FDT 2.0: Improving scalability of the fuzzy decision tree induction tool - integrating database storage.

PubMed

Durham, Erin-Elizabeth A; Yu, Xiaxia; Harrison, Robert W

2014-12-01

Effective machine-learning handles large datasets efficiently. One key feature of handling large data is the use of databases such as MySQL. The freeware fuzzy decision tree induction tool, FDT, is a scalable supervised-classification software tool implementing fuzzy decision trees. It is based on an optimized fuzzy ID3 (FID3) algorithm. FDT 2.0 improves upon FDT 1.0 by bridging the gap between data science and data engineering: it combines a robust decisioning tool with data retention for future decisions, so that the tool does not need to be recalibrated from scratch every time a new decision is required. In this paper we briefly review the analytical capabilities of the freeware FDT tool and its major features and functionalities; examples of large biological datasets from HIV, microRNAs and sRNAs are included. This work shows how to integrate fuzzy decision algorithms with modern database technology. In addition, we show that integrating the fuzzy decision tree induction tool with database storage allows for optimal user satisfaction in today's Data Analytics world.

Support vector machines

NASA Technical Reports Server (NTRS)

Garay, Michael J.; Mazzoni, Dominic; Davies, Roger; Wagstaff, Kiri

2004-01-01

Support Vector Machines (SVMs) are a type of supervised learning algorith,, other examples of which are Artificial Neural Networks (ANNs), Decision Trees, and Naive Bayesian Classifiers. Supervised learning algorithms are used to classify objects labled by a 'supervisor' - typically a human 'expert.'.

Stacked Denoising Autoencoders Applied to Star/Galaxy Classification

NASA Astrophysics Data System (ADS)

Qin, Hao-ran; Lin, Ji-ming; Wang, Jun-yi

2017-04-01

In recent years, the deep learning algorithm, with the characteristics of strong adaptability, high accuracy, and structural complexity, has become more and more popular, but it has not yet been used in astronomy. In order to solve the problem that the star/galaxy classification accuracy is high for the bright source set, but low for the faint source set of the Sloan Digital Sky Survey (SDSS) data, we introduced the new deep learning algorithm, namely the SDA (stacked denoising autoencoder) neural network and the dropout fine-tuning technique, which can greatly improve the robustness and antinoise performance. We randomly selected respectively the bright source sets and faint source sets from the SDSS DR12 and DR7 data with spectroscopic measurements, and made preprocessing on them. Then, we randomly selected respectively the training sets and testing sets without replacement from the bright source sets and faint source sets. At last, using these training sets we made the training to obtain the SDA models of the bright sources and faint sources in the SDSS DR7 and DR12, respectively. We compared the test result of the SDA model on the DR12 testing set with the test results of the Library for Support Vector Machines (LibSVM), J48 decision tree, Logistic Model Tree (LMT), Support Vector Machine (SVM), Logistic Regression, and Decision Stump algorithm, and compared the test result of the SDA model on the DR7 testing set with the test results of six kinds of decision trees. The experiments show that the SDA has a better classification accuracy than other machine learning algorithms for the faint source sets of DR7 and DR12. Especially, when the completeness function is used as the evaluation index, compared with the decision tree algorithms, the correctness rate of SDA has improved about 15% for the faint source set of SDSS-DR7.

Meta-Learning Approach for Automatic Parameter Tuning: A Case Study with Educational Datasets

ERIC Educational Resources Information Center

Molina, M. M.; Luna, J. M.; Romero, C.; Ventura, S.

2012-01-01

This paper proposes to the use of a meta-learning approach for automatic parameter tuning of a well-known decision tree algorithm by using past information about algorithm executions. Fourteen educational datasets were analysed using various combinations of parameter values to examine the effects of the parameter values on accuracy classification.…

Automated rule-base creation via CLIPS-Induce

NASA Technical Reports Server (NTRS)

Murphy, Patrick M.

1994-01-01

Many CLIPS rule-bases contain one or more rule groups that perform classification. In this paper we describe CLIPS-Induce, an automated system for the creation of a CLIPS classification rule-base from a set of test cases. CLIPS-Induce consists of two components, a decision tree induction component and a CLIPS production extraction component. ID3, a popular decision tree induction algorithm, is used to induce a decision tree from the test cases. CLIPS production extraction is accomplished through a top-down traversal of the decision tree. Nodes of the tree are used to construct query rules, and branches of the tree are used to construct classification rules. The learned CLIPS productions may easily be incorporated into a large CLIPS system that perform tasks such as accessing a database or displaying information.

Prediction of microRNA target genes using an efficient genetic algorithm-based decision tree.

PubMed

Rabiee-Ghahfarrokhi, Behzad; Rafiei, Fariba; Niknafs, Ali Akbar; Zamani, Behzad

2015-01-01

MicroRNAs (miRNAs) are small, non-coding RNA molecules that regulate gene expression in almost all plants and animals. They play an important role in key processes, such as proliferation, apoptosis, and pathogen-host interactions. Nevertheless, the mechanisms by which miRNAs act are not fully understood. The first step toward unraveling the function of a particular miRNA is the identification of its direct targets. This step has shown to be quite challenging in animals primarily because of incomplete complementarities between miRNA and target mRNAs. In recent years, the use of machine-learning techniques has greatly increased the prediction of miRNA targets, avoiding the need for costly and time-consuming experiments to achieve miRNA targets experimentally. Among the most important machine-learning algorithms are decision trees, which classify data based on extracted rules. In the present work, we used a genetic algorithm in combination with C4.5 decision tree for prediction of miRNA targets. We applied our proposed method to a validated human datasets. We nearly achieved 93.9% accuracy of classification, which could be related to the selection of best rules.

Prediction of microRNA target genes using an efficient genetic algorithm-based decision tree

PubMed Central

Rabiee-Ghahfarrokhi, Behzad; Rafiei, Fariba; Niknafs, Ali Akbar; Zamani, Behzad

2015-01-01

MicroRNAs (miRNAs) are small, non-coding RNA molecules that regulate gene expression in almost all plants and animals. They play an important role in key processes, such as proliferation, apoptosis, and pathogen–host interactions. Nevertheless, the mechanisms by which miRNAs act are not fully understood. The first step toward unraveling the function of a particular miRNA is the identification of its direct targets. This step has shown to be quite challenging in animals primarily because of incomplete complementarities between miRNA and target mRNAs. In recent years, the use of machine-learning techniques has greatly increased the prediction of miRNA targets, avoiding the need for costly and time-consuming experiments to achieve miRNA targets experimentally. Among the most important machine-learning algorithms are decision trees, which classify data based on extracted rules. In the present work, we used a genetic algorithm in combination with C4.5 decision tree for prediction of miRNA targets. We applied our proposed method to a validated human datasets. We nearly achieved 93.9% accuracy of classification, which could be related to the selection of best rules. PMID:26649272

Evaluation of Decision Trees for Cloud Detection from AVHRR Data

NASA Technical Reports Server (NTRS)

Shiffman, Smadar; Nemani, Ramakrishna

2005-01-01

Automated cloud detection and tracking is an important step in assessing changes in radiation budgets associated with global climate change via remote sensing. Data products based on satellite imagery are available to the scientific community for studying trends in the Earth's atmosphere. The data products include pixel-based cloud masks that assign cloud-cover classifications to pixels. Many cloud-mask algorithms have the form of decision trees. The decision trees employ sequential tests that scientists designed based on empirical astrophysics studies and simulations. Limitations of existing cloud masks restrict our ability to accurately track changes in cloud patterns over time. In a previous study we compared automatically learned decision trees to cloud masks included in Advanced Very High Resolution Radiometer (AVHRR) data products from the year 2000. In this paper we report the replication of the study for five-year data, and for a gold standard based on surface observations performed by scientists at weather stations in the British Islands. For our sample data, the accuracy of automatically learned decision trees was greater than the accuracy of the cloud masks p < 0.001.

Logic Learning Machine and standard supervised methods for Hodgkin's lymphoma prognosis using gene expression data and clinical variables.

PubMed

Parodi, Stefano; Manneschi, Chiara; Verda, Damiano; Ferrari, Enrico; Muselli, Marco

2018-03-01

This study evaluates the performance of a set of machine learning techniques in predicting the prognosis of Hodgkin's lymphoma using clinical factors and gene expression data. Analysed samples from 130 Hodgkin's lymphoma patients included a small set of clinical variables and more than 54,000 gene features. Machine learning classifiers included three black-box algorithms ( k-nearest neighbour, Artificial Neural Network, and Support Vector Machine) and two methods based on intelligible rules (Decision Tree and the innovative Logic Learning Machine method). Support Vector Machine clearly outperformed any of the other methods. Among the two rule-based algorithms, Logic Learning Machine performed better and identified a set of simple intelligible rules based on a combination of clinical variables and gene expressions. Decision Tree identified a non-coding gene ( XIST) involved in the early phases of X chromosome inactivation that was overexpressed in females and in non-relapsed patients. XIST expression might be responsible for the better prognosis of female Hodgkin's lymphoma patients.

The use of decision trees and naïve Bayes algorithms and trace element patterns for controlling the authenticity of free-range-pastured hens' eggs.

PubMed

Barbosa, Rommel Melgaço; Nacano, Letícia Ramos; Freitas, Rodolfo; Batista, Bruno Lemos; Barbosa, Fernando

2014-09-01

This article aims to evaluate 2 machine learning algorithms, decision trees and naïve Bayes (NB), for egg classification (free-range eggs compared with battery eggs). The database used for the study consisted of 15 chemical elements (As, Ba, Cd, Co, Cs, Cu, Fe, Mg, Mn, Mo, Pb, Se, Sr, V, and Zn) determined in 52 eggs samples (20 free-range and 32 battery eggs) by inductively coupled plasma mass spectrometry. Our results demonstrated that decision trees and NB associated with the mineral contents of eggs provide a high level of accuracy (above 80% and 90%, respectively) for classification between free-range and battery eggs and can be used as an alternative method for adulteration evaluation. © 2014 Institute of Food Technologists®

Scalable Regression Tree Learning on Hadoop using OpenPlanet

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

Yin, Wei; Simmhan, Yogesh; Prasanna, Viktor

As scientific and engineering domains attempt to effectively analyze the deluge of data arriving from sensors and instruments, machine learning is becoming a key data mining tool to build prediction models. Regression tree is a popular learning model that combines decision trees and linear regression to forecast numerical target variables based on a set of input features. Map Reduce is well suited for addressing such data intensive learning applications, and a proprietary regression tree algorithm, PLANET, using MapReduce has been proposed earlier. In this paper, we describe an open source implement of this algorithm, OpenPlanet, on the Hadoop framework usingmore » a hybrid approach. Further, we evaluate the performance of OpenPlanet using realworld datasets from the Smart Power Grid domain to perform energy use forecasting, and propose tuning strategies of Hadoop parameters to improve the performance of the default configuration by 75% for a training dataset of 17 million tuples on a 64-core Hadoop cluster on FutureGrid.« less

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.

Teaching a Machine to Feel Postoperative Pain: Combining High-Dimensional Clinical Data with Machine Learning Algorithms to Forecast Acute Postoperative Pain

PubMed Central

Tighe, Patrick J.; Harle, Christopher A.; Hurley, Robert W.; Aytug, Haldun; Boezaart, Andre P.; Fillingim, Roger B.

2015-01-01

Background Given their ability to process highly dimensional datasets with hundreds of variables, machine learning algorithms may offer one solution to the vexing challenge of predicting postoperative pain. Methods Here, we report on the application of machine learning algorithms to predict postoperative pain outcomes in a retrospective cohort of 8071 surgical patients using 796 clinical variables. Five algorithms were compared in terms of their ability to forecast moderate to severe postoperative pain: Least Absolute Shrinkage and Selection Operator (LASSO), gradient-boosted decision tree, support vector machine, neural network, and k-nearest neighbor, with logistic regression included for baseline comparison. Results In forecasting moderate to severe postoperative pain for postoperative day (POD) 1, the LASSO algorithm, using all 796 variables, had the highest accuracy with an area under the receiver-operating curve (ROC) of 0.704. Next, the gradient-boosted decision tree had an ROC of 0.665 and the k-nearest neighbor algorithm had an ROC of 0.643. For POD 3, the LASSO algorithm, using all variables, again had the highest accuracy, with an ROC of 0.727. Logistic regression had a lower ROC of 0.5 for predicting pain outcomes on POD 1 and 3. Conclusions Machine learning algorithms, when combined with complex and heterogeneous data from electronic medical record systems, can forecast acute postoperative pain outcomes with accuracies similar to methods that rely only on variables specifically collected for pain outcome prediction. PMID:26031220

Rough Set Based Splitting Criterion for Binary Decision Tree Classifiers

DTIC Science & Technology

2006-09-26

Alata O. Fernandez-Maloigne C., and Ferrie J.C. (2001). Unsupervised Algorithm for the Segmentation of Three-Dimensional Magnetic Resonance Brain ...instinctual and learned responses in the brain , causing it to make decisions based on patterns in the stimuli. Using this deceptively simple process...2001. [2] Bohn C. (1997). An Incremental Unsupervised Learning Scheme for Function Approximation. In: Proceedings of the 1997 IEEE International

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.

Improving medical diagnosis reliability using Boosted C5.0 decision tree empowered by Particle Swarm Optimization.

PubMed

Pashaei, Elnaz; Ozen, Mustafa; Aydin, Nizamettin

2015-08-01

Improving accuracy of supervised classification algorithms in biomedical applications is one of active area of research. In this study, we improve the performance of Particle Swarm Optimization (PSO) combined with C4.5 decision tree (PSO+C4.5) classifier by applying Boosted C5.0 decision tree as the fitness function. To evaluate the effectiveness of our proposed method, it is implemented on 1 microarray dataset and 5 different medical data sets obtained from UCI machine learning databases. Moreover, the results of PSO + Boosted C5.0 implementation are compared to eight well-known benchmark classification methods (PSO+C4.5, support vector machine under the kernel of Radial Basis Function, Classification And Regression Tree (CART), C4.5 decision tree, C5.0 decision tree, Boosted C5.0 decision tree, Naive Bayes and Weighted K-Nearest neighbor). Repeated five-fold cross-validation method was used to justify the performance of classifiers. Experimental results show that our proposed method not only improve the performance of PSO+C4.5 but also obtains higher classification accuracy compared to the other classification methods.

Label-free sensor for automatic identification of erythrocytes using digital in-line holographic microscopy and machine learning.

PubMed

Go, Taesik; Byeon, Hyeokjun; Lee, Sang Joon

2018-04-30

Cell types of erythrocytes should be identified because they are closely related to their functionality and viability. Conventional methods for classifying erythrocytes are time consuming and labor intensive. Therefore, an automatic and accurate erythrocyte classification system is indispensable in healthcare and biomedical fields. In this study, we proposed a new label-free sensor for automatic identification of erythrocyte cell types using a digital in-line holographic microscopy (DIHM) combined with machine learning algorithms. A total of 12 features, including information on intensity distributions, morphological descriptors, and optical focusing characteristics, is quantitatively obtained from numerically reconstructed holographic images. All individual features for discocytes, echinocytes, and spherocytes are statistically different. To improve the performance of cell type identification, we adopted several machine learning algorithms, such as decision tree model, support vector machine, linear discriminant classification, and k-nearest neighbor classification. With the aid of these machine learning algorithms, the extracted features are effectively utilized to distinguish erythrocytes. Among the four tested algorithms, the decision tree model exhibits the best identification performance for the training sets (n = 440, 98.18%) and test sets (n = 190, 97.37%). This proposed methodology, which smartly combined DIHM and machine learning, would be helpful for sensing abnormal erythrocytes and computer-aided diagnosis of hematological diseases in clinic. Copyright © 2017 Elsevier B.V. All rights reserved.

Using Machine Learning and Natural Language Processing Algorithms to Automate the Evaluation of Clinical Decision Support in Electronic Medical Record Systems.

PubMed

Szlosek, Donald A; Ferrett, Jonathan

2016-01-01

As the number of clinical decision support systems (CDSSs) incorporated into electronic medical records (EMRs) increases, so does the need to evaluate their effectiveness. The use of medical record review and similar manual methods for evaluating decision rules is laborious and inefficient. The authors use machine learning and Natural Language Processing (NLP) algorithms to accurately evaluate a clinical decision support rule through an EMR system, and they compare it against manual evaluation. Modeled after the EMR system EPIC at Maine Medical Center, we developed a dummy data set containing physician notes in free text for 3,621 artificial patients records undergoing a head computed tomography (CT) scan for mild traumatic brain injury after the incorporation of an electronic best practice approach. We validated the accuracy of the Best Practice Advisories (BPA) using three machine learning algorithms-C-Support Vector Classification (SVC), Decision Tree Classifier (DecisionTreeClassifier), k-nearest neighbors classifier (KNeighborsClassifier)-by comparing their accuracy for adjudicating the occurrence of a mild traumatic brain injury against manual review. We then used the best of the three algorithms to evaluate the effectiveness of the BPA, and we compared the algorithm's evaluation of the BPA to that of manual review. The electronic best practice approach was found to have a sensitivity of 98.8 percent (96.83-100.0), specificity of 10.3 percent, PPV = 7.3 percent, and NPV = 99.2 percent when reviewed manually by abstractors. Though all the machine learning algorithms were observed to have a high level of prediction, the SVC displayed the highest with a sensitivity 93.33 percent (92.49-98.84), specificity of 97.62 percent (96.53-98.38), PPV = 50.00, NPV = 99.83. The SVC algorithm was observed to have a sensitivity of 97.9 percent (94.7-99.86), specificity 10.30 percent, PPV 7.25 percent, and NPV 99.2 percent for evaluating the best practice approach, after accounting for 17 cases (0.66 percent) where the patient records had to be reviewed manually due to the NPL systems inability to capture the proper diagnosis. CDSSs incorporated into EMRs can be evaluated in an automatic fashion by using NLP and machine learning techniques.

Binary Classification using Decision Tree based Genetic Programming and Its Application to Analysis of Bio-mass Data

NASA Astrophysics Data System (ADS)

To, Cuong; Pham, Tuan D.

2010-01-01

In machine learning, pattern recognition may be the most popular task. "Similar" patterns identification is also very important in biology because first, it is useful for prediction of patterns associated with disease, for example cancer tissue (normal or tumor); second, similarity or dissimilarity of the kinetic patterns is used to identify coordinately controlled genes or proteins involved in the same regulatory process. Third, similar genes (proteins) share similar functions. In this paper, we present an algorithm which uses genetic programming to create decision tree for binary classification problem. The application of the algorithm was implemented on five real biological databases. Base on the results of comparisons with well-known methods, we see that the algorithm is outstanding in most of cases.

Extensions and applications of ensemble-of-trees methods in machine learning

NASA Astrophysics Data System (ADS)

Bleich, Justin

Ensemble-of-trees algorithms have emerged to the forefront of machine learning due to their ability to generate high forecasting accuracy for a wide array of regression and classification problems. Classic ensemble methodologies such as random forests (RF) and stochastic gradient boosting (SGB) rely on algorithmic procedures to generate fits to data. In contrast, more recent ensemble techniques such as Bayesian Additive Regression Trees (BART) and Dynamic Trees (DT) focus on an underlying Bayesian probability model to generate the fits. These new probability model-based approaches show much promise versus their algorithmic counterparts, but also offer substantial room for improvement. The first part of this thesis focuses on methodological advances for ensemble-of-trees techniques with an emphasis on the more recent Bayesian approaches. In particular, we focus on extensions of BART in four distinct ways. First, we develop a more robust implementation of BART for both research and application. We then develop a principled approach to variable selection for BART as well as the ability to naturally incorporate prior information on important covariates into the algorithm. Next, we propose a method for handling missing data that relies on the recursive structure of decision trees and does not require imputation. Last, we relax the assumption of homoskedasticity in the BART model to allow for parametric modeling of heteroskedasticity. The second part of this thesis returns to the classic algorithmic approaches in the context of classification problems with asymmetric costs of forecasting errors. First we consider the performance of RF and SGB more broadly and demonstrate its superiority to logistic regression for applications in criminology with asymmetric costs. Next, we use RF to forecast unplanned hospital readmissions upon patient discharge with asymmetric costs taken into account. Finally, we explore the construction of stable decision trees for forecasts of violence during probation hearings in court systems.

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.

Some Results of Weak Anticipative Concept Applied in Simulation Based Decision Support in Enterprise

NASA Astrophysics Data System (ADS)

Kljajić, Miroljub; Kofjač, Davorin; Kljajić Borštnar, Mirjana; Škraba, Andrej

2010-11-01

The simulation models are used as for decision support and learning in enterprises and in schools. Tree cases of successful applications demonstrate usefulness of weak anticipative information. Job shop scheduling production with makespan criterion presents a real case customized flexible furniture production optimization. The genetic algorithm for job shop scheduling optimization is presented. Simulation based inventory control for products with stochastic lead time and demand describes inventory optimization for products with stochastic lead time and demand. Dynamic programming and fuzzy control algorithms reduce the total cost without producing stock-outs in most cases. Values of decision making information based on simulation were discussed too. All two cases will be discussed from optimization, modeling and learning point of view.

Classification

NASA Astrophysics Data System (ADS)

Oza, Nikunj

2012-03-01

A supervised learning task involves constructing a mapping from input data (normally described by several features) to the appropriate outputs. A set of training examples— examples with known output values—is used by a learning algorithm to generate a model. This model is intended to approximate the mapping between the inputs and outputs. This model can be used to generate predicted outputs for inputs that have not been seen before. Within supervised learning, one type of task is a classification learning task, in which each output is one or more classes to which the input belongs. For example, we may have data consisting of observations of sunspots. In a classification learning task, our goal may be to learn to classify sunspots into one of several types. Each example may correspond to one candidate sunspot with various measurements or just an image. A learning algorithm would use the supplied examples to generate a model that approximates the mapping between each supplied set of measurements and the type of sunspot. This model can then be used to classify previously unseen sunspots based on the candidate’s measurements. The generalization performance of a learned model (how closely the target outputs and the model’s predicted outputs agree for patterns that have not been presented to the learning algorithm) would provide an indication of how well the model has learned the desired mapping. More formally, a classification learning algorithm L takes a training set T as its input. The training set consists of |T| examples or instances. It is assumed that there is a probability distribution D from which all training examples are drawn independently—that is, all the training examples are independently and identically distributed (i.i.d.). The ith training example is of the form (x_i, y_i), where x_i is a vector of values of several features and y_i represents the class to be predicted.* In the sunspot classification example given above, each training example would represent one sunspot’s classification (y_i) and the corresponding set of measurements (x_i). The output of a supervised learning algorithm is a model h that approximates the unknown mapping from the inputs to the outputs. In our example, h would map from the sunspot measurements to the type of sunspot. We may have a test set S—a set of examples not used in training that we use to test how well the model h predicts the outputs on new examples. Just as with the examples in T, the examples in S are assumed to be independent and identically distributed (i.i.d.) draws from the distribution D. We measure the error of h on the test set as the proportion of test cases that h misclassifies: 1/|S| Sigma(x,y union S)[I(h(x)!= y)] where I(v) is the indicator function—it returns 1 if v is true and 0 otherwise. In our sunspot classification example, we would identify additional examples of sunspots that were not used in generating the model, and use these to determine how accurate the model is—the fraction of the test samples that the model classifies correctly. An example of a classification model is the decision tree shown in Figure 23.1. We will discuss the decision tree learning algorithm in more detail later—for now, we assume that, given a training set with examples of sunspots, this decision tree is derived. This can be used to classify previously unseen examples of sunpots. For example, if a new sunspot’s inputs indicate that its "Group Length" is in the range 10-15, then the decision tree would classify the sunspot as being of type “E,” whereas if the "Group Length" is "NULL," the "Magnetic Type" is "bipolar," and the "Penumbra" is "rudimentary," then it would be classified as type "C." In this chapter, we will add to the above description of classification problems. We will discuss decision trees and several other classification models. In particular, we will discuss the learning algorithms that generate these classification models, how to use them to classify new examples, and the strengths and weaknesses of these models. We will end with pointers to further reading on classification methods applied to astronomy data.

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 design of decision-tree induction algorithms tailored to flexible-receptor docking data.

PubMed

Barros, Rodrigo C; Winck, Ana T; Machado, Karina S; Basgalupp, Márcio P; de Carvalho, André C P L F; Ruiz, Duncan D; de Souza, Osmar Norberto

2012-11-21

This paper addresses the prediction of the free energy of binding of a drug candidate with enzyme InhA associated with Mycobacterium tuberculosis. This problem is found within rational drug design, where interactions between drug candidates and target proteins are verified through molecular docking simulations. In this application, it is important not only to correctly predict the free energy of binding, but also to provide a comprehensible model that could be validated by a domain specialist. Decision-tree induction algorithms have been successfully used in drug-design related applications, specially considering that decision trees are simple to understand, interpret, and validate. There are several decision-tree induction algorithms available for general-use, but each one has a bias that makes it more suitable for a particular data distribution. In this article, we propose and investigate the automatic design of decision-tree induction algorithms tailored to particular drug-enzyme binding data sets. We investigate the performance of our new method for evaluating binding conformations of different drug candidates to InhA, and we analyze our findings with respect to decision tree accuracy, comprehensibility, and biological relevance. The empirical analysis indicates that our method is capable of automatically generating decision-tree induction algorithms that significantly outperform the traditional C4.5 algorithm with respect to both accuracy and comprehensibility. In addition, we provide the biological interpretation of the rules generated by our approach, reinforcing the importance of comprehensible predictive models in this particular bioinformatics application. We conclude that automatically designing a decision-tree algorithm tailored to molecular docking data is a promising alternative for the prediction of the free energy from the binding of a drug candidate with a flexible-receptor.

Automatic design of decision-tree induction algorithms tailored to flexible-receptor docking data

PubMed Central

2012-01-01

Background This paper addresses the prediction of the free energy of binding of a drug candidate with enzyme InhA associated with Mycobacterium tuberculosis. This problem is found within rational drug design, where interactions between drug candidates and target proteins are verified through molecular docking simulations. In this application, it is important not only to correctly predict the free energy of binding, but also to provide a comprehensible model that could be validated by a domain specialist. Decision-tree induction algorithms have been successfully used in drug-design related applications, specially considering that decision trees are simple to understand, interpret, and validate. There are several decision-tree induction algorithms available for general-use, but each one has a bias that makes it more suitable for a particular data distribution. In this article, we propose and investigate the automatic design of decision-tree induction algorithms tailored to particular drug-enzyme binding data sets. We investigate the performance of our new method for evaluating binding conformations of different drug candidates to InhA, and we analyze our findings with respect to decision tree accuracy, comprehensibility, and biological relevance. Results The empirical analysis indicates that our method is capable of automatically generating decision-tree induction algorithms that significantly outperform the traditional C4.5 algorithm with respect to both accuracy and comprehensibility. In addition, we provide the biological interpretation of the rules generated by our approach, reinforcing the importance of comprehensible predictive models in this particular bioinformatics application. Conclusions We conclude that automatically designing a decision-tree algorithm tailored to molecular docking data is a promising alternative for the prediction of the free energy from the binding of a drug candidate with a flexible-receptor. PMID:23171000

A Modified Decision Tree Algorithm Based on Genetic Algorithm for Mobile User Classification Problem

PubMed Central

Liu, Dong-sheng; Fan, Shu-jiang

2014-01-01

In order to offer mobile customers better service, we should classify the mobile user firstly. Aimed at the limitations of previous classification methods, this paper puts forward a modified decision tree algorithm for mobile user classification, which introduced genetic algorithm to optimize the results of the decision tree algorithm. We also take the context information as a classification attributes for the mobile user and we classify the context into public context and private context classes. Then we analyze the processes and operators of the algorithm. At last, we make an experiment on the mobile user with the algorithm, we can classify the mobile user into Basic service user, E-service user, Plus service user, and Total service user classes and we can also get some rules about the mobile user. Compared to C4.5 decision tree algorithm and SVM algorithm, the algorithm we proposed in this paper has higher accuracy and more simplicity. PMID:24688389

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.

A P2P Botnet detection scheme based on decision tree and adaptive multilayer neural networks.

PubMed

Alauthaman, Mohammad; Aslam, Nauman; Zhang, Li; Alasem, Rafe; Hossain, M A

2018-01-01

In recent years, Botnets have been adopted as a popular method to carry and spread many malicious codes on the Internet. These malicious codes pave the way to execute many fraudulent activities including spam mail, distributed denial-of-service attacks and click fraud. While many Botnets are set up using centralized communication architecture, the peer-to-peer (P2P) Botnets can adopt a decentralized architecture using an overlay network for exchanging command and control data making their detection even more difficult. This work presents a method of P2P Bot detection based on an adaptive multilayer feed-forward neural network in cooperation with decision trees. A classification and regression tree is applied as a feature selection technique to select relevant features. With these features, a multilayer feed-forward neural network training model is created using a resilient back-propagation learning algorithm. A comparison of feature set selection based on the decision tree, principal component analysis and the ReliefF algorithm indicated that the neural network model with features selection based on decision tree has a better identification accuracy along with lower rates of false positives. The usefulness of the proposed approach is demonstrated by conducting experiments on real network traffic datasets. In these experiments, an average detection rate of 99.08 % with false positive rate of 0.75 % was observed.

Software tool for data mining and its applications

NASA Astrophysics Data System (ADS)

Yang, Jie; Ye, Chenzhou; Chen, Nianyi

2002-03-01

A software tool for data mining is introduced, which integrates pattern recognition (PCA, Fisher, clustering, hyperenvelop, regression), artificial intelligence (knowledge representation, decision trees), statistical learning (rough set, support vector machine), computational intelligence (neural network, genetic algorithm, fuzzy systems). It consists of nine function models: pattern recognition, decision trees, association rule, fuzzy rule, neural network, genetic algorithm, Hyper Envelop, support vector machine, visualization. The principle and knowledge representation of some function models of data mining are described. The software tool of data mining is realized by Visual C++ under Windows 2000. Nonmonotony in data mining is dealt with by concept hierarchy and layered mining. The software tool of data mining has satisfactorily applied in the prediction of regularities of the formation of ternary intermetallic compounds in alloy systems, and diagnosis of brain glioma.

Decision tree methods: applications for classification and prediction.

PubMed

Song, Yan-Yan; Lu, Ying

2015-04-25

Decision tree methodology is a commonly used data mining method for establishing classification systems based on multiple covariates or for developing prediction algorithms for a target variable. This method classifies a population into branch-like segments that construct an inverted tree with a root node, internal nodes, and leaf nodes. The algorithm is non-parametric and can efficiently deal with large, complicated datasets without imposing a complicated parametric structure. When the sample size is large enough, study data can be divided into training and validation datasets. Using the training dataset to build a decision tree model and a validation dataset to decide on the appropriate tree size needed to achieve the optimal final model. This paper introduces frequently used algorithms used to develop decision trees (including CART, C4.5, CHAID, and QUEST) and describes the SPSS and SAS programs that can be used to visualize tree structure.

Reconciliation of Decision-Making Heuristics Based on Decision Trees Topologies and Incomplete Fuzzy Probabilities Sets

PubMed Central

Doubravsky, Karel; Dohnal, Mirko

2015-01-01

Complex decision making tasks of different natures, e.g. economics, safety engineering, ecology and biology, are based on vague, sparse, partially inconsistent and subjective knowledge. Moreover, decision making economists / engineers are usually not willing to invest too much time into study of complex formal theories. They require such decisions which can be (re)checked by human like common sense reasoning. One important problem related to realistic decision making tasks are incomplete data sets required by the chosen decision making algorithm. This paper presents a relatively simple algorithm how some missing III (input information items) can be generated using mainly decision tree topologies and integrated into incomplete data sets. The algorithm is based on an easy to understand heuristics, e.g. a longer decision tree sub-path is less probable. This heuristic can solve decision problems under total ignorance, i.e. the decision tree topology is the only information available. But in a practice, isolated information items e.g. some vaguely known probabilities (e.g. fuzzy probabilities) are usually available. It means that a realistic problem is analysed under partial ignorance. The proposed algorithm reconciles topology related heuristics and additional fuzzy sets using fuzzy linear programming. The case study, represented by a tree with six lotteries and one fuzzy probability, is presented in details. PMID:26158662

Reconciliation of Decision-Making Heuristics Based on Decision Trees Topologies and Incomplete Fuzzy Probabilities Sets.

PubMed

Doubravsky, Karel; Dohnal, Mirko

2015-01-01

Complex decision making tasks of different natures, e.g. economics, safety engineering, ecology and biology, are based on vague, sparse, partially inconsistent and subjective knowledge. Moreover, decision making economists / engineers are usually not willing to invest too much time into study of complex formal theories. They require such decisions which can be (re)checked by human like common sense reasoning. One important problem related to realistic decision making tasks are incomplete data sets required by the chosen decision making algorithm. This paper presents a relatively simple algorithm how some missing III (input information items) can be generated using mainly decision tree topologies and integrated into incomplete data sets. The algorithm is based on an easy to understand heuristics, e.g. a longer decision tree sub-path is less probable. This heuristic can solve decision problems under total ignorance, i.e. the decision tree topology is the only information available. But in a practice, isolated information items e.g. some vaguely known probabilities (e.g. fuzzy probabilities) are usually available. It means that a realistic problem is analysed under partial ignorance. The proposed algorithm reconciles topology related heuristics and additional fuzzy sets using fuzzy linear programming. The case study, represented by a tree with six lotteries and one fuzzy probability, is presented in details.

[Prediction of regional soil quality based on mutual information theory integrated with decision tree algorithm].

PubMed

Lin, Fen-Fang; Wang, Ke; Yang, Ning; Yan, Shi-Guang; Zheng, Xin-Yu

2012-02-01

In this paper, some main factors such as soil type, land use pattern, lithology type, topography, road, and industry type that affect soil quality were used to precisely obtain the spatial distribution characteristics of regional soil quality, mutual information theory was adopted to select the main environmental factors, and decision tree algorithm See 5.0 was applied to predict the grade of regional soil quality. The main factors affecting regional soil quality were soil type, land use, lithology type, distance to town, distance to water area, altitude, distance to road, and distance to industrial land. The prediction accuracy of the decision tree model with the variables selected by mutual information was obviously higher than that of the model with all variables, and, for the former model, whether of decision tree or of decision rule, its prediction accuracy was all higher than 80%. Based on the continuous and categorical data, the method of mutual information theory integrated with decision tree could not only reduce the number of input parameters for decision tree algorithm, but also predict and assess regional soil quality effectively.

Creating ensembles of oblique decision trees with evolutionary algorithms and sampling

DOEpatents

Cantu-Paz, Erick [Oakland, CA; Kamath, Chandrika [Tracy, CA

2006-06-13

A decision tree system that is part of a parallel object-oriented pattern recognition system, which in turn is part of an object oriented data mining system. A decision tree process includes the step of reading the data. If necessary, the data is sorted. A potential split of the data is evaluated according to some criterion. An initial split of the data is determined. The final split of the data is determined using evolutionary algorithms and statistical sampling techniques. The data is split. Multiple decision trees are combined in ensembles.

Implementation of Data Mining to Analyze Drug Cases Using C4.5 Decision Tree

NASA Astrophysics Data System (ADS)

Wahyuni, Sri

2018-03-01

Data mining was the process of finding useful information from a large set of databases. One of the existing techniques in data mining was classification. The method used was decision tree method and algorithm used was C4.5 algorithm. The decision tree method was a method that transformed a very large fact into a decision tree which was presenting the rules. Decision tree method was useful for exploring data, as well as finding a hidden relationship between a number of potential input variables with a target variable. The decision tree of the C4.5 algorithm was constructed with several stages including the selection of attributes as roots, created a branch for each value and divided the case into the branch. These stages would be repeated for each branch until all the cases on the branch had the same class. From the solution of the decision tree there would be some rules of a case. In this case the researcher classified the data of prisoners at Labuhan Deli prison to know the factors of detainees committing criminal acts of drugs. By applying this C4.5 algorithm, then the knowledge was obtained as information to minimize the criminal acts of drugs. From the findings of the research, it was found that the most influential factor of the detainee committed the criminal act of drugs was from the address variable.

A comparative assessment of decision trees algorithms for flash flood susceptibility modeling at Haraz watershed, northern Iran.

PubMed

Khosravi, Khabat; Pham, Binh Thai; Chapi, Kamran; Shirzadi, Ataollah; Shahabi, Himan; Revhaug, Inge; Prakash, Indra; Tien Bui, Dieu

2018-06-15

Floods are one of the most damaging natural hazards causing huge loss of property, infrastructure and lives. Prediction of occurrence of flash flood locations is very difficult due to sudden change in climatic condition and manmade factors. However, prior identification of flood susceptible areas can be done with the help of machine learning techniques for proper timely management of flood hazards. In this study, we tested four decision trees based machine learning models namely Logistic Model Trees (LMT), Reduced Error Pruning Trees (REPT), Naïve Bayes Trees (NBT), and Alternating Decision Trees (ADT) for flash flood susceptibility mapping at the Haraz Watershed in the northern part of Iran. For this, a spatial database was constructed with 201 present and past flood locations and eleven flood-influencing factors namely ground slope, altitude, curvature, Stream Power Index (SPI), Topographic Wetness Index (TWI), land use, rainfall, river density, distance from river, lithology, and Normalized Difference Vegetation Index (NDVI). Statistical evaluation measures, the Receiver Operating Characteristic (ROC) curve, and Freidman and Wilcoxon signed-rank tests were used to validate and compare the prediction capability of the models. Results show that the ADT model has the highest prediction capability for flash flood susceptibility assessment, followed by the NBT, the LMT, and the REPT, respectively. These techniques have proven successful in quickly determining flood susceptible areas. Copyright © 2018 Elsevier B.V. All rights reserved.

A template-finding algorithm and a comprehensive benchmark for homology modeling of proteins

PubMed Central

Vallat, Brinda Kizhakke; Pillardy, Jaroslaw; Elber, Ron

2010-01-01

The first step in homology modeling is to identify a template protein for the target sequence. The template structure is used in later phases of the calculation to construct an atomically detailed model for the target. We have built from the Protein Data Bank a large-scale learning set that includes tens of millions of pair matches that can be either a true template or a false one. Discriminatory learning (learning from positive and negative examples) is employed to train a decision tree. Each branch of the tree is a mathematical programming model. The decision tree is tested on an independent set from PDB entries and on the sequences of CASP7. It provides significant enrichment of true templates (between 50-100 percent) when compared to PSI-BLAST. The model is further verified by building atomically detailed structures for each of the tentative true templates with modeller. The probability that a true match does not yield an acceptable structural model (within 6Å RMSD from the native structure), decays linearly as a function of the TM structural-alignment score. PMID:18300226

Machine Learning

NASA Astrophysics Data System (ADS)

Hoffmann, Achim; Mahidadia, Ashesh

The purpose of this chapter is to present fundamental ideas and techniques of machine learning suitable for the field of this book, i.e., for automated scientific discovery. The chapter focuses on those symbolic machine learning methods, which produce results that are suitable to be interpreted and understood by humans. This is particularly important in the context of automated scientific discovery as the scientific theories to be produced by machines are usually meant to be interpreted by humans. This chapter contains some of the most influential ideas and concepts in machine learning research to give the reader a basic insight into the field. After the introduction in Sect. 1, general ideas of how learning problems can be framed are given in Sect. 2. The section provides useful perspectives to better understand what learning algorithms actually do. Section 3 presents the Version space model which is an early learning algorithm as well as a conceptual framework, that provides important insight into the general mechanisms behind most learning algorithms. In section 4, a family of learning algorithms, the AQ family for learning classification rules is presented. The AQ family belongs to the early approaches in machine learning. The next, Sect. 5 presents the basic principles of decision tree learners. Decision tree learners belong to the most influential class of inductive learning algorithms today. Finally, a more recent group of learning systems are presented in Sect. 6, which learn relational concepts within the framework of logic programming. This is a particularly interesting group of learning systems since the framework allows also to incorporate background knowledge which may assist in generalisation. Section 7 discusses Association Rules - a technique that comes from the related field of Data mining. Section 8 presents the basic idea of the Naive Bayesian Classifier. While this is a very popular learning technique, the learning result is not well suited for human comprehension as it is essentially a large collection of probability values. In Sect. 9, we present a generic method for improving accuracy of a given learner by generatingmultiple classifiers using variations of the training data. While this works well in most cases, the resulting classifiers have significantly increased complexity and, hence, tend to destroy the human readability of the learning result that a single learner may produce. Section 10 contains a summary, mentions briefly other techniques not discussed in this chapter and presents outlook on the potential of machine learning in the future.

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…

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.

Learning Instance-Specific Predictive Models

PubMed Central

Visweswaran, Shyam; Cooper, Gregory F.

