge. RSF variable selection yielded 20 variables that were independently predictive of long-term mortality, 14 of which were ECG biomarkers related to autonomic tone, atrial conduction, and ventricular depolarization and repolarization. Conclusions We identified 14 ECG biomarkers from amongst hundreds that were associated with long-term prognosis using a novel random forest variable selection methodology. These were related to autonomic tone, atrial conduction, ventricular depolarization, and ventricular repolarization. Quantitative ECG biomarkers have prognostic importance, and may be markers of subclinical disease in apparently healthy post-menopausal women. PMID:21862719

Accuracy assessments and areal estimates using two-phase stratified random sampling, cluster plots, and the multivariate composite estimator

Treesearch

Raymond L. Czaplewski

2000-01-01

Consider the following example of an accuracy assessment. Landsat data are used to build a thematic map of land cover for a multicounty region. The map classifier (e.g., a supervised classification algorithm) assigns each pixel into one category of land cover. The classification system includes 12 different types of forest and land cover: black spruce, balsam fir,...

Prediction of Protein-Protein Interaction Sites by Random Forest Algorithm with mRMR and IFS

PubMed Central

Li, Bi-Qing; Feng, Kai-Yan; Chen, Lei; Huang, Tao; Cai, Yu-Dong

2012-01-01

Prediction of protein-protein interaction (PPI) sites is one of the most challenging problems in computational biology. Although great progress has been made by employing various machine learning approaches with numerous characteristic features, the problem is still far from being solved. In this study, we developed a novel predictor based on Random Forest (RF) algorithm with the Minimum Redundancy Maximal Relevance (mRMR) method followed by incremental feature selection (IFS). We incorporated features of physicochemical/biochemical properties, sequence conservation, residual disorder, secondary structure and solvent accessibility. We also included five 3D structural features to predict protein-protein interaction sites and achieved an overall accuracy of 0.672997 and MCC of 0.347977. Feature analysis showed that 3D structural features such as Depth Index (DPX) and surface curvature (SC) contributed most to the prediction of protein-protein interaction sites. It was also shown via site-specific feature analysis that the features of individual residues from PPI sites contribute most to the determination of protein-protein interaction sites. It is anticipated that our prediction method will become a useful tool for identifying PPI sites, and that the feature analysis described in this paper will provide useful insights into the mechanisms of interaction. PMID:22937126

Application of Machine Learning Approaches for Classifying Sitting Posture Based on Force and Acceleration Sensors.

PubMed

Zemp, Roland; Tanadini, Matteo; Plüss, Stefan; Schnüriger, Karin; Singh, Navrag B; Taylor, William R; Lorenzetti, Silvio

2016-01-01

Occupational musculoskeletal disorders, particularly chronic low back pain (LBP), are ubiquitous due to prolonged static sitting or nonergonomic sitting positions. Therefore, the aim of this study was to develop an instrumented chair with force and acceleration sensors to determine the accuracy of automatically identifying the user's sitting position by applying five different machine learning methods (Support Vector Machines, Multinomial Regression, Boosting, Neural Networks, and Random Forest). Forty-one subjects were requested to sit four times in seven different prescribed sitting positions (total 1148 samples). Sixteen force sensor values and the backrest angle were used as the explanatory variables (features) for the classification. The different classification methods were compared by means of a Leave-One-Out cross-validation approach. The best performance was achieved using the Random Forest classification algorithm, producing a mean classification accuracy of 90.9% for subjects with which the algorithm was not familiar. The classification accuracy varied between 81% and 98% for the seven different sitting positions. The present study showed the possibility of accurately classifying different sitting positions by means of the introduced instrumented office chair combined with machine learning analyses. The use of such novel approaches for the accurate assessment of chair usage could offer insights into the relationships between sitting position, sitting behaviour, and the occurrence of musculoskeletal disorders.

Assessing and comparison of different machine learning methods in parent-offspring trios for genotype imputation.

PubMed

Mikhchi, Abbas; Honarvar, Mahmood; Kashan, Nasser Emam Jomeh; Aminafshar, Mehdi

2016-06-21

Genotype imputation is an important tool for prediction of unknown genotypes for both unrelated individuals and parent-offspring trios. Several imputation methods are available and can either employ universal machine learning methods, or deploy algorithms dedicated to infer missing genotypes. In this research the performance of eight machine learning methods: Support Vector Machine, K-Nearest Neighbors, Extreme Learning Machine, Radial Basis Function, Random Forest, AdaBoost, LogitBoost, and TotalBoost compared in terms of the imputation accuracy, computation time and the factors affecting imputation accuracy. The methods employed using real and simulated datasets to impute the un-typed SNPs in parent-offspring trios. The tested methods show that imputation of parent-offspring trios can be accurate. The Random Forest and Support Vector Machine were more accurate than the other machine learning methods. The TotalBoost performed slightly worse than the other methods.The running times were different between methods. The ELM was always most fast algorithm. In case of increasing the sample size, the RBF requires long imputation time.The tested methods in this research can be an alternative for imputation of un-typed SNPs in low missing rate of data. However, it is recommended that other machine learning methods to be used for imputation. Copyright © 2016 Elsevier Ltd. All rights reserved.

Simultaneous feature selection and parameter optimisation using an artificial ant colony: case study of melting point prediction.

PubMed

O'Boyle, Noel M; Palmer, David S; Nigsch, Florian; Mitchell, John Bo

2008-10-29

We present a novel feature selection algorithm, Winnowing Artificial Ant Colony (WAAC), that performs simultaneous feature selection and model parameter optimisation for the development of predictive quantitative structure-property relationship (QSPR) models. The WAAC algorithm is an extension of the modified ant colony algorithm of Shen et al. (J Chem Inf Model 2005, 45: 1024-1029). We test the ability of the algorithm to develop a predictive partial least squares model for the Karthikeyan dataset (J Chem Inf Model 2005, 45: 581-590) of melting point values. We also test its ability to perform feature selection on a support vector machine model for the same dataset. Starting from an initial set of 203 descriptors, the WAAC algorithm selected a PLS model with 68 descriptors which has an RMSE on an external test set of 46.6 degrees C and R2 of 0.51. The number of components chosen for the model was 49, which was close to optimal for this feature selection. The selected SVM model has 28 descriptors (cost of 5, epsilon of 0.21) and an RMSE of 45.1 degrees C and R2 of 0.54. This model outperforms a kNN model (RMSE of 48.3 degrees C, R2 of 0.47) for the same data and has similar performance to a Random Forest model (RMSE of 44.5 degrees C, R2 of 0.55). However it is much less prone to bias at the extremes of the range of melting points as shown by the slope of the line through the residuals: -0.43 for WAAC/SVM, -0.53 for Random Forest. With a careful choice of objective function, the WAAC algorithm can be used to optimise machine learning and regression models that suffer from overfitting. Where model parameters also need to be tuned, as is the case with support vector machine and partial least squares models, it can optimise these simultaneously. The moving probabilities used by the algorithm are easily interpreted in terms of the best and current models of the ants, and the winnowing procedure promotes the removal of irrelevant descriptors.

Classification of nanoparticle diffusion processes in vital cells by a multifeature random forests approach: application to simulated data, darkfield, and confocal laser scanning microscopy

NASA Astrophysics Data System (ADS)

Wagner, Thorsten; Kroll, Alexandra; Wiemann, Martin; Lipinski, Hans-Gerd

2016-04-01

Darkfield and confocal laser scanning microscopy both allow for a simultaneous observation of live cells and single nanoparticles. Accordingly, a characterization of nanoparticle uptake and intracellular mobility appears possible within living cells. Single particle tracking makes it possible to characterize the particle and the surrounding cell. In case of free diffusion, the mean squared displacement for each trajectory of a nanoparticle can be measured which allows computing the corresponding diffusion coefficient and, if desired, converting it into the hydrodynamic diameter using the Stokes-Einstein equation and the viscosity of the fluid. However, within the more complex system of a cell's cytoplasm unrestrained diffusion is scarce and several other types of movements may occur. Thus, confined or anomalous diffusion (e.g. diffusion in porous media), active transport, and combinations thereof were described by several authors. To distinguish between these types of particle movement we developed an appropriate classification method, and simulated three types of particle motion in a 2D plane using a Monte Carlo approach: (1) normal diffusion, using random direction and step-length, (2) subdiffusion, using confinements like a reflective boundary with defined radius or reflective objects in the closer vicinity, and (3) superdiffusion, using a directed flow added to the normal diffusion. To simulate subdiffusion we devised a new method based on tracks of different length combined with equally probable obstacle interaction. Next we estimated the fractal dimension, elongation and the ratio of long-time / short-time diffusion coefficients. These features were used to train a random forests classification algorithm. The accuracy for simulated trajectories with 180 steps was 97% (95%-CI: 0.9481-0.9884). The balanced accuracy was 94%, 99% and 98% for normal-, sub- and superdiffusion, respectively. Nanoparticle tracking analysis was used with 100 nm polystyrene particles to get trajectories for normal diffusion. As a next step we identified diffusion types of nanoparticles in vital cells and incubated V79 fibroblasts with 50 nm gold nanoparticles, which appeared as intensely bright objects due to their surface plasmon resonance. The movement of particles in both the extracellular and intracellular space was observed by dark field and confocal laser scanning microscopy. After reducing background noise from the video it became possible to identify individual particle spots by a maximum detection algorithm and trace them using the robust single-particle tracking algorithm proposed by Jaqaman, which is able to handle motion heterogeneity and particle disappearance. The particle trajectories inside cells indicated active transport (superdiffusion) as well as subdiffusion. Eventually, the random forest classification algorithm, after being trained by the above simulations, successfully classified the trajectories observed in live cells.

VizieR Online Data Catalog: Gamma-ray AGN type determination (Hassan+, 2013)

NASA Astrophysics Data System (ADS)

Hassan, T.; Mirabal, N.; Contreras, J. L.; Oya, I.

2013-11-01

In this paper, we employ Support Vector Machines (SVMs) and Random Forest (RF) that embody two of the most robust supervised learning algorithms available today. We are interested in building classifiers that can distinguish between two AGN classes: BL Lacs and FSRQs. In the 2FGL, there is a total set of 1074 identified/associated AGN objects with the following labels: 'bzb' (BL Lacs), 'bzq' (FSRQs), 'agn' (other non-blazar AGN) and 'agu' (active galaxies of uncertain type). From this global set, we group the identified/associated blazars ('bzb' and 'bzq' labels) as the training/testing set of our algorithms. (2 data files).

Ecological interactions and the Netflix problem.

PubMed

Desjardins-Proulx, Philippe; Laigle, Idaline; Poisot, Timothée; Gravel, Dominique

2017-01-01

Species interactions are a key component of ecosystems but we generally have an incomplete picture of who-eats-who in a given community. Different techniques have been devised to predict species interactions using theoretical models or abundances. Here, we explore the K nearest neighbour approach, with a special emphasis on recommendation, along with a supervised machine learning technique. Recommenders are algorithms developed for companies like Netflix to predict whether a customer will like a product given the preferences of similar customers. These machine learning techniques are well-suited to study binary ecological interactions since they focus on positive-only data. By removing a prey from a predator, we find that recommenders can guess the missing prey around 50% of the times on the first try, with up to 881 possibilities. Traits do not improve significantly the results for the K nearest neighbour, although a simple test with a supervised learning approach (random forests) show we can predict interactions with high accuracy using only three traits per species. This result shows that binary interactions can be predicted without regard to the ecological community given only three variables: body mass and two variables for the species' phylogeny. These techniques are complementary, as recommenders can predict interactions in the absence of traits, using only information about other species' interactions, while supervised learning algorithms such as random forests base their predictions on traits only but do not exploit other species' interactions. Further work should focus on developing custom similarity measures specialized for ecology to improve the KNN algorithms and using richer data to capture indirect relationships between species.

Ecological interactions and the Netflix problem

PubMed Central

Laigle, Idaline; Poisot, Timothée; Gravel, Dominique

2017-01-01

Species interactions are a key component of ecosystems but we generally have an incomplete picture of who-eats-who in a given community. Different techniques have been devised to predict species interactions using theoretical models or abundances. Here, we explore the K nearest neighbour approach, with a special emphasis on recommendation, along with a supervised machine learning technique. Recommenders are algorithms developed for companies like Netflix to predict whether a customer will like a product given the preferences of similar customers. These machine learning techniques are well-suited to study binary ecological interactions since they focus on positive-only data. By removing a prey from a predator, we find that recommenders can guess the missing prey around 50% of the times on the first try, with up to 881 possibilities. Traits do not improve significantly the results for the K nearest neighbour, although a simple test with a supervised learning approach (random forests) show we can predict interactions with high accuracy using only three traits per species. This result shows that binary interactions can be predicted without regard to the ecological community given only three variables: body mass and two variables for the species’ phylogeny. These techniques are complementary, as recommenders can predict interactions in the absence of traits, using only information about other species’ interactions, while supervised learning algorithms such as random forests base their predictions on traits only but do not exploit other species’ interactions. Further work should focus on developing custom similarity measures specialized for ecology to improve the KNN algorithms and using richer data to capture indirect relationships between species. PMID:28828250

Integrating human and machine intelligence in galaxy morphology classification tasks

NASA Astrophysics Data System (ADS)

Beck, Melanie R.; Scarlata, Claudia; Fortson, Lucy F.; Lintott, Chris J.; Simmons, B. D.; Galloway, Melanie A.; Willett, Kyle W.; Dickinson, Hugh; Masters, Karen L.; Marshall, Philip J.; Wright, Darryl

2018-06-01

Quantifying galaxy morphology is a challenging yet scientifically rewarding task. As the scale of data continues to increase with upcoming surveys, traditional classification methods will struggle to handle the load. We present a solution through an integration of visual and automated classifications, preserving the best features of both human and machine. We demonstrate the effectiveness of such a system through a re-analysis of visual galaxy morphology classifications collected during the Galaxy Zoo 2 (GZ2) project. We reprocess the top-level question of the GZ2 decision tree with a Bayesian classification aggregation algorithm dubbed SWAP, originally developed for the Space Warps gravitational lens project. Through a simple binary classification scheme, we increase the classification rate nearly 5-fold classifying 226 124 galaxies in 92 d of GZ2 project time while reproducing labels derived from GZ2 classification data with 95.7 per cent accuracy. We next combine this with a Random Forest machine learning algorithm that learns on a suite of non-parametric morphology indicators widely used for automated morphologies. We develop a decision engine that delegates tasks between human and machine and demonstrate that the combined system provides at least a factor of 8 increase in the classification rate, classifying 210 803 galaxies in just 32 d of GZ2 project time with 93.1 per cent accuracy. As the Random Forest algorithm requires a minimal amount of computational cost, this result has important implications for galaxy morphology identification tasks in the era of Euclid and other large-scale surveys.

Machine-Learning Techniques for the Determination of Attrition of Forces Due to Atmospheric Conditions

DTIC Science & Technology

2018-02-01

the possibility of a correlation between aircraft incidents in the National Transportation Safety Board database and meteorological conditions. If a...strong correlation could be found, it could be used to derive a model to predict aircraft incidents and become part of a decision support tool for...techniques, primarily the random forest algorithm, were used to explore the possibility of a correlation between aircraft incidents in the National

Novel approaches to assess the quality of fertility data stored in dairy herd management software.

PubMed

Hermans, K; Waegeman, W; Opsomer, G; Van Ranst, B; De Koster, J; Van Eetvelde, M; Hostens, M

2017-05-01

Scientific journals and popular press magazines are littered with articles in which the authors use data from dairy herd management software. Almost none of such papers include data cleaning and data quality assessment in their study design despite this being a very critical step during data mining. This paper presents 2 novel data cleaning methods that permit identification of animals with good and bad data quality. The first method is a deterministic or rule-based data cleaning method. Reproduction and mutation or life-changing events such as birth and death were converted to a symbolic (alphabetical letter) representation and split into triplets (3-letter code). The triplets were manually labeled as physiologically correct, suspicious, or impossible. The deterministic data cleaning method was applied to assess the quality of data stored in dairy herd management from 26 farms enrolled in the herd health management program from the Faculty of Veterinary Medicine Ghent University, Belgium. In total, 150,443 triplets were created, 65.4% were labeled as correct, 17.4% as suspicious, and 17.2% as impossible. The second method, a probabilistic method, uses a machine learning algorithm (random forests) to predict the correctness of fertility and mutation events in an early stage of data cleaning. The prediction accuracy of the random forests algorithm was compared with a classical linear statistical method (penalized logistic regression), outperforming the latter substantially, with a superior receiver operating characteristic curve and a higher accuracy (89 vs. 72%). From those results, we conclude that the triplet method can be used to assess the quality of reproduction data stored in dairy herd management software and that a machine learning technique such as random forests is capable of predicting the correctness of fertility data. Copyright © 2017 American Dairy Science Association. Published by Elsevier Inc. All rights reserved.

A machine learning method to estimate PM2.5 concentrations across China with remote sensing, meteorological and land use information.

PubMed

Chen, Gongbo; Li, Shanshan; Knibbs, Luke D; Hamm, N A S; Cao, Wei; Li, Tiantian; Guo, Jianping; Ren, Hongyan; Abramson, Michael J; Guo, Yuming

2018-09-15

Machine learning algorithms have very high predictive ability. However, no study has used machine learning to estimate historical concentrations of PM 2.5 (particulate matter with aerodynamic diameter ≤ 2.5 μm) at daily time scale in China at a national level. To estimate daily concentrations of PM 2.5 across China during 2005-2016. Daily ground-level PM 2.5 data were obtained from 1479 stations across China during 2014-2016. Data on aerosol optical depth (AOD), meteorological conditions and other predictors were downloaded. A random forests model (non-parametric machine learning algorithms) and two traditional regression models were developed to estimate ground-level PM 2.5 concentrations. The best-fit model was then utilized to estimate the daily concentrations of PM 2.5 across China with a resolution of 0.1° (≈10 km) during 2005-2016. The daily random forests model showed much higher predictive accuracy than the other two traditional regression models, explaining the majority of spatial variability in daily PM 2.5 [10-fold cross-validation (CV) R 2  = 83%, root mean squared prediction error (RMSE) = 28.1 μg/m 3 ]. At the monthly and annual time-scale, the explained variability of average PM 2.5 increased up to 86% (RMSE = 10.7 μg/m 3 and 6.9 μg/m 3 , respectively). Taking advantage of a novel application of modeling framework and the most recent ground-level PM 2.5 observations, the machine learning method showed higher predictive ability than previous studies. Random forests approach can be used to estimate historical exposure to PM 2.5 in China with high accuracy. Copyright © 2018 Elsevier B.V. All rights reserved.

Mapping forests in monsoon Asia with ALOS PALSAR 50-m mosaic images and MODIS imagery in 2010

PubMed Central

Qin, Yuanwei; Xiao, Xiangming; Dong, Jinwei; Zhang, Geli; Roy, Partha Sarathi; Joshi, Pawan Kumar; Gilani, Hammad; Murthy, Manchiraju Sri Ramachandra; Jin, Cui; Wang, Jie; Zhang, Yao; Chen, Bangqian; Menarguez, Michael Angelo; Biradar, Chandrashekhar M.; Bajgain, Rajen; Li, Xiangping; Dai, Shengqi; Hou, Ying; Xin, Fengfei; Moore III, Berrien

2016-01-01

Extensive forest changes have occurred in monsoon Asia, substantially affecting climate, carbon cycle and biodiversity. Accurate forest cover maps at fine spatial resolutions are required to qualify and quantify these effects. In this study, an algorithm was developed to map forests in 2010, with the use of structure and biomass information from the Advanced Land Observation System (ALOS) Phased Array L-band Synthetic Aperture Radar (PALSAR) mosaic dataset and the phenological information from MODerate Resolution Imaging Spectroradiometer (MOD13Q1 and MOD09A1) products. Our forest map (PALSARMOD50 m F/NF) was assessed through randomly selected ground truth samples from high spatial resolution images and had an overall accuracy of 95%. Total area of forests in monsoon Asia in 2010 was estimated to be ~6.3 × 106 km2. The distribution of evergreen and deciduous forests agreed reasonably well with the median Normalized Difference Vegetation Index (NDVI) in winter. PALSARMOD50 m F/NF map showed good spatial and areal agreements with selected forest maps generated by the Japan Aerospace Exploration Agency (JAXA F/NF), European Space Agency (ESA F/NF), Boston University (MCD12Q1 F/NF), Food and Agricultural Organization (FAO FRA), and University of Maryland (Landsat forests), but relatively large differences and uncertainties in tropical forests and evergreen and deciduous forests. PMID:26864143

Mapping forests in monsoon Asia with ALOS PALSAR 50-m mosaic images and MODIS imagery in 2010.

PubMed

Qin, Yuanwei; Xiao, Xiangming; Dong, Jinwei; Zhang, Geli; Roy, Partha Sarathi; Joshi, Pawan Kumar; Gilani, Hammad; Murthy, Manchiraju Sri Ramachandra; Jin, Cui; Wang, Jie; Zhang, Yao; Chen, Bangqian; Menarguez, Michael Angelo; Biradar, Chandrashekhar M; Bajgain, Rajen; Li, Xiangping; Dai, Shengqi; Hou, Ying; Xin, Fengfei; Moore, Berrien

2016-02-11

Extensive forest changes have occurred in monsoon Asia, substantially affecting climate, carbon cycle and biodiversity. Accurate forest cover maps at fine spatial resolutions are required to qualify and quantify these effects. In this study, an algorithm was developed to map forests in 2010, with the use of structure and biomass information from the Advanced Land Observation System (ALOS) Phased Array L-band Synthetic Aperture Radar (PALSAR) mosaic dataset and the phenological information from MODerate Resolution Imaging Spectroradiometer (MOD13Q1 and MOD09A1) products. Our forest map (PALSARMOD50 m F/NF) was assessed through randomly selected ground truth samples from high spatial resolution images and had an overall accuracy of 95%. Total area of forests in monsoon Asia in 2010 was estimated to be ~6.3 × 10(6 )km(2). The distribution of evergreen and deciduous forests agreed reasonably well with the median Normalized Difference Vegetation Index (NDVI) in winter. PALSARMOD50 m F/NF map showed good spatial and areal agreements with selected forest maps generated by the Japan Aerospace Exploration Agency (JAXA F/NF), European Space Agency (ESA F/NF), Boston University (MCD12Q1 F/NF), Food and Agricultural Organization (FAO FRA), and University of Maryland (Landsat forests), but relatively large differences and uncertainties in tropical forests and evergreen and deciduous forests.

Developing reservoir monthly inflow forecasts using artificial intelligence and climate phenomenon information

NASA Astrophysics Data System (ADS)

Yang, Tiantian; Asanjan, Ata Akbari; Welles, Edwin; Gao, Xiaogang; Sorooshian, Soroosh; Liu, Xiaomang

2017-04-01

Reservoirs are fundamental human-built infrastructures that collect, store, and deliver fresh surface water in a timely manner for many purposes. Efficient reservoir operation requires policy makers and operators to understand how reservoir inflows are changing under different hydrological and climatic conditions to enable forecast-informed operations. Over the last decade, the uses of Artificial Intelligence and Data Mining [AI & DM] techniques in assisting reservoir streamflow subseasonal to seasonal forecasts have been increasing. In this study, Random Forest [RF), Artificial Neural Network (ANN), and Support Vector Regression (SVR) are employed and compared with respect to their capabilities for predicting 1 month-ahead reservoir inflows for two headwater reservoirs in USA and China. Both current and lagged hydrological information and 17 known climate phenomenon indices, i.e., PDO and ENSO, etc., are selected as predictors for simulating reservoir inflows. Results show (1) three methods are capable of providing monthly reservoir inflows with satisfactory statistics; (2) the results obtained by Random Forest have the best statistical performances compared with the other two methods; (3) another advantage of Random Forest algorithm is its capability of interpreting raw model inputs; (4) climate phenomenon indices are useful in assisting monthly or seasonal forecasts of reservoir inflow; and (5) different climate conditions are autocorrelated with up to several months, and the climatic information and their lags are cross correlated with local hydrological conditions in our case studies.

Voice based gender classification using machine learning

NASA Astrophysics Data System (ADS)

Raahul, A.; Sapthagiri, R.; Pankaj, K.; Vijayarajan, V.

2017-11-01

Gender identification is one of the major problem speech analysis today. Tracing the gender from acoustic data i.e., pitch, median, frequency etc. Machine learning gives promising results for classification problem in all the research domains. There are several performance metrics to evaluate algorithms of an area. Our Comparative model algorithm for evaluating 5 different machine learning algorithms based on eight different metrics in gender classification from acoustic data. Agenda is to identify gender, with five different algorithms: Linear Discriminant Analysis (LDA), K-Nearest Neighbour (KNN), Classification and Regression Trees (CART), Random Forest (RF), and Support Vector Machine (SVM) on basis of eight different metrics. The main parameter in evaluating any algorithms is its performance. Misclassification rate must be less in classification problems, which says that the accuracy rate must be high. Location and gender of the person have become very crucial in economic markets in the form of AdSense. Here with this comparative model algorithm, we are trying to assess the different ML algorithms and find the best fit for gender classification of acoustic data.

Improving the Spatial Prediction of Soil Organic Carbon Stocks in a Complex Tropical Mountain Landscape by Methodological Specifications in Machine Learning Approaches

PubMed Central

Schmidt, Johannes; Glaser, Bruno

2016-01-01

Tropical forests are significant carbon sinks and their soils’ carbon storage potential is immense. However, little is known about the soil organic carbon (SOC) stocks of tropical mountain areas whose complex soil-landscape and difficult accessibility pose a challenge to spatial analysis. The choice of methodology for spatial prediction is of high importance to improve the expected poor model results in case of low predictor-response correlations. Four aspects were considered to improve model performance in predicting SOC stocks of the organic layer of a tropical mountain forest landscape: Different spatial predictor settings, predictor selection strategies, various machine learning algorithms and model tuning. Five machine learning algorithms: random forests, artificial neural networks, multivariate adaptive regression splines, boosted regression trees and support vector machines were trained and tuned to predict SOC stocks from predictors derived from a digital elevation model and satellite image. Topographical predictors were calculated with a GIS search radius of 45 to 615 m. Finally, three predictor selection strategies were applied to the total set of 236 predictors. All machine learning algorithms—including the model tuning and predictor selection—were compared via five repetitions of a tenfold cross-validation. The boosted regression tree algorithm resulted in the overall best model. SOC stocks ranged between 0.2 to 17.7 kg m-2, displaying a huge variability with diffuse insolation and curvatures of different scale guiding the spatial pattern. Predictor selection and model tuning improved the models’ predictive performance in all five machine learning algorithms. The rather low number of selected predictors favours forward compared to backward selection procedures. Choosing predictors due to their indiviual performance was vanquished by the two procedures which accounted for predictor interaction. PMID:27128736

Can We Train Machine Learning Methods to Outperform the High-dimensional Propensity Score Algorithm?

PubMed

Karim, Mohammad Ehsanul; Pang, Menglan; Platt, Robert W

2018-03-01

The use of retrospective health care claims datasets is frequently criticized for the lack of complete information on potential confounders. Utilizing patient's health status-related information from claims datasets as surrogates or proxies for mismeasured and unobserved confounders, the high-dimensional propensity score algorithm enables us to reduce bias. Using a previously published cohort study of postmyocardial infarction statin use (1998-2012), we compare the performance of the algorithm with a number of popular machine learning approaches for confounder selection in high-dimensional covariate spaces: random forest, least absolute shrinkage and selection operator, and elastic net. Our results suggest that, when the data analysis is done with epidemiologic principles in mind, machine learning methods perform as well as the high-dimensional propensity score algorithm. Using a plasmode framework that mimicked the empirical data, we also showed that a hybrid of machine learning and high-dimensional propensity score algorithms generally perform slightly better than both in terms of mean squared error, when a bias-based analysis is used.

Effects of plot size on forest-type algorithm accuracy

Treesearch

James A. Westfall

2009-01-01

The Forest Inventory and Analysis (FIA) program utilizes an algorithm to consistently determine the forest type for forested conditions on sample plots. Forest type is determined from tree size and species information. Thus, the accuracy of results is often dependent on the number of trees present, which is highly correlated with plot area. This research examines the...

The influence of negative training set size on machine learning-based virtual screening.

PubMed

Kurczab, Rafał; Smusz, Sabina; Bojarski, Andrzej J

2014-01-01

The paper presents a thorough analysis of the influence of the number of negative training examples on the performance of machine learning methods. The impact of this rather neglected aspect of machine learning methods application was examined for sets containing a fixed number of positive and a varying number of negative examples randomly selected from the ZINC database. An increase in the ratio of positive to negative training instances was found to greatly influence most of the investigated evaluating parameters of ML methods in simulated virtual screening experiments. In a majority of cases, substantial increases in precision and MCC were observed in conjunction with some decreases in hit recall. The analysis of dynamics of those variations let us recommend an optimal composition of training data. The study was performed on several protein targets, 5 machine learning algorithms (SMO, Naïve Bayes, Ibk, J48 and Random Forest) and 2 types of molecular fingerprints (MACCS and CDK FP). The most effective classification was provided by the combination of CDK FP with SMO or Random Forest algorithms. The Naïve Bayes models appeared to be hardly sensitive to changes in the number of negative instances in the training set. In conclusion, the ratio of positive to negative training instances should be taken into account during the preparation of machine learning experiments, as it might significantly influence the performance of particular classifier. What is more, the optimization of negative training set size can be applied as a boosting-like approach in machine learning-based virtual screening.

The influence of negative training set size on machine learning-based virtual screening

PubMed Central

2014-01-01

Background The paper presents a thorough analysis of the influence of the number of negative training examples on the performance of machine learning methods. Results The impact of this rather neglected aspect of machine learning methods application was examined for sets containing a fixed number of positive and a varying number of negative examples randomly selected from the ZINC database. An increase in the ratio of positive to negative training instances was found to greatly influence most of the investigated evaluating parameters of ML methods in simulated virtual screening experiments. In a majority of cases, substantial increases in precision and MCC were observed in conjunction with some decreases in hit recall. The analysis of dynamics of those variations let us recommend an optimal composition of training data. The study was performed on several protein targets, 5 machine learning algorithms (SMO, Naïve Bayes, Ibk, J48 and Random Forest) and 2 types of molecular fingerprints (MACCS and CDK FP). The most effective classification was provided by the combination of CDK FP with SMO or Random Forest algorithms. The Naïve Bayes models appeared to be hardly sensitive to changes in the number of negative instances in the training set. Conclusions In conclusion, the ratio of positive to negative training instances should be taken into account during the preparation of machine learning experiments, as it might significantly influence the performance of particular classifier. What is more, the optimization of negative training set size can be applied as a boosting-like approach in machine learning-based virtual screening. PMID:24976867

Prediction of body mass index status from voice signals based on machine learning for automated medical applications.

PubMed

Lee, Bum Ju; Kim, Keun Ho; Ku, Boncho; Jang, Jun-Su; Kim, Jong Yeol

2013-05-01

The body mass index (BMI) provides essential medical information related to body weight for the treatment and prognosis prediction of diseases such as cardiovascular disease, diabetes, and stroke. We propose a method for the prediction of normal, overweight, and obese classes based only on the combination of voice features that are associated with BMI status, independently of weight and height measurements. A total of 1568 subjects were divided into 4 groups according to age and gender differences. We performed statistical analyses by analysis of variance (ANOVA) and Scheffe test to find significant features in each group. We predicted BMI status (normal, overweight, and obese) by a logistic regression algorithm and two ensemble classification algorithms (bagging and random forests) based on statistically significant features. In the Female-2030 group (females aged 20-40 years), classification experiments using an imbalanced (original) data set gave area under the receiver operating characteristic curve (AUC) values of 0.569-0.731 by logistic regression, whereas experiments using a balanced data set gave AUC values of 0.893-0.994 by random forests. AUC values in Female-4050 (females aged 41-60 years), Male-2030 (males aged 20-40 years), and Male-4050 (males aged 41-60 years) groups by logistic regression in imbalanced data were 0.585-0.654, 0.581-0.614, and 0.557-0.653, respectively. AUC values in Female-4050, Male-2030, and Male-4050 groups in balanced data were 0.629-0.893 by bagging, 0.707-0.916 by random forests, and 0.695-0.854 by bagging, respectively. In each group, we found discriminatory features showing statistical differences among normal, overweight, and obese classes. The results showed that the classification models built by logistic regression in imbalanced data were better than those built by the other two algorithms, and significant features differed according to age and gender groups. Our results could support the development of BMI diagnosis tools for real-time monitoring; such tools are considered helpful in improving automated BMI status diagnosis in remote healthcare or telemedicine and are expected to have applications in forensic and medical science. Copyright © 2013 Elsevier B.V. All rights reserved.

Applying genetic algorithms to set the optimal combination of forest fire related variables and model forest fire susceptibility based on data mining models. The case of Dayu County, China.

PubMed

Hong, Haoyuan; Tsangaratos, Paraskevas; Ilia, Ioanna; Liu, Junzhi; Zhu, A-Xing; Xu, Chong

2018-07-15

The main objective of the present study was to utilize Genetic Algorithms (GA) in order to obtain the optimal combination of forest fire related variables and apply data mining methods for constructing a forest fire susceptibility map. In the proposed approach, a Random Forest (RF) and a Support Vector Machine (SVM) was used to produce a forest fire susceptibility map for the Dayu County which is located in southwest of Jiangxi Province, China. For this purpose, historic forest fires and thirteen forest fire related variables were analyzed, namely: elevation, slope angle, aspect, curvature, land use, soil cover, heat load index, normalized difference vegetation index, mean annual temperature, mean annual wind speed, mean annual rainfall, distance to river network and distance to road network. The Natural Break and the Certainty Factor method were used to classify and weight the thirteen variables, while a multicollinearity analysis was performed to determine the correlation among the variables and decide about their usability. The optimal set of variables, determined by the GA limited the number of variables into eight excluding from the analysis, aspect, land use, heat load index, distance to river network and mean annual rainfall. The performance of the forest fire models was evaluated by using the area under the Receiver Operating Characteristic curve (ROC-AUC) based on the validation dataset. Overall, the RF models gave higher AUC values. Also the results showed that the proposed optimized models outperform the original models. Specifically, the optimized RF model gave the best results (0.8495), followed by the original RF (0.8169), while the optimized SVM gave lower values (0.7456) than the RF, however higher than the original SVM (0.7148) model. The study highlights the significance of feature selection techniques in forest fire susceptibility, whereas data mining methods could be considered as a valid approach for forest fire susceptibility modeling. Copyright © 2018 Elsevier B.V. All rights reserved.

Pre-operative prediction of surgical morbidity in children: comparison of five statistical models.

PubMed

Cooper, Jennifer N; Wei, Lai; Fernandez, Soledad A; Minneci, Peter C; Deans, Katherine J

2015-02-01

The accurate prediction of surgical risk is important to patients and physicians. Logistic regression (LR) models are typically used to estimate these risks. However, in the fields of data mining and machine-learning, many alternative classification and prediction algorithms have been developed. This study aimed to compare the performance of LR to several data mining algorithms for predicting 30-day surgical morbidity in children. We used the 2012 National Surgical Quality Improvement Program-Pediatric dataset to compare the performance of (1) a LR model that assumed linearity and additivity (simple LR model) (2) a LR model incorporating restricted cubic splines and interactions (flexible LR model) (3) a support vector machine, (4) a random forest and (5) boosted classification trees for predicting surgical morbidity. The ensemble-based methods showed significantly higher accuracy, sensitivity, specificity, PPV, and NPV than the simple LR model. However, none of the models performed better than the flexible LR model in terms of the aforementioned measures or in model calibration or discrimination. Support vector machines, random forests, and boosted classification trees do not show better performance than LR for predicting pediatric surgical morbidity. After further validation, the flexible LR model derived in this study could be used to assist with clinical decision-making based on patient-specific surgical risks. Copyright © 2014 Elsevier Ltd. All rights reserved.

Development of a fire detection algorithm for the COMS (Communication Ocean and Meteorological Satellite)

NASA Astrophysics Data System (ADS)

Kim, Goo; Kim, Dae Sun; Lee, Yang-Won

2013-10-01

The forest fires do much damage to our life in ecological and economic aspects. South Korea is probably more liable to suffer from the forest fire because mountain area occupies more than half of land in South Korea. They have recently launched the COMS(Communication Ocean and Meteorological Satellite) which is a geostationary satellite. In this paper, we developed forest fire detection algorithm using COMS data. Generally, forest fire detection algorithm uses characteristics of 4 and 11 micrometer brightness temperature. Our algorithm additionally uses LST(Land Surface Temperature). We confirmed the result of our fire detection algorithm using statistical data of Korea Forest Service and ASTER(Advanced Spaceborne Thermal Emission and Reflection Radiometer) images. We used the data in South Korea On April 1 and 2, 2011 because there are small and big forest fires at that time. The detection rate was 80% in terms of the frequency of the forest fires and was 99% in terms of the damaged area. Considering the number of COMS's channels and its low resolution, this result is a remarkable outcome. To provide users with the result of our algorithm, we developed a smartphone application for users JSP(Java Server Page). This application can work regardless of the smartphone's operating system. This study can be unsuitable for other areas and days because we used just two days data. To improve the accuracy of our algorithm, we need analysis using long-term data as future work.

Amazon Forest Structure from IKONOS Satellite Data and the Automated Characterization of Forest Canopy Properties

Treesearch

Michael Palace; Michael Keller; Gregory P. Asner; Stephen Hagen; Bobby Braswell

2008-01-01

We developed an automated tree crown analysis algorithm using 1-m panchromatic IKONOS satellite images to examine forest canopy structure in the Brazilian Amazon. The algorithm was calibrated on the landscape level with tree geometry and forest stand data at the Fazenda Cauaxi (3.75◦ S, 48.37◦ W) in the eastern Amazon, and then compared with forest...

Learning-based 3T brain MRI segmentation with guidance from 7T MRI labeling.

PubMed

Deng, Minghui; Yu, Renping; Wang, Li; Shi, Feng; Yap, Pew-Thian; Shen, Dinggang

2016-12-01

Segmentation of brain magnetic resonance (MR) images into white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF) is crucial for brain structural measurement and disease diagnosis. Learning-based segmentation methods depend largely on the availability of good training ground truth. However, the commonly used 3T MR images are of insufficient image quality and often exhibit poor intensity contrast between WM, GM, and CSF. Therefore, they are not ideal for providing good ground truth label data for training learning-based methods. Recent advances in ultrahigh field 7T imaging make it possible to acquire images with excellent intensity contrast and signal-to-noise ratio. In this paper, the authors propose an algorithm based on random forest for segmenting 3T MR images by training a series of classifiers based on reliable labels obtained semiautomatically from 7T MR images. The proposed algorithm iteratively refines the probability maps of WM, GM, and CSF via a cascade of random forest classifiers for improved tissue segmentation. The proposed method was validated on two datasets, i.e., 10 subjects collected at their institution and 797 3T MR images from the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset. Specifically, for the mean Dice ratio of all 10 subjects, the proposed method achieved 94.52% ± 0.9%, 89.49% ± 1.83%, and 79.97% ± 4.32% for WM, GM, and CSF, respectively, which are significantly better than the state-of-the-art methods (p-values < 0.021). For the ADNI dataset, the group difference comparisons indicate that the proposed algorithm outperforms state-of-the-art segmentation methods. The authors have developed and validated a novel fully automated method for 3T brain MR image segmentation. © 2016 American Association of Physicists in Medicine.

Learning-based 3T brain MRI segmentation with guidance from 7T MRI labeling.

PubMed

Deng, Minghui; Yu, Renping; Wang, Li; Shi, Feng; Yap, Pew-Thian; Shen, Dinggang

2016-12-01

Segmentation of brain magnetic resonance (MR) images into white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF) is crucial for brain structural measurement and disease diagnosis. Learning-based segmentation methods depend largely on the availability of good training ground truth. However, the commonly used 3T MR images are of insufficient image quality and often exhibit poor intensity contrast between WM, GM, and CSF. Therefore, they are not ideal for providing good ground truth label data for training learning-based methods. Recent advances in ultrahigh field 7T imaging make it possible to acquire images with excellent intensity contrast and signal-to-noise ratio. In this paper, the authors propose an algorithm based on random forest for segmenting 3T MR images by training a series of classifiers based on reliable labels obtained semiautomatically from 7T MR images. The proposed algorithm iteratively refines the probability maps of WM, GM, and CSF via a cascade of random forest classifiers for improved tissue segmentation. The proposed method was validated on two datasets, i.e., 10 subjects collected at their institution and 797 3T MR images from the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset. Specifically, for the mean Dice ratio of all 10 subjects, the proposed method achieved 94.52% ± 0.9%, 89.49% ± 1.83%, and 79.97% ± 4.32% for WM, GM, and CSF, respectively, which are significantly better than the state-of-the-art methods (p-values < 0.021). For the ADNI dataset, the group difference comparisons indicate that the proposed algorithm outperforms state-of-the-art segmentation methods. The authors have developed and validated a novel fully automated method for 3T brain MR image segmentation.

Classification of suicide attempters in schizophrenia using sociocultural and clinical features: A machine learning approach.

PubMed

Hettige, Nuwan C; Nguyen, Thai Binh; Yuan, Chen; Rajakulendran, Thanara; Baddour, Jermeen; Bhagwat, Nikhil; Bani-Fatemi, Ali; Voineskos, Aristotle N; Mallar Chakravarty, M; De Luca, Vincenzo

2017-07-01

Suicide is a major concern for those afflicted by schizophrenia. Identifying patients at the highest risk for future suicide attempts remains a complex problem for psychiatric interventions. Machine learning models allow for the integration of many risk factors in order to build an algorithm that predicts which patients are likely to attempt suicide. Currently it is unclear how to integrate previously identified risk factors into a clinically relevant predictive tool to estimate the probability of a patient with schizophrenia for attempting suicide. We conducted a cross-sectional assessment on a sample of 345 participants diagnosed with schizophrenia spectrum disorders. Suicide attempters and non-attempters were clearly identified using the Columbia Suicide Severity Rating Scale (C-SSRS) and the Beck Suicide Ideation Scale (BSS). We developed four classification algorithms using a regularized regression, random forest, elastic net and support vector machine models with sociocultural and clinical variables as features to train the models. All classification models performed similarly in identifying suicide attempters and non-attempters. Our regularized logistic regression model demonstrated an accuracy of 67% and an area under the curve (AUC) of 0.71, while the random forest model demonstrated 66% accuracy and an AUC of 0.67. Support vector classifier (SVC) model demonstrated an accuracy of 67% and an AUC of 0.70, and the elastic net model demonstrated and accuracy of 65% and an AUC of 0.71. Machine learning algorithms offer a relatively successful method for incorporating many clinical features to predict individuals at risk for future suicide attempts. Increased performance of these models using clinically relevant variables offers the potential to facilitate early treatment and intervention to prevent future suicide attempts. Copyright © 2017 Elsevier Inc. All rights reserved.

Evaluating total inorganic nitrogen in coastal waters through fusion of multi-temporal RADARSAT-2 and optical imagery using random forest algorithm

NASA Astrophysics Data System (ADS)

Liu, Meiling; Liu, Xiangnan; Li, Jin; Ding, Chao; Jiang, Jiale

2014-12-01

Satellites routinely provide frequent, large-scale, near-surface views of many oceanographic variables pertinent to plankton ecology. However, the nutrient fertility of water can be challenging to detect accurately using remote sensing technology. This research has explored an approach to estimate the nutrient fertility in coastal waters through the fusion of synthetic aperture radar (SAR) images and optical images using the random forest (RF) algorithm. The estimation of total inorganic nitrogen (TIN) in the Hong Kong Sea, China, was used as a case study. In March of 2009 and May and August of 2010, a sequence of multi-temporal in situ data and CCD images from China's HJ-1 satellite and RADARSAT-2 images were acquired. Four sensitive parameters were selected as input variables to evaluate TIN: single-band reflectance, a normalized difference spectral index (NDSI) and HV and VH polarizations. The RF algorithm was used to merge the different input variables from the SAR and optical imagery to generate a new dataset (i.e., the TIN outputs). The results showed the temporal-spatial distribution of TIN. The TIN values decreased from coastal waters to the open water areas, and TIN values in the northeast area were higher than those found in the southwest region of the study area. The maximum TIN values occurred in May. Additionally, the estimation accuracy for estimating TIN was significantly improved when the SAR and optical data were used in combination rather than a single data type alone. This study suggests that this method of estimating nutrient fertility in coastal waters by effectively fusing data from multiple sensors is very promising.

Characterization of cervigram image sharpness using multiple self-referenced measurements and random forest classifiers

NASA Astrophysics Data System (ADS)

Jaiswal, Mayoore; Horning, Matt; Hu, Liming; Ben-Or, Yau; Champlin, Cary; Wilson, Benjamin; Levitz, David

2018-02-01

Cervical cancer is the fourth most common cancer among women worldwide and is especially prevalent in low resource settings due to lack of screening and treatment options. Visual inspection with acetic acid (VIA) is a widespread and cost-effective screening method for cervical pre-cancer lesions, but accuracy depends on the experience level of the health worker. Digital cervicography, capturing images of the cervix, enables review by an off-site expert or potentially a machine learning algorithm. These reviews require images of sufficient quality. However, image quality varies greatly across users. A novel algorithm was developed to evaluate the sharpness of images captured with the MobileODT's digital cervicography device (EVA System), in order to, eventually provide feedback to the health worker. The key challenges are that the algorithm evaluates only a single image of each cervix, it needs to be robust to the variability in cervix images and fast enough to run in real time on a mobile device, and the machine learning model needs to be small enough to fit on a mobile device's memory, train on a small imbalanced dataset and run in real-time. In this paper, the focus scores of a preprocessed image and a Gaussian-blurred version of the image are calculated using established methods and used as features. A feature selection metric is proposed to select the top features which were then used in a random forest classifier to produce the final focus score. The resulting model, based on nine calculated focus scores, achieved significantly better accuracy than any single focus measure when tested on a holdout set of images. The area under the receiver operating characteristics curve was 0.9459.

Data-driven mapping of the potential mountain permafrost distribution.

PubMed

Deluigi, Nicola; Lambiel, Christophe; Kanevski, Mikhail

2017-07-15

Existing mountain permafrost distribution models generally offer a good overview of the potential extent of this phenomenon at a regional scale. They are however not always able to reproduce the high spatial discontinuity of permafrost at the micro-scale (scale of a specific landform; ten to several hundreds of meters). To overcome this lack, we tested an alternative modelling approach using three classification algorithms belonging to statistics and machine learning: Logistic regression, Support Vector Machines and Random forests. These supervised learning techniques infer a classification function from labelled training data (pixels of permafrost absence and presence) with the aim of predicting the permafrost occurrence where it is unknown. The research was carried out in a 588km 2 area of the Western Swiss Alps. Permafrost evidences were mapped from ortho-image interpretation (rock glacier inventorying) and field data (mainly geoelectrical and thermal data). The relationship between selected permafrost evidences and permafrost controlling factors was computed with the mentioned techniques. Classification performances, assessed with AUROC, range between 0.81 for Logistic regression, 0.85 with Support Vector Machines and 0.88 with Random forests. The adopted machine learning algorithms have demonstrated to be efficient for permafrost distribution modelling thanks to consistent results compared to the field reality. The high resolution of the input dataset (10m) allows elaborating maps at the micro-scale with a modelled permafrost spatial distribution less optimistic than classic spatial models. Moreover, the probability output of adopted algorithms offers a more precise overview of the potential distribution of mountain permafrost than proposing simple indexes of the permafrost favorability. These encouraging results also open the way to new possibilities of permafrost data analysis and mapping. Copyright © 2017 Elsevier B.V. All rights reserved.

Simultaneous feature selection and parameter optimisation using an artificial ant colony: case study of melting point prediction

PubMed Central

O'Boyle, Noel M; Palmer, David S; Nigsch, Florian; Mitchell, John BO

2008-01-01

Background We present a novel feature selection algorithm, Winnowing Artificial Ant Colony (WAAC), that performs simultaneous feature selection and model parameter optimisation for the development of predictive quantitative structure-property relationship (QSPR) models. The WAAC algorithm is an extension of the modified ant colony algorithm of Shen et al. (J Chem Inf Model 2005, 45: 1024–1029). We test the ability of the algorithm to develop a predictive partial least squares model for the Karthikeyan dataset (J Chem Inf Model 2005, 45: 581–590) of melting point values. We also test its ability to perform feature selection on a support vector machine model for the same dataset. Results Starting from an initial set of 203 descriptors, the WAAC algorithm selected a PLS model with 68 descriptors which has an RMSE on an external test set of 46.6°C and R2 of 0.51. The number of components chosen for the model was 49, which was close to optimal for this feature selection. The selected SVM model has 28 descriptors (cost of 5, ε of 0.21) and an RMSE of 45.1°C and R2 of 0.54. This model outperforms a kNN model (RMSE of 48.3°C, R2 of 0.47) for the same data and has similar performance to a Random Forest model (RMSE of 44.5°C, R2 of 0.55). However it is much less prone to bias at the extremes of the range of melting points as shown by the slope of the line through the residuals: -0.43 for WAAC/SVM, -0.53 for Random Forest. Conclusion With a careful choice of objective function, the WAAC algorithm can be used to optimise machine learning and regression models that suffer from overfitting. Where model parameters also need to be tuned, as is the case with support vector machine and partial least squares models, it can optimise these simultaneously. The moving probabilities used by the algorithm are easily interpreted in terms of the best and current models of the ants, and the winnowing procedure promotes the removal of irrelevant descriptors. PMID:18959785

Beyond where to how: a machine learning approach for sensing mobility contexts using smartphone sensors.

PubMed

Guinness, Robert E

2015-04-28

This paper presents the results of research on the use of smartphone sensors (namely, GPS and accelerometers), geospatial information (points of interest, such as bus stops and train stations) and machine learning (ML) to sense mobility contexts. Our goal is to develop techniques to continuously and automatically detect a smartphone user's mobility activities, including walking, running, driving and using a bus or train, in real-time or near-real-time (<5 s). We investigated a wide range of supervised learning techniques for classification, including decision trees (DT), support vector machines (SVM), naive Bayes classifiers (NB), Bayesian networks (BN), logistic regression (LR), artificial neural networks (ANN) and several instance-based classifiers (KStar, LWLand IBk). Applying ten-fold cross-validation, the best performers in terms of correct classification rate (i.e., recall) were DT (96.5%), BN (90.9%), LWL (95.5%) and KStar (95.6%). In particular, the DT-algorithm RandomForest exhibited the best overall performance. After a feature selection process for a subset of algorithms, the performance was improved slightly. Furthermore, after tuning the parameters of RandomForest, performance improved to above 97.5%. Lastly, we measured the computational complexity of the classifiers, in terms of central processing unit (CPU) time needed for classification, to provide a rough comparison between the algorithms in terms of battery usage requirements. As a result, the classifiers can be ranked from lowest to highest complexity (i.e., computational cost) as follows: SVM, ANN, LR, BN, DT, NB, IBk, LWL and KStar. The instance-based classifiers take considerably more computational time than the non-instance-based classifiers, whereas the slowest non-instance-based classifier (NB) required about five-times the amount of CPU time as the fastest classifier (SVM). The above results suggest that DT algorithms are excellent candidates for detecting mobility contexts in smartphones, both in terms of performance and computational complexity.

Automated classification of seismic sources in a large database: a comparison of Random Forests and Deep Neural Networks.

NASA Astrophysics Data System (ADS)

Hibert, Clement; Stumpf, André; Provost, Floriane; Malet, Jean-Philippe

2017-04-01

In the past decades, the increasing quality of seismic sensors and capability to transfer remotely large quantity of data led to a fast densification of local, regional and global seismic networks for near real-time monitoring of crustal and surface processes. This technological advance permits the use of seismology to document geological and natural/anthropogenic processes (volcanoes, ice-calving, landslides, snow and rock avalanches, geothermal fields), but also led to an ever-growing quantity of seismic data. This wealth of seismic data makes the construction of complete seismicity catalogs, which include earthquakes but also other sources of seismic waves, more challenging and very time-consuming as this critical pre-processing stage is classically done by human operators and because hundreds of thousands of seismic signals have to be processed. To overcome this issue, the development of automatic methods for the processing of continuous seismic data appears to be a necessity. The classification algorithm should satisfy the need of a method that is robust, precise and versatile enough to be deployed to monitor the seismicity in very different contexts. In this study, we evaluate the ability of machine learning algorithms for the analysis of seismic sources at the Piton de la Fournaise volcano being Random Forest and Deep Neural Network classifiers. We gather a catalog of more than 20,000 events, belonging to 8 classes of seismic sources. We define 60 attributes, based on the waveform, the frequency content and the polarization of the seismic waves, to parameterize the seismic signals recorded. We show that both algorithms provide similar positive classification rates, with values exceeding 90% of the events. When trained with a sufficient number of events, the rate of positive identification can reach 99%. These very high rates of positive identification open the perspective of an operational implementation of these algorithms for near-real time monitoring of mass movements and other environmental sources at the local, regional and even global scale.

Beyond Where to How: A Machine Learning Approach for Sensing Mobility Contexts Using Smartphone Sensors †

PubMed Central

Guinness, Robert E.