2013-01-01

This paper introduces a Bayesian algorithm for constructing predictive models from data that are optimized to predict a target variable well for a particular instance. This algorithm learns Markov blanket models, carries out Bayesian model averaging over a set of models to predict a target variable of the instance at hand, and employs an instance-specific heuristic to locate a set of suitable models to average over. We call this method the instance-specific Markov blanket (ISMB) algorithm. The ISMB algorithm was evaluated on 21 UCI data sets using five different performance measures and its performance was compared to that of several commonly used predictive algorithms, including nave Bayes, C4.5 decision tree, logistic regression, neural networks, k-Nearest Neighbor, Lazy Bayesian Rules, and AdaBoost. Over all the data sets, the ISMB algorithm performed better on average on all performance measures against all the comparison algorithms. PMID:25045325

Multispectral imaging burn wound tissue classification system: a comparison of test accuracies between several common machine learning algorithms

NASA Astrophysics Data System (ADS)

Squiers, John J.; Li, Weizhi; King, Darlene R.; Mo, Weirong; Zhang, Xu; Lu, Yang; Sellke, Eric W.; Fan, Wensheng; DiMaio, J. Michael; Thatcher, Jeffrey E.

2016-03-01

The clinical judgment of expert burn surgeons is currently the standard on which diagnostic and therapeutic decisionmaking regarding burn injuries is based. Multispectral imaging (MSI) has the potential to increase the accuracy of burn depth assessment and the intraoperative identification of viable wound bed during surgical debridement of burn injuries. A highly accurate classification model must be developed using machine-learning techniques in order to translate MSI data into clinically-relevant information. An animal burn model was developed to build an MSI training database and to study the burn tissue classification ability of several models trained via common machine-learning algorithms. The algorithms tested, from least to most complex, were: K-nearest neighbors (KNN), decision tree (DT), linear discriminant analysis (LDA), weighted linear discriminant analysis (W-LDA), quadratic discriminant analysis (QDA), ensemble linear discriminant analysis (EN-LDA), ensemble K-nearest neighbors (EN-KNN), and ensemble decision tree (EN-DT). After the ground-truth database of six tissue types (healthy skin, wound bed, blood, hyperemia, partial injury, full injury) was generated by histopathological analysis, we used 10-fold cross validation to compare the algorithms' performances based on their accuracies in classifying data against the ground truth, and each algorithm was tested 100 times. The mean test accuracy of the algorithms were KNN 68.3%, DT 61.5%, LDA 70.5%, W-LDA 68.1%, QDA 68.9%, EN-LDA 56.8%, EN-KNN 49.7%, and EN-DT 36.5%. LDA had the highest test accuracy, reflecting the bias-variance tradeoff over the range of complexities inherent to the algorithms tested. Several algorithms were able to match the current standard in burn tissue classification, the clinical judgment of expert burn surgeons. These results will guide further development of an MSI burn tissue classification system. Given that there are few surgeons and facilities specializing in burn care, this technology may improve the standard of burn care for patients without access to specialized facilities.

A Novel Artificial Intelligence System for Endotracheal Intubation.

PubMed

Carlson, Jestin N; Das, Samarjit; De la Torre, Fernando; Frisch, Adam; Guyette, Francis X; Hodgins, Jessica K; Yealy, Donald M

2016-01-01

Adequate visualization of the glottic opening is a key factor to successful endotracheal intubation (ETI); however, few objective tools exist to help guide providers' ETI attempts toward the glottic opening in real-time. Machine learning/artificial intelligence has helped to automate the detection of other visual structures but its utility with ETI is unknown. We sought to test the accuracy of various computer algorithms in identifying the glottic opening, creating a tool that could aid successful intubation. We collected a convenience sample of providers who each performed ETI 10 times on a mannequin using a video laryngoscope (C-MAC, Karl Storz Corp, Tuttlingen, Germany). We recorded each attempt and reviewed one-second time intervals for the presence or absence of the glottic opening. Four different machine learning/artificial intelligence algorithms analyzed each attempt and time point: k-nearest neighbor (KNN), support vector machine (SVM), decision trees, and neural networks (NN). We used half of the videos to train the algorithms and the second half to test the accuracy, sensitivity, and specificity of each algorithm. We enrolled seven providers, three Emergency Medicine attendings, and four paramedic students. From the 70 total recorded laryngoscopic video attempts, we created 2,465 time intervals. The algorithms had the following sensitivity and specificity for detecting the glottic opening: KNN (70%, 90%), SVM (70%, 90%), decision trees (68%, 80%), and NN (72%, 78%). Initial efforts at computer algorithms using artificial intelligence are able to identify the glottic opening with over 80% accuracy. With further refinements, video laryngoscopy has the potential to provide real-time, direction feedback to the provider to help guide successful ETI.

Learning Extended Finite State Machines

NASA Technical Reports Server (NTRS)

Cassel, Sofia; Howar, Falk; Jonsson, Bengt; Steffen, Bernhard

2014-01-01

We present an active learning algorithm for inferring extended finite state machines (EFSM)s, combining data flow and control behavior. Key to our learning technique is a novel learning model based on so-called tree queries. The learning algorithm uses the tree queries to infer symbolic data constraints on parameters, e.g., sequence numbers, time stamps, identifiers, or even simple arithmetic. We describe sufficient conditions for the properties that the symbolic constraints provided by a tree query in general must have to be usable in our learning model. We have evaluated our algorithm in a black-box scenario, where tree queries are realized through (black-box) testing. Our case studies include connection establishment in TCP and a priority queue from the Java Class Library.

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.

Two Trees: Migrating Fault Trees to Decision Trees for Real Time Fault Detection on International Space Station

NASA Technical Reports Server (NTRS)

Lee, Charles; Alena, Richard L.; Robinson, Peter

2004-01-01

We started from ISS fault trees example to migrate to decision trees, presented a method to convert fault trees to decision trees. The method shows that the visualizations of root cause of fault are easier and the tree manipulating becomes more programmatic via available decision tree programs. The visualization of decision trees for the diagnostic shows a format of straight forward and easy understands. For ISS real time fault diagnostic, the status of the systems could be shown by mining the signals through the trees and see where it stops at. The other advantage to use decision trees is that the trees can learn the fault patterns and predict the future fault from the historic data. The learning is not only on the static data sets but also can be online, through accumulating the real time data sets, the decision trees can gain and store faults patterns in the trees and recognize them when they come.

Block-Based Connected-Component Labeling Algorithm Using Binary Decision Trees

PubMed Central

Chang, Wan-Yu; Chiu, Chung-Cheng; Yang, Jia-Horng

2015-01-01

In this paper, we propose a fast labeling algorithm based on block-based concepts. Because the number of memory access points directly affects the time consumption of the labeling algorithms, the aim of the proposed algorithm is to minimize neighborhood operations. Our algorithm utilizes a block-based view and correlates a raster scan to select the necessary pixels generated by a block-based scan mask. We analyze the advantages of a sequential raster scan for the block-based scan mask, and integrate the block-connected relationships using two different procedures with binary decision trees to reduce unnecessary memory access. This greatly simplifies the pixel locations of the block-based scan mask. Furthermore, our algorithm significantly reduces the number of leaf nodes and depth levels required in the binary decision tree. We analyze the labeling performance of the proposed algorithm alongside that of other labeling algorithms using high-resolution images and foreground images. The experimental results from synthetic and real image datasets demonstrate that the proposed algorithm is faster than other methods. PMID:26393597

Predicting Developmental Status from 12 to 24 Months in Infants at Risk for Autism Spectrum Disorder: A Preliminary Report

ERIC Educational Resources Information Center

Macari, Suzanne L.; Campbell, Daniel; Gengoux, Grace W.; Saulnier, Celine A.; Klin, Ami J.; Chawarska, Katarzyna

2012-01-01

The study examined whether performance profiles on individual items of the Toddler Module of the Autism Diagnostic Observation Schedule at 12 months are associated with developmental status at 24 months in infants at high and low risk for developing Autism Spectrum Disorder (ASD). A nonparametric decision-tree learning algorithm identified sets of…

A research of selected textural features for detection of asbestos-cement roofing sheets using orthoimages

NASA Astrophysics Data System (ADS)

Książek, Judyta

2015-10-01

At present, there has been a great interest in the development of texture based image classification methods in many different areas. This study presents the results of research carried out to assess the usefulness of selected textural features for detection of asbestos-cement roofs in orthophotomap classification. Two different orthophotomaps of southern Poland (with ground resolution: 5 cm and 25 cm) were used. On both orthoimages representative samples for two classes: asbestos-cement roofing sheets and other roofing materials were selected. Estimation of texture analysis usefulness was conducted using machine learning methods based on decision trees (C5.0 algorithm). For this purpose, various sets of texture parameters were calculated in MaZda software. During the calculation of decision trees different numbers of texture parameters groups were considered. In order to obtain the best settings for decision trees models cross-validation was performed. Decision trees models with the lowest mean classification error were selected. The accuracy of the classification was held based on validation data sets, which were not used for the classification learning. For 5 cm ground resolution samples, the lowest mean classification error was 15.6%. The lowest mean classification error in the case of 25 cm ground resolution was 20.0%. The obtained results confirm potential usefulness of the texture parameter image processing for detection of asbestos-cement roofing sheets. In order to improve the accuracy another extended study should be considered in which additional textural features as well as spectral characteristics should be analyzed.

Hierarchical Learning of Tree Classifiers for Large-Scale Plant Species Identification.

PubMed

Fan, Jianping; Zhou, Ning; Peng, Jinye; Gao, Ling

2015-11-01

In this paper, a hierarchical multi-task structural learning algorithm is developed to support large-scale plant species identification, where a visual tree is constructed for organizing large numbers of plant species in a coarse-to-fine fashion and determining the inter-related learning tasks automatically. For a given parent node on the visual tree, it contains a set of sibling coarse-grained categories of plant species or sibling fine-grained plant species, and a multi-task structural learning algorithm is developed to train their inter-related classifiers jointly for enhancing their discrimination power. The inter-level relationship constraint, e.g., a plant image must first be assigned to a parent node (high-level non-leaf node) correctly if it can further be assigned to the most relevant child node (low-level non-leaf node or leaf node) on the visual tree, is formally defined and leveraged to learn more discriminative tree classifiers over the visual tree. Our experimental results have demonstrated the effectiveness of our hierarchical multi-task structural learning algorithm on training more discriminative tree classifiers for large-scale plant species identification.

Joint Extraction of Entities and Relations Using Reinforcement Learning and Deep Learning.

PubMed

Feng, Yuntian; Zhang, Hongjun; Hao, Wenning; Chen, Gang

2017-01-01

We use both reinforcement learning and deep learning to simultaneously extract entities and relations from unstructured texts. For reinforcement learning, we model the task as a two-step decision process. Deep learning is used to automatically capture the most important information from unstructured texts, which represent the state in the decision process. By designing the reward function per step, our proposed method can pass the information of entity extraction to relation extraction and obtain feedback in order to extract entities and relations simultaneously. Firstly, we use bidirectional LSTM to model the context information, which realizes preliminary entity extraction. On the basis of the extraction results, attention based method can represent the sentences that include target entity pair to generate the initial state in the decision process. Then we use Tree-LSTM to represent relation mentions to generate the transition state in the decision process. Finally, we employ Q -Learning algorithm to get control policy π in the two-step decision process. Experiments on ACE2005 demonstrate that our method attains better performance than the state-of-the-art method and gets a 2.4% increase in recall-score.

Joint Extraction of Entities and Relations Using Reinforcement Learning and Deep Learning

PubMed Central

Zhang, Hongjun; Chen, Gang

2017-01-01

We use both reinforcement learning and deep learning to simultaneously extract entities and relations from unstructured texts. For reinforcement learning, we model the task as a two-step decision process. Deep learning is used to automatically capture the most important information from unstructured texts, which represent the state in the decision process. By designing the reward function per step, our proposed method can pass the information of entity extraction to relation extraction and obtain feedback in order to extract entities and relations simultaneously. Firstly, we use bidirectional LSTM to model the context information, which realizes preliminary entity extraction. On the basis of the extraction results, attention based method can represent the sentences that include target entity pair to generate the initial state in the decision process. Then we use Tree-LSTM to represent relation mentions to generate the transition state in the decision process. Finally, we employ Q-Learning algorithm to get control policy π in the two-step decision process. Experiments on ACE2005 demonstrate that our method attains better performance than the state-of-the-art method and gets a 2.4% increase in recall-score. PMID:28894463

Cost-effectiveness Analysis with Influence Diagrams.

PubMed

Arias, M; Díez, F J

2015-01-01

Cost-effectiveness analysis (CEA) is used increasingly in medicine to determine whether the health benefit of an intervention is worth the economic cost. Decision trees, the standard decision modeling technique for non-temporal domains, can only perform CEA for very small problems. To develop a method for CEA in problems involving several dozen variables. We explain how to build influence diagrams (IDs) that explicitly represent cost and effectiveness. We propose an algorithm for evaluating cost-effectiveness IDs directly, i.e., without expanding an equivalent decision tree. The evaluation of an ID returns a set of intervals for the willingness to pay - separated by cost-effectiveness thresholds - and, for each interval, the cost, the effectiveness, and the optimal intervention. The algorithm that evaluates the ID directly is in general much more efficient than the brute-force method, which is in turn more efficient than the expansion of an equivalent decision tree. Using OpenMarkov, an open-source software tool that implements this algorithm, we have been able to perform CEAs on several IDs whose equivalent decision trees contain millions of branches. IDs can perform CEA on large problems that cannot be analyzed with decision trees.

Aneurysmal subarachnoid hemorrhage prognostic decision-making algorithm using classification and regression tree analysis.

PubMed

Lo, Benjamin W Y; Fukuda, Hitoshi; Angle, Mark; Teitelbaum, Jeanne; Macdonald, R Loch; Farrokhyar, Forough; Thabane, Lehana; Levine, Mitchell A H

2016-01-01

Classification and regression tree analysis involves the creation of a decision tree by recursive partitioning of a dataset into more homogeneous subgroups. Thus far, there is scarce literature on using this technique to create clinical prediction tools for aneurysmal subarachnoid hemorrhage (SAH). The classification and regression tree analysis technique was applied to the multicenter Tirilazad database (3551 patients) in order to create the decision-making algorithm. In order to elucidate prognostic subgroups in aneurysmal SAH, neurologic, systemic, and demographic factors were taken into account. The dependent variable used for analysis was the dichotomized Glasgow Outcome Score at 3 months. Classification and regression tree analysis revealed seven prognostic subgroups. Neurological grade, occurrence of post-admission stroke, occurrence of post-admission fever, and age represented the explanatory nodes of this decision tree. Split sample validation revealed classification accuracy of 79% for the training dataset and 77% for the testing dataset. In addition, the occurrence of fever at 1-week post-aneurysmal SAH is associated with increased odds of post-admission stroke (odds ratio: 1.83, 95% confidence interval: 1.56-2.45, P < 0.01). A clinically useful classification tree was generated, which serves as a prediction tool to guide bedside prognostication and clinical treatment decision making. This prognostic decision-making algorithm also shed light on the complex interactions between a number of risk factors in determining outcome after aneurysmal SAH.

Applying Data Mining Techniques to Extract Hidden Patterns about Breast Cancer Survival in an Iranian Cohort Study.

PubMed

Khalkhali, Hamid Reza; Lotfnezhad Afshar, Hadi; Esnaashari, Omid; Jabbari, Nasrollah

2016-01-01

Breast cancer survival has been analyzed by many standard data mining algorithms. A group of these algorithms belonged to the decision tree category. Ability of the decision tree algorithms in terms of visualizing and formulating of hidden patterns among study variables were main reasons to apply an algorithm from the decision tree category in the current study that has not studied already. The classification and regression trees (CART) was applied to a breast cancer database contained information on 569 patients in 2007-2010. The measurement of Gini impurity used for categorical target variables was utilized. The classification error that is a function of tree size was measured by 10-fold cross-validation experiments. The performance of created model was evaluated by the criteria as accuracy, sensitivity and specificity. The CART model produced a decision tree with 17 nodes, 9 of which were associated with a set of rules. The rules were meaningful clinically. They showed in the if-then format that Stage was the most important variable for predicting breast cancer survival. The scores of accuracy, sensitivity and specificity were: 80.3%, 93.5% and 53%, respectively. The current study model as the first one created by the CART was able to extract useful hidden rules from a relatively small size dataset.

An Isometric Mapping Based Co-Location Decision Tree Algorithm

NASA Astrophysics Data System (ADS)

Zhou, G.; Wei, J.; Zhou, X.; Zhang, R.; Huang, W.; Sha, H.; Chen, J.

2018-05-01

Decision tree (DT) induction has been widely used in different pattern classification. However, most traditional DTs have the disadvantage that they consider only non-spatial attributes (ie, spectral information) as a result of classifying pixels, which can result in objects being misclassified. Therefore, some researchers have proposed a co-location decision tree (Cl-DT) method, which combines co-location and decision tree to solve the above the above-mentioned traditional decision tree problems. Cl-DT overcomes the shortcomings of the existing DT algorithms, which create a node for each value of a given attribute, which has a higher accuracy than the existing decision tree approach. However, for non-linearly distributed data instances, the euclidean distance between instances does not reflect the true positional relationship between them. In order to overcome these shortcomings, this paper proposes an isometric mapping method based on Cl-DT (called, (Isomap-based Cl-DT), which is a method that combines heterogeneous and Cl-DT together. Because isometric mapping methods use geodetic distances instead of Euclidean distances between non-linearly distributed instances, the true distance between instances can be reflected. The experimental results and several comparative analyzes show that: (1) The extraction method of exposed carbonate rocks is of high accuracy. (2) The proposed method has many advantages, because the total number of nodes, the number of leaf nodes and the number of nodes are greatly reduced compared to Cl-DT. Therefore, the Isomap -based Cl-DT algorithm can construct a more accurate and faster decision tree.

Paradigms for machine learning

NASA Technical Reports Server (NTRS)

Schlimmer, Jeffrey C.; Langley, Pat

1991-01-01

Five paradigms are described for machine learning: connectionist (neural network) methods, genetic algorithms and classifier systems, empirical methods for inducing rules and decision trees, analytic learning methods, and case-based approaches. Some dimensions are considered along with these paradigms vary in their approach to learning, and the basic methods are reviewed that are used within each framework, together with open research issues. It is argued that the similarities among the paradigms are more important than their differences, and that future work should attempt to bridge the existing boundaries. Finally, some recent developments in the field of machine learning are discussed, and their impact on both research and applications is examined.

Automated Decision Tree Classification of Corneal Shape

PubMed Central

Twa, Michael D.; Parthasarathy, Srinivasan; Roberts, Cynthia; Mahmoud, Ashraf M.; Raasch, Thomas W.; Bullimore, Mark A.

2011-01-01

Purpose The volume and complexity of data produced during videokeratography examinations present a challenge of interpretation. As a consequence, results are often analyzed qualitatively by subjective pattern recognition or reduced to comparisons of summary indices. We describe the application of decision tree induction, an automated machine learning classification method, to discriminate between normal and keratoconic corneal shapes in an objective and quantitative way. We then compared this method with other known classification methods. Methods The corneal surface was modeled with a seventh-order Zernike polynomial for 132 normal eyes of 92 subjects and 112 eyes of 71 subjects diagnosed with keratoconus. A decision tree classifier was induced using the C4.5 algorithm, and its classification performance was compared with the modified Rabinowitz–McDonnell index, Schwiegerling’s Z3 index (Z3), Keratoconus Prediction Index (KPI), KISA%, and Cone Location and Magnitude Index using recommended classification thresholds for each method. We also evaluated the area under the receiver operator characteristic (ROC) curve for each classification method. Results Our decision tree classifier performed equal to or better than the other classifiers tested: accuracy was 92% and the area under the ROC curve was 0.97. Our decision tree classifier reduced the information needed to distinguish between normal and keratoconus eyes using four of 36 Zernike polynomial coefficients. The four surface features selected as classification attributes by the decision tree method were inferior elevation, greater sagittal depth, oblique toricity, and trefoil. Conclusions Automated decision tree classification of corneal shape through Zernike polynomials is an accurate quantitative method of classification that is interpretable and can be generated from any instrument platform capable of raw elevation data output. This method of pattern classification is extendable to other classification problems. PMID:16357645

Data mining for multiagent rules, strategies, and fuzzy decision tree structure

NASA Astrophysics Data System (ADS)

Smith, James F., III; Rhyne, Robert D., II; Fisher, Kristin

2002-03-01

A fuzzy logic based resource manager (RM) has been developed that automatically allocates electronic attack resources in real-time over many dissimilar platforms. Two different data mining algorithms have been developed to determine rules, strategies, and fuzzy decision tree structure. The first data mining algorithm uses a genetic algorithm as a data mining function and is called from an electronic game. The game allows a human expert to play against the resource manager in a simulated battlespace with each of the defending platforms being exclusively directed by the fuzzy resource manager and the attacking platforms being controlled by the human expert or operating autonomously under their own logic. This approach automates the data mining problem. The game automatically creates a database reflecting the domain expert's knowledge. It calls a data mining function, a genetic algorithm, for data mining of the database as required and allows easy evaluation of the information mined in the second step. The criterion for re- optimization is discussed as well as experimental results. Then a second data mining algorithm that uses a genetic program as a data mining function is introduced to automatically discover fuzzy decision tree structures. Finally, a fuzzy decision tree generated through this process is discussed.

An assessment of support vector machines for land cover classification

USGS Publications Warehouse

Huang, C.; Davis, L.S.; Townshend, J.R.G.

2002-01-01

The support vector machine (SVM) is a group of theoretically superior machine learning algorithms. It was found competitive with the best available machine learning algorithms in classifying high-dimensional data sets. This paper gives an introduction to the theoretical development of the SVM and an experimental evaluation of its accuracy, stability and training speed in deriving land cover classifications from satellite images. The SVM was compared to three other popular classifiers, including the maximum likelihood classifier (MLC), neural network classifiers (NNC) and decision tree classifiers (DTC). The impacts of kernel configuration on the performance of the SVM and of the selection of training data and input variables on the four classifiers were also evaluated in this experiment.

Fish to meat intake ratio and cooking oils are associated with hepatitis C virus carriers with persistently normal alanine aminotransferase levels.

PubMed

Otsuka, Momoka; Uchida, Yuki; Kawaguchi, Takumi; Taniguchi, Eitaro; Kawaguchi, Atsushi; Kitani, Shingo; Itou, Minoru; Oriishi, Tetsuharu; Kakuma, Tatsuyuki; Tanaka, Suiko; Yagi, Minoru; Sata, Michio

2012-10-01

  Dietary habits are involved in the development of chronic inflammation; however, the impact of dietary profiles of hepatitis C virus carriers with persistently normal alanine transaminase levels (HCV-PNALT) remains unclear. The decision-tree algorithm is a data-mining statistical technique, which uncovers meaningful profiles of factors from a data collection. We aimed to investigate dietary profiles associated with HCV-PNALT using a decision-tree algorithm.   Twenty-seven HCV-PNALT and 41 patients with chronic hepatitis C were enrolled in this study. Dietary habit was assessed using a validated semiquantitative food frequency questionnaire. A decision-tree algorithm was created by dietary variables, and was evaluated by area under the receiver operating characteristic curve analysis (AUROC).   In multivariate analysis, fish to meat ratio, dairy product and cooking oils were identified as independent variables associated with HCV-PNALT. The decision-tree algorithm was created with two variables: a fish to meat ratio and cooking oils/ideal bodyweight. When subjects showed a fish to meat ratio of 1.24 or more, 68.8% of the subjects were HCV-PNALT. On the other hand, 11.5% of the subjects were HCV-PNALT when subjects showed a fish to meat ratio of less than 1.24 and cooking oil/ideal bodyweight of less than 0.23 g/kg. The difference in the proportion of HCV-PNALT between these groups are significant (odds ratio 16.87, 95% CI 3.40-83.67, P = 0.0005). Fivefold cross-validation of the decision-tree algorithm showed an AUROC of 0.6947 (95% CI 0.5656-0.8238, P = 0.0067).   The decision-tree algorithm disclosed that fish to meat ratio and cooking oil/ideal bodyweight were associated with HCV-PNALT. © 2012 The Japan Society of Hepatology.

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.

Using decision trees to characterize verbal communication during change and stuck episodes in the therapeutic process

PubMed Central

Masías, Víctor H.; Krause, Mariane; Valdés, Nelson; Pérez, J. C.; Laengle, Sigifredo

2015-01-01

Methods are needed for creating models to characterize verbal communication between therapists and their patients that are suitable for teaching purposes without losing analytical potential. A technique meeting these twin requirements is proposed that uses decision trees to identify both change and stuck episodes in therapist-patient communication. Three decision tree algorithms (C4.5, NBTree, and REPTree) are applied to the problem of characterizing verbal responses into change and stuck episodes in the therapeutic process. The data for the problem is derived from a corpus of 8 successful individual therapy sessions with 1760 speaking turns in a psychodynamic context. The decision tree model that performed best was generated by the C4.5 algorithm. It delivered 15 rules characterizing the verbal communication in the two types of episodes. Decision trees are a promising technique for analyzing verbal communication during significant therapy events and have much potential for use in teaching practice on changes in therapeutic communication. The development of pedagogical methods using decision trees can support the transmission of academic knowledge to therapeutic practice. PMID:25914657

Using decision trees to characterize verbal communication during change and stuck episodes in the therapeutic process.

PubMed

Masías, Víctor H; Krause, Mariane; Valdés, Nelson; Pérez, J C; Laengle, Sigifredo

2015-01-01

Methods are needed for creating models to characterize verbal communication between therapists and their patients that are suitable for teaching purposes without losing analytical potential. A technique meeting these twin requirements is proposed that uses decision trees to identify both change and stuck episodes in therapist-patient communication. Three decision tree algorithms (C4.5, NBTree, and REPTree) are applied to the problem of characterizing verbal responses into change and stuck episodes in the therapeutic process. The data for the problem is derived from a corpus of 8 successful individual therapy sessions with 1760 speaking turns in a psychodynamic context. The decision tree model that performed best was generated by the C4.5 algorithm. It delivered 15 rules characterizing the verbal communication in the two types of episodes. Decision trees are a promising technique for analyzing verbal communication during significant therapy events and have much potential for use in teaching practice on changes in therapeutic communication. The development of pedagogical methods using decision trees can support the transmission of academic knowledge to therapeutic practice.

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.

Application of decision tree model for the ground subsidence hazard mapping near abandoned underground coal mines.

PubMed

Lee, Saro; Park, Inhye

2013-09-30

Subsidence of ground caused by underground mines poses hazards to human life and property. This study analyzed the hazard to ground subsidence using factors that can affect ground subsidence and a decision tree approach in a geographic information system (GIS). The study area was Taebaek, Gangwon-do, Korea, where many abandoned underground coal mines exist. Spatial data, topography, geology, and various ground-engineering data for the subsidence area were collected and compiled in a database for mapping ground-subsidence hazard (GSH). The subsidence area was randomly split 50/50 for training and validation of the models. A data-mining classification technique was applied to the GSH mapping, and decision trees were constructed using the chi-squared automatic interaction detector (CHAID) and the quick, unbiased, and efficient statistical tree (QUEST) algorithms. The frequency ratio model was also applied to the GSH mapping for comparing with probabilistic model. The resulting GSH maps were validated using area-under-the-curve (AUC) analysis with the subsidence area data that had not been used for training the model. The highest accuracy was achieved by the decision tree model using CHAID algorithm (94.01%) comparing with QUEST algorithms (90.37%) and frequency ratio model (86.70%). These accuracies are higher than previously reported results for decision tree. Decision tree methods can therefore be used efficiently for GSH analysis and might be widely used for prediction of various spatial events. Copyright © 2013. Published by Elsevier Ltd.

Learning and Tuning of Fuzzy Rules

NASA Technical Reports Server (NTRS)

Berenji, Hamid R.

1997-01-01

In this chapter, we review some of the current techniques for learning and tuning fuzzy rules. For clarity, we refer to the process of generating rules from data as the learning problem and distinguish it from tuning an already existing set of fuzzy rules. For learning, we touch on unsupervised learning techniques such as fuzzy c-means, fuzzy decision tree systems, fuzzy genetic algorithms, and linear fuzzy rules generation methods. For tuning, we discuss Jang's ANFIS architecture, Berenji-Khedkar's GARIC architecture and its extensions in GARIC-Q. We show that the hybrid techniques capable of learning and tuning fuzzy rules, such as CART-ANFIS, RNN-FLCS, and GARIC-RB, are desirable in development of a number of future intelligent systems.

Application of the pessimistic pruning to increase the accuracy of C4.5 algorithm in diagnosing chronic kidney disease

NASA Astrophysics Data System (ADS)

Muslim, M. A.; Herowati, A. J.; Sugiharti, E.; Prasetiyo, B.

2018-03-01

A technique to dig valuable information buried or hidden in data collection which is so big to be found an interesting patterns that was previously unknown is called data mining. Data mining has been applied in the healthcare industry. One technique used data mining is classification. The decision tree included in the classification of data mining and algorithm developed by decision tree is C4.5 algorithm. A classifier is designed using applying pessimistic pruning in C4.5 algorithm in diagnosing chronic kidney disease. Pessimistic pruning use to identify and remove branches that are not needed, this is done to avoid overfitting the decision tree generated by the C4.5 algorithm. In this paper, the result obtained using these classifiers are presented and discussed. Using pessimistic pruning shows increase accuracy of C4.5 algorithm of 1.5% from 95% to 96.5% in diagnosing of chronic kidney disease.

Analytical and CASE study on Limited Search, ID3, CHAID, C4.5, Improved C4.5 and OVA Decision Tree Algorithms to design Decision Support System

NASA Astrophysics Data System (ADS)

Kaur, Parneet; Singh, Sukhwinder; Garg, Sushil; Harmanpreet

2010-11-01

In this paper we study about classification algorithms for farm DSS. By applying classification algorithms i.e. Limited search, ID3, CHAID, C4.5, Improved C4.5 and One VS all Decision Tree on common data set of crop with specified class, results are obtained. The tool used to derive results is SPINA. The graphical results obtained from tool are compared to suggest best technique to develop farm Decision Support System. This analysis would help to researchers to design effective and fast DSS for farmer to take decision for enhancing their yield.

Vlsi implementation of flexible architecture for decision tree classification in data mining

NASA Astrophysics Data System (ADS)

Sharma, K. Venkatesh; Shewandagn, Behailu; Bhukya, Shankar Nayak

2017-07-01

The Data mining algorithms have become vital to researchers in science, engineering, medicine, business, search and security domains. In recent years, there has been a terrific raise in the size of the data being collected and analyzed. Classification is the main difficulty faced in data mining. In a number of the solutions developed for this problem, most accepted one is Decision Tree Classification (DTC) that gives high precision while handling very large amount of data. This paper presents VLSI implementation of flexible architecture for Decision Tree classification in data mining using c4.5 algorithm.

Applied Swarm-based medicine: collecting decision trees for patterns of algorithms analysis.

PubMed

Panje, Cédric M; Glatzer, Markus; von Rappard, Joscha; Rothermundt, Christian; Hundsberger, Thomas; Zumstein, Valentin; Plasswilm, Ludwig; Putora, Paul Martin

2017-08-16

The objective consensus methodology has recently been applied in consensus finding in several studies on medical decision-making among clinical experts or guidelines. The main advantages of this method are an automated analysis and comparison of treatment algorithms of the participating centers which can be performed anonymously. Based on the experience from completed consensus analyses, the main steps for the successful implementation of the objective consensus methodology were identified and discussed among the main investigators. The following steps for the successful collection and conversion of decision trees were identified and defined in detail: problem definition, population selection, draft input collection, tree conversion, criteria adaptation, problem re-evaluation, results distribution and refinement, tree finalisation, and analysis. This manuscript provides information on the main steps for successful collection of decision trees and summarizes important aspects at each point of the analysis.

Short communication: Prediction of retention pay-off using a machine learning algorithm.

PubMed

Shahinfar, Saleh; Kalantari, Afshin S; Cabrera, Victor; Weigel, Kent

2014-05-01

Replacement decisions have a major effect on dairy farm profitability. Dynamic programming (DP) has been widely studied to find the optimal replacement policies in dairy cattle. However, DP models are computationally intensive and might not be practical for daily decision making. Hence, the ability of applying machine learning on a prerun DP model to provide fast and accurate predictions of nonlinear and intercorrelated variables makes it an ideal methodology. Milk class (1 to 5), lactation number (1 to 9), month in milk (1 to 20), and month of pregnancy (0 to 9) were used to describe all cows in a herd in a DP model. Twenty-seven scenarios based on all combinations of 3 levels (base, 20% above, and 20% below) of milk production, milk price, and replacement cost were solved with the DP model, resulting in a data set of 122,716 records, each with a calculated retention pay-off (RPO). Then, a machine learning model tree algorithm was used to mimic the evaluated RPO with DP. The correlation coefficient factor was used to observe the concordance of RPO evaluated by DP and RPO predicted by the model tree. The obtained correlation coefficient was 0.991, with a corresponding value of 0.11 for relative absolute error. At least 100 instances were required per model constraint, resulting in 204 total equations (models). When these models were used for binary classification of positive and negative RPO, error rates were 1% false negatives and 9% false positives. Applying this trained model from simulated data for prediction of RPO for 102 actual replacement records from the University of Wisconsin-Madison dairy herd resulted in a 0.994 correlation with 0.10 relative absolute error rate. Overall results showed that model tree has a potential to be used in conjunction with DP to assist farmers in their replacement decisions. Copyright © 2014 American Dairy Science Association. Published by Elsevier Inc. All rights reserved.

Evolutionary Algorithm Based Automated Reverse Engineering and Defect Discovery

DTIC Science & Technology

2007-09-21

a previous application of a GP as a data mining function to evolve fuzzy decision trees symbolically [3-5], the terminal set consisted of fuzzy...of input and output information is required. In the case of fuzzy decision trees, the database represented a collection of scenarios about which the...fuzzy decision tree to be evolved would make decisions . The database also had entries created by experts representing decisions about the scenarios

Automatic energy expenditure measurement for health science.

PubMed

Catal, Cagatay; Akbulut, Akhan

2018-04-01

It is crucial to predict the human energy expenditure in any sports activity and health science application accurately to investigate the impact of the activity. However, measurement of the real energy expenditure is not a trivial task and involves complex steps. The objective of this work is to improve the performance of existing estimation models of energy expenditure by using machine learning algorithms and several data from different sensors and provide this estimation service in a cloud-based platform. In this study, we used input data such as breathe rate, and hearth rate from three sensors. Inputs are received from a web form and sent to the web service which applies a regression model on Azure cloud platform. During the experiments, we assessed several machine learning models based on regression methods. Our experimental results showed that our novel model which applies Boosted Decision Tree Regression in conjunction with the median aggregation technique provides the best result among other five regression algorithms. This cloud-based energy expenditure system which uses a web service showed that cloud computing technology is a great opportunity to develop estimation systems and the new model which applies Boosted Decision Tree Regression with the median aggregation provides remarkable results. Copyright © 2018 Elsevier B.V. All rights reserved.

Automated structural classification of lipids by machine learning.

PubMed

Taylor, Ryan; Miller, Ryan H; Miller, Ryan D; Porter, Michael; Dalgleish, James; Prince, John T

2015-03-01

Modern lipidomics is largely dependent upon structural ontologies because of the great diversity exhibited in the lipidome, but no automated lipid classification exists to facilitate this partitioning. The size of the putative lipidome far exceeds the number currently classified, despite a decade of work. Automated classification would benefit ongoing classification efforts by decreasing the time needed and increasing the accuracy of classification while providing classifications for mass spectral identification algorithms. We introduce a tool that automates classification into the LIPID MAPS ontology of known lipids with >95% accuracy and novel lipids with 63% accuracy. The classification is based upon simple chemical characteristics and modern machine learning algorithms. The decision trees produced are intelligible and can be used to clarify implicit assumptions about the current LIPID MAPS classification scheme. These characteristics and decision trees are made available to facilitate alternative implementations. We also discovered many hundreds of lipids that are currently misclassified in the LIPID MAPS database, strongly underscoring the need for automated classification. Source code and chemical characteristic lists as SMARTS search strings are available under an open-source license at https://www.github.com/princelab/lipid_classifier. © The Author 2014. Published by Oxford University Press. All rights reserved. For Permissions, please e-mail: journals.permissions@oup.com.

Propensity score estimation: neural networks, support vector machines, decision trees (CART), and meta-classifiers as alternatives to logistic regression.

PubMed

Westreich, Daniel; Lessler, Justin; Funk, Michele Jonsson

2010-08-01

Propensity scores for the analysis of observational data are typically estimated using logistic regression. Our objective in this review was to assess machine learning alternatives to logistic regression, which may accomplish the same goals but with fewer assumptions or greater accuracy. We identified alternative methods for propensity score estimation and/or classification from the public health, biostatistics, discrete mathematics, and computer science literature, and evaluated these algorithms for applicability to the problem of propensity score estimation, potential advantages over logistic regression, and ease of use. We identified four techniques as alternatives to logistic regression: neural networks, support vector machines, decision trees (classification and regression trees [CART]), and meta-classifiers (in particular, boosting). Although the assumptions of logistic regression are well understood, those assumptions are frequently ignored. All four alternatives have advantages and disadvantages compared with logistic regression. Boosting (meta-classifiers) and, to a lesser extent, decision trees (particularly CART), appear to be most promising for use in the context of propensity score analysis, but extensive simulation studies are needed to establish their utility in practice. Copyright (c) 2010 Elsevier Inc. All rights reserved.

Estimates of Single Sensor Error Statistics for the MODIS Matchup Database Using Machine Learning

NASA Astrophysics Data System (ADS)

Kumar, C.; Podesta, G. P.; Minnett, P. J.; Kilpatrick, K. A.

2017-12-01

Sea surface temperature (SST) is a fundamental quantity for understanding weather and climate dynamics. Although sensors aboard satellites provide global and repeated SST coverage, a characterization of SST precision and bias is necessary for determining the suitability of SST retrievals in various applications. Guidance on how to derive meaningful error estimates is still being developed. Previous methods estimated retrieval uncertainty based on geophysical factors, e.g. season or "wet" and "dry" atmospheres, but the discrete nature of these bins led to spatial discontinuities in SST maps. Recently, a new approach clustered retrievals based on the terms (excluding offset) in the statistical algorithm used to estimate SST. This approach resulted in over 600 clusters - too many to understand the geophysical conditions that influence retrieval error. Using MODIS and buoy SST matchups (2002 - 2016), we use machine learning algorithms (recursive and conditional trees, random forests) to gain insight into geophysical conditions leading to the different signs and magnitudes of MODIS SST residuals (satellite SSTs minus buoy SSTs). MODIS retrievals were first split into three categories: < -0.4 C, -0.4 C ≤ residual ≤ 0.4 C, and > 0.4 C. These categories are heavily unbalanced, with residuals > 0.4 C being much less frequent. Performance of classification algorithms is affected by imbalance, thus we tested various rebalancing algorithms (oversampling, undersampling, combinations of the two). We consider multiple features for the decision tree algorithms: regressors from the MODIS SST algorithm, proxies for temperature deficit, and spatial homogeneity of brightness temperatures (BTs), e.g., the range of 11 μm BTs inside a 25 km2 area centered on the buoy location. These features and a rebalancing of classes led to an 81.9% accuracy when classifying SST retrievals into the < -0.4 C and -0.4 C ≤ residual ≤ 0.4 C categories. Spatial homogeneity in BTs consistently appears as a very important variable for classification, suggesting that unidentified cloud contamination still is one of the causes leading to negative SST residuals. Precision and accuracy of error estimates from our decision tree classifier are enhanced using this knowledge.

A junction-tree based learning algorithm to optimize network wide traffic control: A coordinated multi-agent framework

DOE PAGES

Zhu, Feng; Aziz, H. M. Abdul; Qian, Xinwu; ...

2015-01-31

Our study develops a novel reinforcement learning algorithm for the challenging coordinated signal control problem. Traffic signals are modeled as intelligent agents interacting with the stochastic traffic environment. The model is built on the framework of coordinated reinforcement learning. The Junction Tree Algorithm (JTA) based reinforcement learning is proposed to obtain an exact inference of the best joint actions for all the coordinated intersections. Moreover, the algorithm is implemented and tested with a network containing 18 signalized intersections in VISSIM. Finally, our results show that the JTA based algorithm outperforms independent learning (Q-learning), real-time adaptive learning, and fixed timing plansmore » in terms of average delay, number of stops, and vehicular emissions at the network level.« less

Aid decision algorithms to estimate the risk in congenital heart surgery.

PubMed

Ruiz-Fernández, Daniel; Monsalve Torra, Ana; Soriano-Payá, Antonio; Marín-Alonso, Oscar; Triana Palencia, Eddy

2016-04-01

In this paper, we have tested the suitability of using different artificial intelligence-based algorithms for decision support when classifying the risk of congenital heart surgery. In this sense, classification of those surgical risks provides enormous benefits as the a priori estimation of surgical outcomes depending on either the type of disease or the type of repair, and other elements that influence the final result. This preventive estimation may help to avoid future complications, or even death. We have evaluated four machine learning algorithms to achieve our objective: multilayer perceptron, self-organizing map, radial basis function networks and decision trees. The architectures implemented have the aim of classifying among three types of surgical risk: low complexity, medium complexity and high complexity. Accuracy outcomes achieved range between 80% and 99%, being the multilayer perceptron method the one that offered a higher hit ratio. According to the results, it is feasible to develop a clinical decision support system using the evaluated algorithms. Such system would help cardiology specialists, paediatricians and surgeons to forecast the level of risk related to a congenital heart disease surgery. Copyright © 2015 Elsevier Ireland Ltd. All rights reserved.

Extending Correlation Filter-Based Visual Tracking by Tree-Structured Ensemble and Spatial Windowing.

PubMed

Gundogdu, Erhan; Ozkan, Huseyin; Alatan, A Aydin

2017-11-01

Correlation filters have been successfully used in visual tracking due to their modeling power and computational efficiency. However, the state-of-the-art correlation filter-based (CFB) tracking algorithms tend to quickly discard the previous poses of the target, since they consider only a single filter in their models. On the contrary, our approach is to register multiple CFB trackers for previous poses and exploit the registered knowledge when an appearance change occurs. To this end, we propose a novel tracking algorithm [of complexity O(D) ] based on a large ensemble of CFB trackers. The ensemble [of size O(2 D ) ] is organized over a binary tree (depth D ), and learns the target appearance subspaces such that each constituent tracker becomes an expert of a certain appearance. During tracking, the proposed algorithm combines only the appearance-aware relevant experts to produce boosted tracking decisions. Additionally, we propose a versatile spatial windowing technique to enhance the individual expert trackers. For this purpose, spatial windows are learned for target objects as well as the correlation filters and then the windowed regions are processed for more robust correlations. In our extensive experiments on benchmark datasets, we achieve a substantial performance increase by using the proposed tracking algorithm together with the spatial windowing.

Using Boosting Decision Trees in Gravitational Wave Searches triggered by Gamma-ray Bursts

NASA Astrophysics Data System (ADS)

Zuraw, Sarah; LIGO Collaboration

2015-04-01

The search for gravitational wave bursts requires the ability to distinguish weak signals from background detector noise. Gravitational wave bursts are characterized by their transient nature, making them particularly difficult to detect as they are similar to non-Gaussian noise fluctuations in the detector. The Boosted Decision Tree method is a powerful machine learning algorithm which uses Multivariate Analysis techniques to explore high-dimensional data sets in order to distinguish between gravitational wave signal and background detector noise. It does so by training with known noise events and simulated gravitational wave events. The method is tested using waveform models and compared with the performance of the standard gravitational wave burst search pipeline for Gamma-ray Bursts. It is shown that the method is able to effectively distinguish between signal and background events under a variety of conditions and over multiple Gamma-ray Burst events. This example demonstrates the usefulness and robustness of the Boosted Decision Tree and Multivariate Analysis techniques as a detection method for gravitational wave bursts. LIGO, UMass, PREP, NEGAP.

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

Is it worth changing pattern recognition methods for structural health monitoring?

NASA Astrophysics Data System (ADS)

Bull, L. A.; Worden, K.; Cross, E. J.; Dervilis, N.

2017-05-01

The key element of this work is to demonstrate alternative strategies for using pattern recognition algorithms whilst investigating structural health monitoring. This paper looks to determine if it makes any difference in choosing from a range of established classification techniques: from decision trees and support vector machines, to Gaussian processes. Classification algorithms are tested on adjustable synthetic data to establish performance metrics, then all techniques are applied to real SHM data. To aid the selection of training data, an informative chain of artificial intelligence tools is used to explore an active learning interaction between meaningful clusters of data.

VC-dimension of univariate decision trees.

PubMed

Yildiz, Olcay Taner

2015-02-01

In this paper, we give and prove the lower bounds of the Vapnik-Chervonenkis (VC)-dimension of the univariate decision tree hypothesis class. The VC-dimension of the univariate decision tree depends on the VC-dimension values of its subtrees and the number of inputs. Via a search algorithm that calculates the VC-dimension of univariate decision trees exhaustively, we show that our VC-dimension bounds are tight for simple trees. To verify that the VC-dimension bounds are useful, we also use them to get VC-generalization bounds for complexity control using structural risk minimization in decision trees, i.e., pruning. Our simulation results show that structural risk minimization pruning using the VC-dimension bounds finds trees that are more accurate as those pruned using cross validation.

Discovering Decision Knowledge from Web Log Portfolio for Managing Classroom Processes by Applying Decision Tree and Data Cube Technology.

ERIC Educational Resources Information Center

Chen, Gwo-Dong; Liu, Chen-Chung; Ou, Kuo-Liang; Liu, Baw-Jhiune

2000-01-01

Discusses the use of Web logs to record student behavior that can assist teachers in assessing performance and making curriculum decisions for distance learning students who are using Web-based learning systems. Adopts decision tree and data cube information processing methodologies for developing more effective pedagogical strategies. (LRW)

Data Exploration and Analysis of Alternative Learning System Accreditation and Equivalency Test Result Using Data Mining

NASA Astrophysics Data System (ADS)

Talingdan, J. A.; Trinidad, J. T., Jr.; Palaoag, T. D.

2018-03-01

Alternative Learning System (ALS) is a subsystem of Depatment of Education (DepEd) that serves as an option of learners who cannot afford to go in a formal education. The research focuses on the data exploration and analysis of ALS accreditation and equivalency test result using data mining. The ALS 2014 to 2016 A & E test results in the secondary level were used as data sets in the study. The A & E test results revealed that the passing rate is doubled per year. The results were clustered using k- means clustering algorithm and they were grouped into good, medium, and low standard learners to identify students need exceptional stuff for enhancement. From the clustered data, it was found out that the strand they are weak in is strand 4 which is the Development of Self and a Sense of Community with a general average of 84.23. It also revealed that the essay type of exam got the lowest score with a general average of 2.14 compared to the multiple type of exam that covers the five learning strands. Furthermore, decision tree and naive bayes were also employed in the study to predict the performance of the learners in the A & E test and determine which is better to use for prediction. It was concluded that naive bayes performs better because the accuracy rate is higher than the decision tree algorithm.

An automated approach to the design of decision tree classifiers

NASA Technical Reports Server (NTRS)

Argentiero, P.; Chin, R.; Beaudet, P.

1982-01-01

An automated technique is presented for designing effective decision tree classifiers predicated only on a priori class statistics. The procedure relies on linear feature extractions and Bayes table look-up decision rules. Associated error matrices are computed and utilized to provide an optimal design of the decision tree at each so-called 'node'. A by-product of this procedure is a simple algorithm for computing the global probability of correct classification assuming the statistical independence of the decision rules. Attention is given to a more precise definition of decision tree classification, the mathematical details on the technique for automated decision tree design, and an example of a simple application of the procedure using class statistics acquired from an actual Landsat scene.

Decision-Tree Formulation With Order-1 Lateral Execution

NASA Technical Reports Server (NTRS)

James, Mark

2007-01-01

A compact symbolic formulation enables mapping of an arbitrarily complex decision tree of a certain type into a highly computationally efficient multidimensional software object. The type of decision trees to which this formulation applies is that known in the art as the Boolean class of balanced decision trees. Parallel lateral slices of an object created by means of this formulation can be executed in constant time considerably less time than would otherwise be required. Decision trees of various forms are incorporated into almost all large software systems. A decision tree is a way of hierarchically solving a problem, proceeding through a set of true/false responses to a conclusion. By definition, a decision tree has a tree-like structure, wherein each internal node denotes a test on an attribute, each branch from an internal node represents an outcome of a test, and leaf nodes represent classes or class distributions that, in turn represent possible conclusions. The drawback of decision trees is that execution of them can be computationally expensive (and, hence, time-consuming) because each non-leaf node must be examined to determine whether to progress deeper into a tree structure or to examine an alternative. The present formulation was conceived as an efficient means of representing a decision tree and executing it in as little time as possible. The formulation involves the use of a set of symbolic algorithms to transform a decision tree into a multi-dimensional object, the rank of which equals the number of lateral non-leaf nodes. The tree can then be executed in constant time by means of an order-one table lookup. The sequence of operations performed by the algorithms is summarized as follows: 1. Determination of whether the tree under consideration can be encoded by means of this formulation. 2. Extraction of decision variables. 3. Symbolic optimization of the decision tree to minimize its form. 4. Expansion and transformation of all nested conjunctive-disjunctive paths to a flattened conjunctive form composed only of equality checks when possible. If each reduced conjunctive form contains only equality checks and all of these forms use the same variables, then the decision tree can be reduced to an order-one operation through a table lookup. The speedup to order one is accomplished by distributing each decision variable over a surface of a multidimensional object by mapping the equality constant to an index

A Decision-Tree-Oriented Guidance Mechanism for Conducting Nature Science Observation Activities in a Context-Aware Ubiquitous Learning

ERIC Educational Resources Information Center

Hwang, Gwo-Jen; Chu, Hui-Chun; Shih, Ju-Ling; Huang, Shu-Hsien; Tsai, Chin-Chung

2010-01-01

A context-aware ubiquitous learning environment is an authentic learning environment with personalized digital supports. While showing the potential of applying such a learning environment, researchers have also indicated the challenges of providing adaptive and dynamic support to individual students. In this paper, a decision-tree-oriented…

Decision-Tree Analysis for Predicting First-Time Pass/Fail Rates for the NCLEX-RN® in Associate Degree Nursing Students.

PubMed

Chen, Hsiu-Chin; Bennett, Sean

2016-08-01

Little evidence shows the use of decision-tree algorithms in identifying predictors and analyzing their associations with pass rates for the NCLEX-RN(®) in associate degree nursing students. This longitudinal and retrospective cohort study investigated whether a decision-tree algorithm could be used to develop an accurate prediction model for the students' passing or failing the NCLEX-RN. This study used archived data from 453 associate degree nursing students in a selected program. The chi-squared automatic interaction detection analysis of the decision trees module was used to examine the effect of the collected predictors on passing/failing the NCLEX-RN. The actual percentage scores of Assessment Technologies Institute®'s RN Comprehensive Predictor(®) accurately identified students at risk of failing. The classification model correctly classified 92.7% of the students for passing. This study applied the decision-tree model to analyze a sequence database for developing a prediction model for early remediation in preparation for the NCLEXRN. [J Nurs Educ. 2016;55(8):454-457.]. Copyright 2016, SLACK Incorporated.

hs-CRP is strongly associated with coronary heart disease (CHD): A data mining approach using decision tree algorithm.

PubMed

Tayefi, Maryam; Tajfard, Mohammad; Saffar, Sara; Hanachi, Parichehr; Amirabadizadeh, Ali Reza; Esmaeily, Habibollah; Taghipour, Ali; Ferns, Gordon A; Moohebati, Mohsen; Ghayour-Mobarhan, Majid

2017-04-01

Coronary heart disease (CHD) is an important public health problem globally. Algorithms incorporating the assessment of clinical biomarkers together with several established traditional risk factors can help clinicians to predict CHD and support clinical decision making with respect to interventions. Decision tree (DT) is a data mining model for extracting hidden knowledge from large databases. We aimed to establish a predictive model for coronary heart disease using a decision tree algorithm. Here we used a dataset of 2346 individuals including 1159 healthy participants and 1187 participant who had undergone coronary angiography (405 participants with negative angiography and 782 participants with positive angiography). We entered 10 variables of a total 12 variables into the DT algorithm (including age, sex, FBG, TG, hs-CRP, TC, HDL, LDL, SBP and DBP). Our model could identify the associated risk factors of CHD with sensitivity, specificity, accuracy of 96%, 87%, 94% and respectively. Serum hs-CRP levels was at top of the tree in our model, following by FBG, gender and age. Our model appears to be an accurate, specific and sensitive model for identifying the presence of CHD, but will require validation in prospective studies. Copyright © 2017 Elsevier B.V. All rights reserved.

A review of machine learning in obesity.

PubMed

DeGregory, K W; Kuiper, P; DeSilvio, T; Pleuss, J D; Miller, R; Roginski, J W; Fisher, C B; Harness, D; Viswanath, S; Heymsfield, S B; Dungan, I; Thomas, D M

2018-05-01

Rich sources of obesity-related data arising from sensors, smartphone apps, electronic medical health records and insurance data can bring new insights for understanding, preventing and treating obesity. For such large datasets, machine learning provides sophisticated and elegant tools to describe, classify and predict obesity-related risks and outcomes. Here, we review machine learning methods that predict and/or classify such as linear and logistic regression, artificial neural networks, deep learning and decision tree analysis. We also review methods that describe and characterize data such as cluster analysis, principal component analysis, network science and topological data analysis. We introduce each method with a high-level overview followed by examples of successful applications. The algorithms were then applied to National Health and Nutrition Examination Survey to demonstrate methodology, utility and outcomes. The strengths and limitations of each method were also evaluated. This summary of machine learning algorithms provides a unique overview of the state of data analysis applied specifically to obesity. © 2018 World Obesity Federation.

PCA based feature reduction to improve the accuracy of decision tree c4.5 classification

NASA Astrophysics Data System (ADS)

Nasution, M. Z. F.; Sitompul, O. S.; Ramli, M.

2018-03-01

Splitting attribute is a major process in Decision Tree C4.5 classification. However, this process does not give a significant impact on the establishment of the decision tree in terms of removing irrelevant features. It is a major problem in decision tree classification process called over-fitting resulting from noisy data and irrelevant features. In turns, over-fitting creates misclassification and data imbalance. Many algorithms have been proposed to overcome misclassification and overfitting on classifications Decision Tree C4.5. Feature reduction is one of important issues in classification model which is intended to remove irrelevant data in order to improve accuracy. The feature reduction framework is used to simplify high dimensional data to low dimensional data with non-correlated attributes. In this research, we proposed a framework for selecting relevant and non-correlated feature subsets. We consider principal component analysis (PCA) for feature reduction to perform non-correlated feature selection and Decision Tree C4.5 algorithm for the classification. From the experiments conducted using available data sets from UCI Cervical cancer data set repository with 858 instances and 36 attributes, we evaluated the performance of our framework based on accuracy, specificity and precision. Experimental results show that our proposed framework is robust to enhance classification accuracy with 90.70% accuracy rates.

Performance evaluation of the machine learning algorithms used in inference mechanism of a medical decision support system.

PubMed

Bal, Mert; Amasyali, M Fatih; Sever, Hayri; Kose, Guven; Demirhan, Ayse

2014-01-01

The importance of the decision support systems is increasingly supporting the decision making process in cases of uncertainty and the lack of information and they are widely used in various fields like engineering, finance, medicine, and so forth, Medical decision support systems help the healthcare personnel to select optimal method during the treatment of the patients. Decision support systems are intelligent software systems that support decision makers on their decisions. The design of decision support systems consists of four main subjects called inference mechanism, knowledge-base, explanation module, and active memory. Inference mechanism constitutes the basis of decision support systems. There are various methods that can be used in these mechanisms approaches. Some of these methods are decision trees, artificial neural networks, statistical methods, rule-based methods, and so forth. In decision support systems, those methods can be used separately or a hybrid system, and also combination of those methods. In this study, synthetic data with 10, 100, 1000, and 2000 records have been produced to reflect the probabilities on the ALARM network. The accuracy of 11 machine learning methods for the inference mechanism of medical decision support system is compared on various data sets.

A Decision Tree for Psychology Majors: Supplying Questions as Well as Answers.

ERIC Educational Resources Information Center

Poe, Retta E.

1988-01-01

Outlines the development of a psychology careers decision tree to help faculty advise students plan their program. States that students using the decision tree may benefit by learning more about their career options and by acquiring better question-asking skills. (GEA)

Propensity score estimation: machine learning and classification methods as alternatives to logistic regression

PubMed Central

Westreich, Daniel; Lessler, Justin; Funk, Michele Jonsson

2010-01-01

Summary Objective Propensity scores for the analysis of observational data are typically estimated using logistic regression. Our objective in this Review was to assess machine learning alternatives to logistic regression which may accomplish the same goals but with fewer assumptions or greater accuracy. Study Design and Setting We identified alternative methods for propensity score estimation and/or classification from the public health, biostatistics, discrete mathematics, and computer science literature, and evaluated these algorithms for applicability to the problem of propensity score estimation, potential advantages over logistic regression, and ease of use. Results We identified four techniques as alternatives to logistic regression: neural networks, support vector machines, decision trees (CART), and meta-classifiers (in particular, boosting). Conclusion While the assumptions of logistic regression are well understood, those assumptions are frequently ignored. All four alternatives have advantages and disadvantages compared with logistic regression. Boosting (meta-classifiers) and to a lesser extent decision trees (particularly CART) appear to be most promising for use in the context of propensity score analysis, but extensive simulation studies are needed to establish their utility in practice. PMID:20630332

Intelligent Diagnostic Assistant for Complicated Skin Diseases through C5's Algorithm.

PubMed

Jeddi, Fatemeh Rangraz; Arabfard, Masoud; Kermany, Zahra Arab

2017-09-01

Intelligent Diagnostic Assistant can be used for complicated diagnosis of skin diseases, which are among the most common causes of disability. The aim of this study was to design and implement a computerized intelligent diagnostic assistant for complicated skin diseases through C5's Algorithm. An applied-developmental study was done in 2015. Knowledge base was developed based on interviews with dermatologists through questionnaires and checklists. Knowledge representation was obtained from the train data in the database using Excel Microsoft Office. Clementine Software and C5's Algorithms were applied to draw the decision tree. Analysis of test accuracy was performed based on rules extracted using inference chains. The rules extracted from the decision tree were entered into the CLIPS programming environment and the intelligent diagnostic assistant was designed then. The rules were defined using forward chaining inference technique and were entered into Clips programming environment as RULE. The accuracy and error rates obtained in the training phase from the decision tree were 99.56% and 0.44%, respectively. The accuracy of the decision tree was 98% and the error was 2% in the test phase. Intelligent diagnostic assistant can be used as a reliable system with high accuracy, sensitivity, specificity, and agreement.

Machine learning algorithms for meteorological event classification in the coastal area using in-situ data

NASA Astrophysics Data System (ADS)

Sokolov, Anton; Gengembre, Cyril; Dmitriev, Egor; Delbarre, Hervé

2017-04-01

The problem is considered of classification of local atmospheric meteorological events in the coastal area such as sea breezes, fogs and storms. The in-situ meteorological data as wind speed and direction, temperature, humidity and turbulence are used as predictors. Local atmospheric events of 2013-2014 were analysed manually to train classification algorithms in the coastal area of English Channel in Dunkirk (France). Then, ultrasonic anemometer data and LIDAR wind profiler data were used as predictors. A few algorithms were applied to determine meteorological events by local data such as a decision tree, the nearest neighbour classifier, a support vector machine. The comparison of classification algorithms was carried out, the most important predictors for each event type were determined. It was shown that in more than 80 percent of the cases machine learning algorithms detect the meteorological class correctly. We expect that this methodology could be applied also to classify events by climatological in-situ data or by modelling data. It allows estimating frequencies of each event in perspective of climate change.

Understanding the undelaying mechanism of HA-subtyping in the level of physic-chemical characteristics of protein.

PubMed

Ebrahimi, Mansour; Aghagolzadeh, Parisa; Shamabadi, Narges; Tahmasebi, Ahmad; Alsharifi, Mohammed; Adelson, David L; Hemmatzadeh, Farhid; Ebrahimie, Esmaeil

2014-01-01

The evolution of the influenza A virus to increase its host range is a major concern worldwide. Molecular mechanisms of increasing host range are largely unknown. Influenza surface proteins play determining roles in reorganization of host-sialic acid receptors and host range. In an attempt to uncover the physic-chemical attributes which govern HA subtyping, we performed a large scale functional analysis of over 7000 sequences of 16 different HA subtypes. Large number (896) of physic-chemical protein characteristics were calculated for each HA sequence. Then, 10 different attribute weighting algorithms were used to find the key characteristics distinguishing HA subtypes. Furthermore, to discover machine leaning models which can predict HA subtypes, various Decision Tree, Support Vector Machine, Naïve Bayes, and Neural Network models were trained on calculated protein characteristics dataset as well as 10 trimmed datasets generated by attribute weighting algorithms. The prediction accuracies of the machine learning methods were evaluated by 10-fold cross validation. The results highlighted the frequency of Gln (selected by 80% of attribute weighting algorithms), percentage/frequency of Tyr, percentage of Cys, and frequencies of Try and Glu (selected by 70% of attribute weighting algorithms) as the key features that are associated with HA subtyping. Random Forest tree induction algorithm and RBF kernel function of SVM (scaled by grid search) showed high accuracy of 98% in clustering and predicting HA subtypes based on protein attributes. Decision tree models were successful in monitoring the short mutation/reassortment paths by which influenza virus can gain the key protein structure of another HA subtype and increase its host range in a short period of time with less energy consumption. Extracting and mining a large number of amino acid attributes of HA subtypes of influenza A virus through supervised algorithms represent a new avenue for understanding and predicting possible future structure of influenza pandemics.

Understanding the Underlying Mechanism of HA-Subtyping in the Level of Physic-Chemical Characteristics of Protein

PubMed Central

Ebrahimi, Mansour; Aghagolzadeh, Parisa; Shamabadi, Narges; Tahmasebi, Ahmad; Alsharifi, Mohammed; Adelson, David L.

2014-01-01

The evolution of the influenza A virus to increase its host range is a major concern worldwide. Molecular mechanisms of increasing host range are largely unknown. Influenza surface proteins play determining roles in reorganization of host-sialic acid receptors and host range. In an attempt to uncover the physic-chemical attributes which govern HA subtyping, we performed a large scale functional analysis of over 7000 sequences of 16 different HA subtypes. Large number (896) of physic-chemical protein characteristics were calculated for each HA sequence. Then, 10 different attribute weighting algorithms were used to find the key characteristics distinguishing HA subtypes. Furthermore, to discover machine leaning models which can predict HA subtypes, various Decision Tree, Support Vector Machine, Naïve Bayes, and Neural Network models were trained on calculated protein characteristics dataset as well as 10 trimmed datasets generated by attribute weighting algorithms. The prediction accuracies of the machine learning methods were evaluated by 10-fold cross validation. The results highlighted the frequency of Gln (selected by 80% of attribute weighting algorithms), percentage/frequency of Tyr, percentage of Cys, and frequencies of Try and Glu (selected by 70% of attribute weighting algorithms) as the key features that are associated with HA subtyping. Random Forest tree induction algorithm and RBF kernel function of SVM (scaled by grid search) showed high accuracy of 98% in clustering and predicting HA subtypes based on protein attributes. Decision tree models were successful in monitoring the short mutation/reassortment paths by which influenza virus can gain the key protein structure of another HA subtype and increase its host range in a short period of time with less energy consumption. Extracting and mining a large number of amino acid attributes of HA subtypes of influenza A virus through supervised algorithms represent a new avenue for understanding and predicting possible future structure of influenza pandemics. PMID:24809455

Prediction of insemination outcomes in Holstein dairy cattle using alternative machine learning algorithms.

PubMed

Shahinfar, Saleh; Page, David; Guenther, Jerry; Cabrera, Victor; Fricke, Paul; Weigel, Kent

2014-02-01

When making the decision about whether or not to breed a given cow, knowledge about the expected outcome would have an economic impact on profitability of the breeding program and net income of the farm. The outcome of each breeding can be affected by many management and physiological features that vary between farms and interact with each other. Hence, the ability of machine learning algorithms to accommodate complex relationships in the data and missing values for explanatory variables makes these algorithms well suited for investigation of reproduction performance in dairy cattle. The objective of this study was to develop a user-friendly and intuitive on-farm tool to help farmers make reproduction management decisions. Several different machine learning algorithms were applied to predict the insemination outcomes of individual cows based on phenotypic and genotypic data. Data from 26 dairy farms in the Alta Genetics (Watertown, WI) Advantage Progeny Testing Program were used, representing a 10-yr period from 2000 to 2010. Health, reproduction, and production data were extracted from on-farm dairy management software, and estimated breeding values were downloaded from the US Department of Agriculture Agricultural Research Service Animal Improvement Programs Laboratory (Beltsville, MD) database. The edited data set consisted of 129,245 breeding records from primiparous Holstein cows and 195,128 breeding records from multiparous Holstein cows. Each data point in the final data set included 23 and 25 explanatory variables and 1 binary outcome for of 0.756 ± 0.005 and 0.736 ± 0.005 for primiparous and multiparous cows, respectively. The naïve Bayes algorithm, Bayesian network, and decision tree algorithms showed somewhat poorer classification performance. An information-based variable selection procedure identified herd average conception rate, incidence of ketosis, number of previous (failed) inseminations, days in milk at breeding, and mastitis as the most effective explanatory variables in predicting pregnancy outcome. Copyright © 2014 American Dairy Science Association. Published by Elsevier Inc. All rights reserved.

Optical diagnosis of cervical cancer by higher order spectra and boosting

NASA Astrophysics Data System (ADS)

Pratiher, Sawon; Mukhopadhyay, Sabyasachi; Barman, Ritwik; Pratiher, Souvik; Pradhan, Asima; Ghosh, Nirmalya; Panigrahi, Prasanta K.

2017-03-01

In this contribution, we report the application of higher order statistical moments using decision tree and ensemble based learning methodology for the development of diagnostic algorithms for optical diagnosis of cancer. The classification results were compared to those obtained with an independent feature extractors like linear discriminant analysis (LDA). The performance and efficacy of these methodology using higher order statistics as a classifier using boosting has higher specificity and sensitivity while being much faster as compared to other time-frequency domain based methods.

Identifying pollution sources and predicting urban air quality using ensemble learning methods

NASA Astrophysics Data System (ADS)

Singh, Kunwar P.; Gupta, Shikha; Rai, Premanjali

2013-12-01

In this study, principal components analysis (PCA) was performed to identify air pollution sources and tree based ensemble learning models were constructed to predict the urban air quality of Lucknow (India) using the air quality and meteorological databases pertaining to a period of five years. PCA identified vehicular emissions and fuel combustion as major air pollution sources. The air quality indices revealed the air quality unhealthy during the summer and winter. Ensemble models were constructed to discriminate between the seasonal air qualities, factors responsible for discrimination, and to predict the air quality indices. Accordingly, single decision tree (SDT), decision tree forest (DTF), and decision treeboost (DTB) were constructed and their generalization and predictive performance was evaluated in terms of several statistical parameters and compared with conventional machine learning benchmark, support vector machines (SVM). The DT and SVM models discriminated the seasonal air quality rendering misclassification rate (MR) of 8.32% (SDT); 4.12% (DTF); 5.62% (DTB), and 6.18% (SVM), respectively in complete data. The AQI and CAQI regression models yielded a correlation between measured and predicted values and root mean squared error of 0.901, 6.67 and 0.825, 9.45 (SDT); 0.951, 4.85 and 0.922, 6.56 (DTF); 0.959, 4.38 and 0.929, 6.30 (DTB); 0.890, 7.00 and 0.836, 9.16 (SVR) in complete data. The DTF and DTB models outperformed the SVM both in classification and regression which could be attributed to the incorporation of the bagging and boosting algorithms in these models. The proposed ensemble models successfully predicted the urban ambient air quality and can be used as effective tools for its management.

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.

A New Automated Design Method Based on Machine Learning for CMOS Analog Circuits

NASA Astrophysics Data System (ADS)

Moradi, Behzad; Mirzaei, Abdolreza

2016-11-01

A new simulation based automated CMOS analog circuit design method which applies a multi-objective non-Darwinian-type evolutionary algorithm based on Learnable Evolution Model (LEM) is proposed in this article. The multi-objective property of this automated design of CMOS analog circuits is governed by a modified Strength Pareto Evolutionary Algorithm (SPEA) incorporated in the LEM algorithm presented here. LEM includes a machine learning method such as the decision trees that makes a distinction between high- and low-fitness areas in the design space. The learning process can detect the right directions of the evolution and lead to high steps in the evolution of the individuals. The learning phase shortens the evolution process and makes remarkable reduction in the number of individual evaluations. The expert designer's knowledge on circuit is applied in the design process in order to reduce the design space as well as the design time. The circuit evaluation is made by HSPICE simulator. In order to improve the design accuracy, bsim3v3 CMOS transistor model is adopted in this proposed design method. This proposed design method is tested on three different operational amplifier circuits. The performance of this proposed design method is verified by comparing it with the evolutionary strategy algorithm and other similar methods.

Analysis of data mining classification by comparison of C4.5 and ID algorithms

NASA Astrophysics Data System (ADS)

Sudrajat, R.; Irianingsih, I.; Krisnawan, D.

2017-01-01

The rapid development of information technology, triggered by the intensive use of information technology. For example, data mining widely used in investment. Many techniques that can be used assisting in investment, the method that used for classification is decision tree. Decision tree has a variety of algorithms, such as C4.5 and ID3. Both algorithms can generate different models for similar data sets and different accuracy. C4.5 and ID3 algorithms with discrete data provide accuracy are 87.16% and 99.83% and C4.5 algorithm with numerical data is 89.69%. C4.5 and ID3 algorithms with discrete data provides 520 and 598 customers and C4.5 algorithm with numerical data is 546 customers. From the analysis of the both algorithm it can classified quite well because error rate less than 15%.

MODIS Snow Cover Mapping Decision Tree Technique: Snow and Cloud Discrimination

NASA Technical Reports Server (NTRS)

Riggs, George A.; Hall, Dorothy K.

2010-01-01

Accurate mapping of snow cover continues to challenge cryospheric scientists and modelers. The Moderate-Resolution Imaging Spectroradiometer (MODIS) snow data products have been used since 2000 by many investigators to map and monitor snow cover extent for various applications. Users have reported on the utility of the products and also on problems encountered. Three problems or hindrances in the use of the MODIS snow data products that have been reported in the literature are: cloud obscuration, snow/cloud confusion, and snow omission errors in thin or sparse snow cover conditions. Implementation of the MODIS snow algorithm in a decision tree technique using surface reflectance input to mitigate those problems is being investigated. The objective of this work is to use a decision tree structure for the snow algorithm. This should alleviate snow/cloud confusion and omission errors and provide a snow map with classes that convey information on how snow was detected, e.g. snow under clear sky, snow tinder cloud, to enable users' flexibility in interpreting and deriving a snow map. Results of a snow cover decision tree algorithm are compared to the standard MODIS snow map and found to exhibit improved ability to alleviate snow/cloud confusion in some situations allowing up to about 5% increase in mapped snow cover extent, thus accuracy, in some scenes.

Safety validation of decision trees for hepatocellular carcinoma.

PubMed

Wang, Xian-Qiang; Liu, Zhe; Lv, Wen-Ping; Luo, Ying; Yang, Guang-Yun; Li, Chong-Hui; Meng, Xiang-Fei; Liu, Yang; Xu, Ke-Sen; Dong, Jia-Hong

2015-08-21

To evaluate a different decision tree for safe liver resection and verify its efficiency. A total of 2457 patients underwent hepatic resection between January 2004 and December 2010 at the Chinese PLA General Hospital, and 634 hepatocellular carcinoma (HCC) patients were eligible for the final analyses. Post-hepatectomy liver failure (PHLF) was identified by the association of prothrombin time < 50% and serum bilirubin > 50 μmol/L (the "50-50" criteria), which were assessed at day 5 postoperatively or later. The Swiss-Clavien decision tree, Tokyo University-Makuuchi decision tree, and Chinese consensus decision tree were adopted to divide patients into two groups based on those decision trees in sequence, and the PHLF rates were recorded. The overall mortality and PHLF rate were 0.16% and 3.0%. A total of 19 patients experienced PHLF. The numbers of patients to whom the Swiss-Clavien, Tokyo University-Makuuchi, and Chinese consensus decision trees were applied were 581, 573, and 622, and the PHLF rates were 2.75%, 2.62%, and 2.73%, respectively. Significantly more cases satisfied the Chinese consensus decision tree than the Swiss-Clavien decision tree and Tokyo University-Makuuchi decision tree (P < 0.01，P < 0.01); nevertheless, the latter two shared no difference (P = 0.147). The PHLF rate exhibited no significant difference with respect to the three decision trees. The Chinese consensus decision tree expands the indications for hepatic resection for HCC patients and does not increase the PHLF rate compared to the Swiss-Clavien and Tokyo University-Makuuchi decision trees. It would be a safe and effective algorithm for hepatectomy in patients with hepatocellular carcinoma.

Fuzzy support vector machine: an efficient rule-based classification technique for microarrays.

PubMed

Hajiloo, Mohsen; Rabiee, Hamid R; Anooshahpour, Mahdi

2013-01-01

The abundance of gene expression microarray data has led to the development of machine learning algorithms applicable for tackling disease diagnosis, disease prognosis, and treatment selection problems. However, these algorithms often produce classifiers with weaknesses in terms of accuracy, robustness, and interpretability. This paper introduces fuzzy support vector machine which is a learning algorithm based on combination of fuzzy classifiers and kernel machines for microarray classification. Experimental results on public leukemia, prostate, and colon cancer datasets show that fuzzy support vector machine applied in combination with filter or wrapper feature selection methods develops a robust model with higher accuracy than the conventional microarray classification models such as support vector machine, artificial neural network, decision trees, k nearest neighbors, and diagonal linear discriminant analysis. Furthermore, the interpretable rule-base inferred from fuzzy support vector machine helps extracting biological knowledge from microarray data. Fuzzy support vector machine as a new classification model with high generalization power, robustness, and good interpretability seems to be a promising tool for gene expression microarray classification.

Classification and Progression Based on CFS-GA and C5.0 Boost Decision Tree of TCM Zheng in Chronic Hepatitis B.

PubMed

Chen, Xiao Yu; Ma, Li Zhuang; Chu, Na; Zhou, Min; Hu, Yiyang

2013-01-01

Chronic hepatitis B (CHB) is a serious public health problem, and Traditional Chinese Medicine (TCM) plays an important role in the control and treatment for CHB. In the treatment of TCM, zheng discrimination is the most important step. In this paper, an approach based on CFS-GA (Correlation based Feature Selection and Genetic Algorithm) and C5.0 boost decision tree is used for zheng classification and progression in the TCM treatment of CHB. The CFS-GA performs better than the typical method of CFS. By CFS-GA, the acquired attribute subset is classified by C5.0 boost decision tree for TCM zheng classification of CHB, and C5.0 decision tree outperforms two typical decision trees of NBTree and REPTree on CFS-GA, CFS, and nonselection in comparison. Based on the critical indicators from C5.0 decision tree, important lab indicators in zheng progression are obtained by the method of stepwise discriminant analysis for expressing TCM zhengs in CHB, and alterations of the important indicators are also analyzed in zheng progression. In conclusion, all the three decision trees perform better on CFS-GA than on CFS and nonselection, and C5.0 decision tree outperforms the two typical decision trees both on attribute selection and nonselection.

TreePOD: Sensitivity-Aware Selection of Pareto-Optimal Decision Trees.

PubMed

Muhlbacher, Thomas; Linhardt, Lorenz; Moller, Torsten; Piringer, Harald

2018-01-01

Balancing accuracy gains with other objectives such as interpretability is a key challenge when building decision trees. However, this process is difficult to automate because it involves know-how about the domain as well as the purpose of the model. This paper presents TreePOD, a new approach for sensitivity-aware model selection along trade-offs. TreePOD is based on exploring a large set of candidate trees generated by sampling the parameters of tree construction algorithms. Based on this set, visualizations of quantitative and qualitative tree aspects provide a comprehensive overview of possible tree characteristics. Along trade-offs between two objectives, TreePOD provides efficient selection guidance by focusing on Pareto-optimal tree candidates. TreePOD also conveys the sensitivities of tree characteristics on variations of selected parameters by extending the tree generation process with a full-factorial sampling. We demonstrate how TreePOD supports a variety of tasks involved in decision tree selection and describe its integration in a holistic workflow for building and selecting decision trees. For evaluation, we illustrate a case study for predicting critical power grid states, and we report qualitative feedback from domain experts in the energy sector. This feedback suggests that TreePOD enables users with and without statistical background a confident and efficient identification of suitable decision trees.

Prediction of Allogeneic Hematopoietic Stem-Cell Transplantation Mortality 100 Days After Transplantation Using a Machine Learning Algorithm: A European Group for Blood and Marrow Transplantation Acute Leukemia Working Party Retrospective Data Mining Study.

PubMed

Shouval, Roni; Labopin, Myriam; Bondi, Ori; Mishan-Shamay, Hila; Shimoni, Avichai; Ciceri, Fabio; Esteve, Jordi; Giebel, Sebastian; Gorin, Norbert C; Schmid, Christoph; Polge, Emmanuelle; Aljurf, Mahmoud; Kroger, Nicolaus; Craddock, Charles; Bacigalupo, Andrea; Cornelissen, Jan J; Baron, Frederic; Unger, Ron; Nagler, Arnon; Mohty, Mohamad

2015-10-01

Allogeneic hematopoietic stem-cell transplantation (HSCT) is potentially curative for acute leukemia (AL), but carries considerable risk. Machine learning algorithms, which are part of the data mining (DM) approach, may serve for transplantation-related mortality risk prediction. This work is a retrospective DM study on a cohort of 28,236 adult HSCT recipients from the AL registry of the European Group for Blood and Marrow Transplantation. The primary objective was prediction of overall mortality (OM) at 100 days after HSCT. Secondary objectives were estimation of nonrelapse mortality, leukemia-free survival, and overall survival at 2 years. Donor, recipient, and procedural characteristics were analyzed. The alternating decision tree machine learning algorithm was applied for model development on 70% of the data set and validated on the remaining data. OM prevalence at day 100 was 13.9% (n=3,936). Of the 20 variables considered, 10 were selected by the model for OM prediction, and several interactions were discovered. By using a logistic transformation function, the crude score was transformed into individual probabilities for 100-day OM (range, 3% to 68%). The model's discrimination for the primary objective performed better than the European Group for Blood and Marrow Transplantation score (area under the receiver operating characteristics curve, 0.701 v 0.646; P<.001). Calibration was excellent. Scores assigned were also predictive of secondary objectives. The alternating decision tree model provides a robust tool for risk evaluation of patients with AL before HSCT, and is available online (http://bioinfo.lnx.biu.ac.il/∼bondi/web1.html). It is presented as a continuous probabilistic score for the prediction of day 100 OM, extending prediction to 2 years. The DM method has proved useful for clinical prediction in HSCT. © 2015 by American Society of Clinical Oncology.

What Satisfies Students?: Mining Student-Opinion Data with Regression and Decision Tree Analysis

ERIC Educational Resources Information Center

Thomas, Emily H.; Galambos, Nora

2004-01-01

To investigate how students' characteristics and experiences affect satisfaction, this study uses regression and decision tree analysis with the CHAID algorithm to analyze student-opinion data. A data mining approach identifies the specific aspects of students' university experience that most influence three measures of general satisfaction. The…

Computerization of guidelines: a knowledge specification method to convert text to detailed decision tree for electronic implementation.

PubMed

Aguirre-Junco, Angel-Ricardo; Colombet, Isabelle; Zunino, Sylvain; Jaulent, Marie-Christine; Leneveut, Laurence; Chatellier, Gilles

2004-01-01

The initial step for the computerization of guidelines is the knowledge specification from the prose text of guidelines. We describe a method of knowledge specification based on a structured and systematic analysis of text allowing detailed specification of a decision tree. We use decision tables to validate the decision algorithm and decision trees to specify and represent this algorithm, along with elementary messages of recommendation. Edition tools are also necessary to facilitate the process of validation and workflow between expert physicians who will validate the specified knowledge and computer scientist who will encode the specified knowledge in a guide-line model. Applied to eleven different guidelines issued by an official agency, the method allows a quick and valid computerization and integration in a larger decision support system called EsPeR (Personalized Estimate of Risks). The quality of the text guidelines is however still to be developed further. The method used for computerization could help to define a framework usable at the initial step of guideline development in order to produce guidelines ready for electronic implementation.

Minimizing the cost of translocation failure with decision-tree models that predict species' behavioral response in translocation sites.

PubMed

Ebrahimi, Mehregan; Ebrahimie, Esmaeil; Bull, C Michael

2015-08-01

The high number of failures is one reason why translocation is often not recommended. Considering how behavior changes during translocations may improve translocation success. To derive decision-tree models for species' translocation, we used data on the short-term responses of an endangered Australian skink in 5 simulated translocations with different release conditions. We used 4 different decision-tree algorithms (decision tree, decision-tree parallel, decision stump, and random forest) with 4 different criteria (gain ratio, information gain, gini index, and accuracy) to investigate how environmental and behavioral parameters may affect the success of a translocation. We assumed behavioral changes that increased dispersal away from a release site would reduce translocation success. The trees became more complex when we included all behavioral parameters as attributes, but these trees yielded more detailed information about why and how dispersal occurred. According to these complex trees, there were positive associations between some behavioral parameters, such as fight and dispersal, that showed there was a higher chance, for example, of dispersal among lizards that fought than among those that did not fight. Decision trees based on parameters related to release conditions were easier to understand and could be used by managers to make translocation decisions under different circumstances. © 2015 Society for Conservation Biology.

HD-MTL: Hierarchical Deep Multi-Task Learning for Large-Scale Visual Recognition.