2015-01-01

This paper presents the results of research on the use of smartphone sensors (namely, GPS and accelerometers), geospatial information (points of interest, such as bus stops and train stations) and machine learning (ML) to sense mobility contexts. Our goal is to develop techniques to continuously and automatically detect a smartphone user's mobility activities, including walking, running, driving and using a bus or train, in real-time or near-real-time (<5 s). We investigated a wide range of supervised learning techniques for classification, including decision trees (DT), support vector machines (SVM), naive Bayes classifiers (NB), Bayesian networks (BN), logistic regression (LR), artificial neural networks (ANN) and several instance-based classifiers (KStar, LWLand IBk). Applying ten-fold cross-validation, the best performers in terms of correct classification rate (i.e., recall) were DT (96.5%), BN (90.9%), LWL (95.5%) and KStar (95.6%). In particular, the DT-algorithm RandomForest exhibited the best overall performance. After a feature selection process for a subset of algorithms, the performance was improved slightly. Furthermore, after tuning the parameters of RandomForest, performance improved to above 97.5%. Lastly, we measured the computational complexity of the classifiers, in terms of central processing unit (CPU) time needed for classification, to provide a rough comparison between the algorithms in terms of battery usage requirements. As a result, the classifiers can be ranked from lowest to highest complexity (i.e., computational cost) as follows: SVM, ANN, LR, BN, DT, NB, IBk, LWL and KStar. The instance-based classifiers take considerably more computational time than the non-instance-based classifiers, whereas the slowest non-instance-based classifier (NB) required about five-times the amount of CPU time as the fastest classifier (SVM). The above results suggest that DT algorithms are excellent candidates for detecting mobility contexts in smartphones, both in terms of performance and computational complexity. PMID:25928060

Data-Driven Lead-Acid Battery Prognostics Using Random Survival Forests

DTIC Science & Technology

2014-10-02

Kogalur, Blackstone , & Lauer, 2008; Ishwaran & Kogalur, 2010). Random survival forest is a sur- vival analysis extension of Random Forests (Breiman, 2001...Statistics & probability letters, 80(13), 1056–1064. Ishwaran, H., Kogalur, U. B., Blackstone , E. H., & Lauer, M. S. (2008). Random survival forests. The

Exploiting machine learning algorithms for tree species classification in a semiarid woodland using RapidEye image

NASA Astrophysics Data System (ADS)

Adelabu, Samuel; Mutanga, Onisimo; Adam, Elhadi; Cho, Moses Azong

2013-01-01

Classification of different tree species in semiarid areas can be challenging as a result of the change in leaf structure and orientation due to soil moisture constraints. Tree species mapping is, however, a key parameter for forest management in semiarid environments. In this study, we examined the suitability of 5-band RapidEye satellite data for the classification of five tree species in mopane woodland of Botswana using machine leaning algorithms with limited training samples.We performed classification using random forest (RF) and support vector machines (SVM) based on EnMap box. The overall accuracies for classifying the five tree species was 88.75 and 85% for both SVM and RF, respectively. We also demonstrated that the new red-edge band in the RapidEye sensor has the potential for classifying tree species in semiarid environments when integrated with other standard bands. Similarly, we observed that where there are limited training samples, SVM is preferred over RF. Finally, we demonstrated that the two accuracy measures of quantity and allocation disagreement are simpler and more helpful for the vast majority of remote sensing classification process than the kappa coefficient. Overall, high species classification can be achieved using strategically located RapidEye bands integrated with advanced processing algorithms.

Evolving optimised decision rules for intrusion detection using particle swarm paradigm

NASA Astrophysics Data System (ADS)

Sivatha Sindhu, Siva S.; Geetha, S.; Kannan, A.

2012-12-01

The aim of this article is to construct a practical intrusion detection system (IDS) that properly analyses the statistics of network traffic pattern and classify them as normal or anomalous class. The objective of this article is to prove that the choice of effective network traffic features and a proficient machine-learning paradigm enhances the detection accuracy of IDS. In this article, a rule-based approach with a family of six decision tree classifiers, namely Decision Stump, C4.5, Naive Baye's Tree, Random Forest, Random Tree and Representative Tree model to perform the detection of anomalous network pattern is introduced. In particular, the proposed swarm optimisation-based approach selects instances that compose training set and optimised decision tree operate over this trained set producing classification rules with improved coverage, classification capability and generalisation ability. Experiment with the Knowledge Discovery and Data mining (KDD) data set which have information on traffic pattern, during normal and intrusive behaviour shows that the proposed algorithm produces optimised decision rules and outperforms other machine-learning algorithm.

Recognising discourse causality triggers in the biomedical domain.

PubMed

Mihăilă, Claudiu; Ananiadou, Sophia

2013-12-01

Current domain-specific information extraction systems represent an important resource for biomedical researchers, who need to process vast amounts of knowledge in a short time. Automatic discourse causality recognition can further reduce their workload by suggesting possible causal connections and aiding in the curation of pathway models. We describe here an approach to the automatic identification of discourse causality triggers in the biomedical domain using machine learning. We create several baselines and experiment with and compare various parameter settings for three algorithms, i.e. Conditional Random Fields (CRF), Support Vector Machines (SVM) and Random Forests (RF). We also evaluate the impact of lexical, syntactic, and semantic features on each of the algorithms, showing that semantics improves the performance in all cases. We test our comprehensive feature set on two corpora containing gold standard annotations of causal relations, and demonstrate the need for more gold standard data. The best performance of 79.35% F-score is achieved by CRFs when using all three feature types.

Machine learning algorithms for the creation of clinical healthcare enterprise systems

NASA Astrophysics Data System (ADS)

Mandal, Indrajit

2017-10-01

Clinical recommender systems are increasingly becoming popular for improving modern healthcare systems. Enterprise systems are persuasively used for creating effective nurse care plans to provide nurse training, clinical recommendations and clinical quality control. A novel design of a reliable clinical recommender system based on multiple classifier system (MCS) is implemented. A hybrid machine learning (ML) ensemble based on random subspace method and random forest is presented. The performance accuracy and robustness of proposed enterprise architecture are quantitatively estimated to be above 99% and 97%, respectively (above 95% confidence interval). The study then extends to experimental analysis of the clinical recommender system with respect to the noisy data environment. The ranking of items in nurse care plan is demonstrated using machine learning algorithms (MLAs) to overcome the drawback of the traditional association rule method. The promising experimental results are compared against the sate-of-the-art approaches to highlight the advancement in recommendation technology. The proposed recommender system is experimentally validated using five benchmark clinical data to reinforce the research findings.

Machine Learning Algorithms for prediction of regions of high Reynolds Averaged Navier Stokes Uncertainty

NASA Astrophysics Data System (ADS)

Mishra, Aashwin; Iaccarino, Gianluca

2017-11-01

In spite of their deficiencies, RANS models represent the workhorse for industrial investigations into turbulent flows. In this context, it is essential to provide diagnostic measures to assess the quality of RANS predictions. To this end, the primary step is to identify feature importances amongst massive sets of potentially descriptive and discriminative flow features. This aids the physical interpretability of the resultant discrepancy model and its extensibility to similar problems. Recent investigations have utilized approaches such as Random Forests, Support Vector Machines and the Least Absolute Shrinkage and Selection Operator for feature selection. With examples, we exhibit how such methods may not be suitable for turbulent flow datasets. The underlying rationale, such as the correlation bias and the required conditions for the success of penalized algorithms, are discussed with illustrative examples. Finally, we provide alternate approaches using convex combinations of regularized regression approaches and randomized sub-sampling in combination with feature selection algorithms, to infer model structure from data. This research was supported by the Defense Advanced Research Projects Agency under the Enabling Quantification of Uncertainty in Physical Systems (EQUiPS) project (technical monitor: Dr Fariba Fahroo).

A serum protein-based algorithm for the detection of Alzheimer disease.

PubMed

O'Bryant, Sid E; Xiao, Guanghua; Barber, Robert; Reisch, Joan; Doody, Rachelle; Fairchild, Thomas; Adams, Perrie; Waring, Steven; Diaz-Arrastia, Ramon

2010-09-01

To develop an algorithm that separates patients with Alzheimer disease (AD) from controls. Longitudinal case-control study. The Texas Alzheimer's Research Consortium project. Patients  We analyzed serum protein-based multiplex biomarker data from 197 patients diagnosed with AD and 203 controls. Main Outcome Measure  The total sample was randomized equally into training and test sets and random forest methods were applied to the training set to create a biomarker risk score. The biomarker risk score had a sensitivity and specificity of 0.80 and 0.91, respectively, and an area under the curve of 0.91 in detecting AD. When age, sex, education, and APOE status were added to the algorithm, the sensitivity, specificity, and area under the curve were 0.94, 0.84, and 0.95, respectively. These initial data suggest that serum protein-based biomarkers can be combined with clinical information to accurately classify AD. A disproportionate number of inflammatory and vascular markers were weighted most heavily in the analyses. Additionally, these markers consistently distinguished cases from controls in significant analysis of microarray, logistic regression, and Wilcoxon analyses, suggesting the existence of an inflammatory-related endophenotype of AD that may provide targeted therapeutic opportunities for this subset of patients.

Application of Machine-Learning Models to Predict Tacrolimus Stable Dose in Renal Transplant Recipients

NASA Astrophysics Data System (ADS)

Tang, Jie; Liu, Rong; Zhang, Yue-Li; Liu, Mou-Ze; Hu, Yong-Fang; Shao, Ming-Jie; Zhu, Li-Jun; Xin, Hua-Wen; Feng, Gui-Wen; Shang, Wen-Jun; Meng, Xiang-Guang; Zhang, Li-Rong; Ming, Ying-Zi; Zhang, Wei

2017-02-01

Tacrolimus has a narrow therapeutic window and considerable variability in clinical use. Our goal was to compare the performance of multiple linear regression (MLR) and eight machine learning techniques in pharmacogenetic algorithm-based prediction of tacrolimus stable dose (TSD) in a large Chinese cohort. A total of 1,045 renal transplant patients were recruited, 80% of which were randomly selected as the “derivation cohort” to develop dose-prediction algorithm, while the remaining 20% constituted the “validation cohort” to test the final selected algorithm. MLR, artificial neural network (ANN), regression tree (RT), multivariate adaptive regression splines (MARS), boosted regression tree (BRT), support vector regression (SVR), random forest regression (RFR), lasso regression (LAR) and Bayesian additive regression trees (BART) were applied and their performances were compared in this work. Among all the machine learning models, RT performed best in both derivation [0.71 (0.67-0.76)] and validation cohorts [0.73 (0.63-0.82)]. In addition, the ideal rate of RT was 4% higher than that of MLR. To our knowledge, this is the first study to use machine learning models to predict TSD, which will further facilitate personalized medicine in tacrolimus administration in the future.

Why choose Random Forest to predict rare species distribution with few samples in large undersampled areas? Three Asian crane species models provide supporting evidence.

PubMed

Mi, Chunrong; Huettmann, Falk; Guo, Yumin; Han, Xuesong; Wen, Lijia

2017-01-01

Species distribution models (SDMs) have become an essential tool in ecology, biogeography, evolution and, more recently, in conservation biology. How to generalize species distributions in large undersampled areas, especially with few samples, is a fundamental issue of SDMs. In order to explore this issue, we used the best available presence records for the Hooded Crane ( Grus monacha , n  = 33), White-naped Crane ( Grus vipio , n  = 40), and Black-necked Crane ( Grus nigricollis , n  = 75) in China as three case studies, employing four powerful and commonly used machine learning algorithms to map the breeding distributions of the three species: TreeNet (Stochastic Gradient Boosting, Boosted Regression Tree Model), Random Forest, CART (Classification and Regression Tree) and Maxent (Maximum Entropy Models). In addition, we developed an ensemble forecast by averaging predicted probability of the above four models results. Commonly used model performance metrics (Area under ROC (AUC) and true skill statistic (TSS)) were employed to evaluate model accuracy. The latest satellite tracking data and compiled literature data were used as two independent testing datasets to confront model predictions. We found Random Forest demonstrated the best performance for the most assessment method, provided a better model fit to the testing data, and achieved better species range maps for each crane species in undersampled areas. Random Forest has been generally available for more than 20 years and has been known to perform extremely well in ecological predictions. However, while increasingly on the rise, its potential is still widely underused in conservation, (spatial) ecological applications and for inference. Our results show that it informs ecological and biogeographical theories as well as being suitable for conservation applications, specifically when the study area is undersampled. This method helps to save model-selection time and effort, and allows robust and rapid assessments and decisions for efficient conservation.

Why choose Random Forest to predict rare species distribution with few samples in large undersampled areas? Three Asian crane species models provide supporting evidence

PubMed Central

Mi, Chunrong; Huettmann, Falk; Han, Xuesong; Wen, Lijia

2017-01-01

Species distribution models (SDMs) have become an essential tool in ecology, biogeography, evolution and, more recently, in conservation biology. How to generalize species distributions in large undersampled areas, especially with few samples, is a fundamental issue of SDMs. In order to explore this issue, we used the best available presence records for the Hooded Crane (Grus monacha, n = 33), White-naped Crane (Grus vipio, n = 40), and Black-necked Crane (Grus nigricollis, n = 75) in China as three case studies, employing four powerful and commonly used machine learning algorithms to map the breeding distributions of the three species: TreeNet (Stochastic Gradient Boosting, Boosted Regression Tree Model), Random Forest, CART (Classification and Regression Tree) and Maxent (Maximum Entropy Models). In addition, we developed an ensemble forecast by averaging predicted probability of the above four models results. Commonly used model performance metrics (Area under ROC (AUC) and true skill statistic (TSS)) were employed to evaluate model accuracy. The latest satellite tracking data and compiled literature data were used as two independent testing datasets to confront model predictions. We found Random Forest demonstrated the best performance for the most assessment method, provided a better model fit to the testing data, and achieved better species range maps for each crane species in undersampled areas. Random Forest has been generally available for more than 20 years and has been known to perform extremely well in ecological predictions. However, while increasingly on the rise, its potential is still widely underused in conservation, (spatial) ecological applications and for inference. Our results show that it informs ecological and biogeographical theories as well as being suitable for conservation applications, specifically when the study area is undersampled. This method helps to save model-selection time and effort, and allows robust and rapid assessments and decisions for efficient conservation. PMID:28097060

Methods for Real-Time Prediction of the Mode of Travel Using Smartphone-Based GPS and Accelerometer Data

PubMed Central

Martin, Bryan D.; Wolfson, Julian; Adomavicius, Gediminas; Fan, Yingling

2017-01-01

We propose and compare combinations of several methods for classifying transportation activity data from smartphone GPS and accelerometer sensors. We have two main objectives. First, we aim to classify our data as accurately as possible. Second, we aim to reduce the dimensionality of the data as much as possible in order to reduce the computational burden of the classification. We combine dimension reduction and classification algorithms and compare them with a metric that balances accuracy and dimensionality. In doing so, we develop a classification algorithm that accurately classifies five different modes of transportation (i.e., walking, biking, car, bus and rail) while being computationally simple enough to run on a typical smartphone. Further, we use data that required no behavioral changes from the smartphone users to collect. Our best classification model uses the random forest algorithm to achieve 96.8% accuracy. PMID:28885550

Methods for Real-Time Prediction of the Mode of Travel Using Smartphone-Based GPS and Accelerometer Data.

PubMed

Martin, Bryan D; Addona, Vittorio; Wolfson, Julian; Adomavicius, Gediminas; Fan, Yingling

2017-09-08

We propose and compare combinations of several methods for classifying transportation activity data from smartphone GPS and accelerometer sensors. We have two main objectives. First, we aim to classify our data as accurately as possible. Second, we aim to reduce the dimensionality of the data as much as possible in order to reduce the computational burden of the classification. We combine dimension reduction and classification algorithms and compare them with a metric that balances accuracy and dimensionality. In doing so, we develop a classification algorithm that accurately classifies five different modes of transportation (i.e., walking, biking, car, bus and rail) while being computationally simple enough to run on a typical smartphone. Further, we use data that required no behavioral changes from the smartphone users to collect. Our best classification model uses the random forest algorithm to achieve 96.8% accuracy.

On the information content of hydrological signatures and their relationship to catchment attributes

NASA Astrophysics Data System (ADS)

Addor, Nans; Clark, Martyn P.; Prieto, Cristina; Newman, Andrew J.; Mizukami, Naoki; Nearing, Grey; Le Vine, Nataliya

2017-04-01

Hydrological signatures, which are indices characterizing hydrologic behavior, are increasingly used for the evaluation, calibration and selection of hydrological models. Their key advantage is to provide more direct insights into specific hydrological processes than aggregated metrics (e.g., the Nash-Sutcliffe efficiency). A plethora of signatures now exists, which enable characterizing a variety of hydrograph features, but also makes the selection of signatures for new studies challenging. Here we propose that the selection of signatures should be based on their information content, which we estimated using several approaches, all leading to similar conclusions. To explore the relationship between hydrological signatures and the landscape, we extended a previously published data set of hydrometeorological time series for 671 catchments in the contiguous United States, by characterizing the climatic conditions, topography, soil, vegetation and stream network of each catchment. This new catchment attributes data set will soon be in open access, and we are looking forward to introducing it to the community. We used this data set in a data-learning algorithm (random forests) to explore whether hydrological signatures could be inferred from catchment attributes alone. We find that some signatures can be predicted remarkably well by random forests and, interestingly, the same signatures are well captured when simulating discharge using a conceptual hydrological model. We discuss what this result reveals about our understanding of hydrological processes shaping hydrological signatures. We also identify which catchment attributes exert the strongest control on catchment behavior, in particular during extreme hydrological events. Overall, climatic attributes have the most significant influence, and strongly condition how well hydrological signatures can be predicted by random forests and simulated by the hydrological model. In contrast, soil characteristics at the catchment scale are not found to be significant predictors by random forests, which raises questions on how to best use soil data for hydrological modeling, for instance for parameter estimation. We finally demonstrate that signatures with high spatial variability are poorly captured by random forests and model simulations, which makes their regionalization delicate. We conclude with a ranking of signatures based on their information content, and propose that the signatures with high information content are best suited for model calibration, model selection and understanding hydrologic similarity.

Comparison of machine-learning methods for above-ground biomass estimation based on Landsat imagery

NASA Astrophysics Data System (ADS)

Wu, Chaofan; Shen, Huanhuan; Shen, Aihua; Deng, Jinsong; Gan, Muye; Zhu, Jinxia; Xu, Hongwei; Wang, Ke

2016-07-01

Biomass is one significant biophysical parameter of a forest ecosystem, and accurate biomass estimation on the regional scale provides important information for carbon-cycle investigation and sustainable forest management. In this study, Landsat satellite imagery data combined with field-based measurements were integrated through comparisons of five regression approaches [stepwise linear regression, K-nearest neighbor, support vector regression, random forest (RF), and stochastic gradient boosting] with two different candidate variable strategies to implement the optimal spatial above-ground biomass (AGB) estimation. The results suggested that RF algorithm exhibited the best performance by 10-fold cross-validation with respect to R2 (0.63) and root-mean-square error (26.44 ton/ha). Consequently, the map of estimated AGB was generated with a mean value of 89.34 ton/ha in northwestern Zhejiang Province, China, with a similar pattern to the distribution mode of local forest species. This research indicates that machine-learning approaches associated with Landsat imagery provide an economical way for biomass estimation. Moreover, ensemble methods using all candidate variables, especially for Landsat images, provide an alternative for regional biomass simulation.

Improved forest change detection with terrain illumination corrected landsat images

USDA-ARS?s Scientific Manuscript database

An illumination correction algorithm has been developed to improve the accuracy of forest change detection from Landsat reflectance data. This algorithm is based on an empirical rotation model and was tested on the Landsat imagery pair over Cherokee National Forest, Tennessee, Uinta-Wasatch-Cache N...

Random Forests (RFs) for Estimation, Uncertainty Prediction and Interpretation of Monthly Solar Potential

NASA Astrophysics Data System (ADS)

Assouline, Dan; Mohajeri, Nahid; Scartezzini, Jean-Louis

2017-04-01

Solar energy is clean, widely available, and arguably the most promising renewable energy resource. Taking full advantage of solar power, however, requires a deep understanding of its patterns and dependencies in space and time. The recent advances in Machine Learning brought powerful algorithms to estimate the spatio-temporal variations of solar irradiance (the power per unit area received from the Sun, W/m2), using local weather and terrain information. Such algorithms include Deep Learning (e.g. Artificial Neural Networks), or kernel methods (e.g. Support Vector Machines). However, most of these methods have some disadvantages, as they: (i) are complex to tune, (ii) are mainly used as a black box and offering no interpretation on the variables contributions, (iii) often do not provide uncertainty predictions (Assouline et al., 2016). To provide a reasonable solar mapping with good accuracy, these gaps would ideally need to be filled. We present here simple steps using one ensemble learning algorithm namely, Random Forests (Breiman, 2001) to (i) estimate monthly solar potential with good accuracy, (ii) provide information on the contribution of each feature in the estimation, and (iii) offer prediction intervals for each point estimate. We have selected Switzerland as an example. Using a Digital Elevation Model (DEM) along with monthly solar irradiance time series and weather data, we build monthly solar maps for Global Horizontal Irradiance (GHI), Diffuse Horizontal Irradiance (GHI), and Extraterrestrial Irradiance (EI). The weather data include monthly values for temperature, precipitation, sunshine duration, and cloud cover. In order to explain the impact of each feature on the solar irradiance of each point estimate, we extend the contribution method (Kuz'min et al., 2011) to a regression setting. Contribution maps for all features can then be computed for each solar map. This provides precious information on the spatial variation of the features impact all across Switzerland maps. Finally, as RFs are based on bootstrap samples of the training data, they can produce prediction intervals by looking at the trees estimates distribution, instead of taking the mean estimate. To do so, a simple idea is to grow all trees fully so that each leaf has exactly one value, that is, a training sample value. Then, for each point estimate, we compute percentiles of the trees estimates data to build a prediction interval. Two issues arise from this process: (i) growing the trees fully is not always possible, and (ii) there is a risk of over-fitting. We show how to solve them. These steps can be used for any type of environmental mapping so as to extract useful information on uncertainty and feature impact interpretation. References -Assouline, D., Mohajeri, N., & Scartezzini, J. L. (2017). Quantifying rooftop photovoltaic solar energy potential: A machine learning approach. Solar Energy, 141, 278-296. -Breiman, L. (2001). Random forests. Machine learning, 45(1), 5-32. -Kuz'min, V. E., Polishchuk, P. G., Artemenko, A. G., & Andronati, S. A. (2011). Interpretation of QSAR models based on random forest methods. Molecular Informatics, 30(6-7), 593-603.

Improving the MODIS Global Snow-Mapping Algorithm

NASA Technical Reports Server (NTRS)

Klein, Andrew G.; Hall, Dorothy K.; Riggs, George A.

1997-01-01

An algorithm (Snowmap) is under development to produce global snow maps at 500 meter resolution on a daily basis using data from the NASA MODIS instrument. MODIS, the Moderate Resolution Imaging Spectroradiometer, will be launched as part of the first Earth Observing System (EOS) platform in 1998. Snowmap is a fully automated, computationally frugal algorithm that will be ready to implement at launch. Forests represent a major limitation to the global mapping of snow cover as a forest canopy both obscures and shadows the snow underneath. Landsat Thematic Mapper (TM) and MODIS Airborne Simulator (MAS) data are used to investigate the changes in reflectance that occur as a forest stand becomes snow covered and to propose changes to the Snowmap algorithm that will improve snow classification accuracy forested areas.

c-Fos expression predicts long-term social memory retrieval in mice.

PubMed

Lüscher Dias, Thomaz; Fernandes Golino, Hudson; Moura de Oliveira, Vinícius Elias; Dutra Moraes, Márcio Flávio; Schenatto Pereira, Grace

2016-10-15

The way the rodent brain generally processes socially relevant information is rather well understood. How social information is stored into long-term social memory, however, is still under debate. Here, brain c-Fos expression was measured after adult mice were exposed to familiar or novel juveniles and expression was compared in several memory and socially relevant brain areas. Machine Learning algorithm Random Forest was then used to predict the social interaction category of adult mice based on c-Fos expression in these areas. Interaction with a familiar co-specific altered brain activation in the olfactory bulb, amygdala, hippocampus, lateral septum and medial prefrontal cortex. Remarkably, Random Forest was able to predict interaction with a familiar juvenile with 100% accuracy. Activity in the olfactory bulb, amygdala, hippocampus and the medial prefrontal cortex were crucial to this prediction. From our results, we suggest long-term social memory depends on initial social olfactory processing in the medial amygdala and its output connections synergistically with non-social contextual integration by the hippocampus and medial prefrontal cortex top-down modulation of primary olfactory structures. Copyright © 2016 Elsevier B.V. All rights reserved.

Quantifying and Characterizing Tonic Thermal Pain Across Subjects From EEG Data Using Random Forest Models.

PubMed

Vijayakumar, Vishal; Case, Michelle; Shirinpour, Sina; He, Bin

2017-12-01

Effective pain assessment and management strategies are needed to better manage pain. In addition to self-report, an objective pain assessment system can provide a more complete picture of the neurophysiological basis for pain. In this study, a robust and accurate machine learning approach is developed to quantify tonic thermal pain across healthy subjects into a maximum of ten distinct classes. A random forest model was trained to predict pain scores using time-frequency wavelet representations of independent components obtained from electroencephalography (EEG) data, and the relative importance of each frequency band to pain quantification is assessed. The mean classification accuracy for predicting pain on an independent test subject for a range of 1-10 is 89.45%, highest among existing state of the art quantification algorithms for EEG. The gamma band is the most important to both intersubject and intrasubject classification accuracy. The robustness and generalizability of the classifier are demonstrated. Our results demonstrate the potential of this tool to be used clinically to help us to improve chronic pain treatment and establish spectral biomarkers for future pain-related studies using EEG.

Text Categorization on Hadith Sahih Al-Bukhari using Random Forest

NASA Astrophysics Data System (ADS)

Fauzan Afianto, Muhammad; Adiwijaya; Al-Faraby, Said

2018-03-01

Al-Hadith is a collection of words, deeds, provisions, and approvals of Rasulullah Shallallahu Alaihi wa Salam that becomes the second fundamental laws of Islam after Al-Qur’an. As a fundamental of Islam, Muslims must learn, memorize, and practice Al-Qur’an and Al-Hadith. One of venerable Imam which was also the narrator of Al-Hadith is Imam Bukhari. He spent over 16 years to compile about 2602 Hadith (without repetition) and over 7000 Hadith with repetition. Automatic text categorization is a task of developing software tools that able to classify text of hypertext document under pre-defined categories or subject code[1]. The algorithm that would be used is Random Forest, which is a development from Decision Tree. In this final project research, the author decided to make a system that able to categorize text document that contains Hadith that narrated by Imam Bukhari under several categories such as suggestion, prohibition, and information. As for the evaluation method, K-fold cross validation with F1-Score will be used and the result is 90%.

Evaluation of Semi-supervised Learning for Classification of Protein Crystallization Imagery.

PubMed

Sigdel, Madhav; Dinç, İmren; Dinç, Semih; Sigdel, Madhu S; Pusey, Marc L; Aygün, Ramazan S

2014-03-01

In this paper, we investigate the performance of two wrapper methods for semi-supervised learning algorithms for classification of protein crystallization images with limited labeled images. Firstly, we evaluate the performance of semi-supervised approach using self-training with naïve Bayesian (NB) and sequential minimum optimization (SMO) as the base classifiers. The confidence values returned by these classifiers are used to select high confident predictions to be used for self-training. Secondly, we analyze the performance of Yet Another Two Stage Idea (YATSI) semi-supervised learning using NB, SMO, multilayer perceptron (MLP), J48 and random forest (RF) classifiers. These results are compared with the basic supervised learning using the same training sets. We perform our experiments on a dataset consisting of 2250 protein crystallization images for different proportions of training and test data. Our results indicate that NB and SMO using both self-training and YATSI semi-supervised approaches improve accuracies with respect to supervised learning. On the other hand, MLP, J48 and RF perform better using basic supervised learning. Overall, random forest classifier yields the best accuracy with supervised learning for our dataset.

An evaluation of ISOCLS and CLASSY clustering algorithms for forest classification in northern Idaho. [Elk River quadrange of the Clearwater National Forest

NASA Technical Reports Server (NTRS)

Werth, L. F. (Principal Investigator)

1981-01-01

Both the iterative self-organizing clustering system (ISOCLS) and the CLASSY algorithms were applied to forest and nonforest classes for one 1:24,000 quadrangle map of northern Idaho and the classification and mapping accuracies were evaluated with 1:30,000 color infrared aerial photography. Confusion matrices for the two clustering algorithms were generated and studied to determine which is most applicable to forest and rangeland inventories in future projects. In an unsupervised mode, ISOCLS requires many trial-and-error runs to find the proper parameters to separate desired information classes. CLASSY tells more in a single run concerning the classes that can be separated, shows more promise for forest stratification than ISOCLS, and shows more promise for consistency. One major drawback to CLASSY is that important forest and range classes that are smaller than a minimum cluster size will be combined with other classes. The algorithm requires so much computer storage that only data sets as small as a quadrangle can be used at one time.

Scalable Nearest Neighbor Algorithms for High Dimensional Data.

PubMed

Muja, Marius; Lowe, David G

2014-11-01

For many computer vision and machine learning problems, large training sets are key for good performance. However, the most computationally expensive part of many computer vision and machine learning algorithms consists of finding nearest neighbor matches to high dimensional vectors that represent the training data. We propose new algorithms for approximate nearest neighbor matching and evaluate and compare them with previous algorithms. For matching high dimensional features, we find two algorithms to be the most efficient: the randomized k-d forest and a new algorithm proposed in this paper, the priority search k-means tree. We also propose a new algorithm for matching binary features by searching multiple hierarchical clustering trees and show it outperforms methods typically used in the literature. We show that the optimal nearest neighbor algorithm and its parameters depend on the data set characteristics and describe an automated configuration procedure for finding the best algorithm to search a particular data set. In order to scale to very large data sets that would otherwise not fit in the memory of a single machine, we propose a distributed nearest neighbor matching framework that can be used with any of the algorithms described in the paper. All this research has been released as an open source library called fast library for approximate nearest neighbors (FLANN), which has been incorporated into OpenCV and is now one of the most popular libraries for nearest neighbor matching.

Continuous Change Detection and Classification (CCDC) of Land Cover Using All Available Landsat Data

NASA Astrophysics Data System (ADS)

Zhu, Z.; Woodcock, C. E.

2012-12-01

A new algorithm for Continuous Change Detection and Classification (CCDC) of land cover using all available Landsat data is developed. This new algorithm is capable of detecting many kinds of land cover change as new images are collected and at the same time provide land cover maps for any given time. To better identify land cover change, a two step cloud, cloud shadow, and snow masking algorithm is used for eliminating "noisy" observations. Next, a time series model that has components of seasonality, trend, and break estimates the surface reflectance and temperature. The time series model is updated continuously with newly acquired observations. Due to the high variability in spectral response for different kinds of land cover change, the CCDC algorithm uses a data-driven threshold derived from all seven Landsat bands. When the difference between observed and predicted exceeds the thresholds three consecutive times, a pixel is identified as land cover change. Land cover classification is done after change detection. Coefficients from the time series models and the Root Mean Square Error (RMSE) from model fitting are used as classification inputs for the Random Forest Classifier (RFC). We applied this new algorithm for one Landsat scene (Path 12 Row 31) that includes all of Rhode Island as well as much of Eastern Massachusetts and parts of Connecticut. A total of 532 Landsat images acquired between 1982 and 2011 were processed. During this period, 619,924 pixels were detected to change once (91% of total changed pixels) and 60,199 pixels were detected to change twice (8% of total changed pixels). The most frequent land cover change category is from mixed forest to low density residential which occupies more than 8% of total land cover change pixels.

Multivariate classification with random forests for gravitational wave searches of black hole binary coalescence

NASA Astrophysics Data System (ADS)

Baker, Paul T.; Caudill, Sarah; Hodge, Kari A.; Talukder, Dipongkar; Capano, Collin; Cornish, Neil J.

2015-03-01

Searches for gravitational waves produced by coalescing black hole binaries with total masses ≳25 M⊙ use matched filtering with templates of short duration. Non-Gaussian noise bursts in gravitational wave detector data can mimic short signals and limit the sensitivity of these searches. Previous searches have relied on empirically designed statistics incorporating signal-to-noise ratio and signal-based vetoes to separate gravitational wave candidates from noise candidates. We report on sensitivity improvements achieved using a multivariate candidate ranking statistic derived from a supervised machine learning algorithm. We apply the random forest of bagged decision trees technique to two separate searches in the high mass (≳25 M⊙ ) parameter space. For a search which is sensitive to gravitational waves from the inspiral, merger, and ringdown of binary black holes with total mass between 25 M⊙ and 100 M⊙ , we find sensitive volume improvements as high as 70±13%-109±11% when compared to the previously used ranking statistic. For a ringdown-only search which is sensitive to gravitational waves from the resultant perturbed intermediate mass black hole with mass roughly between 10 M⊙ and 600 M⊙ , we find sensitive volume improvements as high as 61±4%-241±12% when compared to the previously used ranking statistic. We also report how sensitivity improvements can differ depending on mass regime, mass ratio, and available data quality information. Finally, we describe the techniques used to tune and train the random forest classifier that can be generalized to its use in other searches for gravitational waves.

Comparison of Models for the Prediction of Medical Costs of Spinal Fusion in Taiwan Diagnosis-Related Groups by Machine Learning Algorithms.

PubMed

Kuo, Ching-Yen; Yu, Liang-Chin; Chen, Hou-Chaung; Chan, Chien-Lung

2018-01-01

The aims of this study were to compare the performance of machine learning methods for the prediction of the medical costs associated with spinal fusion in terms of profit or loss in Taiwan Diagnosis-Related Groups (Tw-DRGs) and to apply these methods to explore the important factors associated with the medical costs of spinal fusion. A data set was obtained from a regional hospital in Taoyuan city in Taiwan, which contained data from 2010 to 2013 on patients of Tw-DRG49702 (posterior and other spinal fusion without complications or comorbidities). Naïve-Bayesian, support vector machines, logistic regression, C4.5 decision tree, and random forest methods were employed for prediction using WEKA 3.8.1. Five hundred thirty-two cases were categorized as belonging to the Tw-DRG49702 group. The mean medical cost was US $4,549.7, and the mean age of the patients was 62.4 years. The mean length of stay was 9.3 days. The length of stay was an important variable in terms of determining medical costs for patients undergoing spinal fusion. The random forest method had the best predictive performance in comparison to the other methods, achieving an accuracy of 84.30%, a sensitivity of 71.4%, a specificity of 92.2%, and an AUC of 0.904. Our study demonstrated that the random forest model can be employed to predict the medical costs of Tw-DRG49702, and could inform hospital strategy in terms of increasing the financial management efficiency of this operation.

Prediction of soil attributes through interpolators in a deglaciated environment with complex landforms

NASA Astrophysics Data System (ADS)

Schünemann, Adriano Luis; Inácio Fernandes Filho, Elpídio; Rocha Francelino, Marcio; Rodrigues Santos, Gérson; Thomazini, Andre; Batista Pereira, Antônio; Gonçalves Reynaud Schaefer, Carlos Ernesto

2017-04-01

The knowledge of environmental variables values, in non-sampled sites from a minimum data set can be accessed through interpolation technique. Kriging and the classifier Random Forest algorithm are examples of predictors with this aim. The objective of this work was to compare methods of soil attributes spatialization in a recent deglaciated environment with complex landforms. Prediction of the selected soil attributes (potassium, calcium and magnesium) from ice-free areas were tested by using morphometric covariables, and geostatistical models without these covariables. For this, 106 soil samples were collected at 0-10 cm depth in Keller Peninsula, King George Island, Maritime Antarctica. Soil chemical analysis was performed by the gravimetric method, determining values of potassium, calcium and magnesium for each sampled point. Digital terrain models (DTMs) were obtained by using Terrestrial Laser Scanner. DTMs were generated from a cloud of points with spatial resolutions of 1, 5, 10, 20 and 30 m. Hence, 40 morphometric covariates were generated. Simple Kriging was performed using the R package software. The same data set coupled with morphometric covariates, was used to predict values of the studied attributes in non-sampled sites through Random Forest interpolator. Little differences were observed on the DTMs generated by Simple kriging and Random Forest interpolators. Also, DTMs with better spatial resolution did not improved the quality of soil attributes prediction. Results revealed that Simple Kriging can be used as interpolator when morphometric covariates are not available, with little impact regarding quality. It is necessary to go further in soil chemical attributes prediction techniques, especially in periglacial areas with complex landforms.

The brain MRI classification problem from wavelets perspective

NASA Astrophysics Data System (ADS)

Bendib, Mohamed M.; Merouani, Hayet F.; Diaba, Fatma

2015-02-01

Haar and Daubechies 4 (DB4) are the most used wavelets for brain MRI (Magnetic Resonance Imaging) classification. The former is simple and fast to compute while the latter is more complex and offers a better resolution. This paper explores the potential of both of them in performing Normal versus Pathological discrimination on the one hand, and Multiclassification on the other hand. The Whole Brain Atlas is used as a validation database, and the Random Forest (RF) algorithm is employed as a learning approach. The achieved results are discussed and statistically compared.

Large unbalanced credit scoring using Lasso-logistic regression ensemble.

PubMed

Wang, Hong; Xu, Qingsong; Zhou, Lifeng

2015-01-01

Recently, various ensemble learning methods with different base classifiers have been proposed for credit scoring problems. However, for various reasons, there has been little research using logistic regression as the base classifier. In this paper, given large unbalanced data, we consider the plausibility of ensemble learning using regularized logistic regression as the base classifier to deal with credit scoring problems. In this research, the data is first balanced and diversified by clustering and bagging algorithms. Then we apply a Lasso-logistic regression learning ensemble to evaluate the credit risks. We show that the proposed algorithm outperforms popular credit scoring models such as decision tree, Lasso-logistic regression and random forests in terms of AUC and F-measure. We also provide two importance measures for the proposed model to identify important variables in the data.

Prediction of protein-protein interaction network using a multi-objective optimization approach.

PubMed

Chowdhury, Archana; Rakshit, Pratyusha; Konar, Amit

2016-06-01

Protein-Protein Interactions (PPIs) are very important as they coordinate almost all cellular processes. This paper attempts to formulate PPI prediction problem in a multi-objective optimization framework. The scoring functions for the trial solution deal with simultaneous maximization of functional similarity, strength of the domain interaction profiles, and the number of common neighbors of the proteins predicted to be interacting. The above optimization problem is solved using the proposed Firefly Algorithm with Nondominated Sorting. Experiments undertaken reveal that the proposed PPI prediction technique outperforms existing methods, including gene ontology-based Relative Specific Similarity, multi-domain-based Domain Cohesion Coupling method, domain-based Random Decision Forest method, Bagging with REP Tree, and evolutionary/swarm algorithm-based approaches, with respect to sensitivity, specificity, and F1 score.

Cascaded face alignment via intimacy definition feature

NASA Astrophysics Data System (ADS)

Li, Hailiang; Lam, Kin-Man; Chiu, Man-Yau; Wu, Kangheng; Lei, Zhibin

2017-09-01

Recent years have witnessed the emerging popularity of regression-based face aligners, which directly learn mappings between facial appearance and shape-increment manifolds. We propose a random-forest based, cascaded regression model for face alignment by using a locally lightweight feature, namely intimacy definition feature. This feature is more discriminative than the pose-indexed feature, more efficient than the histogram of oriented gradients feature and the scale-invariant feature transform feature, and more compact than the local binary feature (LBF). Experimental validation of our algorithm shows that our approach achieves state-of-the-art performance when testing on some challenging datasets. Compared with the LBF-based algorithm, our method achieves about twice the speed, 20% improvement in terms of alignment accuracy and saves an order of magnitude on memory requirement.

Large-Scale Mixed Temperate Forest Mapping at the Single Tree Level using Airborne Laser Scanning

NASA Astrophysics Data System (ADS)

Scholl, V.; Morsdorf, F.; Ginzler, C.; Schaepman, M. E.

2017-12-01

Monitoring vegetation on a single tree level is critical to understand and model a variety of processes, functions, and changes in forest systems. Remote sensing technologies are increasingly utilized to complement and upscale the field-based measurements of forest inventories. Airborne laser scanning (ALS) systems provide valuable information in the vertical dimension for effective vegetation structure mapping. Although many algorithms exist to extract single tree segments from forest scans, they are often tuned to perform well in homogeneous coniferous or deciduous areas and are not successful in mixed forests. Other methods are too computationally expensive to apply operationally. The aim of this study was to develop a single tree detection workflow using leaf-off ALS data for the canton of Aargau in Switzerland. Aargau covers an area of over 1,400km2 and features mixed forests with various development stages and topography. Forest type was classified using random forests to guide local parameter selection. Canopy height model-based treetop maxima were detected and maintained based on the relationship between tree height and window size, used as a proxy to crown diameter. Watershed segmentation was used to generate crown polygons surrounding each maximum. The location, height, and crown dimensions of single trees were derived from the ALS returns within each polygon. Validation was performed through comparison with field measurements and extrapolated estimates from long-term monitoring plots of the Swiss National Forest Inventory within the framework of the Swiss Federal Institute for Forest, Snow, and Landscape Research. This method shows promise for robust, large-scale single tree detection in mixed forests. The single tree data will aid ecological studies as well as forest management practices. Figure description: Height-normalized ALS point cloud data (top) and resulting single tree segments (bottom) on the Laegeren mountain in Switzerland.

Virtual screening by a new Clustering-based Weighted Similarity Extreme Learning Machine approach

PubMed Central

Kudisthalert, Wasu

2018-01-01

Machine learning techniques are becoming popular in virtual screening tasks. One of the powerful machine learning algorithms is Extreme Learning Machine (ELM) which has been applied to many applications and has recently been applied to virtual screening. We propose the Weighted Similarity ELM (WS-ELM) which is based on a single layer feed-forward neural network in a conjunction of 16 different similarity coefficients as activation function in the hidden layer. It is known that the performance of conventional ELM is not robust due to random weight selection in the hidden layer. Thus, we propose a Clustering-based WS-ELM (CWS-ELM) that deterministically assigns weights by utilising clustering algorithms i.e. k-means clustering and support vector clustering. The experiments were conducted on one of the most challenging datasets–Maximum Unbiased Validation Dataset–which contains 17 activity classes carefully selected from PubChem. The proposed algorithms were then compared with other machine learning techniques such as support vector machine, random forest, and similarity searching. The results show that CWS-ELM in conjunction with support vector clustering yields the best performance when utilised together with Sokal/Sneath(1) coefficient. Furthermore, ECFP_6 fingerprint presents the best results in our framework compared to the other types of fingerprints, namely ECFP_4, FCFP_4, and FCFP_6. PMID:29652912

Validation of optical codes based on 3D nanostructures

NASA Astrophysics Data System (ADS)

Carnicer, Artur; Javidi, Bahram

2017-05-01

Image information encoding using random phase masks produce speckle-like noise distributions when the sample is propagated in the Fresnel domain. As a result, information cannot be accessed by simple visual inspection. Phase masks can be easily implemented in practice by attaching cello-tape to the plain-text message. Conventional 2D-phase masks can be generalized to 3D by combining glass and diffusers resulting in a more complex, physical unclonable function. In this communication, we model the behavior of a 3D phase mask using a simple approach: light is propagated trough glass using the angular spectrum of plane waves whereas the diffusor is described as a random phase mask and a blurring effect on the amplitude of the propagated wave. Using different designs for the 3D phase mask and multiple samples, we demonstrate that classification is possible using the k-nearest neighbors and random forests machine learning algorithms.

Regional mapping of forest canopy water content and biomass using AIRSAR images over BOREAS study area

NASA Technical Reports Server (NTRS)

Saatchi, Sasan; Rignot, Eric; Vanzyl, Jakob

1995-01-01

In recent years, monitoring vegetation biomass over various climate zones has become the primary focus of several studies interested in assessing the role of the ecosystem responses to climate change and human activities. Airborne and spaceborne Synthetic Aperture Radar (SAR) systems provide a useful tool to directly estimate biomass due to its sensitivity to structural and moisture characteristics of vegetation canopies. Even though the sensitivity of SAR data to total aboveground biomass has been successfully demonstrated in many controlled experiments over boreal forests and forest plantations, so far, no biomass estimation algorithm has been developed. This is mainly due to the fact that the SAR data, even at lowest frequency (P-band) saturates at biomass levels of about 200 tons/ha, and the structure and moisture information in the SAR signal forces the estimation algorithm to be forest type dependent. In this paper, we discuss the development of a hybrid forest biomass algorithm which uses a SAR derived land cover map in conjunction with a forest backscatter model and an inversion algorithm to estimate forest canopy water content. It is shown that unlike the direct biomass estimation from SAR data, the estimation of water content does not depend on the seasonal and/or environmental conditions. The total aboveground biomass can then be derived from canopy water content for each type of forest by incorporating other ecological information. Preliminary results from this technique over several boreal forest stands indicate that (1) the forest biomass can be estimated with reasonable accuracy, and (2) the saturation level of the SAR signal can be enhanced by separating the crown and trunk biomass in the inversion algorithm. We have used the JPL AIRSAR data over BOREAS southern study area to test the algorithm and to generate regional scale water content and biomass maps. The results are compared with ground data and the sources of errors are discussed. Several SAR images in synoptic modes are used to generate the parameter maps. The maps are then combined to generate mosaic maps over the BOREAS modeling grid.

Layers: A molecular surface peeling algorithm and its applications to analyze protein structures

PubMed Central

Karampudi, Naga Bhushana Rao; Bahadur, Ranjit Prasad

2015-01-01

We present an algorithm ‘Layers’ to peel the atoms of proteins as layers. Using Layers we show an efficient way to transform protein structures into 2D pattern, named residue transition pattern (RTP), which is independent of molecular orientations. RTP explains the folding patterns of proteins and hence identification of similarity between proteins is simple and reliable using RTP than with the standard sequence or structure based methods. Moreover, Layers generates a fine-tunable coarse model for the molecular surface by using non-random sampling. The coarse model can be used for shape comparison, protein recognition and ligand design. Additionally, Layers can be used to develop biased initial configuration of molecules for protein folding simulations. We have developed a random forest classifier to predict the RTP of a given polypeptide sequence. Layers is a standalone application; however, it can be merged with other applications to reduce the computational load when working with large datasets of protein structures. Layers is available freely at http://www.csb.iitkgp.ernet.in/applications/mol_layers/main. PMID:26553411

California Drought Effects on Sierra Trees Mapped by NASA

NASA Image and Video Library

2016-06-27

California, reveals the devastating effect of California's ongoing drought on Sierra Nevada conifer forests. The map will be used to help the U.S. Forest Service assess and respond to the impacts of increased tree mortality caused by the drought, particularly where wildlands meet urban areas within the Sierra National Forest. After several years of extreme drought, the highly stressed conifers (trees or bushes that produce cones and are usually green year-round) of the Sierra Nevada are now more susceptible to bark beetles (Dendroctonus spp.). While bark beetles killing trees in the Sierra Nevada is a natural phenomenon, the scale of mortality in the last couple of years is far greater than previously observed. The U.S. Forest Service is using recent airborne spectroscopic measurements from NASA's Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) instrument aboard NASA's ER-2 aircraft, together with new advanced algorithms, to quantify this impact over this large region of rugged terrain. The high-altitude ER-2 aircraft is based at NASA's Armstrong Flight Research Center, Edwards, California. The image was created by scientists at the USFS's Pacific Southwest Region Remote Sensing Lab, McClellan, California, by performing a time series analysis of AVIRIS images. Scientists evaluated baseline tree mortality on public lands in the summer of 2015 using a machine learning algorithm called "random forest." This algorithm classifies the AVIRIS measurements as dominated by either shrubs, healthy trees or newly dead conifer trees. To quantify how much the amount of dead vegetation increased during the fall of 2015, the Forest Service scientists conducted an advanced spectral mixture analysis. This analysis evaluates each spectrum to determine the fraction of green vegetation, dead vegetation and soil. The full spectral range of AVIRIS is important to separate the signatures of soil and dead vegetation. To produce this comprehensive Sierra National Forest tree mortality map, the result from the summer of 2015 was evaluated to look for increases of more than 10 percent in dead vegetation during the fall of 2015. AVIRIS measures spectra of the Earth system to conduct advanced science research. These western U.S. AVIRIS measurements were acquired as part of NASA's Hyperspectral Infrared Imager (HyspIRI) preparatory airborne campaign. HyspIRI was one of the space missions suggested to NASA by the National Academy of Sciences in its 2007 decadal survey for Earth Science. In the future, HyspIRI could provide spectral and thermal measurements of this type globally for ecosystem research and additional science objectives. http://photojournal.jpl.nasa.gov/catalog/PIA20717

Calibrating random forests for probability estimation.

PubMed

Dankowski, Theresa; Ziegler, Andreas

2016-09-30

Probabilities can be consistently estimated using random forests. It is, however, unclear how random forests should be updated to make predictions for other centers or at different time points. In this work, we present two approaches for updating random forests for probability estimation. The first method has been proposed by Elkan and may be used for updating any machine learning approach yielding consistent probabilities, so-called probability machines. The second approach is a new strategy specifically developed for random forests. Using the terminal nodes, which represent conditional probabilities, the random forest is first translated to logistic regression models. These are, in turn, used for re-calibration. The two updating strategies were compared in a simulation study and are illustrated with data from the German Stroke Study Collaboration. In most simulation scenarios, both methods led to similar improvements. In the simulation scenario in which the stricter assumptions of Elkan's method were not met, the logistic regression-based re-calibration approach for random forests outperformed Elkan's method. It also performed better on the stroke data than Elkan's method. The strength of Elkan's method is its general applicability to any probability machine. However, if the strict assumptions underlying this approach are not met, the logistic regression-based approach is preferable for updating random forests for probability estimation. © 2016 The Authors. Statistics in Medicine Published by John Wiley & Sons Ltd. © 2016 The Authors. Statistics in Medicine Published by John Wiley & Sons Ltd.

Predicting surface fuel models and fuel metrics using lidar and CIR imagery in a dense mixed conifer forest

Treesearch

Marek K. Jakubowksi; Qinghua Guo; Brandon Collins; Scott Stephens; Maggi Kelly

2013-01-01

We compared the ability of several classification and regression algorithms to predict forest stand structure metrics and standard surface fuel models. Our study area spans a dense, topographically complex Sierra Nevada mixed-conifer forest. We used clustering, regression trees, and support vector machine algorithms to analyze high density (average 9 pulses/m

Automated transient identification in the Dark Energy Survey

DOE Office of Scientific and Technical Information (OSTI.GOV)

Goldstein, D. A.

2015-08-20

We describe an algorithm for identifying point-source transients and moving objects on reference-subtracted optical images containing artifacts of processing and instrumentation. The algorithm makes use of the supervised machine learning technique known as Random Forest. We present results from its use in the Dark Energy Survey Supernova program (DES-SN), where it was trained using a sample of 898,963 signal and background events generated by the transient detection pipeline. After reprocessing the data collected during the first DES-SN observing season (2013 September through 2014 February) using the algorithm, the number of transient candidates eligible for human scanning decreased by a factormore » of 13.4, while only 1.0 percent of the artificial Type Ia supernovae (SNe) injected into search images to monitor survey efficiency were lost, most of which were very faint events. Here we characterize the algorithm's performance in detail, and we discuss how it can inform pipeline design decisions for future time-domain imaging surveys, such as the Large Synoptic Survey Telescope and the Zwicky Transient Facility.« less

Automated transient identification in the Dark Energy Survey

DOE PAGES

Goldstein, D. A.; D'Andrea, C. B.; Fischer, J. A.; ...

2015-09-01

We describe an algorithm for identifying point-source transients and moving objects on reference-subtracted optical images containing artifacts of processing and instrumentation. The algorithm makes use of the supervised machine learning technique known as Random Forest. We present results from its use in the Dark Energy Survey Supernova program (DES-SN), where it was trained using a sample of 898,963 signal and background events generated by the transient detection pipeline. After reprocessing the data collected during the first DES-SN observing season (2013 September through 2014 February) using the algorithm, the number of transient candidates eligible for human scanning decreased by a factormore » of 13.4, while only 1.0% of the artificial Type Ia supernovae (SNe) injected into search images to monitor survey efficiency were lost, most of which were very faint events. Furthermore, we characterize the algorithm's performance in detail, and we discuss how it can inform pipeline design decisions for future time-domain imaging surveys, such as the Large Synoptic Survey Telescope and the Zwicky Transient Facility.« less

Improving graph-based OCT segmentation for severe pathology in retinitis pigmentosa patients

NASA Astrophysics Data System (ADS)

Lang, Andrew; Carass, Aaron; Bittner, Ava K.; Ying, Howard S.; Prince, Jerry L.

2017-03-01

Three dimensional segmentation of macular optical coherence tomography (OCT) data of subjects with retinitis pigmentosa (RP) is a challenging problem due to the disappearance of the photoreceptor layers, which causes algorithms developed for segmentation of healthy data to perform poorly on RP patients. In this work, we present enhancements to a previously developed graph-based OCT segmentation pipeline to enable processing of RP data. The algorithm segments eight retinal layers in RP data by relaxing constraints on the thickness and smoothness of each layer learned from healthy data. Following from prior work, a random forest classifier is first trained on the RP data to estimate boundary probabilities, which are used by a graph search algorithm to find the optimal set of nine surfaces that fit the data. Due to the intensity disparity between normal layers of healthy controls and layers in various stages of degeneration in RP patients, an additional intensity normalization step is introduced. Leave-one-out validation on data acquired from nine subjects showed an average overall boundary error of 4.22 μm as compared to 6.02 μm using the original algorithm.

Novel image analysis approach for quantifying expression of nuclear proteins assessed by immunohistochemistry: application to measurement of oestrogen and progesterone receptor levels in breast cancer.

PubMed

Rexhepaj, Elton; Brennan, Donal J; Holloway, Peter; Kay, Elaine W; McCann, Amanda H; Landberg, Goran; Duffy, Michael J; Jirstrom, Karin; Gallagher, William M

2008-01-01

Manual interpretation of immunohistochemistry (IHC) is a subjective, time-consuming and variable process, with an inherent intra-observer and inter-observer variability. Automated image analysis approaches offer the possibility of developing rapid, uniform indicators of IHC staining. In the present article we describe the development of a novel approach for automatically quantifying oestrogen receptor (ER) and progesterone receptor (PR) protein expression assessed by IHC in primary breast cancer. Two cohorts of breast cancer patients (n = 743) were used in the study. Digital images of breast cancer tissue microarrays were captured using the Aperio ScanScope XT slide scanner (Aperio Technologies, Vista, CA, USA). Image analysis algorithms were developed using MatLab 7 (MathWorks, Apple Hill Drive, MA, USA). A fully automated nuclear algorithm was developed to discriminate tumour from normal tissue and to quantify ER and PR expression in both cohorts. Random forest clustering was employed to identify optimum thresholds for survival analysis. The accuracy of the nuclear algorithm was initially confirmed by a histopathologist, who validated the output in 18 representative images. In these 18 samples, an excellent correlation was evident between the results obtained by manual and automated analysis (Spearman's rho = 0.9, P < 0.001). Optimum thresholds for survival analysis were identified using random forest clustering. This revealed 7% positive tumour cells as the optimum threshold for the ER and 5% positive tumour cells for the PR. Moreover, a 7% cutoff level for the ER predicted a better response to tamoxifen than the currently used 10% threshold. Finally, linear regression was employed to demonstrate a more homogeneous pattern of expression for the ER (R = 0.860) than for the PR (R = 0.681). In summary, we present data on the automated quantification of the ER and the PR in 743 primary breast tumours using a novel unsupervised image analysis algorithm. This novel approach provides a useful tool for the quantification of biomarkers on tissue specimens, as well as for objective identification of appropriate cutoff thresholds for biomarker positivity. It also offers the potential to identify proteins with a homogeneous pattern of expression.

Mental Health Risk Adjustment with Clinical Categories and Machine Learning.

PubMed

Shrestha, Akritee; Bergquist, Savannah; Montz, Ellen; Rose, Sherri

2017-12-15

To propose nonparametric ensemble machine learning for mental health and substance use disorders (MHSUD) spending risk adjustment formulas, including considering Clinical Classification Software (CCS) categories as diagnostic covariates over the commonly used Hierarchical Condition Category (HCC) system. 2012-2013 Truven MarketScan database. We implement 21 algorithms to predict MHSUD spending, as well as a weighted combination of these algorithms called super learning. The algorithm collection included seven unique algorithms that were supplied with three differing sets of MHSUD-related predictors alongside demographic covariates: HCC, CCS, and HCC + CCS diagnostic variables. Performance was evaluated based on cross-validated R 2 and predictive ratios. Results show that super learning had the best performance based on both metrics. The top single algorithm was random forests, which improved on ordinary least squares regression by 10 percent with respect to relative efficiency. CCS categories-based formulas were generally more predictive of MHSUD spending compared to HCC-based formulas. Literature supports the potential benefit of implementing a separate MHSUD spending risk adjustment formula. Our results suggest there is an incentive to explore machine learning for MHSUD-specific risk adjustment, as well as considering CCS categories over HCCs. © Health Research and Educational Trust.

An evaluation of supervised classifiers for indirectly detecting salt-affected areas at irrigation scheme level

NASA Astrophysics Data System (ADS)

Muller, Sybrand Jacobus; van Niekerk, Adriaan

2016-07-01

Soil salinity often leads to reduced crop yield and quality and can render soils barren. Irrigated areas are particularly at risk due to intensive cultivation and secondary salinization caused by waterlogging. Regular monitoring of salt accumulation in irrigation schemes is needed to keep its negative effects under control. The dynamic spatial and temporal characteristics of remote sensing can provide a cost-effective solution for monitoring salt accumulation at irrigation scheme level. This study evaluated a range of pan-fused SPOT-5 derived features (spectral bands, vegetation indices, image textures and image transformations) for classifying salt-affected areas in two distinctly different irrigation schemes in South Africa, namely Vaalharts and Breede River. The relationship between the input features and electro conductivity measurements were investigated using regression modelling (stepwise linear regression, partial least squares regression, curve fit regression modelling) and supervised classification (maximum likelihood, nearest neighbour, decision tree analysis, support vector machine and random forests). Classification and regression trees and random forest were used to select the most important features for differentiating salt-affected and unaffected areas. The results showed that the regression analyses produced weak models (<0.4 R squared). Better results were achieved using the supervised classifiers, but the algorithms tend to over-estimate salt-affected areas. A key finding was that none of the feature sets or classification algorithms stood out as being superior for monitoring salt accumulation at irrigation scheme level. This was attributed to the large variations in the spectral responses of different crops types at different growing stages, coupled with their individual tolerances to saline conditions.

Applying a weighted random forests method to extract karst sinkholes from LiDAR data

NASA Astrophysics Data System (ADS)

Zhu, Junfeng; Pierskalla, William P.

2016-02-01

Detailed mapping of sinkholes provides critical information for mitigating sinkhole hazards and understanding groundwater and surface water interactions in karst terrains. LiDAR (Light Detection and Ranging) measures the earth's surface in high-resolution and high-density and has shown great potentials to drastically improve locating and delineating sinkholes. However, processing LiDAR data to extract sinkholes requires separating sinkholes from other depressions, which can be laborious because of the sheer number of the depressions commonly generated from LiDAR data. In this study, we applied the random forests, a machine learning method, to automatically separate sinkholes from other depressions in a karst region in central Kentucky. The sinkhole-extraction random forest was grown on a training dataset built from an area where LiDAR-derived depressions were manually classified through a visual inspection and field verification process. Based on the geometry of depressions, as well as natural and human factors related to sinkholes, 11 parameters were selected as predictive variables to form the dataset. Because the training dataset was imbalanced with the majority of depressions being non-sinkholes, a weighted random forests method was used to improve the accuracy of predicting sinkholes. The weighted random forest achieved an average accuracy of 89.95% for the training dataset, demonstrating that the random forest can be an effective sinkhole classifier. Testing of the random forest in another area, however, resulted in moderate success with an average accuracy rate of 73.96%. This study suggests that an automatic sinkhole extraction procedure like the random forest classifier can significantly reduce time and labor costs and makes its more tractable to map sinkholes using LiDAR data for large areas. However, the random forests method cannot totally replace manual procedures, such as visual inspection and field verification.

Biodiversity mapping in a tropical West African forest with airborne hyperspectral data.

PubMed

Vaglio Laurin, Gaia; Cheung-Wai Chan, Jonathan; Chen, Qi; Lindsell, Jeremy A; Coomes, David A; Guerriero, Leila; Del Frate, Fabio; Miglietta, Franco; Valentini, Riccardo

2014-01-01

Tropical forests are major repositories of biodiversity, but are fast disappearing as land is converted to agriculture. Decision-makers need to know which of the remaining forests to prioritize for conservation, but the only spatial information on forest biodiversity has, until recently, come from a sparse network of ground-based plots. Here we explore whether airborne hyperspectral imagery can be used to predict the alpha diversity of upper canopy trees in a West African forest. The abundance of tree species were collected from 64 plots (each 1250 m(2) in size) within a Sierra Leonean national park, and Shannon-Wiener biodiversity indices were calculated. An airborne spectrometer measured reflectances of 186 bands in the visible and near-infrared spectral range at 1 m(2) resolution. The standard deviations of these reflectance values and their first-order derivatives were calculated for each plot from the c. 1250 pixels of hyperspectral information within them. Shannon-Wiener indices were then predicted from these plot-based reflectance statistics using a machine-learning algorithm (Random Forest). The regression model fitted the data well (pseudo-R(2) = 84.9%), and we show that standard deviations of green-band reflectances and infra-red region derivatives had the strongest explanatory powers. Our work shows that airborne hyperspectral sensing can be very effective at mapping canopy tree diversity, because its high spatial resolution allows within-plot heterogeneity in reflectance to be characterized, making it an effective tool for monitoring forest biodiversity over large geographic scales.

Biodiversity Mapping in a Tropical West African Forest with Airborne Hyperspectral Data

PubMed Central

Vaglio Laurin, Gaia; Chan, Jonathan Cheung-Wai; Chen, Qi; Lindsell, Jeremy A.; Coomes, David A.; Guerriero, Leila; Frate, Fabio Del; Miglietta, Franco; Valentini, Riccardo

2014-01-01

Tropical forests are major repositories of biodiversity, but are fast disappearing as land is converted to agriculture. Decision-makers need to know which of the remaining forests to prioritize for conservation, but the only spatial information on forest biodiversity has, until recently, come from a sparse network of ground-based plots. Here we explore whether airborne hyperspectral imagery can be used to predict the alpha diversity of upper canopy trees in a West African forest. The abundance of tree species were collected from 64 plots (each 1250 m2 in size) within a Sierra Leonean national park, and Shannon-Wiener biodiversity indices were calculated. An airborne spectrometer measured reflectances of 186 bands in the visible and near-infrared spectral range at 1 m2 resolution. The standard deviations of these reflectance values and their first-order derivatives were calculated for each plot from the c. 1250 pixels of hyperspectral information within them. Shannon-Wiener indices were then predicted from these plot-based reflectance statistics using a machine-learning algorithm (Random Forest). The regression model fitted the data well (pseudo-R2 = 84.9%), and we show that standard deviations of green-band reflectances and infra-red region derivatives had the strongest explanatory powers. Our work shows that airborne hyperspectral sensing can be very effective at mapping canopy tree diversity, because its high spatial resolution allows within-plot heterogeneity in reflectance to be characterized, making it an effective tool for monitoring forest biodiversity over large geographic scales. PMID:24937407

Random forests, a novel approach for discrimination of fish populations using parasites as biological tags.

PubMed

Perdiguero-Alonso, Diana; Montero, Francisco E; Kostadinova, Aneta; Raga, Juan Antonio; Barrett, John

2008-10-01

Due to the complexity of host-parasite relationships, discrimination between fish populations using parasites as biological tags is difficult. This study introduces, to our knowledge for the first time, random forests (RF) as a new modelling technique in the application of parasite community data as biological markers for population assignment of fish. This novel approach is applied to a dataset with a complex structure comprising 763 parasite infracommunities in population samples of Atlantic cod, Gadus morhua, from the spawning/feeding areas in five regions in the North East Atlantic (Baltic, Celtic, Irish and North seas and Icelandic waters). The learning behaviour of RF is evaluated in comparison with two other algorithms applied to class assignment problems, the linear discriminant function analysis (LDA) and artificial neural networks (ANN). The three algorithms are used to develop predictive models applying three cross-validation procedures in a series of experiments (252 models in total). The comparative approach to RF, LDA and ANN algorithms applied to the same datasets demonstrates the competitive potential of RF for developing predictive models since RF exhibited better accuracy of prediction and outperformed LDA and ANN in the assignment of fish to their regions of sampling using parasite community data. The comparative analyses and the validation experiment with a 'blind' sample confirmed that RF models performed more effectively with a large and diverse training set and a large number of variables. The discrimination results obtained for a migratory fish species with largely overlapping parasite communities reflects the high potential of RF for developing predictive models using data that are both complex and noisy, and indicates that it is a promising tool for parasite tag studies. Our results suggest that parasite community data can be used successfully to discriminate individual cod from the five different regions of the North East Atlantic studied using RF.

EDITORIAL: Special section on foliage penetration

NASA Astrophysics Data System (ADS)

Fiddy, M. A.; Lang, R.; McGahan, R. V.

2004-04-01

Waves in Random Media was founded in 1991 to provide a forum for papers dealing with electromagnetic and acoustic waves as they propagate and scatter through media or objects having some degree of randomness. This is a broad charter since, in practice, all scattering obstacles and structures have roughness or randomness, often on the scale of the wavelength being used to probe them. Including this random component leads to some quite different methods for describing propagation effects, for example, when propagating through the atmosphere or the ground. This special section on foliage penetration (FOPEN) focuses on the problems arising from microwave propagation through foliage and vegetation. Applications of such studies include the estimation for forest biomass and the moisture of the underlying soil, as well as detecting objects hidden therein. In addition to the so-called `direct problem' of trying to describe energy propagating through such media, the complementary inverse problem is of great interest and much harder to solve. The development of theoretical models and associated numerical algorithms for identifying objects concealed by foliage has applications in surveillance, ranging from monitoring drug trafficking to targeting military vehicles. FOPEN can be employed to map the earth's surface in cases when it is under a forest canopy, permitting the identification of objects or targets on that surface, but the process for doing so is not straightforward. There has been an increasing interest in foliage penetration synthetic aperture radar (FOPEN or FOPENSAR) over the last 10 years and this special section provides a broad overview of many of the issues involved. The detection, identification, and geographical location of targets under foliage or otherwise obscured by poor visibility conditions remains a challenge. In particular, a trade-off often needs to be appreciated, namely that diminishing the deleterious effects of multiple scattering from leaves is typically associated with a significant loss in target resolution. Foliage is more or less transparent to some radar frequencies, but longer wavelengths found in the VHF (30 to 300 MHz) and UHF (300 MHz to 3 GHz) portions of the microwave spectrum have more chance of penetrating foliage than do wavelengths at the X band (8 to 12 GHz). Reflection and multiple scattering occur for some other frequencies and models of the processes involved are crucial. Two topical reviews can be found in this issue, one on the microwave radiometry of forests (page S275) and another describing ionospheric effects on space-based radar (page S189). Subsequent papers present new results on modelling coherent backscatter from forests (page S299), modelling forests as discrete random media over a random interface (page S359) and interpreting ranging scatterometer data from forests (page S317). Cloude et al present research on identifying targets beneath foliage using polarimetric SAR interferometry (page S393) while Treuhaft and Siqueira use interferometric radar to describe forest structure and biomass (page S345). Vechhia et al model scattering from leaves (page S333) and Semichaevsky et al address the problem of the trade-off between increasing wavelength, reduction in multiple scattering, and target resolution (page S415).

Analysis of Naïve Bayes Algorithm for Email Spam Filtering across Multiple Datasets

NASA Astrophysics Data System (ADS)

Fitriah Rusland, Nurul; Wahid, Norfaradilla; Kasim, Shahreen; Hafit, Hanayanti

2017-08-01

E-mail spam continues to become a problem on the Internet. Spammed e-mail may contain many copies of the same message, commercial advertisement or other irrelevant posts like pornographic content. In previous research, different filtering techniques are used to detect these e-mails such as using Random Forest, Naïve Bayesian, Support Vector Machine (SVM) and Neutral Network. In this research, we test Naïve Bayes algorithm for e-mail spam filtering on two datasets and test its performance, i.e., Spam Data and SPAMBASE datasets [8]. The performance of the datasets is evaluated based on their accuracy, recall, precision and F-measure. Our research use WEKA tool for the evaluation of Naïve Bayes algorithm for e-mail spam filtering on both datasets. The result shows that the type of email and the number of instances of the dataset has an influence towards the performance of Naïve Bayes.

A simple algorithm for large-scale mapping of evergreen forests in tropical America, Africa and Asia

Treesearch

Xiangming Xiao; Chandrashekhar M. Biradar; Christina Czarnecki; Tunrayo Alabi; Michael Keller

2009-01-01

The areal extent and spatial distribution of evergreen forests in the tropical zones are important for the study of climate, carbon cycle and biodiversity. However, frequent cloud cover in the tropical regions makes mapping evergreen forests a challenging task. In this study we developed a simple and novel mapping algorithm that is based on the temporal profile...

QUANTIFYING FOREST ABOVEGROUND CARBON POOLS AND FLUXES USING MULTI-TEMPORAL LIDAR A report on field monitoring, remote sensing MMV, GIS integration, and modeling results for forestry field validation test to quantify aboveground tree biomass and carbon

DOE Office of Scientific and Technical Information (OSTI.GOV)

Lee Spangler; Lee A. Vierling; Eva K. Stand

2012-04-01

Sound policy recommendations relating to the role of forest management in mitigating atmospheric carbon dioxide (CO{sub 2}) depend upon establishing accurate methodologies for quantifying forest carbon pools for large tracts of land that can be dynamically updated over time. Light Detection and Ranging (LiDAR) remote sensing is a promising technology for achieving accurate estimates of aboveground biomass and thereby carbon pools; however, not much is known about the accuracy of estimating biomass change and carbon flux from repeat LiDAR acquisitions containing different data sampling characteristics. In this study, discrete return airborne LiDAR data was collected in 2003 and 2009 acrossmore » {approx}20,000 hectares (ha) of an actively managed, mixed conifer forest landscape in northern Idaho, USA. Forest inventory plots, established via a random stratified sampling design, were established and sampled in 2003 and 2009. The Random Forest machine learning algorithm was used to establish statistical relationships between inventory data and forest structural metrics derived from the LiDAR acquisitions. Aboveground biomass maps were created for the study area based on statistical relationships developed at the plot level. Over this 6-year period, we found that the mean increase in biomass due to forest growth across the non-harvested portions of the study area was 4.8 metric ton/hectare (Mg/ha). In these non-harvested areas, we found a significant difference in biomass increase among forest successional stages, with a higher biomass increase in mature and old forest compared to stand initiation and young forest. Approximately 20% of the landscape had been disturbed by harvest activities during the six-year time period, representing a biomass loss of >70 Mg/ha in these areas. During the study period, these harvest activities outweighed growth at the landscape scale, resulting in an overall loss in aboveground carbon at this site. The 30-fold increase in sampling density between the 2003 and 2009 did not affect the biomass estimates. Overall, LiDAR data coupled with field reference data offer a powerful method for calculating pools and changes in aboveground carbon in forested systems. The results of our study suggest that multitemporal LiDAR-based approaches are likely to be useful for high quality estimates of aboveground carbon change in conifer forest systems.« less

Identifying relevant hyperspectral bands using Boruta: a temporal analysis of water hyacinth biocontrol

NASA Astrophysics Data System (ADS)

Agjee, Na'eem Hoosen; Ismail, Riyad; Mutanga, Onisimo

2016-10-01

Water hyacinth plants (Eichhornia crassipes) are threatening freshwater ecosystems throughout Africa. The Neochetina spp. weevils are seen as an effective solution that can combat the proliferation of the invasive alien plant. We aimed to determine if multitemporal hyperspectral data could be utilized to detect the efficacy of the biocontrol agent. The random forest (RF) algorithm was used to classify variable infestation levels for 6 weeks using: (1) all the hyperspectral bands, (2) bands selected by the recursive feature elimination (RFE) algorithm, and (3) bands selected by the Boruta algorithm. Results showed that the RF model using all the bands successfully produced low-classification errors (12.50% to 32.29%) for all 6 weeks. However, the RF model using Boruta selected bands produced lower classification errors (8.33% to 15.62%) than the RF model using all the bands or bands selected by the RFE algorithm (11.25% to 21.25%) for all 6 weeks, highlighting the utility of Boruta as an all relevant band selection algorithm. All relevant bands selected by Boruta included: 352, 754, 770, 771, 775, 781, 782, 783, 786, and 789 nm. It was concluded that RF coupled with Boruta band-selection algorithm can be utilized to undertake multitemporal monitoring of variable infestation levels on water hyacinth plants.

Large Unbalanced Credit Scoring Using Lasso-Logistic Regression Ensemble

PubMed Central

Wang, Hong; Xu, Qingsong; Zhou, Lifeng

2015-01-01

Recently, various ensemble learning methods with different base classifiers have been proposed for credit scoring problems. However, for various reasons, there has been little research using logistic regression as the base classifier. In this paper, given large unbalanced data, we consider the plausibility of ensemble learning using regularized logistic regression as the base classifier to deal with credit scoring problems. In this research, the data is first balanced and diversified by clustering and bagging algorithms. Then we apply a Lasso-logistic regression learning ensemble to evaluate the credit risks. We show that the proposed algorithm outperforms popular credit scoring models such as decision tree, Lasso-logistic regression and random forests in terms of AUC and F-measure. We also provide two importance measures for the proposed model to identify important variables in the data. PMID:25706988

Indonesian name matching using machine learning supervised approach

NASA Astrophysics Data System (ADS)

Alifikri, Mohamad; Arif Bijaksana, Moch.

2018-03-01

Most existing name matching methods are developed for English language and so they cover the characteristics of this language. Up to this moment, there is no specific one has been designed and implemented for Indonesian names. The purpose of this thesis is to develop Indonesian name matching dataset as a contribution to academic research and to propose suitable feature set by utilizing combination of context of name strings and its permute-winkler score. Machine learning classification algorithms is taken as the method for performing name matching. Based on the experiments, by using tuned Random Forest algorithm and proposed features, there is an improvement of matching performance by approximately 1.7% and it is able to reduce until 70% misclassification result of the state of the arts methods. This improving performance makes the matching system more effective and reduces the risk of misclassified matches.

Classifying bent radio galaxies from a mixture of point-like/extended images with Machine Learning.

NASA Astrophysics Data System (ADS)

Bastien, David; Oozeer, Nadeem; Somanah, Radhakrishna

2017-05-01

The hypothesis that bent radio sources are supposed to be found in rich, massive galaxy clusters and the avalibility of huge amount of data from radio surveys have fueled our motivation to use Machine Learning (ML) to identify bent radio sources and as such use them as tracers for galaxy clusters. The shapelet analysis allowed us to decompose radio images into 256 features that could be fed into the ML algorithm. Additionally, ideas from the field of neuro-psychology helped us to consider training the machine to identify bent galaxies at different orientations. From our analysis, we found that the Random Forest algorithm was the most effective with an accuracy rate of 92% for a classification of point and extended sources as well as an accuracy of 80% for bent and unbent classification.

Individual tree detection in intact forest and degraded forest areas in the north region of Mato Grosso State, Brazilian Amazon

NASA Astrophysics Data System (ADS)

Santos, E. G.; Jorge, A.; Shimabukuro, Y. E.; Gasparini, K.

2017-12-01

The State of Mato Grosso - MT has the second largest area with degraded forest among the states of the Brazilian Legal Amazon. Land use and land cover change processes that occur in this region cause the loss of forest biomass, releasing greenhouse gases that contribute to the increase of temperature on earth. These degraded forest areas lose biomass according to the intensity and magnitude of the degradation type. The estimate of forest biomass, commonly performed by forest inventory through sample plots, shows high variance in degraded forest areas. Due to this variance and complexity of tropical forests, the aim of this work was to estimate forest biomass using LiDAR point clouds in three distinct forest areas: one degraded by fire, another by selective logging and one area of intact forest. The approach applied in these areas was the Individual Tree Detection (ITD). To isolate the trees, we generated Canopy Height Models (CHM) images, which are obtained by subtracting the Digital Elevation Model (MDE) and the Digital Terrain Model (MDT), created by the cloud of LiDAR points. The trees in the CHM images are isolated by an algorithm provided by the Quantitative Ecology research group at the School of Forestry at Northern Arizona University (SILVA, 2015). With these points, metrics were calculated for some areas, which were used in the model of biomass estimation. The methodology used in this work was expected to reduce the error in biomass estimate in the study area. The cloud points of the most representative trees were analyzed, and thus field data was correlated with the individual trees found by the proposed algorithm. In a pilot study, the proposed methodology was applied generating the individual tree metrics: total height and area of the crown. When correlating 339 isolated trees, an unsatisfactory R² was obtained, as heights found by the algorithm were lower than those obtained in the field, with an average difference of 2.43 m. This shows that the algorithm used to isolate trees in temperate areas did not obtained satisfactory results in the tropical forest of Mato Grosso State. Due to this, in future works two algorithms, one developed by Dalponte et al. (2015) and another by Li et al. (2012) will be used.

Development of machine learning models for diagnosis of glaucoma.

PubMed

Kim, Seong Jae; Cho, Kyong Jin; Oh, Sejong

2017-01-01

The study aimed to develop machine learning models that have strong prediction power and interpretability for diagnosis of glaucoma based on retinal nerve fiber layer (RNFL) thickness and visual field (VF). We collected various candidate features from the examination of retinal nerve fiber layer (RNFL) thickness and visual field (VF). We also developed synthesized features from original features. We then selected the best features proper for classification (diagnosis) through feature evaluation. We used 100 cases of data as a test dataset and 399 cases of data as a training and validation dataset. To develop the glaucoma prediction model, we considered four machine learning algorithms: C5.0, random forest (RF), support vector machine (SVM), and k-nearest neighbor (KNN). We repeatedly composed a learning model using the training dataset and evaluated it by using the validation dataset. Finally, we got the best learning model that produces the highest validation accuracy. We analyzed quality of the models using several measures. The random forest model shows best performance and C5.0, SVM, and KNN models show similar accuracy. In the random forest model, the classification accuracy is 0.98, sensitivity is 0.983, specificity is 0.975, and AUC is 0.979. The developed prediction models show high accuracy, sensitivity, specificity, and AUC in classifying among glaucoma and healthy eyes. It will be used for predicting glaucoma against unknown examination records. Clinicians may reference the prediction results and be able to make better decisions. We may combine multiple learning models to increase prediction accuracy. The C5.0 model includes decision rules for prediction. It can be used to explain the reasons for specific predictions.

Random forests for classification in ecology

USGS Publications Warehouse

Cutler, D.R.; Edwards, T.C.; Beard, K.H.; Cutler, A.; Hess, K.T.; Gibson, J.; Lawler, J.J.

2007-01-01

Classification procedures are some of the most widely used statistical methods in ecology. Random forests (RF) is a new and powerful statistical classifier that is well established in other disciplines but is relatively unknown in ecology. Advantages of RF compared to other statistical classifiers include (1) very high classification accuracy; (2) a novel method of determining variable importance; (3) ability to model complex interactions among predictor variables; (4) flexibility to perform several types of statistical data analysis, including regression, classification, survival analysis, and unsupervised learning; and (5) an algorithm for imputing missing values. We compared the accuracies of RF and four other commonly used statistical classifiers using data on invasive plant species presence in Lava Beds National Monument, California, USA, rare lichen species presence in the Pacific Northwest, USA, and nest sites for cavity nesting birds in the Uinta Mountains, Utah, USA. We observed high classification accuracy in all applications as measured by cross-validation and, in the case of the lichen data, by independent test data, when comparing RF to other common classification methods. We also observed that the variables that RF identified as most important for classifying invasive plant species coincided with expectations based on the literature. ?? 2007 by the Ecological Society of America.

Integrating Geo-Spatial Data for Regional Landslide Susceptibility Modeling in Consideration of Run-Out Signature

NASA Astrophysics Data System (ADS)

Lai, J.-S.; Tsai, F.; Chiang, S.-H.

2016-06-01

This study implements a data mining-based algorithm, the random forests classifier, with geo-spatial data to construct a regional and rainfall-induced landslide susceptibility model. The developed model also takes account of landslide regions (source, non-occurrence and run-out signatures) from the original landslide inventory in order to increase the reliability of the susceptibility modelling. A total of ten causative factors were collected and used in this study, including aspect, curvature, elevation, slope, faults, geology, NDVI (Normalized Difference Vegetation Index), rivers, roads and soil data. Consequently, this study transforms the landslide inventory and vector-based causative factors into the pixel-based format in order to overlay with other raster data for constructing the random forests based model. This study also uses original and edited topographic data in the analysis to understand their impacts to the susceptibility modeling. Experimental results demonstrate that after identifying the run-out signatures, the overall accuracy and Kappa coefficient have been reached to be become more than 85 % and 0.8, respectively. In addition, correcting unreasonable topographic feature of the digital terrain model also produces more reliable modelling results.

Estimation of sleep status in sleep apnea patients using a novel head actigraphy technique.

PubMed

Hummel, Richard; Bradley, T Douglas; Fernie, Geoff R; Chang, S J Isaac; Alshaer, Hisham

2015-01-01

Polysomnography is a comprehensive modality for diagnosing sleep apnea (SA), but it is expensive and not widely available. Several technologies have been developed for portable diagnosis of SA in the home, most of which lack the ability to detect sleep status. Wrist actigraphy (accelerometry) has been adopted to cover this limitation. However, head actigraphy has not been systematically evaluated for this purpose. Therefore, the aim of this study was to evaluate the ability of head actigraphy to detect sleep/wake status. We obtained full overnight 3-axis head accelerometry data from 75 sleep apnea patient recordings. These were split into training and validation groups (2:1). Data were preprocessed and 5 features were extracted. Different feature combinations were fed into 3 different classifiers, namely support vector machine, logistic regression, and random forests, each of which was trained and validated on a different subgroup. The random forest algorithm yielded the highest performance, with an area under the receiver operating characteristic (ROC) curve of 0.81 for detection of sleep status. This shows that this technique has a very good performance in detecting sleep status in SA patients despite the specificities in this population, such as respiration related movements.

Evaluation of Semi-supervised Learning for Classification of Protein Crystallization Imagery

PubMed Central

Sigdel, Madhav; Dinç, İmren; Dinç, Semih; Sigdel, Madhu S.; Pusey, Marc L.; Aygün, Ramazan S.

2015-01-01

In this paper, we investigate the performance of two wrapper methods for semi-supervised learning algorithms for classification of protein crystallization images with limited labeled images. Firstly, we evaluate the performance of semi-supervised approach using self-training with naïve Bayesian (NB) and sequential minimum optimization (SMO) as the base classifiers. The confidence values returned by these classifiers are used to select high confident predictions to be used for self-training. Secondly, we analyze the performance of Yet Another Two Stage Idea (YATSI) semi-supervised learning using NB, SMO, multilayer perceptron (MLP), J48 and random forest (RF) classifiers. These results are compared with the basic supervised learning using the same training sets. We perform our experiments on a dataset consisting of 2250 protein crystallization images for different proportions of training and test data. Our results indicate that NB and SMO using both self-training and YATSI semi-supervised approaches improve accuracies with respect to supervised learning. On the other hand, MLP, J48 and RF perform better using basic supervised learning. Overall, random forest classifier yields the best accuracy with supervised learning for our dataset. PMID:25914518

A machine learning system to improve heart failure patient assistance.

PubMed

Guidi, Gabriele; Pettenati, Maria Chiara; Melillo, Paolo; Iadanza, Ernesto

2014-11-01

In this paper, we present a clinical decision support system (CDSS) for the analysis of heart failure (HF) patients, providing various outputs such as an HF severity evaluation, HF-type prediction, as well as a management interface that compares the different patients' follow-ups. The whole system is composed of a part of intelligent core and of an HF special-purpose management tool also providing the function to act as interface for the artificial intelligence training and use. To implement the smart intelligent functions, we adopted a machine learning approach. In this paper, we compare the performance of a neural network (NN), a support vector machine, a system with fuzzy rules genetically produced, and a classification and regression tree and its direct evolution, which is the random forest, in analyzing our database. Best performances in both HF severity evaluation and HF-type prediction functions are obtained by using the random forest algorithm. The management tool allows the cardiologist to populate a "supervised database" suitable for machine learning during his or her regular outpatient consultations. The idea comes from the fact that in literature there are a few databases of this type, and they are not scalable to our case.

Predicting the accuracy of ligand overlay methods with Random Forest models.

PubMed

Nandigam, Ravi K; Evans, David A; Erickson, Jon A; Kim, Sangtae; Sutherland, Jeffrey J

2008-12-01

The accuracy of binding mode prediction using standard molecular overlay methods (ROCS, FlexS, Phase, and FieldCompare) is studied. Previous work has shown that simple decision tree modeling can be used to improve accuracy by selection of the best overlay template. This concept is extended to the use of Random Forest (RF) modeling for template and algorithm selection. An extensive data set of 815 ligand-bound X-ray structures representing 5 gene families was used for generating ca. 70,000 overlays using four programs. RF models, trained using standard measures of ligand and protein similarity and Lipinski-related descriptors, are used for automatically selecting the reference ligand and overlay method maximizing the probability of reproducing the overlay deduced from X-ray structures (i.e., using rmsd < or = 2 A as the criteria for success). RF model scores are highly predictive of overlay accuracy, and their use in template and method selection produces correct overlays in 57% of cases for 349 overlay ligands not used for training RF models. The inclusion in the models of protein sequence similarity enables the use of templates bound to related protein structures, yielding useful results even for proteins having no available X-ray structures.

Cluster ensemble based on Random Forests for genetic data.

PubMed

Alhusain, Luluah; Hafez, Alaaeldin M

2017-01-01

Clustering plays a crucial role in several application domains, such as bioinformatics. In bioinformatics, clustering has been extensively used as an approach for detecting interesting patterns in genetic data. One application is population structure analysis, which aims to group individuals into subpopulations based on shared genetic variations, such as single nucleotide polymorphisms. Advances in DNA sequencing technology have facilitated the obtainment of genetic datasets with exceptional sizes. Genetic data usually contain hundreds of thousands of genetic markers genotyped for thousands of individuals, making an efficient means for handling such data desirable. Random Forests (RFs) has emerged as an efficient algorithm capable of handling high-dimensional data. RFs provides a proximity measure that can capture different levels of co-occurring relationships between variables. RFs has been widely considered a supervised learning method, although it can be converted into an unsupervised learning method. Therefore, RF-derived proximity measure combined with a clustering technique may be well suited for determining the underlying structure of unlabeled data. This paper proposes, RFcluE, a cluster ensemble approach for determining the underlying structure of genetic data based on RFs. The approach comprises a cluster ensemble framework to combine multiple runs of RF clustering. Experiments were conducted on high-dimensional, real genetic dataset to evaluate the proposed approach. The experiments included an examination of the impact of parameter changes, comparing RFcluE performance against other clustering methods, and an assessment of the relationship between the diversity and quality of the ensemble and its effect on RFcluE performance. This paper proposes, RFcluE, a cluster ensemble approach based on RF clustering to address the problem of population structure analysis and demonstrate the effectiveness of the approach. The paper also illustrates that applying a cluster ensemble approach, combining multiple RF clusterings, produces more robust and higher-quality results as a consequence of feeding the ensemble with diverse views of high-dimensional genetic data obtained through bagging and random subspace, the two key features of the RF algorithm.

Automatic localization of landmark sets in head CT images with regression forests for image registration initialization

NASA Astrophysics Data System (ADS)

Zhang, Dongqing; Liu, Yuan; Noble, Jack H.; Dawant, Benoit M.

2016-03-01

Cochlear Implants (CIs) are electrode arrays that are surgically inserted into the cochlea. Individual contacts stimulate frequency-mapped nerve endings thus replacing the natural electro-mechanical transduction mechanism. CIs are programmed post-operatively by audiologists but this is currently done using behavioral tests without imaging information that permits relating electrode position to inner ear anatomy. We have recently developed a series of image processing steps that permit the segmentation of the inner ear anatomy and the localization of individual contacts. We have proposed a new programming strategy that uses this information and we have shown in a study with 68 participants that 78% of long term recipients preferred the programming parameters determined with this new strategy. A limiting factor to the large scale evaluation and deployment of our technique is the amount of user interaction still required in some of the steps used in our sequence of image processing algorithms. One such step is the rough registration of an atlas to target volumes prior to the use of automated intensity-based algorithms when the target volumes have very different fields of view and orientations. In this paper we propose a solution to this problem. It relies on a random forest-based approach to automatically localize a series of landmarks. Our results obtained from 83 images with 132 registration tasks show that automatic initialization of an intensity-based algorithm proves to be a reliable technique to replace the manual step.

Improvement of Forest Fire Detection Algorithm Using Brightness Temperature Lapse Rate Correction in HIMAWARI-8 IR Channels: Application to the 6 may 2017 Samcheok City, Korea

NASA Astrophysics Data System (ADS)

Park, S. H.; Park, W.; Jung, H. S.

2018-04-01

Forest fires are a major natural disaster that destroys a forest area and a natural environment. In order to minimize the damage caused by the forest fire, it is necessary to know the location and the time of day and continuous monitoring is required until fire is fully put out. We have tried to improve the forest fire detection algorithm by using a method to reduce the variability of surrounding pixels. We focused that forest areas of East Asia, part of the Himawari-8 AHI coverage, are mostly located in mountainous areas. The proposed method was applied to the forest fire detection in Samcheok city, Korea on May 6 to 10, 2017.

A Noise-Assisted Data Analysis Method for Automatic EOG-Based Sleep Stage Classification Using Ensemble Learning.

PubMed

Olesen, Alexander Neergaard; Christensen, Julie A E; Sorensen, Helge B D; Jennum, Poul J

2016-08-01

Reducing the number of recording modalities for sleep staging research can benefit both researchers and patients, under the condition that they provide as accurate results as conventional systems. This paper investigates the possibility of exploiting the multisource nature of the electrooculography (EOG) signals by presenting a method for automatic sleep staging using the complete ensemble empirical mode decomposition with adaptive noise algorithm, and a random forest classifier. It achieves a high overall accuracy of 82% and a Cohen's kappa of 0.74 indicating substantial agreement between automatic and manual scoring.

Sleep state classification using pressure sensor mats.

PubMed

Baran Pouyan, M; Nourani, M; Pompeo, M

2015-08-01

Sleep state detection is valuable in assessing patient's sleep quality and in-bed general behavior. In this paper, a novel classification approach of sleep states (sleep, pre-wake, wake) is proposed that uses only surface pressure sensors. In our method, a mobility metric is defined based on successive pressure body maps. Then, suitable statistical features are computed based on the mobility metric. Finally, a customized random forest classifier is employed to identify various classes including a new class for pre-wake state. Our algorithm achieves 96.1% and 88% accuracies for two (sleep, wake) and three (sleep, pre-wake, wake) class identification, respectively.

Evaluation of Algorithms for a Miles-in-Trail Decision Support Tool

NASA Technical Reports Server (NTRS)

Bloem, Michael; Hattaway, David; Bambos, Nicholas

2012-01-01

Four machine learning algorithms were prototyped and evaluated for use in a proposed decision support tool that would assist air traffic managers as they set Miles-in-Trail restrictions. The tool would display probabilities that each possible Miles-in-Trail value should be used in a given situation. The algorithms were evaluated with an expected Miles-in-Trail cost that assumes traffic managers set restrictions based on the tool-suggested probabilities. Basic Support Vector Machine, random forest, and decision tree algorithms were evaluated, as was a softmax regression algorithm that was modified to explicitly reduce the expected Miles-in-Trail cost. The algorithms were evaluated with data from the summer of 2011 for air traffic flows bound to the Newark Liberty International Airport (EWR) over the ARD, PENNS, and SHAFF fixes. The algorithms were provided with 18 input features that describe the weather at EWR, the runway configuration at EWR, the scheduled traffic demand at EWR and the fixes, and other traffic management initiatives in place at EWR. Features describing other traffic management initiatives at EWR and the weather at EWR achieved relatively high information gain scores, indicating that they are the most useful for estimating Miles-in-Trail. In spite of a high variance or over-fitting problem, the decision tree algorithm achieved the lowest expected Miles-in-Trail costs when the algorithms were evaluated using 10-fold cross validation with the summer 2011 data for these air traffic flows.

Modeling biophysical properties of broad-leaved stands in the hyrcanian forests of Iran using fused airborne laser scanner data and ultraCam-D images

NASA Astrophysics Data System (ADS)

Mohammadi, Jahangir; Shataee, Shaban; Namiranian, Manochehr; Næsset, Erik

2017-09-01

Inventories of mixed broad-leaved forests of Iran mainly rely on terrestrial measurements. Due to rapid changes and disturbances and great complexity of the silvicultural systems of these multilayer forests, frequent repetition of conventional ground-based plot surveys is often cost prohibitive. Airborne laser scanning (ALS) and multispectral data offer an alternative or supplement to conventional inventories in the Hyrcanian forests of Iran. In this study, the capability of a combination of ALS and UltraCam-D data to model stand volume, tree density, and basal area using random forest (RF) algorithm was evaluated. Systematic sampling was applied to collect field plot data on a 150 m × 200 m sampling grid within a 1100 ha study area located at 36°38‧- 36°42‧N and 54°24‧-54°25‧E. A total of 308 circular plots (0.1 ha) were measured for calculation of stand volume, tree density, and basal area per hectare. For each plot, a set of variables was extracted from both ALS and multispectral data. The RF algorithm was used for modeling of the biophysical properties using ALS and UltraCam-D data separately and combined. The results showed that combining the ALS data and UltraCam-D images provided a slight increase in prediction accuracy compared to separate modeling. The RMSE as percentage of the mean, the mean difference between observed and predicted values, and standard deviation of the differences using a combination of ALS data and UltraCam-D images in an independent validation at 0.1-ha plot level were 31.7%, 1.1%, and 84 m3 ha-1 for stand volume; 27.2%, 0.86%, and 6.5 m2 ha-1 for basal area, and 35.8%, -4.6%, and 77.9 n ha-1 for tree density, respectively. Based on the results, we conclude that fusion of ALS and UltraCam-D data may be useful for modeling of stand volume, basal area, and tree density and thus gain insights into structural characteristics in the complex Hyrcanian forests.

Non-random species loss in a forest herbaceous layer following nitrogen addition

Treesearch

Christopher A. ​Walter; Mary Beth Adams; Frank S. Gilliam; William T. Peterjohn

2017-01-01

Nitrogen (N) additions have decreased species richness (S) in hardwood forest herbaceous layers, yet the functional mechanisms for these decreases have not been explicitly evaluated.We tested two hypothesized mechanisms, random species loss (RSL) and non-random species loss (NRSL), in the hardwood forest herbaceous layer of a long-term, plot-scale...

(abstract) Using an Inversion Algorithm to Retrieve Parameters and Monitor Changes over Forested Areas from SAR Data

NASA Technical Reports Server (NTRS)

Moghaddam, Mahta

1995-01-01

In this work, the application of an inversion algorithm based on a nonlinear opimization technique to retrieve forest parameters from multifrequency polarimetric SAR data is discussed. The approach discussed here allows for retrieving and monitoring changes in forest parameters in a quantative and systematic fashion using SAR data. The parameters to be inverted directly from the data are the electromagnetic scattering properties of the forest components such as their dielectric constants and size characteristics. Once these are known, attributes such as canopy moisture content can be obtained, which are useful in the ecosystem models.

Dynamic species classification of microorganisms across time, abiotic and biotic environments—A sliding window approach

PubMed Central

Griffiths, Jason I.; Fronhofer, Emanuel A.; Garnier, Aurélie; Seymour, Mathew; Altermatt, Florian; Petchey, Owen L.

2017-01-01

The development of video-based monitoring methods allows for rapid, dynamic and accurate monitoring of individuals or communities, compared to slower traditional methods, with far reaching ecological and evolutionary applications. Large amounts of data are generated using video-based methods, which can be effectively processed using machine learning (ML) algorithms into meaningful ecological information. ML uses user defined classes (e.g. species), derived from a subset (i.e. training data) of video-observed quantitative features (e.g. phenotypic variation), to infer classes in subsequent observations. However, phenotypic variation often changes due to environmental conditions, which may lead to poor classification, if environmentally induced variation in phenotypes is not accounted for. Here we describe a framework for classifying species under changing environmental conditions based on the random forest classification. A sliding window approach was developed that restricts temporal and environmentally conditions to improve the classification. We tested our approach by applying the classification framework to experimental data. The experiment used a set of six ciliate species to monitor changes in community structure and behavior over hundreds of generations, in dozens of species combinations and across a temperature gradient. Differences in biotic and abiotic conditions caused simplistic classification approaches to be unsuccessful. In contrast, the sliding window approach allowed classification to be highly successful, as phenotypic differences driven by environmental change, could be captured by the classifier. Importantly, classification using the random forest algorithm showed comparable success when validated against traditional, slower, manual identification. Our framework allows for reliable classification in dynamic environments, and may help to improve strategies for long-term monitoring of species in changing environments. Our classification pipeline can be applied in fields assessing species community dynamics, such as eco-toxicology, ecology and evolutionary ecology. PMID:28472193

Exploring Capabilities of SENTINEL-2 for Vegetation Mapping Using Random Forest

NASA Astrophysics Data System (ADS)

Saini, R.; Ghosh, S. K.

2018-04-01

Accurate vegetation mapping is essential for monitoring crop and sustainable agricultural practice. This study aims to explore the capabilities of Sentinel-2 data over Landsat-8 Operational Land Imager (OLI) data for vegetation mapping. Two combination of Sentinel-2 dataset have been considered, first combination is 4-band dataset at 10m resolution which consists of NIR, R, G and B bands, while second combination is generated by stacking 4 bands having 10 m resolution along with other six sharpened bands using Gram-Schmidt algorithm. For Landsat-8 OLI dataset, six multispectral bands have been pan-sharpened to have a spatial resolution of 15 m using Gram-Schmidt algorithm. Random Forest (RF) and Maximum Likelihood classifier (MLC) have been selected for classification of images. It is found that, overall accuracy achieved by RF for 4-band, 10-band dataset of Sentinel-2 and Landsat-8 OLI are 88.38 %, 90.05 % and 86.68 % respectively. While, MLC give an overall accuracy of 85.12 %, 87.14 % and 83.56 % for 4-band, 10-band Sentinel and Landsat-8 OLI respectively. Results shown that 10-band Sentinel-2 dataset gives highest accuracy and shows a rise of 3.37 % for RF and 3.58 % for MLC compared to Landsat-8 OLI. However, all the classes show significant improvement in accuracy but a major rise in accuracy is observed for Sugarcane, Wheat and Fodder for Sentinel 10-band imagery. This study substantiates the fact that Sentinel-2 data can be utilized for mapping of vegetation with a good degree of accuracy when compared to Landsat-8 OLI specifically when objective is to map a sub class of vegetation.

A domain analysis approach to clear-air turbulence forecasting using high-density in-situ measurements

NASA Astrophysics Data System (ADS)

Abernethy, Jennifer A.

Pilots' ability to avoid clear-air turbulence (CAT) during flight affects the safety of the millions of people who fly commercial airlines and other aircraft, and turbulence costs millions in injuries and aircraft maintenance every year. Forecasting CAT is not straightforward, however; microscale features like the turbulence eddies that affect aircraft (100m) are below the current resolution of operational numerical weather prediction (NWP) models, and the only evidence of CAT episodes, until recently, has been sparse, subjective reports from pilots known as PIREPs. To forecast CAT, researchers use a simple weighted sum of top-performing turbulence indicators derived from NWP model outputs---termed diagnostics---based on their agreement with current PIREPs. However, a new, quantitative source of observation data---high-density measurements made by sensor equipment and software on aircraft, called in-situ measurements---is now available. The main goal of this thesis is to develop new data analysis and processing techniques to apply to the model and new observation data, in order to improve CAT forecasting accuracy. This thesis shows that using in-situ data improves forecasting accuracy and that automated machine learning algorithms such as support vector machines (SVM), logistic regression, and random forests, can match current performance while eliminating almost all hand-tuning. Feature subset selection is paired with the new algorithms to choose diagnostics that predict well as a group rather than individually. Specializing forecasts and choice of diagnostics by geographic region further improves accuracy because of the geographic variation in turbulence sources. This work uses random forests to find climatologically-relevant regions based on these variations and implements a forecasting system testbed which brings these techniques together to rapidly prototype new, regionalized versions of operational CAT forecasting systems.

Integrated Application of Random Forest and Artificial Neural Network Algorithms to Predict Viral Contamination in Coastal Waters

NASA Astrophysics Data System (ADS)

Shamkhali Chenar, S.; Deng, Z.

2017-12-01

Pathogenic viruses pose a significant public health threat and economic losses to shellfish industry in the coastal environment. Norovirus is a contagious virus and the leading cause of epidemic gastroenteritis following consumption of oysters harvested from sewage-contaminated waters. While it is challenging to detect noroviruses in coastal waters due to the lack of sensitive and routine diagnostic methods, machine learning techniques are allowing us to prevent or at least reduce the risks by developing effective predictive models. This study attempts to develop an algorithm between historical norovirus outbreak reports and environmental parameters including water temperature, solar radiation, water level, salinity, precipitation, and wind. For this purpose, the Random Forests statistical technique was utilized to select relevant environmental parameters and their various combinations with different time lags controlling the virus distribution in oyster harvesting areas along the Louisiana Coast. An Artificial Neural Networks (ANN) approach was then presented to predict the outbreaks using a final set of input variables. Finally, a sensitivity analysis was conducted to evaluate relative importance and contribution of the input variables to the model output. Findings demonstrated that the developed model was capable of reproducing historical oyster norovirus outbreaks along the Louisiana Coast with the overall accuracy of than 99.83%, demonstrating the efficacy of the model. Moreover, the increase in water temperature, solar radiation, water level, and salinity, and the decrease in wind and rainfall are associated with the reduction in the model-predicted risk of norovirus outbreak according to sensitivity analysis results. In conclusion, the presented machine learning approach provided reliable tools for predicting potential norovirus outbreaks and could be used for early detection of possible outbreaks and reduce the risk of norovirus to public health and the seafood industry.

Automatic detection of anatomical regions in frontal x-ray images: comparing convolutional neural networks to random forest

NASA Astrophysics Data System (ADS)

Olory Agomma, R.; Vázquez, C.; Cresson, T.; De Guise, J.

2018-02-01

Most algorithms to detect and identify anatomical structures in medical images require either to be initialized close to the target structure, or to know that the structure is present in the image, or to be trained on a homogeneous database (e.g. all full body or all lower limbs). Detecting these structures when there is no guarantee that the structure is present in the image, or when the image database is heterogeneous (mixed configurations), is a challenge for automatic algorithms. In this work we compared two state-of-the-art machine learning techniques in order to determine which one is the most appropriate for predicting targets locations based on image patches. By knowing the position of thirteen landmarks points, labelled by an expert in EOS frontal radiography, we learn the displacement between salient points detected in the image and these thirteen landmarks. The learning step is carried out with a machine learning approach by exploring two methods: Convolutional Neural Network (CNN) and Random Forest (RF). The automatic detection of the thirteen landmarks points in a new image is then obtained by averaging the positions of each one of these thirteen landmarks estimated from all the salient points in the new image. We respectively obtain for CNN and RF, an average prediction error (both mean and standard deviation in mm) of 29 +/-18 and 30 +/- 21 for the thirteen landmarks points, indicating the approximate location of anatomical regions. On the other hand, the learning time is 9 days for CNN versus 80 minutes for RF. We provide a comparison of the results between the two machine learning approaches.

Saliency-Guided Change Detection of Remotely Sensed Images Using Random Forest

NASA Astrophysics Data System (ADS)

Feng, W.; Sui, H.; Chen, X.

2018-04-01

Studies based on object-based image analysis (OBIA) representing the paradigm shift in change detection (CD) have achieved remarkable progress in the last decade. Their aim has been developing more intelligent interpretation analysis methods in the future. The prediction effect and performance stability of random forest (RF), as a new kind of machine learning algorithm, are better than many single predictors and integrated forecasting method. In this paper, we present a novel CD approach for high-resolution remote sensing images, which incorporates visual saliency and RF. First, highly homogeneous and compact image super-pixels are generated using super-pixel segmentation, and the optimal segmentation result is obtained through image superimposition and principal component analysis (PCA). Second, saliency detection is used to guide the search of interest regions in the initial difference image obtained via the improved robust change vector analysis (RCVA) algorithm. The salient regions within the difference image that correspond to the binarized saliency map are extracted, and the regions are subject to the fuzzy c-means (FCM) clustering to obtain the pixel-level pre-classification result, which can be used as a prerequisite for superpixel-based analysis. Third, on the basis of the optimal segmentation and pixel-level pre-classification results, different super-pixel change possibilities are calculated. Furthermore, the changed and unchanged super-pixels that serve as the training samples are automatically selected. The spectral features and Gabor features of each super-pixel are extracted. Finally, superpixel-based CD is implemented by applying RF based on these samples. Experimental results on Ziyuan 3 (ZY3) multi-spectral images show that the proposed method outperforms the compared methods in the accuracy of CD, and also confirm the feasibility and effectiveness of the proposed approach.

Is laparoscopic sleeve gastrectomy safer than laparoscopic gastric bypass? a comparison of 30-day complications using the MBSAQIP data registry.

PubMed

Kumar, Sandhya B; Hamilton, Barbara C; Wood, Stephanie G; Rogers, Stanley J; Carter, Jonathan T; Lin, Matthew Y

2018-03-01

Laparoscopic sleeve gastrectomy (LSG) has become popular due to its technical ease and excellent short-term results. Understanding the risk profile of LSG compared with the gold standard laparoscopic Roux-en-Y gastric bypass (LRYGB) is critical for patient selection. To use traditional regression techniques and random forest classification algorithms to compare LSG with LRYGB using the 2015 Metabolic and Bariatric Surgery Accreditation and Quality Improvement Data Registry. United States. Outcomes were leak, morbidity, and mortality within 30 days. Variable importance was assessed using random forest algorithms. Multivariate models were created in a training set and evaluated on the testing set with receiver operating characteristic curves. The adjusted odds of each outcome were compared. Of 134,142 patients, 93,062 (69%) underwent LSG and 41,080 (31%) underwent LRYGB. One hundred seventy-eight deaths occurred in 96 (.1%) of LSG patients compared with 82 (.2%) of LRYGB patients (P<.001). Morbidity occurred in 8% (5.8% in LSG versus 11.7% in LRYGB, P<.001). Leaks occurred in 1% (.8% in LSG versus 1.6% in LRYGB, P<.001). The most important predictors of all outcomes were body mass index, albumin, and age. In the adjusted multivariate models, LRYGB had higher odds of all complications (leak: odds ratio 2.10, P<.001; morbidity: odds ratio 2.02, P<.001; death: odds ratio 1.64, P<.01). In the Metabolic and Bariatric Surgery Accreditation and Quality Improvements data registry for 2015, LSG had half the risk-adjusted odds of death, serious morbidity, and leak in the first 30 days compared with LRYGB. Copyright © 2018 American Society for Bariatric Surgery. Published by Elsevier Inc. All rights reserved.

Multi-class computational evolution: development, benchmark evaluation and application to RNA-Seq biomarker discovery.

PubMed

Crabtree, Nathaniel M; Moore, Jason H; Bowyer, John F; George, Nysia I

2017-01-01

A computational evolution system (CES) is a knowledge discovery engine that can identify subtle, synergistic relationships in large datasets. Pareto optimization allows CESs to balance accuracy with model complexity when evolving classifiers. Using Pareto optimization, a CES is able to identify a very small number of features while maintaining high classification accuracy. A CES can be designed for various types of data, and the user can exploit expert knowledge about the classification problem in order to improve discrimination between classes. These characteristics give CES an advantage over other classification and feature selection algorithms, particularly when the goal is to identify a small number of highly relevant, non-redundant biomarkers. Previously, CESs have been developed only for binary class datasets. In this study, we developed a multi-class CES. The multi-class CES was compared to three common feature selection and classification algorithms: support vector machine (SVM), random k-nearest neighbor (RKNN), and random forest (RF). The algorithms were evaluated on three distinct multi-class RNA sequencing datasets. The comparison criteria were run-time, classification accuracy, number of selected features, and stability of selected feature set (as measured by the Tanimoto distance). The performance of each algorithm was data-dependent. CES performed best on the dataset with the smallest sample size, indicating that CES has a unique advantage since the accuracy of most classification methods suffer when sample size is small. The multi-class extension of CES increases the appeal of its application to complex, multi-class datasets in order to identify important biomarkers and features.