PubMed

Fan, Jianping; Zhao, Tianyi; Kuang, Zhenzhong; Zheng, Yu; Zhang, Ji; Yu, Jun; Peng, Jinye

2017-02-09

In this paper, a hierarchical deep multi-task learning (HD-MTL) algorithm is developed to support large-scale visual recognition (e.g., recognizing thousands or even tens of thousands of atomic object classes automatically). First, multiple sets of multi-level deep features are extracted from different layers of deep convolutional neural networks (deep CNNs), and they are used to achieve more effective accomplishment of the coarseto- fine tasks for hierarchical visual recognition. A visual tree is then learned by assigning the visually-similar atomic object classes with similar learning complexities into the same group, which can provide a good environment for determining the interrelated learning tasks automatically. By leveraging the inter-task relatedness (inter-class similarities) to learn more discriminative group-specific deep representations, our deep multi-task learning algorithm can train more discriminative node classifiers for distinguishing the visually-similar atomic object classes effectively. Our hierarchical deep multi-task learning (HD-MTL) algorithm can integrate two discriminative regularization terms to control the inter-level error propagation effectively, and it can provide an end-to-end approach for jointly learning more representative deep CNNs (for image representation) and more discriminative tree classifier (for large-scale visual recognition) and updating them simultaneously. Our incremental deep learning algorithms can effectively adapt both the deep CNNs and the tree classifier to the new training images and the new object classes. Our experimental results have demonstrated that our HD-MTL algorithm can achieve very competitive results on improving the accuracy rates for large-scale visual recognition.

Decision Tree Algorithm-Generated Single-Nucleotide Polymorphism Barcodes of rbcL Genes for 38 Brassicaceae Species Tagging.

PubMed

Yang, Cheng-Hong; Wu, Kuo-Chuan; Chuang, Li-Yeh; Chang, Hsueh-Wei

2018-01-01

DNA barcode sequences are accumulating in large data sets. A barcode is generally a sequence larger than 1000 base pairs and generates a computational burden. Although the DNA barcode was originally envisioned as straightforward species tags, the identification usage of barcode sequences is rarely emphasized currently. Single-nucleotide polymorphism (SNP) association studies provide us an idea that the SNPs may be the ideal target of feature selection to discriminate between different species. We hypothesize that SNP-based barcodes may be more effective than the full length of DNA barcode sequences for species discrimination. To address this issue, we tested a r ibulose diphosphate carboxylase ( rbcL ) S NP b arcoding (RSB) strategy using a decision tree algorithm. After alignment and trimming, 31 SNPs were discovered in the rbcL sequences from 38 Brassicaceae plant species. In the decision tree construction, these SNPs were computed to set up the decision rule to assign the sequences into 2 groups level by level. After algorithm processing, 37 nodes and 31 loci were required for discriminating 38 species. Finally, the sequence tags consisting of 31 rbcL SNP barcodes were identified for discriminating 38 Brassicaceae species based on the decision tree-selected SNP pattern using RSB method. Taken together, this study provides the rational that the SNP aspect of DNA barcode for rbcL gene is a useful and effective sequence for tagging 38 Brassicaceae species.

Computational intelligence techniques for biological data mining: An overview

NASA Astrophysics Data System (ADS)

Faye, Ibrahima; Iqbal, Muhammad Javed; Said, Abas Md; Samir, Brahim Belhaouari

2014-10-01

Computational techniques have been successfully utilized for a highly accurate analysis and modeling of multifaceted and raw biological data gathered from various genome sequencing projects. These techniques are proving much more effective to overcome the limitations of the traditional in-vitro experiments on the constantly increasing sequence data. However, most critical problems that caught the attention of the researchers may include, but not limited to these: accurate structure and function prediction of unknown proteins, protein subcellular localization prediction, finding protein-protein interactions, protein fold recognition, analysis of microarray gene expression data, etc. To solve these problems, various classification and clustering techniques using machine learning have been extensively used in the published literature. These techniques include neural network algorithms, genetic algorithms, fuzzy ARTMAP, K-Means, K-NN, SVM, Rough set classifiers, decision tree and HMM based algorithms. Major difficulties in applying the above algorithms include the limitations found in the previous feature encoding and selection methods while extracting the best features, increasing classification accuracy and decreasing the running time overheads of the learning algorithms. The application of this research would be potentially useful in the drug design and in the diagnosis of some diseases. This paper presents a concise overview of the well-known protein classification techniques.

Enhancement of Fast Face Detection Algorithm Based on a Cascade of Decision Trees

NASA Astrophysics Data System (ADS)

Khryashchev, V. V.; Lebedev, A. A.; Priorov, A. L.

2017-05-01

Face detection algorithm based on a cascade of ensembles of decision trees (CEDT) is presented. The new approach allows detecting faces other than the front position through the use of multiple classifiers. Each classifier is trained for a specific range of angles of the rotation head. The results showed a high rate of productivity for CEDT on images with standard size. The algorithm increases the area under the ROC-curve of 13% compared to a standard Viola-Jones face detection algorithm. Final realization of given algorithm consist of 5 different cascades for frontal/non-frontal faces. One more thing which we take from the simulation results is a low computational complexity of CEDT algorithm in comparison with standard Viola-Jones approach. This could prove important in the embedded system and mobile device industries because it can reduce the cost of hardware and make battery life longer.

Automated Proton Track Identification in MicroBooNE Using Gradient Boosted Decision Trees

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

Woodruff, Katherine

MicroBooNE is a liquid argon time projection chamber (LArTPC) neutrino experiment that is currently running in the Booster Neutrino Beam at Fermilab. LArTPC technology allows for high-resolution, three-dimensional representations of neutrino interactions. A wide variety of software tools for automated reconstruction and selection of particle tracks in LArTPCs are actively being developed. Short, isolated proton tracks, the signal for low- momentum-transfer neutral current (NC) elastic events, are easily hidden in a large cosmic background. Detecting these low-energy tracks will allow us to probe interesting regions of the proton's spin structure. An effective method for selecting NC elastic events is tomore » combine a highly efficient track reconstruction algorithm to find all candidate tracks with highly accurate particle identification using a machine learning algorithm. We present our work on particle track classification using gradient tree boosting software (XGBoost) and the performance on simulated neutrino data.« less

Data-driven modeling of hydroclimatic trends and soil moisture: Multi-scale data integration and decision support

NASA Astrophysics Data System (ADS)

Coopersmith, Evan Joseph

The techniques and information employed for decision-making vary with the spatial and temporal scope of the assessment required. In modern agriculture, the farm owner or manager makes decisions on a day-to-day or even hour-to-hour basis for dozens of fields scattered over as much as a fifty-mile radius from some central location. Following precipitation events, land begins to dry. Land-owners and managers often trace serpentine paths of 150+ miles every morning to inspect the conditions of their various parcels. His or her objective lies in appropriate resource usage -- is a given tract of land dry enough to be workable at this moment or would he or she be better served waiting patiently? Longer-term, these owners and managers decide upon which seeds will grow most effectively and which crops will make their operations profitable. At even longer temporal scales, decisions are made regarding which fields must be acquired and sold and what types of equipment will be necessary in future operations. This work develops and validates algorithms for these shorter-term decisions, along with models of national climate patterns and climate changes to enable longer-term operational planning. A test site at the University of Illinois South Farms (Urbana, IL, USA) served as the primary location to validate machine learning algorithms, employing public sources of precipitation and potential evapotranspiration to model the wetting/drying process. In expanding such local decision support tools to locations on a national scale, one must recognize the heterogeneity of hydroclimatic and soil characteristics throughout the United States. Machine learning algorithms modeling the wetting/drying process must address this variability, and yet it is wholly impractical to construct a separate algorithm for every conceivable location. For this reason, a national hydrological classification system is presented, allowing clusters of hydroclimatic similarity to emerge naturally from annual regime curve data and facilitate the development of cluster-specific algorithms. Given the desire to enable intelligent decision-making at any location, this classification system is developed in a manner that will allow for classification anywhere in the U.S., even in an ungauged basin. Daily time series data from 428 catchments in the MOPEX database are analyzed to produce an empirical classification tree, partitioning the United States into regions of hydroclimatic similarity. In constructing a classification tree based upon 55 years of data, it is important to recognize the non-stationary nature of climate data. The shifts in climatic regimes will cause certain locations to shift their ultimate position within the classification tree, requiring decision-makers to alter land usage, farming practices, and equipment needs, and algorithms to adjust accordingly. This work adapts the classification model to address the issue of regime shifts over larger temporal scales and suggests how land-usage and farming protocol may vary from hydroclimatic shifts in decades to come. Finally, the generalizability of the hydroclimatic classification system is tested with a physically-based soil moisture model calibrated at several locations throughout the continental United States. The soil moisture model is calibrated at a given site and then applied with the same parameters at other sites within and outside the same hydroclimatic class. The model's performance deteriorates minimally if the calibration and validation location are within the same hydroclimatic class, but deteriorates significantly if the calibration and validates sites are located in different hydroclimatic classes. These soil moisture estimates at the field scale are then further refined by the introduction of LiDAR elevation data, distinguishing faster-drying peaks and ridges from slower-drying valleys. The inclusion of LiDAR enabled multiple locations within the same field to be predicted accurately despite non-identical topography. This cross-application of parametric calibrations and LiDAR-driven disaggregation facilitates decision-support at locations without proximally-located soil moisture sensors.

Application of preprocessing filtering on Decision Tree C4.5 and rough set theory

NASA Astrophysics Data System (ADS)

Chan, Joseph C. C.; Lin, Tsau Y.

2001-03-01

This paper compares two artificial intelligence methods: the Decision Tree C4.5 and Rough Set Theory on the stock market data. The Decision Tree C4.5 is reviewed with the Rough Set Theory. An enhanced window application is developed to facilitate the pre-processing filtering by introducing the feature (attribute) transformations, which allows users to input formulas and create new attributes. Also, the application produces three varieties of data set with delaying, averaging, and summation. The results prove the improvement of pre-processing by applying feature (attribute) transformations on Decision Tree C4.5. Moreover, the comparison between Decision Tree C4.5 and Rough Set Theory is based on the clarity, automation, accuracy, dimensionality, raw data, and speed, which is supported by the rules sets generated by both algorithms on three different sets of data.

Quantifying the Beauty of Words: A Neurocognitive Poetics Perspective

PubMed Central

Jacobs, Arthur M.

2017-01-01

In this paper I would like to pave the ground for future studies in Computational Stylistics and (Neuro-)Cognitive Poetics by describing procedures for predicting the subjective beauty of words. A set of eight tentative word features is computed via Quantitative Narrative Analysis (QNA) and a novel metric for quantifying word beauty, the aesthetic potential is proposed. Application of machine learning algorithms fed with this QNA data shows that a classifier of the decision tree family excellently learns to split words into beautiful vs. ugly ones. The results shed light on surface and semantic features theoretically relevant for affective-aesthetic processes in literary reading and generate quantitative predictions for neuroaesthetic studies of verbal materials. PMID:29311877

Quantifying the Beauty of Words: A Neurocognitive Poetics Perspective.

PubMed

Jacobs, Arthur M

2017-01-01

In this paper I would like to pave the ground for future studies in Computational Stylistics and (Neuro-)Cognitive Poetics by describing procedures for predicting the subjective beauty of words. A set of eight tentative word features is computed via Quantitative Narrative Analysis (QNA) and a novel metric for quantifying word beauty, the aesthetic potential is proposed. Application of machine learning algorithms fed with this QNA data shows that a classifier of the decision tree family excellently learns to split words into beautiful vs. ugly ones. The results shed light on surface and semantic features theoretically relevant for affective-aesthetic processes in literary reading and generate quantitative predictions for neuroaesthetic studies of verbal materials.

What Satisfies Students? Mining Student-Opinion Data with Regression and Decision-Tree Analysis. AIR 2002 Forum Paper.

ERIC Educational Resources Information Center

Thomas, Emily H.; Galambos, Nora

To investigate how students' characteristics and experiences affect satisfaction, this study used regression and decision-tree analysis with the CHAID algorithm to analyze student opinion data from a sample of 1,783 college students. A data-mining approach identifies the specific aspects of students' university experience that most influence three…

Machine Learning Through Signature Trees. Applications to Human Speech.

ERIC Educational Resources Information Center

White, George M.

A signature tree is a binary decision tree used to classify unknown patterns. An attempt was made to develop a computer program for manipulating signature trees as a general research tool for exploring machine learning and pattern recognition. The program was applied to the problem of speech recognition to test its effectiveness for a specific…

FCMPSO: An Imputation for Missing Data Features in Heart Disease Classification

NASA Astrophysics Data System (ADS)

Salleh, Mohd Najib Mohd; Ashikin Samat, Nurul

2017-08-01

The application of data mining and machine learning in directing clinical research into possible hidden knowledge is becoming greatly influential in medical areas. Heart Disease is a killer disease around the world, and early prevention through efficient methods can help to reduce the mortality number. Medical data may contain many uncertainties, as they are fuzzy and vague in nature. Nonetheless, imprecise features data such as no values and missing values can affect quality of classification results. Nevertheless, the other complete features are still capable to give information in certain features. Therefore, an imputation approach based on Fuzzy C-Means and Particle Swarm Optimization (FCMPSO) is developed in preprocessing stage to help fill in the missing values. Then, the complete dataset is trained in classification algorithm, Decision Tree. The experiment is trained with Heart Disease dataset and the performance is analysed using accuracy, precision, and ROC values. Results show that the performance of Decision Tree is increased after the application of FCMSPO for imputation.

New Splitting Criteria for Decision Trees in Stationary Data Streams.

PubMed

Jaworski, Maciej; Duda, Piotr; Rutkowski, Leszek; Jaworski, Maciej; Duda, Piotr; Rutkowski, Leszek; Rutkowski, Leszek; Duda, Piotr; Jaworski, Maciej

2018-06-01

The most popular tools for stream data mining are based on decision trees. In previous 15 years, all designed methods, headed by the very fast decision tree algorithm, relayed on Hoeffding's inequality and hundreds of researchers followed this scheme. Recently, we have demonstrated that although the Hoeffding decision trees are an effective tool for dealing with stream data, they are a purely heuristic procedure; for example, classical decision trees such as ID3 or CART cannot be adopted to data stream mining using Hoeffding's inequality. Therefore, there is an urgent need to develop new algorithms, which are both mathematically justified and characterized by good performance. In this paper, we address this problem by developing a family of new splitting criteria for classification in stationary data streams and investigating their probabilistic properties. The new criteria, derived using appropriate statistical tools, are based on the misclassification error and the Gini index impurity measures. The general division of splitting criteria into two types is proposed. Attributes chosen based on type- splitting criteria guarantee, with high probability, the highest expected value of split measure. Type- criteria ensure that the chosen attribute is the same, with high probability, as it would be chosen based on the whole infinite data stream. Moreover, in this paper, two hybrid splitting criteria are proposed, which are the combinations of single criteria based on the misclassification error and Gini index.

Robust Blind Learning Algorithm for Nonlinear Equalization Using Input Decision Information.

PubMed

Xu, Lu; Huang, Defeng David; Guo, Yingjie Jay

2015-12-01

In this paper, we propose a new blind learning algorithm, namely, the Benveniste-Goursat input-output decision (BG-IOD), to enhance the convergence performance of neural network-based equalizers for nonlinear channel equalization. In contrast to conventional blind learning algorithms, where only the output of the equalizer is employed for updating system parameters, the BG-IOD exploits a new type of extra information, the input decision information obtained from the input of the equalizer, to mitigate the influence of the nonlinear equalizer structure on parameters learning, thereby leading to improved convergence performance. We prove that, with the input decision information, a desirable convergence capability that the output symbol error rate (SER) is always less than the input SER if the input SER is below a threshold, can be achieved. Then, the BG soft-switching technique is employed to combine the merits of both input and output decision information, where the former is used to guarantee SER convergence and the latter is to improve SER performance. Simulation results show that the proposed algorithm outperforms conventional blind learning algorithms, such as stochastic quadratic distance and dual mode constant modulus algorithm, in terms of both convergence performance and SER performance, for nonlinear equalization.

Global Bathymetry: Machine Learning for Data Editing

NASA Astrophysics Data System (ADS)

Sandwell, D. T.; Tea, B.; Freund, Y.

2017-12-01

The accuracy of global bathymetry depends primarily on the coverage and accuracy of the sounding data and secondarily on the depth predicted from gravity. A main focus of our research is to add newly-available data to the global compilation. Most data sources have 1-12% of erroneous soundings caused by a wide array of blunders and measurement errors. Over the years we have hand-edited this data using undergraduate employees at UCSD (440 million soundings at 500 m resolution). We are developing a machine learning approach to refine the flagging of the older soundings and provide automated editing of newly-acquired soundings. The approach has three main steps: 1) Combine the sounding data with additional information that may inform the machine learning algorithm. The additional parameters include: depth predicted from gravity; distance to the nearest sounding from other cruises; seafloor age; spreading rate; sediment thickness; and vertical gravity gradient. 2) Use available edit decisions as training data sets for a boosted tree algorithm with a binary logistic objective function and L2 regularization. Initial results with poor quality single beam soundings show that the automated algorithm matches the hand-edited data 89% of the time. The results show that most of the information for detecting outliers comes from predicted depth with secondary contributions from distance to the nearest sounding and longitude. A similar analysis using very high quality multibeam data shows that the automated algorithm matches the hand-edited data 93% of the time. Again, most of the information for detecting outliers comes from predicted depth secondary contributions from distance to the nearest sounding and longitude. 3) The third step in the process is to use the machine learning parameters, derived from the training data, to edit 12 million newly acquired single beam sounding data provided by the National Geospatial-Intelligence Agency. The output of the learning algorithm will be confidence ratedindicating which edits the algorithm is confident on and which it is not confident. We expect the majority ( 90%) of edits to be confident and not require human intervention. Human intervention will be required only on the 10% unconfident decisions, thus reducing the amount of human work by a factor of 10 or more.

Self-Learning Embedded System for Object Identification in Intelligent Infrastructure Sensors.

PubMed

Villaverde, Monica; Perez, David; Moreno, Felix

2015-11-17

The emergence of new horizons in the field of travel assistant management leads to the development of cutting-edge systems focused on improving the existing ones. Moreover, new opportunities are being also presented since systems trend to be more reliable and autonomous. In this paper, a self-learning embedded system for object identification based on adaptive-cooperative dynamic approaches is presented for intelligent sensor's infrastructures. The proposed system is able to detect and identify moving objects using a dynamic decision tree. Consequently, it combines machine learning algorithms and cooperative strategies in order to make the system more adaptive to changing environments. Therefore, the proposed system may be very useful for many applications like shadow tolls since several types of vehicles may be distinguished, parking optimization systems, improved traffic conditions systems, etc.

Classifying smoking urges via machine learning.

PubMed

Dumortier, Antoine; Beckjord, Ellen; Shiffman, Saul; Sejdić, Ervin

2016-12-01

Smoking is the largest preventable cause of death and diseases in the developed world, and advances in modern electronics and machine learning can help us deliver real-time intervention to smokers in novel ways. In this paper, we examine different machine learning approaches to use situational features associated with having or not having urges to smoke during a quit attempt in order to accurately classify high-urge states. To test our machine learning approaches, specifically, Bayes, discriminant analysis and decision tree learning methods, we used a dataset collected from over 300 participants who had initiated a quit attempt. The three classification approaches are evaluated observing sensitivity, specificity, accuracy and precision. The outcome of the analysis showed that algorithms based on feature selection make it possible to obtain high classification rates with only a few features selected from the entire dataset. The classification tree method outperformed the naive Bayes and discriminant analysis methods, with an accuracy of the classifications up to 86%. These numbers suggest that machine learning may be a suitable approach to deal with smoking cessation matters, and to predict smoking urges, outlining a potential use for mobile health applications. In conclusion, machine learning classifiers can help identify smoking situations, and the search for the best features and classifier parameters significantly improves the algorithms' performance. In addition, this study also supports the usefulness of new technologies in improving the effect of smoking cessation interventions, the management of time and patients by therapists, and thus the optimization of available health care resources. Future studies should focus on providing more adaptive and personalized support to people who really need it, in a minimum amount of time by developing novel expert systems capable of delivering real-time interventions. Copyright © 2016 Elsevier Ireland Ltd. All rights reserved.

Learning to change taxonomies

NASA Astrophysics Data System (ADS)

Eneva, Elena; Petrushin, Valery A.

2002-03-01

Taxonomies are valuable tools for structuring and representing our knowledge about the world. They are widely used in many domains, where information about species, products, customers, publications, etc. needs to be organized. In the absence of standards, many taxonomies of the same entities can co-exist. A problem arises when data categorized in a particular taxonomy needs to be used by a procedure (methodology or algorithm) that uses a different taxonomy. Usually, a labor-intensive manual approach is used to solve this problem. This paper describes a machine learning approach which aids domain experts in changing taxonomies. It allows learning relationships between two taxonomies and mapping the data from one taxonomy into another. The proposed approach uses decision trees and bootstrapping for learning mappings of instances from the source to the target taxonomies. A C4.5 decision tree classifier is trained on a small manually labeled training set and applied to a randomly selected sample from the unlabeled data. The classification results are analyzed and the misclassified items are corrected and all items are added to the training set. This procedure is iterated until unlabeled data is available or an acceptable error rate is reached. In the latter case the last classifier is used to label all the remaining data. We test our approach on a database of products obtained from as grocery store chain and find that it performs well, reaching 92.6% accuracy while requiring the human expert to explicitly label only 18% of the entire data.

Solar Flare Prediction Model with Three Machine-learning Algorithms using Ultraviolet Brightening and Vector Magnetograms

NASA Astrophysics Data System (ADS)

Nishizuka, N.; Sugiura, K.; Kubo, Y.; Den, M.; Watari, S.; Ishii, M.

2017-02-01

We developed a flare prediction model using machine learning, which is optimized to predict the maximum class of flares occurring in the following 24 hr. Machine learning is used to devise algorithms that can learn from and make decisions on a huge amount of data. We used solar observation data during the period 2010-2015, such as vector magnetograms, ultraviolet (UV) emission, and soft X-ray emission taken by the Solar Dynamics Observatory and the Geostationary Operational Environmental Satellite. We detected active regions (ARs) from the full-disk magnetogram, from which ˜60 features were extracted with their time differentials, including magnetic neutral lines, the current helicity, the UV brightening, and the flare history. After standardizing the feature database, we fully shuffled and randomly separated it into two for training and testing. To investigate which algorithm is best for flare prediction, we compared three machine-learning algorithms: the support vector machine, k-nearest neighbors (k-NN), and extremely randomized trees. The prediction score, the true skill statistic, was higher than 0.9 with a fully shuffled data set, which is higher than that for human forecasts. It was found that k-NN has the highest performance among the three algorithms. The ranking of the feature importance showed that previous flare activity is most effective, followed by the length of magnetic neutral lines, the unsigned magnetic flux, the area of UV brightening, and the time differentials of features over 24 hr, all of which are strongly correlated with the flux emergence dynamics in an AR.

Solar Flare Prediction Model with Three Machine-learning Algorithms using Ultraviolet Brightening and Vector Magnetograms

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

Nishizuka, N.; Kubo, Y.; Den, M.

We developed a flare prediction model using machine learning, which is optimized to predict the maximum class of flares occurring in the following 24 hr. Machine learning is used to devise algorithms that can learn from and make decisions on a huge amount of data. We used solar observation data during the period 2010–2015, such as vector magnetograms, ultraviolet (UV) emission, and soft X-ray emission taken by the Solar Dynamics Observatory and the Geostationary Operational Environmental Satellite . We detected active regions (ARs) from the full-disk magnetogram, from which ∼60 features were extracted with their time differentials, including magnetic neutralmore » lines, the current helicity, the UV brightening, and the flare history. After standardizing the feature database, we fully shuffled and randomly separated it into two for training and testing. To investigate which algorithm is best for flare prediction, we compared three machine-learning algorithms: the support vector machine, k-nearest neighbors (k-NN), and extremely randomized trees. The prediction score, the true skill statistic, was higher than 0.9 with a fully shuffled data set, which is higher than that for human forecasts. It was found that k-NN has the highest performance among the three algorithms. The ranking of the feature importance showed that previous flare activity is most effective, followed by the length of magnetic neutral lines, the unsigned magnetic flux, the area of UV brightening, and the time differentials of features over 24 hr, all of which are strongly correlated with the flux emergence dynamics in an AR.« less

Evaluation of machine learning algorithms for classification of primary biological aerosol using a new UV-LIF spectrometer

NASA Astrophysics Data System (ADS)

Ruske, Simon; Topping, David O.; Foot, Virginia E.; Kaye, Paul H.; Stanley, Warren R.; Crawford, Ian; Morse, Andrew P.; Gallagher, Martin W.

2017-03-01

Characterisation of bioaerosols has important implications within environment and public health sectors. Recent developments in ultraviolet light-induced fluorescence (UV-LIF) detectors such as the Wideband Integrated Bioaerosol Spectrometer (WIBS) and the newly introduced Multiparameter Bioaerosol Spectrometer (MBS) have allowed for the real-time collection of fluorescence, size and morphology measurements for the purpose of discriminating between bacteria, fungal spores and pollen.This new generation of instruments has enabled ever larger data sets to be compiled with the aim of studying more complex environments. In real world data sets, particularly those from an urban environment, the population may be dominated by non-biological fluorescent interferents, bringing into question the accuracy of measurements of quantities such as concentrations. It is therefore imperative that we validate the performance of different algorithms which can be used for the task of classification.For unsupervised learning we tested hierarchical agglomerative clustering with various different linkages. For supervised learning, 11 methods were tested, including decision trees, ensemble methods (random forests, gradient boosting and AdaBoost), two implementations for support vector machines (libsvm and liblinear) and Gaussian methods (Gaussian naïve Bayesian, quadratic and linear discriminant analysis, the k-nearest neighbours algorithm and artificial neural networks).The methods were applied to two different data sets produced using the new MBS, which provides multichannel UV-LIF fluorescence signatures for single airborne biological particles. The first data set contained mixed PSLs and the second contained a variety of laboratory-generated aerosol.Clustering in general performs slightly worse than the supervised learning methods, correctly classifying, at best, only 67. 6 and 91. 1 % for the two data sets respectively. For supervised learning the gradient boosting algorithm was found to be the most effective, on average correctly classifying 82. 8 and 98. 27 % of the testing data, respectively, across the two data sets.A possible alternative to gradient boosting is neural networks. We do however note that this method requires much more user input than the other methods, and we suggest that further research should be conducted using this method, especially using parallelised hardware such as the GPU, which would allow for larger networks to be trained, which could possibly yield better results.We also saw that some methods, such as clustering, failed to utilise the additional shape information provided by the instrument, whilst for others, such as the decision trees, ensemble methods and neural networks, improved performance could be attained with the inclusion of such information.

Blood oxygen level dependent magnetic resonance imaging for detecting pathological patterns in lupus nephritis patients: a preliminary study using a decision tree model.

PubMed

Shi, Huilan; Jia, Junya; Li, Dong; Wei, Li; Shang, Wenya; Zheng, Zhenfeng

2018-02-09

Precise renal histopathological diagnosis will guide therapy strategy in patients with lupus nephritis. Blood oxygen level dependent (BOLD) magnetic resonance imaging (MRI) has been applicable noninvasive technique in renal disease. This current study was performed to explore whether BOLD MRI could contribute to diagnose renal pathological pattern. Adult patients with lupus nephritis renal pathological diagnosis were recruited for this study. Renal biopsy tissues were assessed based on the lupus nephritis ISN/RPS 2003 classification. The Blood oxygen level dependent magnetic resonance imaging (BOLD-MRI) was used to obtain functional magnetic resonance parameter, R2* values. Several functions of R2* values were calculated and used to construct algorithmic models for renal pathological patterns. In addition, the algorithmic models were compared as to their diagnostic capability. Both Histopathology and BOLD MRI were used to examine a total of twelve patients. Renal pathological patterns included five classes III (including 3 as class III + V) and seven classes IV (including 4 as class IV + V). Three algorithmic models, including decision tree, line discriminant, and logistic regression, were constructed to distinguish the renal pathological pattern of class III and class IV. The sensitivity of the decision tree model was better than that of the line discriminant model (71.87% vs 59.48%, P < 0.001) and inferior to that of the Logistic regression model (71.87% vs 78.71%, P < 0.001). The specificity of decision tree model was equivalent to that of the line discriminant model (63.87% vs 63.73%, P = 0.939) and higher than that of the logistic regression model (63.87% vs 38.0%, P < 0.001). The Area under the ROC curve (AUROCC) of the decision tree model was greater than that of the line discriminant model (0.765 vs 0.629, P < 0.001) and logistic regression model (0.765 vs 0.662, P < 0.001). BOLD MRI is a useful non-invasive imaging technique for the evaluation of lupus nephritis. Decision tree models constructed using functions of R2* values may facilitate the prediction of renal pathological patterns.

Could machine learning improve the prediction of pelvic nodal status of prostate cancer patients? Preliminary results of a pilot study.

PubMed

De Bari, B; Vallati, M; Gatta, R; Simeone, C; Girelli, G; Ricardi, U; Meattini, I; Gabriele, P; Bellavita, R; Krengli, M; Cafaro, I; Cagna, E; Bunkheila, F; Borghesi, S; Signor, M; Di Marco, A; Bertoni, F; Stefanacci, M; Pasinetti, N; Buglione, M; Magrini, S M

2015-07-01

We tested and compared performances of Roach formula, Partin tables and of three Machine Learning (ML) based algorithms based on decision trees in identifying N+ prostate cancer (PC). 1,555 cN0 and 50 cN+ PC were analyzed. Results were also verified on an independent population of 204 operated cN0 patients, with a known pN status (187 pN0, 17 pN1 patients). ML performed better, also when tested on the surgical population, with accuracy, specificity, and sensitivity ranging between 48-86%, 35-91%, and 17-79%, respectively. ML potentially allows better prediction of the nodal status of PC, potentially allowing a better tailoring of pelvic irradiation.

Occupancy schedules learning process through a data mining framework

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

D'Oca, Simona; Hong, Tianzhen

Building occupancy is a paramount factor in building energy simulations. Specifically, lighting, plug loads, HVAC equipment utilization, fresh air requirements and internal heat gain or loss greatly depends on the level of occupancy within a building. Developing the appropriate methodologies to describe and reproduce the intricate network responsible for human-building interactions are needed. Extrapolation of patterns from big data streams is a powerful analysis technique which will allow for a better understanding of energy usage in buildings. A three-step data mining framework is applied to discover occupancy patterns in office spaces. First, a data set of 16 offices with 10more » minute interval occupancy data, over a two year period is mined through a decision tree model which predicts the occupancy presence. Then a rule induction algorithm is used to learn a pruned set of rules on the results from the decision tree model. Finally, a cluster analysis is employed in order to obtain consistent patterns of occupancy schedules. Furthermore, the identified occupancy rules and schedules are representative as four archetypal working profiles that can be used as input to current building energy modeling programs, such as EnergyPlus or IDA-ICE, to investigate impact of occupant presence on design, operation and energy use in office buildings.« less

Occupancy schedules learning process through a data mining framework

DOE PAGES

D'Oca, Simona; Hong, Tianzhen

2014-12-17

Building occupancy is a paramount factor in building energy simulations. Specifically, lighting, plug loads, HVAC equipment utilization, fresh air requirements and internal heat gain or loss greatly depends on the level of occupancy within a building. Developing the appropriate methodologies to describe and reproduce the intricate network responsible for human-building interactions are needed. Extrapolation of patterns from big data streams is a powerful analysis technique which will allow for a better understanding of energy usage in buildings. A three-step data mining framework is applied to discover occupancy patterns in office spaces. First, a data set of 16 offices with 10more » minute interval occupancy data, over a two year period is mined through a decision tree model which predicts the occupancy presence. Then a rule induction algorithm is used to learn a pruned set of rules on the results from the decision tree model. Finally, a cluster analysis is employed in order to obtain consistent patterns of occupancy schedules. Furthermore, the identified occupancy rules and schedules are representative as four archetypal working profiles that can be used as input to current building energy modeling programs, such as EnergyPlus or IDA-ICE, to investigate impact of occupant presence on design, operation and energy use in office buildings.« less

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.

Holoentropy enabled-decision tree for automatic classification of diabetic retinopathy using retinal fundus images.

PubMed

Mane, Vijay Mahadeo; Jadhav, D V

2017-05-24

Diabetic retinopathy (DR) is the most common diabetic eye disease. Doctors are using various test methods to detect DR. But, the availability of test methods and requirements of domain experts pose a new challenge in the automatic detection of DR. In order to fulfill this objective, a variety of algorithms has been developed in the literature. In this paper, we propose a system consisting of a novel sparking process and a holoentropy-based decision tree for automatic classification of DR images to further improve the effectiveness. The sparking process algorithm is developed for automatic segmentation of blood vessels through the estimation of optimal threshold. The holoentropy enabled decision tree is newly developed for automatic classification of retinal images into normal or abnormal using hybrid features which preserve the disease-level patterns even more than the signal level of the feature. The effectiveness of the proposed system is analyzed using standard fundus image databases DIARETDB0 and DIARETDB1 for sensitivity, specificity and accuracy. The proposed system yields sensitivity, specificity and accuracy values of 96.72%, 97.01% and 96.45%, respectively. The experimental result reveals that the proposed technique outperforms the existing algorithms.

Application of data mining techniques to explore predictors of HCC in Egyptian patients with HCV-related chronic liver disease.

PubMed

Omran, Dalia Abd El Hamid; Awad, AbuBakr Hussein; Mabrouk, Mahasen Abd El Rahman; Soliman, Ahmad Fouad; Aziz, Ashraf Omar Abdel

2015-01-01

Hepatocellular carcinoma (HCC) is the second most common malignancy in Egypt. Data mining is a method of predictive analysis which can explore tremendous volumes of information to discover hidden patterns and relationships. Our aim here was to develop a non-invasive algorithm for prediction of HCC. Such an algorithm should be economical, reliable, easy to apply and acceptable by domain experts. This cross-sectional study enrolled 315 patients with hepatitis C virus (HCV) related chronic liver disease (CLD); 135 HCC, 116 cirrhotic patients without HCC and 64 patients with chronic hepatitis C. Using data mining analysis, we constructed a decision tree learning algorithm to predict HCC. The decision tree algorithm was able to predict HCC with recall (sensitivity) of 83.5% and precession (specificity) of 83.3% using only routine data. The correctly classified instances were 259 (82.2%), and the incorrectly classified instances were 56 (17.8%). Out of 29 attributes, serum alpha fetoprotein (AFP), with an optimal cutoff value of ≥50.3 ng/ml was selected as the best predictor of HCC. To a lesser extent, male sex, presence of cirrhosis, AST>64U/L, and ascites were variables associated with HCC. Data mining analysis allows discovery of hidden patterns and enables the development of models to predict HCC, utilizing routine data as an alternative to CT and liver biopsy. This study has highlighted a new cutoff for AFP (≥50.3 ng/ml). Presence of a score of >2 risk variables (out of 5) can successfully predict HCC with a sensitivity of 96% and specificity of 82%.

Fault diagnosis of helical gearbox using acoustic signal and wavelets

NASA Astrophysics Data System (ADS)

Pranesh, SK; Abraham, Siju; Sugumaran, V.; Amarnath, M.

2017-05-01

The efficient transmission of power in machines is needed and gears are an appropriate choice. Faults in gears result in loss of energy and money. The monitoring and fault diagnosis are done by analysis of the acoustic and vibrational signals which are generally considered to be unwanted by products. This study proposes the usage of machine learning algorithm for condition monitoring of a helical gearbox by using the sound signals produced by the gearbox. Artificial faults were created and subsequently signals were captured by a microphone. An extensive study using different wavelet transformations for feature extraction from the acoustic signals was done, followed by waveletselection and feature selection using J48 decision tree and feature classification was performed using K star algorithm. Classification accuracy of 100% was obtained in the study

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.

Visual saliency-based fast intracoding algorithm for high efficiency video coding

NASA Astrophysics Data System (ADS)

Zhou, Xin; Shi, Guangming; Zhou, Wei; Duan, Zhemin

2017-01-01

Intraprediction has been significantly improved in high efficiency video coding over H.264/AVC with quad-tree-based coding unit (CU) structure from size 64×64 to 8×8 and more prediction modes. However, these techniques cause a dramatic increase in computational complexity. An intracoding algorithm is proposed that consists of perceptual fast CU size decision algorithm and fast intraprediction mode decision algorithm. First, based on the visual saliency detection, an adaptive and fast CU size decision method is proposed to alleviate intraencoding complexity. Furthermore, a fast intraprediction mode decision algorithm with step halving rough mode decision method and early modes pruning algorithm is presented to selectively check the potential modes and effectively reduce the complexity of computation. Experimental results show that our proposed fast method reduces the computational complexity of the current HM to about 57% in encoding time with only 0.37% increases in BD rate. Meanwhile, the proposed fast algorithm has reasonable peak signal-to-noise ratio losses and nearly the same subjective perceptual quality.

Machine learning methods can replace 3D profile method in classification of amyloidogenic hexapeptides.

PubMed

Stanislawski, Jerzy; Kotulska, Malgorzata; Unold, Olgierd

2013-01-17

Amyloids are proteins capable of forming fibrils. Many of them underlie serious diseases, like Alzheimer disease. The number of amyloid-associated diseases is constantly increasing. Recent studies indicate that amyloidogenic properties can be associated with short segments of aminoacids, which transform the structure when exposed. A few hundreds of such peptides have been experimentally found. Experimental testing of all possible aminoacid combinations is currently not feasible. Instead, they can be predicted by computational methods. 3D profile is a physicochemical-based method that has generated the most numerous dataset - ZipperDB. However, it is computationally very demanding. Here, we show that dataset generation can be accelerated. Two methods to increase the classification efficiency of amyloidogenic candidates are presented and tested: simplified 3D profile generation and machine learning methods. We generated a new dataset of hexapeptides, using more economical 3D profile algorithm, which showed very good classification overlap with ZipperDB (93.5%). The new part of our dataset contains 1779 segments, with 204 classified as amyloidogenic. The dataset of 6-residue sequences with their binary classification, based on the energy of the segment, was applied for training machine learning methods. A separate set of sequences from ZipperDB was used as a test set. The most effective methods were Alternating Decision Tree and Multilayer Perceptron. Both methods obtained area under ROC curve of 0.96, accuracy 91%, true positive rate ca. 78%, and true negative rate 95%. A few other machine learning methods also achieved a good performance. The computational time was reduced from 18-20 CPU-hours (full 3D profile) to 0.5 CPU-hours (simplified 3D profile) to seconds (machine learning). We showed that the simplified profile generation method does not introduce an error with regard to the original method, while increasing the computational efficiency. Our new dataset proved representative enough to use simple statistical methods for testing the amylogenicity based only on six letter sequences. Statistical machine learning methods such as Alternating Decision Tree and Multilayer Perceptron can replace the energy based classifier, with advantage of very significantly reduced computational time and simplicity to perform the analysis. Additionally, a decision tree provides a set of very easily interpretable rules.

Statistical Methods in Ai: Rare Event Learning Using Associative Rules and Higher-Order Statistics

NASA Astrophysics Data System (ADS)

Iyer, V.; Shetty, S.; Iyengar, S. S.

2015-07-01

Rare event learning has not been actively researched since lately due to the unavailability of algorithms which deal with big samples. The research addresses spatio-temporal streams from multi-resolution sensors to find actionable items from a perspective of real-time algorithms. This computing framework is independent of the number of input samples, application domain, labelled or label-less streams. A sampling overlap algorithm such as Brooks-Iyengar is used for dealing with noisy sensor streams. We extend the existing noise pre-processing algorithms using Data-Cleaning trees. Pre-processing using ensemble of trees using bagging and multi-target regression showed robustness to random noise and missing data. As spatio-temporal streams are highly statistically correlated, we prove that a temporal window based sampling from sensor data streams converges after n samples using Hoeffding bounds. Which can be used for fast prediction of new samples in real-time. The Data-cleaning tree model uses a nonparametric node splitting technique, which can be learned in an iterative way which scales linearly in memory consumption for any size input stream. The improved task based ensemble extraction is compared with non-linear computation models using various SVM kernels for speed and accuracy. We show using empirical datasets the explicit rule learning computation is linear in time and is only dependent on the number of leafs present in the tree ensemble. The use of unpruned trees (t) in our proposed ensemble always yields minimum number (m) of leafs keeping pre-processing computation to n × t log m compared to N2 for Gram Matrix. We also show that the task based feature induction yields higher Qualify of Data (QoD) in the feature space compared to kernel methods using Gram Matrix.

A Machine Learning Framework for Plan Payment Risk Adjustment.

PubMed

Rose, Sherri

2016-12-01

To introduce cross-validation and a nonparametric machine learning framework for plan payment risk adjustment and then assess whether they have the potential to improve risk adjustment. 2011-2012 Truven MarketScan database. We compare the performance of multiple statistical approaches within a broad machine learning framework for estimation of risk adjustment formulas. Total annual expenditure was predicted using age, sex, geography, inpatient diagnoses, and hierarchical condition category variables. The methods included regression, penalized regression, decision trees, neural networks, and an ensemble super learner, all in concert with screening algorithms that reduce the set of variables considered. The performance of these methods was compared based on cross-validated R 2 . Our results indicate that a simplified risk adjustment formula selected via this nonparametric framework maintains much of the efficiency of a traditional larger formula. The ensemble approach also outperformed classical regression and all other algorithms studied. The implementation of cross-validated machine learning techniques provides novel insight into risk adjustment estimation, possibly allowing for a simplified formula, thereby reducing incentives for increased coding intensity as well as the ability of insurers to "game" the system with aggressive diagnostic upcoding. © Health Research and Educational Trust.

Soft context clustering for F0 modeling in HMM-based speech synthesis

NASA Astrophysics Data System (ADS)

Khorram, Soheil; Sameti, Hossein; King, Simon

2015-12-01

This paper proposes the use of a new binary decision tree, which we call a soft decision tree, to improve generalization performance compared to the conventional `hard' decision tree method that is used to cluster context-dependent model parameters in statistical parametric speech synthesis. We apply the method to improve the modeling of fundamental frequency, which is an important factor in synthesizing natural-sounding high-quality speech. Conventionally, hard decision tree-clustered hidden Markov models (HMMs) are used, in which each model parameter is assigned to a single leaf node. However, this `divide-and-conquer' approach leads to data sparsity, with the consequence that it suffers from poor generalization, meaning that it is unable to accurately predict parameters for models of unseen contexts: the hard decision tree is a weak function approximator. To alleviate this, we propose the soft decision tree, which is a binary decision tree with soft decisions at the internal nodes. In this soft clustering method, internal nodes select both their children with certain membership degrees; therefore, each node can be viewed as a fuzzy set with a context-dependent membership function. The soft decision tree improves model generalization and provides a superior function approximator because it is able to assign each context to several overlapped leaves. In order to use such a soft decision tree to predict the parameters of the HMM output probability distribution, we derive the smoothest (maximum entropy) distribution which captures all partial first-order moments and a global second-order moment of the training samples. Employing such a soft decision tree architecture with maximum entropy distributions, a novel speech synthesis system is trained using maximum likelihood (ML) parameter re-estimation and synthesis is achieved via maximum output probability parameter generation. In addition, a soft decision tree construction algorithm optimizing a log-likelihood measure is developed. Both subjective and objective evaluations were conducted and indicate a considerable improvement over the conventional method.

Evaluation of Machine Learning Algorithms for Classification of Primary Biological Aerosol using a new UV-LIF spectrometer

NASA Astrophysics Data System (ADS)

Ruske, S. T.; Topping, D. O.; Foot, V. E.; Kaye, P. H.; Stanley, W. R.; Morse, A. P.; Crawford, I.; Gallagher, M. W.

2016-12-01

Characterisation of bio-aerosols has important implications within Environment and Public Health sectors. Recent developments in Ultra-Violet Light Induced Fluorescence (UV-LIF) detectors such as the Wideband Integrated bio-aerosol Spectrometer (WIBS) and the newly introduced Multiparameter bio-aerosol Spectrometer (MBS) has allowed for the real time collection of fluorescence, size and morphology measurements for the purpose of discriminating between bacteria, fungal Spores and pollen. This new generation of instruments has enabled ever-larger data sets to be compiled with the aim of studying more complex environments, yet the algorithms used for specie classification remain largely invalidated. It is therefore imperative that we validate the performance of different algorithms that can be used for the task of classification, which is the focus of this study. For unsupervised learning we test Hierarchical Agglomerative Clustering with various different linkages. For supervised learning, ten methods were tested; including decision trees, ensemble methods: Random Forests, Gradient Boosting and AdaBoost; two implementations for support vector machines: libsvm and liblinear; Gaussian methods: Gaussian naïve Bayesian, quadratic and linear discriminant analysis and finally the k-nearest neighbours algorithm. The methods were applied to two different data sets measured using a new Multiparameter bio-aerosol Spectrometer. We find that clustering, in general, performs slightly worse than the supervised learning methods correctly classifying, at best, only 72.7 and 91.1 percent for the two data sets. For supervised learning the gradient boosting algorithm was found to be the most effective, on average correctly classifying 88.1 and 97.8 percent of the testing data respectively across the two data sets. We discuss the wider relevance of these results with regards to challenging existing classification in real-world environments.

A data driven approach for condition monitoring of wind turbine blade using vibration signals through best-first tree algorithm and functional trees algorithm: A comparative study.

PubMed

Joshuva, A; Sugumaran, V

2017-03-01

Wind energy is one of the important renewable energy resources available in nature. It is one of the major resources for production of energy because of its dependability due to the development of the technology and relatively low cost. Wind energy is converted into electrical energy using rotating blades. Due to environmental conditions and large structure, the blades are subjected to various vibration forces that may cause damage to the blades. This leads to a liability in energy production and turbine shutdown. The downtime can be reduced when the blades are diagnosed continuously using structural health condition monitoring. These are considered as a pattern recognition problem which consists of three phases namely, feature extraction, feature selection, and feature classification. In this study, statistical features were extracted from vibration signals, feature selection was carried out using a J48 decision tree algorithm and feature classification was performed using best-first tree algorithm and functional trees algorithm. The better algorithm is suggested for fault diagnosis of wind turbine blade. Copyright © 2017 ISA. Published by Elsevier Ltd. All rights reserved.

Learning from examples - Generation and evaluation of decision trees for software resource analysis

NASA Technical Reports Server (NTRS)

Selby, Richard W.; Porter, Adam A.

1988-01-01

A general solution method for the automatic generation of decision (or classification) trees is investigated. The approach is to provide insights through in-depth empirical characterization and evaluation of decision trees for software resource data analysis. The trees identify classes of objects (software modules) that had high development effort. Sixteen software systems ranging from 3,000 to 112,000 source lines were selected for analysis from a NASA production environment. The collection and analysis of 74 attributes (or metrics), for over 4,700 objects, captured information about the development effort, faults, changes, design style, and implementation style. A total of 9,600 decision trees were automatically generated and evaluated. The trees correctly identified 79.3 percent of the software modules that had high development effort or faults, and the trees generated from the best parameter combinations correctly identified 88.4 percent of the modules on the average.

Behavioral Modeling for Mental Health using Machine Learning Algorithms.

PubMed

Srividya, M; Mohanavalli, S; Bhalaji, N

2018-04-03

Mental health is an indicator of emotional, psychological and social well-being of an individual. It determines how an individual thinks, feels and handle situations. Positive mental health helps one to work productively and realize their full potential. Mental health is important at every stage of life, from childhood and adolescence through adulthood. Many factors contribute to mental health problems which lead to mental illness like stress, social anxiety, depression, obsessive compulsive disorder, drug addiction, and personality disorders. It is becoming increasingly important to determine the onset of the mental illness to maintain proper life balance. The nature of machine learning algorithms and Artificial Intelligence (AI) can be fully harnessed for predicting the onset of mental illness. Such applications when implemented in real time will benefit the society by serving as a monitoring tool for individuals with deviant behavior. This research work proposes to apply various machine learning algorithms such as support vector machines, decision trees, naïve bayes classifier, K-nearest neighbor classifier and logistic regression to identify state of mental health in a target group. The responses obtained from the target group for the designed questionnaire were first subject to unsupervised learning techniques. The labels obtained as a result of clustering were validated by computing the Mean Opinion Score. These cluster labels were then used to build classifiers to predict the mental health of an individual. Population from various groups like high school students, college students and working professionals were considered as target groups. The research presents an analysis of applying the aforementioned machine learning algorithms on the target groups and also suggests directions for future work.

Photometric Supernova Classification with Machine Learning

NASA Astrophysics Data System (ADS)

Lochner, Michelle; McEwen, Jason D.; Peiris, Hiranya V.; Lahav, Ofer; Winter, Max K.

2016-08-01

Automated photometric supernova classification has become an active area of research in recent years in light of current and upcoming imaging surveys such as the Dark Energy Survey (DES) and the Large Synoptic Survey Telescope, given that spectroscopic confirmation of type for all supernovae discovered will be impossible. Here, we develop a multi-faceted classification pipeline, combining existing and new approaches. Our pipeline consists of two stages: extracting descriptive features from the light curves and classification using a machine learning algorithm. Our feature extraction methods vary from model-dependent techniques, namely SALT2 fits, to more independent techniques that fit parametric models to curves, to a completely model-independent wavelet approach. We cover a range of representative machine learning algorithms, including naive Bayes, k-nearest neighbors, support vector machines, artificial neural networks, and boosted decision trees (BDTs). We test the pipeline on simulated multi-band DES light curves from the Supernova Photometric Classification Challenge. Using the commonly used area under the curve (AUC) of the Receiver Operating Characteristic as a metric, we find that the SALT2 fits and the wavelet approach, with the BDTs algorithm, each achieve an AUC of 0.98, where 1 represents perfect classification. We find that a representative training set is essential for good classification, whatever the feature set or algorithm, with implications for spectroscopic follow-up. Importantly, we find that by using either the SALT2 or the wavelet feature sets with a BDT algorithm, accurate classification is possible purely from light curve data, without the need for any redshift information.

Learning Optimal Individualized Treatment Rules from Electronic Health Record Data

PubMed Central

Wang, Yuanjia; Wu, Peng; Liu, Ying; Weng, Chunhua; Zeng, Donglin

2016-01-01

Medical research is experiencing a paradigm shift from “one-size-fits-all” strategy to a precision medicine approach where the right therapy, for the right patient, and at the right time, will be prescribed. We propose a statistical method to estimate the optimal individualized treatment rules (ITRs) that are tailored according to subject-specific features using electronic health records (EHR) data. Our approach merges statistical modeling and medical domain knowledge with machine learning algorithms to assist personalized medical decision making using EHR. We transform the estimation of optimal ITR into a classification problem and account for the non-experimental features of the EHR data and confounding by clinical indication. We create a broad range of feature variables that reflect both patient health status and healthcare data collection process. Using EHR data collected at Columbia University clinical data warehouse, we construct a decision tree for choosing the best second line therapy for treating type 2 diabetes patients. PMID:28503676

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.

A decision tree algorithm for investigation of model biases related to dynamical cores and physical parameterizations: CESM/CAM EVALUATION BY DECISION TREES

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

Soner Yorgun, M.; Rood, Richard B.

An object-based evaluation method using a pattern recognition algorithm (i.e., classification trees) is applied to the simulated orographic precipitation for idealized experimental setups using the National Center of Atmospheric Research (NCAR) Community Atmosphere Model (CAM) with the finite volume (FV) and the Eulerian spectral transform dynamical cores with varying resolutions. Daily simulations were analyzed and three different types of precipitation features were identified by the classification tree algorithm. The statistical characteristics of these features (i.e., maximum value, mean value, and variance) were calculated to quantify the difference between the dynamical cores and changing resolutions. Even with the simple and smoothmore » topography in the idealized setups, complexity in the precipitation fields simulated by the models develops quickly. The classification tree algorithm using objective thresholding successfully detected different types of precipitation features even as the complexity of the precipitation field increased. The results show that the complexity and the bias introduced in small-scale phenomena due to the spectral transform method of CAM Eulerian spectral dynamical core is prominent, and is an important reason for its dissimilarity from the FV dynamical core. The resolvable scales, both in horizontal and vertical dimensions, have significant effect on the simulation of precipitation. The results of this study also suggest that an efficient and informative study about the biases produced by GCMs should involve daily (or even hourly) output (rather than monthly mean) analysis over local scales.« less

A decision tree algorithm for investigation of model biases related to dynamical cores and physical parameterizations: CESM/CAM EVALUATION BY DECISION TREES

DOE PAGES

Soner Yorgun, M.; Rood, Richard B.

2016-11-11

An object-based evaluation method using a pattern recognition algorithm (i.e., classification trees) is applied to the simulated orographic precipitation for idealized experimental setups using the National Center of Atmospheric Research (NCAR) Community Atmosphere Model (CAM) with the finite volume (FV) and the Eulerian spectral transform dynamical cores with varying resolutions. Daily simulations were analyzed and three different types of precipitation features were identified by the classification tree algorithm. The statistical characteristics of these features (i.e., maximum value, mean value, and variance) were calculated to quantify the difference between the dynamical cores and changing resolutions. Even with the simple and smoothmore » topography in the idealized setups, complexity in the precipitation fields simulated by the models develops quickly. The classification tree algorithm using objective thresholding successfully detected different types of precipitation features even as the complexity of the precipitation field increased. The results show that the complexity and the bias introduced in small-scale phenomena due to the spectral transform method of CAM Eulerian spectral dynamical core is prominent, and is an important reason for its dissimilarity from the FV dynamical core. The resolvable scales, both in horizontal and vertical dimensions, have significant effect on the simulation of precipitation. The results of this study also suggest that an efficient and informative study about the biases produced by GCMs should involve daily (or even hourly) output (rather than monthly mean) analysis over local scales.« less

Multi-objective evolutionary algorithms for fuzzy classification in survival prediction.

PubMed

Jiménez, Fernando; Sánchez, Gracia; Juárez, José M

2014-03-01

This paper presents a novel rule-based fuzzy classification methodology for survival/mortality prediction in severe burnt patients. Due to the ethical aspects involved in this medical scenario, physicians tend not to accept a computer-based evaluation unless they understand why and how such a recommendation is given. Therefore, any fuzzy classifier model must be both accurate and interpretable. The proposed methodology is a three-step process: (1) multi-objective constrained optimization of a patient's data set, using Pareto-based elitist multi-objective evolutionary algorithms to maximize accuracy and minimize the complexity (number of rules) of classifiers, subject to interpretability constraints; this step produces a set of alternative (Pareto) classifiers; (2) linguistic labeling, which assigns a linguistic label to each fuzzy set of the classifiers; this step is essential to the interpretability of the classifiers; (3) decision making, whereby a classifier is chosen, if it is satisfactory, according to the preferences of the decision maker. If no classifier is satisfactory for the decision maker, the process starts again in step (1) with a different input parameter set. The performance of three multi-objective evolutionary algorithms, niched pre-selection multi-objective algorithm, elitist Pareto-based multi-objective evolutionary algorithm for diversity reinforcement (ENORA) and the non-dominated sorting genetic algorithm (NSGA-II), was tested using a patient's data set from an intensive care burn unit and a standard machine learning data set from an standard machine learning repository. The results are compared using the hypervolume multi-objective metric. Besides, the results have been compared with other non-evolutionary techniques and validated with a multi-objective cross-validation technique. Our proposal improves the classification rate obtained by other non-evolutionary techniques (decision trees, artificial neural networks, Naive Bayes, and case-based reasoning) obtaining with ENORA a classification rate of 0.9298, specificity of 0.9385, and sensitivity of 0.9364, with 14.2 interpretable fuzzy rules on average. Our proposal improves the accuracy and interpretability of the classifiers, compared with other non-evolutionary techniques. We also conclude that ENORA outperforms niched pre-selection and NSGA-II algorithms. Moreover, given that our multi-objective evolutionary methodology is non-combinational based on real parameter optimization, the time cost is significantly reduced compared with other evolutionary approaches existing in literature based on combinational optimization. Copyright © 2014 Elsevier B.V. All rights reserved.

Protein attributes contribute to halo-stability, bioinformatics approach

PubMed Central

2011-01-01

Halophile proteins can tolerate high salt concentrations. Understanding halophilicity features is the first step toward engineering halostable crops. To this end, we examined protein features contributing to the halo-toleration of halophilic organisms. We compared more than 850 features for halophilic and non-halophilic proteins with various screening, clustering, decision tree, and generalized rule induction models to search for patterns that code for halo-toleration. Up to 251 protein attributes selected by various attribute weighting algorithms as important features contribute to halo-stability; from them 14 attributes selected by 90% of models and the count of hydrogen gained the highest value (1.0) in 70% of attribute weighting models, showing the importance of this attribute in feature selection modeling. The other attributes mostly were the frequencies of di-peptides. No changes were found in the numbers of groups when K-Means and TwoStep clustering modeling were performed on datasets with or without feature selection filtering. Although the depths of induced trees were not high, the accuracies of trees were higher than 94% and the frequency of hydrophobic residues pointed as the most important feature to build trees. The performance evaluation of decision tree models had the same values and the best correctness percentage recorded with the Exhaustive CHAID and CHAID models. We did not find any significant difference in the percent of correctness, performance evaluation, and mean correctness of various decision tree models with or without feature selection. For the first time, we analyzed the performance of different screening, clustering, and decision tree algorithms for discriminating halophilic and non-halophilic proteins and the results showed that amino acid composition can be used to discriminate between halo-tolerant and halo-sensitive proteins. PMID:21592393

Learning Parsimonious Classification Rules from Gene Expression Data Using Bayesian Networks with Local Structure.

PubMed

Lustgarten, Jonathan Lyle; Balasubramanian, Jeya Balaji; Visweswaran, Shyam; Gopalakrishnan, Vanathi

2017-03-01

The comprehensibility of good predictive models learned from high-dimensional gene expression data is attractive because it can lead to biomarker discovery. Several good classifiers provide comparable predictive performance but differ in their abilities to summarize the observed data. We extend a Bayesian Rule Learning (BRL-GSS) algorithm, previously shown to be a significantly better predictor than other classical approaches in this domain. It searches a space of Bayesian networks using a decision tree representation of its parameters with global constraints, and infers a set of IF-THEN rules. The number of parameters and therefore the number of rules are combinatorial to the number of predictor variables in the model. We relax these global constraints to a more generalizable local structure (BRL-LSS). BRL-LSS entails more parsimonious set of rules because it does not have to generate all combinatorial rules. The search space of local structures is much richer than the space of global structures. We design the BRL-LSS with the same worst-case time-complexity as BRL-GSS while exploring a richer and more complex model space. We measure predictive performance using Area Under the ROC curve (AUC) and Accuracy. We measure model parsimony performance by noting the average number of rules and variables needed to describe the observed data. We evaluate the predictive and parsimony performance of BRL-GSS, BRL-LSS and the state-of-the-art C4.5 decision tree algorithm, across 10-fold cross-validation using ten microarray gene-expression diagnostic datasets. In these experiments, we observe that BRL-LSS is similar to BRL-GSS in terms of predictive performance, while generating a much more parsimonious set of rules to explain the same observed data. BRL-LSS also needs fewer variables than C4.5 to explain the data with similar predictive performance. We also conduct a feasibility study to demonstrate the general applicability of our BRL methods on the newer RNA sequencing gene-expression data.

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.

Learning in data-limited multimodal scenarios: Scandent decision forests and tree-based features.

PubMed

Hor, Soheil; Moradi, Mehdi

2016-12-01

Incomplete and inconsistent datasets often pose difficulties in multimodal studies. We introduce the concept of scandent decision trees to tackle these difficulties. Scandent trees are decision trees that optimally mimic the partitioning of the data determined by another decision tree, and crucially, use only a subset of the feature set. We show how scandent trees can be used to enhance the performance of decision forests trained on a small number of multimodal samples when we have access to larger datasets with vastly incomplete feature sets. Additionally, we introduce the concept of tree-based feature transforms in the decision forest paradigm. When combined with scandent trees, the tree-based feature transforms enable us to train a classifier on a rich multimodal dataset, and use it to classify samples with only a subset of features of the training data. Using this methodology, we build a model trained on MRI and PET images of the ADNI dataset, and then test it on cases with only MRI data. We show that this is significantly more effective in staging of cognitive impairments compared to a similar decision forest model trained and tested on MRI only, or one that uses other kinds of feature transform applied to the MRI data. Copyright © 2016. Published by Elsevier B.V.

Case-based explanation of non-case-based learning methods.

PubMed Central

Caruana, R.; Kangarloo, H.; Dionisio, J. D.; Sinha, U.; Johnson, D.

1999-01-01

We show how to generate case-based explanations for non-case-based learning methods such as artificial neural nets or decision trees. The method uses the trained model (e.g., the neural net or the decision tree) as a distance metric to determine which cases in the training set are most similar to the case that needs to be explained. This approach is well suited to medical domains, where it is important to understand predictions made by complex machine learning models, and where training and clinical practice makes users adept at case interpretation. PMID:10566351

Comparing deep neural network and other machine learning algorithms for stroke prediction in a large-scale population-based electronic medical claims database.

PubMed

Chen-Ying Hung; Wei-Chen Chen; Po-Tsun Lai; Ching-Heng Lin; Chi-Chun Lee

2017-07-01

Electronic medical claims (EMCs) can be used to accurately predict the occurrence of a variety of diseases, which can contribute to precise medical interventions. While there is a growing interest in the application of machine learning (ML) techniques to address clinical problems, the use of deep-learning in healthcare have just gained attention recently. Deep learning, such as deep neural network (DNN), has achieved impressive results in the areas of speech recognition, computer vision, and natural language processing in recent years. However, deep learning is often difficult to comprehend due to the complexities in its framework. Furthermore, this method has not yet been demonstrated to achieve a better performance comparing to other conventional ML algorithms in disease prediction tasks using EMCs. In this study, we utilize a large population-based EMC database of around 800,000 patients to compare DNN with three other ML approaches for predicting 5-year stroke occurrence. The result shows that DNN and gradient boosting decision tree (GBDT) can result in similarly high prediction accuracies that are better compared to logistic regression (LR) and support vector machine (SVM) approaches. Meanwhile, DNN achieves optimal results by using lesser amounts of patient data when comparing to GBDT method.

A Mixtures-of-Trees Framework for Multi-Label Classification

PubMed Central

Hong, Charmgil; Batal, Iyad; Hauskrecht, Milos

2015-01-01

We propose a new probabilistic approach for multi-label classification that aims to represent the class posterior distribution P(Y|X). Our approach uses a mixture of tree-structured Bayesian networks, which can leverage the computational advantages of conditional tree-structured models and the abilities of mixtures to compensate for tree-structured restrictions. We develop algorithms for learning the model from data and for performing multi-label predictions using the learned model. Experiments on multiple datasets demonstrate that our approach outperforms several state-of-the-art multi-label classification methods. PMID:25927011

Algorithms in the First-Line Treatment of Metastatic Clear Cell Renal Cell Carcinoma--Analysis Using Diagnostic Nodes.

PubMed

Rothermundt, Christian; Bailey, Alexandra; Cerbone, Linda; Eisen, Tim; Escudier, Bernard; Gillessen, Silke; Grünwald, Viktor; Larkin, James; McDermott, David; Oldenburg, Jan; Porta, Camillo; Rini, Brian; Schmidinger, Manuela; Sternberg, Cora; Putora, Paul M

2015-09-01

With the advent of targeted therapies, many treatment options in the first-line setting of metastatic clear cell renal cell carcinoma (mccRCC) have emerged. Guidelines and randomized trial reports usually do not elucidate the decision criteria for the different treatment options. In order to extract the decision criteria for the optimal therapy for patients, we performed an analysis of treatment algorithms from experts in the field. Treatment algorithms for the treatment of mccRCC from experts of 11 institutions were obtained, and decision trees were deduced. Treatment options were identified and a list of unified decision criteria determined. The final decision trees were analyzed with a methodology based on diagnostic nodes, which allows for an automated cross-comparison of decision trees. The most common treatment recommendations were determined, and areas of discordance were identified. The analysis revealed heterogeneity in most clinical scenarios. The recommendations selected for first-line treatment of mccRCC included sunitinib, pazopanib, temsirolimus, interferon-α combined with bevacizumab, high-dose interleukin-2, sorafenib, axitinib, everolimus, and best supportive care. The criteria relevant for treatment decisions were performance status, Memorial Sloan Kettering Cancer Center risk group, only or mainly lung metastases, cardiac insufficiency, hepatic insufficiency, age, and "zugzwang" (composite of multiple, related criteria). In the present study, we used diagnostic nodes to compare treatment algorithms in the first-line treatment of mccRCC. The results illustrate the heterogeneity of the decision criteria and treatment strategies for mccRCC and how available data are interpreted and implemented differently among experts. The data provided in the present report should not be considered to serve as treatment recommendations for the management of treatment-naïve patients with multiple metastases from metastatic clear cell renal cell carcinoma outside a clinical trial; however, the data highlight the different treatment options and the criteria used to select them. The diversity in decision making and how results from phase III trials can be interpreted and implemented differently in daily practice are demonstrated. ©AlphaMed Press.

A Fast Exact k-Nearest Neighbors Algorithm for High Dimensional Search Using k-Means Clustering and Triangle Inequality.

PubMed

Wang, Xueyi

2012-02-08

The k-nearest neighbors (k-NN) algorithm is a widely used machine learning method that finds nearest neighbors of a test object in a feature space. We present a new exact k-NN algorithm called kMkNN (k-Means for k-Nearest Neighbors) that uses the k-means clustering and the triangle inequality to accelerate the searching for nearest neighbors in a high dimensional space. The kMkNN algorithm has two stages. In the buildup stage, instead of using complex tree structures such as metric trees, kd-trees, or ball-tree, kMkNN uses a simple k-means clustering method to preprocess the training dataset. In the searching stage, given a query object, kMkNN finds nearest training objects starting from the nearest cluster to the query object and uses the triangle inequality to reduce the distance calculations. Experiments show that the performance of kMkNN is surprisingly good compared to the traditional k-NN algorithm and tree-based k-NN algorithms such as kd-trees and ball-trees. On a collection of 20 datasets with up to 10(6) records and 10(4) dimensions, kMkNN shows a 2-to 80-fold reduction of distance calculations and a 2- to 60-fold speedup over the traditional k-NN algorithm for 16 datasets. Furthermore, kMkNN performs significant better than a kd-tree based k-NN algorithm for all datasets and performs better than a ball-tree based k-NN algorithm for most datasets. The results show that kMkNN is effective for searching nearest neighbors in high dimensional spaces.

Modeling flash floods in ungauged mountain catchments of China: A decision tree learning approach for parameter regionalization

NASA Astrophysics Data System (ADS)

Ragettli, S.; Zhou, J.; Wang, H.; Liu, C.

2017-12-01

Flash floods in small mountain catchments are one of the most frequent causes of loss of life and property from natural hazards in China. Hydrological models can be a useful tool for the anticipation of these events and the issuing of timely warnings. Since sub-daily streamflow information is unavailable for most small basins in China, one of the main challenges is finding appropriate parameter values for simulating flash floods in ungauged catchments. In this study, we use decision tree learning to explore parameter set transferability between different catchments. For this purpose, the physically-based, semi-distributed rainfall-runoff model PRMS-OMS is set up for 35 catchments in ten Chinese provinces. Hourly data from more than 800 storm runoff events are used to calibrate the model and evaluate the performance of parameter set transfers between catchments. For each catchment, 58 catchment attributes are extracted from several data sets available for whole China. We then use a data mining technique (decision tree learning) to identify catchment similarities that can be related to good transfer performance. Finally, we use the splitting rules of decision trees for finding suitable donor catchments for ungauged target catchments. We show that decision tree learning allows to optimally utilize the information content of available catchment descriptors and outperforms regionalization based on a conventional measure of physiographic-climatic similarity by 15%-20%. Similar performance can be achieved with a regionalization method based on spatial proximity, but decision trees offer flexible rules for selecting suitable donor catchments, not relying on the vicinity of gauged catchments. This flexibility makes the method particularly suitable for implementation in sparsely gauged environments. We evaluate the probability to detect flood events exceeding a given return period, considering measured discharge and PRMS-OMS simulated flows with regionalized parameters. Overall, the probability of detection of an event with a return period of 10 years is 62%. 44% of all 10-year flood peaks can be detected with a timing error of 2 hours or less. These results indicate that the modeling system can provide useful information about the timing and magnitude of flood events at ungauged sites.

A Spatiotemporal Prediction Framework for Air Pollution Based on Deep RNN

NASA Astrophysics Data System (ADS)

Fan, J.; Li, Q.; Hou, J.; Feng, X.; Karimian, H.; Lin, S.

2017-10-01

Time series data in practical applications always contain missing values due to sensor malfunction, network failure, outliers etc. In order to handle missing values in time series, as well as the lack of considering temporal properties in machine learning models, we propose a spatiotemporal prediction framework based on missing value processing algorithms and deep recurrent neural network (DRNN). By using missing tag and missing interval to represent time series patterns, we implement three different missing value fixing algorithms, which are further incorporated into deep neural network that consists of LSTM (Long Short-term Memory) layers and fully connected layers. Real-world air quality and meteorological datasets (Jingjinji area, China) are used for model training and testing. Deep feed forward neural networks (DFNN) and gradient boosting decision trees (GBDT) are trained as baseline models against the proposed DRNN. Performances of three missing value fixing algorithms, as well as different machine learning models are evaluated and analysed. Experiments show that the proposed DRNN framework outperforms both DFNN and GBDT, therefore validating the capacity of the proposed framework. Our results also provides useful insights for better understanding of different strategies that handle missing values.

Research on Classification of Chinese Text Data Based on SVM

NASA Astrophysics Data System (ADS)

Lin, Yuan; Yu, Hongzhi; Wan, Fucheng; Xu, Tao

2017-09-01

Data Mining has important application value in today’s industry and academia. Text classification is a very important technology in data mining. At present, there are many mature algorithms for text classification. KNN, NB, AB, SVM, decision tree and other classification methods all show good classification performance. Support Vector Machine’ (SVM) classification method is a good classifier in machine learning research. This paper will study the classification effect based on the SVM method in the Chinese text data, and use the support vector machine method in the chinese text to achieve the classify chinese text, and to able to combination of academia and practical application.

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.

Managing and learning with multiple models: Objectives and optimization algorithms

USGS Publications Warehouse

Probert, William J. M.; Hauser, C.E.; McDonald-Madden, E.; Runge, M.C.; Baxter, P.W.J.; Possingham, H.P.

2011-01-01

The quality of environmental decisions should be gauged according to managers' objectives. Management objectives generally seek to maximize quantifiable measures of system benefit, for instance population growth rate. Reaching these goals often requires a certain degree of learning about the system. Learning can occur by using management action in combination with a monitoring system. Furthermore, actions can be chosen strategically to obtain specific kinds of information. Formal decision making tools can choose actions to favor such learning in two ways: implicitly via the optimization algorithm that is used when there is a management objective (for instance, when using adaptive management), or explicitly by quantifying knowledge and using it as the fundamental project objective, an approach new to conservation.This paper outlines three conservation project objectives - a pure management objective, a pure learning objective, and an objective that is a weighted mixture of these two. We use eight optimization algorithms to choose actions that meet project objectives and illustrate them in a simulated conservation project. The algorithms provide a taxonomy of decision making tools in conservation management when there is uncertainty surrounding competing models of system function. The algorithms build upon each other such that their differences are highlighted and practitioners may see where their decision making tools can be improved. ?? 2010 Elsevier Ltd.

Concurrent approach for evolving compact decision rule sets

NASA Astrophysics Data System (ADS)

Marmelstein, Robert E.; Hammack, Lonnie P.; Lamont, Gary B.

1999-02-01

The induction of decision rules from data is important to many disciplines, including artificial intelligence and pattern recognition. To improve the state of the art in this area, we introduced the genetic rule and classifier construction environment (GRaCCE). It was previously shown that GRaCCE consistently evolved decision rule sets from data, which were significantly more compact than those produced by other methods (such as decision tree algorithms). The primary disadvantage of GRaCCe, however, is its relatively poor run-time execution performance. In this paper, a concurrent version of the GRaCCE architecture is introduced, which improves the efficiency of the original algorithm. A prototype of the algorithm is tested on an in- house parallel processor configuration and the results are discussed.

Using machine learning to predict radiation pneumonitis in patients with stage I non-small cell lung cancer treated with stereotactic body radiation therapy

NASA Astrophysics Data System (ADS)

Valdes, Gilmer; Solberg, Timothy D.; Heskel, Marina; Ungar, Lyle; Simone, Charles B., II

2016-08-01

To develop a patient-specific ‘big data’ clinical decision tool to predict pneumonitis in stage I non-small cell lung cancer (NSCLC) patients after stereotactic body radiation therapy (SBRT). 61 features were recorded for 201 consecutive patients with stage I NSCLC treated with SBRT, in whom 8 (4.0%) developed radiation pneumonitis. Pneumonitis thresholds were found for each feature individually using decision stumps. The performance of three different algorithms (Decision Trees, Random Forests, RUSBoost) was evaluated. Learning curves were developed and the training error analyzed and compared to the testing error in order to evaluate the factors needed to obtain a cross-validated error smaller than 0.1. These included the addition of new features, increasing the complexity of the algorithm and enlarging the sample size and number of events. In the univariate analysis, the most important feature selected was the diffusion capacity of the lung for carbon monoxide (DLCO adj%). On multivariate analysis, the three most important features selected were the dose to 15 cc of the heart, dose to 4 cc of the trachea or bronchus, and race. Higher accuracy could be achieved if the RUSBoost algorithm was used with regularization. To predict radiation pneumonitis within an error smaller than 10%, we estimate that a sample size of 800 patients is required. Clinically relevant thresholds that put patients at risk of developing radiation pneumonitis were determined in a cohort of 201 stage I NSCLC patients treated with SBRT. The consistency of these thresholds can provide radiation oncologists with an estimate of their reliability and may inform treatment planning and patient counseling. The accuracy of the classification is limited by the number of patients in the study and not by the features gathered or the complexity of the algorithm.

IND - THE IND DECISION TREE PACKAGE

NASA Technical Reports Server (NTRS)

Buntine, W.

1994-01-01

A common approach to supervised classification and prediction in artificial intelligence and statistical pattern recognition is the use of decision trees. A tree is "grown" from data using a recursive partitioning algorithm to create a tree which has good prediction of classes on new data. Standard algorithms are CART (by Breiman Friedman, Olshen and Stone) and ID3 and its successor C4 (by Quinlan). As well as reimplementing parts of these algorithms and offering experimental control suites, IND also introduces Bayesian and MML methods and more sophisticated search in growing trees. These produce more accurate class probability estimates that are important in applications like diagnosis. IND is applicable to most data sets consisting of independent instances, each described by a fixed length vector of attribute values. An attribute value may be a number, one of a set of attribute specific symbols, or it may be omitted. One of the attributes is delegated the "target" and IND grows trees to predict the target. Prediction can then be done on new data or the decision tree printed out for inspection. IND provides a range of features and styles with convenience for the casual user as well as fine-tuning for the advanced user or those interested in research. IND can be operated in a CART-like mode (but without regression trees, surrogate splits or multivariate splits), and in a mode like the early version of C4. Advanced features allow more extensive search, interactive control and display of tree growing, and Bayesian and MML algorithms for tree pruning and smoothing. These often produce more accurate class probability estimates at the leaves. IND also comes with a comprehensive experimental control suite. IND consists of four basic kinds of routines: data manipulation routines, tree generation routines, tree testing routines, and tree display routines. The data manipulation routines are used to partition a single large data set into smaller training and test sets. The generation routines are used to build classifiers. The test routines are used to evaluate classifiers and to classify data using a classifier. And the display routines are used to display classifiers in various formats. IND is written in C-language for Sun4 series computers. It consists of several programs with controlling shell scripts. Extensive UNIX man entries are included. IND is designed to be used on any UNIX system, although it has only been thoroughly tested on SUN platforms. The standard distribution medium for IND is a .25 inch streaming magnetic tape cartridge in UNIX tar format. An electronic copy of the documentation in PostScript format is included on the distribution medium. IND was developed in 1992.

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

A key for the Forest Service hardwood tree grades

Treesearch

Gary W. Miller; Leland F. Hanks; Harry V., Jr. Wiant

1986-01-01

A dichotomous key organizes the USDA Forest Service hardwood tree grade specifications into a stepwise procedure for those learning to grade hardwood sawtimber. The key addresses the major grade factors, tree size, surface characteristics, and allowable cull deductions in a series of paried choices that lead the user to a decision regarding tree grade.

PHOTOMETRIC SUPERNOVA CLASSIFICATION WITH MACHINE LEARNING

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

Lochner, Michelle; Peiris, Hiranya V.; Lahav, Ofer

Automated photometric supernova classification has become an active area of research in recent years in light of current and upcoming imaging surveys such as the Dark Energy Survey (DES) and the Large Synoptic Survey Telescope, given that spectroscopic confirmation of type for all supernovae discovered will be impossible. Here, we develop a multi-faceted classification pipeline, combining existing and new approaches. Our pipeline consists of two stages: extracting descriptive features from the light curves and classification using a machine learning algorithm. Our feature extraction methods vary from model-dependent techniques, namely SALT2 fits, to more independent techniques that fit parametric models tomore » curves, to a completely model-independent wavelet approach. We cover a range of representative machine learning algorithms, including naive Bayes, k -nearest neighbors, support vector machines, artificial neural networks, and boosted decision trees (BDTs). We test the pipeline on simulated multi-band DES light curves from the Supernova Photometric Classification Challenge. Using the commonly used area under the curve (AUC) of the Receiver Operating Characteristic as a metric, we find that the SALT2 fits and the wavelet approach, with the BDTs algorithm, each achieve an AUC of 0.98, where 1 represents perfect classification. We find that a representative training set is essential for good classification, whatever the feature set or algorithm, with implications for spectroscopic follow-up. Importantly, we find that by using either the SALT2 or the wavelet feature sets with a BDT algorithm, accurate classification is possible purely from light curve data, without the need for any redshift information.« less

Reinforcement Learning for Weakly-Coupled MDPs and an Application to Planetary Rover Control

NASA Technical Reports Server (NTRS)

Bernstein, Daniel S.; Zilberstein, Shlomo

2003-01-01

Weakly-coupled Markov decision processes can be decomposed into subprocesses that interact only through a small set of bottleneck states. We study a hierarchical reinforcement learning algorithm designed to take advantage of this particular type of decomposability. To test our algorithm, we use a decision-making problem faced by autonomous planetary rovers. In this problem, a Mars rover must decide which activities to perform and when to traverse between science sites in order to make the best use of its limited resources. In our experiments, the hierarchical algorithm performs better than Q-learning in the early stages of learning, but unlike Q-learning it converges to a suboptimal policy. This suggests that it may be advantageous to use the hierarchical algorithm when training time is limited.

Photometric classification of type Ia supernovae in the SuperNova Legacy Survey with supervised learning

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

Möller, A.; Ruhlmann-Kleider, V.; Leloup, C.

In the era of large astronomical surveys, photometric classification of supernovae (SNe) has become an important research field due to limited spectroscopic resources for candidate follow-up and classification. In this work, we present a method to photometrically classify type Ia supernovae based on machine learning with redshifts that are derived from the SN light-curves. This method is implemented on real data from the SNLS deferred pipeline, a purely photometric pipeline that identifies SNe Ia at high-redshifts (0.2 < z < 1.1). Our method consists of two stages: feature extraction (obtaining the SN redshift from photometry and estimating light-curve shape parameters)more » and machine learning classification. We study the performance of different algorithms such as Random Forest and Boosted Decision Trees. We evaluate the performance using SN simulations and real data from the first 3 years of the Supernova Legacy Survey (SNLS), which contains large spectroscopically and photometrically classified type Ia samples. Using the Area Under the Curve (AUC) metric, where perfect classification is given by 1, we find that our best-performing classifier (Extreme Gradient Boosting Decision Tree) has an AUC of 0.98.We show that it is possible to obtain a large photometrically selected type Ia SN sample with an estimated contamination of less than 5%. When applied to data from the first three years of SNLS, we obtain 529 events. We investigate the differences between classifying simulated SNe, and real SN survey data. In particular, we find that applying a thorough set of selection cuts to the SN sample is essential for good classification. This work demonstrates for the first time the feasibility of machine learning classification in a high- z SN survey with application to real SN data.« less

Computational approaches for the classification of seed storage proteins.

PubMed

Radhika, V; Rao, V Sree Hari

2015-07-01

Seed storage proteins comprise a major part of the protein content of the seed and have an important role on the quality of the seed. These storage proteins are important because they determine the total protein content and have an effect on the nutritional quality and functional properties for food processing. Transgenic plants are being used to develop improved lines for incorporation into plant breeding programs and the nutrient composition of seeds is a major target of molecular breeding programs. Hence, classification of these proteins is crucial for the development of superior varieties with improved nutritional quality. In this study we have applied machine learning algorithms for classification of seed storage proteins. We have presented an algorithm based on nearest neighbor approach for classification of seed storage proteins and compared its performance with decision tree J48, multilayer perceptron neural (MLP) network and support vector machine (SVM) libSVM. The model based on our algorithm has been able to give higher classification accuracy in comparison to the other methods.

Decentralized learning in Markov games.

PubMed

Vrancx, Peter; Verbeeck, Katja; Nowé, Ann

2008-08-01

Learning automata (LA) were recently shown to be valuable tools for designing multiagent reinforcement learning algorithms. One of the principal contributions of the LA theory is that a set of decentralized independent LA is able to control a finite Markov chain with unknown transition probabilities and rewards. In this paper, we propose to extend this algorithm to Markov games--a straightforward extension of single-agent Markov decision problems to distributed multiagent decision problems. We show that under the same ergodic assumptions of the original theorem, the extended algorithm will converge to a pure equilibrium point between agent policies.

C-fuzzy variable-branch decision tree with storage and classification error rate constraints

NASA Astrophysics Data System (ADS)

Yang, Shiueng-Bien

2009-10-01

The C-fuzzy decision tree (CFDT), which is based on the fuzzy C-means algorithm, has recently been proposed. The CFDT is grown by selecting the nodes to be split according to its classification error rate. However, the CFDT design does not consider the classification time taken to classify the input vector. Thus, the CFDT can be improved. We propose a new C-fuzzy variable-branch decision tree (CFVBDT) with storage and classification error rate constraints. The design of the CFVBDT consists of two phases-growing and pruning. The CFVBDT is grown by selecting the nodes to be split according to the classification error rate and the classification time in the decision tree. Additionally, the pruning method selects the nodes to prune based on the storage requirement and the classification time of the CFVBDT. Furthermore, the number of branches of each internal node is variable in the CFVBDT. Experimental results indicate that the proposed CFVBDT outperforms the CFDT and other methods.

Prediction of the compression ratio for municipal solid waste using decision tree.