Thorough statistical comparison of machine learning regression models and their ensembles for sub-pixel imperviousness and imperviousness change mapping

NASA Astrophysics Data System (ADS)

Drzewiecki, Wojciech

2017-12-01

We evaluated the performance of nine machine learning regression algorithms and their ensembles for sub-pixel estimation of impervious areas coverages from Landsat imagery. The accuracy of imperviousness mapping in individual time points was assessed based on RMSE, MAE and R2. These measures were also used for the assessment of imperviousness change intensity estimations. The applicability for detection of relevant changes in impervious areas coverages at sub-pixel level was evaluated using overall accuracy, F-measure and ROC Area Under Curve. The results proved that Cubist algorithm may be advised for Landsat-based mapping of imperviousness for single dates. Stochastic gradient boosting of regression trees (GBM) may be also considered for this purpose. However, Random Forest algorithm is endorsed for both imperviousness change detection and mapping of its intensity. In all applications the heterogeneous model ensembles performed at least as well as the best individual models or better. They may be recommended for improving the quality of sub-pixel imperviousness and imperviousness change mapping. The study revealed also limitations of the investigated methodology for detection of subtle changes of imperviousness inside the pixel. None of the tested approaches was able to reliably classify changed and non-changed pixels if the relevant change threshold was set as one or three percent. Also for fi ve percent change threshold most of algorithms did not ensure that the accuracy of change map is higher than the accuracy of random classifi er. For the threshold of relevant change set as ten percent all approaches performed satisfactory.

Automated Transient Identification in the Dark Energy Survey

NASA Astrophysics Data System (ADS)

Goldstein, D. A.; D'Andrea, C. B.; Fischer, J. A.; Foley, R. J.; Gupta, R. R.; Kessler, R.; Kim, A. G.; Nichol, R. C.; Nugent, P. E.; Papadopoulos, A.; Sako, M.; Smith, M.; Sullivan, M.; Thomas, R. C.; Wester, W.; Wolf, R. C.; Abdalla, F. B.; Banerji, M.; Benoit-Lévy, A.; Bertin, E.; Brooks, D.; Carnero Rosell, A.; Castander, F. J.; da Costa, L. N.; Covarrubias, R.; DePoy, D. L.; Desai, S.; Diehl, H. T.; Doel, P.; Eifler, T. F.; Fausti Neto, A.; Finley, D. A.; Flaugher, B.; Fosalba, P.; Frieman, J.; Gerdes, D.; Gruen, D.; Gruendl, R. A.; James, D.; Kuehn, K.; Kuropatkin, N.; Lahav, O.; Li, T. S.; Maia, M. A. G.; Makler, M.; March, M.; Marshall, J. L.; Martini, P.; Merritt, K. W.; Miquel, R.; Nord, B.; Ogando, R.; Plazas, A. A.; Romer, A. K.; Roodman, A.; Sanchez, E.; Scarpine, V.; Schubnell, M.; Sevilla-Noarbe, I.; Smith, R. C.; Soares-Santos, M.; Sobreira, F.; Suchyta, E.; Swanson, M. E. C.; Tarle, G.; Thaler, J.; Walker, A. R.

2015-09-01

We describe an algorithm for identifying point-source transients and moving objects on reference-subtracted optical images containing artifacts of processing and instrumentation. The algorithm makes use of the supervised machine learning technique known as Random Forest. We present results from its use in the Dark Energy Survey Supernova program (DES-SN), where it was trained using a sample of 898,963 signal and background events generated by the transient detection pipeline. After reprocessing the data collected during the first DES-SN observing season (2013 September through 2014 February) using the algorithm, the number of transient candidates eligible for human scanning decreased by a factor of 13.4, while only 1.0% of the artificial Type Ia supernovae (SNe) injected into search images to monitor survey efficiency were lost, most of which were very faint events. Here we characterize the algorithm’s performance in detail, and we discuss how it can inform pipeline design decisions for future time-domain imaging surveys, such as the Large Synoptic Survey Telescope and the Zwicky Transient Facility. An implementation of the algorithm and the training data used in this paper are available at at http://portal.nersc.gov/project/dessn/autoscan.

Using Machine Learning To Predict Which Light Curves Will Yield Stellar Rotation Periods

NASA Astrophysics Data System (ADS)

Agüeros, Marcel; Teachey, Alexander

2018-01-01

Using time-domain photometry to reliably measure a solar-type star's rotation period requires that its light curve have a number of favorable characteristics. The probability of recovering a period will be a non-linear function of these light curve features, which are either astrophysical in nature or set by the observations. We employ standard machine learning algorithms (artificial neural networks and random forests) to predict whether a given light curve will produce a robust rotation period measurement from its Lomb-Scargle periodogram. The algorithms are trained and validated using salient statistics extracted from both simulated light curves and their corresponding periodograms, and we apply these classifiers to the most recent Intermediate Palomar Transient Factory (iPTF) data release. With this pipeline, we anticipate measuring rotation periods for a significant fraction of the ∼4x108 stars in the iPTF footprint.

Design and implementation of ticket price forecasting system

NASA Astrophysics Data System (ADS)

Li, Yuling; Li, Zhichao

2018-05-01

With the advent of the aviation travel industry, a large number of data mining technologies have been developed to increase profits for airlines in the past two decades. The implementation of the digital optimization strategy leads to price discrimination, for example, similar seats on the same flight are purchased at different prices, depending on the time of purchase, the supplier, and so on. Price fluctuations make the prediction of ticket prices have application value. In this paper, a combination of ARMA algorithm and random forest algorithm is proposed to predict the price of air ticket. The experimental results show that the model is more reliable by comparing the forecasting results with the actual results of each price model. The model is helpful for passengers to buy tickets and to save money. Based on the proposed model, using Python language and SQL Server database, we design and implement the ticket price forecasting system.

Storm-based Cloud-to-Ground Lightning Probabilities and Warnings

NASA Astrophysics Data System (ADS)

Calhoun, K. M.; Meyer, T.; Kingfield, D.

2017-12-01

A new cloud-to-ground (CG) lightning probability algorithm has been developed using machine-learning methods. With storm-based inputs of Earth Networks' in-cloud lightning, Vaisala's CG lightning, multi-radar/multi-sensor (MRMS) radar derived products including the Maximum Expected Size of Hail (MESH) and Vertically Integrated Liquid (VIL), and near storm environmental data including lapse rate and CAPE, a random forest algorithm was trained to produce probabilities of CG lightning up to one-hour in advance. As part of the Prototype Probabilistic Hazard Information experiment in the Hazardous Weather Testbed in 2016 and 2017, National Weather Service forecasters were asked to use this CG lightning probability guidance to create rapidly updating probability grids and warnings for the threat of CG lightning for 0-60 minutes. The output from forecasters was shared with end-users, including emergency managers and broadcast meteorologists, as part of an integrated warning team.

Machine learning methods in chemoinformatics

PubMed Central

Mitchell, John B O

2014-01-01

Machine learning algorithms are generally developed in computer science or adjacent disciplines and find their way into chemical modeling by a process of diffusion. Though particular machine learning methods are popular in chemoinformatics and quantitative structure–activity relationships (QSAR), many others exist in the technical literature. This discussion is methods-based and focused on some algorithms that chemoinformatics researchers frequently use. It makes no claim to be exhaustive. We concentrate on methods for supervised learning, predicting the unknown property values of a test set of instances, usually molecules, based on the known values for a training set. Particularly relevant approaches include Artificial Neural Networks, Random Forest, Support Vector Machine, k-Nearest Neighbors and naïve Bayes classifiers. WIREs Comput Mol Sci 2014, 4:468–481. How to cite this article: WIREs Comput Mol Sci 2014, 4:468–481. doi:10.1002/wcms.1183 PMID:25285160

Geographical traceability of Marsdenia tenacissima by Fourier transform infrared spectroscopy and chemometrics

NASA Astrophysics Data System (ADS)

Li, Chao; Yang, Sheng-Chao; Guo, Qiao-Sheng; Zheng, Kai-Yan; Wang, Ping-Li; Meng, Zhen-Gui

2016-01-01

A combination of Fourier transform infrared spectroscopy with chemometrics tools provided an approach for studying Marsdenia tenacissima according to its geographical origin. A total of 128 M. tenacissima samples from four provinces in China were analyzed with FTIR spectroscopy. Six pattern recognition methods were used to construct the discrimination models: support vector machine-genetic algorithms, support vector machine-particle swarm optimization, K-nearest neighbors, radial basis function neural network, random forest and support vector machine-grid search. Experimental results showed that K-nearest neighbors was superior to other mathematical algorithms after data were preprocessed with wavelet de-noising, with a discrimination rate of 100% in both the training and prediction sets. This study demonstrated that FTIR spectroscopy coupled with K-nearest neighbors could be successfully applied to determine the geographical origins of M. tenacissima samples, thereby providing reliable authentication in a rapid, cheap and noninvasive way.

ERRATUM: “Automated Transient Identi cation in the Dark Energy Survey” (2015, AJ, 150, 82)

DOE PAGES

Goldstein, D. A.; D’Andrea, C. B.; Fischer, J. A.; ...

2015-08-20

Here, we describe an algorithm for identifying point-source transients and moving objects on reference-subtracted optical images containing artifacts of processing and instrumentation. The algorithm makes use of the supervised machine learning technique known as Random Forest. We present results from its use in the Dark Energy Survey Supernova program (DES-SN), where it was trained using a sample of 898,963 signal and background events generated by the transient detection pipeline. After reprocessing the data collected during the first DES-SN observing season (2013 September through 2014 February) using the algorithm, the number of transient candidates eligible for human scanning decreased by amore » factor of 13.4, while only 1.0% of the artificial Type Ia supernovae (SNe) injected into search images to monitor survey efficiency were lost, most of which were very faint events. Here we characterize the algorithm's performance in detail, and we discuss how it can inform pipeline design decisions for future time-domain imaging surveys, such as the Large Synoptic Survey Telescope and the Zwicky Transient Facility. An implementation of the algorithm and the training data used in this paper are available at at http://portal.nersc.gov/project/dessn/autoscan.« less

Classification of Parkinson's disease utilizing multi-edit nearest-neighbor and ensemble learning algorithms with speech samples.

PubMed

Zhang, He-Hua; Yang, Liuyang; Liu, Yuchuan; Wang, Pin; Yin, Jun; Li, Yongming; Qiu, Mingguo; Zhu, Xueru; Yan, Fang

2016-11-16

The use of speech based data in the classification of Parkinson disease (PD) has been shown to provide an effect, non-invasive mode of classification in recent years. Thus, there has been an increased interest in speech pattern analysis methods applicable to Parkinsonism for building predictive tele-diagnosis and tele-monitoring models. One of the obstacles in optimizing classifications is to reduce noise within the collected speech samples, thus ensuring better classification accuracy and stability. While the currently used methods are effect, the ability to invoke instance selection has been seldomly examined. In this study, a PD classification algorithm was proposed and examined that combines a multi-edit-nearest-neighbor (MENN) algorithm and an ensemble learning algorithm. First, the MENN algorithm is applied for selecting optimal training speech samples iteratively, thereby obtaining samples with high separability. Next, an ensemble learning algorithm, random forest (RF) or decorrelated neural network ensembles (DNNE), is used to generate trained samples from the collected training samples. Lastly, the trained ensemble learning algorithms are applied to the test samples for PD classification. This proposed method was examined using a more recently deposited public datasets and compared against other currently used algorithms for validation. Experimental results showed that the proposed algorithm obtained the highest degree of improved classification accuracy (29.44%) compared with the other algorithm that was examined. Furthermore, the MENN algorithm alone was found to improve classification accuracy by as much as 45.72%. Moreover, the proposed algorithm was found to exhibit a higher stability, particularly when combining the MENN and RF algorithms. This study showed that the proposed method could improve PD classification when using speech data and can be applied to future studies seeking to improve PD classification methods.

Approximating prediction uncertainty for random forest regression models

Treesearch

John W. Coulston; Christine E. Blinn; Valerie A. Thomas; Randolph H. Wynne

2016-01-01

Machine learning approaches such as random forest have increased for the spatial modeling and mapping of continuous variables. Random forest is a non-parametric ensemble approach, and unlike traditional regression approaches there is no direct quantification of prediction error. Understanding prediction uncertainty is important when using model-based continuous maps as...

Investigation of the Capability of Compact Polarimetric SAR Interferometry to Estimate Forest Height

NASA Astrophysics Data System (ADS)

Zhang, Hong; Xie, Lei; Wang, Chao; Chen, Jiehong

2013-08-01

The main objective of this paper is to investigate the capability of compact Polarimetric SAR Interferometry (C-PolInSAR) on forest height estimation. For this, the pseudo fully polarimetric interferomteric (F-PolInSAR) covariance matrix is firstly reconstructed, then the three- stage inversion algorithm, hybrid algorithm, Music and Capon algorithm are applied to both C-PolInSAR covariance matrix and pseudo F-PolInSAR covariance matrix. The availability of forest height estimation is demonstrated using L-band data generated by simulator PolSARProSim and X-band airborne data acquired by East China Research Institute of Electronic Engineering, China Electronics Technology Group Corporation.

Object-based assessment of burn severity in diseased forests using high-spatial and high-spectral resolution MASTER airborne imagery

NASA Astrophysics Data System (ADS)

Chen, Gang; Metz, Margaret R.; Rizzo, David M.; Dillon, Whalen W.; Meentemeyer, Ross K.

2015-04-01

Forest ecosystems are subject to a variety of disturbances with increasing intensities and frequencies, which may permanently change the trajectories of forest recovery and disrupt the ecosystem services provided by trees. Fire and invasive species, especially exotic disease-causing pathogens and insects, are examples of disturbances that together could pose major threats to forest health. This study examines the impacts of fire and exotic disease (sudden oak death) on forests, with an emphasis on the assessment of post-fire burn severity in a forest where trees have experienced three stages of disease progression pre-fire: early-stage (trees retaining dried foliage and fine twigs), middle-stage (trees losing fine crown fuels), and late-stage (trees falling down). The research was conducted by applying Geographic Object-Based Image Analysis (GEOBIA) to MASTER airborne images that were acquired immediately following the fire for rapid assessment and contained both high-spatial (4 m) and high-spectral (50 bands) resolutions. Although GEOBIA has gradually become a standard tool for analyzing high-spatial resolution imagery, high-spectral resolution data (dozens to hundreds of bands) can dramatically reduce computation efficiency in the process of segmentation and object-based variable extraction, leading to complicated variable selection for succeeding modeling. Hence, we also assessed two widely used band reduction algorithms, PCA (principal component analysis) and MNF (minimum noise fraction), for the delineation of image objects and the subsequent performance of burn severity models using either PCA or MNF derived variables. To increase computation efficiency, only the top 5 PCA and MNF and top 10 PCA and MNF components were evaluated, which accounted for 10% and 20% of the total number of the original 50 spectral bands, respectively. Results show that if no band reduction was applied the models developed for the three stages of disease progression had relatively similar performance, where both spectral responses and texture contributed to burn assessments. However, the application of PCA and MNF introduced much greater variation among models across the three stages. For the early-stage disease progression, neither band reduction algorithms improved or retained the accuracy of burn severity modeling (except for the use of 10 MNF components). Compared to the no-band-reduction scenario, band reduction led to a greater level of overestimation of low-degree burns and underestimation of medium-degree burns, suggesting that the spectral variation removed by PCA and MNF was vital for distinguishing between the spectral reflectance from disease-induced dried crowns (still retaining high structural complexity) and fire ash. For the middle-stage, both algorithms improved the model R2 values by 2-37%, while the late-stage models had comparable or better performance to those using the original 50 spectral bands. This could be explained by the loss of tree crowns enabling better signal penetration, thus leading to reduced spectral variation from canopies. Hence, spectral bands containing a high degree of random noise were correctly removed by the band reduction algorithms. Compared to the middle-stage, the late-stage forest stands were covered by large piles of fallen trees and branches, resulting in higher variability of MASTER imagery. The ability of band reduction to improve the model performance for these late-stage forest stands was reduced, because the valuable spectral variation representing the actual late-stage forest status was partially removed by both algorithms as noise. Our results indicate that PCA and MNF are promising for balancing computation efficiency and the performance of burn severity models in forest stands subject to the middle and late stages of sudden oak death disease progression. Compared to PCA, MNF dramatically reduced image spectral variation, generating larger image objects with less complexity of object shapes. Whereas, PCA-based models delivered superior performance in most evaluated cases suggesting that some key spectral variability contributing to the accuracy of burn severity models in diseased forests may have been removed together with true spectral noise through MNF transformations.

Novel solutions for an old disease: diagnosis of acute appendicitis with random forest, support vector machines, and artificial neural networks.

PubMed

Hsieh, Chung-Ho; Lu, Ruey-Hwa; Lee, Nai-Hsin; Chiu, Wen-Ta; Hsu, Min-Huei; Li, Yu-Chuan Jack

2011-01-01

Diagnosing acute appendicitis clinically is still difficult. We developed random forests, support vector machines, and artificial neural network models to diagnose acute appendicitis. Between January 2006 and December 2008, patients who had a consultation session with surgeons for suspected acute appendicitis were enrolled. Seventy-five percent of the data set was used to construct models including random forest, support vector machines, artificial neural networks, and logistic regression. Twenty-five percent of the data set was withheld to evaluate model performance. The area under the receiver operating characteristic curve (AUC) was used to evaluate performance, which was compared with that of the Alvarado score. Data from a total of 180 patients were collected, 135 used for training and 45 for testing. The mean age of patients was 39.4 years (range, 16-85). Final diagnosis revealed 115 patients with and 65 without appendicitis. The AUC of random forest, support vector machines, artificial neural networks, logistic regression, and Alvarado was 0.98, 0.96, 0.91, 0.87, and 0.77, respectively. The sensitivity, specificity, positive, and negative predictive values of random forest were 94%, 100%, 100%, and 87%, respectively. Random forest performed better than artificial neural networks, logistic regression, and Alvarado. We demonstrated that random forest can predict acute appendicitis with good accuracy and, deployed appropriately, can be an effective tool in clinical decision making. Copyright © 2011 Mosby, Inc. All rights reserved.

The experimental design of the Missouri Ozark Forest Ecosystem Project

Treesearch

Steven L. Sheriff; Shuoqiong He

1997-01-01

The Missouri Ozark Forest Ecosystem Project (MOFEP) is an experiment that examines the effects of three forest management practices on the forest community. MOFEP is designed as a randomized complete block design using nine sites divided into three blocks. Treatments of uneven-aged, even-aged, and no-harvest management were randomly assigned to sites within each block...

Application of AIS Technology to Forest Mapping

NASA Technical Reports Server (NTRS)

Yool, S. R.; Star, J. L.

1985-01-01

Concerns about environmental effects of large scale deforestation have prompted efforts to map forests over large areas using various remote sensing data and image processing techniques. Basic research on the spectral characteristics of forest vegetation are required to form a basis for development of new techniques, and for image interpretation. Examination of LANDSAT data and image processing algorithms over a portion of boreal forest have demonstrated the complexity of relations between the various expressions of forest canopies, environmental variability, and the relative capacities of different image processing algorithms to achieve high classification accuracies under these conditions. Airborne Imaging Spectrometer (AIS) data may in part provide the means to interpret the responses of standard data and techniques to the vegetation based on its relatively high spectral resolution.

Random Forest as an Imputation Method for Education and Psychology Research: Its Impact on Item Fit and Difficulty of the Rasch Model

ERIC Educational Resources Information Center

Golino, Hudson F.; Gomes, Cristiano M. A.

2016-01-01

This paper presents a non-parametric imputation technique, named random forest, from the machine learning field. The random forest procedure has two main tuning parameters: the number of trees grown in the prediction and the number of predictors used. Fifty experimental conditions were created in the imputation procedure, with different…

Prediction of carbonate rock type from NMR responses using data mining techniques

NASA Astrophysics Data System (ADS)

Gonçalves, Eduardo Corrêa; da Silva, Pablo Nascimento; Silveira, Carla Semiramis; Carneiro, Giovanna; Domingues, Ana Beatriz; Moss, Adam; Pritchard, Tim; Plastino, Alexandre; Azeredo, Rodrigo Bagueira de Vasconcellos

2017-05-01

Recent studies have indicated that the accurate identification of carbonate rock types in a reservoir can be employed as a preliminary step to enhance the effectiveness of petrophysical property modeling. Furthermore, rock typing activity has been shown to be of key importance in several steps of formation evaluation, such as the study of sedimentary series, reservoir zonation and well-to-well correlation. In this paper, a methodology based exclusively on the analysis of 1H-NMR (Nuclear Magnetic Resonance) relaxation responses - using data mining algorithms - is evaluated to perform the automatic classification of carbonate samples according to their rock type. We analyze the effectiveness of six different classification algorithms (k-NN, Naïve Bayes, C4.5, Random Forest, SMO and Multilayer Perceptron) and two data preprocessing strategies (discretization and feature selection). The dataset used in this evaluation is formed by 78 1H-NMR T2 distributions of fully brine-saturated rock samples from six different rock type classes. The experiments reveal that the combination of preprocessing strategies with classification algorithms is able to achieve a prediction accuracy of 97.4%.

A Hybrid Spectral Clustering and Deep Neural Network Ensemble Algorithm for Intrusion Detection in Sensor Networks

PubMed Central

Ma, Tao; Wang, Fen; Cheng, Jianjun; Yu, Yang; Chen, Xiaoyun

2016-01-01

The development of intrusion detection systems (IDS) that are adapted to allow routers and network defence systems to detect malicious network traffic disguised as network protocols or normal access is a critical challenge. This paper proposes a novel approach called SCDNN, which combines spectral clustering (SC) and deep neural network (DNN) algorithms. First, the dataset is divided into k subsets based on sample similarity using cluster centres, as in SC. Next, the distance between data points in a testing set and the training set is measured based on similarity features and is fed into the deep neural network algorithm for intrusion detection. Six KDD-Cup99 and NSL-KDD datasets and a sensor network dataset were employed to test the performance of the model. These experimental results indicate that the SCDNN classifier not only performs better than backpropagation neural network (BPNN), support vector machine (SVM), random forest (RF) and Bayes tree models in detection accuracy and the types of abnormal attacks found. It also provides an effective tool of study and analysis of intrusion detection in large networks. PMID:27754380

A Hybrid Spectral Clustering and Deep Neural Network Ensemble Algorithm for Intrusion Detection in Sensor Networks.

PubMed

Ma, Tao; Wang, Fen; Cheng, Jianjun; Yu, Yang; Chen, Xiaoyun

2016-10-13

The development of intrusion detection systems (IDS) that are adapted to allow routers and network defence systems to detect malicious network traffic disguised as network protocols or normal access is a critical challenge. This paper proposes a novel approach called SCDNN, which combines spectral clustering (SC) and deep neural network (DNN) algorithms. First, the dataset is divided into k subsets based on sample similarity using cluster centres, as in SC. Next, the distance between data points in a testing set and the training set is measured based on similarity features and is fed into the deep neural network algorithm for intrusion detection. Six KDD-Cup99 and NSL-KDD datasets and a sensor network dataset were employed to test the performance of the model. These experimental results indicate that the SCDNN classifier not only performs better than backpropagation neural network (BPNN), support vector machine (SVM), random forest (RF) and Bayes tree models in detection accuracy and the types of abnormal attacks found. It also provides an effective tool of study and analysis of intrusion detection in large networks.

Using Random Forest Models to Predict Organizational Violence

NASA Technical Reports Server (NTRS)

Levine, Burton; Bobashev, Georgly

2012-01-01

We present a methodology to access the proclivity of an organization to commit violence against nongovernment personnel. We fitted a Random Forest model using the Minority at Risk Organizational Behavior (MAROS) dataset. The MAROS data is longitudinal; so, individual observations are not independent. We propose a modification to the standard Random Forest methodology to account for the violation of the independence assumption. We present the results of the model fit, an example of predicting violence for an organization; and finally, we present a summary of the forest in a "meta-tree,"

Forecasting Daily Patient Outflow From a Ward Having No Real-Time Clinical Data

PubMed Central

Tran, Truyen; Luo, Wei; Phung, Dinh; Venkatesh, Svetha

2016-01-01

Background: Modeling patient flow is crucial in understanding resource demand and prioritization. We study patient outflow from an open ward in an Australian hospital, where currently bed allocation is carried out by a manager relying on past experiences and looking at demand. Automatic methods that provide a reasonable estimate of total next-day discharges can aid in efficient bed management. The challenges in building such methods lie in dealing with large amounts of discharge noise introduced by the nonlinear nature of hospital procedures, and the nonavailability of real-time clinical information in wards. Objective Our study investigates different models to forecast the total number of next-day discharges from an open ward having no real-time clinical data. Methods We compared 5 popular regression algorithms to model total next-day discharges: (1) autoregressive integrated moving average (ARIMA), (2) the autoregressive moving average with exogenous variables (ARMAX), (3) k-nearest neighbor regression, (4) random forest regression, and (5) support vector regression. Although the autoregressive integrated moving average model relied on past 3-month discharges, nearest neighbor forecasting used median of similar discharges in the past in estimating next-day discharge. In addition, the ARMAX model used the day of the week and number of patients currently in ward as exogenous variables. For the random forest and support vector regression models, we designed a predictor set of 20 patient features and 88 ward-level features. Results Our data consisted of 12,141 patient visits over 1826 days. Forecasting quality was measured using mean forecast error, mean absolute error, symmetric mean absolute percentage error, and root mean square error. When compared with a moving average prediction model, all 5 models demonstrated superior performance with the random forests achieving 22.7% improvement in mean absolute error, for all days in the year 2014. Conclusions In the absence of clinical information, our study recommends using patient-level and ward-level data in predicting next-day discharges. Random forest and support vector regression models are able to use all available features from such data, resulting in superior performance over traditional autoregressive methods. An intelligent estimate of available beds in wards plays a crucial role in relieving access block in emergency departments. PMID:27444059

Spatial inventory integrating raster databases and point sample data. [Geographic Information System for timber inventory

NASA Technical Reports Server (NTRS)

Strahler, A. H.; Woodcock, C. E.; Logan, T. L.

1983-01-01

A timber inventory of the Eldorado National Forest, located in east-central California, provides an example of the use of a Geographic Information System (GIS) to stratify large areas of land for sampling and the collection of statistical data. The raster-based GIS format of the VICAR/IBIS software system allows simple and rapid tabulation of areas, and facilitates the selection of random locations for ground sampling. Algorithms that simplify the complex spatial pattern of raster-based information, and convert raster format data to strings of coordinate vectors, provide a link to conventional vector-based geographic information systems.

Comparison of four machine learning algorithms for their applicability in satellite-based optical rainfall retrievals

NASA Astrophysics Data System (ADS)

Meyer, Hanna; Kühnlein, Meike; Appelhans, Tim; Nauss, Thomas

2016-03-01

Machine learning (ML) algorithms have successfully been demonstrated to be valuable tools in satellite-based rainfall retrievals which show the practicability of using ML algorithms when faced with high dimensional and complex data. Moreover, recent developments in parallel computing with ML present new possibilities for training and prediction speed and therefore make their usage in real-time systems feasible. This study compares four ML algorithms - random forests (RF), neural networks (NNET), averaged neural networks (AVNNET) and support vector machines (SVM) - for rainfall area detection and rainfall rate assignment using MSG SEVIRI data over Germany. Satellite-based proxies for cloud top height, cloud top temperature, cloud phase and cloud water path serve as predictor variables. The results indicate an overestimation of rainfall area delineation regardless of the ML algorithm (averaged bias = 1.8) but a high probability of detection ranging from 81% (SVM) to 85% (NNET). On a 24-hour basis, the performance of the rainfall rate assignment yielded R2 values between 0.39 (SVM) and 0.44 (AVNNET). Though the differences in the algorithms' performance were rather small, NNET and AVNNET were identified as the most suitable algorithms. On average, they demonstrated the best performance in rainfall area delineation as well as in rainfall rate assignment. NNET's computational speed is an additional advantage in work with large datasets such as in remote sensing based rainfall retrievals. However, since no single algorithm performed considerably better than the others we conclude that further research in providing suitable predictors for rainfall is of greater necessity than an optimization through the choice of the ML algorithm.

Discrimination of crop types with TerraSAR-X-derived information

NASA Astrophysics Data System (ADS)

Sonobe, Rei; Tani, Hiroshi; Wang, Xiufeng; Kobayashi, Nobuyuki; Shimamura, Hideki

Although classification maps are required for management and for the estimation of agricultural disaster compensation, those techniques have yet to be established. This paper describes the comparison of three different classification algorithms for mapping crops in Hokkaido, Japan, using TerraSAR-X (including TanDEM-X) dual-polarimetric data. In the study area, beans, beets, grasslands, maize, potatoes and winter wheat were cultivated. In this study, classification using TerraSAR-X-derived information was performed. Coherence values, polarimetric parameters and gamma nought values were also obtained and evaluated regarding their usefulness in crop classification. Accurate classification may be possible with currently existing supervised learning models. A comparison between the classification and regression tree (CART), support vector machine (SVM) and random forests (RF) algorithms was performed. Even though J-M distances were lower than 1.0 on all TerraSAR-X acquisition days, good results were achieved (e.g., separability between winter wheat and grass) due to the characteristics of the machine learning algorithm. It was found that SVM performed best, achieving an overall accuracy of 95.0% based on the polarimetric parameters and gamma nought values for HH and VV polarizations. The misclassified fields were less than 100 a in area and 79.5-96.3% were less than 200 a with the exception of grassland. When some feature such as a road or windbreak forest is present in the TerraSAR-X data, the ratio of its extent to that of the field is relatively higher for the smaller fields, which leads to misclassifications.

A Global Study of GPP focusing on Light Use Efficiency in a Random Forest Regression Model

NASA Astrophysics Data System (ADS)

Fang, W.; Wei, S.; Yi, C.; Hendrey, G. R.

2016-12-01

Light use efficiency (LUE) is at the core of mechanistic modeling of global gross primary production (GPP). However, most LUE estimates in global models are satellite-based and coarsely measured with emphasis on environmental variables. Others are from eddy covariance towers with much greater spatial and temporal data quality and emphasis on mechanistic processes, but in a limited number of sites. In this paper, we conducted a comprehensive global study of tower-based LUE from 237 FLUXNET towers, and scaled up LUEs from in-situ tower level to global biome level. We integrated key environmental and biological variables into the tower-based LUE estimates, at 0.5o x 0.5o grid-cell resolution, using a random forest regression (RFR) approach. We then developed an RFR-LUE-GPP model using the grid-cell LUE data, and compared it to a tower-LUE-GPP model by the conventional way of treating LUE as a series of biome-specific constants. In order to calibrate the LUE models, we developed a data-driven RFR-GPP model using a random forest regression method. Our results showed that LUE varies largely with latitude. We estimated a global area-weighted average of LUE at 1.21 gC m-2 MJ-1 APAR, which led to an estimated global GPP of 102.9 Gt C /year from 2000 to 2005. The tower-LUE-GPP model tended to overestimate forest GPP in tropical and boreal regions. Large uncertainties exist in GPP estimates over sparsely vegetated areas covered by savannas and woody savannas around the middle to low latitudes (i.g. 20oS to 40oS and 5oN to 15oN) due to lack of available data. Model results were improved by incorporating Köppen climate types to represent climate /meteorological information in machine learning modeling. This shed new light on the recognized issues of climate dependence of spring onset of photosynthesis and the challenges in modeling the biome GPP of evergreen broad leaf forests (EBF) accurately. The divergent responses of GPP to temperature and precipitation at mid-high latitudes and at mid-low latitudes echoed the necessity of modeling GPP separately by latitudes. This work provided a global distribution of LUE estimate, and developed a comprehensive algorithm modeling global terrestrial carbon with high spatial and temporal resolutions.

Integrating Natural Language Processing and Machine Learning Algorithms to Categorize Oncologic Response in Radiology Reports.

PubMed

Chen, Po-Hao; Zafar, Hanna; Galperin-Aizenberg, Maya; Cook, Tessa

2018-04-01

A significant volume of medical data remains unstructured. Natural language processing (NLP) and machine learning (ML) techniques have shown to successfully extract insights from radiology reports. However, the codependent effects of NLP and ML in this context have not been well-studied. Between April 1, 2015 and November 1, 2016, 9418 cross-sectional abdomen/pelvis CT and MR examinations containing our internal structured reporting element for cancer were separated into four categories: Progression, Stable Disease, Improvement, or No Cancer. We combined each of three NLP techniques with five ML algorithms to predict the assigned label using the unstructured report text and compared the performance of each combination. The three NLP algorithms included term frequency-inverse document frequency (TF-IDF), term frequency weighting (TF), and 16-bit feature hashing. The ML algorithms included logistic regression (LR), random decision forest (RDF), one-vs-all support vector machine (SVM), one-vs-all Bayes point machine (BPM), and fully connected neural network (NN). The best-performing NLP model consisted of tokenized unigrams and bigrams with TF-IDF. Increasing N-gram length yielded little to no added benefit for most ML algorithms. With all parameters optimized, SVM had the best performance on the test dataset, with 90.6 average accuracy and F score of 0.813. The interplay between ML and NLP algorithms and their effect on interpretation accuracy is complex. The best accuracy is achieved when both algorithms are optimized concurrently.

An Automated Approach to Map the History of Forest Disturbance from Insect Mortality and Harvest with Landsat Time-Series Data

NASA Technical Reports Server (NTRS)

Rudasill-Neigh, Christopher S.; Bolton, Douglas K.; Diabate, Mouhamad; Williams, Jennifer J.; Carvalhais, Nuno

2014-01-01

Forests contain a majority of the aboveground carbon (C) found in ecosystems, and understanding biomass lost from disturbance is essential to improve our C-cycle knowledge. Our study region in the Wisconsin and Minnesota Laurentian Forest had a strong decline in Normalized Difference Vegetation Index (NDVI) from 1982 to 2007, observed with the National Ocean and Atmospheric Administration's (NOAA) series of Advanced Very High Resolution Radiometer (AVHRR). To understand the potential role of disturbances in the terrestrial C-cycle, we developed an algorithm to map forest disturbances from either harvest or insect outbreak for Landsat time-series stacks. We merged two image analysis approaches into one algorithm to monitor forest change that included: (1) multiple disturbance index thresholds to capture clear-cut harvest; and (2) a spectral trajectory-based image analysis with multiple confidence interval thresholds to map insect outbreak. We produced 20 maps and evaluated classification accuracy with air-photos and insect air-survey data to understand the performance of our algorithm. We achieved overall accuracies ranging from 65% to 75%, with an average accuracy of 72%. The producer's and user's accuracy ranged from a maximum of 32% to 70% for insect disturbance, 60% to 76% for insect mortality and 82% to 88% for harvested forest, which was the dominant disturbance agent. Forest disturbances accounted for 22% of total forested area (7349 km2). Our algorithm provides a basic approach to map disturbance history where large impacts to forest stands have occurred and highlights the limited spectral sensitivity of Landsat time-series to outbreaks of defoliating insects. We found that only harvest and insect mortality events can be mapped with adequate accuracy with a non-annual Landsat time-series. This limited our land cover understanding of NDVI decline drivers. We demonstrate that to capture more subtle disturbances with spectral trajectories, future observations must be temporally dense to distinguish between type and frequency in heterogeneous landscapes.

Automatic co-segmentation of lung tumor based on random forest in PET-CT images

NASA Astrophysics Data System (ADS)

Jiang, Xueqing; Xiang, Dehui; Zhang, Bin; Zhu, Weifang; Shi, Fei; Chen, Xinjian

2016-03-01

In this paper, a fully automatic method is proposed to segment the lung tumor in clinical 3D PET-CT images. The proposed method effectively combines PET and CT information to make full use of the high contrast of PET images and superior spatial resolution of CT images. Our approach consists of three main parts: (1) initial segmentation, in which spines are removed in CT images and initial connected regions achieved by thresholding based segmentation in PET images; (2) coarse segmentation, in which monotonic downhill function is applied to rule out structures which have similar standardized uptake values (SUV) to the lung tumor but do not satisfy a monotonic property in PET images; (3) fine segmentation, random forests method is applied to accurately segment the lung tumor by extracting effective features from PET and CT images simultaneously. We validated our algorithm on a dataset which consists of 24 3D PET-CT images from different patients with non-small cell lung cancer (NSCLC). The average TPVF, FPVF and accuracy rate (ACC) were 83.65%, 0.05% and 99.93%, respectively. The correlation analysis shows our segmented lung tumor volumes has strong correlation ( average 0.985) with the ground truth 1 and ground truth 2 labeled by a clinical expert.

Building rooftop classification using random forests for large-scale PV deployment

NASA Astrophysics Data System (ADS)

Assouline, Dan; Mohajeri, Nahid; Scartezzini, Jean-Louis

2017-10-01

Large scale solar Photovoltaic (PV) deployment on existing building rooftops has proven to be one of the most efficient and viable sources of renewable energy in urban areas. As it usually requires a potential analysis over the area of interest, a crucial step is to estimate the geometric characteristics of the building rooftops. In this paper, we introduce a multi-layer machine learning methodology to classify 6 roof types, 9 aspect (azimuth) classes and 5 slope (tilt) classes for all building rooftops in Switzerland, using GIS processing. We train Random Forests (RF), an ensemble learning algorithm, to build the classifiers. We use (2 × 2) [m2 ] LiDAR data (considering buildings and vegetation) to extract several rooftop features, and a generalised footprint polygon data to localize buildings. The roof classifier is trained and tested with 1252 labeled roofs from three different urban areas, namely Baden, Luzern, and Winterthur. The results for roof type classification show an average accuracy of 67%. The aspect and slope classifiers are trained and tested with 11449 labeled roofs in the Zurich periphery area. The results for aspect and slope classification show different accuracies depending on the classes: while some classes are well identified, other under-represented classes remain challenging to detect.

Automatic Classification of Time-variable X-Ray Sources

NASA Astrophysics Data System (ADS)

Lo, Kitty K.; Farrell, Sean; Murphy, Tara; Gaensler, B. M.

2014-05-01

To maximize the discovery potential of future synoptic surveys, especially in the field of transient science, it will be necessary to use automatic classification to identify some of the astronomical sources. The data mining technique of supervised classification is suitable for this problem. Here, we present a supervised learning method to automatically classify variable X-ray sources in the Second XMM-Newton Serendipitous Source Catalog (2XMMi-DR2). Random Forest is our classifier of choice since it is one of the most accurate learning algorithms available. Our training set consists of 873 variable sources and their features are derived from time series, spectra, and other multi-wavelength contextual information. The 10 fold cross validation accuracy of the training data is ~97% on a 7 class data set. We applied the trained classification model to 411 unknown variable 2XMM sources to produce a probabilistically classified catalog. Using the classification margin and the Random Forest derived outlier measure, we identified 12 anomalous sources, of which 2XMM J180658.7-500250 appears to be the most unusual source in the sample. Its X-ray spectra is suggestive of a ultraluminous X-ray source but its variability makes it highly unusual. Machine-learned classification and anomaly detection will facilitate scientific discoveries in the era of all-sky surveys.

Human tracking in thermal images using adaptive particle filters with online random forest learning

NASA Astrophysics Data System (ADS)

Ko, Byoung Chul; Kwak, Joon-Young; Nam, Jae-Yeal

2013-11-01

This paper presents a fast and robust human tracking method to use in a moving long-wave infrared thermal camera under poor illumination with the existence of shadows and cluttered backgrounds. To improve the human tracking performance while minimizing the computation time, this study proposes an online learning of classifiers based on particle filters and combination of a local intensity distribution (LID) with oriented center-symmetric local binary patterns (OCS-LBP). Specifically, we design a real-time random forest (RF), which is the ensemble of decision trees for confidence estimation, and confidences of the RF are converted into a likelihood function of the target state. First, the target model is selected by the user and particles are sampled. Then, RFs are generated using the positive and negative examples with LID and OCS-LBP features by online learning. The learned RF classifiers are used to detect the most likely target position in the subsequent frame in the next stage. Then, the RFs are learned again by means of fast retraining with the tracked object and background appearance in the new frame. The proposed algorithm is successfully applied to various thermal videos as tests and its tracking performance is better than those of other methods.

Modelling past land use using archaeological and pollen data

NASA Astrophysics Data System (ADS)

Pirzamanbein, Behnaz; Lindström, johan; Poska, Anneli; Gaillard-Lemdahl, Marie-José

2016-04-01

Accurate maps of past land use are necessary for studying the impact of anthropogenic land-cover changes on climate and biodiversity. We develop a Bayesian hierarchical model to reconstruct the land use using Gaussian Markov random fields. The model uses two observations sets: 1) archaeological data, representing human settlements, urbanization and agricultural findings; and 2) pollen-based land estimates of the three land-cover types Coniferous forest, Broadleaved forest and Unforested/Open land. The pollen based estimates are obtained from the REVEALS model, based on pollen counts from lakes and bogs. Our developed model uses the sparse pollen-based estimations to reconstruct the spatial continuous cover of three land cover types. Using the open-land component and the archaeological data, the extent of land-use is reconstructed. The model is applied on three time periods - centred around 1900 CE, 1000 and, 4000 BCE over Sweden for which both pollen-based estimates and archaeological data are available. To estimate the model parameters and land use, a block updated Markov chain Monte Carlo (MCMC) algorithm is applied. Using the MCMC posterior samples uncertainties in land-use predictions are computed. Due to lack of good historic land use data, model results are evaluated by cross-validation. Keywords. Spatial reconstruction, Gaussian Markov random field, Fossil pollen records, Archaeological data, Human land-use, Prediction uncertainty

Automatic estimation of voice onset time for word-initial stops by applying random forest to onset detection.

PubMed

Lin, Chi-Yueh; Wang, Hsiao-Chuan

2011-07-01

The voice onset time (VOT) of a stop consonant is the interval between its burst onset and voicing onset. Among a variety of research topics on VOT, one that has been studied for years is how VOTs are efficiently measured. Manual annotation is a feasible way, but it becomes a time-consuming task when the corpus size is large. This paper proposes an automatic VOT estimation method based on an onset detection algorithm. At first, a forced alignment is applied to identify the locations of stop consonants. Then a random forest based onset detector searches each stop segment for its burst and voicing onsets to estimate a VOT. The proposed onset detection can detect the onsets in an efficient and accurate manner with only a small amount of training data. The evaluation data extracted from the TIMIT corpus were 2344 words with a word-initial stop. The experimental results showed that 83.4% of the estimations deviate less than 10 ms from their manually labeled values, and 96.5% of the estimations deviate by less than 20 ms. Some factors that influence the proposed estimation method, such as place of articulation, voicing of a stop consonant, and quality of succeeding vowel, were also investigated. © 2011 Acoustical Society of America

Evaluating the statistical performance of less applied algorithms in classification of worldview-3 imagery data in an urbanized landscape

NASA Astrophysics Data System (ADS)

Ranaie, Mehrdad; Soffianian, Alireza; Pourmanafi, Saeid; Mirghaffari, Noorollah; Tarkesh, Mostafa

2018-03-01

In recent decade, analyzing the remotely sensed imagery is considered as one of the most common and widely used procedures in the environmental studies. In this case, supervised image classification techniques play a central role. Hence, taking a high resolution Worldview-3 over a mixed urbanized landscape in Iran, three less applied image classification methods including Bagged CART, Stochastic gradient boosting model and Neural network with feature extraction were tested and compared with two prevalent methods: random forest and support vector machine with linear kernel. To do so, each method was run ten time and three validation techniques was used to estimate the accuracy statistics consist of cross validation, independent validation and validation with total of train data. Moreover, using ANOVA and Tukey test, statistical difference significance between the classification methods was significantly surveyed. In general, the results showed that random forest with marginal difference compared to Bagged CART and stochastic gradient boosting model is the best performing method whilst based on independent validation there was no significant difference between the performances of classification methods. It should be finally noted that neural network with feature extraction and linear support vector machine had better processing speed than other.

DHSpred: support-vector-machine-based human DNase I hypersensitive sites prediction using the optimal features selected by random forest.

PubMed

Manavalan, Balachandran; Shin, Tae Hwan; Lee, Gwang

2018-01-05

DNase I hypersensitive sites (DHSs) are genomic regions that provide important information regarding the presence of transcriptional regulatory elements and the state of chromatin. Therefore, identifying DHSs in uncharacterized DNA sequences is crucial for understanding their biological functions and mechanisms. Although many experimental methods have been proposed to identify DHSs, they have proven to be expensive for genome-wide application. Therefore, it is necessary to develop computational methods for DHS prediction. In this study, we proposed a support vector machine (SVM)-based method for predicting DHSs, called DHSpred (DNase I Hypersensitive Site predictor in human DNA sequences), which was trained with 174 optimal features. The optimal combination of features was identified from a large set that included nucleotide composition and di- and trinucleotide physicochemical properties, using a random forest algorithm. DHSpred achieved a Matthews correlation coefficient and accuracy of 0.660 and 0.871, respectively, which were 3% higher than those of control SVM predictors trained with non-optimized features, indicating the efficiency of the feature selection method. Furthermore, the performance of DHSpred was superior to that of state-of-the-art predictors. An online prediction server has been developed to assist the scientific community, and is freely available at: http://www.thegleelab.org/DHSpred.html.

DHSpred: support-vector-machine-based human DNase I hypersensitive sites prediction using the optimal features selected by random forest

PubMed Central

Manavalan, Balachandran; Shin, Tae Hwan; Lee, Gwang

2018-01-01

DNase I hypersensitive sites (DHSs) are genomic regions that provide important information regarding the presence of transcriptional regulatory elements and the state of chromatin. Therefore, identifying DHSs in uncharacterized DNA sequences is crucial for understanding their biological functions and mechanisms. Although many experimental methods have been proposed to identify DHSs, they have proven to be expensive for genome-wide application. Therefore, it is necessary to develop computational methods for DHS prediction. In this study, we proposed a support vector machine (SVM)-based method for predicting DHSs, called DHSpred (DNase I Hypersensitive Site predictor in human DNA sequences), which was trained with 174 optimal features. The optimal combination of features was identified from a large set that included nucleotide composition and di- and trinucleotide physicochemical properties, using a random forest algorithm. DHSpred achieved a Matthews correlation coefficient and accuracy of 0.660 and 0.871, respectively, which were 3% higher than those of control SVM predictors trained with non-optimized features, indicating the efficiency of the feature selection method. Furthermore, the performance of DHSpred was superior to that of state-of-the-art predictors. An online prediction server has been developed to assist the scientific community, and is freely available at: http://www.thegleelab.org/DHSpred.html PMID:29416743

Performance of Activity Classification Algorithms in Free-living Older Adults

PubMed Central

Sasaki, Jeffer Eidi; Hickey, Amanda; Staudenmayer, John; John, Dinesh; Kent, Jane A.; Freedson, Patty S.

2015-01-01

Purpose To compare activity type classification rates of machine learning algorithms trained on laboratory versus free-living accelerometer data in older adults. Methods Thirty-five older adults (21F and 14M ; 70.8 ± 4.9 y) performed selected activities in the laboratory while wearing three ActiGraph GT3X+ activity monitors (dominant hip, wrist, and ankle). Monitors were initialized to collect raw acceleration data at a sampling rate of 80 Hz. Fifteen of the participants also wore the GT3X+ in free-living settings and were directly observed for 2-3 hours. Time- and frequency- domain features from acceleration signals of each monitor were used to train Random Forest (RF) and Support Vector Machine (SVM) models to classify five activity types: sedentary, standing, household, locomotion, and recreational activities. All algorithms were trained on lab data (RFLab and SVMLab) and free-living data (RFFL and SVMFL) using 20 s signal sampling windows. Classification accuracy rates of both types of algorithms were tested on free-living data using a leave-one-out technique. Results Overall classification accuracy rates for the algorithms developed from lab data were between 49% (wrist) to 55% (ankle) for the SVMLab algorithms, and 49% (wrist) to 54% (ankle) for RFLab algorithms. The classification accuracy rates for SVMFL and RFFL algorithms ranged from 58% (wrist) to 69% (ankle) and from 61% (wrist) to 67% (ankle), respectively. Conclusion Our algorithms developed on free-living accelerometer data were more accurate in classifying activity type in free-living older adults than our algorithms developed on laboratory accelerometer data. Future studies should consider using free-living accelerometer data to train machine-learning algorithms in older adults. PMID:26673129

Performance of Activity Classification Algorithms in Free-Living Older Adults.

PubMed

Sasaki, Jeffer Eidi; Hickey, Amanda M; Staudenmayer, John W; John, Dinesh; Kent, Jane A; Freedson, Patty S

2016-05-01

The objective of this study is to compare activity type classification rates of machine learning algorithms trained on laboratory versus free-living accelerometer data in older adults. Thirty-five older adults (21 females and 14 males, 70.8 ± 4.9 yr) performed selected activities in the laboratory while wearing three ActiGraph GT3X+ activity monitors (in the dominant hip, wrist, and ankle; ActiGraph, LLC, Pensacola, FL). Monitors were initialized to collect raw acceleration data at a sampling rate of 80 Hz. Fifteen of the participants also wore GT3X+ in free-living settings and were directly observed for 2-3 h. Time- and frequency-domain features from acceleration signals of each monitor were used to train random forest (RF) and support vector machine (SVM) models to classify five activity types: sedentary, standing, household, locomotion, and recreational activities. All algorithms were trained on laboratory data (RFLab and SVMLab) and free-living data (RFFL and SVMFL) using 20-s signal sampling windows. Classification accuracy rates of both types of algorithms were tested on free-living data using a leave-one-out technique. Overall classification accuracy rates for the algorithms developed from laboratory data were between 49% (wrist) and 55% (ankle) for the SVMLab algorithms and 49% (wrist) to 54% (ankle) for the RFLab algorithms. The classification accuracy rates for SVMFL and RFFL algorithms ranged from 58% (wrist) to 69% (ankle) and from 61% (wrist) to 67% (ankle), respectively. Our algorithms developed on free-living accelerometer data were more accurate in classifying the activity type in free-living older adults than those on our algorithms developed on laboratory accelerometer data. Future studies should consider using free-living accelerometer data to train machine learning algorithms in older adults.

Filling of Cloud-Induced Gaps for Land Use and Land Cover Classifications Around Refugee Camps

NASA Astrophysics Data System (ADS)

Braun, Andreas; Hagensieker, Ron; Hochschild, Volker

2016-08-01

Clouds cover is one of the main constraints in the field of optical remote sensing. Especially the use of multispectral imagery is affected by either fully obscured data or parts of the image which remain unusable. This study compares four algorithms for the filling of cloud induced gaps in classified land cover products based on Markov Random Fields (MRF), Random Forest (RF), Closest Spectral Fit (CSF) operators. They are tested on a classified image of Sentinel-2 where artificial clouds are filled by information derived from a scene of Sentinel-1. The approaches rely on different mathematical principles and therefore produced results varying in both pattern and quality. Overall accuracies for the filled areas range from 57 to 64 %. Best results are achieved by CSF, however some classes (e.g. sands and grassland) remain critical through all approaches.

Analysis on Vertical Scattering Signatures in Forestry with PolInSAR

NASA Astrophysics Data System (ADS)

Guo, Shenglong; Li, Yang; Zhang, Jingjing; Hong, Wen

2014-11-01

We apply accurate topographic phase to the Freeman-Durden decomposition for polarimetric SAR interferometry (PolInSAR) data. The cross correlation matrix obtained from PolInSAR observations can be decomposed into three scattering mechanisms matrices accounting for the odd-bounce, double-bounce and volume scattering. We estimate the phase based on the Random volume over Ground (RVoG) model, and as the initial input parameter of the numerical method which is used to solve the parameters of decomposition. In addition, the modified volume scattering model introduced by Y. Yamaguchi is applied to the PolInSAR target decomposition in forest areas rather than the pure random volume scattering as proposed by Freeman-Durden to make best fit to the actual measured data. This method can accurately retrieve the magnitude associated with each mechanism and their vertical location along the vertical dimension. We test the algorithms with L- and P- band simulated data.

Mapping stand-age distribution of Russian forests from satellite data

NASA Astrophysics Data System (ADS)

Chen, D.; Loboda, T. V.; Hall, A.; Channan, S.; Weber, C. Y.

2013-12-01

Russian boreal forest is a critical component of the global boreal biome as approximately two thirds of the boreal forest is located in Russia. Numerous studies have shown that wildfire and logging have led to extensive modifications of forest cover in the region since 2000. Forest disturbance and subsequent regrowth influences carbon and energy budgets and, in turn, affect climate. Several global and regional satellite-based data products have been developed from coarse (>100m) and moderate (10-100m) resolution imagery to monitor forest cover change over the past decade, record of forest cover change pre-dating year 2000 is very fragmented. Although by using stacks of Landsat images, some information regarding the past disturbances can be obtained, the quantity and locations of such stacks with sufficient number of images are extremely limited, especially in Eastern Siberia. This paper describes a modified method which is built upon previous work to hindcast the disturbance history and map stand-age distribution in the Russian boreal forest. Utilizing data from both Landsat and the Moderate Resolution Imaging Spectroradiometer (MODIS), a wall-to-wall map indicating the estimated age of forest in the Russian boreal forest is created. Our previous work has shown that disturbances can be mapped successfully up to 30 years in the past as the spectral signature of regrowing forests is statistically significantly different from that of mature forests. The presented algorithm ingests 55 multi-temporal stacks of Landsat imagery available over Russian forest before 2001 and processes through a standardized and semi-automated approach to extract training and validation data samples. Landsat data, dating back to 1984, are used to generate maps of forest disturbance using temporal shifts in Disturbance Index through the multi-temporal stack of imagery in selected locations. These maps are then used as reference data to train a decision tree classifier on 50 MODIS-based indices. The resultant map provides an estimate of forest age based on the regrowth curves observed from Landsat imagery. The accuracy of the resultant map is assessed against three datasets: 1) subset of the disturbance maps developed within the algorithm, 2) independent disturbance maps created by the Northern Eurasia Land Dynamics Analysis (NELDA) project, and 3) field-based stand-age distribution from forestry inventory units. The current version of the product presents a considerable improvement on the previous version which used Landsat data samples at a set of randomly selected locations, resulting a strong bias of the training samples towards the Landsat-rich regions (e.g. European Russia) whereas regions such as Siberia were under-sampled. Aiming at improving accuracy, the current method significantly increases the number of training Landsat samples compared to the previous work. Aside from the previously used data, the current method uses all available Landsat data for the under-sampled regions in order to increase the representativeness of the total samples. The finial accuracy assessment is still ongoing, however, the initial results suggested an overall accuracy expressed in Kappa > 0.8. We plan to release both the training data and the final disturbance map of the Russian boreal forest to the public after the validation is completed.