PubMed

Heshmati R, Ali Akbar; Mokhtari, Maryam; Shakiba Rad, Saeed

2014-01-01

The compression ratio of municipal solid waste (MSW) is an essential parameter for evaluation of waste settlement and landfill design. However, no appropriate model has been proposed to estimate the waste compression ratio so far. In this study, a decision tree method was utilized to predict the waste compression ratio (C'c). The tree was constructed using Quinlan's M5 algorithm. A reliable database retrieved from the literature was used to develop a practical model that relates C'c to waste composition and properties, including dry density, dry weight water content, and percentage of biodegradable organic waste using the decision tree method. The performance of the developed model was examined in terms of different statistical criteria, including correlation coefficient, root mean squared error, mean absolute error and mean bias error, recommended by researchers. The obtained results demonstrate that the suggested model is able to evaluate the compression ratio of MSW effectively.

Knowledge Guided Evolutionary Algorithms in Financial Investing

ERIC Educational Resources Information Center

Wimmer, Hayden

2013-01-01

A large body of literature exists on evolutionary computing, genetic algorithms, decision trees, codified knowledge, and knowledge management systems; however, the intersection of these computing topics has not been widely researched. Moving through the set of all possible solutions--or traversing the search space--at random exhibits no control…

Predicting Pre-planting Risk of Stagonospora nodorum blotch in Winter Wheat Using Machine Learning Models.

PubMed

Mehra, Lucky K; Cowger, Christina; Gross, Kevin; Ojiambo, Peter S

2016-01-01

Pre-planting factors have been associated with the late-season severity of Stagonospora nodorum blotch (SNB), caused by the fungal pathogen Parastagonospora nodorum, in winter wheat (Triticum aestivum). The relative importance of these factors in the risk of SNB has not been determined and this knowledge can facilitate disease management decisions prior to planting of the wheat crop. In this study, we examined the performance of multiple regression (MR) and three machine learning algorithms namely artificial neural networks, categorical and regression trees, and random forests (RF), in predicting the pre-planting risk of SNB in wheat. Pre-planting factors tested as potential predictor variables were cultivar resistance, latitude, longitude, previous crop, seeding rate, seed treatment, tillage type, and wheat residue. Disease severity assessed at the end of the growing season was used as the response variable. The models were developed using 431 disease cases (unique combinations of predictors) collected from 2012 to 2014 and these cases were randomly divided into training, validation, and test datasets. Models were evaluated based on the regression of observed against predicted severity values of SNB, sensitivity-specificity ROC analysis, and the Kappa statistic. A strong relationship was observed between late-season severity of SNB and specific pre-planting factors in which latitude, longitude, wheat residue, and cultivar resistance were the most important predictors. The MR model explained 33% of variability in the data, while machine learning models explained 47 to 79% of the total variability. Similarly, the MR model correctly classified 74% of the disease cases, while machine learning models correctly classified 81 to 83% of these cases. Results show that the RF algorithm, which explained 79% of the variability within the data, was the most accurate in predicting the risk of SNB, with an accuracy rate of 93%. The RF algorithm could allow early assessment of the risk of SNB, facilitating sound disease management decisions prior to planting of wheat.

A finite element-based machine learning approach for modeling the mechanical behavior of the breast tissues under compression in real-time.

PubMed

Martínez-Martínez, F; Rupérez-Moreno, M J; Martínez-Sober, M; Solves-Llorens, J A; Lorente, D; Serrano-López, A J; Martínez-Sanchis, S; Monserrat, C; Martín-Guerrero, J D

2017-11-01

This work presents a data-driven method to simulate, in real-time, the biomechanical behavior of the breast tissues in some image-guided interventions such as biopsies or radiotherapy dose delivery as well as to speed up multimodal registration algorithms. Ten real breasts were used for this work. Their deformation due to the displacement of two compression plates was simulated off-line using the finite element (FE) method. Three machine learning models were trained with the data from those simulations. Then, they were used to predict in real-time the deformation of the breast tissues during the compression. The models were a decision tree and two tree-based ensemble methods (extremely randomized trees and random forest). Two different experimental setups were designed to validate and study the performance of these models under different conditions. The mean 3D Euclidean distance between nodes predicted by the models and those extracted from the FE simulations was calculated to assess the performance of the models in the validation set. The experiments proved that extremely randomized trees performed better than the other two models. The mean error committed by the three models in the prediction of the nodal displacements was under 2 mm, a threshold usually set for clinical applications. The time needed for breast compression prediction is sufficiently short to allow its use in real-time (<0.2 s). Copyright © 2017 Elsevier Ltd. All rights reserved.

Predictive models for subtypes of autism spectrum disorder based on single-nucleotide polymorphisms and magnetic resonance imaging.

PubMed

Jiao, Y; Chen, R; Ke, X; Cheng, L; Chu, K; Lu, Z; Herskovits, E H

2011-01-01

Autism spectrum disorder (ASD) is a neurodevelopmental disorder, of which Asperger syndrome and high-functioning autism are subtypes. Our goal is: 1) to determine whether a diagnostic model based on single-nucleotide polymorphisms (SNPs), brain regional thickness measurements, or brain regional volume measurements can distinguish Asperger syndrome from high-functioning autism; and 2) to compare the SNP, thickness, and volume-based diagnostic models. Our study included 18 children with ASD: 13 subjects with high-functioning autism and 5 subjects with Asperger syndrome. For each child, we obtained 25 SNPs for 8 ASD-related genes; we also computed regional cortical thicknesses and volumes for 66 brain structures, based on structural magnetic resonance (MR) examination. To generate diagnostic models, we employed five machine-learning techniques: decision stump, alternating decision trees, multi-class alternating decision trees, logistic model trees, and support vector machines. For SNP-based classification, three decision-tree-based models performed better than the other two machine-learning models. The performance metrics for three decision-tree-based models were similar: decision stump was modestly better than the other two methods, with accuracy = 90%, sensitivity = 0.95 and specificity = 0.75. All thickness and volume-based diagnostic models performed poorly. The SNP-based diagnostic models were superior to those based on thickness and volume. For SNP-based classification, rs878960 in GABRB3 (gamma-aminobutyric acid A receptor, beta 3) was selected by all tree-based models. Our analysis demonstrated that SNP-based classification was more accurate than morphometry-based classification in ASD subtype classification. Also, we found that one SNP--rs878960 in GABRB3--distinguishes Asperger syndrome from high-functioning autism.

Fault diagnosis of automobile hydraulic brake system using statistical features and support vector machines

NASA Astrophysics Data System (ADS)

Jegadeeshwaran, R.; Sugumaran, V.

2015-02-01

Hydraulic brakes in automobiles are important components for the safety of passengers; therefore, the brakes are a good subject for condition monitoring. The condition of the brake components can be monitored by using the vibration characteristics. On-line condition monitoring by using machine learning approach is proposed in this paper as a possible solution to such problems. The vibration signals for both good as well as faulty conditions of brakes were acquired from a hydraulic brake test setup with the help of a piezoelectric transducer and a data acquisition system. Descriptive statistical features were extracted from the acquired vibration signals and the feature selection was carried out using the C4.5 decision tree algorithm. There is no specific method to find the right number of features required for classification for a given problem. Hence an extensive study is needed to find the optimum number of features. The effect of the number of features was also studied, by using the decision tree as well as Support Vector Machines (SVM). The selected features were classified using the C-SVM and Nu-SVM with different kernel functions. The results are discussed and the conclusion of the study is presented.

Using decision-tree classifier systems to extract knowledge from databases

NASA Technical Reports Server (NTRS)

St.clair, D. C.; Sabharwal, C. L.; Hacke, Keith; Bond, W. E.

1990-01-01

One difficulty in applying artificial intelligence techniques to the solution of real world problems is that the development and maintenance of many AI systems, such as those used in diagnostics, require large amounts of human resources. At the same time, databases frequently exist which contain information about the process(es) of interest. Recently, efforts to reduce development and maintenance costs of AI systems have focused on using machine learning techniques to extract knowledge from existing databases. Research is described in the area of knowledge extraction using a class of machine learning techniques called decision-tree classifier systems. Results of this research suggest ways of performing knowledge extraction which may be applied in numerous situations. In addition, a measurement called the concept strength metric (CSM) is described which can be used to determine how well the resulting decision tree can differentiate between the concepts it has learned. The CSM can be used to determine whether or not additional knowledge needs to be extracted from the database. An experiment involving real world data is presented to illustrate the concepts described.

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.

Unified framework for triaxial accelerometer-based fall event detection and classification using cumulants and hierarchical decision tree classifier.

PubMed

Kambhampati, Satya Samyukta; Singh, Vishal; Manikandan, M Sabarimalai; Ramkumar, Barathram

2015-08-01

In this Letter, the authors present a unified framework for fall event detection and classification using the cumulants extracted from the acceleration (ACC) signals acquired using a single waist-mounted triaxial accelerometer. The main objective of this Letter is to find suitable representative cumulants and classifiers in effectively detecting and classifying different types of fall and non-fall events. It was discovered that the first level of the proposed hierarchical decision tree algorithm implements fall detection using fifth-order cumulants and support vector machine (SVM) classifier. In the second level, the fall event classification algorithm uses the fifth-order cumulants and SVM. Finally, human activity classification is performed using the second-order cumulants and SVM. The detection and classification results are compared with those of the decision tree, naive Bayes, multilayer perceptron and SVM classifiers with different types of time-domain features including the second-, third-, fourth- and fifth-order cumulants and the signal magnitude vector and signal magnitude area. The experimental results demonstrate that the second- and fifth-order cumulant features and SVM classifier can achieve optimal detection and classification rates of above 95%, as well as the lowest false alarm rate of 1.03%.

Data Clustering and Evolving Fuzzy Decision Tree for Data Base Classification Problems

NASA Astrophysics Data System (ADS)

Chang, Pei-Chann; Fan, Chin-Yuan; Wang, Yen-Wen

Data base classification suffers from two well known difficulties, i.e., the high dimensionality and non-stationary variations within the large historic data. This paper presents a hybrid classification model by integrating a case based reasoning technique, a Fuzzy Decision Tree (FDT), and Genetic Algorithms (GA) to construct a decision-making system for data classification in various data base applications. The model is major based on the idea that the historic data base can be transformed into a smaller case-base together with a group of fuzzy decision rules. As a result, the model can be more accurately respond to the current data under classifying from the inductions by these smaller cases based fuzzy decision trees. Hit rate is applied as a performance measure and the effectiveness of our proposed model is demonstrated by experimentally compared with other approaches on different data base classification applications. The average hit rate of our proposed model is the highest among others.

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.

Strategic Decision-Making Learning from Label Distributions: An Approach for Facial Age Estimation.

PubMed

Zhao, Wei; Wang, Han

2016-06-28

Nowadays, label distribution learning is among the state-of-the-art methodologies in facial age estimation. It takes the age of each facial image instance as a label distribution with a series of age labels rather than the single chronological age label that is commonly used. However, this methodology is deficient in its simple decision-making criterion: the final predicted age is only selected at the one with maximum description degree. In many cases, different age labels may have very similar description degrees. Consequently, blindly deciding the estimated age by virtue of the highest description degree would miss or neglect other valuable age labels that may contribute a lot to the final predicted age. In this paper, we propose a strategic decision-making label distribution learning algorithm (SDM-LDL) with a series of strategies specialized for different types of age label distribution. Experimental results from the most popular aging face database, FG-NET, show the superiority and validity of all the proposed strategic decision-making learning algorithms over the existing label distribution learning and other single-label learning algorithms for facial age estimation. The inner properties of SDM-LDL are further explored with more advantages.

Strategic Decision-Making Learning from Label Distributions: An Approach for Facial Age Estimation

PubMed Central

Zhao, Wei; Wang, Han

2016-01-01

Nowadays, label distribution learning is among the state-of-the-art methodologies in facial age estimation. It takes the age of each facial image instance as a label distribution with a series of age labels rather than the single chronological age label that is commonly used. However, this methodology is deficient in its simple decision-making criterion: the final predicted age is only selected at the one with maximum description degree. In many cases, different age labels may have very similar description degrees. Consequently, blindly deciding the estimated age by virtue of the highest description degree would miss or neglect other valuable age labels that may contribute a lot to the final predicted age. In this paper, we propose a strategic decision-making label distribution learning algorithm (SDM-LDL) with a series of strategies specialized for different types of age label distribution. Experimental results from the most popular aging face database, FG-NET, show the superiority and validity of all the proposed strategic decision-making learning algorithms over the existing label distribution learning and other single-label learning algorithms for facial age estimation. The inner properties of SDM-LDL are further explored with more advantages. PMID:27367691

Tree Classification Software

NASA Technical Reports Server (NTRS)

Buntine, Wray

1993-01-01

This paper introduces the IND Tree Package to prospective users. IND does supervised learning using classification trees. This learning task is a basic tool used in the development of diagnosis, monitoring and expert systems. The IND Tree Package was developed as part of a NASA project to semi-automate the development of data analysis and modelling algorithms using artificial intelligence techniques. The IND Tree Package integrates features from CART and C4 with newer Bayesian and minimum encoding methods for growing classification trees and graphs. The IND Tree Package also provides an experimental control suite on top. The newer features give improved probability estimates often required in diagnostic and screening tasks. The package comes with a manual, Unix 'man' entries, and a guide to tree methods and research. The IND Tree Package is implemented in C under Unix and was beta-tested at university and commercial research laboratories in the United States.

From learning taxonomies to phylogenetic learning: integration of 16S rRNA gene data into FAME-based bacterial classification.

PubMed

Slabbinck, Bram; Waegeman, Willem; Dawyndt, Peter; De Vos, Paul; De Baets, Bernard

2010-01-30

Machine learning techniques have shown to improve bacterial species classification based on fatty acid methyl ester (FAME) data. Nonetheless, FAME analysis has a limited resolution for discrimination of bacteria at the species level. In this paper, we approach the species classification problem from a taxonomic point of view. Such a taxonomy or tree is typically obtained by applying clustering algorithms on FAME data or on 16S rRNA gene data. The knowledge gained from the tree can then be used to evaluate FAME-based classifiers, resulting in a novel framework for bacterial species classification. In view of learning in a taxonomic framework, we consider two types of trees. First, a FAME tree is constructed with a supervised divisive clustering algorithm. Subsequently, based on 16S rRNA gene sequence analysis, phylogenetic trees are inferred by the NJ and UPGMA methods. In this second approach, the species classification problem is based on the combination of two different types of data. Herein, 16S rRNA gene sequence data is used for phylogenetic tree inference and the corresponding binary tree splits are learned based on FAME data. We call this learning approach 'phylogenetic learning'. Supervised Random Forest models are developed to train the classification tasks in a stratified cross-validation setting. In this way, better classification results are obtained for species that are typically hard to distinguish by a single or flat multi-class classification model. FAME-based bacterial species classification is successfully evaluated in a taxonomic framework. Although the proposed approach does not improve the overall accuracy compared to flat multi-class classification, it has some distinct advantages. First, it has better capabilities for distinguishing species on which flat multi-class classification fails. Secondly, the hierarchical classification structure allows to easily evaluate and visualize the resolution of FAME data for the discrimination of bacterial species. Summarized, by phylogenetic learning we are able to situate and evaluate FAME-based bacterial species classification in a more informative context.

From learning taxonomies to phylogenetic learning: Integration of 16S rRNA gene data into FAME-based bacterial classification

PubMed Central

2010-01-01

Background Machine learning techniques have shown to improve bacterial species classification based on fatty acid methyl ester (FAME) data. Nonetheless, FAME analysis has a limited resolution for discrimination of bacteria at the species level. In this paper, we approach the species classification problem from a taxonomic point of view. Such a taxonomy or tree is typically obtained by applying clustering algorithms on FAME data or on 16S rRNA gene data. The knowledge gained from the tree can then be used to evaluate FAME-based classifiers, resulting in a novel framework for bacterial species classification. Results In view of learning in a taxonomic framework, we consider two types of trees. First, a FAME tree is constructed with a supervised divisive clustering algorithm. Subsequently, based on 16S rRNA gene sequence analysis, phylogenetic trees are inferred by the NJ and UPGMA methods. In this second approach, the species classification problem is based on the combination of two different types of data. Herein, 16S rRNA gene sequence data is used for phylogenetic tree inference and the corresponding binary tree splits are learned based on FAME data. We call this learning approach 'phylogenetic learning'. Supervised Random Forest models are developed to train the classification tasks in a stratified cross-validation setting. In this way, better classification results are obtained for species that are typically hard to distinguish by a single or flat multi-class classification model. Conclusions FAME-based bacterial species classification is successfully evaluated in a taxonomic framework. Although the proposed approach does not improve the overall accuracy compared to flat multi-class classification, it has some distinct advantages. First, it has better capabilities for distinguishing species on which flat multi-class classification fails. Secondly, the hierarchical classification structure allows to easily evaluate and visualize the resolution of FAME data for the discrimination of bacterial species. Summarized, by phylogenetic learning we are able to situate and evaluate FAME-based bacterial species classification in a more informative context. PMID:20113515

Algorithmic Case Pedagogy, Learning and Gender

ERIC Educational Resources Information Center

Bromley, Robert; Huang, Zhenyu

2015-01-01

Great investment has been made in developing algorithmically-based cases within online homework management systems. This has been done because publishers are convinced that textbook adoption decisions are influenced by the incorporation of these systems within their products. These algorithmic assignments are thought to promote learning while…

A hybrid approach to select features and classify diseases based on medical data

NASA Astrophysics Data System (ADS)

AbdelLatif, Hisham; Luo, Jiawei

2018-03-01

Feature selection is popular problem in the classification of diseases in clinical medicine. Here, we developing a hybrid methodology to classify diseases, based on three medical datasets, Arrhythmia, Breast cancer, and Hepatitis datasets. This methodology called k-means ANOVA Support Vector Machine (K-ANOVA-SVM) uses K-means cluster with ANOVA statistical to preprocessing data and selection the significant features, and Support Vector Machines in the classification process. To compare and evaluate the performance, we choice three classification algorithms, decision tree Naïve Bayes, Support Vector Machines and applied the medical datasets direct to these algorithms. Our methodology was a much better classification accuracy is given of 98% in Arrhythmia datasets, 92% in Breast cancer datasets and 88% in Hepatitis datasets, Compare to use the medical data directly with decision tree Naïve Bayes, and Support Vector Machines. Also, the ROC curve and precision with (K-ANOVA-SVM) Achieved best results than other algorithms

Multi-output decision trees for lesion segmentation in multiple sclerosis

NASA Astrophysics Data System (ADS)

Jog, Amod; Carass, Aaron; Pham, Dzung L.; Prince, Jerry L.

2015-03-01

Multiple Sclerosis (MS) is a disease of the central nervous system in which the protective myelin sheath of the neurons is damaged. MS leads to the formation of lesions, predominantly in the white matter of the brain and the spinal cord. The number and volume of lesions visible in magnetic resonance (MR) imaging (MRI) are important criteria for diagnosing and tracking the progression of MS. Locating and delineating lesions manually requires the tedious and expensive efforts of highly trained raters. In this paper, we propose an automated algorithm to segment lesions in MR images using multi-output decision trees. We evaluated our algorithm on the publicly available MICCAI 2008 MS Lesion Segmentation Challenge training dataset of 20 subjects, and showed improved results in comparison to state-of-the-art methods. We also evaluated our algorithm on an in-house dataset of 49 subjects with a true positive rate of 0.41 and a positive predictive value 0.36.

A decision support system using combined-classifier for high-speed data stream in smart grid

NASA Astrophysics Data System (ADS)

Yang, Hang; Li, Peng; He, Zhian; Guo, Xiaobin; Fong, Simon; Chen, Huajun

2016-11-01

Large volume of high-speed streaming data is generated by big power grids continuously. In order to detect and avoid power grid failure, decision support systems (DSSs) are commonly adopted in power grid enterprises. Among all the decision-making algorithms, incremental decision tree is the most widely used one. In this paper, we propose a combined classifier that is a composite of a cache-based classifier (CBC) and a main tree classifier (MTC). We integrate this classifier into a stream processing engine on top of the DSS such that high-speed steaming data can be transformed into operational intelligence efficiently. Experimental results show that our proposed classifier can return more accurate answers than other existing ones.

Decision Trees Predicting Tumor Shrinkage for Head and Neck Cancer: Implications for Adaptive Radiotherapy.

PubMed

Surucu, Murat; Shah, Karan K; Mescioglu, Ibrahim; Roeske, John C; Small, William; Choi, Mehee; Emami, Bahman

2016-02-01

To develop decision trees predicting for tumor volume reduction in patients with head and neck (H&N) cancer using pretreatment clinical and pathological parameters. Forty-eight patients treated with definitive concurrent chemoradiotherapy for squamous cell carcinoma of the nasopharynx, oropharynx, oral cavity, or hypopharynx were retrospectively analyzed. These patients were rescanned at a median dose of 37.8 Gy and replanned to account for anatomical changes. The percentages of gross tumor volume (GTV) change from initial to rescan computed tomography (CT; %GTVΔ) were calculated. Two decision trees were generated to correlate %GTVΔ in primary and nodal volumes with 14 characteristics including age, gender, Karnofsky performance status (KPS), site, human papilloma virus (HPV) status, tumor grade, primary tumor growth pattern (endophytic/exophytic), tumor/nodal/group stages, chemotherapy regimen, and primary, nodal, and total GTV volumes in the initial CT scan. The C4.5 Decision Tree induction algorithm was implemented. The median %GTVΔ for primary, nodal, and total GTVs was 26.8%, 43.0%, and 31.2%, respectively. Type of chemotherapy, age, primary tumor growth pattern, site, KPS, and HPV status were the most predictive parameters for primary %GTVΔ decision tree, whereas for nodal %GTVΔ, KPS, site, age, primary tumor growth pattern, initial primary GTV, and total GTV volumes were predictive. Both decision trees had an accuracy of 88%. There can be significant changes in primary and nodal tumor volumes during the course of H&N chemoradiotherapy. Considering the proposed decision trees, radiation oncologists can select patients predicted to have high %GTVΔ, who would theoretically gain the most benefit from adaptive radiotherapy, in order to better use limited clinical resources. © The Author(s) 2015.

Identification of pests and diseases of Dalbergia hainanensis based on EVI time series and classification of decision tree

NASA Astrophysics Data System (ADS)

Luo, Qiu; Xin, Wu; Qiming, Xiong

2017-06-01

In the process of vegetation remote sensing information extraction, the problem of phenological features and low performance of remote sensing analysis algorithm is not considered. To solve this problem, the method of remote sensing vegetation information based on EVI time-series and the classification of decision-tree of multi-source branch similarity is promoted. Firstly, to improve the time-series stability of recognition accuracy, the seasonal feature of vegetation is extracted based on the fitting span range of time-series. Secondly, the decision-tree similarity is distinguished by adaptive selection path or probability parameter of component prediction. As an index, it is to evaluate the degree of task association, decide whether to perform migration of multi-source decision tree, and ensure the speed of migration. Finally, the accuracy of classification and recognition of pests and diseases can reach 87%--98% of commercial forest in Dalbergia hainanensis, which is significantly better than that of MODIS coverage accuracy of 80%--96% in this area. Therefore, the validity of the proposed method can be verified.

Profiling Arthritis Pain with a Decision Tree.

PubMed

Hung, Man; Bounsanga, Jerry; Liu, Fangzhou; Voss, Maren W

2018-06-01

Arthritis is the leading cause of work disability and contributes to lost productivity. Previous studies showed that various factors predict pain, but they were limited in sample size and scope from a data analytics perspective. The current study applied machine learning algorithms to identify predictors of pain associated with arthritis in a large national sample. Using data from the 2011 to 2012 Medical Expenditure Panel Survey, data mining was performed to develop algorithms to identify factors and patterns that contribute to risk of pain. The model incorporated over 200 variables within the algorithm development, including demographic data, medical claims, laboratory tests, patient-reported outcomes, and sociobehavioral characteristics. The developed algorithms to predict pain utilize variables readily available in patient medical records. Using the machine learning classification algorithm J48 with 50-fold cross-validations, we found that the model can significantly distinguish those with and without pain (c-statistics = 0.9108). The F measure was 0.856, accuracy rate was 85.68%, sensitivity was 0.862, specificity was 0.852, and precision was 0.849. Physical and mental function scores, the ability to climb stairs, and overall assessment of feeling were the most discriminative predictors from the 12 identified variables, predicting pain with 86% accuracy for individuals with arthritis. In this era of rapid expansion of big data application, the nature of healthcare research is moving from hypothesis-driven to data-driven solutions. The algorithms generated in this study offer new insights on individualized pain prediction, allowing the development of cost-effective care management programs for those experiencing arthritis pain. © 2017 World Institute of Pain.

Multi-Parent Clustering Algorithms from Stochastic Grammar Data Models

NASA Technical Reports Server (NTRS)

Mjoisness, Eric; Castano, Rebecca; Gray, Alexander

1999-01-01

We introduce a statistical data model and an associated optimization-based clustering algorithm which allows data vectors to belong to zero, one or several "parent" clusters. For each data vector the algorithm makes a discrete decision among these alternatives. Thus, a recursive version of this algorithm would place data clusters in a Directed Acyclic Graph rather than a tree. We test the algorithm with synthetic data generated according to the statistical data model. We also illustrate the algorithm using real data from large-scale gene expression assays.

Personalized Modeling for Prediction with Decision-Path Models

PubMed Central

Visweswaran, Shyam; Ferreira, Antonio; Ribeiro, Guilherme A.; Oliveira, Alexandre C.; Cooper, Gregory F.

2015-01-01

Deriving predictive models in medicine typically relies on a population approach where a single model is developed from a dataset of individuals. In this paper we describe and evaluate a personalized approach in which we construct a new type of decision tree model called decision-path model that takes advantage of the particular features of a given person of interest. We introduce three personalized methods that derive personalized decision-path models. We compared the performance of these methods to that of Classification And Regression Tree (CART) that is a population decision tree to predict seven different outcomes in five medical datasets. Two of the three personalized methods performed statistically significantly better on area under the ROC curve (AUC) and Brier skill score compared to CART. The personalized approach of learning decision path models is a new approach for predictive modeling that can perform better than a population approach. PMID:26098570

3D Visualization of Machine Learning Algorithms with Astronomical Data

NASA Astrophysics Data System (ADS)

Kent, Brian R.

2016-01-01

We present innovative machine learning (ML) methods using unsupervised clustering with minimum spanning trees (MSTs) to study 3D astronomical catalogs. Utilizing Python code to build trees based on galaxy catalogs, we can render the results with the visualization suite Blender to produce interactive 360 degree panoramic videos. The catalogs and their ML results can be explored in a 3D space using mobile devices, tablets or desktop browsers. We compare the statistics of the MST results to a number of machine learning methods relating to optimization and efficiency.

Rapid Prediction of Bacterial Heterotrophic Fluxomics Using Machine Learning and Constraint Programming.

PubMed

Wu, Stephen Gang; Wang, Yuxuan; Jiang, Wu; Oyetunde, Tolutola; Yao, Ruilian; Zhang, Xuehong; Shimizu, Kazuyuki; Tang, Yinjie J; Bao, Forrest Sheng

2016-04-01

13C metabolic flux analysis (13C-MFA) has been widely used to measure in vivo enzyme reaction rates (i.e., metabolic flux) in microorganisms. Mining the relationship between environmental and genetic factors and metabolic fluxes hidden in existing fluxomic data will lead to predictive models that can significantly accelerate flux quantification. In this paper, we present a web-based platform MFlux (http://mflux.org) that predicts the bacterial central metabolism via machine learning, leveraging data from approximately 100 13C-MFA papers on heterotrophic bacterial metabolisms. Three machine learning methods, namely Support Vector Machine (SVM), k-Nearest Neighbors (k-NN), and Decision Tree, were employed to study the sophisticated relationship between influential factors and metabolic fluxes. We performed a grid search of the best parameter set for each algorithm and verified their performance through 10-fold cross validations. SVM yields the highest accuracy among all three algorithms. Further, we employed quadratic programming to adjust flux profiles to satisfy stoichiometric constraints. Multiple case studies have shown that MFlux can reasonably predict fluxomes as a function of bacterial species, substrate types, growth rate, oxygen conditions, and cultivation methods. Due to the interest of studying model organism under particular carbon sources, bias of fluxome in the dataset may limit the applicability of machine learning models. This problem can be resolved after more papers on 13C-MFA are published for non-model species.

Rapid Prediction of Bacterial Heterotrophic Fluxomics Using Machine Learning and Constraint Programming

PubMed Central

Wu, Stephen Gang; Wang, Yuxuan; Jiang, Wu; Oyetunde, Tolutola; Yao, Ruilian; Zhang, Xuehong; Shimizu, Kazuyuki; Tang, Yinjie J.; Bao, Forrest Sheng

2016-01-01

13C metabolic flux analysis (13C-MFA) has been widely used to measure in vivo enzyme reaction rates (i.e., metabolic flux) in microorganisms. Mining the relationship between environmental and genetic factors and metabolic fluxes hidden in existing fluxomic data will lead to predictive models that can significantly accelerate flux quantification. In this paper, we present a web-based platform MFlux (http://mflux.org) that predicts the bacterial central metabolism via machine learning, leveraging data from approximately 100 13C-MFA papers on heterotrophic bacterial metabolisms. Three machine learning methods, namely Support Vector Machine (SVM), k-Nearest Neighbors (k-NN), and Decision Tree, were employed to study the sophisticated relationship between influential factors and metabolic fluxes. We performed a grid search of the best parameter set for each algorithm and verified their performance through 10-fold cross validations. SVM yields the highest accuracy among all three algorithms. Further, we employed quadratic programming to adjust flux profiles to satisfy stoichiometric constraints. Multiple case studies have shown that MFlux can reasonably predict fluxomes as a function of bacterial species, substrate types, growth rate, oxygen conditions, and cultivation methods. Due to the interest of studying model organism under particular carbon sources, bias of fluxome in the dataset may limit the applicability of machine learning models. This problem can be resolved after more papers on 13C-MFA are published for non-model species. PMID:27092947

The discovery of structural form

PubMed Central

Kemp, Charles; Tenenbaum, Joshua B.

2008-01-01

Algorithms for finding structure in data have become increasingly important both as tools for scientific data analysis and as models of human learning, yet they suffer from a critical limitation. Scientists discover qualitatively new forms of structure in observed data: For instance, Linnaeus recognized the hierarchical organization of biological species, and Mendeleev recognized the periodic structure of the chemical elements. Analogous insights play a pivotal role in cognitive development: Children discover that object category labels can be organized into hierarchies, friendship networks are organized into cliques, and comparative relations (e.g., “bigger than” or “better than”) respect a transitive order. Standard algorithms, however, can only learn structures of a single form that must be specified in advance: For instance, algorithms for hierarchical clustering create tree structures, whereas algorithms for dimensionality-reduction create low-dimensional spaces. Here, we present a computational model that learns structures of many different forms and that discovers which form is best for a given dataset. The model makes probabilistic inferences over a space of graph grammars representing trees, linear orders, multidimensional spaces, rings, dominance hierarchies, cliques, and other forms and successfully discovers the underlying structure of a variety of physical, biological, and social domains. Our approach brings structure learning methods closer to human abilities and may lead to a deeper computational understanding of cognitive development. PMID:18669663

Hybrid analysis for indicating patients with breast cancer using temperature time series.

PubMed

Silva, Lincoln F; Santos, Alair Augusto S M D; Bravo, Renato S; Silva, Aristófanes C; Muchaluat-Saade, Débora C; Conci, Aura

2016-07-01

Breast cancer is the most common cancer among women worldwide. Diagnosis and treatment in early stages increase cure chances. The temperature of cancerous tissue is generally higher than that of healthy surrounding tissues, making thermography an option to be considered in screening strategies of this cancer type. This paper proposes a hybrid methodology for analyzing dynamic infrared thermography in order to indicate patients with risk of breast cancer, using unsupervised and supervised machine learning techniques, which characterizes the methodology as hybrid. The dynamic infrared thermography monitors or quantitatively measures temperature changes on the examined surface, after a thermal stress. In the dynamic infrared thermography execution, a sequence of breast thermograms is generated. In the proposed methodology, this sequence is processed and analyzed by several techniques. First, the region of the breasts is segmented and the thermograms of the sequence are registered. Then, temperature time series are built and the k-means algorithm is applied on these series using various values of k. Clustering formed by k-means algorithm, for each k value, is evaluated using clustering validation indices, generating values treated as features in the classification model construction step. A data mining tool was used to solve the combined algorithm selection and hyperparameter optimization (CASH) problem in classification tasks. Besides the classification algorithm recommended by the data mining tool, classifiers based on Bayesian networks, neural networks, decision rules and decision tree were executed on the data set used for evaluation. Test results support that the proposed analysis methodology is able to indicate patients with breast cancer. Among 39 tested classification algorithms, K-Star and Bayes Net presented 100% classification accuracy. Furthermore, among the Bayes Net, multi-layer perceptron, decision table and random forest classification algorithms, an average accuracy of 95.38% was obtained. Copyright © 2016 Elsevier Ireland Ltd. All rights reserved.

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.

Multivariate analysis of flow cytometric data using decision trees.

PubMed

Simon, Svenja; Guthke, Reinhard; Kamradt, Thomas; Frey, Oliver

2012-01-01

Characterization of the response of the host immune system is important in understanding the bidirectional interactions between the host and microbial pathogens. For research on the host site, flow cytometry has become one of the major tools in immunology. Advances in technology and reagents allow now the simultaneous assessment of multiple markers on a single cell level generating multidimensional data sets that require multivariate statistical analysis. We explored the explanatory power of the supervised machine learning method called "induction of decision trees" in flow cytometric data. In order to examine whether the production of a certain cytokine is depended on other cytokines, datasets from intracellular staining for six cytokines with complex patterns of co-expression were analyzed by induction of decision trees. After weighting the data according to their class probabilities, we created a total of 13,392 different decision trees for each given cytokine with different parameter settings. For a more realistic estimation of the decision trees' quality, we used stratified fivefold cross validation and chose the "best" tree according to a combination of different quality criteria. While some of the decision trees reflected previously known co-expression patterns, we found that the expression of some cytokines was not only dependent on the co-expression of others per se, but was also dependent on the intensity of expression. Thus, for the first time we successfully used induction of decision trees for the analysis of high dimensional flow cytometric data and demonstrated the feasibility of this method to reveal structural patterns in such data sets.

A combined NLP-differential evolution algorithm approach for the optimization of looped water distribution systems

NASA Astrophysics Data System (ADS)

Zheng, Feifei; Simpson, Angus R.; Zecchin, Aaron C.

2011-08-01

This paper proposes a novel optimization approach for the least cost design of looped water distribution systems (WDSs). Three distinct steps are involved in the proposed optimization approach. In the first step, the shortest-distance tree within the looped network is identified using the Dijkstra graph theory algorithm, for which an extension is proposed to find the shortest-distance tree for multisource WDSs. In the second step, a nonlinear programming (NLP) solver is employed to optimize the pipe diameters for the shortest-distance tree (chords of the shortest-distance tree are allocated the minimum allowable pipe sizes). Finally, in the third step, the original looped water network is optimized using a differential evolution (DE) algorithm seeded with diameters in the proximity of the continuous pipe sizes obtained in step two. As such, the proposed optimization approach combines the traditional deterministic optimization technique of NLP with the emerging evolutionary algorithm DE via the proposed network decomposition. The proposed methodology has been tested on four looped WDSs with the number of decision variables ranging from 21 to 454. Results obtained show the proposed approach is able to find optimal solutions with significantly less computational effort than other optimization techniques.

Classification techniques on computerized systems to predict and/or to detect Apnea: A systematic review.

PubMed

Pombo, Nuno; Garcia, Nuno; Bousson, Kouamana

2017-03-01

Sleep apnea syndrome (SAS), which can significantly decrease the quality of life is associated with a major risk factor of health implications such as increased cardiovascular disease, sudden death, depression, irritability, hypertension, and learning difficulties. Thus, it is relevant and timely to present a systematic review describing significant applications in the framework of computational intelligence-based SAS, including its performance, beneficial and challenging effects, and modeling for the decision-making on multiple scenarios. This study aims to systematically review the literature on systems for the detection and/or prediction of apnea events using a classification model. Forty-five included studies revealed a combination of classification techniques for the diagnosis of apnea, such as threshold-based (14.75%) and machine learning (ML) models (85.25%). In addition, the ML models, were clustered in a mind map, include neural networks (44.26%), regression (4.91%), instance-based (11.47%), Bayesian algorithms (1.63%), reinforcement learning (4.91%), dimensionality reduction (8.19%), ensemble learning (6.55%), and decision trees (3.27%). A classification model should provide an auto-adaptive and no external-human action dependency. In addition, the accuracy of the classification models is related with the effective features selection. New high-quality studies based on randomized controlled trials and validation of models using a large and multiple sample of data are recommended. Copyright © 2017 Elsevier Ireland Ltd. All rights reserved.

Maximum-likelihood soft-decision decoding of block codes using the A* algorithm

NASA Technical Reports Server (NTRS)

Ekroot, L.; Dolinar, S.

1994-01-01

The A* algorithm finds the path in a finite depth binary tree that optimizes a function. Here, it is applied to maximum-likelihood soft-decision decoding of block codes where the function optimized over the codewords is the likelihood function of the received sequence given each codeword. The algorithm considers codewords one bit at a time, making use of the most reliable received symbols first and pursuing only the partially expanded codewords that might be maximally likely. A version of the A* algorithm for maximum-likelihood decoding of block codes has been implemented for block codes up to 64 bits in length. The efficiency of this algorithm makes simulations of codes up to length 64 feasible. This article details the implementation currently in use, compares the decoding complexity with that of exhaustive search and Viterbi decoding algorithms, and presents performance curves obtained with this implementation of the A* algorithm for several codes.

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.

Sequential decision tree using the analytic hierarchy process for decision support in rectal cancer.

PubMed

Suner, Aslı; Çelikoğlu, Can Cengiz; Dicle, Oğuz; Sökmen, Selman

2012-09-01

The aim of the study is to determine the most appropriate method for construction of a sequential decision tree in the management of rectal cancer, using various patient-specific criteria and treatments such as surgery, chemotherapy, and radiotherapy. An analytic hierarchy process (AHP) was used to determine the priorities of variables. Relevant criteria used in two decision steps and their relative priorities were established by a panel of five general surgeons. Data were collected via a web-based application and analyzed using the "Expert Choice" software specifically developed for the AHP. Consistency ratios in the AHP method were calculated for each set of judgments, and the priorities of sub-criteria were determined. A sequential decision tree was constructed for the best treatment decision process, using priorities determined by the AHP method. Consistency ratios in the AHP method were calculated for each decision step, and the judgments were considered consistent. The tumor-related criterion "presence of perforation" (0.331) and the patient-surgeon-related criterion "surgeon's experience" (0.630) had the highest priority in the first decision step. In the second decision step, the tumor-related criterion "the stage of the disease" (0.230) and the patient-surgeon-related criterion "surgeon's experience" (0.281) were the paramount criteria. The results showed some variation in the ranking of criteria between the decision steps. In the second decision step, for instance, the tumor-related criterion "presence of perforation" was just the fifth. The consistency of decision support systems largely depends on the quality of the underlying decision tree. When several choices and variables have to be considered in a decision, it is very important to determine priorities. The AHP method seems to be effective for this purpose. The decision algorithm developed by this method is more realistic and will improve the quality of the decision tree. Copyright © 2012 Elsevier B.V. All rights reserved.

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.

Large-scale linear rankSVM.

PubMed

Lee, Ching-Pei; Lin, Chih-Jen

2014-04-01

Linear rankSVM is one of the widely used methods for learning to rank. Although its performance may be inferior to nonlinear methods such as kernel rankSVM and gradient boosting decision trees, linear rankSVM is useful to quickly produce a baseline model. Furthermore, following its recent development for classification, linear rankSVM may give competitive performance for large and sparse data. A great deal of works have studied linear rankSVM. The focus is on the computational efficiency when the number of preference pairs is large. In this letter, we systematically study existing works, discuss their advantages and disadvantages, and propose an efficient algorithm. We discuss different implementation issues and extensions with detailed experiments. Finally, we develop a robust linear rankSVM tool for public use.

Towards the prediction of essential genes by integration of network topology, cellular localization and biological process information

PubMed Central

2009-01-01

Background The identification of essential genes is important for the understanding of the minimal requirements for cellular life and for practical purposes, such as drug design. However, the experimental techniques for essential genes discovery are labor-intensive and time-consuming. Considering these experimental constraints, a computational approach capable of accurately predicting essential genes would be of great value. We therefore present here a machine learning-based computational approach relying on network topological features, cellular localization and biological process information for prediction of essential genes. Results We constructed a decision tree-based meta-classifier and trained it on datasets with individual and grouped attributes-network topological features, cellular compartments and biological processes-to generate various predictors of essential genes. We showed that the predictors with better performances are those generated by datasets with integrated attributes. Using the predictor with all attributes, i.e., network topological features, cellular compartments and biological processes, we obtained the best predictor of essential genes that was then used to classify yeast genes with unknown essentiality status. Finally, we generated decision trees by training the J48 algorithm on datasets with all network topological features, cellular localization and biological process information to discover cellular rules for essentiality. We found that the number of protein physical interactions, the nuclear localization of proteins and the number of regulating transcription factors are the most important factors determining gene essentiality. Conclusion We were able to demonstrate that network topological features, cellular localization and biological process information are reliable predictors of essential genes. Moreover, by constructing decision trees based on these data, we could discover cellular rules governing essentiality. PMID:19758426

Application of Decision Tree on Collision Avoidance System Design and Verification for Quadcopter

NASA Astrophysics Data System (ADS)

Chen, C.-W.; Hsieh, P.-H.; Lai, W.-H.