Estimating Forest Aboveground Biomass by Combining Optical and SAR Data: A Case Study in Genhe, Inner Mongolia, China

PubMed Central

Shao, Zhenfeng; Zhang, Linjing

2016-01-01

Estimation of forest aboveground biomass is critical for regional carbon policies and sustainable forest management. Passive optical remote sensing and active microwave remote sensing both play an important role in the monitoring of forest biomass. However, optical spectral reflectance is saturated in relatively dense vegetation areas, and microwave backscattering is significantly influenced by the underlying soil when the vegetation coverage is low. Both of these conditions decrease the estimation accuracy of forest biomass. A new optical and microwave integrated vegetation index (VI) was proposed based on observations from both field experiments and satellite (Landsat 8 Operational Land Imager (OLI) and RADARSAT-2) data. According to the difference in interaction between the multispectral reflectance and microwave backscattering signatures with biomass, the combined VI (COVI) was designed using the weighted optical optimized soil-adjusted vegetation index (OSAVI) and microwave horizontally transmitted and vertically received signal (HV) to overcome the disadvantages of both data types. The performance of the COVI was evaluated by comparison with those of the sole optical data, Synthetic Aperture Radar (SAR) data, and the simple combination of independent optical and SAR variables. The most accurate performance was obtained by the models based on the COVI and optical and microwave optimal variables excluding OSAVI and HV, in combination with a random forest algorithm and the largest number of reference samples. The results also revealed that the predictive accuracy depended highly on the statistical method and the number of sample units. The validation indicated that this integrated method of determining the new VI is a good synergistic way to combine both optical and microwave information for the accurate estimation of forest biomass. PMID:27338378

An integrated method for atherosclerotic carotid plaque segmentation in ultrasound image.

PubMed

Qian, Chunjun; Yang, Xiaoping

2018-01-01

Carotid artery atherosclerosis is an important cause of stroke. Ultrasound imaging has been widely used in the diagnosis of atherosclerosis. Therefore, segmenting atherosclerotic carotid plaque in ultrasound image is an important task. Accurate plaque segmentation is helpful for the measurement of carotid plaque burden. In this paper, we propose and evaluate a novel learning-based integrated framework for plaque segmentation. In our study, four different classification algorithms, along with the auto-context iterative algorithm, were employed to effectively integrate features from ultrasound images and later also the iteratively estimated and refined probability maps together for pixel-wise classification. The four classification algorithms were support vector machine with linear kernel, support vector machine with radial basis function kernel, AdaBoost and random forest. The plaque segmentation was implemented in the generated probability map. The performance of the four different learning-based plaque segmentation methods was tested on 29 B-mode ultrasound images. The evaluation indices for our proposed methods were consisted of sensitivity, specificity, Dice similarity coefficient, overlap index, error of area, absolute error of area, point-to-point distance, and Hausdorff point-to-point distance, along with the area under the ROC curve. The segmentation method integrated the random forest and an auto-context model obtained the best results (sensitivity 80.4 ± 8.4%, specificity 96.5 ± 2.0%, Dice similarity coefficient 81.0 ± 4.1%, overlap index 68.3 ± 5.8%, error of area -1.02 ± 18.3%, absolute error of area 14.7 ± 10.9%, point-to-point distance 0.34 ± 0.10 mm, Hausdorff point-to-point distance 1.75 ± 1.02 mm, and area under the ROC curve 0.897), which were almost the best, compared with that from the existed methods. Our proposed learning-based integrated framework investigated in this study could be useful for atherosclerotic carotid plaque segmentation, which will be helpful for the measurement of carotid plaque burden. Copyright © 2017 Elsevier B.V. All rights reserved.

Forest Roadidentification and Extractionof Through Advanced Log Matching Techniques

NASA Astrophysics Data System (ADS)

Zhang, W.; Hu, B.; Quist, L.

2017-10-01

A novel algorithm for forest road identification and extraction was developed. The algorithm utilized Laplacian of Gaussian (LoG) filter and slope calculation on high resolution multispectral imagery and LiDAR data respectively to extract both primary road and secondary road segments in the forest area. The proposed method used road shape feature to extract the road segments, which have been further processed as objects with orientation preserved. The road network was generated after post processing with tensor voting. The proposed method was tested on Hearst forest, located in central Ontario, Canada. Based on visual examination against manually digitized roads, the majority of roads from the test area have been identified and extracted from the process.

Unbiased split variable selection for random survival forests using maximally selected rank statistics.

PubMed

Wright, Marvin N; Dankowski, Theresa; Ziegler, Andreas

2017-04-15

The most popular approach for analyzing survival data is the Cox regression model. The Cox model may, however, be misspecified, and its proportionality assumption may not always be fulfilled. An alternative approach for survival prediction is random forests for survival outcomes. The standard split criterion for random survival forests is the log-rank test statistic, which favors splitting variables with many possible split points. Conditional inference forests avoid this split variable selection bias. However, linear rank statistics are utilized by default in conditional inference forests to select the optimal splitting variable, which cannot detect non-linear effects in the independent variables. An alternative is to use maximally selected rank statistics for the split point selection. As in conditional inference forests, splitting variables are compared on the p-value scale. However, instead of the conditional Monte-Carlo approach used in conditional inference forests, p-value approximations are employed. We describe several p-value approximations and the implementation of the proposed random forest approach. A simulation study demonstrates that unbiased split variable selection is possible. However, there is a trade-off between unbiased split variable selection and runtime. In benchmark studies of prediction performance on simulated and real datasets, the new method performs better than random survival forests if informative dichotomous variables are combined with uninformative variables with more categories and better than conditional inference forests if non-linear covariate effects are included. In a runtime comparison, the method proves to be computationally faster than both alternatives, if a simple p-value approximation is used. Copyright © 2017 John Wiley & Sons, Ltd. Copyright © 2017 John Wiley & Sons, Ltd.

The influence of conifer forest canopy cover on the accuracy of two individual tree measurement algorithms using lidar data

Treesearch

Michael J. Falkowski; Alistair M.S. Smith; Paul E. Gessler; Andrew T. Hudak; Lee A. Vierling; Jeffrey S. Evans

2008-01-01

Individual tree detection algorithms can provide accurate measurements of individual tree locations, crown diameters (from aerial photography and light detection and ranging (lidar) data), and tree heights (from lidar data). However, to be useful for forest management goals relating to timber harvest, carbon accounting, and ecological processes, there is a need to...

Applying an efficient K-nearest neighbor search to forest attribute imputation

Treesearch

Andrew O. Finley; Ronald E. McRoberts; Alan R. Ek

2006-01-01

This paper explores the utility of an efficient nearest neighbor (NN) search algorithm for applications in multi-source kNN forest attribute imputation. The search algorithm reduces the number of distance calculations between a given target vector and each reference vector, thereby, decreasing the time needed to discover the NN subset. Results of five trials show gains...

Estimating the chance of success in IVF treatment using a ranking algorithm.

PubMed

Güvenir, H Altay; Misirli, Gizem; Dilbaz, Serdar; Ozdegirmenci, Ozlem; Demir, Berfu; Dilbaz, Berna

2015-09-01

In medicine, estimating the chance of success for treatment is important in deciding whether to begin the treatment or not. This paper focuses on the domain of in vitro fertilization (IVF), where estimating the outcome of a treatment is very crucial in the decision to proceed with treatment for both the clinicians and the infertile couples. IVF treatment is a stressful and costly process. It is very stressful for couples who want to have a baby. If an initial evaluation indicates a low pregnancy rate, decision of the couple may change not to start the IVF treatment. The aim of this study is twofold, firstly, to develop a technique that can be used to estimate the chance of success for a couple who wants to have a baby and secondly, to determine the attributes and their particular values affecting the outcome in IVF treatment. We propose a new technique, called success estimation using a ranking algorithm (SERA), for estimating the success of a treatment using a ranking-based algorithm. The particular ranking algorithm used here is RIMARC. The performance of the new algorithm is compared with two well-known algorithms that assign class probabilities to query instances. The algorithms used in the comparison are Naïve Bayes Classifier and Random Forest. The comparison is done in terms of area under the ROC curve, accuracy and execution time, using tenfold stratified cross-validation. The results indicate that the proposed SERA algorithm has a potential to be used successfully to estimate the probability of success in medical treatment.

Automated attribution of remotely-sensed ecological disturbances using spatial and temporal characteristics of common disturbance classes.

NASA Astrophysics Data System (ADS)

Cooper, L. A.; Ballantyne, A.

2017-12-01

Forest disturbances are critical components of ecosystems. Knowledge of their prevalence and impacts is necessary to accurately describe forest health and ecosystem services through time. While there are currently several methods available to identify and describe forest disturbances, especially those which occur in North America, the process remains inefficient and inaccessible in many parts of the world. Here, we introduce a preliminary approach to streamline and automate both the detection and attribution of forest disturbances. We use a combination of the Breaks for Additive Season and Trend (BFAST) detection algorithm to detect disturbances in combination with supervised and unsupervised classification algorithms to attribute the detections to disturbance classes. Both spatial and temporal disturbance characteristics are derived and utilized for the goal of automating the disturbance attribution process. The resulting preliminary algorithm is applied to up-scaled (100m) Landsat data for several different ecosystems in North America, with varying success. Our results indicate that supervised classification is more reliable than unsupervised classification, but that limited training data are required for a region. Future work will improve the algorithm through refining and validating at sites within North America before applying this approach globally.

Mapping Sub-Saharan African Agriculture in High-Resolution Satellite Imagery with Computer Vision & Machine Learning

NASA Astrophysics Data System (ADS)

Debats, Stephanie Renee

Smallholder farms dominate in many parts of the world, including Sub-Saharan Africa. These systems are characterized by small, heterogeneous, and often indistinct field patterns, requiring a specialized methodology to map agricultural landcover. In this thesis, we developed a benchmark labeled data set of high-resolution satellite imagery of agricultural fields in South Africa. We presented a new approach to mapping agricultural fields, based on efficient extraction of a vast set of simple, highly correlated, and interdependent features, followed by a random forest classifier. The algorithm achieved similar high performance across agricultural types, including spectrally indistinct smallholder fields, and demonstrated the ability to generalize across large geographic areas. In sensitivity analyses, we determined multi-temporal images provided greater performance gains than the addition of multi-spectral bands. We also demonstrated how active learning can be incorporated in the algorithm to create smaller, more efficient training data sets, which reduced computational resources, minimized the need for humans to hand-label data, and boosted performance. We designed a patch-based uncertainty metric to drive the active learning framework, based on the regular grid of a crowdsourcing platform, and demonstrated how subject matter experts can be replaced with fleets of crowdsourcing workers. Our active learning algorithm achieved similar performance as an algorithm trained with randomly selected data, but with 62% less data samples. This thesis furthers the goal of providing accurate agricultural landcover maps, at a scale that is relevant for the dominant smallholder class. Accurate maps are crucial for monitoring and promoting agricultural production. Furthermore, improved agricultural landcover maps will aid a host of other applications, including landcover change assessments, cadastral surveys to strengthen smallholder land rights, and constraints for crop modeling and famine prediction.

A comparison of the conditional inference survival forest model to random survival forests based on a simulation study as well as on two applications with time-to-event data.

PubMed

Nasejje, Justine B; Mwambi, Henry; Dheda, Keertan; Lesosky, Maia

2017-07-28

Random survival forest (RSF) models have been identified as alternative methods to the Cox proportional hazards model in analysing time-to-event data. These methods, however, have been criticised for the bias that results from favouring covariates with many split-points and hence conditional inference forests for time-to-event data have been suggested. Conditional inference forests (CIF) are known to correct the bias in RSF models by separating the procedure for the best covariate to split on from that of the best split point search for the selected covariate. In this study, we compare the random survival forest model to the conditional inference model (CIF) using twenty-two simulated time-to-event datasets. We also analysed two real time-to-event datasets. The first dataset is based on the survival of children under-five years of age in Uganda and it consists of categorical covariates with most of them having more than two levels (many split-points). The second dataset is based on the survival of patients with extremely drug resistant tuberculosis (XDR TB) which consists of mainly categorical covariates with two levels (few split-points). The study findings indicate that the conditional inference forest model is superior to random survival forest models in analysing time-to-event data that consists of covariates with many split-points based on the values of the bootstrap cross-validated estimates for integrated Brier scores. However, conditional inference forests perform comparably similar to random survival forests models in analysing time-to-event data consisting of covariates with fewer split-points. Although survival forests are promising methods in analysing time-to-event data, it is important to identify the best forest model for analysis based on the nature of covariates of the dataset in question.

SNP selection and classification of genome-wide SNP data using stratified sampling random forests.

PubMed

Wu, Qingyao; Ye, Yunming; Liu, Yang; Ng, Michael K

2012-09-01

For high dimensional genome-wide association (GWA) case-control data of complex disease, there are usually a large portion of single-nucleotide polymorphisms (SNPs) that are irrelevant with the disease. A simple random sampling method in random forest using default mtry parameter to choose feature subspace, will select too many subspaces without informative SNPs. Exhaustive searching an optimal mtry is often required in order to include useful and relevant SNPs and get rid of vast of non-informative SNPs. However, it is too time-consuming and not favorable in GWA for high-dimensional data. The main aim of this paper is to propose a stratified sampling method for feature subspace selection to generate decision trees in a random forest for GWA high-dimensional data. Our idea is to design an equal-width discretization scheme for informativeness to divide SNPs into multiple groups. In feature subspace selection, we randomly select the same number of SNPs from each group and combine them to form a subspace to generate a decision tree. The advantage of this stratified sampling procedure can make sure each subspace contains enough useful SNPs, but can avoid a very high computational cost of exhaustive search of an optimal mtry, and maintain the randomness of a random forest. We employ two genome-wide SNP data sets (Parkinson case-control data comprised of 408 803 SNPs and Alzheimer case-control data comprised of 380 157 SNPs) to demonstrate that the proposed stratified sampling method is effective, and it can generate better random forest with higher accuracy and lower error bound than those by Breiman's random forest generation method. For Parkinson data, we also show some interesting genes identified by the method, which may be associated with neurological disorders for further biological investigations.

Regional Distribution of Forest Height and Biomass from Multisensor Data Fusion

NASA Technical Reports Server (NTRS)

Yu, Yifan; Saatchi, Sassan; Heath, Linda S.; LaPoint, Elizabeth; Myneni, Ranga; Knyazikhin, Yuri

2010-01-01

Elevation data acquired from radar interferometry at C-band from SRTM are used in data fusion techniques to estimate regional scale forest height and aboveground live biomass (AGLB) over the state of Maine. Two fusion techniques have been developed to perform post-processing and parameter estimations from four data sets: 1 arc sec National Elevation Data (NED), SRTM derived elevation (30 m), Landsat Enhanced Thematic Mapper (ETM) bands (30 m), derived vegetation index (VI) and NLCD2001 land cover map. The first fusion algorithm corrects for missing or erroneous NED data using an iterative interpolation approach and produces distribution of scattering phase centers from SRTM-NED in three dominant forest types of evergreen conifers, deciduous, and mixed stands. The second fusion technique integrates the USDA Forest Service, Forest Inventory and Analysis (FIA) ground-based plot data to develop an algorithm to transform the scattering phase centers into mean forest height and aboveground biomass. Height estimates over evergreen (R2 = 0.86, P < 0.001; RMSE = 1.1 m) and mixed forests (R2 = 0.93, P < 0.001, RMSE = 0.8 m) produced the best results. Estimates over deciduous forests were less accurate because of the winter acquisition of SRTM data and loss of scattering phase center from tree ]surface interaction. We used two methods to estimate AGLB; algorithms based on direct estimation from the scattering phase center produced higher precision (R2 = 0.79, RMSE = 25 Mg/ha) than those estimated from forest height (R2 = 0.25, RMSE = 66 Mg/ha). We discuss sources of uncertainty and implications of the results in the context of mapping regional and continental scale forest biomass distribution.

Next-generation forest change mapping across the United States: the landscape change monitoring system (LCMS)

Treesearch

Sean P. Healey; Warren B. Cohen; Yang Zhiqiang; Ken Brewer; Evan Brooks; Noel Gorelick; Mathew Gregory; Alexander Hernandez; Chengquan Huang; Joseph Hughes; Robert Kennedy; Thomas Loveland; Kevin Megown; Gretchen Moisen; Todd Schroeder; Brian Schwind; Stephen Stehman; Daniel Steinwand; James Vogelmann; Curtis Woodcock; Limin Yang; Zhe Zhu

2015-01-01

Forest change information is critical in forest planning, ecosystem modeling, and in updating forest condition maps. The Landsat satellite platform has provided consistent observations of the world’s ecosystems since 1972. A number of innovative change detection algorithms have been developed to use the Landsat archive to identify and characterize forest change. The...

Forest height estimation from mountain forest areas using general model-based decomposition for polarimetric interferometric synthetic aperture radar images

NASA Astrophysics Data System (ADS)

Minh, Nghia Pham; Zou, Bin; Cai, Hongjun; Wang, Chengyi

2014-01-01

The estimation of forest parameters over mountain forest areas using polarimetric interferometric synthetic aperture radar (PolInSAR) images is one of the greatest interests in remote sensing applications. For mountain forest areas, scattering mechanisms are strongly affected by the ground topography variations. Most of the previous studies in modeling microwave backscattering signatures of forest area have been carried out over relatively flat areas. Therefore, a new algorithm for the forest height estimation from mountain forest areas using the general model-based decomposition (GMBD) for PolInSAR image is proposed. This algorithm enables the retrieval of not only the forest parameters, but also the magnitude associated with each mechanism. In addition, general double- and single-bounce scattering models are proposed to fit for the cross-polarization and off-diagonal term by separating their independent orientation angle, which remains unachieved in the previous model-based decompositions. The efficiency of the proposed approach is demonstrated with simulated data from PolSARProSim software and ALOS-PALSAR spaceborne PolInSAR datasets over the Kalimantan areas, Indonesia. Experimental results indicate that forest height could be effectively estimated by GMBD.

Improved Passive Microwave Algorithms for North America and Eurasia

NASA Technical Reports Server (NTRS)

Foster, James; Chang, Alfred; Hall, Dorothy

1997-01-01

Microwave algorithms simplify complex physical processes in order to estimate geophysical parameters such as snow cover and snow depth. The microwave radiances received at the satellite sensor and expressed as brightness temperatures are a composite of contributions from the Earth's surface, the Earth's atmosphere and from space. Owing to the coarse resolution inherent to passive microwave sensors, each pixel value represents a mixture of contributions from different surface types including deep snow, shallow snow, forests and open areas. Algorithms are generated in order to resolve these mixtures. The accuracy of the retrieved information is affected by uncertainties in the assumptions used in the radiative transfer equation (Steffen et al., 1992). One such uncertainty in the Chang et al., (1987) snow algorithm is that the snow grain radius is 0.3 mm for all layers of the snowpack and for all physiographic regions. However, this is not usually the case. The influence of larger grain sizes appears to be of more importance for deeper snowpacks in the interior of Eurasia. Based on this consideration and the effects of forests, a revised SMMR snow algorithm produces more realistic snow mass values. The purpose of this study is to present results of the revised algorithm (referred to for the remainder of this paper as the GSFC 94 snow algorithm) which incorporates differences in both fractional forest cover and snow grain size. Results from the GSFC 94 algorithm will be compared to the original Chang et al. (1987) algorithm and to climatological snow depth data as well.

Tear fluid proteomics multimarkers for diabetic retinopathy screening

PubMed Central

2013-01-01

Background The aim of the project was to develop a novel method for diabetic retinopathy screening based on the examination of tear fluid biomarker changes. In order to evaluate the usability of protein biomarkers for pre-screening purposes several different approaches were used, including machine learning algorithms. Methods All persons involved in the study had diabetes. Diabetic retinopathy (DR) was diagnosed by capturing 7-field fundus images, evaluated by two independent ophthalmologists. 165 eyes were examined (from 119 patients), 55 were diagnosed healthy and 110 images showed signs of DR. Tear samples were taken from all eyes and state-of-the-art nano-HPLC coupled ESI-MS/MS mass spectrometry protein identification was performed on all samples. Applicability of protein biomarkers was evaluated by six different optimally parameterized machine learning algorithms: Support Vector Machine, Recursive Partitioning, Random Forest, Naive Bayes, Logistic Regression, K-Nearest Neighbor. Results Out of the six investigated machine learning algorithms the result of Recursive Partitioning proved to be the most accurate. The performance of the system realizing the above algorithm reached 74% sensitivity and 48% specificity. Conclusions Protein biomarkers selected and classified with machine learning algorithms alone are at present not recommended for screening purposes because of low specificity and sensitivity values. This tool can be potentially used to improve the results of image processing methods as a complementary tool in automatic or semiautomatic systems. PMID:23919537

VT0005 In Action: National Forest Biomass Inventory Using Airborne Lidar Sampling

NASA Astrophysics Data System (ADS)

Saatchi, S. S.; Xu, L.; Meyer, V.; Ferraz, A.; Yang, Y.; Shapiro, A.; Bastin, J. F.

2016-12-01

Tropical countries are required to produce robust and verifiable estimates of forest carbon stocks for successful implementation of climate change mitigation. Lack of systematic national inventory data due to access, cost, and infrastructure, has impacted the capacity of most tropical countries to accurately report the GHG emissions to the international community. Here, we report on the development of the aboveground forest carbon (AGC) map of Democratic Republic of Congo (DRC) by using the VCS (Verified Carbon Standard) methodology developed by Sassan Saatchi (VT0005) using high-resolution airborne LiDAR samples. The methodology provides the distribution of the carbon stocks in aboveground live trees of more than 150 million ha of forests at 1-ha spatial resolution in DRC using more than 430, 000 ha of systematic random airborne Lidar inventory samples of forest structure. We developed a LIDAR aboveground biomass allometry using more than 100 1-ha plots across forest types and power-law model with LIDAR height metrics and average landscape scale wood density. The methodology provided estimates of forest biomass over the entire country using two approaches: 1) mean, variance, and total carbon estimates for each forest type present in DRC using inventory statistical techniques, and 2) a wall-to-wall map of the forest biomass extrapolated using satellite radar (ALOS PALSAR), surface topography from SRTM, and spectral information from Landsat (TM) and machine learning algorithms. We present the methodology, the estimates of carbon stocks and the spatial uncertainty over the entire country. AcknowledgementsThe theoretical research was carried out partially at the Jet Propulsion Laboratory, California Institute of Technology, under a contract with the National Aeronautics and Space Administration, and the design and implementation in the Democratic Republic of Congo was carried out at the Institute of Environment and Sustainability at University of California Los Angeles through the support of the International Climate Initiative of the German Ministry of Environment, Conservation and Nuclear Security, and the KFW Development Bank.

Quantification of the heterogeneity of prognostic cellular biomarkers in ewing sarcoma using automated image and random survival forest analysis.

PubMed

Bühnemann, Claudia; Li, Simon; Yu, Haiyue; Branford White, Harriet; Schäfer, Karl L; Llombart-Bosch, Antonio; Machado, Isidro; Picci, Piero; Hogendoorn, Pancras C W; Athanasou, Nicholas A; Noble, J Alison; Hassan, A Bassim

2014-01-01

Driven by genomic somatic variation, tumour tissues are typically heterogeneous, yet unbiased quantitative methods are rarely used to analyse heterogeneity at the protein level. Motivated by this problem, we developed automated image segmentation of images of multiple biomarkers in Ewing sarcoma to generate distributions of biomarkers between and within tumour cells. We further integrate high dimensional data with patient clinical outcomes utilising random survival forest (RSF) machine learning. Using material from cohorts of genetically diagnosed Ewing sarcoma with EWSR1 chromosomal translocations, confocal images of tissue microarrays were segmented with level sets and watershed algorithms. Each cell nucleus and cytoplasm were identified in relation to DAPI and CD99, respectively, and protein biomarkers (e.g. Ki67, pS6, Foxo3a, EGR1, MAPK) localised relative to nuclear and cytoplasmic regions of each cell in order to generate image feature distributions. The image distribution features were analysed with RSF in relation to known overall patient survival from three separate cohorts (185 informative cases). Variation in pre-analytical processing resulted in elimination of a high number of non-informative images that had poor DAPI localisation or biomarker preservation (67 cases, 36%). The distribution of image features for biomarkers in the remaining high quality material (118 cases, 104 features per case) were analysed by RSF with feature selection, and performance assessed using internal cross-validation, rather than a separate validation cohort. A prognostic classifier for Ewing sarcoma with low cross-validation error rates (0.36) was comprised of multiple features, including the Ki67 proliferative marker and a sub-population of cells with low cytoplasmic/nuclear ratio of CD99. Through elimination of bias, the evaluation of high-dimensionality biomarker distribution within cell populations of a tumour using random forest analysis in quality controlled tumour material could be achieved. Such an automated and integrated methodology has potential application in the identification of prognostic classifiers based on tumour cell heterogeneity.

Robust automated classification of first-motion polarities for focal mechanism determination with machine learning

NASA Astrophysics Data System (ADS)

Ross, Z. E.; Meier, M. A.; Hauksson, E.

2017-12-01

Accurate first-motion polarities are essential for determining earthquake focal mechanisms, but are difficult to measure automatically because of picking errors and signal to noise issues. Here we develop an algorithm for reliable automated classification of first-motion polarities using machine learning algorithms. A classifier is designed to identify whether the first-motion polarity is up, down, or undefined by examining the waveform data directly. We first improve the accuracy of automatic P-wave onset picks by maximizing a weighted signal/noise ratio for a suite of candidate picks around the automatic pick. We then use the waveform amplitudes before and after the optimized pick as features for the classification. We demonstrate the method's potential by training and testing the classifier on tens of thousands of hand-made first-motion picks by the Southern California Seismic Network. The classifier assigned the same polarity as chosen by an analyst in more than 94% of the records. We show that the method is generalizable to a variety of learning algorithms, including neural networks and random forest classifiers. The method is suitable for automated processing of large seismic waveform datasets, and can potentially be used in real-time applications, e.g. for improving the source characterizations of earthquake early warning algorithms.

Multi-Temporal Classification and Change Detection Using Uav Images

NASA Astrophysics Data System (ADS)

Makuti, S.; Nex, F.; Yang, M. Y.

2018-05-01

In this paper different methodologies for the classification and change detection of UAV image blocks are explored. UAV is not only the cheapest platform for image acquisition but it is also the easiest platform to operate in repeated data collections over a changing area like a building construction site. Two change detection techniques have been evaluated in this study: the pre-classification and the post-classification algorithms. These methods are based on three main steps: feature extraction, classification and change detection. A set of state of the art features have been used in the tests: colour features (HSV), textural features (GLCM) and 3D geometric features. For classification purposes Conditional Random Field (CRF) has been used: the unary potential was determined using the Random Forest algorithm while the pairwise potential was defined by the fully connected CRF. In the performed tests, different feature configurations and settings have been considered to assess the performance of these methods in such challenging task. Experimental results showed that the post-classification approach outperforms the pre-classification change detection method. This was analysed using the overall accuracy, where by post classification have an accuracy of up to 62.6 % and the pre classification change detection have an accuracy of 46.5 %. These results represent a first useful indication for future works and developments.

Local-search based prediction of medical image registration error

NASA Astrophysics Data System (ADS)

Saygili, Görkem

2018-03-01

Medical image registration is a crucial task in many different medical imaging applications. Hence, considerable amount of work has been published recently that aim to predict the error in a registration without any human effort. If provided, these error predictions can be used as a feedback to the registration algorithm to further improve its performance. Recent methods generally start with extracting image-based and deformation-based features, then apply feature pooling and finally train a Random Forest (RF) regressor to predict the real registration error. Image-based features can be calculated after applying a single registration but provide limited accuracy whereas deformation-based features such as variation of deformation vector field may require up to 20 registrations which is a considerably high time-consuming task. This paper proposes to use extracted features from a local search algorithm as image-based features to estimate the error of a registration. The proposed method comprises a local search algorithm to find corresponding voxels between registered image pairs and based on the amount of shifts and stereo confidence measures, it predicts the amount of registration error in millimetres densely using a RF regressor. Compared to other algorithms in the literature, the proposed algorithm does not require multiple registrations, can be efficiently implemented on a Graphical Processing Unit (GPU) and can still provide highly accurate error predictions in existence of large registration error. Experimental results with real registrations on a public dataset indicate a substantially high accuracy achieved by using features from the local search algorithm.

Estimation of Boreal Forest Biomass Using Spaceborne SAR Systems

NASA Technical Reports Server (NTRS)

Saatchi, Sassan; Moghaddam, Mahta

1995-01-01

In this paper, we report on the use of a semiempirical algorithm derived from a two layer radar backscatter model for forest canopies. The model stratifies the forest canopy into crown and stem layers, separates the structural and biometric attributes of the canopy. The structural parameters are estimated by training the model with polarimetric SAR (synthetic aperture radar) data acquired over homogeneous stands with known above ground biomass. Given the structural parameters, the semi-empirical algorithm has four remaining parameters, crown biomass, stem biomass, surface soil moisture, and surface rms height that can be estimated by at least four independent SAR measurements. The algorithm has been used to generate biomass maps over the entire images acquired by JPL AIRSAR and SIR-C SAR systems. The semi-empirical algorithms are then modified to be used by single frequency radar systems such as ERS-1, JERS-1, and Radarsat. The accuracy. of biomass estimation from single channel radars is compared with the case when the channels are used together in synergism or in a polarimetric system.

A mangrove forest map of China in 2015: Analysis of time series Landsat 7/8 and Sentinel-1A imagery in Google Earth Engine cloud computing platform

NASA Astrophysics Data System (ADS)

Chen, Bangqian; Xiao, Xiangming; Li, Xiangping; Pan, Lianghao; Doughty, Russell; Ma, Jun; Dong, Jinwei; Qin, Yuanwei; Zhao, Bin; Wu, Zhixiang; Sun, Rui; Lan, Guoyu; Xie, Guishui; Clinton, Nicholas; Giri, Chandra

2017-09-01

Due to rapid losses of mangrove forests caused by anthropogenic disturbances and climate change, accurate and contemporary maps of mangrove forests are needed to understand how mangrove ecosystems are changing and establish plans for sustainable management. In this study, a new classification algorithm was developed using the biophysical characteristics of mangrove forests in China. More specifically, these forests were mapped by identifying: (1) greenness, canopy coverage, and tidal inundation from time series Landsat data, and (2) elevation, slope, and intersection-with-sea criterion. The annual mean Normalized Difference Vegetation Index (NDVI) was found to be a key variable in determining the classification thresholds of greenness, canopy coverage, and tidal inundation of mangrove forests, which are greatly affected by tide dynamics. In addition, the integration of Sentinel-1A VH band and modified Normalized Difference Water Index (mNDWI) shows great potential in identifying yearlong tidal and fresh water bodies, which is related to mangrove forests. This algorithm was developed using 6 typical Regions of Interest (ROIs) as algorithm training and was run on the Google Earth Engine (GEE) cloud computing platform to process 1941 Landsat images (25 Path/Row) and 586 Sentinel-1A images circa 2015. The resultant mangrove forest map of China at 30 m spatial resolution has an overall/users/producer's accuracy greater than 95% when validated with ground reference data. In 2015, China's mangrove forests had a total area of 20,303 ha, about 92% of which was in the Guangxi Zhuang Autonomous Region, Guangdong, and Hainan Provinces. This study has demonstrated the potential of using the GEE platform, time series Landsat and Sentine-1A SAR images to identify and map mangrove forests along the coastal zones. The resultant mangrove forest maps are likely to be useful for the sustainable management and ecological assessments of mangrove forests in China.

Adapting GNU random forest program for Unix and Windows

NASA Astrophysics Data System (ADS)

Jirina, Marcel; Krayem, M. Said; Jirina, Marcel, Jr.

2013-10-01

The Random Forest is a well-known method and also a program for data clustering and classification. Unfortunately, the original Random Forest program is rather difficult to use. Here we describe a new version of this program originally written in Fortran 77. The modified program in Fortran 95 needs to be compiled only once and information for different tasks is passed with help of arguments. The program was tested with 24 data sets from UCI MLR and results are available on the net.

Forest structures retrieval from LiDAR onboard ULA

NASA Astrophysics Data System (ADS)

Shang, Xiaoxia; Chazette, Patrick; Totems, Julien; Marnas, Fabien; Sanak, Joseph

2013-04-01

Following the United Nations Framework Convention on Climate Change, the assessment of forest carbon stock is one of the main elements for a better understanding of the carbon cycle and its evolution following the climate change. The forests sequester 80% of the continental biospheric carbon and this efficiency is a function of the tree species and the tree health. The airborne backscatter LiDAR onboard the ultra light aircraft (ULA) can provide the key information on the forest vertical structures and evolution in the time. The most important structural parameter is the tree top height, which is directly linked to the above-ground biomass using non-linear relationships. In order to test the LiDAR capability for retrieving the tree top height, the LiDAR ULICE (Ultraviolet LIdar for Canopy Experiment) has been used over different forest types, from coniferous (maritime pins) to deciduous (oaks, hornbeams ...) trees. ULICE works at the wavelength of 355 nm with a sampling along the line-of-sight between 15 and 75 cm. According to the LiDAR signal to noise ratio (SNR), two different algorithms have been used in our study. The first algorithm is a threshold method directly based on the comparison between the LiDAR signal and the noise distributions, while the second one used a low pass filter by fitting a Gaussian curve family. In this paper, we will present these two algorithms and their evolution as a function of the SNR. The main error sources will be also discussed and assessed for each algorithm. The results show that these algorithms have great potential for ground-segment of future space borne LiDAR missions dedicated to the forest survey at the global scale. Acknowledgements: the canopy LiDAR system ULICE has been developed by CEA (Commissariat à l'Energie Atomique). It has been deployed with the support of CNES (Centre National d'Etude Spariales) and ANR (Agence Nationale de la Recherche). We acknowledge the ULA pilots Franck Toussaint for logistical help during the ULA campaign.

FORCARB2: An updated version of the U.S. Forest Carbon Budget Model

Treesearch

Linda S. Heath; Michael C. Nichols; James E. Smith; John R. Mills

2010-01-01

FORCARB2, an updated version of the U.S. FORest CARBon Budget Model (FORCARB), produces estimates of carbon stocks and stock changes for forest ecosystems and forest products at 5-year intervals. FORCARB2 includes a new methodology for carbon in harvested wood products, updated initial inventory data, a revised algorithm for dead wood, and now includes public forest...

Species distribution modelling for Rhipicephalus microplus (Acari: Ixodidae) in Benin, West Africa: comparing datasets and modelling algorithms.

PubMed

De Clercq, E M; Leta, S; Estrada-Peña, A; Madder, M; Adehan, S; Vanwambeke, S O

2015-01-01

Rhipicephalus microplus is one of the most widely distributed and economically important ticks, transmitting Babesia bigemina, B. bovis and Anaplasma marginale. It was recently introduced to West Africa on live animals originating from Brazil. Knowing the precise environmental suitability for the tick would allow veterinary health officials to draft vector control strategies for different regions of the country. To test the performance of modelling algorithms and different sets of environmental explanatory variables, species distribution models for this tick species in Benin were developed using generalized linear models, linear discriminant analysis and random forests. The training data for these models were a dataset containing reported absence or presence in 104 farms, randomly selected across Benin. These farms were sampled at the end of the rainy season, which corresponds with an annual peak in tick abundance. Two environmental datasets for the country of Benin were compared: one based on interpolated climate data (WorldClim) and one based on remotely sensed images (MODIS). The pixel size for both environmental datasets was 1 km. Highly suitable areas occurred mainly along the warmer and humid coast extending northwards to central Benin. The northern hot and drier areas were found to be unsuitable. The models developed and tested on data from the entire country were generally found to perform well, having an AUC value greater than 0.92. Although statistically significant, only small differences in accuracy measures were found between the modelling algorithms, or between the environmental datasets. The resulting risk maps differed nonetheless. Models based on interpolated climate suggested gradual variations in habitat suitability, while those based on remotely sensed data indicated a sharper contrast between suitable and unsuitable areas, and a patchy distribution of the suitable areas. Remotely sensed data yielded more spatial detail in the predictions. When computing accuracy measures on a subset of data along the invasion front, the modelling technique Random Forest outperformed the other modelling approaches, and results with MODIS-derived variables were better than those using WorldClim data. The high environmental suitability for R. microplus in the southern half of Benin raises concern at the regional level for animal health, including its potential to substantially alter transmission risk of Babesia bovis. The northern part of Benin appeared overall of low environmental suitability. Continuous surveillance in the transition zone however remains relevant, in relation to important cattle movements in the region, and to the invasive character of R. microplus. Copyright © 2014 The Authors. Published by Elsevier B.V. All rights reserved.

Digital spatial data for predicted nitrate and arsenic concentrations in basin-fill aquifers of the Southwest Principal Aquifers study area

USGS Publications Warehouse

McKinney, Tim S.; Anning, David W.

2012-01-01

This product "Digital spatial data for predicted nitrate and arsenic concentrations in basin-fill aquifers of the Southwest Principal Aquifers study area" is a 1:250,000-scale vector spatial dataset developed as part of a regional Southwest Principal Aquifers (SWPA) study (Anning and others, 2012). The study examined the vulnerability of basin-fill aquifers in the southwestern United States to nitrate contamination and arsenic enrichment. Statistical models were developed by using the random forest classifier algorithm to predict concentrations of nitrate and arsenic across a model grid that represents local- and basin-scale measures of source, aquifer susceptibility, and geochemical conditions.

A Comparative Study with RapidMiner and WEKA Tools over some Classification Techniques for SMS Spam

NASA Astrophysics Data System (ADS)

Foozy, Cik Feresa Mohd; Ahmad, Rabiah; Faizal Abdollah, M. A.; Chai Wen, Chuah

2017-08-01

SMS Spamming is a serious attack that can manipulate the use of the SMS by spreading the advertisement in bulk. By sending the unwanted SMS that contain advertisement can make the users feeling disturb and this against the privacy of the mobile users. To overcome these issues, many studies have proposed to detect SMS Spam by using data mining tools. This paper will do a comparative study using five machine learning techniques such as Naïve Bayes, K-NN (K-Nearest Neighbour Algorithm), Decision Tree, Random Forest and Decision Stumps to observe the accuracy result between RapidMiner and WEKA for dataset SMS Spam UCI Machine Learning repository.

Automated source classification of new transient sources

NASA Astrophysics Data System (ADS)

Oertel, M.; Kreikenbohm, A.; Wilms, J.; DeLuca, A.

2017-10-01

The EXTraS project harvests the hitherto unexplored temporal domain information buried in the serendipitous data collected by the European Photon Imaging Camera (EPIC) onboard the ESA XMM-Newton mission since its launch. This includes a search for fast transients, missed by standard image analysis, and a search and characterization of variability in hundreds of thousands of sources. We present an automated classification scheme for new transient sources in the EXTraS project. The method is as follows: source classification features of a training sample are used to train machine learning algorithms (performed in R; randomForest (Breiman, 2001) in supervised mode) which are then tested on a sample of known source classes and used for classification.

Amazon Rain Forest Classification Using J-ERS-1 SAR Data

NASA Technical Reports Server (NTRS)

Freeman, A.; Kramer, C.; Alves, M.; Chapman, B.

1994-01-01

The Amazon rain forest is a region of the earth that is undergoing rapid change. Man-made disturbance, such as clear cutting for agriculture or mining, is altering the rain forest ecosystem. For many parts of the rain forest, seasonal changes from the wet to the dry season are also significant. Changes in the seasonal cycle of flooding and draining can cause significant alterations in the forest ecosystem.Because much of the Amazon basin is regularly covered by thick clouds, optical and infrared coverage from the LANDSAT and SPOT satellites is sporadic. Imaging radar offers a much better potential for regular monitoring of changes in this region. In particular, the J-ERS-1 satellite carries an L-band HH SAR system, which via an on-board tape recorder, can collect data from almost anywhere on the globe at any time of year.In this paper, we show how J-ERS-1 radar images can be used to accurately classify different forest types (i.e., forest, hill forest, flooded forest), disturbed areas such as clear cuts and urban areas, and river courses in the Amazon basin. J-ERS-1 data has also shown significant differences between the dry and wet season, indicating a strong potential for monitoring seasonal change. The algorithm used to classify J-ERS-1 data is a standard maximum-likelihood classifier, using the radar image local mean and standard deviation of texture as input. Rivers and clear cuts are detected using edge detection and region-growing algorithms. Since this classifier is intended to operate successfully on data taken over the entire Amazon, several options are available to enable the user to modify the algorithm to suit a particular image.

Mapping Deforestation area in North Korea Using Phenology-based Multi-Index and Random Forest

NASA Astrophysics Data System (ADS)

Jin, Y.; Sung, S.; Lee, D. K.; Jeong, S.

2016-12-01

Forest ecosystem provides ecological benefits to both humans and wildlife. Growing global demand for food and fiber is accelerating the pressure on the forest ecosystem in whole world from agriculture and logging. In recently, North Korea lost almost 40 % of its forests to crop fields for food production and cut-down of forest for fuel woods between 1990 and 2015. It led to the increased damage caused by natural disasters and is known to be one of the most forest degraded areas in the world. The characteristic of forest landscape in North Korea is complex and heterogeneous, the major landscape types in the forest are hillside farm, unstocked forest, natural forest and plateau vegetation. Remote sensing can be used for the forest degradation mapping of a dynamic landscape at a broad scale of detail and spatial distribution. Confusion mostly occurred between hillside farmland and unstocked forest, but also between unstocked forest and forest. Most previous forest degradation that used focused on the classification of broad types such as deforests area and sand from the perspective of land cover classification. The objective of this study is using random forest for mapping degraded forest in North Korea by phenological based vegetation index derived from MODIS products, which has various environmental factors such as vegetation, soil and water at a regional scale for improving accuracy. The model created by random forest resulted in an overall accuracy was 91.44%. Class user's accuracy of hillside farmland and unstocked forest were 97.2% and 84%%, which indicate the degraded forest. Unstocked forest had relative low user accuracy due to misclassified hillside farmland and forest samples. Producer's accuracy of hillside farmland and unstocked forest were 85.2% and 93.3%, repectly. In this case hillside farmland had lower produce accuracy mainly due to confusion with field, unstocked forest and forest. Such a classification of degraded forest could supply essential information to decide the priority of forest management and restoration in degraded forest area.

Subpixel urban land cover estimation: comparing cubist, random forests, and support vector regression

Treesearch

Jeffrey T. Walton

2008-01-01

Three machine learning subpixel estimation methods (Cubist, Random Forests, and support vector regression) were applied to estimate urban cover. Urban forest canopy cover and impervious surface cover were estimated from Landsat-7 ETM+ imagery using a higher resolution cover map resampled to 30 m as training and reference data. Three different band combinations (...

Algorithmic decision rules for estimating growth, removals, and mortality within a national-scale forest inventory (USA)

Treesearch

William H. McWilliams; Carol L. Alerich; William A. Bechtold; Mark Hansen; Christopher M. Oswalt; Mike Thompson; Jeff Turner

2012-01-01

The U.S. Department of Agriculture, Forest Service, Forest Inventory and Analysis (FIA) program maintains the National Information Management System (NIMS) that provides the computational framework for the annual forest inventory of the United States. Questions regarding the impact of key elements of programming logic, processing criteria, and estimation procedures...

DOE Office of Scientific and Technical Information (OSTI.GOV)

Díaz, Mario C.; Beroiz, Martín; Peñuela, Tania

We present the results of the optical follow-up conducted by the TOROS collaboration of the first gravitational-wave event GW150914. We conducted unfiltered CCD observations (0.35–1 μ m) with the 1.5 m telescope at Bosque Alegre starting ∼2.5 days after the alarm. Given our limited field of view (∼100 arcmin{sup 2}), we targeted 14 nearby galaxies that were observable from the site and were located within the area of higher localization probability. We analyzed the observations using two independent implementations of difference-imaging algorithms, followed by a Random-Forest-based algorithm to discriminate between real and bogus transients. We did not find any bonamore » fide transient event in the surveyed area down to a 5 σ limiting magnitude of r = 21.7 mag (AB). Our result is consistent with the LIGO detection of a binary black hole merger, for which no electromagnetic counterparts are expected, and with the expected rates of other astrophysical transients.« less

Classification Algorithms for Big Data Analysis, a Map Reduce Approach

NASA Astrophysics Data System (ADS)

Ayma, V. A.; Ferreira, R. S.; Happ, P.; Oliveira, D.; Feitosa, R.; Costa, G.; Plaza, A.; Gamba, P.

2015-03-01

Since many years ago, the scientific community is concerned about how to increase the accuracy of different classification methods, and major achievements have been made so far. Besides this issue, the increasing amount of data that is being generated every day by remote sensors raises more challenges to be overcome. In this work, a tool within the scope of InterIMAGE Cloud Platform (ICP), which is an open-source, distributed framework for automatic image interpretation, is presented. The tool, named ICP: Data Mining Package, is able to perform supervised classification procedures on huge amounts of data, usually referred as big data, on a distributed infrastructure using Hadoop MapReduce. The tool has four classification algorithms implemented, taken from WEKA's machine learning library, namely: Decision Trees, Naïve Bayes, Random Forest and Support Vector Machines (SVM). The results of an experimental analysis using a SVM classifier on data sets of different sizes for different cluster configurations demonstrates the potential of the tool, as well as aspects that affect its performance.

Fast Human Detection for Intelligent Monitoring Using Surveillance Visible Sensors

PubMed Central

Ko, Byoung Chul; Jeong, Mira; Nam, JaeYeal

2014-01-01

Human detection using visible surveillance sensors is an important and challenging work for intruder detection and safety management. The biggest barrier of real-time human detection is the computational time required for dense image scaling and scanning windows extracted from an entire image. This paper proposes fast human detection by selecting optimal levels of image scale using each level's adaptive region-of-interest (ROI). To estimate the image-scaling level, we generate a Hough windows map (HWM) and select a few optimal image scales based on the strength of the HWM and the divide-and-conquer algorithm. Furthermore, adaptive ROIs are arranged per image scale to provide a different search area. We employ a cascade random forests classifier to separate candidate windows into human and nonhuman classes. The proposed algorithm has been successfully applied to real-world surveillance video sequences, and its detection accuracy and computational speed show a better performance than those of other related methods. PMID:25393782

Estimating Unbiased Land Cover Change Areas In The Colombian Amazon Using Landsat Time Series And Statistical Inference Methods

NASA Astrophysics Data System (ADS)

Arevalo, P. A.; Olofsson, P.; Woodcock, C. E.

2017-12-01

Unbiased estimation of the areas of conversion between land categories ("activity data") and their uncertainty is crucial for providing more robust calculations of carbon emissions to the atmosphere, as well as their removals. This is particularly important for the REDD+ mechanism of UNFCCC where an economic compensation is tied to the magnitude and direction of such fluxes. Dense time series of Landsat data and statistical protocols are becoming an integral part of forest monitoring efforts, but there are relatively few studies in the tropics focused on using these methods to advance operational MRV systems (Monitoring, Reporting and Verification). We present the results of a prototype methodology for continuous monitoring and unbiased estimation of activity data that is compliant with the IPCC Approach 3 for representation of land. We used a break detection algorithm (Continuous Change Detection and Classification, CCDC) to fit pixel-level temporal segments to time series of Landsat data in the Colombian Amazon. The segments were classified using a Random Forest classifier to obtain annual maps of land categories between 2001 and 2016. Using these maps, a biannual stratified sampling approach was implemented and unbiased stratified estimators constructed to calculate area estimates with confidence intervals for each of the stable and change classes. Our results provide evidence of a decrease in primary forest as a result of conversion to pastures, as well as increase in secondary forest as pastures are abandoned and the forest allowed to regenerate. Estimating areas of other land transitions proved challenging because of their very small mapped areas compared to stable classes like forest, which corresponds to almost 90% of the study area. Implications on remote sensing data processing, sample allocation and uncertainty reduction are also discussed.

Randomized Dynamic Mode Decomposition

NASA Astrophysics Data System (ADS)

Erichson, N. Benjamin; Brunton, Steven L.; Kutz, J. Nathan

2017-11-01

The dynamic mode decomposition (DMD) is an equation-free, data-driven matrix decomposition that is capable of providing accurate reconstructions of spatio-temporal coherent structures arising in dynamical systems. We present randomized algorithms to compute the near-optimal low-rank dynamic mode decomposition for massive datasets. Randomized algorithms are simple, accurate and able to ease the computational challenges arising with `big data'. Moreover, randomized algorithms are amenable to modern parallel and distributed computing. The idea is to derive a smaller matrix from the high-dimensional input data matrix using randomness as a computational strategy. Then, the dynamic modes and eigenvalues are accurately learned from this smaller representation of the data, whereby the approximation quality can be controlled via oversampling and power iterations. Here, we present randomized DMD algorithms that are categorized by how many passes the algorithm takes through the data. Specifically, the single-pass randomized DMD does not require data to be stored for subsequent passes. Thus, it is possible to approximately decompose massive fluid flows (stored out of core memory, or not stored at all) using single-pass algorithms, which is infeasible with traditional DMD algorithms.

A Practical and Automated Approach to Large Area Forest Disturbance Mapping with Remote Sensing

PubMed Central

Ozdogan, Mutlu

2014-01-01

In this paper, I describe a set of procedures that automate forest disturbance mapping using a pair of Landsat images. The approach is built on the traditional pair-wise change detection method, but is designed to extract training data without user interaction and uses a robust classification algorithm capable of handling incorrectly labeled training data. The steps in this procedure include: i) creating masks for water, non-forested areas, clouds, and cloud shadows; ii) identifying training pixels whose value is above or below a threshold defined by the number of standard deviations from the mean value of the histograms generated from local windows in the short-wave infrared (SWIR) difference image; iii) filtering the original training data through a number of classification algorithms using an n-fold cross validation to eliminate mislabeled training samples; and finally, iv) mapping forest disturbance using a supervised classification algorithm. When applied to 17 Landsat footprints across the U.S. at five-year intervals between 1985 and 2010, the proposed approach produced forest disturbance maps with 80 to 95% overall accuracy, comparable to those obtained from traditional approaches to forest change detection. The primary sources of mis-classification errors included inaccurate identification of forests (errors of commission), issues related to the land/water mask, and clouds and cloud shadows missed during image screening. The approach requires images from the peak growing season, at least for the deciduous forest sites, and cannot readily distinguish forest harvest from natural disturbances or other types of land cover change. The accuracy of detecting forest disturbance diminishes with the number of years between the images that make up the image pair. Nevertheless, the relatively high accuracies, little or no user input needed for processing, speed of map production, and simplicity of the approach make the new method especially practical for forest cover change analysis over very large regions. PMID:24717283

Assimilating leaf area index of three typical types of subtropical forest in China from MODIS time series data based on the integrated ensemble Kalman filter and PROSAIL model

NASA Astrophysics Data System (ADS)

Li, Xuejian; Mao, Fangjie; Du, Huaqiang; Zhou, Guomo; Xu, Xiaojun; Han, Ning; Sun, Shaobo; Gao, Guolong; Chen, Liang

2017-04-01

Subtropical forest ecosystems play essential roles in the global carbon cycle and in carbon sequestration functions, which challenge the traditional understanding of the main functional areas of carbon sequestration in the temperate forests of Europe and America. The leaf area index (LAI) is an important biological parameter in the spatiotemporal simulation of the carbon cycle, and it has considerable significance in carbon cycle research. Dynamic retrieval based on remote sensing data is an important method with which to obtain large-scale high-accuracy assessments of LAI. This study developed an algorithm for assimilating LAI dynamics based on an integrated ensemble Kalman filter using MODIS LAI data, MODIS reflectance data, and canopy reflectance data modeled by PROSAIL, for three typical types of subtropical forest (Moso bamboo forest, Lei bamboo forest, and evergreen and deciduous broadleaf forest) in China during 2014-2015. There were some errors of assimilation in winter, because of the bad data quality of the MODIS product. Overall, the assimilated LAI well matched the observed LAI, with R2 of 0.82, 0.93, and 0.87, RMSE of 0.73, 0.49, and 0.42, and aBIAS of 0.50, 0.23, and 0.03 for Moso bamboo forest, Lei bamboo forest, and evergreen and deciduous broadleaf forest, respectively. The algorithm greatly decreased the uncertainty of the MODIS LAI in the growing season and it improved the accuracy of the MODIS LAI. The advantage of the algorithm is its use of biophysical parameters (e.g., measured LAI) in the LAI assimilation, which makes it possible to assimilate long-term MODIS LAI time series data, and to provide high-accuracy LAI data for the study of carbon cycle characteristics in subtropical forest ecosystems.

A practical and automated approach to large area forest disturbance mapping with remote sensing.

PubMed

Ozdogan, Mutlu

2014-01-01

In this paper, I describe a set of procedures that automate forest disturbance mapping using a pair of Landsat images. The approach is built on the traditional pair-wise change detection method, but is designed to extract training data without user interaction and uses a robust classification algorithm capable of handling incorrectly labeled training data. The steps in this procedure include: i) creating masks for water, non-forested areas, clouds, and cloud shadows; ii) identifying training pixels whose value is above or below a threshold defined by the number of standard deviations from the mean value of the histograms generated from local windows in the short-wave infrared (SWIR) difference image; iii) filtering the original training data through a number of classification algorithms using an n-fold cross validation to eliminate mislabeled training samples; and finally, iv) mapping forest disturbance using a supervised classification algorithm. When applied to 17 Landsat footprints across the U.S. at five-year intervals between 1985 and 2010, the proposed approach produced forest disturbance maps with 80 to 95% overall accuracy, comparable to those obtained from traditional approaches to forest change detection. The primary sources of mis-classification errors included inaccurate identification of forests (errors of commission), issues related to the land/water mask, and clouds and cloud shadows missed during image screening. The approach requires images from the peak growing season, at least for the deciduous forest sites, and cannot readily distinguish forest harvest from natural disturbances or other types of land cover change. The accuracy of detecting forest disturbance diminishes with the number of years between the images that make up the image pair. Nevertheless, the relatively high accuracies, little or no user input needed for processing, speed of map production, and simplicity of the approach make the new method especially practical for forest cover change analysis over very large regions.