2017-08-01

The purpose of the research is to build a collision avoidance system with decision tree algorithm used for quadcopters. While the ultrasonic range finder judges the distance is in collision avoidance interval, the access will be replaced from operator to the system to control the altitude of the UAV. According to the former experiences on operating quadcopters, we can obtain the appropriate pitch angle. The UAS implement the following three motions to avoid collisions. Case1: initial slow avoidance stage, Case2: slow avoidance stage and Case3: Rapid avoidance stage. Then the training data of collision avoidance test will be transmitted to the ground station via wireless transmission module to further analysis. The entire decision tree algorithm of collision avoidance system, transmission data, and ground station have been verified in some flight tests. In the flight test, the quadcopter can implement avoidance motion in real-time and move away from obstacles steadily. In the avoidance area, the authority of the collision avoidance system is higher than the operator and implements the avoidance process. The quadcopter can successfully fly away from the obstacles in 1.92 meter per second and the minimum distance between the quadcopter and the obstacle is 1.05 meters.

Multiattribute Decision Modeling Techniques: A Comparative Analysis

DTIC Science & Technology

1988-08-01

Analytic Hierarchy Process ( AHP ). It is structurally similar to SMART, but elicitation methods are different and there are several algorithms for...reconciliation of inconsistent judgments and for consistency checks that are not available in any of the utility procedures. The AHP has been applied...of commercially available software packages that implement the AHP algorithms. Elicitation Methods. The AHP builds heavily on value trees, which

Predicting volume of distribution with decision tree-based regression methods using predicted tissue:plasma partition coefficients.

PubMed

Freitas, Alex A; Limbu, Kriti; Ghafourian, Taravat

2015-01-01

Volume of distribution is an important pharmacokinetic property that indicates the extent of a drug's distribution in the body tissues. This paper addresses the problem of how to estimate the apparent volume of distribution at steady state (Vss) of chemical compounds in the human body using decision tree-based regression methods from the area of data mining (or machine learning). Hence, the pros and cons of several different types of decision tree-based regression methods have been discussed. The regression methods predict Vss using, as predictive features, both the compounds' molecular descriptors and the compounds' tissue:plasma partition coefficients (Kt:p) - often used in physiologically-based pharmacokinetics. Therefore, this work has assessed whether the data mining-based prediction of Vss can be made more accurate by using as input not only the compounds' molecular descriptors but also (a subset of) their predicted Kt:p values. Comparison of the models that used only molecular descriptors, in particular, the Bagging decision tree (mean fold error of 2.33), with those employing predicted Kt:p values in addition to the molecular descriptors, such as the Bagging decision tree using adipose Kt:p (mean fold error of 2.29), indicated that the use of predicted Kt:p values as descriptors may be beneficial for accurate prediction of Vss using decision trees if prior feature selection is applied. Decision tree based models presented in this work have an accuracy that is reasonable and similar to the accuracy of reported Vss inter-species extrapolations in the literature. The estimation of Vss for new compounds in drug discovery will benefit from methods that are able to integrate large and varied sources of data and flexible non-linear data mining methods such as decision trees, which can produce interpretable models. Graphical AbstractDecision trees for the prediction of tissue partition coefficient and volume of distribution of drugs.

Classifying smoking urges via machine learning

PubMed Central

Dumortier, Antoine; Beckjord, Ellen; Shiffman, Saul; Sejdić, Ervin

2016-01-01

Background and objective Smoking is the largest preventable cause of death and diseases in the developed world, and advances in modern electronics and machine learning can help us deliver real-time intervention to smokers in novel ways. In this paper, we examine different machine learning approaches to use situational features associated with having or not having urges to smoke during a quit attempt in order to accurately classify high-urge states. Methods To test our machine learning approaches, specifically, Bayes, discriminant analysis and decision tree learning methods, we used a dataset collected from over 300 participants who had initiated a quit attempt. The three classification approaches are evaluated observing sensitivity, specificity, accuracy and precision. Results The outcome of the analysis showed that algorithms based on feature selection make it possible to obtain high classification rates with only a few features selected from the entire dataset. The classification tree method outperformed the naive Bayes and discriminant analysis methods, with an accuracy of the classifications up to 86%. These numbers suggest that machine learning may be a suitable approach to deal with smoking cessation matters, and to predict smoking urges, outlining a potential use for mobile health applications. Conclusions In conclusion, machine learning classifiers can help identify smoking situations, and the search for the best features and classifier parameters significantly improves the algorithms’ performance. In addition, this study also supports the usefulness of new technologies in improving the effect of smoking cessation interventions, the management of time and patients by therapists, and thus the optimization of available health care resources. Future studies should focus on providing more adaptive and personalized support to people who really need it, in a minimum amount of time by developing novel expert systems capable of delivering real-time interventions. PMID:28110725

Rejecting Non-MIP-Like Tracks using Boosted Decision Trees with the T2K Pi-Zero Subdetector

NASA Astrophysics Data System (ADS)

Hogan, Matthew; Schwehr, Jacklyn; Cherdack, Daniel; Wilson, Robert; T2K Collaboration

2016-03-01

Tokai-to-Kamioka (T2K) is a long-baseline neutrino experiment with a narrow band energy spectrum peaked at 600 MeV. The Pi-Zero detector (PØD) is a plastic scintillator-based detector located in the off-axis near detector complex 280 meters from the beam origin. It is designed to constrain neutral-current induced π0 production background at the far detector using the water target which is interleaved between scintillator layers. A PØD-based measurement of charged-current (CC) single charged pion (1π+) production on water is being developed which will have expanded phase space coverage as compared to the previous analysis. The signal channel for this analysis, which for T2K is dominated by Δ production, is defined as events that produce a single muon, single charged pion, and any number of nucleons in the final state. The analysis will employ machine learning algorithms to enhance CC1π+ selection by studying topological observables that characterize signal well. Important observables for this analysis are those that discriminate a minimum ionizing particle (MIP) like a muon or pion from a proton at the T2K energies. This work describes the development of a discriminator using Boosted Decision Trees to reject non-MIP-like PØD tracks.

Effective Prediction of Errors by Non-native Speakers Using Decision Tree for Speech Recognition-Based CALL System

NASA Astrophysics Data System (ADS)

Wang, Hongcui; Kawahara, Tatsuya

CALL (Computer Assisted Language Learning) systems using ASR (Automatic Speech Recognition) for second language learning have received increasing interest recently. However, it still remains a challenge to achieve high speech recognition performance, including accurate detection of erroneous utterances by non-native speakers. Conventionally, possible error patterns, based on linguistic knowledge, are added to the lexicon and language model, or the ASR grammar network. However, this approach easily falls in the trade-off of coverage of errors and the increase of perplexity. To solve the problem, we propose a method based on a decision tree to learn effective prediction of errors made by non-native speakers. An experimental evaluation with a number of foreign students learning Japanese shows that the proposed method can effectively generate an ASR grammar network, given a target sentence, to achieve both better coverage of errors and smaller perplexity, resulting in significant improvement in ASR accuracy.

The Burn Medical Assistant: Developing Machine Learning Algorithms to Aid in the Estimation of Burn Wound Size

DTIC Science & Technology

2017-10-01

hypothesis that a computer machine learning algorithm can analyze and classify burn injures using multispectral imaging within 5% of an expert clinician...morbidity. In response to these challenges, the USAISR developed and obtained FDA 510(k) clearance of the Burn Navigator™, a computer decision support... computer decision support software (CDSS), can significantly change the CDSS algorithm’s recommendations and thus the total fluid administered to a

Learn ++.NC: combining ensemble of classifiers with dynamically weighted consult-and-vote for efficient incremental learning of new classes.

PubMed

Muhlbaier, Michael D; Topalis, Apostolos; Polikar, Robi

2009-01-01

We have previously introduced an incremental learning algorithm Learn(++), which learns novel information from consecutive data sets by generating an ensemble of classifiers with each data set, and combining them by weighted majority voting. However, Learn(++) suffers from an inherent "outvoting" problem when asked to learn a new class omega(new) introduced by a subsequent data set, as earlier classifiers not trained on this class are guaranteed to misclassify omega(new) instances. The collective votes of earlier classifiers, for an inevitably incorrect decision, then outweigh the votes of the new classifiers' correct decision on omega(new) instances--until there are enough new classifiers to counteract the unfair outvoting. This forces Learn(++) to generate an unnecessarily large number of classifiers. This paper describes Learn(++).NC, specifically designed for efficient incremental learning of multiple new classes using significantly fewer classifiers. To do so, Learn (++).NC introduces dynamically weighted consult and vote (DW-CAV), a novel voting mechanism for combining classifiers: individual classifiers consult with each other to determine which ones are most qualified to classify a given instance, and decide how much weight, if any, each classifier's decision should carry. Experiments on real-world problems indicate that the new algorithm performs remarkably well with substantially fewer classifiers, not only as compared to its predecessor Learn(++), but also as compared to several other algorithms recently proposed for similar problems.

Mastering the game of Go without human knowledge.

PubMed

Silver, David; Schrittwieser, Julian; Simonyan, Karen; Antonoglou, Ioannis; Huang, Aja; Guez, Arthur; Hubert, Thomas; Baker, Lucas; Lai, Matthew; Bolton, Adrian; Chen, Yutian; Lillicrap, Timothy; Hui, Fan; Sifre, Laurent; van den Driessche, George; Graepel, Thore; Hassabis, Demis

2017-10-18

A long-standing goal of artificial intelligence is an algorithm that learns, tabula rasa, superhuman proficiency in challenging domains. Recently, AlphaGo became the first program to defeat a world champion in the game of Go. The tree search in AlphaGo evaluated positions and selected moves using deep neural networks. These neural networks were trained by supervised learning from human expert moves, and by reinforcement learning from self-play. Here we introduce an algorithm based solely on reinforcement learning, without human data, guidance or domain knowledge beyond game rules. AlphaGo becomes its own teacher: a neural network is trained to predict AlphaGo's own move selections and also the winner of AlphaGo's games. This neural network improves the strength of the tree search, resulting in higher quality move selection and stronger self-play in the next iteration. Starting tabula rasa, our new program AlphaGo Zero achieved superhuman performance, winning 100-0 against the previously published, champion-defeating AlphaGo.

Mastering the game of Go without human knowledge

NASA Astrophysics Data System (ADS)

Silver, David; Schrittwieser, Julian; Simonyan, Karen; Antonoglou, Ioannis; Huang, Aja; Guez, Arthur; Hubert, Thomas; Baker, Lucas; Lai, Matthew; Bolton, Adrian; Chen, Yutian; Lillicrap, Timothy; Hui, Fan; Sifre, Laurent; van den Driessche, George; Graepel, Thore; Hassabis, Demis

2017-10-01

A long-standing goal of artificial intelligence is an algorithm that learns, tabula rasa, superhuman proficiency in challenging domains. Recently, AlphaGo became the first program to defeat a world champion in the game of Go. The tree search in AlphaGo evaluated positions and selected moves using deep neural networks. These neural networks were trained by supervised learning from human expert moves, and by reinforcement learning from self-play. Here we introduce an algorithm based solely on reinforcement learning, without human data, guidance or domain knowledge beyond game rules. AlphaGo becomes its own teacher: a neural network is trained to predict AlphaGo’s own move selections and also the winner of AlphaGo’s games. This neural network improves the strength of the tree search, resulting in higher quality move selection and stronger self-play in the next iteration. Starting tabula rasa, our new program AlphaGo Zero achieved superhuman performance, winning 100-0 against the previously published, champion-defeating AlphaGo.

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.

Scalable Machine Learning for Massive Astronomical Datasets

NASA Astrophysics Data System (ADS)

Ball, Nicholas M.; Gray, A.

2014-04-01

We present the ability to perform data mining and machine learning operations on a catalog of half a billion astronomical objects. This is the result of the combination of robust, highly accurate machine learning algorithms with linear scalability that renders the applications of these algorithms to massive astronomical data tractable. We demonstrate the core algorithms kernel density estimation, K-means clustering, linear regression, nearest neighbors, random forest and gradient-boosted decision tree, singular value decomposition, support vector machine, and two-point correlation function. Each of these is relevant for astronomical applications such as finding novel astrophysical objects, characterizing artifacts in data, object classification (including for rare objects), object distances, finding the important features describing objects, density estimation of distributions, probabilistic quantities, and exploring the unknown structure of new data. The software, Skytree Server, runs on any UNIX-based machine, a virtual machine, or cloud-based and distributed systems including Hadoop. We have integrated it on the cloud computing system of the Canadian Astronomical Data Centre, the Canadian Advanced Network for Astronomical Research (CANFAR), creating the world's first cloud computing data mining system for astronomy. We demonstrate results showing the scaling of each of our major algorithms on large astronomical datasets, including the full 470,992,970 objects of the 2 Micron All-Sky Survey (2MASS) Point Source Catalog. We demonstrate the ability to find outliers in the full 2MASS dataset utilizing multiple methods, e.g., nearest neighbors. This is likely of particular interest to the radio astronomy community given, for example, that survey projects contain groups dedicated to this topic. 2MASS is used as a proof-of-concept dataset due to its convenience and availability. These results are of interest to any astronomical project with large and/or complex datasets that wishes to extract the full scientific value from its data.

Scalable Machine Learning for Massive Astronomical Datasets

NASA Astrophysics Data System (ADS)

Ball, Nicholas M.; Astronomy Data Centre, Canadian

2014-01-01

We present the ability to perform data mining and machine learning operations on a catalog of half a billion astronomical objects. This is the result of the combination of robust, highly accurate machine learning algorithms with linear scalability that renders the applications of these algorithms to massive astronomical data tractable. We demonstrate the core algorithms kernel density estimation, K-means clustering, linear regression, nearest neighbors, random forest and gradient-boosted decision tree, singular value decomposition, support vector machine, and two-point correlation function. Each of these is relevant for astronomical applications such as finding novel astrophysical objects, characterizing artifacts in data, object classification (including for rare objects), object distances, finding the important features describing objects, density estimation of distributions, probabilistic quantities, and exploring the unknown structure of new data. The software, Skytree Server, runs on any UNIX-based machine, a virtual machine, or cloud-based and distributed systems including Hadoop. We have integrated it on the cloud computing system of the Canadian Astronomical Data Centre, the Canadian Advanced Network for Astronomical Research (CANFAR), creating the world's first cloud computing data mining system for astronomy. We demonstrate results showing the scaling of each of our major algorithms on large astronomical datasets, including the full 470,992,970 objects of the 2 Micron All-Sky Survey (2MASS) Point Source Catalog. We demonstrate the ability to find outliers in the full 2MASS dataset utilizing multiple methods, e.g., nearest neighbors, and the local outlier factor. 2MASS is used as a proof-of-concept dataset due to its convenience and availability. These results are of interest to any astronomical project with large and/or complex datasets that wishes to extract the full scientific value from its data.

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

Active Learning Using Hint Information.

PubMed

Li, Chun-Liang; Ferng, Chun-Sung; Lin, Hsuan-Tien

2015-08-01

The abundance of real-world data and limited labeling budget calls for active learning, an important learning paradigm for reducing human labeling efforts. Many recently developed active learning algorithms consider both uncertainty and representativeness when making querying decisions. However, exploiting representativeness with uncertainty concurrently usually requires tackling sophisticated and challenging learning tasks, such as clustering. In this letter, we propose a new active learning framework, called hinted sampling, which takes both uncertainty and representativeness into account in a simpler way. We design a novel active learning algorithm within the hinted sampling framework with an extended support vector machine. Experimental results validate that the novel active learning algorithm can result in a better and more stable performance than that achieved by state-of-the-art algorithms. We also show that the hinted sampling framework allows improving another active learning algorithm designed from the transductive support vector machine.

Integrative image segmentation optimization and machine learning approach for high quality land-use and land-cover mapping using multisource remote sensing data

NASA Astrophysics Data System (ADS)

Gibril, Mohamed Barakat A.; Idrees, Mohammed Oludare; Yao, Kouame; Shafri, Helmi Zulhaidi Mohd

2018-01-01

The growing use of optimization for geographic object-based image analysis and the possibility to derive a wide range of information about the image in textual form makes machine learning (data mining) a versatile tool for information extraction from multiple data sources. This paper presents application of data mining for land-cover classification by fusing SPOT-6, RADARSAT-2, and derived dataset. First, the images and other derived indices (normalized difference vegetation index, normalized difference water index, and soil adjusted vegetation index) were combined and subjected to segmentation process with optimal segmentation parameters obtained using combination of spatial and Taguchi statistical optimization. The image objects, which carry all the attributes of the input datasets, were extracted and related to the target land-cover classes through data mining algorithms (decision tree) for classification. To evaluate the performance, the result was compared with two nonparametric classifiers: support vector machine (SVM) and random forest (RF). Furthermore, the decision tree classification result was evaluated against six unoptimized trials segmented using arbitrary parameter combinations. The result shows that the optimized process produces better land-use land-cover classification with overall classification accuracy of 91.79%, 87.25%, and 88.69% for SVM and RF, respectively, while the results of the six unoptimized classifications yield overall accuracy between 84.44% and 88.08%. Higher accuracy of the optimized data mining classification approach compared to the unoptimized results indicates that the optimization process has significant impact on the classification quality.

Genetic programming based ensemble system for microarray data classification.

PubMed

Liu, Kun-Hong; Tong, Muchenxuan; Xie, Shu-Tong; Yee Ng, Vincent To

2015-01-01

Recently, more and more machine learning techniques have been applied to microarray data analysis. The aim of this study is to propose a genetic programming (GP) based new ensemble system (named GPES), which can be used to effectively classify different types of cancers. Decision trees are deployed as base classifiers in this ensemble framework with three operators: Min, Max, and Average. Each individual of the GP is an ensemble system, and they become more and more accurate in the evolutionary process. The feature selection technique and balanced subsampling technique are applied to increase the diversity in each ensemble system. The final ensemble committee is selected by a forward search algorithm, which is shown to be capable of fitting data automatically. The performance of GPES is evaluated using five binary class and six multiclass microarray datasets, and results show that the algorithm can achieve better results in most cases compared with some other ensemble systems. By using elaborate base classifiers or applying other sampling techniques, the performance of GPES may be further improved.

Genetic Programming Based Ensemble System for Microarray Data Classification

PubMed Central

Liu, Kun-Hong; Tong, Muchenxuan; Xie, Shu-Tong; Yee Ng, Vincent To

2015-01-01

Recently, more and more machine learning techniques have been applied to microarray data analysis. The aim of this study is to propose a genetic programming (GP) based new ensemble system (named GPES), which can be used to effectively classify different types of cancers. Decision trees are deployed as base classifiers in this ensemble framework with three operators: Min, Max, and Average. Each individual of the GP is an ensemble system, and they become more and more accurate in the evolutionary process. The feature selection technique and balanced subsampling technique are applied to increase the diversity in each ensemble system. The final ensemble committee is selected by a forward search algorithm, which is shown to be capable of fitting data automatically. The performance of GPES is evaluated using five binary class and six multiclass microarray datasets, and results show that the algorithm can achieve better results in most cases compared with some other ensemble systems. By using elaborate base classifiers or applying other sampling techniques, the performance of GPES may be further improved. PMID:25810748

A Pruning Neural Network Model in Credit Classification Analysis

PubMed Central

Tang, Yajiao; Ji, Junkai; Dai, Hongwei; Yu, Yang; Todo, Yuki

2018-01-01

Nowadays, credit classification models are widely applied because they can help financial decision-makers to handle credit classification issues. Among them, artificial neural networks (ANNs) have been widely accepted as the convincing methods in the credit industry. In this paper, we propose a pruning neural network (PNN) and apply it to solve credit classification problem by adopting the well-known Australian and Japanese credit datasets. The model is inspired by synaptic nonlinearity of a dendritic tree in a biological neural model. And it is trained by an error back-propagation algorithm. The model is capable of realizing a neuronal pruning function by removing the superfluous synapses and useless dendrites and forms a tidy dendritic morphology at the end of learning. Furthermore, we utilize logic circuits (LCs) to simulate the dendritic structures successfully which makes PNN be implemented on the hardware effectively. The statistical results of our experiments have verified that PNN obtains superior performance in comparison with other classical algorithms in terms of accuracy and computational efficiency. PMID:29606961

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.

Very short-term reactive forecasting of the solar ultraviolet index using an extreme learning machine integrated with the solar zenith angle.

PubMed

Deo, Ravinesh C; Downs, Nathan; Parisi, Alfio V; Adamowski, Jan F; Quilty, John M

2017-05-01

Exposure to erythemally-effective solar ultraviolet radiation (UVR) that contributes to malignant keratinocyte cancers and associated health-risk is best mitigated through innovative decision-support systems, with global solar UV index (UVI) forecast necessary to inform real-time sun-protection behaviour recommendations. It follows that the UVI forecasting models are useful tools for such decision-making. In this study, a model for computationally-efficient data-driven forecasting of diffuse and global very short-term reactive (VSTR) (10-min lead-time) UVI, enhanced by drawing on the solar zenith angle (θ s ) data, was developed using an extreme learning machine (ELM) algorithm. An ELM algorithm typically serves to address complex and ill-defined forecasting problems. UV spectroradiometer situated in Toowoomba, Australia measured daily cycles (0500-1700h) of UVI over the austral summer period. After trialling activations functions based on sine, hard limit, logarithmic and tangent sigmoid and triangular and radial basis networks for best results, an optimal ELM architecture utilising logarithmic sigmoid equation in hidden layer, with lagged combinations of θ s as the predictor data was developed. ELM's performance was evaluated using statistical metrics: correlation coefficient (r), Willmott's Index (WI), Nash-Sutcliffe efficiency coefficient (E NS ), root mean square error (RMSE), and mean absolute error (MAE) between observed and forecasted UVI. Using these metrics, the ELM model's performance was compared to that of existing methods: multivariate adaptive regression spline (MARS), M5 Model Tree, and a semi-empirical (Pro6UV) clear sky model. Based on RMSE and MAE values, the ELM model (0.255, 0.346, respectively) outperformed the MARS (0.310, 0.438) and M5 Model Tree (0.346, 0.466) models. Concurring with these metrics, the Willmott's Index for the ELM, MARS and M5 Model Tree models were 0.966, 0.942 and 0.934, respectively. About 57% of the ELM model's absolute errors were small in magnitude (±0.25), whereas the MARS and M5 Model Tree models generated 53% and 48% of such errors, respectively, indicating the latter models' errors to be distributed in larger magnitude error range. In terms of peak global UVI forecasting, with half the level of error, the ELM model outperformed MARS and M5 Model Tree. A comparison of the magnitude of hourly-cumulated errors of 10-min lead time forecasts for diffuse and global UVI highlighted ELM model's greater accuracy compared to MARS, M5 Model Tree or Pro6UV models. This confirmed the versatility of an ELM model drawing on θ s data for VSTR forecasting of UVI at near real-time horizon. When applied to the goal of enhancing expert systems, ELM-based accurate forecasts capable of reacting quickly to measured conditions can enhance real-time exposure advice for the public, mitigating the potential for solar UV-exposure-related disease. Crown Copyright © 2017. Published by Elsevier Inc. All rights reserved.

The application of a decision tree to establish the parameters associated with hypertension.

PubMed

Tayefi, Maryam; Esmaeili, Habibollah; Saberi Karimian, Maryam; Amirabadi Zadeh, Alireza; Ebrahimi, Mahmoud; Safarian, Mohammad; Nematy, Mohsen; Parizadeh, Seyed Mohammad Reza; Ferns, Gordon A; Ghayour-Mobarhan, Majid

2017-02-01

Hypertension is an important risk factor for cardiovascular disease (CVD). The goal of this study was to establish the factors associated with hypertension by using a decision-tree algorithm as a supervised classification method of data mining. Data from a cross-sectional study were used in this study. A total of 9078 subjects who met the inclusion criteria were recruited. 70% of these subjects (6358 cases) were randomly allocated to the training dataset for the constructing of the decision-tree. The remaining 30% (2720 cases) were used as the testing dataset to evaluate the performance of decision-tree. Two models were evaluated in this study. In model I, age, gender, body mass index, marital status, level of education, occupation status, depression and anxiety status, physical activity level, smoking status, LDL, TG, TC, FBG, uric acid and hs-CRP were considered as input variables and in model II, age, gender, WBC, RBC, HGB, HCT MCV, MCH, PLT, RDW and PDW were considered as input variables. The validation of the model was assessed by constructing a receiver operating characteristic (ROC) curve. The prevalence rates of hypertension were 32% in our population. For the decision-tree model I, the accuracy, sensitivity, specificity and area under the ROC curve (AUC) value for identifying the related risk factors of hypertension were 73%, 63%, 77% and 0.72, respectively. The corresponding values for model II were 70%, 61%, 74% and 0.68, respectively. We have developed a decision tree model to identify the risk factors associated with hypertension that maybe used to develop programs for hypertension management. Copyright © 2016 Elsevier Ireland Ltd. All rights reserved.

Self-growing neural network architecture using crisp and fuzzy entropy

NASA Technical Reports Server (NTRS)

Cios, Krzysztof J.

1992-01-01

The paper briefly describes the self-growing neural network algorithm, CID2, which makes decision trees equivalent to hidden layers of a neural network. The algorithm generates a feedforward architecture using crisp and fuzzy entropy measures. The results of a real-life recognition problem of distinguishing defects in a glass ribbon and of a benchmark problem of differentiating two spirals are shown and discussed.

Self-growing neural network architecture using crisp and fuzzy entropy

NASA Technical Reports Server (NTRS)

Cios, Krzysztof J.

1992-01-01

The paper briefly describes the self-growing neural network algorithm, CID3, which makes decision trees equivalent to hidden layers of a neural network. The algorithm generates a feedforward architecture using crisp and fuzzy entropy measures. The results for a real-life recognition problem of distinguishing defects in a glass ribbon, and for a benchmark problen of telling two spirals apart are shown and discussed.

Automatic Data Filter Customization Using a Genetic Algorithm

NASA Technical Reports Server (NTRS)

Mandrake, Lukas

2013-01-01

This work predicts whether a retrieval algorithm will usefully determine CO2 concentration from an input spectrum of GOSAT (Greenhouse Gases Observing Satellite). This was done to eliminate needless runtime on atmospheric soundings that would never yield useful results. A space of 50 dimensions was examined for predictive power on the final CO2 results. Retrieval algorithms are frequently expensive to run, and wasted effort defeats requirements and expends needless resources. This algorithm could be used to help predict and filter unneeded runs in any computationally expensive regime. Traditional methods such as the Fischer discriminant analysis and decision trees can attempt to predict whether a sounding will be properly processed. However, this work sought to detect a subsection of the dimensional space that can be simply filtered out to eliminate unwanted runs. LDAs (linear discriminant analyses) and other systems examine the entire data and judge a "best fit," giving equal weight to complex and problematic regions as well as simple, clear-cut regions. In this implementation, a genetic space of "left" and "right" thresholds outside of which all data are rejected was defined. These left/right pairs are created for each of the 50 input dimensions. A genetic algorithm then runs through countless potential filter settings using a JPL computer cluster, optimizing the tossed-out data s yield (proper vs. improper run removal) and number of points tossed. This solution is robust to an arbitrary decision boundary within the data and avoids the global optimization problem of whole-dataset fitting using LDA or decision trees. It filters out runs that would not have produced useful CO2 values to save needless computation. This would be an algorithmic preprocessing improvement to any computationally expensive system.

Image processing meta-algorithm development via genetic manipulation of existing algorithm graphs

NASA Astrophysics Data System (ADS)

Schalkoff, Robert J.; Shaaban, Khaled M.

1999-07-01

Automatic algorithm generation for image processing applications is not a new idea, however previous work is either restricted to morphological operates or impractical. In this paper, we show recent research result in the development and use of meta-algorithms, i.e. algorithms which lead to new algorithms. Although the concept is generally applicable, the application domain in this work is restricted to image processing. The meta-algorithm concept described in this paper is based upon out work in dynamic algorithm. The paper first present the concept of dynamic algorithms which, on the basis of training and archived algorithmic experience embedded in an algorithm graph (AG), dynamically adjust the sequence of operations applied to the input image data. Each node in the tree-based representation of a dynamic algorithm with out degree greater than 2 is a decision node. At these nodes, the algorithm examines the input data and determines which path will most likely achieve the desired results. This is currently done using nearest-neighbor classification. The details of this implementation are shown. The constrained perturbation of existing algorithm graphs, coupled with a suitable search strategy, is one mechanism to achieve meta-algorithm an doffers rich potential for the discovery of new algorithms. In our work, a meta-algorithm autonomously generates new dynamic algorithm graphs via genetic recombination of existing algorithm graphs. The AG representation is well suited to this genetic-like perturbation, using a commonly- employed technique in artificial neural network synthesis, namely the blueprint representation of graphs. A number of exam. One of the principal limitations of our current approach is the need for significant human input in the learning phase. Efforts to overcome this limitation are discussed. Future research directions are indicated.

An evaluation of consensus techniques for diagnostic interpretation

NASA Astrophysics Data System (ADS)

Sauter, Jake N.; LaBarre, Victoria M.; Furst, Jacob D.; Raicu, Daniela S.

2018-02-01

Learning diagnostic labels from image content has been the standard in computer-aided diagnosis. Most computer-aided diagnosis systems use low-level image features extracted directly from image content to train and test machine learning classifiers for diagnostic label prediction. When the ground truth for the diagnostic labels is not available, reference truth is generated from the experts diagnostic interpretations of the image/region of interest. More specifically, when the label is uncertain, e.g. when multiple experts label an image and their interpretations are different, techniques to handle the label variability are necessary. In this paper, we compare three consensus techniques that are typically used to encode the variability in the experts labeling of the medical data: mean, median and mode, and their effects on simple classifiers that can handle deterministic labels (decision trees) and probabilistic vectors of labels (belief decision trees). Given that the NIH/NCI Lung Image Database Consortium (LIDC) data provides interpretations for lung nodules by up to four radiologists, we leverage the LIDC data to evaluate and compare these consensus approaches when creating computer-aided diagnosis systems for lung nodules. First, low-level image features of nodules are extracted and paired with their radiologists semantic ratings (1= most likely benign, , 5 = most likely malignant); second, machine learning multi-class classifiers that handle deterministic labels (decision trees) and probabilistic vectors of labels (belief decision trees) are built to predict the lung nodules semantic ratings. We show that the mean-based consensus generates the most robust classi- fier overall when compared to the median- and mode-based consensus. Lastly, the results of this study show that, when building CAD systems with uncertain diagnostic interpretation, it is important to evaluate different strategies for encoding and predicting the diagnostic label.

Application and Exploration of Big Data Mining in Clinical Medicine.

PubMed

Zhang, Yue; Guo, Shu-Li; Han, Li-Na; Li, Tie-Ling

2016-03-20

To review theories and technologies of big data mining and their application in clinical medicine. Literatures published in English or Chinese regarding theories and technologies of big data mining and the concrete applications of data mining technology in clinical medicine were obtained from PubMed and Chinese Hospital Knowledge Database from 1975 to 2015. Original articles regarding big data mining theory/technology and big data mining's application in the medical field were selected. This review characterized the basic theories and technologies of big data mining including fuzzy theory, rough set theory, cloud theory, Dempster-Shafer theory, artificial neural network, genetic algorithm, inductive learning theory, Bayesian network, decision tree, pattern recognition, high-performance computing, and statistical analysis. The application of big data mining in clinical medicine was analyzed in the fields of disease risk assessment, clinical decision support, prediction of disease development, guidance of rational use of drugs, medical management, and evidence-based medicine. Big data mining has the potential to play an important role in clinical medicine.

DeepSAT: A Deep Learning Approach to Tree-Cover Delineation in 1-m NAIP Imagery for the Continental United States

NASA Technical Reports Server (NTRS)

Ganguly, Sangram; Basu, Saikat; Nemani, Ramakrishna R.; Mukhopadhyay, Supratik; Michaelis, Andrew; Votava, Petr

2016-01-01

High resolution tree cover classification maps are needed to increase the accuracy of current land ecosystem and climate model outputs. Limited studies are in place that demonstrates the state-of-the-art in deriving very high resolution (VHR) tree cover products. In addition, most methods heavily rely on commercial softwares that are difficult to scale given the region of study (e.g. continents to globe). Complexities in present approaches relate to (a) scalability of the algorithm, (b) large image data processing (compute and memory intensive), (c) computational cost, (d) massively parallel architecture, and (e) machine learning automation. In addition, VHR satellite datasets are of the order of terabytes and features extracted from these datasets are of the order of petabytes. In our present study, we have acquired the National Agriculture Imagery Program (NAIP) dataset for the Continental United States at a spatial resolution of 1-m. This data comes as image tiles (a total of quarter million image scenes with 60 million pixels) and has a total size of 65 terabytes for a single acquisition. Features extracted from the entire dataset would amount to 8-10 petabytes. In our proposed approach, we have implemented a novel semi-automated machine learning algorithm rooted on the principles of "deep learning" to delineate the percentage of tree cover. Using the NASA Earth Exchange (NEX) initiative, we have developed an end-to-end architecture by integrating a segmentation module based on Statistical Region Merging, a classification algorithm using Deep Belief Network and a structured prediction algorithm using Conditional Random Fields to integrate the results from the segmentation and classification modules to create per-pixel class labels. The training process is scaled up using the power of GPUs and the prediction is scaled to quarter million NAIP tiles spanning the whole of Continental United States using the NEX HPC supercomputing cluster. An initial pilot over the state of California spanning a total of 11,095 NAIP tiles covering a total geographical area of 163,696 sq. miles has produced true positive rates of around 88 percent for fragmented forests and 74 percent for urban tree cover areas, with false positive rates lower than 2 percent for both landscapes.

DeepSAT: A Deep Learning Approach to Tree-cover Delineation in 1-m NAIP Imagery for the Continental United States

NASA Astrophysics Data System (ADS)

Ganguly, S.; Basu, S.; Nemani, R. R.; Mukhopadhyay, S.; Michaelis, A.; Votava, P.

2016-12-01

High resolution tree cover classification maps are needed to increase the accuracy of current land ecosystem and climate model outputs. Limited studies are in place that demonstrates the state-of-the-art in deriving very high resolution (VHR) tree cover products. In addition, most methods heavily rely on commercial softwares that are difficult to scale given the region of study (e.g. continents to globe). Complexities in present approaches relate to (a) scalability of the algorithm, (b) large image data processing (compute and memory intensive), (c) computational cost, (d) massively parallel architecture, and (e) machine learning automation. In addition, VHR satellite datasets are of the order of terabytes and features extracted from these datasets are of the order of petabytes. In our present study, we have acquired the National Agriculture Imagery Program (NAIP) dataset for the Continental United States at a spatial resolution of 1-m. This data comes as image tiles (a total of quarter million image scenes with 60 million pixels) and has a total size of 65 terabytes for a single acquisition. Features extracted from the entire dataset would amount to 8-10 petabytes. In our proposed approach, we have implemented a novel semi-automated machine learning algorithm rooted on the principles of "deep learning" to delineate the percentage of tree cover. Using the NASA Earth Exchange (NEX) initiative, we have developed an end-to-end architecture by integrating a segmentation module based on Statistical Region Merging, a classification algorithm using Deep Belief Network and a structured prediction algorithm using Conditional Random Fields to integrate the results from the segmentation and classification modules to create per-pixel class labels. The training process is scaled up using the power of GPUs and the prediction is scaled to quarter million NAIP tiles spanning the whole of Continental United States using the NEX HPC supercomputing cluster. An initial pilot over the state of California spanning a total of 11,095 NAIP tiles covering a total geographical area of 163,696 sq. miles has produced true positive rates of around 88% for fragmented forests and 74% for urban tree cover areas, with false positive rates lower than 2% for both landscapes.

Application of Machine Learning to Predict Dietary Lapses During Weight Loss.

PubMed

Goldstein, Stephanie P; Zhang, Fengqing; Thomas, John G; Butryn, Meghan L; Herbert, James D; Forman, Evan M

2018-05-01

Individuals who adhere to dietary guidelines provided during weight loss interventions tend to be more successful with weight control. Any deviation from dietary guidelines can be referred to as a "lapse." There is a growing body of research showing that lapses are predictable using a variety of physiological, environmental, and psychological indicators. With recent technological advancements, it may be possible to assess these triggers and predict dietary lapses in real time. The current study sought to use machine learning techniques to predict lapses and evaluate the utility of combining both group- and individual-level data to enhance lapse prediction. The current study trained and tested a machine learning algorithm capable of predicting dietary lapses from a behavioral weight loss program among adults with overweight/obesity (n = 12). Participants were asked to follow a weight control diet for 6 weeks and complete ecological momentary assessment (EMA; repeated brief surveys delivered via smartphone) regarding dietary lapses and relevant triggers. WEKA decision trees were used to predict lapses with an accuracy of 0.72 for the group of participants. However, generalization of the group algorithm to each individual was poor, and as such, group- and individual-level data were combined to improve prediction. The findings suggest that 4 weeks of individual data collection is recommended to attain optimal model performance. The predictive algorithm could be utilized to provide in-the-moment interventions to prevent dietary lapses and therefore enhance weight losses. Furthermore, methods in the current study could be translated to other types of health behavior lapses.

Classification tree for the assessment of sedentary lifestyle among hypertensive.

PubMed

Castelo Guedes Martins, Larissa; Venícios de Oliveira Lopes, Marcos; Gomes Guedes, Nirla; Paixão de Menezes, Angélica; de Oliveira Farias, Odaleia; Alves Dos Santos, Naftale

2016-04-01

To develop a classification tree of clinical indicators for the correct prediction of the nursing diagnosis "Sedentary lifestyle" (SL) in people with high blood pressure (HTN). A cross-sectional study conducted in an outpatient care center specializing in high blood pressure and Mellitus diabetes located in northeastern Brazil. The sample consisted of 285 people between 19 and 59 years old diagnosed with high blood pressure and was applied an interview and physical examination, obtaining socio-demographic information, related factors and signs and symptoms that made the defining characteristics for the diagnosis under study. The tree was generated using the CHAID algorithm (Chi-square Automatic Interaction Detection). The construction of the decision tree allowed establishing the interactions between clinical indicators that facilitate a probabilistic analysis of multiple situations allowing quantify the probability of an individual presenting a sedentary lifestyle. The tree included the clinical indicator Choose daily routine without exercise as the first node. People with this indicator showed a probability of 0.88 of presenting the SL. The second node was composed of the indicator Does not perform physical activity during leisure, with 0.99 probability of presenting the SL with these two indicators. The predictive capacity of the tree was established at 69.5%. Decision trees help nurses who care HTN people in decision-making in assessing the characteristics that increase the probability of SL nursing diagnosis, optimizing the time for diagnostic inference.

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.

Robust High-dimensional Bioinformatics Data Streams Mining by ODR-ioVFDT

PubMed Central

Wang, Dantong; Fong, Simon; Wong, Raymond K.; Mohammed, Sabah; Fiaidhi, Jinan; Wong, Kelvin K. L.

2017-01-01

Outlier detection in bioinformatics data streaming mining has received significant attention by research communities in recent years. The problems of how to distinguish noise from an exception and deciding whether to discard it or to devise an extra decision path for accommodating it are causing dilemma. In this paper, we propose a novel algorithm called ODR with incrementally Optimized Very Fast Decision Tree (ODR-ioVFDT) for taking care of outliers in the progress of continuous data learning. By using an adaptive interquartile-range based identification method, a tolerance threshold is set. It is then used to judge if a data of exceptional value should be included for training or otherwise. This is different from the traditional outlier detection/removal approaches which are two separate steps in processing through the data. The proposed algorithm is tested using datasets of five bioinformatics scenarios and comparing the performance of our model and other ones without ODR. The results show that ODR-ioVFDT has better performance in classification accuracy, kappa statistics, and time consumption. The ODR-ioVFDT applied onto bioinformatics streaming data processing for detecting and quantifying the information of life phenomena, states, characters, variables and components of the organism can help to diagnose and treat disease more effectively. PMID:28230161

Interpretation of diagnostic data: 6. How to do it with more complex maths.

PubMed

1983-11-15

We have now shown you how to use decision analysis in making those rare, tough diagnostic decisions that are not soluble through other, easier routes. In summary, to "use more complex maths" the following steps will be useful: Create a decision tree or map of all the pertinent courses of action and their consequences. Assign probabilities to the branches of each chance node. Assign utilities to each of the potential outcomes shown on the decision tree. Combine the probabilities and utilities for each node on the decision tree. Pick the decision that leads to the highest expected utility. Test your decision for its sensitivity to clinically sensible changes in probabilities and utilities. That concludes this series of clinical epidemiology rounds. You've come a long way from "doing it with pictures" and are now able to extract most of the diagnostic information that can be provided from signs, symptoms and laboratory investigations. We would appreciate learning whether you have found this series useful and how we can do a better job of presenting these and other elements of "the science of the art of medicine".