Satellite-based estimation of evapotranspiration in typical forests of China

NASA Astrophysics Data System (ADS)

Wang, Y.; Li, R.

2017-12-01

Evapotranspiration (ET) is the key process affecting the interaction between land surface and atmosphere. Satellite remote sensing is the only feasible technique to monitor the terrestrial ET on large scale. Microwave Emissivity Difference Vegetation Index (EDVI) indicates vegetation water content and can be retrieved under both clear and cloudy sky. Based on EDVI, a quantitative algorithm for ET estimation in China was developed. In this study, we improved the EDVI-based ET algorithm by using the datasets from multiple platforms, including Moderate-Resolution Imaging Spectroradiometer (MODIS), Clouds and Earth's Radiation energy system (CERES) and European Centre for Medium-Range Weather Forecasts (ECMWF). As primary inputs of the algorithm, they are all independent from ground-based measurements. The improved algorithm was tested in three ChinaFlux forest sites, Dinghushan(DHS) subtropical evergreen broad-leaved forest site, Qianyanzhou(QYZ) subtropical man-planted forest site and Changbaishan(CBS) temperate deciduous broad-leaved coniferous mixed forest site. Validations against the in-situ measured ETobs from 2003 to 2005 showed that the EDVI-based algorithm has the capability to simulate midday ET within reasonable accuracies. In terms of the magnitude and seasonal cycle, the estimated ETcal are in very good agreement with the ETobs. The correlation coefficients(R) between ETcal and ETobs during midday vary from 0.51 to 0.80 over the study years, with the annual mean bias (relative bias) ranging from -53.02 Wm-2 (-26.46%) to 34.02 Wm-2 (+23.69%). At monthly scale, the R of monthly mean ETcal and ETobs can reach to 0.83, 0.93 and 0.82 at DHS, QYZ and CBS, with bias of +3.0%, -22.3% and -9.7%, respectively. Contamination from precipitation can partly affect the performances of this algorithm. Validation results generally become better after removing those samples in rainy days. The results indicate that this EDVI-based algorithm, driven completely by using satellite and reanalysis datasets, has a great potential for monitoring terrestrial ET in large spatial scale and under both clear and cloudy sky.

Combining semi-automated image analysis techniques with machine learning algorithms to accelerate large-scale genetic studies.

PubMed

Atkinson, Jonathan A; Lobet, Guillaume; Noll, Manuel; Meyer, Patrick E; Griffiths, Marcus; Wells, Darren M

2017-10-01

Genetic analyses of plant root systems require large datasets of extracted architectural traits. To quantify such traits from images of root systems, researchers often have to choose between automated tools (that are prone to error and extract only a limited number of architectural traits) or semi-automated ones (that are highly time consuming). We trained a Random Forest algorithm to infer architectural traits from automatically extracted image descriptors. The training was performed on a subset of the dataset, then applied to its entirety. This strategy allowed us to (i) decrease the image analysis time by 73% and (ii) extract meaningful architectural traits based on image descriptors. We also show that these traits are sufficient to identify the quantitative trait loci that had previously been discovered using a semi-automated method. We have shown that combining semi-automated image analysis with machine learning algorithms has the power to increase the throughput of large-scale root studies. We expect that such an approach will enable the quantification of more complex root systems for genetic studies. We also believe that our approach could be extended to other areas of plant phenotyping. © The Authors 2017. Published by Oxford University Press.

Combining semi-automated image analysis techniques with machine learning algorithms to accelerate large-scale genetic studies

PubMed Central

Atkinson, Jonathan A.; Lobet, Guillaume; Noll, Manuel; Meyer, Patrick E.; Griffiths, Marcus

2017-01-01

Abstract Genetic analyses of plant root systems require large datasets of extracted architectural traits. To quantify such traits from images of root systems, researchers often have to choose between automated tools (that are prone to error and extract only a limited number of architectural traits) or semi-automated ones (that are highly time consuming). We trained a Random Forest algorithm to infer architectural traits from automatically extracted image descriptors. The training was performed on a subset of the dataset, then applied to its entirety. This strategy allowed us to (i) decrease the image analysis time by 73% and (ii) extract meaningful architectural traits based on image descriptors. We also show that these traits are sufficient to identify the quantitative trait loci that had previously been discovered using a semi-automated method. We have shown that combining semi-automated image analysis with machine learning algorithms has the power to increase the throughput of large-scale root studies. We expect that such an approach will enable the quantification of more complex root systems for genetic studies. We also believe that our approach could be extended to other areas of plant phenotyping. PMID:29020748

Estimating Forest Canopy Heights and Aboveground Biomass with Simulated ICESat-2 Data

NASA Astrophysics Data System (ADS)

Malambo, L.; Narine, L.; Popescu, S. C.; Neuenschwander, A. L.; Sheridan, R.

2016-12-01

The Ice, Cloud and Land Elevation Satellite (ICESat) 2 is scheduled for launch in 2017 and one of its overall science objectives will be to measure vegetation heights, which can be used to estimate and monitor aboveground biomass (AGB) over large spatial scales. This study serves to develop a methodology for utilizing vegetation data collected by ICESat-2 that will be on a five-year mission from 2017, for mapping forest canopy heights and estimating aboveground forest biomass (AGB). The specific objectives are to, (1) simulate ICESat-2 photon-counting lidar (PCL) data, (2) utilize simulated PCL data to estimate forest canopy heights and propose a methodology for upscaling PCL height measurements to obtain spatially contiguous coverage and, (3) estimate and map AGB using simulated PCL data. The laser pulse from ICESat-2 will be divided into three pairs of beams spaced approximately 3 km apart, with footprints measuring approximately 14 m in diameter and with 70 cm along-track intervals. Using existing airborne lidar data (ALS) for Sam Houston National Forest (SHNF) and known ICESat-2 beam locations, footprints are generated along beam locations and PCL data are then simulated from discrete return lidar points within each footprint. By applying data processing algorithms, photons are classified into top of canopy points and ground surface elevation points to yield tree canopy height values within each ICESat-2 footprint. AGB is then estimated using simple linear regression that utilizes AGB from a biomass map generated with ALS data for SHNF and simulated PCL height metrics for 100 m segments along ICESat-2 tracks. Two approaches also investigated for upscaling AGB estimates to provide wall-to-wall coverage of AGB are (1) co-kriging and (2) Random Forest. Height and AGB maps, which are the outcomes of this study, will demonstrate how data acquired by ICESat-2 can be used to measure forest parameters and in extension, estimate forest carbon for climate change initiatives.

Random Forest-Based Recognition of Isolated Sign Language Subwords Using Data from Accelerometers and Surface Electromyographic Sensors.

PubMed

Su, Ruiliang; Chen, Xiang; Cao, Shuai; Zhang, Xu

2016-01-14

Sign language recognition (SLR) has been widely used for communication amongst the hearing-impaired and non-verbal community. This paper proposes an accurate and robust SLR framework using an improved decision tree as the base classifier of random forests. This framework was used to recognize Chinese sign language subwords using recordings from a pair of portable devices worn on both arms consisting of accelerometers (ACC) and surface electromyography (sEMG) sensors. The experimental results demonstrated the validity of the proposed random forest-based method for recognition of Chinese sign language (CSL) subwords. With the proposed method, 98.25% average accuracy was obtained for the classification of a list of 121 frequently used CSL subwords. Moreover, the random forests method demonstrated a superior performance in resisting the impact of bad training samples. When the proportion of bad samples in the training set reached 50%, the recognition error rate of the random forest-based method was only 10.67%, while that of a single decision tree adopted in our previous work was almost 27.5%. Our study offers a practical way of realizing a robust and wearable EMG-ACC-based SLR systems.

Pseudo CT estimation from MRI using patch-based random forest

NASA Astrophysics Data System (ADS)

Yang, Xiaofeng; Lei, Yang; Shu, Hui-Kuo; Rossi, Peter; Mao, Hui; Shim, Hyunsuk; Curran, Walter J.; Liu, Tian

2017-02-01

Recently, MR simulators gain popularity because of unnecessary radiation exposure of CT simulators being used in radiation therapy planning. We propose a method for pseudo CT estimation from MR images based on a patch-based random forest. Patient-specific anatomical features are extracted from the aligned training images and adopted as signatures for each voxel. The most robust and informative features are identified using feature selection to train the random forest. The well-trained random forest is used to predict the pseudo CT of a new patient. This prediction technique was tested with human brain images and the prediction accuracy was assessed using the original CT images. Peak signal-to-noise ratio (PSNR) and feature similarity (FSIM) indexes were used to quantify the differences between the pseudo and original CT images. The experimental results showed the proposed method could accurately generate pseudo CT images from MR images. In summary, we have developed a new pseudo CT prediction method based on patch-based random forest, demonstrated its clinical feasibility, and validated its prediction accuracy. This pseudo CT prediction technique could be a useful tool for MRI-based radiation treatment planning and attenuation correction in a PET/MRI scanner.

Post-hurricane forest damage assessment using satellite remote sensing

Treesearch

W. Wang; J.J. Qu; X. Hao; Y. Liu; J.A. Stanturf

2010-01-01

This study developed a rapid assessment algorithm for post-hurricane forest damage estimation using moderate resolution imaging spectroradiometer (MODIS) measurements. The performance of five commonly used vegetation indices as post-hurricane forest damage indicators was investigated through statistical analysis. The Normalized Difference Infrared Index (NDII) was...

Machine-Learning Algorithms to Code Public Health Spending Accounts

PubMed Central

Leider, Jonathon P.; Resnick, Beth A.; Alfonso, Y. Natalia; Bishai, David

2017-01-01

Objectives: Government public health expenditure data sets require time- and labor-intensive manipulation to summarize results that public health policy makers can use. Our objective was to compare the performances of machine-learning algorithms with manual classification of public health expenditures to determine if machines could provide a faster, cheaper alternative to manual classification. Methods: We used machine-learning algorithms to replicate the process of manually classifying state public health expenditures, using the standardized public health spending categories from the Foundational Public Health Services model and a large data set from the US Census Bureau. We obtained a data set of 1.9 million individual expenditure items from 2000 to 2013. We collapsed these data into 147 280 summary expenditure records, and we followed a standardized method of manually classifying each expenditure record as public health, maybe public health, or not public health. We then trained 9 machine-learning algorithms to replicate the manual process. We calculated recall, precision, and coverage rates to measure the performance of individual and ensembled algorithms. Results: Compared with manual classification, the machine-learning random forests algorithm produced 84% recall and 91% precision. With algorithm ensembling, we achieved our target criterion of 90% recall by using a consensus ensemble of ≥6 algorithms while still retaining 93% coverage, leaving only 7% of the summary expenditure records unclassified. Conclusions: Machine learning can be a time- and cost-saving tool for estimating public health spending in the United States. It can be used with standardized public health spending categories based on the Foundational Public Health Services model to help parse public health expenditure information from other types of health-related spending, provide data that are more comparable across public health organizations, and evaluate the impact of evidence-based public health resource allocation. PMID:28363034

Machine-Learning Algorithms to Code Public Health Spending Accounts.

PubMed

Brady, Eoghan S; Leider, Jonathon P; Resnick, Beth A; Alfonso, Y Natalia; Bishai, David

Government public health expenditure data sets require time- and labor-intensive manipulation to summarize results that public health policy makers can use. Our objective was to compare the performances of machine-learning algorithms with manual classification of public health expenditures to determine if machines could provide a faster, cheaper alternative to manual classification. We used machine-learning algorithms to replicate the process of manually classifying state public health expenditures, using the standardized public health spending categories from the Foundational Public Health Services model and a large data set from the US Census Bureau. We obtained a data set of 1.9 million individual expenditure items from 2000 to 2013. We collapsed these data into 147 280 summary expenditure records, and we followed a standardized method of manually classifying each expenditure record as public health, maybe public health, or not public health. We then trained 9 machine-learning algorithms to replicate the manual process. We calculated recall, precision, and coverage rates to measure the performance of individual and ensembled algorithms. Compared with manual classification, the machine-learning random forests algorithm produced 84% recall and 91% precision. With algorithm ensembling, we achieved our target criterion of 90% recall by using a consensus ensemble of ≥6 algorithms while still retaining 93% coverage, leaving only 7% of the summary expenditure records unclassified. Machine learning can be a time- and cost-saving tool for estimating public health spending in the United States. It can be used with standardized public health spending categories based on the Foundational Public Health Services model to help parse public health expenditure information from other types of health-related spending, provide data that are more comparable across public health organizations, and evaluate the impact of evidence-based public health resource allocation.

Identification of compound-protein interactions through the analysis of gene ontology, KEGG enrichment for proteins and molecular fragments of compounds.

PubMed

Chen, Lei; Zhang, Yu-Hang; Zheng, Mingyue; Huang, Tao; Cai, Yu-Dong

2016-12-01

Compound-protein interactions play important roles in every cell via the recognition and regulation of specific functional proteins. The correct identification of compound-protein interactions can lead to a good comprehension of this complicated system and provide useful input for the investigation of various attributes of compounds and proteins. In this study, we attempted to understand this system by extracting properties from both proteins and compounds, in which proteins were represented by gene ontology and KEGG pathway enrichment scores and compounds were represented by molecular fragments. Advanced feature selection methods, including minimum redundancy maximum relevance, incremental feature selection, and the basic machine learning algorithm random forest, were used to analyze these properties and extract core factors for the determination of actual compound-protein interactions. Compound-protein interactions reported in The Binding Databases were used as positive samples. To improve the reliability of the results, the analytic procedure was executed five times using different negative samples. Simultaneously, five optimal prediction methods based on a random forest and yielding maximum MCCs of approximately 77.55 % were constructed and may be useful tools for the prediction of compound-protein interactions. This work provides new clues to understanding the system of compound-protein interactions by analyzing extracted core features. Our results indicate that compound-protein interactions are related to biological processes involving immune, developmental and hormone-associated pathways.

Using random forest for the risk assessment of coal-floor water inrush in Panjiayao Coal Mine, northern China

NASA Astrophysics Data System (ADS)

Zhao, Dekang; Wu, Qiang; Cui, Fangpeng; Xu, Hua; Zeng, Yifan; Cao, Yufei; Du, Yuanze

2018-04-01

Coal-floor water-inrush incidents account for a large proportion of coal mine disasters in northern China, and accurate risk assessment is crucial for safe coal production. A novel and promising assessment model for water inrush is proposed based on random forest (RF), which is a powerful intelligent machine-learning algorithm. RF has considerable advantages, including high classification accuracy and the capability to evaluate the importance of variables; in particularly, it is robust in dealing with the complicated and non-linear problems inherent in risk assessment. In this study, the proposed model is applied to Panjiayao Coal Mine, northern China. Eight factors were selected as evaluation indices according to systematic analysis of the geological conditions and a field survey of the study area. Risk assessment maps were generated based on RF, and the probabilistic neural network (PNN) model was also used for risk assessment as a comparison. The results demonstrate that the two methods are consistent in the risk assessment of water inrush at the mine, and RF shows a better performance compared to PNN with an overall accuracy higher by 6.67%. It is concluded that RF is more practicable to assess the water-inrush risk than PNN. The presented method will be helpful in avoiding water inrush and also can be extended to various engineering applications.

Automatic classification of time-variable X-ray sources

DOE Office of Scientific and Technical Information (OSTI.GOV)

Lo, Kitty K.; Farrell, Sean; Murphy, Tara

2014-05-01

To maximize the discovery potential of future synoptic surveys, especially in the field of transient science, it will be necessary to use automatic classification to identify some of the astronomical sources. The data mining technique of supervised classification is suitable for this problem. Here, we present a supervised learning method to automatically classify variable X-ray sources in the Second XMM-Newton Serendipitous Source Catalog (2XMMi-DR2). Random Forest is our classifier of choice since it is one of the most accurate learning algorithms available. Our training set consists of 873 variable sources and their features are derived from time series, spectra, andmore » other multi-wavelength contextual information. The 10 fold cross validation accuracy of the training data is ∼97% on a 7 class data set. We applied the trained classification model to 411 unknown variable 2XMM sources to produce a probabilistically classified catalog. Using the classification margin and the Random Forest derived outlier measure, we identified 12 anomalous sources, of which 2XMM J180658.7–500250 appears to be the most unusual source in the sample. Its X-ray spectra is suggestive of a ultraluminous X-ray source but its variability makes it highly unusual. Machine-learned classification and anomaly detection will facilitate scientific discoveries in the era of all-sky surveys.« less

Global patterns and predictions of seafloor biomass using random forests.

PubMed

Wei, Chih-Lin; Rowe, Gilbert T; Escobar-Briones, Elva; Boetius, Antje; Soltwedel, Thomas; Caley, M Julian; Soliman, Yousria; Huettmann, Falk; Qu, Fangyuan; Yu, Zishan; Pitcher, C Roland; Haedrich, Richard L; Wicksten, Mary K; Rex, Michael A; Baguley, Jeffrey G; Sharma, Jyotsna; Danovaro, Roberto; MacDonald, Ian R; Nunnally, Clifton C; Deming, Jody W; Montagna, Paul; Lévesque, Mélanie; Weslawski, Jan Marcin; Wlodarska-Kowalczuk, Maria; Ingole, Baban S; Bett, Brian J; Billett, David S M; Yool, Andrew; Bluhm, Bodil A; Iken, Katrin; Narayanaswamy, Bhavani E

2010-12-30

A comprehensive seafloor biomass and abundance database has been constructed from 24 oceanographic institutions worldwide within the Census of Marine Life (CoML) field projects. The machine-learning algorithm, Random Forests, was employed to model and predict seafloor standing stocks from surface primary production, water-column integrated and export particulate organic matter (POM), seafloor relief, and bottom water properties. The predictive models explain 63% to 88% of stock variance among the major size groups. Individual and composite maps of predicted global seafloor biomass and abundance are generated for bacteria, meiofauna, macrofauna, and megafauna (invertebrates and fishes). Patterns of benthic standing stocks were positive functions of surface primary production and delivery of the particulate organic carbon (POC) flux to the seafloor. At a regional scale, the census maps illustrate that integrated biomass is highest at the poles, on continental margins associated with coastal upwelling and with broad zones associated with equatorial divergence. Lowest values are consistently encountered on the central abyssal plains of major ocean basins The shift of biomass dominance groups with depth is shown to be affected by the decrease in average body size rather than abundance, presumably due to decrease in quantity and quality of food supply. This biomass census and associated maps are vital components of mechanistic deep-sea food web models and global carbon cycling, and as such provide fundamental information that can be incorporated into evidence-based management.

Global Patterns and Predictions of Seafloor Biomass Using Random Forests

PubMed Central

Wei, Chih-Lin; Rowe, Gilbert T.; Escobar-Briones, Elva; Boetius, Antje; Soltwedel, Thomas; Caley, M. Julian; Soliman, Yousria; Huettmann, Falk; Qu, Fangyuan; Yu, Zishan; Pitcher, C. Roland; Haedrich, Richard L.; Wicksten, Mary K.; Rex, Michael A.; Baguley, Jeffrey G.; Sharma, Jyotsna; Danovaro, Roberto; MacDonald, Ian R.; Nunnally, Clifton C.; Deming, Jody W.; Montagna, Paul; Lévesque, Mélanie; Weslawski, Jan Marcin; Wlodarska-Kowalczuk, Maria; Ingole, Baban S.; Bett, Brian J.; Billett, David S. M.; Yool, Andrew; Bluhm, Bodil A.; Iken, Katrin; Narayanaswamy, Bhavani E.

2010-01-01

A comprehensive seafloor biomass and abundance database has been constructed from 24 oceanographic institutions worldwide within the Census of Marine Life (CoML) field projects. The machine-learning algorithm, Random Forests, was employed to model and predict seafloor standing stocks from surface primary production, water-column integrated and export particulate organic matter (POM), seafloor relief, and bottom water properties. The predictive models explain 63% to 88% of stock variance among the major size groups. Individual and composite maps of predicted global seafloor biomass and abundance are generated for bacteria, meiofauna, macrofauna, and megafauna (invertebrates and fishes). Patterns of benthic standing stocks were positive functions of surface primary production and delivery of the particulate organic carbon (POC) flux to the seafloor. At a regional scale, the census maps illustrate that integrated biomass is highest at the poles, on continental margins associated with coastal upwelling and with broad zones associated with equatorial divergence. Lowest values are consistently encountered on the central abyssal plains of major ocean basins The shift of biomass dominance groups with depth is shown to be affected by the decrease in average body size rather than abundance, presumably due to decrease in quantity and quality of food supply. This biomass census and associated maps are vital components of mechanistic deep-sea food web models and global carbon cycling, and as such provide fundamental information that can be incorporated into evidence-based management. PMID:21209928

Accurate prediction of personalized olfactory perception from large-scale chemoinformatic features.

PubMed

Li, Hongyang; Panwar, Bharat; Omenn, Gilbert S; Guan, Yuanfang

2018-02-01

The olfactory stimulus-percept problem has been studied for more than a century, yet it is still hard to precisely predict the odor given the large-scale chemoinformatic features of an odorant molecule. A major challenge is that the perceived qualities vary greatly among individuals due to different genetic and cultural backgrounds. Moreover, the combinatorial interactions between multiple odorant receptors and diverse molecules significantly complicate the olfaction prediction. Many attempts have been made to establish structure-odor relationships for intensity and pleasantness, but no models are available to predict the personalized multi-odor attributes of molecules. In this study, we describe our winning algorithm for predicting individual and population perceptual responses to various odorants in the DREAM Olfaction Prediction Challenge. We find that random forest model consisting of multiple decision trees is well suited to this prediction problem, given the large feature spaces and high variability of perceptual ratings among individuals. Integrating both population and individual perceptions into our model effectively reduces the influence of noise and outliers. By analyzing the importance of each chemical feature, we find that a small set of low- and nondegenerative features is sufficient for accurate prediction. Our random forest model successfully predicts personalized odor attributes of structurally diverse molecules. This model together with the top discriminative features has the potential to extend our understanding of olfactory perception mechanisms and provide an alternative for rational odorant design.

Towards automatic patient selection for chemotherapy in colorectal cancer trials

NASA Astrophysics Data System (ADS)

Wright, Alexander; Magee, Derek; Quirke, Philip; Treanor, Darren E.

2014-03-01

A key factor in the prognosis of colorectal cancer, and its response to chemoradiotherapy, is the ratio of cancer cells to surrounding tissue (the so called tumour:stroma ratio). Currently tumour:stroma ratio is calculated manually, by examining H&E stained slides and counting the proportion of area of each. Virtual slides facilitate this analysis by allowing pathologists to annotate areas of tumour on a given digital slide image, and in-house developed stereometry tools mark random, systematic points on the slide, known as spots. These spots are examined and classified by the pathologist. Typical analyses require a pathologist to score at least 300 spots per tumour. This is a time consuming (10- 60 minutes per case) and laborious task for the pathologist and automating this process is highly desirable. Using an existing dataset of expert-classified spots from one colorectal cancer clinical trial, an automated tumour:stroma detection algorithm has been trained and validated. Each spot is extracted as an image patch, and then processed for feature extraction, identifying colour, texture, stain intensity and object characteristics. These features are used as training data for a random forest classification algorithm, and validated against unseen image patches. This process was repeated for multiple patch sizes. Over 82,000 such patches have been used, and results show an accuracy of 79%, depending on image patch size. A second study examining contextual requirements for pathologist scoring was conducted and indicates that further analysis of structures within each image patch is required in order to improve algorithm accuracy.

A radiation and energy budget algorithm for forest canopies

NASA Astrophysics Data System (ADS)

Tunick, A.

2006-01-01

Previously, it was shown that a one-dimensional, physics-based (conservation-law) computer model can provide a useful mathematical representation of the wind flow, temperatures, and turbulence inside and above a uniform forest stand. A key element of this calculation was a radiation and energy budget algorithm (implemented to predict the heat source). However, to keep the earlier publication brief, a full description of the radiation and energy budget algorithm was not given. Hence, this paper presents our equation set for calculating the incoming total radiation at the canopy top as well as the transmission, reflection, absorption, and emission of the solar flux through a forest stand. In addition, example model output is presented from three interesting numerical experiments, which were conducted to simulate the canopy microclimate for a forest stand that borders the Blossom Point Field Test Facility (located near La Plata, Maryland along the Potomac River). It is anticipated that the current numerical study will be useful to researchers and experimental planners who will be collecting acoustic and meteorological data at the Blossom Point Facility in the near future.

Normalized algorithm for mapping and dating forest disturbances and regrowth for the United States

Treesearch

Liming He; Jing M. Chen; Shaoliang Zhang; Gustavo Gomez; Yude Pan; Kevin McCullough; Richard Birdsey; Jeffrey G. Masek

2011-01-01

Forest disturbances such as harvesting, wildfire and insect infestation are critical ecosystem processes affecting the carbon cycle. Because carbon dynamics are related to time since disturbance, forest stand age that can be used as a surrogate for major clear-cut/fire disturbance information has recently been recognized as an important input to forest carbon cycle...

Screening large-scale association study data: exploiting interactions using random forests.

PubMed

Lunetta, Kathryn L; Hayward, L Brooke; Segal, Jonathan; Van Eerdewegh, Paul

2004-12-10

Genome-wide association studies for complex diseases will produce genotypes on hundreds of thousands of single nucleotide polymorphisms (SNPs). A logical first approach to dealing with massive numbers of SNPs is to use some test to screen the SNPs, retaining only those that meet some criterion for further study. For example, SNPs can be ranked by p-value, and those with the lowest p-values retained. When SNPs have large interaction effects but small marginal effects in a population, they are unlikely to be retained when univariate tests are used for screening. However, model-based screens that pre-specify interactions are impractical for data sets with thousands of SNPs. Random forest analysis is an alternative method that produces a single measure of importance for each predictor variable that takes into account interactions among variables without requiring model specification. Interactions increase the importance for the individual interacting variables, making them more likely to be given high importance relative to other variables. We test the performance of random forests as a screening procedure to identify small numbers of risk-associated SNPs from among large numbers of unassociated SNPs using complex disease models with up to 32 loci, incorporating both genetic heterogeneity and multi-locus interaction. Keeping other factors constant, if risk SNPs interact, the random forest importance measure significantly outperforms the Fisher Exact test as a screening tool. As the number of interacting SNPs increases, the improvement in performance of random forest analysis relative to Fisher Exact test for screening also increases. Random forests perform similarly to the univariate Fisher Exact test as a screening tool when SNPs in the analysis do not interact. In the context of large-scale genetic association studies where unknown interactions exist among true risk-associated SNPs or SNPs and environmental covariates, screening SNPs using random forest analyses can significantly reduce the number of SNPs that need to be retained for further study compared to standard univariate screening methods.

Flood damage estimation of companies: A comparison of Stage-Damage-Functions and Random Forests

NASA Astrophysics Data System (ADS)

Sieg, Tobias; Kreibich, Heidi; Vogel, Kristin; Merz, Bruno

2017-04-01

The development of appropriate flood damage models plays an important role not only for the damage assessment after an event but also to develop adaptation and risk mitigation strategies. So called Stage-Damage-Functions (SDFs) are often applied as a standard approach to estimate flood damage. These functions assign a certain damage to the water depth depending on the use or other characteristics of the exposed objects. Recent studies apply machine learning algorithms like Random Forests (RFs) to model flood damage. These algorithms usually consider more influencing variables and promise to depict a more detailed insight into the damage processes. In addition they provide an inherent validation scheme. Our study focuses on direct, tangible damage of single companies. The objective is to model and validate the flood damage suffered by single companies with SDFs and RFs. The data sets used are taken from two surveys conducted after the floods in the Elbe and Danube catchments in the years 2002 and 2013 in Germany. Damage to buildings (n = 430), equipment (n = 651) as well as goods and stock (n = 530) are taken into account. The model outputs are validated via a comparison with the actual flood damage acquired by the surveys and subsequently compared with each other. This study investigates the gain in model performance with the use of additional data and the advantages and disadvantages of the RFs compared to SDFs. RFs show an increase in model performance with an increasing amount of data records over a comparatively large range, while the model performance of the SDFs is already saturated for a small set of records. In addition, the RFs are able to identify damage influencing variables, which improves the understanding of damage processes. Hence, RFs can slightly improve flood damage predictions and provide additional insight into the underlying mechanisms compared to SDFs.

Recent advances in environmental data mining

NASA Astrophysics Data System (ADS)

Leuenberger, Michael; Kanevski, Mikhail

2016-04-01

Due to the large amount and complexity of data available nowadays in geo- and environmental sciences, we face the need to develop and incorporate more robust and efficient methods for their analysis, modelling and visualization. An important part of these developments deals with an elaboration and application of a contemporary and coherent methodology following the process from data collection to the justification and communication of the results. Recent fundamental progress in machine learning (ML) can considerably contribute to the development of the emerging field - environmental data science. The present research highlights and investigates the different issues that can occur when dealing with environmental data mining using cutting-edge machine learning algorithms. In particular, the main attention is paid to the description of the self-consistent methodology and two efficient algorithms - Random Forest (RF, Breiman, 2001) and Extreme Learning Machines (ELM, Huang et al., 2006), which recently gained a great popularity. Despite the fact that they are based on two different concepts, i.e. decision trees vs artificial neural networks, they both propose promising results for complex, high dimensional and non-linear data modelling. In addition, the study discusses several important issues of data driven modelling, including feature selection and uncertainties. The approach considered is accompanied by simulated and real data case studies from renewable resources assessment and natural hazards tasks. In conclusion, the current challenges and future developments in statistical environmental data learning are discussed. References - Breiman, L., 2001. Random Forests. Machine Learning 45 (1), 5-32. - Huang, G.-B., Zhu, Q.-Y., Siew, C.-K., 2006. Extreme learning machine: theory and applications. Neurocomputing 70 (1-3), 489-501. - Kanevski, M., Pozdnoukhov, A., Timonin, V., 2009. Machine Learning for Spatial Environmental Data. EPFL Press; Lausanne, Switzerland, p.392. - Leuenberger, M., Kanevski, M., 2015. Extreme Learning Machines for spatial environmental data. Computers and Geosciences 85, 64-73.

Application of lifting wavelet and random forest in compound fault diagnosis of gearbox

NASA Astrophysics Data System (ADS)

Chen, Tang; Cui, Yulian; Feng, Fuzhou; Wu, Chunzhi

2018-03-01

Aiming at the weakness of compound fault characteristic signals of a gearbox of an armored vehicle and difficult to identify fault types, a fault diagnosis method based on lifting wavelet and random forest is proposed. First of all, this method uses the lifting wavelet transform to decompose the original vibration signal in multi-layers, reconstructs the multi-layer low-frequency and high-frequency components obtained by the decomposition to get multiple component signals. Then the time-domain feature parameters are obtained for each component signal to form multiple feature vectors, which is input into the random forest pattern recognition classifier to determine the compound fault type. Finally, a variety of compound fault data of the gearbox fault analog test platform are verified, the results show that the recognition accuracy of the fault diagnosis method combined with the lifting wavelet and the random forest is up to 99.99%.

How to estimate the 3D power spectrum of the Lyman-α forest

NASA Astrophysics Data System (ADS)

Font-Ribera, Andreu; McDonald, Patrick; Slosar, Anže

2018-01-01

We derive and numerically implement an algorithm for estimating the 3D power spectrum of the Lyman-α (Lyα) forest flux fluctuations. The algorithm exploits the unique geometry of Lyα forest data to efficiently measure the cross-spectrum between lines of sight as a function of parallel wavenumber, transverse separation and redshift. We start by approximating the global covariance matrix as block-diagonal, where only pixels from the same spectrum are correlated. We then compute the eigenvectors of the derivative of the signal covariance with respect to cross-spectrum parameters, and project the inverse-covariance-weighted spectra onto them. This acts much like a radial Fourier transform over redshift windows. The resulting cross-spectrum inference is then converted into our final product, an approximation of the likelihood for the 3D power spectrum expressed as second order Taylor expansion around a fiducial model. We demonstrate the accuracy and scalability of the algorithm and comment on possible extensions. Our algorithm will allow efficient analysis of the upcoming Dark Energy Spectroscopic Instrument dataset.

How to estimate the 3D power spectrum of the Lyman-α forest

DOE PAGES

Font-Ribera, Andreu; McDonald, Patrick; Slosar, Anže

2018-01-02

Here, we derive and numerically implement an algorithm for estimating the 3D power spectrum of the Lyman-α (Lyα) forest flux fluctuations. The algorithm exploits the unique geometry of Lyα forest data to efficiently measure the cross-spectrum between lines of sight as a function of parallel wavenumber, transverse separation and redshift. We start by approximating the global covariance matrix as block-diagonal, where only pixels from the same spectrum are correlated. We then compute the eigenvectors of the derivative of the signal covariance with respect to cross-spectrum parameters, and project the inverse-covariance-weighted spectra onto them. This acts much like a radial Fouriermore » transform over redshift windows. The resulting cross-spectrum inference is then converted into our final product, an approximation of the likelihood for the 3D power spectrum expressed as second order Taylor expansion around a fiducial model. We demonstrate the accuracy and scalability of the algorithm and comment on possible extensions. Our algorithm will allow efficient analysis of the upcoming Dark Energy Spectroscopic Instrument dataset.« less

How to estimate the 3D power spectrum of the Lyman-α forest

DOE Office of Scientific and Technical Information (OSTI.GOV)

Font-Ribera, Andreu; McDonald, Patrick; Slosar, Anže

Here, we derive and numerically implement an algorithm for estimating the 3D power spectrum of the Lyman-α (Lyα) forest flux fluctuations. The algorithm exploits the unique geometry of Lyα forest data to efficiently measure the cross-spectrum between lines of sight as a function of parallel wavenumber, transverse separation and redshift. We start by approximating the global covariance matrix as block-diagonal, where only pixels from the same spectrum are correlated. We then compute the eigenvectors of the derivative of the signal covariance with respect to cross-spectrum parameters, and project the inverse-covariance-weighted spectra onto them. This acts much like a radial Fouriermore » transform over redshift windows. The resulting cross-spectrum inference is then converted into our final product, an approximation of the likelihood for the 3D power spectrum expressed as second order Taylor expansion around a fiducial model. We demonstrate the accuracy and scalability of the algorithm and comment on possible extensions. Our algorithm will allow efficient analysis of the upcoming Dark Energy Spectroscopic Instrument dataset.« less

Predicting stem total and assortment volumes in an industrial Pinus taeda L. forest plantation using airborne laser scanning data and random forest

Treesearch

Carlos Alberto Silva; Carine Klauberg; Andrew Thomas Hudak; Lee Alexander Vierling; Wan Shafrina Wan Mohd Jaafar; Midhun Mohan; Mariano Garcia; Antonio Ferraz; Adrian Cardil; Sassan Saatchi

2017-01-01

Improvements in the management of pine plantations result in multiple industrial and environmental benefits. Remote sensing techniques can dramatically increase the efficiency of plantation management by reducing or replacing time-consuming field sampling. We tested the utility and accuracy of combining field and airborne lidar data with Random Forest, a supervised...

CNN-BLPred: a Convolutional neural network based predictor for β-Lactamases (BL) and their classes.

PubMed

White, Clarence; Ismail, Hamid D; Saigo, Hiroto; Kc, Dukka B

2017-12-28

The β-Lactamase (BL) enzyme family is an important class of enzymes that plays a key role in bacterial resistance to antibiotics. As the newly identified number of BL enzymes is increasing daily, it is imperative to develop a computational tool to classify the newly identified BL enzymes into one of its classes. There are two types of classification of BL enzymes: Molecular Classification and Functional Classification. Existing computational methods only address Molecular Classification and the performance of these existing methods is unsatisfactory. We addressed the unsatisfactory performance of the existing methods by implementing a Deep Learning approach called Convolutional Neural Network (CNN). We developed CNN-BLPred, an approach for the classification of BL proteins. The CNN-BLPred uses Gradient Boosted Feature Selection (GBFS) in order to select the ideal feature set for each BL classification. Based on the rigorous benchmarking of CCN-BLPred using both leave-one-out cross-validation and independent test sets, CCN-BLPred performed better than the other existing algorithms. Compared with other architectures of CNN, Recurrent Neural Network, and Random Forest, the simple CNN architecture with only one convolutional layer performs the best. After feature extraction, we were able to remove ~95% of the 10,912 features using Gradient Boosted Trees. During 10-fold cross validation, we increased the accuracy of the classic BL predictions by 7%. We also increased the accuracy of Class A, Class B, Class C, and Class D performance by an average of 25.64%. The independent test results followed a similar trend. We implemented a deep learning algorithm known as Convolutional Neural Network (CNN) to develop a classifier for BL classification. Combined with feature selection on an exhaustive feature set and using balancing method such as Random Oversampling (ROS), Random Undersampling (RUS) and Synthetic Minority Oversampling Technique (SMOTE), CNN-BLPred performs significantly better than existing algorithms for BL classification.

Emergence of an optimal search strategy from a simple random walk

PubMed Central

Sakiyama, Tomoko; Gunji, Yukio-Pegio

2013-01-01

In reports addressing animal foraging strategies, it has been stated that Lévy-like algorithms represent an optimal search strategy in an unknown environment, because of their super-diffusion properties and power-law-distributed step lengths. Here, starting with a simple random walk algorithm, which offers the agent a randomly determined direction at each time step with a fixed move length, we investigated how flexible exploration is achieved if an agent alters its randomly determined next step forward and the rule that controls its random movement based on its own directional moving experiences. We showed that our algorithm led to an effective food-searching performance compared with a simple random walk algorithm and exhibited super-diffusion properties, despite the uniform step lengths. Moreover, our algorithm exhibited a power-law distribution independent of uniform step lengths. PMID:23804445

Emergence of an optimal search strategy from a simple random walk.

PubMed

Sakiyama, Tomoko; Gunji, Yukio-Pegio

2013-09-06

In reports addressing animal foraging strategies, it has been stated that Lévy-like algorithms represent an optimal search strategy in an unknown environment, because of their super-diffusion properties and power-law-distributed step lengths. Here, starting with a simple random walk algorithm, which offers the agent a randomly determined direction at each time step with a fixed move length, we investigated how flexible exploration is achieved if an agent alters its randomly determined next step forward and the rule that controls its random movement based on its own directional moving experiences. We showed that our algorithm led to an effective food-searching performance compared with a simple random walk algorithm and exhibited super-diffusion properties, despite the uniform step lengths. Moreover, our algorithm exhibited a power-law distribution independent of uniform step lengths.

Comparison of Different Machine Learning Algorithms for Lithological Mapping Using Remote Sensing Data and Morphological Features: A Case Study in Kurdistan Region, NE Iraq

NASA Astrophysics Data System (ADS)

Othman, Arsalan; Gloaguen, Richard

2015-04-01

Topographic effects and complex vegetation cover hinder lithology classification in mountain regions based not only in field, but also in reflectance remote sensing data. The area of interest "Bardi-Zard" is located in the NE of Iraq. It is part of the Zagros orogenic belt, where seven lithological units outcrop and is known for its chromite deposit. The aim of this study is to compare three machine learning algorithms (MLAs): Maximum Likelihood (ML), Support Vector Machines (SVM), and Random Forest (RF) in the context of a supervised lithology classification task using Advanced Space-borne Thermal Emission and Reflection radiometer (ASTER) satellite, its derived, spatial information (spatial coordinates) and geomorphic data. We emphasize the enhancement in remote sensing lithological mapping accuracy that arises from the integration of geomorphic features and spatial information (spatial coordinates) in classifications. This study identifies that RF is better than ML and SVM algorithms in almost the sixteen combination datasets, which were tested. The overall accuracy of the best dataset combination with the RF map for the all seven classes reach ~80% and the producer and user's accuracies are ~73.91% and 76.09% respectively while the kappa coefficient is ~0.76. TPI is more effective with SVM algorithm than an RF algorithm. This paper demonstrates that adding geomorphic indices such as TPI and spatial information in the dataset increases the lithological classification accuracy.

Predicting the Occurrence of Haze Events in Southeast Asia using Machine Learning Algorithms

NASA Astrophysics Data System (ADS)

Lee, H. H.; Chulakadabba, A.; Tonks, A.; Yang, Z.; Wang, C.

2017-12-01

Severe local- and regional-scale air pollution episodes typically originate from 1) high emissions of air pollutants, 2) poor dispersion conditions, and 3) trans-boundary pollutant transport. Biomass burning activities have become more frequent in Southeast Asia, especially in Sumatra, Borneo, and the mainland Southeast. Trans-boundary transport of biomass burning aerosols often lead to air quality problems in the region. Furthermore, particulate pollutants from human activities besides biomass burning also play an important role in the air quality of Southeast Asia. Singapore, for example, has a dynamic industrial sector including chemical, electric and metallurgic industries, and is the region's major petroleum-refining center. In addition, natural gas and oil power plants, waste incinerators, active port traffic, and a major regional airport further complicate Singapore's air quality issues. In this study, we compare five Machine Learning algorithms: k-Nearest Neighbors, Linear Support Vector Machine, Decision Tree, Random Forest and Artificial Neural Network, to identify haze patterns and determine variable importance. The algorithms were trained using local atmospheric data (i.e. months, atmospheric conditions, wind direction and relative humidity) from three observation stations in Singapore (Changi, Seletar and Paya Labar). We find that the algorithms reveal the associations in data within and between the stations, and provide in-depth interpretation of the haze sources. The algorithms also allow us to predict the probability of haze episodes in Singapore and to determine the correlation between this probability and atmospheric conditions.

An efficient hybrid approach for multiobjective optimization of water distribution systems

NASA Astrophysics Data System (ADS)

Zheng, Feifei; Simpson, Angus R.; Zecchin, Aaron C.

2014-05-01

An efficient hybrid approach for the design of water distribution systems (WDSs) with multiple objectives is described in this paper. The objectives are the minimization of the network cost and maximization of the network resilience. A self-adaptive multiobjective differential evolution (SAMODE) algorithm has been developed, in which control parameters are automatically adapted by means of evolution instead of the presetting of fine-tuned parameter values. In the proposed method, a graph algorithm is first used to decompose a looped WDS into a shortest-distance tree (T) or forest, and chords (Ω). The original two-objective optimization problem is then approximated by a series of single-objective optimization problems of the T to be solved by nonlinear programming (NLP), thereby providing an approximate Pareto optimal front for the original whole network. Finally, the solutions at the approximate front are used to seed the SAMODE algorithm to find an improved front for the original entire network. The proposed approach is compared with two other conventional full-search optimization methods (the SAMODE algorithm and the NSGA-II) that seed the initial population with purely random solutions based on three case studies: a benchmark network and two real-world networks with multiple demand loading cases. Results show that (i) the proposed NLP-SAMODE method consistently generates better-quality Pareto fronts than the full-search methods with significantly improved efficiency; and (ii) the proposed SAMODE algorithm (no parameter tuning) exhibits better performance than the NSGA-II with calibrated parameter values in efficiently offering optimal fronts.

Selection and quality assessment of Landsat data for the North American forest dynamics forest history maps of the US

Treesearch

Karen Schleeweis; Samuel N. Goward; Chengquan Huang; John L. Dwyer; Jennifer L. Dungan; Mary A. Lindsey; Andrew Michaelis; Khaldoun Rishmawi; Jeffery G. Masek

2016-01-01

Using the NASA Earth Exchange platform, the North American Forest Dynamics (NAFD) project mapped forest history wall-to-wall, annually for the contiguous US (1986-2010) using the Vegetation Change Tracker algorithm. As with any effort to identify real changes in remotely sensed time-series, data gaps, shifts in seasonality, misregistration, inconsistent radiometry and...

A fast ergodic algorithm for generating ensembles of equilateral random polygons

NASA Astrophysics Data System (ADS)

Varela, R.; Hinson, K.; Arsuaga, J.; Diao, Y.

2009-03-01

Knotted structures are commonly found in circular DNA and along the backbone of certain proteins. In order to properly estimate properties of these three-dimensional structures it is often necessary to generate large ensembles of simulated closed chains (i.e. polygons) of equal edge lengths (such polygons are called equilateral random polygons). However finding efficient algorithms that properly sample the space of equilateral random polygons is a difficult problem. Currently there are no proven algorithms that generate equilateral random polygons with its theoretical distribution. In this paper we propose a method that generates equilateral random polygons in a 'step-wise uniform' way. We prove that this method is ergodic in the sense that any given equilateral random polygon can be generated by this method and we show that the time needed to generate an equilateral random polygon of length n is linear in terms of n. These two properties make this algorithm a big improvement over the existing generating methods. Detailed numerical comparisons of our algorithm with other widely used algorithms are provided.

Biomass accumulation rates of Amazonian secondary forest and biomass of old-growth forests from Landsat time series and the Geoscience Laser Altimeter System

Treesearch

E. H. Helmer; M. A. Lefsky; D. A. Roberts

2009-01-01

We estimate the age of humid lowland tropical forests in Rondônia, Brazil, from a somewhat densely spaced time series of Landsat images (1975–2003) with an automated procedure, the Threshold Age Mapping Algorithm (TAMA), first described here. We then estimate a landscape-level rate of aboveground woody biomass accumulation of secondary forest by combining forest age...

Design and realization of disaster assessment algorithm after forest fire

NASA Astrophysics Data System (ADS)

Xu, Aijun; Wang, Danfeng; Tang, Lihua

2008-10-01

Based on GIS technology, this paper mainly focuses on the application of disaster assessment algorithm after forest fire and studies on the design and realization of disaster assessment based on GIS. After forest fire through the analysis and processing of multi-sources and heterogeneous data, this paper integrates the foundation that the domestic and foreign scholars laid of the research on assessment for forest fire loss with the related knowledge of assessment, accounting and forest resources appraisal so as to study and approach the theory framework and assessment index of the research on assessment for forest fire loss. The technologies of extracting boundary, overlay analysis, and division processing of multi-sources spatial data are available to realize the application of the investigation method of the burnt forest area and the computation of the fire area. The assessment provides evidence for fire cleaning in burnt areas and new policy making on restoration in terms of the direct and the indirect economic loss and ecological and environmental damage caused by forest fire under the condition of different fire danger classes and different amounts of forest accumulation, thus makes forest resources protection operated in a faster, more efficient and more economical way. Finally, this paper takes Lin'an city of Zhejiang province as a test area to confirm the method mentioned in the paper in terms of key technologies.

Correcting Classifiers for Sample Selection Bias in Two-Phase Case-Control Studies

PubMed Central

Theis, Fabian J.

2017-01-01

Epidemiological studies often utilize stratified data in which rare outcomes or exposures are artificially enriched. This design can increase precision in association tests but distorts predictions when applying classifiers on nonstratified data. Several methods correct for this so-called sample selection bias, but their performance remains unclear especially for machine learning classifiers. With an emphasis on two-phase case-control studies, we aim to assess which corrections to perform in which setting and to obtain methods suitable for machine learning techniques, especially the random forest. We propose two new resampling-based methods to resemble the original data and covariance structure: stochastic inverse-probability oversampling and parametric inverse-probability bagging. We compare all techniques for the random forest and other classifiers, both theoretically and on simulated and real data. Empirical results show that the random forest profits from only the parametric inverse-probability bagging proposed by us. For other classifiers, correction is mostly advantageous, and methods perform uniformly. We discuss consequences of inappropriate distribution assumptions and reason for different behaviors between the random forest and other classifiers. In conclusion, we provide guidance for choosing correction methods when training classifiers on biased samples. For random forests, our method outperforms state-of-the-art procedures if distribution assumptions are roughly fulfilled. We provide our implementation in the R package sambia. PMID:29312464

A Comparison between Decision Tree and Random Forest in Determining the Risk Factors Associated with Type 2 Diabetes.

PubMed

Esmaily, Habibollah; Tayefi, Maryam; Doosti, Hassan; Ghayour-Mobarhan, Majid; Nezami, Hossein; Amirabadizadeh, Alireza

2018-04-24

We aimed to identify the associated risk factors of type 2 diabetes mellitus (T2DM) using data mining approach, decision tree and random forest techniques using the Mashhad Stroke and Heart Atherosclerotic Disorders (MASHAD) Study program. A cross-sectional study. The MASHAD study started in 2010 and will continue until 2020. Two data mining tools, namely decision trees, and random forests, are used for predicting T2DM when some other characteristics are observed on 9528 subjects recruited from MASHAD database. This paper makes a comparison between these two models in terms of accuracy, sensitivity, specificity and the area under ROC curve. The prevalence rate of T2DM was 14% among these subjects. The decision tree model has 64.9% accuracy, 64.5% sensitivity, 66.8% specificity, and area under the ROC curve measuring 68.6%, while the random forest model has 71.1% accuracy, 71.3% sensitivity, 69.9% specificity, and area under the ROC curve measuring 77.3% respectively. The random forest model, when used with demographic, clinical, and anthropometric and biochemical measurements, can provide a simple tool to identify associated risk factors for type 2 diabetes. Such identification can substantially use for managing the health policy to reduce the number of subjects with T2DM .

Do little interactions get lost in dark random forests?

PubMed

Wright, Marvin N; Ziegler, Andreas; König, Inke R

2016-03-31

Random forests have often been claimed to uncover interaction effects. However, if and how interaction effects can be differentiated from marginal effects remains unclear. In extensive simulation studies, we investigate whether random forest variable importance measures capture or detect gene-gene interactions. With capturing interactions, we define the ability to identify a variable that acts through an interaction with another one, while detection is the ability to identify an interaction effect as such. Of the single importance measures, the Gini importance captured interaction effects in most of the simulated scenarios, however, they were masked by marginal effects in other variables. With the permutation importance, the proportion of captured interactions was lower in all cases. Pairwise importance measures performed about equal, with a slight advantage for the joint variable importance method. However, the overall fraction of detected interactions was low. In almost all scenarios the detection fraction in a model with only marginal effects was larger than in a model with an interaction effect only. Random forests are generally capable of capturing gene-gene interactions, but current variable importance measures are unable to detect them as interactions. In most of the cases, interactions are masked by marginal effects and interactions cannot be differentiated from marginal effects. Consequently, caution is warranted when claiming that random forests uncover interactions.

Application of random survival forests in understanding the determinants of under-five child mortality in Uganda in the presence of covariates that satisfy the proportional and non-proportional hazards assumption.

PubMed

Nasejje, Justine B; Mwambi, Henry

2017-09-07

Uganda just like any other Sub-Saharan African country, has a high under-five child mortality rate. To inform policy on intervention strategies, sound statistical methods are required to critically identify factors strongly associated with under-five child mortality rates. The Cox proportional hazards model has been a common choice in analysing data to understand factors strongly associated with high child mortality rates taking age as the time-to-event variable. However, due to its restrictive proportional hazards (PH) assumption, some covariates of interest which do not satisfy the assumption are often excluded in the analysis to avoid mis-specifying the model. Otherwise using covariates that clearly violate the assumption would mean invalid results. Survival trees and random survival forests are increasingly becoming popular in analysing survival data particularly in the case of large survey data and could be attractive alternatives to models with the restrictive PH assumption. In this article, we adopt random survival forests which have never been used in understanding factors affecting under-five child mortality rates in Uganda using Demographic and Health Survey data. Thus the first part of the analysis is based on the use of the classical Cox PH model and the second part of the analysis is based on the use of random survival forests in the presence of covariates that do not necessarily satisfy the PH assumption. Random survival forests and the Cox proportional hazards model agree that the sex of the household head, sex of the child, number of births in the past 1 year are strongly associated to under-five child mortality in Uganda given all the three covariates satisfy the PH assumption. Random survival forests further demonstrated that covariates that were originally excluded from the earlier analysis due to violation of the PH assumption were important in explaining under-five child mortality rates. These covariates include the number of children under the age of five in a household, number of births in the past 5 years, wealth index, total number of children ever born and the child's birth order. The results further indicated that the predictive performance for random survival forests built using covariates including those that violate the PH assumption was higher than that for random survival forests built using only covariates that satisfy the PH assumption. Random survival forests are appealing methods in analysing public health data to understand factors strongly associated with under-five child mortality rates especially in the presence of covariates that violate the proportional hazards assumption.

Assessment of spruce (Picea obovata) abundance by spectral unmixing algorithm for sustainable forest management in highland Natural Reserve (case study of Zigalga Range, South-Ural State Natural Reserve, Russia).

NASA Astrophysics Data System (ADS)

Mikheeva, Anna; Moiseev, Pavel

2017-04-01

In mountain territories climate change affects forest productivity and growth, which results in the tree line advancing and increasing of the forest density. These changes pose new challenges for forest managers whose responsibilities include forest resources inventory, monitoring and protection of ecosystems, and assessment of forest vulnerability. These activities require a range of sources of information, including exact squares of forested areas, forest densities and species abundances. Picea obovata, dominant tree species in South-Ural State Natural Reserve, Russia has regenerated, propagated and increased its relative cover during the recent 70 years. A remarkable shift of the upper limit of Picea obovata up to 60-80 m upslope was registered by repeating photography, especially on gentle slopes. The stands of Picea obovata are monitored by Reserve inspectors on the test plots to ensure that forests maintain or improve their productivity, these studies also include projective cover measurements. However, it is impossible to cover the entire territory of the Reserve by detailed field observations. Remote sensing data from Terra ASTER imagery provides valuable information for large territories (scene covers an area of 60 x 60 km) and can be used for quantitative mapping of forest and non-forest vegetation at regional scale (spatial resolution is 15-30 m for visible and infrared bands). A case study of estimating Picea obovata abundance was conducted for forest and forest-tundra sites of Zigalga Range, using 9-band ASTER multispectral imagery of 23.08.2007, field data and spectral unmixing algorithm. This type of algorithms intends to derive object and its abundance from a mixed pixel of multispectral imagery which can be further converted to object's projective cover. Atmospheric correction was applied to the imagery prior to spectral unmixing, and then pure spectra of Picea obovata were extracted from the image in 10 points and averaged. These points located in Zigalga Range and were visited in summer 2016. We used Mixture-tuned Match Filtering (MTMF) algorithm, a non-linear subpixel classification technique which allows to separate the spectral mixture containing unknown objects, and to derive only known ones. The results of spectral unmixing classification were abundance maps of Picea obovata. The values were statistically determined (there was only selected abundances with high probabilities of presence and low probabilities of absence) and then constrained to the interval [0; 1]. Verification of maps was made at the sites of Iremel Mountains on the same ASTER image, where projective cover of Picea obovata was measured in the field in 147 points. The correlation coefficient between the spectral unmixing abundances and field-measured abundances was 0.7; not a very high value is due to the low sensitivity of the algorithm to detect abundances less than 0.25. The proposed method provides a tool for defining the Picea obovata boundaries more accurately than per-pixel automatic classification and locating new spruce islands in the mixing tree line environment. The abundances can be obtained for large areas with minimum field work which makes this approach cost-effective in providing timely information to nature reserve managers for adapting forest management actions to climate change.

Personalized Physical Activity Coaching: A Machine Learning Approach

PubMed Central

Dijkhuis, Talko B.; van Ittersum, Miriam W.; Velthuijsen, Hugo

2018-01-01

Living a sedentary lifestyle is one of the major causes of numerous health problems. To encourage employees to lead a less sedentary life, the Hanze University started a health promotion program. One of the interventions in the program was the use of an activity tracker to record participants' daily step count. The daily step count served as input for a fortnightly coaching session. In this paper, we investigate the possibility of automating part of the coaching procedure on physical activity by providing personalized feedback throughout the day on a participant’s progress in achieving a personal step goal. The gathered step count data was used to train eight different machine learning algorithms to make hourly estimations of the probability of achieving a personalized, daily steps threshold. In 80% of the individual cases, the Random Forest algorithm was the best performing algorithm (mean accuracy = 0.93, range = 0.88–0.99, and mean F1-score = 0.90, range = 0.87–0.94). To demonstrate the practical usefulness of these models, we developed a proof-of-concept Web application that provides personalized feedback about whether a participant is expected to reach his or her daily threshold. We argue that the use of machine learning could become an invaluable asset in the process of automated personalized coaching. The individualized algorithms allow for predicting physical activity during the day and provides the possibility to intervene in time. PMID:29463052

Gene selection using hybrid binary black hole algorithm and modified binary particle swarm optimization.

PubMed

Pashaei, Elnaz; Pashaei, Elham; Aydin, Nizamettin

2018-04-14

In cancer classification, gene selection is an important data preprocessing technique, but it is a difficult task due to the large search space. Accordingly, the objective of this study is to develop a hybrid meta-heuristic Binary Black Hole Algorithm (BBHA) and Binary Particle Swarm Optimization (BPSO) (4-2) model that emphasizes gene selection. In this model, the BBHA is embedded in the BPSO (4-2) algorithm to make the BPSO (4-2) more effective and to facilitate the exploration and exploitation of the BPSO (4-2) algorithm to further improve the performance. This model has been associated with Random Forest Recursive Feature Elimination (RF-RFE) pre-filtering technique. The classifiers which are evaluated in the proposed framework are Sparse Partial Least Squares Discriminant Analysis (SPLSDA); k-nearest neighbor and Naive Bayes. The performance of the proposed method was evaluated on two benchmark and three clinical microarrays. The experimental results and statistical analysis confirm the better performance of the BPSO (4-2)-BBHA compared with the BBHA, the BPSO (4-2) and several state-of-the-art methods in terms of avoiding local minima, convergence rate, accuracy and number of selected genes. The results also show that the BPSO (4-2)-BBHA model can successfully identify known biologically and statistically significant genes from the clinical datasets. Copyright © 2018 Elsevier Inc. All rights reserved.

Disruption Warning Database Development and Exploratory Machine Learning Studies on Alcator C-Mod

NASA Astrophysics Data System (ADS)

Montes, Kevin; Rea, Cristina; Granetz, Robert

2017-10-01

A database of about 1800 shots from the 2015 campaign on the Alcator C-Mod tokamak is assembled, including disruptive and non-disruptive discharges. The database consists of 40 relevant plasma parameters with data taken from 160k time slices. In order to investigate the possibility of developing a robust disruption prediction algorithm that is tokamak-independent, we focused machine learning studies on a subset of dimensionless parameters such as βp, n /nG , etc. The Random Forests machine learning algorithm provides insight on the available data set by ranking the relative importance of the input features. Its application on the C-Mod database, however, reveals that virtually no one parameter has more importance than any other, and that its classification algorithm has a low rate of successfully predicted samples, as well as poor false positive and false negative rates. Comparing the analysis of this algorithm on the C-Mod database with its application to a similar database on DIII-D, we conclude that disruption prediction may not be feasible on C-Mod. This conclusion is supported by empirical observations that most C-Mod disruptions are caused by radiative collapse due to molybdenum from the first wall, which happens on just a 1-2ms timescale. Supported by the US Dept. of Energy under DE-FC02-99ER54512 and DE-FC02-04ER54698.

Comparative analysis of semantic localization accuracies between adult and pediatric DICOM CT images

NASA Astrophysics Data System (ADS)

Robertson, Duncan; Pathak, Sayan D.; Criminisi, Antonio; White, Steve; Haynor, David; Chen, Oliver; Siddiqui, Khan

2012-02-01

Existing literature describes a variety of techniques for semantic annotation of DICOM CT images, i.e. the automatic detection and localization of anatomical structures. Semantic annotation facilitates enhanced image navigation, linkage of DICOM image content and non-image clinical data, content-based image retrieval, and image registration. A key challenge for semantic annotation algorithms is inter-patient variability. However, while the algorithms described in published literature have been shown to cope adequately with the variability in test sets comprising adult CT scans, the problem presented by the even greater variability in pediatric anatomy has received very little attention. Most existing semantic annotation algorithms can only be extended to work on scans of both adult and pediatric patients by adapting parameters heuristically in light of patient size. In contrast, our approach, which uses random regression forests ('RRF'), learns an implicit model of scale variation automatically using training data. In consequence, anatomical structures can be localized accurately in both adult and pediatric CT studies without the need for parameter adaptation or additional information about patient scale. We show how the RRF algorithm is able to learn scale invariance from a combined training set containing a mixture of pediatric and adult scans. Resulting localization accuracy for both adult and pediatric data remains comparable with that obtained using RRFs trained and tested using only adult data.

NIMEFI: gene regulatory network inference using multiple ensemble feature importance algorithms.

PubMed

Ruyssinck, Joeri; Huynh-Thu, Vân Anh; Geurts, Pierre; Dhaene, Tom; Demeester, Piet; Saeys, Yvan

2014-01-01

One of the long-standing open challenges in computational systems biology is the topology inference of gene regulatory networks from high-throughput omics data. Recently, two community-wide efforts, DREAM4 and DREAM5, have been established to benchmark network inference techniques using gene expression measurements. In these challenges the overall top performer was the GENIE3 algorithm. This method decomposes the network inference task into separate regression problems for each gene in the network in which the expression values of a particular target gene are predicted using all other genes as possible predictors. Next, using tree-based ensemble methods, an importance measure for each predictor gene is calculated with respect to the target gene and a high feature importance is considered as putative evidence of a regulatory link existing between both genes. The contribution of this work is twofold. First, we generalize the regression decomposition strategy of GENIE3 to other feature importance methods. We compare the performance of support vector regression, the elastic net, random forest regression, symbolic regression and their ensemble variants in this setting to the original GENIE3 algorithm. To create the ensemble variants, we propose a subsampling approach which allows us to cast any feature selection algorithm that produces a feature ranking into an ensemble feature importance algorithm. We demonstrate that the ensemble setting is key to the network inference task, as only ensemble variants achieve top performance. As second contribution, we explore the effect of using rankwise averaged predictions of multiple ensemble algorithms as opposed to only one. We name this approach NIMEFI (Network Inference using Multiple Ensemble Feature Importance algorithms) and show that this approach outperforms all individual methods in general, although on a specific network a single method can perform better. An implementation of NIMEFI has been made publicly available.

Hip and Wrist Accelerometer Algorithms for Free-Living Behavior Classification.

PubMed

Ellis, Katherine; Kerr, Jacqueline; Godbole, Suneeta; Staudenmayer, John; Lanckriet, Gert

2016-05-01

Accelerometers are a valuable tool for objective measurement of physical activity (PA). Wrist-worn devices may improve compliance over standard hip placement, but more research is needed to evaluate their validity for measuring PA in free-living settings. Traditional cut-point methods for accelerometers can be inaccurate and need testing in free living with wrist-worn devices. In this study, we developed and tested the performance of machine learning (ML) algorithms for classifying PA types from both hip and wrist accelerometer data. Forty overweight or obese women (mean age = 55.2 ± 15.3 yr; BMI = 32.0 ± 3.7) wore two ActiGraph GT3X+ accelerometers (right hip, nondominant wrist; ActiGraph, Pensacola, FL) for seven free-living days. Wearable cameras captured ground truth activity labels. A classifier consisting of a random forest and hidden Markov model classified the accelerometer data into four activities (sitting, standing, walking/running, and riding in a vehicle). Free-living wrist and hip ML classifiers were compared with each other, with traditional accelerometer cut points, and with an algorithm developed in a laboratory setting. The ML classifier obtained average values of 89.4% and 84.6% balanced accuracy over the four activities using the hip and wrist accelerometer, respectively. In our data set with average values of 28.4 min of walking or running per day, the ML classifier predicted average values of 28.5 and 24.5 min of walking or running using the hip and wrist accelerometer, respectively. Intensity-based cut points and the laboratory algorithm significantly underestimated walking minutes. Our results demonstrate the superior performance of our PA-type classification algorithm, particularly in comparison with traditional cut points. Although the hip algorithm performed better, additional compliance achieved with wrist devices might justify using a slightly lower performing algorithm.

Mapping Forest Height in Gabon Using UAVSAR Multi-Baseline Polarimetric SAR Interferometry and Lidar Fusion

NASA Astrophysics Data System (ADS)

Simard, M.; Denbina, M. W.

2017-12-01

Using data collected by NASA's Uninhabited Aerial Vehicle Synthetic Aperture Radar (UAVSAR) and Land, Vegetation, and Ice Sensor (LVIS) lidar, we have estimated forest canopy height for a number of study areas in the country of Gabon using a new machine learning data fusion approach. Using multi-baseline polarimetric synthetic aperture radar interferometry (PolInSAR) data collected by UAVSAR, forest heights can be estimated using the random volume over ground model. In the case of multi-baseline UAVSAR data consisting of many repeat passes with spatially separated flight tracks, we can estimate different forest height values for each different image pair, or baseline. In order to choose the best forest height estimate for each pixel, the baselines must be selected or ranked, taking care to avoid baselines with unsuitable spatial separation, or severe temporal decorrelation effects. The current baseline selection algorithms in the literature use basic quality metrics derived from the PolInSAR data which are not necessarily indicative of the true height accuracy in all cases. We have developed a new data fusion technique which treats PolInSAR baseline selection as a supervised classification problem, where the classifier is trained using a sparse sampling of lidar data within the PolInSAR coverage area. The classifier uses a large variety of PolInSAR-derived features as input, including radar backscatter as well as features based on the PolInSAR coherence region shape and the PolInSAR complex coherences. The resulting data fusion method produces forest height estimates which are more accurate than a purely radar-based approach, while having a larger coverage area than the input lidar training data, combining some of the strengths of each sensor. The technique demonstrates the strong potential for forest canopy height and above-ground biomass mapping using fusion of PolInSAR with data from future spaceborne lidar missions such as the upcoming Global Ecosystems Dynamics Investigation (GEDI) lidar.

Identification of an Efficient Gene Expression Panel for Glioblastoma Classification

PubMed Central

Zelaya, Ivette; Laks, Dan R.; Zhao, Yining; Kawaguchi, Riki; Gao, Fuying; Kornblum, Harley I.; Coppola, Giovanni

2016-01-01

We present here a novel genetic algorithm-based random forest (GARF) modeling technique that enables a reduction in the complexity of large gene disease signatures to highly accurate, greatly simplified gene panels. When applied to 803 glioblastoma multiforme samples, this method allowed the 840-gene Verhaak et al. gene panel (the standard in the field) to be reduced to a 48-gene classifier, while retaining 90.91% classification accuracy, and outperforming the best available alternative methods. Additionally, using this approach we produced a 32-gene panel which allows for better consistency between RNA-seq and microarray-based classifications, improving cross-platform classification retention from 69.67% to 86.07%. A webpage producing these classifications is available at http://simplegbm.semel.ucla.edu. PMID:27855170

Source localization in an ocean waveguide using supervised machine learning.

PubMed

Niu, Haiqiang; Reeves, Emma; Gerstoft, Peter

2017-09-01

Source localization in ocean acoustics is posed as a machine learning problem in which data-driven methods learn source ranges directly from observed acoustic data. The pressure received by a vertical linear array is preprocessed by constructing a normalized sample covariance matrix and used as the input for three machine learning methods: feed-forward neural networks (FNN), support vector machines (SVM), and random forests (RF). The range estimation problem is solved both as a classification problem and as a regression problem by these three machine learning algorithms. The results of range estimation for the Noise09 experiment are compared for FNN, SVM, RF, and conventional matched-field processing and demonstrate the potential of machine learning for underwater source localization.

Predictive modeling of cardiovascular complications in incident hemodialysis patients.

PubMed

Ion Titapiccolo, J; Ferrario, M; Barbieri, C; Marcelli, D; Mari, F; Gatti, E; Cerutti, S; Smyth, P; Signorini, M G

2012-01-01

The administration of hemodialysis (HD) treatment leads to the continuous collection of a vast quantity of medical data. Many variables related to the patient health status, to the treatment, and to dialyzer settings can be recorded and stored at each treatment session. In this study a dataset of 42 variables and 1526 patients extracted from the Fresenius Medical Care database EuCliD was used to develop and apply a random forest predictive model for the prediction of cardiovascular events in the first year of HD treatment. A ridge-lasso logistic regression algorithm was then applied to the subset of variables mostly involved in the prediction model to get insights in the mechanisms underlying the incidence of cardiovascular complications in this high risk population of patients.

[Raman spectroscopy fluorescence background correction and its application in clustering analysis of medicines].

PubMed

Chen, Shan; Li, Xiao-ning; Liang, Yi-zeng; Zhang, Zhi-min; Liu, Zhao-xia; Zhang, Qi-ming; Ding, Li-xia; Ye, Fei

2010-08-01

During Raman spectroscopy analysis, the organic molecules and contaminations will obscure or swamp Raman signals. The present study starts from Raman spectra of prednisone acetate tablets and glibenclamide tables, which are acquired from the BWTek i-Raman spectrometer. The background is corrected by R package baselineWavelet. Then principle component analysis and random forests are used to perform clustering analysis. Through analyzing the Raman spectra of two medicines, the accurate and validity of this background-correction algorithm is checked and the influences of fluorescence background on Raman spectra clustering analysis is discussed. Thus, it is concluded that it is important to correct fluorescence background for further analysis, and an effective background correction solution is provided for clustering or other analysis.

Accuracy Assessment of Satellite Derived Forest Cover Products in South and Southeast Asia

NASA Astrophysics Data System (ADS)

Gilani, H.; Xu, X.; Jain, A. K.

2017-12-01

South and Southeast Asia (SSEA) region occupies 16 % of worlds land area. It is home to over 50% of the world's population. The SSEA's countries are experiencing significant land-use and land-cover changes (LULCCs), primarily in agriculture, forest, and urban land. For this study, we compiled four existing global forest cover maps for year 2010 by Gong et al.(2015), Hansen et al. (2013), Sexton et al.(2013) and Shimada et al. (2014), which were all medium resolution (≤30 m) products based on Landsat and/or PALSAR satellite images. To evaluate the accuracy of these forest products, we used three types of information: (1) ground measurements, (2) high resolution satellite images and (3) forest cover maps produced at the national scale. The stratified random sampling technique was used to select a set of validation data points from the ground and high-resolution satellite images. Then the confusion matrix method was used to assess and rank the accuracy of the forest cover products for the entire SSEA region. We analyzed the spatial consistency of different forest cover maps, and further evaluated the consistency with terrain characteristics. Our study suggests that global forest cover mapping algorithms are trained and tested using limited ground measurement data. We found significant uncertainties in mountainous areas due to the topographical shadow effect and the dense tree canopies effects. The findings of this study will facilitate to improve our understanding of the forest cover dynamics and their impacts on the quantities and pathways of terrestrial carbon and nitrogen fluxes. Gong, P., et al. (2012). "Finer resolution observation and monitoring of global land cover: first mapping results with Landsat TM and ETM+ data." International Journal of Remote Sensing 34(7): 2607-2654. Hansen, M. C., et al. (2013). "High-Resolution Global Maps of 21st-Century Forest Cover Change." Science 342(6160): 850-853. Sexton, J. O., et al. (2013). "Global, 30-m resolution continuous fields of tree cover: Landsat-based rescaling of MODIS vegetation continuous fields with lidar-based estimates of error." International Journal of Digital Earth: 1-22. Shimada, M., et al. (2014). "New global forest/non-forest maps from ALOS PALSAR data (2007-2010)." Remote Sensing of Environment 155: 13-31.

A k-mer-based barcode DNA classification methodology based on spectral representation and a neural gas network.

PubMed

Fiannaca, Antonino; La Rosa, Massimo; Rizzo, Riccardo; Urso, Alfonso

2015-07-01

In this paper, an alignment-free method for DNA barcode classification that is based on both a spectral representation and a neural gas network for unsupervised clustering is proposed. In the proposed methodology, distinctive words are identified from a spectral representation of DNA sequences. A taxonomic classification of the DNA sequence is then performed using the sequence signature, i.e., the smallest set of k-mers that can assign a DNA sequence to its proper taxonomic category. Experiments were then performed to compare our method with other supervised machine learning classification algorithms, such as support vector machine, random forest, ripper, naïve Bayes, ridor, and classification tree, which also consider short DNA sequence fragments of 200 and 300 base pairs (bp). The experimental tests were conducted over 10 real barcode datasets belonging to different animal species, which were provided by the on-line resource "Barcode of Life Database". The experimental results showed that our k-mer-based approach is directly comparable, in terms of accuracy, recall and precision metrics, with the other classifiers when considering full-length sequences. In addition, we demonstrate the robustness of our method when a classification is performed task with a set of short DNA sequences that were randomly extracted from the original data. For example, the proposed method can reach the accuracy of 64.8% at the species level with 200-bp fragments. Under the same conditions, the best other classifier (random forest) reaches the accuracy of 20.9%. Our results indicate that we obtained a clear improvement over the other classifiers for the study of short DNA barcode sequence fragments. Copyright © 2015 Elsevier B.V. All rights reserved.

Beyond the hype: deep neural networks outperform established methods using a ChEMBL bioactivity benchmark set.

PubMed

Lenselink, Eelke B; Ten Dijke, Niels; Bongers, Brandon; Papadatos, George; van Vlijmen, Herman W T; Kowalczyk, Wojtek; IJzerman, Adriaan P; van Westen, Gerard J P

2017-08-14

The increase of publicly available bioactivity data in recent years has fueled and catalyzed research in chemogenomics, data mining, and modeling approaches. As a direct result, over the past few years a multitude of different methods have been reported and evaluated, such as target fishing, nearest neighbor similarity-based methods, and Quantitative Structure Activity Relationship (QSAR)-based protocols. However, such studies are typically conducted on different datasets, using different validation strategies, and different metrics. In this study, different methods were compared using one single standardized dataset obtained from ChEMBL, which is made available to the public, using standardized metrics (BEDROC and Matthews Correlation Coefficient). Specifically, the performance of Naïve Bayes, Random Forests, Support Vector Machines, Logistic Regression, and Deep Neural Networks was assessed using QSAR and proteochemometric (PCM) methods. All methods were validated using both a random split validation and a temporal validation, with the latter being a more realistic benchmark of expected prospective execution. Deep Neural Networks are the top performing classifiers, highlighting the added value of Deep Neural Networks over other more conventional methods. Moreover, the best method ('DNN_PCM') performed significantly better at almost one standard deviation higher than the mean performance. Furthermore, Multi-task and PCM implementations were shown to improve performance over single task Deep Neural Networks. Conversely, target prediction performed almost two standard deviations under the mean performance. Random Forests, Support Vector Machines, and Logistic Regression performed around mean performance. Finally, using an ensemble of DNNs, alongside additional tuning, enhanced the relative performance by another 27% (compared with unoptimized 'DNN_PCM'). Here, a standardized set to test and evaluate different machine learning algorithms in the context of multi-task learning is offered by providing the data and the protocols. Graphical Abstract .

Newer classification and regression tree techniques: Bagging and Random Forests for ecological prediction

Treesearch

Anantha M. Prasad; Louis R. Iverson; Andy Liaw; Andy Liaw

2006-01-01

We evaluated four statistical models - Regression Tree Analysis (RTA), Bagging Trees (BT), Random Forests (RF), and Multivariate Adaptive Regression Splines (MARS) - for predictive vegetation mapping under current and future climate scenarios according to the Canadian Climate Centre global circulation model.

Comparing spatial regression to random forests for large environmental data sets

EPA Science Inventory

Environmental data may be “large” due to number of records, number of covariates, or both. Random forests has a reputation for good predictive performance when using many covariates, whereas spatial regression, when using reduced rank methods, has a reputatio...

Comparison of Nine Statistical Model Based Warfarin Pharmacogenetic Dosing Algorithms Using the Racially Diverse International Warfarin Pharmacogenetic Consortium Cohort Database

PubMed Central

Liu, Rong; Li, Xi; Zhang, Wei; Zhou, Hong-Hao

2015-01-01

Objective Multiple linear regression (MLR) and machine learning techniques in pharmacogenetic algorithm-based warfarin dosing have been reported. However, performances of these algorithms in racially diverse group have never been objectively evaluated and compared. In this literature-based study, we compared the performances of eight machine learning techniques with those of MLR in a large, racially-diverse cohort. Methods MLR, artificial neural network (ANN), regression tree (RT), multivariate adaptive regression splines (MARS), boosted regression tree (BRT), support vector regression (SVR), random forest regression (RFR), lasso regression (LAR) and Bayesian additive regression trees (BART) were applied in warfarin dose algorithms in a cohort from the International Warfarin Pharmacogenetics Consortium database. Covariates obtained by stepwise regression from 80% of randomly selected patients were used to develop algorithms. To compare the performances of these algorithms, the mean percentage of patients whose predicted dose fell within 20% of the actual dose (mean percentage within 20%) and the mean absolute error (MAE) were calculated in the remaining 20% of patients. The performances of these techniques in different races, as well as the dose ranges of therapeutic warfarin were compared. Robust results were obtained after 100 rounds of resampling. Results BART, MARS and SVR were statistically indistinguishable and significantly out performed all the other approaches in the whole cohort (MAE: 8.84–8.96 mg/week, mean percentage within 20%: 45.88%–46.35%). In the White population, MARS and BART showed higher mean percentage within 20% and lower mean MAE than those of MLR (all p values < 0.05). In the Asian population, SVR, BART, MARS and LAR performed the same as MLR. MLR and LAR optimally performed among the Black population. When patients were grouped in terms of warfarin dose range, all machine learning techniques except ANN and LAR showed significantly higher mean percentage within 20%, and lower MAE (all p values < 0.05) than MLR in the low- and high- dose ranges. Conclusion Overall, machine learning-based techniques, BART, MARS and SVR performed superior than MLR in warfarin pharmacogenetic dosing. Differences of algorithms’ performances exist among the races. Moreover, machine learning-based algorithms tended to perform better in the low- and high- dose ranges than MLR. PMID:26305568

Modeling the Effects of Climate Change on Whitebark Pine Along the Pacific Crest Trail

NASA Astrophysics Data System (ADS)

Anderson, R. S.; Nguyen, A.; Gill, N.; Kannan, S.; Patadia, N.; Meyer, M.; Schmidt, C.

2012-12-01

The Pacific Crest Trail (PCT), one of eight National Scenic Trails, stretches 2,650 miles from Mexico to the Canadian border. At high elevations along this trail, within Inyo and Sierra National Forests, populations of whitebark pine (Pinus albicaulis) have been diminishing due to infestation of the mountain pine beetle (Dendroctonus ponderosae) and are threatened due to a changing climate. Understanding the current and future condition of whitebark pine is a primary goal of forest managers due to its high ecological and economic importance, and it is currently a candidate for protection under the Endangered Species Act (ESA). Using satellite imagery, we analyzed the rate and spatial extent of whitebark pine tree mortality from 1984 to 2011 using the Landsat-based Detection of Trends in Disturbance and Recovery (LandTrendr) program. Climate data, soil properties, and biological features of the whitebark pine were incorporated in the Physiological Principles to Predict Growth (3-PG) model to predict future rates of growth and assess its applicability in modeling natural whitebark pine processes. Finally, the Random Forest algorithm was used with topographic data alongside recent and future climate data from the IPCC A2 and B1 climate scenarios for the years 2030, 2060, and 2090 to model the future distribution of whitebark pine. LandTrendr results indicate beetle related mortality covering 14,940 km2 of forest, 2,880 km2 of which are within whitebark pine forest. By 2090, our results show that under the A2 climate scenario, whitebark pine suitable habitat may be reduced by as much as 99.97% by the year 2090 within our study area. Under the B1 climate scenario, which has decreased CO2 emissions, 13.54% more habitat would be preserved in 2090.

Mapping vegetation heights in China using slope correction ICESat data, SRTM, MODIS-derived and climate data

NASA Astrophysics Data System (ADS)

Huang, Huabing; Liu, Caixia; Wang, Xiaoyi; Biging, Gregory S.; Chen, Yanlei; Yang, Jun; Gong, Peng

2017-07-01

Vegetation height is an important parameter for biomass assessment and vegetation classification. However, vegetation height data over large areas are difficult to obtain. The existing vegetation height data derived from the Ice, Cloud and land Elevation Satellite (ICESat) data only include laser footprints in relatively flat forest regions (<5°). Thus, a large portion of ICESat data over sloping areas has not been used. In this study, we used a new slope correction method to improve the accuracy of estimates of vegetation heights for regions where slopes fall between 5° and 15°. The new method enabled us to use more than 20% additional laser data compared with the existing vegetation height data which only uses ICESat data in relatively flat areas (slope < 5°) in China. With the vegetation height data extracted from ICESat footprints and ancillary data including Moderate Resolution Imaging Spectroradiometer (MODIS) derived data (canopy cover, reflectances and leaf area index), climate data, and topographic data, we developed a wall to wall vegetation height map of China using the Random Forest algorithm. We used the data from 416 field measurements to validate the new vegetation height product. The coefficient of determination (R2) and RMSE of the new vegetation height product were 0.89 and 4.73 m respectively. The accuracy of the product is significantly better than that of the two existing global forest height products produced by Lefsky (2010) and Simard et al. (2011), when compared with the data from 227 field measurements in our study area. The new vegetation height data demonstrated clear distinctions among forest, shrub and grassland, which is promising for improving the classification of vegetation and above-ground forest biomass assessment in China.

Comparative Analysis of Daytime Fire Detection Algorithms, Using AVHRR Data for the 1995 Fire Season in Canda: Perspective for MODIS

NASA Technical Reports Server (NTRS)

Ichoku, Charles; Kaufman, Y. J.; Fraser, R. H.; Jin, J.-Z.; Park, W. M.; Lau, William K. M. (Technical Monitor)

2001-01-01

Two fixed-threshold Canada Centre for Remote Sensing and European Space Agency (CCRS and ESA) and three contextual GIGLIO, International Geosphere and Biosphere Project, and Moderate Resolution Imaging Spectroradiometer (GIGLIO, IGBP, and MODIS) algorithms were used for fire detection with Advanced Very High Resolution Radiometer (AVHRR) data acquired over Canada during the 1995 fire season. The CCRS algorithm was developed for the boreal ecosystem, while the other four are for global application. The MODIS algorithm, although developed specifically for use with the MODIS sensor data, was applied to AVHRR in this study for comparative purposes. Fire detection accuracy assessment for the algorithms was based on comparisons with available 1995 burned area ground survey maps covering five Canadian provinces. Overall accuracy estimations in terms of omission (CCRS=46%, ESA=81%, GIGLIO=75%, IGBP=51%, MODIS=81%) and commission (CCRS=0.35%, ESA=0.08%, GIGLIO=0.56%, IGBP=0.75%, MODIS=0.08%) errors over forested areas revealed large differences in performance between the algorithms, with no relevance to type (fixed-threshold or contextual). CCRS performed best in detecting real forest fires, with the least omission error, while ESA and MODIS produced the highest omission error, probably because of their relatively high threshold values designed for global application. The commission error values appear small because the area of pixels falsely identified by each algorithm was expressed as a ratio of the vast unburned forest area. More detailed study shows that most commission errors in all the algorithms were incurred in nonforest agricultural areas, especially on days with very high surface temperatures. The advantage of the high thresholds in ESA and MODIS was that they incurred the least commission errors.

Mapping forest canopy disturbance in the Upper Great Lakes, USA

Treesearch

James D. Garner; Mark D. Nelson; Brian G. Tavernia; Charles H. (Hobie) Perry; Ian W. Housman

2015-01-01

A map of forest canopy disturbance was generated for Michigan, Wisconsin, and most of Minnesota using 42 Landsat time series stacks (LTSS) and a vegetation change tracker (VCTw) algorithm. Corresponding winter imagery was used to reduce commission errors of forest disturbance by identifying areas of persistent snow cover. The resulting disturbance age map was classed...

Water content measurement in forest soils and decayed wood using time domain reflectometry

Treesearch

Andrew Gray; Thomas Spies

1995-01-01

The use of time domain reflectometry to measure moisture content in forest soils and woody debris was evaluated. Calibrations were developed on undisturbed soil cores from four forest stands and on point samples from decayed logs. An algorithm for interpreting irregularly shaped traces generated by the reflectometer was also developed. Two different calibration...

Distributed Data-aggregation Consensus for Sensor Networks: Relaxation of Consensus Concept and Convergence Property

DTIC Science & Technology

2014-08-01

consensus algorithm called randomized gossip is more suitable [7, 8]. In asynchronous randomized gossip algorithms, pairs of neighboring nodes exchange...messages and perform updates in an asynchronous and unattended manner, and they also 1 The class of broadcast gossip algorithms [9, 10, 11, 12] are...dynamics [2] and asynchronous pairwise randomized gossip [7, 8], broadcast gossip algorithms do not require that nodes know the identities of their

SAR-based change detection using hypothesis testing and Markov random field modelling

NASA Astrophysics Data System (ADS)

Cao, W.; Martinis, S.

2015-04-01

The objective of this study is to automatically detect changed areas caused by natural disasters from bi-temporal co-registered and calibrated TerraSAR-X data. The technique in this paper consists of two steps: Firstly, an automatic coarse detection step is applied based on a statistical hypothesis test for initializing the classification. The original analytical formula as proposed in the constant false alarm rate (CFAR) edge detector is reviewed and rewritten in a compact form of the incomplete beta function, which is a builtin routine in commercial scientific software such as MATLAB and IDL. Secondly, a post-classification step is introduced to optimize the noisy classification result in the previous step. Generally, an optimization problem can be formulated as a Markov random field (MRF) on which the quality of a classification is measured by an energy function. The optimal classification based on the MRF is related to the lowest energy value. Previous studies provide methods for the optimization problem using MRFs, such as the iterated conditional modes (ICM) algorithm. Recently, a novel algorithm was presented based on graph-cut theory. This method transforms a MRF to an equivalent graph and solves the optimization problem by a max-flow/min-cut algorithm on the graph. In this study this graph-cut algorithm is applied iteratively to improve the coarse classification. At each iteration the parameters of the energy function for the current classification are set by the logarithmic probability density function (PDF). The relevant parameters are estimated by the method of logarithmic cumulants (MoLC). Experiments are performed using two flood events in Germany and Australia in 2011 and a forest fire on La Palma in 2009 using pre- and post-event TerraSAR-X data. The results show convincing coarse classifications and considerable improvement by the graph-cut post-classification step.

Assessing the accuracy and stability of variable selection methods for random forest modeling in ecology

EPA Science Inventory

Random forest (RF) modeling has emerged as an important statistical learning method in ecology due to its exceptional predictive performance. However, for large and complex ecological datasets there is limited guidance on variable selection methods for RF modeling. Typically, e...

Effects of Forest Disturbances on Forest Structural Parameters Retrieval from Lidar Waveform Data

NASA Technical Reports Server (NTRS)

Ranson, K, Lon; Sun, G.

2011-01-01

The effect of forest disturbance on the lidar waveform and the forest biomass estimation was demonstrated by model simulation. The results show that the correlation between stand biomass and the lidar waveform indices changes when the stand spatial structure changes due to disturbances rather than the natural succession. This has to be considered in developing algorithms for regional or global mapping of biomass from lidar waveform data.

Satellite change detection of forest damage near the Chernobyl accident

DOE Office of Scientific and Technical Information (OSTI.GOV)

McClellan, G.E.; Anno, G.H.

1992-01-01

A substantial amount of forest within a few kilometers of the Chernobyl nuclear reactor station was badly contaminated with radionuclides by the April 26, 1986, explosion and ensuing fire at reactor No. 4. Radiation doses to conifers in some areas were sufficient to cause discoloration of needles within a few weeks. Other areas, receiving smaller doses, showed foliage changes beginning 6 months to a year later. Multispectral imagery available from Landsat sensors is especially suited for monitoring such changes in vegetation. A series of Landsat Thematic Mapper images was developed that span the 2 yr following the accident. Quantitative dosemore » estimation for the exposed conifers requires an objective change detection algorithm and knowledge of the dose-time response of conifers to ionizing radiation. Pacific-Sierra Research Corporation's Hyperscout{trademark} algorithm is based on an advanced, sensitive technique for change detection particularly suited for multispectral images. The Hyperscout algorithm has been used to assess radiation damage to the forested areas around the Chernobyl nuclear power plant.« less

WDL-RF: Predicting Bioactivities of Ligand Molecules Acting with G Protein-coupled Receptors by Combining Weighted Deep Learning and Random Forest.

PubMed

Wu, Jiansheng; Zhang, Qiuming; Wu, Weijian; Pang, Tao; Hu, Haifeng; Chan, Wallace K B; Ke, Xiaoyan; Zhang, Yang; Wren, Jonathan

2018-02-08

Precise assessment of ligand bioactivities (including IC50, EC50, Ki, Kd, etc.) is essential for virtual screening and lead compound identification. However, not all ligands have experimentally-determined activities. In particular, many G protein-coupled receptors (GPCRs), which are the largest integral membrane protein family and represent targets of nearly 40% drugs on the market, lack published experimental data about ligand interactions. Computational methods with the ability to accurately predict the bioactivity of ligands can help efficiently address this problem. We proposed a new method, WDL-RF, using weighted deep learning and random forest, to model the bioactivity of GPCR-associated ligand molecules. The pipeline of our algorithm consists of two consecutive stages: 1) molecular fingerprint generation through a new weighted deep learning method, and 2) bioactivity calculations with a random forest model; where one uniqueness of the approach is that the model allows end-to-end learning of prediction pipelines with input ligands being of arbitrary size. The method was tested on a set of twenty-six non-redundant GPCRs that have a high number of active ligands, each with 200∼4000 ligand associations. The results from our benchmark show that WDL-RF can generate bioactivity predictions with an average root-mean square error 1.33 and correlation coefficient (r2) 0.80 compared to the experimental measurements, which are significantly more accurate than the control predictors with different molecular fingerprints and descriptors. In particular, data-driven molecular fingerprint features, as extracted from the weighted deep learning models, can help solve deficiencies stemming from the use of traditional hand-crafted features and significantly increase the efficiency of short molecular fingerprints in virtual screening. The WDL-RF web server, as well as source codes and datasets of WDL-RF, is freely available at https://zhanglab.ccmb.med.umich.edu/WDL-RF/ for academic purposes. Xiaoyan Ke (kexynj@hotmail.com); Yang Zhang (zhng@umich.edu). Supplementary data are available at Bioinformatics online. © The Author (2018). Published by Oxford University Press. All rights reserved. For Permissions, please email: journals.permissions@oup.com

TH-CD-206-05: Machine-Learning Based Segmentation of Organs at Risks for Head and Neck Radiotherapy Planning

DOE Office of Scientific and Technical Information (OSTI.GOV)

Ibragimov, B; Pernus, F; Strojan, P

Purpose: Accurate and efficient delineation of tumor target and organs-at-risks is essential for the success of radiotherapy. In reality, despite of decades of intense research efforts, auto-segmentation has not yet become clinical practice. In this study, we present, for the first time, a deep learning-based classification algorithm for autonomous segmentation in head and neck (HaN) treatment planning. Methods: Fifteen HN datasets of CT, MR and PET images with manual annotation of organs-at-risk (OARs) including spinal cord, brainstem, optic nerves, chiasm, eyes, mandible, tongue, parotid glands were collected and saved in a library of plans. We also have ten super-resolution MRmore » images of the tongue area, where the genioglossus and inferior longitudinalis tongue muscles are defined as organs of interest. We applied the concepts of random forest- and deep learning-based object classification for automated image annotation with the aim of using machine learning to facilitate head and neck radiotherapy planning process. In this new paradigm of segmentation, random forests were used for landmark-assisted segmentation of super-resolution MR images. Alternatively to auto-segmentation with random forest-based landmark detection, deep convolutional neural networks were developed for voxel-wise segmentation of OARs in single and multi-modal images. The network consisted of three pairs of convolution and pooing layer, one RuLU layer and a softmax layer. Results: We present a comprehensive study on using machine learning concepts for auto-segmentation of OARs and tongue muscles for the HaN radiotherapy planning. An accuracy of 81.8% in terms of Dice coefficient was achieved for segmentation of genioglossus and inferior longitudinalis tongue muscles. Preliminary results of OARs regimentation also indicate that deep-learning afforded an unprecedented opportunities to improve the accuracy and robustness of radiotherapy planning. Conclusion: A novel machine learning framework has been developed for image annotation and structure segmentation. Our results indicate the great potential of deep learning in radiotherapy treatment planning.« less

Multidecadal Rates of Disturbance- and Climate Change-Induced Land Cover Change in Arctic and Boreal Ecosystems over Western Canada and Alaska Inferred from Dense Landsat Time Series

NASA Astrophysics Data System (ADS)

Wang, J.; Sulla-menashe, D. J.; Woodcock, C. E.; Sonnentag, O.; Friedl, M. A.

2017-12-01

Rapid climate change in arctic and boreal ecosystems is driving changes to land cover composition, including woody expansion in the arctic tundra, successional shifts following boreal fires, and thaw-induced wetland expansion and forest collapse along the southern limit of permafrost. The impacts of these land cover transformations on the physical climate and the carbon cycle are increasingly well-documented from field and model studies, but there have been few attempts to empirically estimate rates of land cover change at decadal time scale and continental spatial scale. Previous studies have used too coarse spatial resolution or have been too limited in temporal range to enable broad multi-decadal assessment of land cover change. As part of NASA's Arctic Boreal Vulnerability Experiment (ABoVE), we are using dense time series of Landsat remote sensing data to map disturbances and classify land cover types across the ABoVE extended domain (spanning western Canada and Alaska) over the last three decades (1982-2014) at 30 m resolution. We utilize regionally-complete and repeated acquisition high-resolution (<2 m) DigitalGlobe imagery to generate training data from across the region that follows a nested, hierarchical classification scheme encompassing plant functional type and cover density, understory type, wetland status, and land use. Additionally, we crosswalk plot-level field data into our scheme for additional high quality training sites. We use the Continuous Change Detection and Classification algorithm to estimate land cover change dates and temporal-spectral features in the Landsat data. These features are used to train random forest classification models and map land cover and analyze land cover change processes, focusing primarily on tundra "shrubification", post-fire succession, and boreal wetland expansion. We will analyze the high resolution data based on stratified random sampling of our change maps to validate and assess the accuracy of our model predictions. In this paper, we present initial results from this effort, including sub-regional analyses focused on several key areas, such as the Taiga Plains and the Southern Arctic ecozones, to calibrate our random forest models and assess results.

Predicting membrane protein types using various decision tree classifiers based on various modes of general PseAAC for imbalanced datasets.

PubMed

Sankari, E Siva; Manimegalai, D

2017-12-21

Predicting membrane protein types is an important and challenging research area in bioinformatics and proteomics. Traditional biophysical methods are used to classify membrane protein types. Due to large exploration of uncharacterized protein sequences in databases, traditional methods are very time consuming, expensive and susceptible to errors. Hence, it is highly desirable to develop a robust, reliable, and efficient method to predict membrane protein types. Imbalanced datasets and large datasets are often handled well by decision tree classifiers. Since imbalanced datasets are taken, the performance of various decision tree classifiers such as Decision Tree (DT), Classification And Regression Tree (CART), C4.5, Random tree, REP (Reduced Error Pruning) tree, ensemble methods such as Adaboost, RUS (Random Under Sampling) boost, Rotation forest and Random forest are analysed. Among the various decision tree classifiers Random forest performs well in less time with good accuracy of 96.35%. Another inference is RUS boost decision tree classifier is able to classify one or two samples in the class with very less samples while the other classifiers such as DT, Adaboost, Rotation forest and Random forest are not sensitive for the classes with fewer samples. Also the performance of decision tree classifiers is compared with SVM (Support Vector Machine) and Naive Bayes classifier. Copyright © 2017 Elsevier Ltd. All rights reserved.

Identification by random forest method of HLA class I amino acid substitutions associated with lower survival at day 100 in unrelated donor hematopoietic cell transplantation.

PubMed

Marino, S R; Lin, S; Maiers, M; Haagenson, M; Spellman, S; Klein, J P; Binkowski, T A; Lee, S J; van Besien, K

2012-02-01

The identification of important amino acid substitutions associated with low survival in hematopoietic cell transplantation (HCT) is hampered by the large number of observed substitutions compared with the small number of patients available for analysis. Random forest analysis is designed to address these limitations. We studied 2107 HCT recipients with good or intermediate risk hematological malignancies to identify HLA class I amino acid substitutions associated with reduced survival at day 100 post transplant. Random forest analysis and traditional univariate and multivariate analyses were used. Random forest analysis identified amino acid substitutions in 33 positions that were associated with reduced 100 day survival, including HLA-A 9, 43, 62, 63, 76, 77, 95, 97, 114, 116, 152, 156, 166 and 167; HLA-B 97, 109, 116 and 156; and HLA-C 6, 9, 11, 14, 21, 66, 77, 80, 95, 97, 99, 116, 156, 163 and 173. In all 13 had been previously reported by other investigators using classical biostatistical approaches. Using the same data set, traditional multivariate logistic regression identified only five amino acid substitutions associated with lower day 100 survival. Random forest analysis is a novel statistical methodology for analysis of HLA mismatching and outcome studies, capable of identifying important amino acid substitutions missed by other methods.

MANUSCRIPT IN PRESS: DEMENTIA & GERIATRIC COGNITIVE DISORDERS

PubMed Central

O’Bryant, Sid E.; Xiao, Guanghua; Barber, Robert; Cullum, C. Munro; Weiner, Myron; Hall, James; Edwards, Melissa; Grammas, Paula; Wilhelmsen, Kirk; Doody, Rachelle; Diaz-Arrastia, Ramon

2015-01-01

Background Prior work on the link between blood-based biomarkers and cognitive status has largely been based on dichotomous classifications rather than detailed neuropsychological functioning. The current project was designed to create serum-based biomarker algorithms that predict neuropsychological test performance. Methods A battery of neuropsychological measures was administered. Random forest analyses were utilized to create neuropsychological test-specific biomarker risk scores in a training set that were entered into linear regression models predicting the respective test scores in the test set. Serum multiplex biomarker data were analyzed on 108 proteins from 395 participants (197 AD cases and 198 controls) from the Texas Alzheimer’s Research and Care Consortium. Results The biomarker risk scores were significant predictors (p<0.05) of scores on all neuropsychological tests. With the exception of premorbid intellectual status (6.6%), the biomarker risk scores alone accounted for a minimum of 12.9% of the variance in neuropsychological scores. Biomarker algorithms (biomarker risk scores + demographics) accounted for substantially more variance in scores. Review of the variable importance plots indicated differential patterns of biomarker significance for each test, suggesting the possibility of domain-specific biomarker algorithms. Conclusions Our findings provide proof-of-concept for a novel area of scientific discovery, which we term “molecular neuropsychology.” PMID:24107792

Detection of Periodic Leg Movements by Machine Learning Methods Using Polysomnographic Parameters Other Than Leg Electromyography

PubMed Central

Umut, İlhan; Çentik, Güven

2016-01-01

The number of channels used for polysomnographic recording frequently causes difficulties for patients because of the many cables connected. Also, it increases the risk of having troubles during recording process and increases the storage volume. In this study, it is intended to detect periodic leg movement (PLM) in sleep with the use of the channels except leg electromyography (EMG) by analysing polysomnography (PSG) data with digital signal processing (DSP) and machine learning methods. PSG records of 153 patients of different ages and genders with PLM disorder diagnosis were examined retrospectively. A novel software was developed for the analysis of PSG records. The software utilizes the machine learning algorithms, statistical methods, and DSP methods. In order to classify PLM, popular machine learning methods (multilayer perceptron, K-nearest neighbour, and random forests) and logistic regression were used. Comparison of classified results showed that while K-nearest neighbour classification algorithm had higher average classification rate (91.87%) and lower average classification error value (RMSE = 0.2850), multilayer perceptron algorithm had the lowest average classification rate (83.29%) and the highest average classification error value (RMSE = 0.3705). Results showed that PLM can be classified with high accuracy (91.87%) without leg EMG record being present. PMID:27213008

Detection of Periodic Leg Movements by Machine Learning Methods Using Polysomnographic Parameters Other Than Leg Electromyography.

PubMed

Umut, İlhan; Çentik, Güven

2016-01-01

The number of channels used for polysomnographic recording frequently causes difficulties for patients because of the many cables connected. Also, it increases the risk of having troubles during recording process and increases the storage volume. In this study, it is intended to detect periodic leg movement (PLM) in sleep with the use of the channels except leg electromyography (EMG) by analysing polysomnography (PSG) data with digital signal processing (DSP) and machine learning methods. PSG records of 153 patients of different ages and genders with PLM disorder diagnosis were examined retrospectively. A novel software was developed for the analysis of PSG records. The software utilizes the machine learning algorithms, statistical methods, and DSP methods. In order to classify PLM, popular machine learning methods (multilayer perceptron, K-nearest neighbour, and random forests) and logistic regression were used. Comparison of classified results showed that while K-nearest neighbour classification algorithm had higher average classification rate (91.87%) and lower average classification error value (RMSE = 0.2850), multilayer perceptron algorithm had the lowest average classification rate (83.29%) and the highest average classification error value (RMSE = 0.3705). Results showed that PLM can be classified with high accuracy (91.87%) without leg EMG record being present.

Missouri Ozark Forest Ecosystem Project: the experiment

Treesearch

Steven L. Sheriff

2002-01-01

Missouri Ozark Forest Ecosystem Project (MOFEP) is a unique experiment to learn about the impacts of management practices on a forest system. Three forest management practices (uneven-aged management, even-aged management, and no-harvest management) as practiced by the Missouri Department of Conservation were randomly assigned to nine forest management sites using a...

Resampling procedures to identify important SNPs using a consensus approach.

PubMed

Pardy, Christopher; Motyer, Allan; Wilson, Susan

2011-11-29

Our goal is to identify common single-nucleotide polymorphisms (SNPs) (minor allele frequency > 1%) that add predictive accuracy above that gained by knowledge of easily measured clinical variables. We take an algorithmic approach to predict each phenotypic variable using a combination of phenotypic and genotypic predictors. We perform our procedure on the first simulated replicate and then validate against the others. Our procedure performs well when predicting Q1 but is less successful for the other outcomes. We use resampling procedures where possible to guard against false positives and to improve generalizability. The approach is based on finding a consensus regarding important SNPs by applying random forests and the least absolute shrinkage and selection operator (LASSO) on multiple subsamples. Random forests are used first to discard unimportant predictors, narrowing our focus to roughly 100 important SNPs. A cross-validation LASSO is then used to further select variables. We combine these procedures to guarantee that cross-validation can be used to choose a shrinkage parameter for the LASSO. If the clinical variables were unavailable, this prefiltering step would be essential. We perform the SNP-based analyses simultaneously rather than one at a time to estimate SNP effects in the presence of other causal variants. We analyzed the first simulated replicate of Genetic Analysis Workshop 17 without knowledge of the true model. Post-conference knowledge of the simulation parameters allowed us to investigate the limitations of our approach. We found that many of the false positives we identified were substantially correlated with genuine causal SNPs.

Predicting Long-Term Cognitive Outcome Following Breast Cancer with Pre-Treatment Resting State fMRI and Random Forest Machine Learning.

PubMed

Kesler, Shelli R; Rao, Arvind; Blayney, Douglas W; Oakley-Girvan, Ingrid A; Karuturi, Meghan; Palesh, Oxana

2017-01-01

We aimed to determine if resting state functional magnetic resonance imaging (fMRI) acquired at pre-treatment baseline could accurately predict breast cancer-related cognitive impairment at long-term follow-up. We evaluated 31 patients with breast cancer (age 34-65) prior to any treatment, post-chemotherapy and 1 year later. Cognitive testing scores were normalized based on data obtained from 43 healthy female controls and then used to categorize patients as impaired or not based on longitudinal changes. We measured clustering coefficient, a measure of local connectivity, by applying graph theory to baseline resting state fMRI and entered these metrics along with relevant patient-related and medical variables into random forest classification. Incidence of cognitive impairment at 1 year follow-up was 55% and was predicted by classification algorithms with up to 100% accuracy ( p < 0.0001). The neuroimaging-based model was significantly more accurate than a model involving patient-related and medical variables ( p = 0.005). Hub regions belonging to several distinct functional networks were the most important predictors of cognitive outcome. Characteristics of these hubs indicated potential spread of brain injury from default mode to other networks over time. These findings suggest that resting state fMRI is a promising tool for predicting future cognitive impairment associated with breast cancer. This information could inform treatment decision making by identifying patients at highest risk for long-term cognitive impairment.

Predicting Long-Term Cognitive Outcome Following Breast Cancer with Pre-Treatment Resting State fMRI and Random Forest Machine Learning

PubMed Central

Kesler, Shelli R.; Rao, Arvind; Blayney, Douglas W.; Oakley-Girvan, Ingrid A.; Karuturi, Meghan; Palesh, Oxana

2017-01-01

We aimed to determine if resting state functional magnetic resonance imaging (fMRI) acquired at pre-treatment baseline could accurately predict breast cancer-related cognitive impairment at long-term follow-up. We evaluated 31 patients with breast cancer (age 34–65) prior to any treatment, post-chemotherapy and 1 year later. Cognitive testing scores were normalized based on data obtained from 43 healthy female controls and then used to categorize patients as impaired or not based on longitudinal changes. We measured clustering coefficient, a measure of local connectivity, by applying graph theory to baseline resting state fMRI and entered these metrics along with relevant patient-related and medical variables into random forest classification. Incidence of cognitive impairment at 1 year follow-up was 55% and was predicted by classification algorithms with up to 100% accuracy (p < 0.0001). The neuroimaging-based model was significantly more accurate than a model involving patient-related and medical variables (p = 0.005). Hub regions belonging to several distinct functional networks were the most important predictors of cognitive outcome. Characteristics of these hubs indicated potential spread of brain injury from default mode to other networks over time. These findings suggest that resting state fMRI is a promising tool for predicting future cognitive impairment associated with breast cancer. This information could inform treatment decision making by identifying patients at highest risk for long-term cognitive impairment. PMID:29187817

Discrimination of raw and processed Dipsacus asperoides by near infrared spectroscopy combined with least squares-support vector machine and random forests

NASA Astrophysics Data System (ADS)

Xin, Ni; Gu, Xiao-Feng; Wu, Hao; Hu, Yu-Zhu; Yang, Zhong-Lin

2012-04-01

Most herbal medicines could be processed to fulfill the different requirements of therapy. The purpose of this study was to discriminate between raw and processed Dipsacus asperoides, a common traditional Chinese medicine, based on their near infrared (NIR) spectra. Least squares-support vector machine (LS-SVM) and random forests (RF) were employed for full-spectrum classification. Three types of kernels, including linear kernel, polynomial kernel and radial basis function kernel (RBF), were checked for optimization of LS-SVM model. For comparison, a linear discriminant analysis (LDA) model was performed for classification, and the successive projections algorithm (SPA) was executed prior to building an LDA model to choose an appropriate subset of wavelengths. The three methods were applied to a dataset containing 40 raw herbs and 40 corresponding processed herbs. We ran 50 runs of 10-fold cross validation to evaluate the model's efficiency. The performance of the LS-SVM with RBF kernel (RBF LS-SVM) was better than the other two kernels. The RF, RBF LS-SVM and SPA-LDA successfully classified all test samples. The mean error rates for the 50 runs of 10-fold cross validation were 1.35% for RBF LS-SVM, 2.87% for RF, and 2.50% for SPA-LDA. The best classification results were obtained by using LS-SVM with RBF kernel, while RF was fast in the training and making predictions.

Local receptive field constrained stacked sparse autoencoder for classification of hyperspectral images.

PubMed

Wan, Xiaoqing; Zhao, Chunhui

2017-06-01

As a competitive machine learning algorithm, the stacked sparse autoencoder (SSA) has achieved outstanding popularity in exploiting high-level features for classification of hyperspectral images (HSIs). In general, in the SSA architecture, the nodes between adjacent layers are fully connected and need to be iteratively fine-tuned during the pretraining stage; however, the nodes of previous layers further away may be less likely to have a dense correlation to the given node of subsequent layers. Therefore, to reduce the classification error and increase the learning rate, this paper proposes the general framework of locally connected SSA; that is, the biologically inspired local receptive field (LRF) constrained SSA architecture is employed to simultaneously characterize the local correlations of spectral features and extract high-level feature representations of hyperspectral data. In addition, the appropriate receptive field constraint is concurrently updated by measuring the spatial distances from the neighbor nodes to the corresponding node. Finally, the efficient random forest classifier is cascaded to the last hidden layer of the SSA architecture as a benchmark classifier. Experimental results on two real HSI datasets demonstrate that the proposed hierarchical LRF constrained stacked sparse autoencoder and random forest (SSARF) provides encouraging results with respect to other contrastive methods, for instance, the improvements of overall accuracy in a range of 0.72%-10.87% for the Indian Pines dataset and 0.74%-7.90% for the Kennedy Space Center dataset; moreover, it generates lower running time compared with the result provided by similar SSARF based methodology.

CNV-RF Is a Random Forest-Based Copy Number Variation Detection Method Using Next-Generation Sequencing.

PubMed

Onsongo, Getiria; Baughn, Linda B; Bower, Matthew; Henzler, Christine; Schomaker, Matthew; Silverstein, Kevin A T; Thyagarajan, Bharat

2016-11-01

Simultaneous detection of small copy number variations (CNVs) (<0.5 kb) and single-nucleotide variants in clinically significant genes is of great interest for clinical laboratories. The analytical variability in next-generation sequencing (NGS) and artifacts in coverage data because of issues with mappability along with lack of robust bioinformatics tools for CNV detection have limited the utility of targeted NGS data to identify CNVs. We describe the development and implementation of a bioinformatics algorithm, copy number variation-random forest (CNV-RF), that incorporates a machine learning component to identify CNVs from targeted NGS data. Using CNV-RF, we identified 12 of 13 deletions in samples with known CNVs, two cases with duplications, and identified novel deletions in 22 additional cases. Furthermore, no CNVs were identified among 60 genes in 14 cases with normal copy number and no CNVs were identified in another 104 patients with clinical suspicion of CNVs. All positive deletions and duplications were confirmed using a quantitative PCR method. CNV-RF also detected heterozygous deletions and duplications with a specificity of 50% across 4813 genes. The ability of CNV-RF to detect clinically relevant CNVs with a high degree of sensitivity along with confirmation using a low-cost quantitative PCR method provides a framework for providing comprehensive NGS-based CNV/single-nucleotide variant detection in a clinical molecular diagnostics laboratory. Copyright © 2016 American Society for Investigative Pathology and the Association for Molecular Pathology. Published by Elsevier Inc. All rights reserved.

GIS-based groundwater potential mapping using boosted regression tree, classification and regression tree, and random forest machine learning models in Iran.

PubMed

Naghibi, Seyed Amir; Pourghasemi, Hamid Reza; Dixon, Barnali

2016-01-01

Groundwater is considered one of the most valuable fresh water resources. The main objective of this study was to produce groundwater spring potential maps in the Koohrang Watershed, Chaharmahal-e-Bakhtiari Province, Iran, using three machine learning models: boosted regression tree (BRT), classification and regression tree (CART), and random forest (RF). Thirteen hydrological-geological-physiographical (HGP) factors that influence locations of springs were considered in this research. These factors include slope degree, slope aspect, altitude, topographic wetness index (TWI), slope length (LS), plan curvature, profile curvature, distance to rivers, distance to faults, lithology, land use, drainage density, and fault density. Subsequently, groundwater spring potential was modeled and mapped using CART, RF, and BRT algorithms. The predicted results from the three models were validated using the receiver operating characteristics curve (ROC). From 864 springs identified, 605 (≈70 %) locations were used for the spring potential mapping, while the remaining 259 (≈30 %) springs were used for the model validation. The area under the curve (AUC) for the BRT model was calculated as 0.8103 and for CART and RF the AUC were 0.7870 and 0.7119, respectively. Therefore, it was concluded that the BRT model produced the best prediction results while predicting locations of springs followed by CART and RF models, respectively. Geospatially integrated BRT, CART, and RF methods proved to be useful in generating the spring potential map (SPM) with reasonable accuracy.

Machine learning to predict the occurrence of bisphosphonate-related osteonecrosis of the jaw associated with dental extraction: A preliminary report.

PubMed

Kim, Dong Wook; Kim, Hwiyoung; Nam, Woong; Kim, Hyung Jun; Cha, In-Ho

2018-04-23

The aim of this study was to build and validate five types of machine learning models that can predict the occurrence of BRONJ associated with dental extraction in patients taking bisphosphonates for the management of osteoporosis. A retrospective review of the medical records was conducted to obtain cases and controls for the study. Total 125 patients consisting of 41 cases and 84 controls were selected for the study. Five machine learning prediction algorithms including multivariable logistic regression model, decision tree, support vector machine, artificial neural network, and random forest were implemented. The outputs of these models were compared with each other and also with conventional methods, such as serum CTX level. Area under the receiver operating characteristic (ROC) curve (AUC) was used to compare the results. The performance of machine learning models was significantly superior to conventional statistical methods and single predictors. The random forest model yielded the best performance (AUC = 0.973), followed by artificial neural network (AUC = 0.915), support vector machine (AUC = 0.882), logistic regression (AUC = 0.844), decision tree (AUC = 0.821), drug holiday alone (AUC = 0.810), and CTX level alone (AUC = 0.630). Machine learning methods showed superior performance in predicting BRONJ associated with dental extraction compared to conventional statistical methods using drug holiday and serum CTX level. Machine learning can thus be applied in a wide range of clinical studies. Copyright © 2017. Published by Elsevier Inc.

Estimation of Carbon Flux of Forest Ecosystem over Qilian Mountains by BIOME-BGC Model

NASA Astrophysics Data System (ADS)

Yan, Min; Tian, Xin; Li, Zengyuan; Chen, Erxue; Li, Chunmei

2014-11-01

The gross primary production (GPP) and net ecosystem exchange (NEE) are important indicators for carbon fluxes. This study aims at evaluating the forest GPP and NEE over the Qilian Mountains using meteorological, remotely sensed and other ancillary data at large scale. To realize this, the widely used ecological-process-based model, Biome-BGC, and remote-sensing-based model, MODIS GPP algorithm, were selected for the simulation of the forest carbon fluxes. The combination of these two models was based on calibrating the Biome-BGC by the optimized MODIS GPP algorithm. The simulated GPP and NEE values were evaluated against the eddy covariance observed GPPs and NEEs, and the well agreements have been reached, with R2=0.76, 0.67 respectively.

Estimation of Carbon Flux of Forest Ecosystem over Qilian Mountains by BIOME-BGC Model

NASA Astrophysics Data System (ADS)

Yan, Min; Tian, Xin; Li, Zengyuan; Chen, Erxue; Li, Chunmei

2014-11-01

The gross primary production (GPP) and net ecosystem exchange (NEE) are important indicators for carbon fluxes. This study aims at evaluating the forest GPP and NEE over the Qilian Mountains using meteorological, remotely sensed and other ancillary data at large scale. To realize this, the widely used ecological-process- based model, Biome-BGC, and remote-sensing-based model, MODIS GPP algorithm, were selected for the simulation of the forest carbon fluxes. The combination of these two models was based on calibrating the Biome-BGC by the optimized MODIS GPP algorithm. The simulated GPP and NEE values were evaluated against the eddy covariance observed GPPs and NEEs, and the well agreements have been reached, with R2=0.76, 0.67 respectively.

Mapping Canopy Damage from Understory Fires in Amazon Forests Using Annual Time Series of Landsat and MODIS Data

NASA Technical Reports Server (NTRS)

Morton, Douglas C.; DeFries, Ruth S.; Nagol, Jyoteshwar; Souza, Carlos M., Jr.; Kasischke, Eric S.; Hurtt, George C.; Dubayah, Ralph

2011-01-01

Understory fires in Amazon forests alter forest structure, species composition, and the likelihood of future disturbance. The annual extent of fire-damaged forest in Amazonia remains uncertain due to difficulties in separating burning from other types of forest damage in satellite data. We developed a new approach, the Burn Damage and Recovery (BDR) algorithm, to identify fire-related canopy damages using spatial and spectral information from multi-year time series of satellite data. The BDR approach identifies understory fires in intact and logged Amazon forests based on the reduction and recovery of live canopy cover in the years following fire damages and the size and shape of individual understory burn scars. The BDR algorithm was applied to time series of Landsat (1997-2004) and MODIS (2000-2005) data covering one Landsat scene (path/row 226/068) in southern Amazonia and the results were compared to field observations, image-derived burn scars, and independent data on selective logging and deforestation. Landsat resolution was essential for detection of burn scars less than 50 ha, yet these small burns contributed only 12% of all burned forest detected during 1997-2002. MODIS data were suitable for mapping medium (50-500 ha) and large (greater than 500 ha) burn scars that accounted for the majority of all fire-damaged forest in this study. Therefore, moderate resolution satellite data may be suitable to provide estimates of the extent of fire-damaged Amazon forest at a regional scale. In the study region, Landsat-based understory fire damages in 1999 (1508 square kilometers) were an order of magnitude higher than during the 1997-1998 El Nino event (124 square kilometers and 39 square kilometers, respectively), suggesting a different link between climate and understory fires than previously reported for other Amazon regions. The results in this study illustrate the potential to address critical questions concerning climate and fire risk in Amazon forests by applying the BDR algorithm over larger areas and longer image time series.

Variable selection with random forest: Balancing stability, performance, and interpretation in ecological and environmental modeling

EPA Science Inventory

Random forest (RF) is popular in ecological and environmental modeling, in part, because of its insensitivity to correlated predictors and resistance to overfitting. Although variable selection has been proposed to improve both performance and interpretation of RF models, it is u...

Random Forests for Evaluating Pedagogy and Informing Personalized Learning

ERIC Educational Resources Information Center

Spoon, Kelly; Beemer, Joshua; Whitmer, John C.; Fan, Juanjuan; Frazee, James P.; Stronach, Jeanne; Bohonak, Andrew J.; Levine, Richard A.

2016-01-01

Random forests are presented as an analytics foundation for educational data mining tasks. The focus is on course- and program-level analytics including evaluating pedagogical approaches and interventions and identifying and characterizing at-risk students. As part of this development, the concept of individualized treatment effects (ITE) is…

Laser-Induced Breakdown Spectroscopy for Rapid Discrimination of Heavy-Metal-Contaminated Seafood Tegillarca granosa

PubMed Central

Ji, Guoli; Ye, Pengchao; Shi, Yijian; Yuan, Leiming; Chen, Xiaojing; Yuan, Mingshun; Zhu, Dehua; Chen, Xi; Hu, Xinyu; Jiang, Jing

2017-01-01

Tegillarca granosa samples contaminated artificially by three kinds of toxic heavy metals including zinc (Zn), cadmium (Cd), and lead (Pb) were attempted to be distinguished using laser-induced breakdown spectroscopy (LIBS) technology and pattern recognition methods in this study. The measured spectra were firstly processed by a wavelet transform algorithm (WTA), then the generated characteristic information was subsequently expressed by an information gain algorithm (IGA). As a result, 30 variables obtained were used as input variables for three classifiers: partial least square discriminant analysis (PLS-DA), support vector machine (SVM), and random forest (RF), among which the RF model exhibited the best performance, with 93.3% discrimination accuracy among those classifiers. Besides, the extracted characteristic information was used to reconstruct the original spectra by inverse WTA, and the corresponding attribution of the reconstructed spectra was then discussed. This work indicates that the healthy shellfish samples of Tegillarca granosa could be distinguished from the toxic heavy-metal-contaminated ones by pattern recognition analysis combined with LIBS technology, which only requires minimal pretreatments. PMID:29149053

Learning Traffic as Images: A Deep Convolutional Neural Network for Large-Scale Transportation Network Speed Prediction.

PubMed

Ma, Xiaolei; Dai, Zhuang; He, Zhengbing; Ma, Jihui; Wang, Yong; Wang, Yunpeng

2017-04-10

This paper proposes a convolutional neural network (CNN)-based method that learns traffic as images and predicts large-scale, network-wide traffic speed with a high accuracy. Spatiotemporal traffic dynamics are converted to images describing the time and space relations of traffic flow via a two-dimensional time-space matrix. A CNN is applied to the image following two consecutive steps: abstract traffic feature extraction and network-wide traffic speed prediction. The effectiveness of the proposed method is evaluated by taking two real-world transportation networks, the second ring road and north-east transportation network in Beijing, as examples, and comparing the method with four prevailing algorithms, namely, ordinary least squares, k-nearest neighbors, artificial neural network, and random forest, and three deep learning architectures, namely, stacked autoencoder, recurrent neural network, and long-short-term memory network. The results show that the proposed method outperforms other algorithms by an average accuracy improvement of 42.91% within an acceptable execution time. The CNN can train the model in a reasonable time and, thus, is suitable for large-scale transportation networks.

Automatic analysis of diabetic peripheral neuropathy using multi-scale quantitative morphology of nerve fibres in corneal confocal microscopy imaging.

PubMed

Dabbah, M A; Graham, J; Petropoulos, I N; Tavakoli, M; Malik, R A

2011-10-01

Diabetic peripheral neuropathy (DPN) is one of the most common long term complications of diabetes. Corneal confocal microscopy (CCM) image analysis is a novel non-invasive technique which quantifies corneal nerve fibre damage and enables diagnosis of DPN. This paper presents an automatic analysis and classification system for detecting nerve fibres in CCM images based on a multi-scale adaptive dual-model detection algorithm. The algorithm exploits the curvilinear structure of the nerve fibres and adapts itself to the local image information. Detected nerve fibres are then quantified and used as feature vectors for classification using random forest (RF) and neural networks (NNT) classifiers. We show, in a comparative study with other well known curvilinear detectors, that the best performance is achieved by the multi-scale dual model in conjunction with the NNT classifier. An evaluation of clinical effectiveness shows that the performance of the automated system matches that of ground-truth defined by expert manual annotation. Copyright © 2011 Elsevier B.V. All rights reserved.

Combining Benford's Law and machine learning to detect money laundering. An actual Spanish court case.

PubMed

Badal-Valero, Elena; Alvarez-Jareño, José A; Pavía, Jose M

2018-01-01

This paper is based on the analysis of the database of operations from a macro-case on money laundering orchestrated between a core company and a group of its suppliers, 26 of which had already been identified by the police as fraudulent companies. In the face of a well-founded suspicion that more companies have perpetrated criminal acts and in order to make better use of what are very limited police resources, we aim to construct a tool to detect money laundering criminals. We combine Benford's Law and machine learning algorithms (logistic regression, decision trees, neural networks, and random forests) to find patterns of money laundering criminals in the context of a real Spanish court case. After mapping each supplier's set of accounting data into a 21-dimensional space using Benford's Law and applying machine learning algorithms, additional companies that could merit further scrutiny are flagged up. A new tool to detect money laundering criminals is proposed in this paper. The tool is tested in the context of a real case. Copyright © 2017 Elsevier B.V. All rights reserved.

Semi-supervised prediction of gene regulatory networks using machine learning algorithms.

PubMed

Patel, Nihir; Wang, Jason T L

2015-10-01

Use of computational methods to predict gene regulatory networks (GRNs) from gene expression data is a challenging task. Many studies have been conducted using unsupervised methods to fulfill the task; however, such methods usually yield low prediction accuracies due to the lack of training data. In this article, we propose semi-supervised methods for GRN prediction by utilizing two machine learning algorithms, namely, support vector machines (SVM) and random forests (RF). The semi-supervised methods make use of unlabelled data for training. We investigated inductive and transductive learning approaches, both of which adopt an iterative procedure to obtain reliable negative training data from the unlabelled data. We then applied our semi-supervised methods to gene expression data of Escherichia coli and Saccharomyces cerevisiae, and evaluated the performance of our methods using the expression data. Our analysis indicated that the transductive learning approach outperformed the inductive learning approach for both organisms. However, there was no conclusive difference identified in the performance of SVM and RF. Experimental results also showed that the proposed semi-supervised methods performed better than existing supervised methods for both organisms.

Learning Traffic as Images: A Deep Convolutional Neural Network for Large-Scale Transportation Network Speed Prediction

PubMed Central

Ma, Xiaolei; Dai, Zhuang; He, Zhengbing; Ma, Jihui; Wang, Yong; Wang, Yunpeng

2017-01-01

This paper proposes a convolutional neural network (CNN)-based method that learns traffic as images and predicts large-scale, network-wide traffic speed with a high accuracy. Spatiotemporal traffic dynamics are converted to images describing the time and space relations of traffic flow via a two-dimensional time-space matrix. A CNN is applied to the image following two consecutive steps: abstract traffic feature extraction and network-wide traffic speed prediction. The effectiveness of the proposed method is evaluated by taking two real-world transportation networks, the second ring road and north-east transportation network in Beijing, as examples, and comparing the method with four prevailing algorithms, namely, ordinary least squares, k-nearest neighbors, artificial neural network, and random forest, and three deep learning architectures, namely, stacked autoencoder, recurrent neural network, and long-short-term memory network. The results show that the proposed method outperforms other algorithms by an average accuracy improvement of 42.91% within an acceptable execution time. The CNN can train the model in a reasonable time and, thus, is suitable for large-scale transportation networks. PMID:28394270

Developing a radiomics framework for classifying non-small cell lung carcinoma subtypes

NASA Astrophysics Data System (ADS)

Yu, Dongdong; Zang, Yali; Dong, Di; Zhou, Mu; Gevaert, Olivier; Fang, Mengjie; Shi, Jingyun; Tian, Jie

2017-03-01

Patient-targeted treatment of non-small cell lung carcinoma (NSCLC) has been well documented according to the histologic subtypes over the past decade. In parallel, recent development of quantitative image biomarkers has recently been highlighted as important diagnostic tools to facilitate histological subtype classification. In this study, we present a radiomics analysis that classifies the adenocarcinoma (ADC) and squamous cell carcinoma (SqCC). We extract 52-dimensional, CT-based features (7 statistical features and 45 image texture features) to represent each nodule. We evaluate our approach on a clinical dataset including 324 ADCs and 110 SqCCs patients with CT image scans. Classification of these features is performed with four different machine-learning classifiers including Support Vector Machines with Radial Basis Function kernel (RBF-SVM), Random forest (RF), K-nearest neighbor (KNN), and RUSBoost algorithms. To improve the classifiers' performance, optimal feature subset is selected from the original feature set by using an iterative forward inclusion and backward eliminating algorithm. Extensive experimental results demonstrate that radiomics features achieve encouraging classification results on both complete feature set (AUC=0.89) and optimal feature subset (AUC=0.91).

On factoring RSA modulus using random-restart hill-climbing algorithm and Pollard’s rho algorithm

NASA Astrophysics Data System (ADS)

Budiman, M. A.; Rachmawati, D.

2017-12-01

The security of the widely-used RSA public key cryptography algorithm depends on the difficulty of factoring a big integer into two large prime numbers. For many years, the integer factorization problem has been intensively and extensively studied in the field of number theory. As a result, a lot of deterministic algorithms such as Euler’s algorithm, Kraitchik’s, and variants of Pollard’s algorithms have been researched comprehensively. Our study takes a rather uncommon approach: rather than making use of intensive number theories, we attempt to factorize RSA modulus n by using random-restart hill-climbing algorithm, which belongs the class of metaheuristic algorithms. The factorization time of RSA moduli with different lengths is recorded and compared with the factorization time of Pollard’s rho algorithm, which is a deterministic algorithm. Our experimental results indicates that while random-restart hill-climbing algorithm is an acceptable candidate to factorize smaller RSA moduli, the factorization speed is much slower than that of Pollard’s rho algorithm.

A machine learning-based framework to identify type 2 diabetes through electronic health records

PubMed Central

Zheng, Tao; Xie, Wei; Xu, Liling; He, Xiaoying; Zhang, Ya; You, Mingrong; Yang, Gong; Chen, You

2016-01-01

Objective To discover diverse genotype-phenotype associations affiliated with Type 2 Diabetes Mellitus (T2DM) via genome-wide association study (GWAS) and phenome-wide association study (PheWAS), more cases (T2DM subjects) and controls (subjects without T2DM) are required to be identified (e.g., via Electronic Health Records (EHR)). However, existing expert based identification algorithms often suffer in a low recall rate and could miss a large number of valuable samples under conservative filtering standards. The goal of this work is to develop a semi-automated framework based on machine learning as a pilot study to liberalize filtering criteria to improve recall rate with a keeping of low false positive rate. Materials and methods We propose a data informed framework for identifying subjects with and without T2DM from EHR via feature engineering and machine learning. We evaluate and contrast the identification performance of widely-used machine learning models within our framework, including k-Nearest-Neighbors, Naïve Bayes, Decision Tree, Random Forest, Support Vector Machine and Logistic Regression. Our framework was conducted on 300 patient samples (161 cases, 60 controls and 79 unconfirmed subjects), randomly selected from 23,281 diabetes related cohort retrieved from a regional distributed EHR repository ranging from 2012 to 2014. Results We apply top-performing machine learning algorithms on the engineered features. We benchmark and contrast the accuracy, precision, AUC, sensitivity and specificity of classification models against the state-of-the-art expert algorithm for identification of T2DM subjects. Our results indicate that the framework achieved high identification performances (∼0.98 in average AUC), which are much higher than the state-of-the-art algorithm (0.71 in AUC). Discussion Expert algorithm-based identification of T2DM subjects from EHR is often hampered by the high missing rates due to their conservative selection criteria. Our framework leverages machine learning and feature engineering to loosen such selection criteria to achieve a high identification rate of cases and controls. Conclusions Our proposed framework demonstrates a more accurate and efficient approach for identifying subjects with and without T2DM from EHR. PMID:27919371

A machine learning-based framework to identify type 2 diabetes through electronic health records.

PubMed

Zheng, Tao; Xie, Wei; Xu, Liling; He, Xiaoying; Zhang, Ya; You, Mingrong; Yang, Gong; Chen, You

2017-01-01

To discover diverse genotype-phenotype associations affiliated with Type 2 Diabetes Mellitus (T2DM) via genome-wide association study (GWAS) and phenome-wide association study (PheWAS), more cases (T2DM subjects) and controls (subjects without T2DM) are required to be identified (e.g., via Electronic Health Records (EHR)). However, existing expert based identification algorithms often suffer in a low recall rate and could miss a large number of valuable samples under conservative filtering standards. The goal of this work is to develop a semi-automated framework based on machine learning as a pilot study to liberalize filtering criteria to improve recall rate with a keeping of low false positive rate. We propose a data informed framework for identifying subjects with and without T2DM from EHR via feature engineering and machine learning. We evaluate and contrast the identification performance of widely-used machine learning models within our framework, including k-Nearest-Neighbors, Naïve Bayes, Decision Tree, Random Forest, Support Vector Machine and Logistic Regression. Our framework was conducted on 300 patient samples (161 cases, 60 controls and 79 unconfirmed subjects), randomly selected from 23,281 diabetes related cohort retrieved from a regional distributed EHR repository ranging from 2012 to 2014. We apply top-performing machine learning algorithms on the engineered features. We benchmark and contrast the accuracy, precision, AUC, sensitivity and specificity of classification models against the state-of-the-art expert algorithm for identification of T2DM subjects. Our results indicate that the framework achieved high identification performances (∼0.98 in average AUC), which are much higher than the state-of-the-art algorithm (0.71 in AUC). Expert algorithm-based identification of T2DM subjects from EHR is often hampered by the high missing rates due to their conservative selection criteria. Our framework leverages machine learning and feature engineering to loosen such selection criteria to achieve a high identification rate of cases and controls. Our proposed framework demonstrates a more accurate and efficient approach for identifying subjects with and without T2DM from EHR. Copyright © 2016 Elsevier Ireland Ltd. All rights reserved.

Old-growth and mature forests near spotted owl nests in western Oregon

NASA Technical Reports Server (NTRS)

Ripple, William J.; Johnson, David H.; Hershey, K. T.; Meslow, E. Charles

1995-01-01

We investigated how the amount of old-growth and mature forest influences the selection of nest sites by northern spotted owls (Strix occidentalis caurina) in the Central Cascade Mountains of Oregon. We used 7 different plot sizes to compare the proportion of mature and old-growth forest between 30 nest sites and 30 random sites. The proportion of old-growth and mature forest was significantly greater at nests sites than at random sites for all plot sizes (P less than or equal to 0.01). Thus, management of the spotted owl might require setting the percentage of old-growth and mature forest retained from harvesting at least 1 standard deviation above the mean for the 30 nest sites we examined.

A two-step nearest neighbors algorithm using satellite imagery for predicting forest structure within species composition classes

Treesearch

Ronald E. McRoberts

2009-01-01

Nearest neighbors techniques have been shown to be useful for predicting multiple forest attributes from forest inventory and Landsat satellite image data. However, in regions lacking good digital land cover information, nearest neighbors selected to predict continuous variables such as tree volume must be selected without regard to relevant categorical variables such...

View Angle Effects on MODIS Snow Mapping in Forests

NASA Technical Reports Server (NTRS)

Xin, Qinchuan; Woodcock, Curtis E.; Liu, Jicheng; Tan, Bin; Melloh, Rae A.; Davis, Robert E.

2012-01-01

Binary snow maps and fractional snow cover data are provided routinely from MODIS (Moderate Resolution Imaging Spectroradiometer). This paper investigates how the wide observation angles of MODIS influence the current snow mapping algorithm in forested areas. Theoretical modeling results indicate that large view zenith angles (VZA) can lead to underestimation of fractional snow cover (FSC) by reducing the amount of the ground surface that is viewable through forest canopies, and by increasing uncertainties during the gridding of MODIS data. At the end of the MODIS scan line, the total modeled error can be as much as 50% for FSC. Empirical analysis of MODIS/Terra snow products in four forest sites shows high fluctuation in FSC estimates on consecutive days. In addition, the normalized difference snow index (NDSI) values, which are the primary input to the MODIS snow mapping algorithms, decrease as VZA increases at the site level. At the pixel level, NDSI values have higher variances, and are correlated with the normalized difference vegetation index (NDVI) in snow covered forests. These findings are consistent with our modeled results, and imply that consideration of view angle effects could improve MODIS snow monitoring in forested areas.

A novel transferable individual tree crown delineation model based on Fishing Net Dragging and boundary classification

NASA Astrophysics Data System (ADS)

Liu, Tao; Im, Jungho; Quackenbush, Lindi J.

2015-12-01

This study provides a novel approach to individual tree crown delineation (ITCD) using airborne Light Detection and Ranging (LiDAR) data in dense natural forests using two main steps: crown boundary refinement based on a proposed Fishing Net Dragging (FiND) method, and segment merging based on boundary classification. FiND starts with approximate tree crown boundaries derived using a traditional watershed method with Gaussian filtering and refines these boundaries using an algorithm that mimics how a fisherman drags a fishing net. Random forest machine learning is then used to classify boundary segments into two classes: boundaries between trees and boundaries between branches that belong to a single tree. Three groups of LiDAR-derived features-two from the pseudo waveform generated along with crown boundaries and one from a canopy height model (CHM)-were used in the classification. The proposed ITCD approach was tested using LiDAR data collected over a mountainous region in the Adirondack Park, NY, USA. Overall accuracy of boundary classification was 82.4%. Features derived from the CHM were generally more important in the classification than the features extracted from the pseudo waveform. A comprehensive accuracy assessment scheme for ITCD was also introduced by considering both area of crown overlap and crown centroids. Accuracy assessment using this new scheme shows the proposed ITCD achieved 74% and 78% as overall accuracy, respectively, for deciduous and mixed forest.

Fast and Robust STEM Reconstruction in Complex Environments Using Terrestrial Laser Scanning

NASA Astrophysics Data System (ADS)

Wang, D.; Hollaus, M.; Puttonen, E.; Pfeifer, N.

2016-06-01

Terrestrial Laser Scanning (TLS) is an effective tool in forest research and management. However, accurate estimation of tree parameters still remains challenging in complex forests. In this paper, we present a novel algorithm for stem modeling in complex environments. This method does not require accurate delineation of stem points from the original point cloud. The stem reconstruction features a self-adaptive cylinder growing scheme. This algorithm is tested for a landslide region in the federal state of Vorarlberg, Austria. The algorithm results are compared with field reference data, which show that our algorithm is able to accurately retrieve the diameter at breast height (DBH) with a root mean square error (RMSE) of ~1.9 cm. This algorithm is further facilitated by applying an advanced sampling technique. Different sampling rates are applied and tested. It is found that a sampling rate of 7.5% is already able to retain the stem fitting quality and simultaneously reduce the computation time significantly by ~88%.

Gaussian Discriminant Analysis for Optimal Delineation of Mild Cognitive Impairment in Alzheimer's Disease.

PubMed

Fang, Chen; Li, Chunfei; Cabrerizo, Mercedes; Barreto, Armando; Andrian, Jean; Rishe, Naphtali; Loewenstein, David; Duara, Ranjan; Adjouadi, Malek

2018-04-12

Over the past few years, several approaches have been proposed to assist in the early diagnosis of Alzheimer's disease (AD) and its prodromal stage of mild cognitive impairment (MCI). Using multimodal biomarkers for this high-dimensional classification problem, the widely used algorithms include Support Vector Machines (SVM), Sparse Representation-based classification (SRC), Deep Belief Networks (DBN) and Random Forest (RF). These widely used algorithms continue to yield unsatisfactory performance for delineating the MCI participants from the cognitively normal control (CN) group. A novel Gaussian discriminant analysis-based algorithm is thus introduced to achieve a more effective and accurate classification performance than the aforementioned state-of-the-art algorithms. This study makes use of magnetic resonance imaging (MRI) data uniquely as input to two separate high-dimensional decision spaces that reflect the structural measures of the two brain hemispheres. The data used include 190 CN, 305 MCI and 133 AD subjects as part of the AD Big Data DREAM Challenge #1. Using 80% data for a 10-fold cross-validation, the proposed algorithm achieved an average F1 score of 95.89% and an accuracy of 96.54% for discriminating AD from CN; and more importantly, an average F1 score of 92.08% and an accuracy of 90.26% for discriminating MCI from CN. Then, a true test was implemented on the remaining 20% held-out test data. For discriminating MCI from CN, an accuracy of 80.61%, a sensitivity of 81.97% and a specificity of 78.38% were obtained. These results show significant improvement over existing algorithms for discriminating the subtle differences between MCI participants and the CN group.

Comparison of machine-learning algorithms to build a predictive model for detecting undiagnosed diabetes - ELSA-Brasil: accuracy study.

PubMed

Olivera, André Rodrigues; Roesler, Valter; Iochpe, Cirano; Schmidt, Maria Inês; Vigo, Álvaro; Barreto, Sandhi Maria; Duncan, Bruce Bartholow

2017-01-01

Type 2 diabetes is a chronic disease associated with a wide range of serious health complications that have a major impact on overall health. The aims here were to develop and validate predictive models for detecting undiagnosed diabetes using data from the Longitudinal Study of Adult Health (ELSA-Brasil) and to compare the performance of different machine-learning algorithms in this task. Comparison of machine-learning algorithms to develop predictive models using data from ELSA-Brasil. After selecting a subset of 27 candidate variables from the literature, models were built and validated in four sequential steps: (i) parameter tuning with tenfold cross-validation, repeated three times; (ii) automatic variable selection using forward selection, a wrapper strategy with four different machine-learning algorithms and tenfold cross-validation (repeated three times), to evaluate each subset of variables; (iii) error estimation of model parameters with tenfold cross-validation, repeated ten times; and (iv) generalization testing on an independent dataset. The models were created with the following machine-learning algorithms: logistic regression, artificial neural network, naïve Bayes, K-nearest neighbor and random forest. The best models were created using artificial neural networks and logistic regression. -These achieved mean areas under the curve of, respectively, 75.24% and 74.98% in the error estimation step and 74.17% and 74.41% in the generalization testing step. Most of the predictive models produced similar results, and demonstrated the feasibility of identifying individuals with highest probability of having undiagnosed diabetes, through easily-obtained clinical data.

Potential for Monitoring Snow Cover in Boreal Forests by Combining MODIS Snow Cover and AMSR-E SWE Maps

NASA Technical Reports Server (NTRS)

Riggs, George A.; Hall, Dorothy K.; Foster, James L.

2009-01-01

Monitoring of snow cover extent and snow water equivalent (SWE) in boreal forests is important for determining the amount of potential runoff and beginning date of snowmelt. The great expanse of the boreal forest necessitates the use of satellite measurements to monitor snow cover. Snow cover in the boreal forest can be mapped with either the Moderate Resolution Imaging Spectroradiometer (MODIS) or the Advanced Microwave Scanning Radiometer for EOS (AMSR-E) microwave instrument. The extent of snow cover is estimated from the MODIS data and SWE is estimated from the AMSR-E. Environmental limitations affect both sensors in different ways to limit their ability to detect snow in some situations. Forest density, snow wetness, and snow depth are factors that limit the effectiveness of both sensors for snow detection. Cloud cover is a significant hindrance to monitoring snow cover extent Using MODIS but is not a hindrance to the use of the AMSR-E. These limitations could be mitigated by combining MODIS and AMSR-E data to allow for improved interpretation of snow cover extent and SWE on a daily basis and provide temporal continuity of snow mapping across the boreal forest regions in Canada. The purpose of this study is to investigate if temporal monitoring of snow cover using a combination of MODIS and AMSR-E data could yield a better interpretation of changing snow cover conditions. The MODIS snow mapping algorithm is based on snow detection using the Normalized Difference Snow Index (NDSI) and the Normalized Difference Vegetation Index (NDVI) to enhance snow detection in dense vegetation. (Other spectral threshold tests are also used to map snow using MODIS.) Snow cover under a forest canopy may have an effect on the NDVI thus we use the NDVI in snow detection. A MODIS snow fraction product is also generated but not used in this study. In this study the NDSI and NDVI components of the snow mapping algorithm were calculated and analyzed to determine how they changed through the seasons. A blended snow product, the Air Force Weather Agency and NASA (ANSA) snow algorithm and product has recently been developed. The ANSA algorithm blends the MODIS snow cover and AMSR-E SWE products into a single snow product that has been shown to improve the performance of snow cover mapping. In this study components of the ANSA snow algorithm are used along with additional MODIS data to monitor daily changes in snow cover over the period of 1 February to 30 June 2008.

A novel image encryption algorithm based on synchronized random bit generated in cascade-coupled chaotic semiconductor ring lasers

NASA Astrophysics Data System (ADS)

Li, Jiafu; Xiang, Shuiying; Wang, Haoning; Gong, Junkai; Wen, Aijun

2018-03-01

In this paper, a novel image encryption algorithm based on synchronization of physical random bit generated in a cascade-coupled semiconductor ring lasers (CCSRL) system is proposed, and the security analysis is performed. In both transmitter and receiver parts, the CCSRL system is a master-slave configuration consisting of a master semiconductor ring laser (M-SRL) with cross-feedback and a solitary SRL (S-SRL). The proposed image encryption algorithm includes image preprocessing based on conventional chaotic maps, pixel confusion based on control matrix extracted from physical random bit, and pixel diffusion based on random bit stream extracted from physical random bit. Firstly, the preprocessing method is used to eliminate the correlation between adjacent pixels. Secondly, physical random bit with verified randomness is generated based on chaos in the CCSRL system, and is used to simultaneously generate the control matrix and random bit stream. Finally, the control matrix and random bit stream are used for the encryption algorithm in order to change the position and the values of pixels, respectively. Simulation results and security analysis demonstrate that the proposed algorithm is effective and able to resist various typical attacks, and thus is an excellent candidate for secure image communication application.

Temporal changes in randomness of bird communities across Central Europe.

PubMed

Renner, Swen C; Gossner, Martin M; Kahl, Tiemo; Kalko, Elisabeth K V; Weisser, Wolfgang W; Fischer, Markus; Allan, Eric

2014-01-01

Many studies have examined whether communities are structured by random or deterministic processes, and both are likely to play a role, but relatively few studies have attempted to quantify the degree of randomness in species composition. We quantified, for the first time, the degree of randomness in forest bird communities based on an analysis of spatial autocorrelation in three regions of Germany. The compositional dissimilarity between pairs of forest patches was regressed against the distance between them. We then calculated the y-intercept of the curve, i.e. the 'nugget', which represents the compositional dissimilarity at zero spatial distance. We therefore assume, following similar work on plant communities, that this represents the degree of randomness in species composition. We then analysed how the degree of randomness in community composition varied over time and with forest management intensity, which we expected to reduce the importance of random processes by increasing the strength of environmental drivers. We found that a high portion of the bird community composition could be explained by chance (overall mean of 0.63), implying that most of the variation in local bird community composition is driven by stochastic processes. Forest management intensity did not consistently affect the mean degree of randomness in community composition, perhaps because the bird communities were relatively insensitive to management intensity. We found a high temporal variation in the degree of randomness, which may indicate temporal variation in assembly processes and in the importance of key environmental drivers. We conclude that the degree of randomness in community composition should be considered in bird community studies, and the high values we find may indicate that bird community composition is relatively hard to predict at the regional scale.

Random-access algorithms for multiuser computer communication networks. Doctoral thesis, 1 September 1986-31 August 1988

DOE Office of Scientific and Technical Information (OSTI.GOV)

Papantoni-Kazakos, P.; Paterakis, M.

1988-07-01

For many communication applications with time constraints (e.g., transmission of packetized voice messages), a critical performance measure is the percentage of messages transmitted within a given amount of time after their generation at the transmitting station. This report presents a random-access algorithm (RAA) suitable for time-constrained applications. Performance analysis demonstrates that significant message-delay improvement is attained at the expense of minimal traffic loss. Also considered is the case of noisy channels. The noise effect appears at erroneously observed channel feedback. Error sensitivity analysis shows that the proposed random-access algorithm is insensitive to feedback channel errors. Window Random-Access Algorithms (RAAs) aremore » considered next. These algorithms constitute an important subclass of Multiple-Access Algorithms (MAAs); they are distributive, and they attain high throughput and low delays by controlling the number of simultaneously transmitting users.« less

Security authentication with a three-dimensional optical phase code using random forest classifier: an overview

NASA Astrophysics Data System (ADS)

Markman, Adam; Carnicer, Artur; Javidi, Bahram

2017-05-01

We overview our recent work [1] on utilizing three-dimensional (3D) optical phase codes for object authentication using the random forest classifier. A simple 3D optical phase code (OPC) is generated by combining multiple diffusers and glass slides. This tag is then placed on a quick-response (QR) code, which is a barcode capable of storing information and can be scanned under non-uniform illumination conditions, rotation, and slight degradation. A coherent light source illuminates the OPC and the transmitted light is captured by a CCD to record the unique signature. Feature extraction on the signature is performed and inputted into a pre-trained random-forest classifier for authentication.

Genetic algorithms with memory- and elitism-based immigrants in dynamic environments.

PubMed

Yang, Shengxiang

2008-01-01

In recent years the genetic algorithm community has shown a growing interest in studying dynamic optimization problems. Several approaches have been devised. The random immigrants and memory schemes are two major ones. The random immigrants scheme addresses dynamic environments by maintaining the population diversity while the memory scheme aims to adapt genetic algorithms quickly to new environments by reusing historical information. This paper investigates a hybrid memory and random immigrants scheme, called memory-based immigrants, and a hybrid elitism and random immigrants scheme, called elitism-based immigrants, for genetic algorithms in dynamic environments. In these schemes, the best individual from memory or the elite from the previous generation is retrieved as the base to create immigrants into the population by mutation. This way, not only can diversity be maintained but it is done more efficiently to adapt genetic algorithms to the current environment. Based on a series of systematically constructed dynamic problems, experiments are carried out to compare genetic algorithms with the memory-based and elitism-based immigrants schemes against genetic algorithms with traditional memory and random immigrants schemes and a hybrid memory and multi-population scheme. The sensitivity analysis regarding some key parameters is also carried out. Experimental results show that the memory-based and elitism-based immigrants schemes efficiently improve the performance of genetic algorithms in dynamic environments.

Automated detection of preserved photoreceptor on optical coherence tomography in choroideremia based on machine learning.

PubMed

Wang, Zhuo; Camino, Acner; Hagag, Ahmed M; Wang, Jie; Weleber, Richard G; Yang, Paul; Pennesi, Mark E; Huang, David; Li, Dengwang; Jia, Yali

2018-05-01

Optical coherence tomography (OCT) can demonstrate early deterioration of the photoreceptor integrity caused by inherited retinal degeneration diseases (IRDs). A machine learning method based on random forests was developed to automatically detect continuous areas of preserved ellipsoid zone structure (an easily recognizable part of the photoreceptors on OCT) in 16 eyes of patients with choroideremia (a type of IRD). Pseudopodial extensions protruding from the preserved ellipsoid zone areas are detected separately by a local active contour routine. The algorithm is implemented on en face images with minimum segmentation requirements, only needing delineation of the Bruch's membrane, thus evading the inaccuracies and technical challenges associated with automatic segmentation of the ellipsoid zone in eyes with severe retinal degeneration. © 2018 WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim.

Fast image interpolation via random forests.

PubMed

Huang, Jun-Jie; Siu, Wan-Chi; Liu, Tian-Rui

2015-10-01

This paper proposes a two-stage framework for fast image interpolation via random forests (FIRF). The proposed FIRF method gives high accuracy, as well as requires low computation. The underlying idea of this proposed work is to apply random forests to classify the natural image patch space into numerous subspaces and learn a linear regression model for each subspace to map the low-resolution image patch to high-resolution image patch. The FIRF framework consists of two stages. Stage 1 of the framework removes most of the ringing and aliasing artifacts in the initial bicubic interpolated image, while Stage 2 further refines the Stage 1 interpolated image. By varying the number of decision trees in the random forests and the number of stages applied, the proposed FIRF method can realize computationally scalable image interpolation. Extensive experimental results show that the proposed FIRF(3, 2) method achieves more than 0.3 dB improvement in peak signal-to-noise ratio over the state-of-the-art nonlocal autoregressive modeling (NARM) method. Moreover, the proposed FIRF(1, 1) obtains similar or better results as NARM while only takes its 0.3% computational time.

Graphic matching based on shape contexts and reweighted random walks

NASA Astrophysics Data System (ADS)

Zhang, Mingxuan; Niu, Dongmei; Zhao, Xiuyang; Liu, Mingjun

2018-04-01

Graphic matching is a very critical issue in all aspects of computer vision. In this paper, a new graphics matching algorithm combining shape contexts and reweighted random walks was proposed. On the basis of the local descriptor, shape contexts, the reweighted random walks algorithm was modified to possess stronger robustness and correctness in the final result. Our main process is to use the descriptor of the shape contexts for the random walk on the iteration, of which purpose is to control the random walk probability matrix. We calculate bias matrix by using descriptors and then in the iteration we use it to enhance random walks' and random jumps' accuracy, finally we get the one-to-one registration result by discretization of the matrix. The algorithm not only preserves the noise robustness of reweighted random walks but also possesses the rotation, translation, scale invariance of shape contexts. Through extensive experiments, based on real images and random synthetic point sets, and comparisons with other algorithms, it is confirmed that this new method can produce excellent results in graphic matching.

Surface electromyography based muscle fatigue detection using high-resolution time-frequency methods and machine learning algorithms.

PubMed

Karthick, P A; Ghosh, Diptasree Maitra; Ramakrishnan, S

2018-02-01

Surface electromyography (sEMG) based muscle fatigue research is widely preferred in sports science and occupational/rehabilitation studies due to its noninvasiveness. However, these signals are complex, multicomponent and highly nonstationary with large inter-subject variations, particularly during dynamic contractions. Hence, time-frequency based machine learning methodologies can improve the design of automated system for these signals. In this work, the analysis based on high-resolution time-frequency methods, namely, Stockwell transform (S-transform), B-distribution (BD) and extended modified B-distribution (EMBD) are proposed to differentiate the dynamic muscle nonfatigue and fatigue conditions. The nonfatigue and fatigue segments of sEMG signals recorded from the biceps brachii of 52 healthy volunteers are preprocessed and subjected to S-transform, BD and EMBD. Twelve features are extracted from each method and prominent features are selected using genetic algorithm (GA) and binary particle swarm optimization (BPSO). Five machine learning algorithms, namely, naïve Bayes, support vector machine (SVM) of polynomial and radial basis kernel, random forest and rotation forests are used for the classification. The results show that all the proposed time-frequency distributions (TFDs) are able to show the nonstationary variations of sEMG signals. Most of the features exhibit statistically significant difference in the muscle fatigue and nonfatigue conditions. The maximum number of features (66%) is reduced by GA and BPSO for EMBD and BD-TFD respectively. The combination of EMBD- polynomial kernel based SVM is found to be most accurate (91% accuracy) in classifying the conditions with the features selected using GA. The proposed methods are found to be capable of handling the nonstationary and multicomponent variations of sEMG signals recorded in dynamic fatiguing contractions. Particularly, the combination of EMBD- polynomial kernel based SVM could be used to detect the dynamic muscle fatigue conditions. Copyright © 2017 Elsevier B.V. All rights reserved.

[Estimation of Hunan forest carbon density based on spectral mixture analysis of MODIS data].

PubMed

Yan, En-ping; Lin, Hui; Wang, Guang-xing; Chen, Zhen-xiong

2015-11-01

With the fast development of remote sensing technology, combining forest inventory sample plot data and remotely sensed images has become a widely used method to map forest carbon density. However, the existence of mixed pixels often impedes the improvement of forest carbon density mapping, especially when low spatial resolution images such as MODIS are used. In this study, MODIS images and national forest inventory sample plot data were used to conduct the study of estimation for forest carbon density. Linear spectral mixture analysis with and without constraint, and nonlinear spectral mixture analysis were compared to derive the fractions of different land use and land cover (LULC) types. Then sequential Gaussian co-simulation algorithm with and without the fraction images from spectral mixture analyses were employed to estimate forest carbon density of Hunan Province. Results showed that 1) Linear spectral mixture analysis with constraint, leading to a mean RMSE of 0.002, more accurately estimated the fractions of LULC types than linear spectral and nonlinear spectral mixture analyses; 2) Integrating spectral mixture analysis model and sequential Gaussian co-simulation algorithm increased the estimation accuracy of forest carbon density to 81.5% from 74.1%, and decreased the RMSE to 5.18 from 7.26; and 3) The mean value of forest carbon density for the province was 30.06 t · hm(-2), ranging from 0.00 to 67.35 t · hm(-2). This implied that the spectral mixture analysis provided a great potential to increase the estimation accuracy of forest carbon density on regional and global level.

Random forests as cumulative effects models: A case study of lakes and rivers in Muskoka, Canada.

PubMed

Jones, F Chris; Plewes, Rachel; Murison, Lorna; MacDougall, Mark J; Sinclair, Sarah; Davies, Christie; Bailey, John L; Richardson, Murray; Gunn, John

2017-10-01

Cumulative effects assessment (CEA) - a type of environmental appraisal - lacks effective methods for modeling cumulative effects, evaluating indicators of ecosystem condition, and exploring the likely outcomes of development scenarios. Random forests are an extension of classification and regression trees, which model response variables by recursive partitioning. Random forests were used to model a series of candidate ecological indicators that described lakes and rivers from a case study watershed (The Muskoka River Watershed, Canada). Suitability of the candidate indicators for use in cumulative effects assessment and watershed monitoring was assessed according to how well they could be predicted from natural habitat features and how sensitive they were to human land-use. The best models explained 75% of the variation in a multivariate descriptor of lake benthic-macroinvertebrate community structure, and 76% of the variation in the conductivity of river water. Similar results were obtained by cross-validation. Several candidate indicators detected a simulated doubling of urban land-use in their catchments, and a few were able to detect a simulated doubling of agricultural land-use. The paper demonstrates that random forests can be used to describe the combined and singular effects of multiple stressors and natural environmental factors, and furthermore, that random forests can be used to evaluate the performance of monitoring indicators. The numerical methods presented are applicable to any ecosystem and indicator type, and therefore represent a step forward for CEA. Crown Copyright © 2017. Published by Elsevier Ltd. All rights reserved.

Improved high-dimensional prediction with Random Forests by the use of co-data.

PubMed

Te Beest, Dennis E; Mes, Steven W; Wilting, Saskia M; Brakenhoff, Ruud H; van de Wiel, Mark A

2017-12-28

Prediction in high dimensional settings is difficult due to the large number of variables relative to the sample size. We demonstrate how auxiliary 'co-data' can be used to improve the performance of a Random Forest in such a setting. Co-data are incorporated in the Random Forest by replacing the uniform sampling probabilities that are used to draw candidate variables by co-data moderated sampling probabilities. Co-data here are defined as any type information that is available on the variables of the primary data, but does not use its response labels. These moderated sampling probabilities are, inspired by empirical Bayes, learned from the data at hand. We demonstrate the co-data moderated Random Forest (CoRF) with two examples. In the first example we aim to predict the presence of a lymph node metastasis with gene expression data. We demonstrate how a set of external p-values, a gene signature, and the correlation between gene expression and DNA copy number can improve the predictive performance. In the second example we demonstrate how the prediction of cervical (pre-)cancer with methylation data can be improved by including the location of the probe relative to the known CpG islands, the number of CpG sites targeted by a probe, and a set of p-values from a related study. The proposed method is able to utilize auxiliary co-data to improve the performance of a Random Forest.

Sampling algorithms for validation of supervised learning models for Ising-like systems

NASA Astrophysics Data System (ADS)

Portman, Nataliya; Tamblyn, Isaac

2017-12-01

In this paper, we build and explore supervised learning models of ferromagnetic system behavior, using Monte-Carlo sampling of the spin configuration space generated by the 2D Ising model. Given the enormous size of the space of all possible Ising model realizations, the question arises as to how to choose a reasonable number of samples that will form physically meaningful and non-intersecting training and testing datasets. Here, we propose a sampling technique called ;ID-MH; that uses the Metropolis-Hastings algorithm creating Markov process across energy levels within the predefined configuration subspace. We show that application of this method retains phase transitions in both training and testing datasets and serves the purpose of validation of a machine learning algorithm. For larger lattice dimensions, ID-MH is not feasible as it requires knowledge of the complete configuration space. As such, we develop a new ;block-ID; sampling strategy: it decomposes the given structure into square blocks with lattice dimension N ≤ 5 and uses ID-MH sampling of candidate blocks. Further comparison of the performance of commonly used machine learning methods such as random forests, decision trees, k nearest neighbors and artificial neural networks shows that the PCA-based Decision Tree regressor is the most accurate predictor of magnetizations of the Ising model. For energies, however, the accuracy of prediction is not satisfactory, highlighting the need to consider more algorithmically complex methods (e.g., deep learning).

Automatic classification of protein structures using physicochemical parameters.

PubMed

Mohan, Abhilash; Rao, M Divya; Sunderrajan, Shruthi; Pennathur, Gautam

2014-09-01

Protein classification is the first step to functional annotation; SCOP and Pfam databases are currently the most relevant protein classification schemes. However, the disproportion in the number of three dimensional (3D) protein structures generated versus their classification into relevant superfamilies/families emphasizes the need for automated classification schemes. Predicting function of novel proteins based on sequence information alone has proven to be a major challenge. The present study focuses on the use of physicochemical parameters in conjunction with machine learning algorithms (Naive Bayes, Decision Trees, Random Forest and Support Vector Machines) to classify proteins into their respective SCOP superfamily/Pfam family, using sequence derived information. Spectrophores™, a 1D descriptor of the 3D molecular field surrounding a structure was used as a benchmark to compare the performance of the physicochemical parameters. The machine learning algorithms were modified to select features based on information gain for each SCOP superfamily/Pfam family. The effect of combining physicochemical parameters and spectrophores on classification accuracy (CA) was studied. Machine learning algorithms trained with the physicochemical parameters consistently classified SCOP superfamilies and Pfam families with a classification accuracy above 90%, while spectrophores performed with a CA of around 85%. Feature selection improved classification accuracy for both physicochemical parameters and spectrophores based machine learning algorithms. Combining both attributes resulted in a marginal loss of performance. Physicochemical parameters were able to classify proteins from both schemes with classification accuracy ranging from 90-96%. These results suggest the usefulness of this method in classifying proteins from amino acid sequences.

Machine Learning for Flood Prediction in Google Earth Engine

NASA Astrophysics Data System (ADS)

Kuhn, C.; Tellman, B.; Max, S. A.; Schwarz, B.

2015-12-01

With the increasing availability of high-resolution satellite imagery, dynamic flood mapping in near real time is becoming a reachable goal for decision-makers. This talk describes a newly developed framework for predicting biophysical flood vulnerability using public data, cloud computing and machine learning. Our objective is to define an approach to flood inundation modeling using statistical learning methods deployed in a cloud-based computing platform. Traditionally, static flood extent maps grounded in physically based hydrologic models can require hours of human expertise to construct at significant financial cost. In addition, desktop modeling software and limited local server storage can impose restraints on the size and resolution of input datasets. Data-driven, cloud-based processing holds promise for predictive watershed modeling at a wide range of spatio-temporal scales. However, these benefits come with constraints. In particular, parallel computing limits a modeler's ability to simulate the flow of water across a landscape, rendering traditional routing algorithms unusable in this platform. Our project pushes these limits by testing the performance of two machine learning algorithms, Support Vector Machine (SVM) and Random Forests, at predicting flood extent. Constructed in Google Earth Engine, the model mines a suite of publicly available satellite imagery layers to use as algorithm inputs. Results are cross-validated using MODIS-based flood maps created using the Dartmouth Flood Observatory detection algorithm. Model uncertainty highlights the difficulty of deploying unbalanced training data sets based on rare extreme events.

Evaluation of machine learning algorithms for prediction of regions of high Reynolds averaged Navier Stokes uncertainty

DOE PAGES

Ling, Julia; Templeton, Jeremy Alan

2015-08-04

Reynolds Averaged Navier Stokes (RANS) models are widely used in industry to predict fluid flows, despite their acknowledged deficiencies. Not only do RANS models often produce inaccurate flow predictions, but there are very limited diagnostics available to assess RANS accuracy for a given flow configuration. If experimental or higher fidelity simulation results are not available for RANS validation, there is no reliable method to evaluate RANS accuracy. This paper explores the potential of utilizing machine learning algorithms to identify regions of high RANS uncertainty. Three different machine learning algorithms were evaluated: support vector machines, Adaboost decision trees, and random forests.more » The algorithms were trained on a database of canonical flow configurations for which validated direct numerical simulation or large eddy simulation results were available, and were used to classify RANS results on a point-by-point basis as having either high or low uncertainty, based on the breakdown of specific RANS modeling assumptions. Classifiers were developed for three different basic RANS eddy viscosity model assumptions: the isotropy of the eddy viscosity, the linearity of the Boussinesq hypothesis, and the non-negativity of the eddy viscosity. It is shown that these classifiers are able to generalize to flows substantially different from those on which they were trained. As a result, feature selection techniques, model evaluation, and extrapolation detection are discussed in the context of turbulence modeling applications.« less