Integrated approach using data mining-based decision tree and object-based image analysis for high-resolution urban mapping of WorldView-2 satellite sensor data

NASA Astrophysics Data System (ADS)

Hamedianfar, Alireza; Shafri, Helmi Zulhaidi Mohd

2016-04-01

This paper integrates decision tree-based data mining (DM) and object-based image analysis (OBIA) to provide a transferable model for the detailed characterization of urban land-cover classes using WorldView-2 (WV-2) satellite images. Many articles have been published on OBIA in recent years based on DM for different applications. However, less attention has been paid to the generation of a transferable model for characterizing detailed urban land cover features. Three subsets of WV-2 images were used in this paper to generate transferable OBIA rule-sets. Many features were explored by using a DM algorithm, which created the classification rules as a decision tree (DT) structure from the first study area. The developed DT algorithm was applied to object-based classifications in the first study area. After this process, we validated the capability and transferability of the classification rules into second and third subsets. Detailed ground truth samples were collected to assess the classification results. The first, second, and third study areas achieved 88%, 85%, and 85% overall accuracies, respectively. Results from the investigation indicate that DM was an efficient method to provide the optimal and transferable classification rules for OBIA, which accelerates the rule-sets creation stage in the OBIA classification domain.

Transportation Modes Classification Using Sensors on Smartphones.

PubMed

Fang, Shih-Hau; Liao, Hao-Hsiang; Fei, Yu-Xiang; Chen, Kai-Hsiang; Huang, Jen-Wei; Lu, Yu-Ding; Tsao, Yu

2016-08-19

This paper investigates the transportation and vehicular modes classification by using big data from smartphone sensors. The three types of sensors used in this paper include the accelerometer, magnetometer, and gyroscope. This study proposes improved features and uses three machine learning algorithms including decision trees, K-nearest neighbor, and support vector machine to classify the user's transportation and vehicular modes. In the experiments, we discussed and compared the performance from different perspectives including the accuracy for both modes, the executive time, and the model size. Results show that the proposed features enhance the accuracy, in which the support vector machine provides the best performance in classification accuracy whereas it consumes the largest prediction time. This paper also investigates the vehicle classification mode and compares the results with that of the transportation modes.

Transportation Modes Classification Using Sensors on Smartphones

PubMed Central

Fang, Shih-Hau; Liao, Hao-Hsiang; Fei, Yu-Xiang; Chen, Kai-Hsiang; Huang, Jen-Wei; Lu, Yu-Ding; Tsao, Yu

2016-01-01

This paper investigates the transportation and vehicular modes classification by using big data from smartphone sensors. The three types of sensors used in this paper include the accelerometer, magnetometer, and gyroscope. This study proposes improved features and uses three machine learning algorithms including decision trees, K-nearest neighbor, and support vector machine to classify the user’s transportation and vehicular modes. In the experiments, we discussed and compared the performance from different perspectives including the accuracy for both modes, the executive time, and the model size. Results show that the proposed features enhance the accuracy, in which the support vector machine provides the best performance in classification accuracy whereas it consumes the largest prediction time. This paper also investigates the vehicle classification mode and compares the results with that of the transportation modes. PMID:27548182

Prediction of Weather Impacted Airport Capacity using Ensemble Learning

NASA Technical Reports Server (NTRS)

Wang, Yao Xun

2011-01-01

Ensemble learning with the Bagging Decision Tree (BDT) model was used to assess the impact of weather on airport capacities at selected high-demand airports in the United States. The ensemble bagging decision tree models were developed and validated using the Federal Aviation Administration (FAA) Aviation System Performance Metrics (ASPM) data and weather forecast at these airports. The study examines the performance of BDT, along with traditional single Support Vector Machines (SVM), for airport runway configuration selection and airport arrival rates (AAR) prediction during weather impacts. Testing of these models was accomplished using observed weather, weather forecast, and airport operation information at the chosen airports. The experimental results show that ensemble methods are more accurate than a single SVM classifier. The airport capacity ensemble method presented here can be used as a decision support model that supports air traffic flow management to meet the weather impacted airport capacity in order to reduce costs and increase safety.

GIGA: a simple, efficient algorithm for gene tree inference in the genomic age

PubMed Central

2010-01-01

Background Phylogenetic relationships between genes are not only of theoretical interest: they enable us to learn about human genes through the experimental work on their relatives in numerous model organisms from bacteria to fruit flies and mice. Yet the most commonly used computational algorithms for reconstructing gene trees can be inaccurate for numerous reasons, both algorithmic and biological. Additional information beyond gene sequence data has been shown to improve the accuracy of reconstructions, though at great computational cost. Results We describe a simple, fast algorithm for inferring gene phylogenies, which makes use of information that was not available prior to the genomic age: namely, a reliable species tree spanning much of the tree of life, and knowledge of the complete complement of genes in a species' genome. The algorithm, called GIGA, constructs trees agglomeratively from a distance matrix representation of sequences, using simple rules to incorporate this genomic age information. GIGA makes use of a novel conceptualization of gene trees as being composed of orthologous subtrees (containing only speciation events), which are joined by other evolutionary events such as gene duplication or horizontal gene transfer. An important innovation in GIGA is that, at every step in the agglomeration process, the tree is interpreted/reinterpreted in terms of the evolutionary events that created it. Remarkably, GIGA performs well even when using a very simple distance metric (pairwise sequence differences) and no distance averaging over clades during the tree construction process. Conclusions GIGA is efficient, allowing phylogenetic reconstruction of very large gene families and determination of orthologs on a large scale. It is exceptionally robust to adding more gene sequences, opening up the possibility of creating stable identifiers for referring to not only extant genes, but also their common ancestors. We compared trees produced by GIGA to those in the TreeFam database, and they were very similar in general, with most differences likely due to poor alignment quality. However, some remaining differences are algorithmic, and can be explained by the fact that GIGA tends to put a larger emphasis on minimizing gene duplication and deletion events. PMID:20534164

GIGA: a simple, efficient algorithm for gene tree inference in the genomic age.

PubMed

Thomas, Paul D

2010-06-09

Phylogenetic relationships between genes are not only of theoretical interest: they enable us to learn about human genes through the experimental work on their relatives in numerous model organisms from bacteria to fruit flies and mice. Yet the most commonly used computational algorithms for reconstructing gene trees can be inaccurate for numerous reasons, both algorithmic and biological. Additional information beyond gene sequence data has been shown to improve the accuracy of reconstructions, though at great computational cost. We describe a simple, fast algorithm for inferring gene phylogenies, which makes use of information that was not available prior to the genomic age: namely, a reliable species tree spanning much of the tree of life, and knowledge of the complete complement of genes in a species' genome. The algorithm, called GIGA, constructs trees agglomeratively from a distance matrix representation of sequences, using simple rules to incorporate this genomic age information. GIGA makes use of a novel conceptualization of gene trees as being composed of orthologous subtrees (containing only speciation events), which are joined by other evolutionary events such as gene duplication or horizontal gene transfer. An important innovation in GIGA is that, at every step in the agglomeration process, the tree is interpreted/reinterpreted in terms of the evolutionary events that created it. Remarkably, GIGA performs well even when using a very simple distance metric (pairwise sequence differences) and no distance averaging over clades during the tree construction process. GIGA is efficient, allowing phylogenetic reconstruction of very large gene families and determination of orthologs on a large scale. It is exceptionally robust to adding more gene sequences, opening up the possibility of creating stable identifiers for referring to not only extant genes, but also their common ancestors. We compared trees produced by GIGA to those in the TreeFam database, and they were very similar in general, with most differences likely due to poor alignment quality. However, some remaining differences are algorithmic, and can be explained by the fact that GIGA tends to put a larger emphasis on minimizing gene duplication and deletion events.

A Semi-Automated Machine Learning Algorithm for Tree Cover Delineation from 1-m Naip Imagery Using a High Performance Computing Architecture

NASA Astrophysics Data System (ADS)

Basu, S.; Ganguly, S.; Nemani, R. R.; Mukhopadhyay, S.; Milesi, C.; Votava, P.; Michaelis, A.; Zhang, G.; Cook, B. D.; Saatchi, S. S.; Boyda, E.

2014-12-01

Accurate tree cover delineation is a useful instrument in the derivation of Above Ground Biomass (AGB) density estimates from Very High Resolution (VHR) satellite imagery data. Numerous algorithms have been designed to perform tree cover delineation in high to coarse resolution satellite imagery, but most of them do not scale to terabytes of data, typical in these VHR datasets. In this paper, we present an automated probabilistic framework for the segmentation and classification of 1-m VHR data as obtained from the National Agriculture Imagery Program (NAIP) for deriving tree cover estimates for the whole of Continental United States, using a High Performance Computing Architecture. The results from the classification and segmentation algorithms are then consolidated into a structured prediction framework using a discriminative undirected probabilistic graphical model based on Conditional Random Field (CRF), which helps in capturing the higher order contextual dependencies between neighboring pixels. Once the final probability maps are generated, the framework is updated and re-trained by incorporating expert knowledge through the relabeling of misclassified image patches. This leads to a significant improvement in the true positive rates and reduction in false positive rates. The tree cover maps were generated for the state of California, which covers a total of 11,095 NAIP tiles and spans a total geographical area of 163,696 sq. miles. Our framework produced correct detection rates of around 85% for fragmented forests and 70% for urban tree cover areas, with false positive rates lower than 3% for both regions. Comparative studies with the National Land Cover Data (NLCD) algorithm and the LiDAR high-resolution canopy height model shows the effectiveness of our algorithm in generating accurate high-resolution tree cover maps.

Spam comments prediction using stacking with ensemble learning

NASA Astrophysics Data System (ADS)

Mehmood, Arif; On, Byung-Won; Lee, Ingyu; Ashraf, Imran; Choi, Gyu Sang

2018-01-01

Illusive comments of product or services are misleading for people in decision making. The current methodologies to predict deceptive comments are concerned for feature designing with single training model. Indigenous features have ability to show some linguistic phenomena but are hard to reveal the latent semantic meaning of the comments. We propose a prediction model on general features of documents using stacking with ensemble learning. Term Frequency/Inverse Document Frequency (TF/IDF) features are inputs to stacking of Random Forest and Gradient Boosted Trees and the outputs of the base learners are encapsulated with decision tree to make final training of the model. The results exhibits that our approach gives the accuracy of 92.19% which outperform the state-of-the-art method.

Predicting diabetes mellitus using SMOTE and ensemble machine learning approach: The Henry Ford ExercIse Testing (FIT) project.

PubMed

Alghamdi, Manal; Al-Mallah, Mouaz; Keteyian, Steven; Brawner, Clinton; Ehrman, Jonathan; Sakr, Sherif

2017-01-01

Machine learning is becoming a popular and important approach in the field of medical research. In this study, we investigate the relative performance of various machine learning methods such as Decision Tree, Naïve Bayes, Logistic Regression, Logistic Model Tree and Random Forests for predicting incident diabetes using medical records of cardiorespiratory fitness. In addition, we apply different techniques to uncover potential predictors of diabetes. This FIT project study used data of 32,555 patients who are free of any known coronary artery disease or heart failure who underwent clinician-referred exercise treadmill stress testing at Henry Ford Health Systems between 1991 and 2009 and had a complete 5-year follow-up. At the completion of the fifth year, 5,099 of those patients have developed diabetes. The dataset contained 62 attributes classified into four categories: demographic characteristics, disease history, medication use history, and stress test vital signs. We developed an Ensembling-based predictive model using 13 attributes that were selected based on their clinical importance, Multiple Linear Regression, and Information Gain Ranking methods. The negative effect of the imbalance class of the constructed model was handled by Synthetic Minority Oversampling Technique (SMOTE). The overall performance of the predictive model classifier was improved by the Ensemble machine learning approach using the Vote method with three Decision Trees (Naïve Bayes Tree, Random Forest, and Logistic Model Tree) and achieved high accuracy of prediction (AUC = 0.92). The study shows the potential of ensembling and SMOTE approaches for predicting incident diabetes using cardiorespiratory fitness data.

A hybrid method for classifying cognitive states from fMRI data.

PubMed

Parida, S; Dehuri, S; Cho, S-B; Cacha, L A; Poznanski, R R

2015-09-01

Functional magnetic resonance imaging (fMRI) makes it possible to detect brain activities in order to elucidate cognitive-states. The complex nature of fMRI data requires under-standing of the analyses applied to produce possible avenues for developing models of cognitive state classification and improving brain activity prediction. While many models of classification task of fMRI data analysis have been developed, in this paper, we present a novel hybrid technique through combining the best attributes of genetic algorithms (GAs) and ensemble decision tree technique that consistently outperforms all other methods which are being used for cognitive-state classification. Specifically, this paper illustrates the combined effort of decision-trees ensemble and GAs for feature selection through an extensive simulation study and discusses the classification performance with respect to fMRI data. We have shown that our proposed method exhibits significant reduction of the number of features with clear edge classification accuracy over ensemble of decision-trees.

Machine learning models for lipophilicity and their domain of applicability.

PubMed

Schroeter, Timon; Schwaighofer, Anton; Mika, Sebastian; Laak, Antonius Ter; Suelzle, Detlev; Ganzer, Ursula; Heinrich, Nikolaus; Müller, Klaus-Robert

2007-01-01

Unfavorable lipophilicity and water solubility cause many drug failures; therefore these properties have to be taken into account early on in lead discovery. Commercial tools for predicting lipophilicity usually have been trained on small and neutral molecules, and are thus often unable to accurately predict in-house data. Using a modern Bayesian machine learning algorithm--a Gaussian process model--this study constructs a log D7 model based on 14,556 drug discovery compounds of Bayer Schering Pharma. Performance is compared with support vector machines, decision trees, ridge regression, and four commercial tools. In a blind test on 7013 new measurements from the last months (including compounds from new projects) 81% were predicted correctly within 1 log unit, compared to only 44% achieved by commercial software. Additional evaluations using public data are presented. We consider error bars for each method (model based error bars, ensemble based, and distance based approaches), and investigate how well they quantify the domain of applicability of each model.

ANNz2: Photometric Redshift and Probability Distribution Function Estimation using Machine Learning

NASA Astrophysics Data System (ADS)

Sadeh, I.; Abdalla, F. B.; Lahav, O.

2016-10-01

We present ANNz2, a new implementation of the public software for photometric redshift (photo-z) estimation of Collister & Lahav, which now includes generation of full probability distribution functions (PDFs). ANNz2 utilizes multiple machine learning methods, such as artificial neural networks and boosted decision/regression trees. The objective of the algorithm is to optimize the performance of the photo-z estimation, to properly derive the associated uncertainties, and to produce both single-value solutions and PDFs. In addition, estimators are made available, which mitigate possible problems of non-representative or incomplete spectroscopic training samples. ANNz2 has already been used as part of the first weak lensing analysis of the Dark Energy Survey, and is included in the experiment's first public data release. Here we illustrate the functionality of the code using data from the tenth data release of the Sloan Digital Sky Survey and the Baryon Oscillation Spectroscopic Survey. The code is available for download at http://github.com/IftachSadeh/ANNZ.

Quantum computation with classical light: Implementation of the Deutsch-Jozsa algorithm

NASA Astrophysics Data System (ADS)

Perez-Garcia, Benjamin; McLaren, Melanie; Goyal, Sandeep K.; Hernandez-Aranda, Raul I.; Forbes, Andrew; Konrad, Thomas

2016-05-01

We propose an optical implementation of the Deutsch-Jozsa Algorithm using classical light in a binary decision-tree scheme. Our approach uses a ring cavity and linear optical devices in order to efficiently query the oracle functional values. In addition, we take advantage of the intrinsic Fourier transforming properties of a lens to read out whether the function given by the oracle is balanced or constant.

A Theoretical Analysis of Why Hybrid Ensembles Work.

PubMed

Hsu, Kuo-Wei

2017-01-01

Inspired by the group decision making process, ensembles or combinations of classifiers have been found favorable in a wide variety of application domains. Some researchers propose to use the mixture of two different types of classification algorithms to create a hybrid ensemble. Why does such an ensemble work? The question remains. Following the concept of diversity, which is one of the fundamental elements of the success of ensembles, we conduct a theoretical analysis of why hybrid ensembles work, connecting using different algorithms to accuracy gain. We also conduct experiments on classification performance of hybrid ensembles of classifiers created by decision tree and naïve Bayes classification algorithms, each of which is a top data mining algorithm and often used to create non-hybrid ensembles. Therefore, through this paper, we provide a complement to the theoretical foundation of creating and using hybrid ensembles.

Prediction of healthy blood with data mining classification by using Decision Tree, Naive Baysian and SVM approaches

NASA Astrophysics Data System (ADS)

Khalilinezhad, Mahdieh; Minaei, Behrooz; Vernazza, Gianni; Dellepiane, Silvana

2015-03-01

Data mining (DM) is the process of discovery knowledge from large databases. Applications of data mining in Blood Transfusion Organizations could be useful for improving the performance of blood donation service. The aim of this research is the prediction of healthiness of blood donors in Blood Transfusion Organization (BTO). For this goal, three famous algorithms such as Decision Tree C4.5, Naïve Bayesian classifier, and Support Vector Machine have been chosen and applied to a real database made of 11006 donors. Seven fields such as sex, age, job, education, marital status, type of donor, results of blood tests (doctors' comments and lab results about healthy or unhealthy blood donors) have been selected as input to these algorithms. The results of the three algorithms have been compared and an error cost analysis has been performed. According to this research and the obtained results, the best algorithm with low error cost and high accuracy is SVM. This research helps BTO to realize a model from blood donors in each area in order to predict the healthy blood or unhealthy blood of donors. This research could be useful if used in parallel with laboratory tests to better separate unhealthy blood.

Decision tree analysis in subarachnoid hemorrhage: prediction of outcome parameters during the course of aneurysmal subarachnoid hemorrhage using decision tree analysis.

PubMed

Hostettler, Isabel Charlotte; Muroi, Carl; Richter, Johannes Konstantin; Schmid, Josef; Neidert, Marian Christoph; Seule, Martin; Boss, Oliver; Pangalu, Athina; Germans, Menno Robbert; Keller, Emanuela

2018-01-19

OBJECTIVE The aim of this study was to create prediction models for outcome parameters by decision tree analysis based on clinical and laboratory data in patients with aneurysmal subarachnoid hemorrhage (aSAH). METHODS The database consisted of clinical and laboratory parameters of 548 patients with aSAH who were admitted to the Neurocritical Care Unit, University Hospital Zurich. To examine the model performance, the cohort was randomly divided into a derivation cohort (60% [n = 329]; training data set) and a validation cohort (40% [n = 219]; test data set). The classification and regression tree prediction algorithm was applied to predict death, functional outcome, and ventriculoperitoneal (VP) shunt dependency. Chi-square automatic interaction detection was applied to predict delayed cerebral infarction on days 1, 3, and 7. RESULTS The overall mortality was 18.4%. The accuracy of the decision tree models was good for survival on day 1 and favorable functional outcome at all time points, with a difference between the training and test data sets of < 5%. Prediction accuracy for survival on day 1 was 75.2%. The most important differentiating factor was the interleukin-6 (IL-6) level on day 1. Favorable functional outcome, defined as Glasgow Outcome Scale scores of 4 and 5, was observed in 68.6% of patients. Favorable functional outcome at all time points had a prediction accuracy of 71.1% in the training data set, with procalcitonin on day 1 being the most important differentiating factor at all time points. A total of 148 patients (27%) developed VP shunt dependency. The most important differentiating factor was hyperglycemia on admission. CONCLUSIONS The multiple variable analysis capability of decision trees enables exploration of dependent variables in the context of multiple changing influences over the course of an illness. The decision tree currently generated increases awareness of the early systemic stress response, which is seemingly pertinent for prognostication.

Privacy-Preserving Classifier Learning

NASA Astrophysics Data System (ADS)

Brickell, Justin; Shmatikov, Vitaly

We present an efficient protocol for the privacy-preserving, distributed learning of decision-tree classifiers. Our protocol allows a user to construct a classifier on a database held by a remote server without learning any additional information about the records held in the database. The server does not learn anything about the constructed classifier, not even the user’s choice of feature and class attributes.

E-Learning Technologies: Employing Matlab Web Server to Facilitate the Education of Mathematical Programming

ERIC Educational Resources Information Center

Karagiannis, P.; Markelis, I.; Paparrizos, K.; Samaras, N.; Sifaleras, A.

2006-01-01

This paper presents new web-based educational software (webNetPro) for "Linear Network Programming." It includes many algorithms for "Network Optimization" problems, such as shortest path problems, minimum spanning tree problems, maximum flow problems and other search algorithms. Therefore, webNetPro can assist the teaching process of courses such…

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.

Predicting metabolic syndrome using decision tree and support vector machine methods.

PubMed

Karimi-Alavijeh, Farzaneh; Jalili, Saeed; Sadeghi, Masoumeh

2016-05-01

Metabolic syndrome which underlies the increased prevalence of cardiovascular disease and Type 2 diabetes is considered as a group of metabolic abnormalities including central obesity, hypertriglyceridemia, glucose intolerance, hypertension, and dyslipidemia. Recently, artificial intelligence based health-care systems are highly regarded because of its success in diagnosis, prediction, and choice of treatment. This study employs machine learning technics for predict the metabolic syndrome. This study aims to employ decision tree and support vector machine (SVM) to predict the 7-year incidence of metabolic syndrome. This research is a practical one in which data from 2107 participants of Isfahan Cohort Study has been utilized. The subjects without metabolic syndrome according to the ATPIII criteria were selected. The features that have been used in this data set include: gender, age, weight, body mass index, waist circumference, waist-to-hip ratio, hip circumference, physical activity, smoking, hypertension, antihypertensive medication use, systolic blood pressure (BP), diastolic BP, fasting blood sugar, 2-hour blood glucose, triglycerides (TGs), total cholesterol, low-density lipoprotein, high density lipoprotein-cholesterol, mean corpuscular volume, and mean corpuscular hemoglobin. Metabolic syndrome was diagnosed based on ATPIII criteria and two methods of decision tree and SVM were selected to predict the metabolic syndrome. The criteria of sensitivity, specificity and accuracy were used for validation. SVM and decision tree methods were examined according to the criteria of sensitivity, specificity and accuracy. Sensitivity, specificity and accuracy were 0.774 (0.758), 0.74 (0.72) and 0.757 (0.739) in SVM (decision tree) method. The results show that SVM method sensitivity, specificity and accuracy is more efficient than decision tree. The results of decision tree method show that the TG is the most important feature in predicting metabolic syndrome. According to this study, in cases where only the final result of the decision is regarded significant, SVM method can be used with acceptable accuracy in decision making medical issues. This method has not been implemented in the previous research.

Quantum ensembles of quantum classifiers.

PubMed

Schuld, Maria; Petruccione, Francesco

2018-02-09

Quantum machine learning witnesses an increasing amount of quantum algorithms for data-driven decision making, a problem with potential applications ranging from automated image recognition to medical diagnosis. Many of those algorithms are implementations of quantum classifiers, or models for the classification of data inputs with a quantum computer. Following the success of collective decision making with ensembles in classical machine learning, this paper introduces the concept of quantum ensembles of quantum classifiers. Creating the ensemble corresponds to a state preparation routine, after which the quantum classifiers are evaluated in parallel and their combined decision is accessed by a single-qubit measurement. This framework naturally allows for exponentially large ensembles in which - similar to Bayesian learning - the individual classifiers do not have to be trained. As an example, we analyse an exponentially large quantum ensemble in which each classifier is weighed according to its performance in classifying the training data, leading to new results for quantum as well as classical machine learning.

3D Cloud Field Prediction using A-Train Data and Machine Learning Techniques

NASA Astrophysics Data System (ADS)

Johnson, C. L.

2017-12-01

Validation of cloud process parameterizations used in global climate models (GCMs) would greatly benefit from observed 3D cloud fields at the size comparable to that of a GCM grid cell. For the highest resolution simulations, surface grid cells are on the order of 100 km by 100 km. CloudSat/CALIPSO data provides 1 km width of detailed vertical cloud fraction profile (CFP) and liquid and ice water content (LWC/IWC). This work utilizes four machine learning algorithms to create nonlinear regressions of CFP, LWC, and IWC data using radiances, surface type and location of measurement as predictors and applies the regression equations to off-track locations generating 3D cloud fields for 100 km by 100 km domains. The CERES-CloudSat-CALIPSO-MODIS (C3M) merged data set for February 2007 is used. Support Vector Machines, Artificial Neural Networks, Gaussian Processes and Decision Trees are trained on 1000 km of continuous C3M data. Accuracy is computed using existing vertical profiles that are excluded from the training data and occur within 100 km of the training data. Accuracy of the four algorithms is compared. Average accuracy for one day of predicted data is 86% for the most successful algorithm. The methodology for training the algorithms, determining valid prediction regions and applying the equations off-track is discussed. Predicted 3D cloud fields are provided as inputs to the Ed4 NASA LaRC Fu-Liou radiative transfer code and resulting TOA radiances compared to observed CERES/MODIS radiances. Differences in computed radiances using predicted profiles and observed radiances are compared.

A strategy for quantum algorithm design assisted by machine learning

NASA Astrophysics Data System (ADS)

Bang, Jeongho; Ryu, Junghee; Yoo, Seokwon; Pawłowski, Marcin; Lee, Jinhyoung

2014-07-01

We propose a method for quantum algorithm design assisted by machine learning. The method uses a quantum-classical hybrid simulator, where a ‘quantum student’ is being taught by a ‘classical teacher’. In other words, in our method, the learning system is supposed to evolve into a quantum algorithm for a given problem, assisted by a classical main-feedback system. Our method is applicable for designing quantum oracle-based algorithms. We chose, as a case study, an oracle decision problem, called a Deutsch-Jozsa problem. We showed by using Monte Carlo simulations that our simulator can faithfully learn a quantum algorithm for solving the problem for a given oracle. Remarkably, the learning time is proportional to the square root of the total number of parameters, rather than showing the exponential dependence found in the classical machine learning-based method.

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.

Identification of Some Zeolite Group Minerals by Application of Artificial Neural Network and Decision Tree Algorithm Based on SEM-EDS Data

NASA Astrophysics Data System (ADS)

Akkaş, Efe; Evren Çubukçu, H.; Akin, Lutfiye; Erkut, Volkan; Yurdakul, Yasin; Karayigit, Ali Ihsan

2016-04-01

Identification of zeolite group minerals is complicated due to their similar chemical formulas and habits. Although the morphologies of various zeolite crystals can be recognized under Scanning Electron Microscope (SEM), it is relatively more challenging and problematic process to identify zeolites using their mineral chemical data. SEMs integrated with energy dispersive X-ray spectrometers (EDS) provide fast and reliable chemical data of minerals. However, considering elemental similarities of characteristic chemical formulae of zeolite species (e.g. Clinoptilolite ((Na,K,Ca)2 -3Al3(Al,Si)2Si13O3612H2O) and Erionite ((Na2,K2,Ca)2Al4Si14O36ṡ15H2O)) EDS data alone does not seem to be sufficient for correct identification. Furthermore, the physical properties of the specimen (e.g. roughness, electrical conductivity) and the applied analytical conditions (e.g. accelerating voltage, beam current, spot size) of the SEM-EDS should be uniform in order to obtain reliable elemental results of minerals having high alkali (Na, K) and H2O (approx. %14-18) contents. This study which was funded by The Scientific and Technological Research Council of Turkey (TUBITAK Project No: 113Y439), aims to construct a database as large as possible for various zeolite minerals and to develop a general prediction model for the identification of zeolite minerals using SEM-EDS data. For this purpose, an artificial neural network and rule based decision tree algorithm were employed. Throughout the analyses, a total of 1850 chemical data were collected from four distinct zeolite species, (Clinoptilolite-Heulandite, Erionite, Analcime and Mordenite) observed in various rocks (e.g. coals, pyroclastics). In order to obtain a representative training data set for each minerals, a selection procedure for reference mineral analyses was applied. During the selection procedure, SEM based crystal morphology data, XRD spectra and re-calculated cationic distribution, obtained by EDS have been used for the characterization of the training set. Consequently, for each zeolite species 250 EDS data (as elemental intensities) used for training and 200 ±50 analyses were tested. Finally, two prediction models were developed. The constructed models with various cross-correlation values (r) yielded an average accuracy of >91% for the best predictions using C5.0 Decision Tree algorithm and back propagation artificial neural network. Despite having similar accuracies, the developed models exhibit different prediction behaviors for some zeolite minerals. The results demonstrate that artificial neural network as a nonlinear tool and decision tree algorithm as a rule based prediction model would be employed to provide considerably efficient and reliable identification/classification of some zeolite minerals regardless of their similar elemental compositions. Keywords: mineral identification; zeolites; energy dispersive spectrometry; artificial neural networks; decision tree.

An application of locally linear model tree algorithm with combination of feature selection in credit scoring

NASA Astrophysics Data System (ADS)

Siami, Mohammad; Gholamian, Mohammad Reza; Basiri, Javad

2014-10-01

Nowadays, credit scoring is one of the most important topics in the banking sector. Credit scoring models have been widely used to facilitate the process of credit assessing. In this paper, an application of the locally linear model tree algorithm (LOLIMOT) was experimented to evaluate the superiority of its performance to predict the customer's credit status. The algorithm is improved with an aim of adjustment by credit scoring domain by means of data fusion and feature selection techniques. Two real world credit data sets - Australian and German - from UCI machine learning database were selected to demonstrate the performance of our new classifier. The analytical results indicate that the improved LOLIMOT significantly increase the prediction accuracy.

Automatic Classification of Tremor Severity in Parkinson's Disease Using a Wearable Device.

PubMed

Jeon, Hyoseon; Lee, Woongwoo; Park, Hyeyoung; Lee, Hong Ji; Kim, Sang Kyong; Kim, Han Byul; Jeon, Beomseok; Park, Kwang Suk

2017-09-09

Although there is clinical demand for new technology that can accurately measure Parkinsonian tremors, automatic scoring of Parkinsonian tremors using machine-learning approaches has not yet been employed. This study aims to fill this gap by proposing machine-learning algorithms as a way to predict the Unified Parkinson's Disease Rating Scale (UPDRS), which are similar to how neurologists rate scores in actual clinical practice. In this study, the tremor signals of 85 patients with Parkinson's disease (PD) were measured using a wrist-watch-type wearable device consisting of an accelerometer and a gyroscope. The displacement and angle signals were calculated from the measured acceleration and angular velocity, and the acceleration, angular velocity, displacement, and angle signals were used for analysis. Nineteen features were extracted from each signal, and the pairwise correlation strategy was used to reduce the number of feature dimensions. With the selected features, a decision tree (DT), support vector machine (SVM), discriminant analysis (DA), random forest (RF), and k -nearest-neighbor ( k NN) algorithm were explored for automatic scoring of the Parkinsonian tremor severity. The performance of the employed classifiers was analyzed using accuracy, recall, and precision, and compared to other findings in similar studies. Finally, the limitations and plans for further study are discussed.

Machine vision based quality inspection of flat glass products

NASA Astrophysics Data System (ADS)

Zauner, G.; Schagerl, M.

2014-03-01

This application paper presents a machine vision solution for the quality inspection of flat glass products. A contact image sensor (CIS) is used to generate digital images of the glass surfaces. The presented machine vision based quality inspection at the end of the production line aims to classify five different glass defect types. The defect images are usually characterized by very little `image structure', i.e. homogeneous regions without distinct image texture. Additionally, these defect images usually consist of only a few pixels. At the same time the appearance of certain defect classes can be very diverse (e.g. water drops). We used simple state-of-the-art image features like histogram-based features (std. deviation, curtosis, skewness), geometric features (form factor/elongation, eccentricity, Hu-moments) and texture features (grey level run length matrix, co-occurrence matrix) to extract defect information. The main contribution of this work now lies in the systematic evaluation of various machine learning algorithms to identify appropriate classification approaches for this specific class of images. In this way, the following machine learning algorithms were compared: decision tree (J48), random forest, JRip rules, naive Bayes, Support Vector Machine (multi class), neural network (multilayer perceptron) and k-Nearest Neighbour. We used a representative image database of 2300 defect images and applied cross validation for evaluation purposes.

Automatic segmentation of airway tree based on local intensity filter and machine learning technique in 3D chest CT volume.

PubMed

Meng, Qier; Kitasaka, Takayuki; Nimura, Yukitaka; Oda, Masahiro; Ueno, Junji; Mori, Kensaku

2017-02-01

Airway segmentation plays an important role in analyzing chest computed tomography (CT) volumes for computerized lung cancer detection, emphysema diagnosis and pre- and intra-operative bronchoscope navigation. However, obtaining a complete 3D airway tree structure from a CT volume is quite a challenging task. Several researchers have proposed automated airway segmentation algorithms basically based on region growing and machine learning techniques. However, these methods fail to detect the peripheral bronchial branches, which results in a large amount of leakage. This paper presents a novel approach for more accurate extraction of the complex airway tree. This proposed segmentation method is composed of three steps. First, Hessian analysis is utilized to enhance the tube-like structure in CT volumes; then, an adaptive multiscale cavity enhancement filter is employed to detect the cavity-like structure with different radii. In the second step, support vector machine learning will be utilized to remove the false positive (FP) regions from the result obtained in the previous step. Finally, the graph-cut algorithm is used to refine the candidate voxels to form an integrated airway tree. A test dataset including 50 standard-dose chest CT volumes was used for evaluating our proposed method. The average extraction rate was about 79.1 % with the significantly decreased FP rate. A new method of airway segmentation based on local intensity structure and machine learning technique was developed. The method was shown to be feasible for airway segmentation in a computer-aided diagnosis system for a lung and bronchoscope guidance system.

Prediction of heart disease using apache spark analysing decision trees and gradient boosting algorithm

NASA Astrophysics Data System (ADS)

Chugh, Saryu; Arivu Selvan, K.; Nadesh, RK

2017-11-01

Numerous destructive things influence the working arrangement of human body as hypertension, smoking, obesity, inappropriate medication taking which causes many contrasting diseases as diabetes, thyroid, strokes and coronary diseases. The impermanence and horribleness of the environment situation is also the reason for the coronary disease. The structure of Apache start relies on the evolution which requires gathering of the data. To break down the significance of use programming focused on data structure the Apache stop ought to be utilized and it gives various central focuses as it is fast in light as it uses memory worked in preparing. Apache Spark continues running on dispersed environment and chops down the data in bunches giving a high profitability rate. Utilizing mining procedure as a part of the determination of coronary disease has been exhaustively examined indicating worthy levels of precision. Decision trees, Neural Network, Gradient Boosting Algorithm are the various apache spark proficiencies which help in collecting the information.

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.

Using an improved association rules mining optimization algorithm in web-based mobile-learning system

NASA Astrophysics Data System (ADS)

Huang, Yin; Chen, Jianhua; Xiong, Shaojun

2009-07-01

Mobile-Learning (M-learning) makes many learners get the advantages of both traditional learning and E-learning. Currently, Web-based Mobile-Learning Systems have created many new ways and defined new relationships between educators and learners. Association rule mining is one of the most important fields in data mining and knowledge discovery in databases. Rules explosion is a serious problem which causes great concerns, as conventional mining algorithms often produce too many rules for decision makers to digest. Since Web-based Mobile-Learning System collects vast amounts of student profile data, data mining and knowledge discovery techniques can be applied to find interesting relationships between attributes of learners, assessments, the solution strategies adopted by learners and so on. Therefore ,this paper focus on a new data-mining algorithm, combined with the advantages of genetic algorithm and simulated annealing algorithm , called ARGSA(Association rules based on an improved Genetic Simulated Annealing Algorithm), to mine the association rules. This paper first takes advantage of the Parallel Genetic Algorithm and Simulated Algorithm designed specifically for discovering association rules. Moreover, the analysis and experiment are also made to show the proposed method is superior to the Apriori algorithm in this Mobile-Learning system.

The application of remote sensing image sea ice monitoring method in Bohai Bay based on C4.5 decision tree algorithm

NASA Astrophysics Data System (ADS)

Ye, Wei; Song, Wei

2018-02-01

In The Paper, the remote sensing monitoring of sea ice problem was turned into a classification problem in data mining. Based on the statistic of the related band data of HJ1B remote sensing images, the main bands of HJ1B images related with the reflectance of seawater and sea ice were found. On the basis, the decision tree rules for sea ice monitoring were constructed by the related bands found above, and then the rules were applied to Liaodong Bay area seriously covered by sea ice for sea ice monitoring. The result proved that the method is effective.

Exploiting Non-sequence Data in Dynamic Model Learning

DTIC Science & Technology

2013-10-01

For our experiments here and in Section 3.5, we implement the proposed algorithms in MATLAB and use the maximum directed spanning tree solver...embarrassingly parallelizable, whereas PM’s maximum directed spanning tree procedure is harder to parallelize. In this experiment, our MATLAB ...some estimation problems, this approach is able to give unique and consistent estimates while the maximum- likelihood method gets entangled in

Machine Learning Methods for Attack Detection in the Smart Grid.

PubMed

Ozay, Mete; Esnaola, Inaki; Yarman Vural, Fatos Tunay; Kulkarni, Sanjeev R; Poor, H Vincent

2016-08-01

Attack detection problems in the smart grid are posed as statistical learning problems for different attack scenarios in which the measurements are observed in batch or online settings. In this approach, machine learning algorithms are used to classify measurements as being either secure or attacked. An attack detection framework is provided to exploit any available prior knowledge about the system and surmount constraints arising from the sparse structure of the problem in the proposed approach. Well-known batch and online learning algorithms (supervised and semisupervised) are employed with decision- and feature-level fusion to model the attack detection problem. The relationships between statistical and geometric properties of attack vectors employed in the attack scenarios and learning algorithms are analyzed to detect unobservable attacks using statistical learning methods. The proposed algorithms are examined on various IEEE test systems. Experimental analyses show that machine learning algorithms can detect attacks with performances higher than attack detection algorithms that employ state vector estimation methods in the proposed attack detection framework.

Applying of Decision Tree Analysis to Risk Factors Associated with Pressure Ulcers in Long-Term Care Facilities.

PubMed

Moon, Mikyung; Lee, Soo-Kyoung

2017-01-01

The purpose of this study was to use decision tree analysis to explore the factors associated with pressure ulcers (PUs) among elderly people admitted to Korean long-term care facilities. The data were extracted from the 2014 National Inpatient Sample (NIS)-data of Health Insurance Review and Assessment Service (HIRA). A MapReduce-based program was implemented to join and filter 5 tables of the NIS. The outcome predicted by the decision tree model was the prevalence of PUs as defined by the Korean Standard Classification of Disease-7 (KCD-7; code L89 * ). Using R 3.3.1, a decision tree was generated with the finalized 15,856 cases and 830 variables. The decision tree displayed 15 subgroups with 8 variables showing 0.804 accuracy, 0.820 sensitivity, and 0.787 specificity. The most significant primary predictor of PUs was length of stay less than 0.5 day. Other predictors were the presence of an infectious wound dressing, followed by having diagnoses numbering less than 3.5 and the presence of a simple dressing. Among diagnoses, "injuries to the hip and thigh" was the top predictor ranking 5th overall. Total hospital cost exceeding 2,200,000 Korean won (US $2,000) rounded out the top 7. These results support previous studies that showed length of stay, comorbidity, and total hospital cost were associated with PUs. Moreover, wound dressings were commonly used to treat PUs. They also show that machine learning, such as a decision tree, could effectively predict PUs using big data.

Lessons Learned from Applications of a Climate Change Decision Tree toWater System Projects in Kenya and Nepal

NASA Astrophysics Data System (ADS)

Ray, P. A.; Bonzanigo, L.; Taner, M. U.; Wi, S.; Yang, Y. C. E.; Brown, C.

2015-12-01

The Decision Tree Framework developed for the World Bank's Water Partnership Program provides resource-limited project planners and program managers with a cost-effective and effort-efficient, scientifically defensible, repeatable, and clear method for demonstrating the robustness of a project to climate change. At the conclusion of this process, the project planner is empowered to confidently communicate the method by which the vulnerabilities of the project have been assessed, and how the adjustments that were made (if any were necessary) improved the project's feasibility and profitability. The framework adopts a "bottom-up" approach to risk assessment that aims at a thorough understanding of a project's vulnerabilities to climate change in the context of other nonclimate uncertainties (e.g., economic, environmental, demographic, political). It helps identify projects that perform well across a wide range of potential future climate conditions, as opposed to seeking solutions that are optimal in expected conditions but fragile to conditions deviating from the expected. Lessons learned through application of the Decision Tree to case studies in Kenya and Nepal will be presented, and aspects of the framework requiring further refinement will be described.

PCM-SABRE: a platform for benchmarking and comparing outcome prediction methods in precision cancer medicine.

PubMed

Eyal-Altman, Noah; Last, Mark; Rubin, Eitan

2017-01-17

Numerous publications attempt to predict cancer survival outcome from gene expression data using machine-learning methods. A direct comparison of these works is challenging for the following reasons: (1) inconsistent measures used to evaluate the performance of different models, and (2) incomplete specification of critical stages in the process of knowledge discovery. There is a need for a platform that would allow researchers to replicate previous works and to test the impact of changes in the knowledge discovery process on the accuracy of the induced models. We developed the PCM-SABRE platform, which supports the entire knowledge discovery process for cancer outcome analysis. PCM-SABRE was developed using KNIME. By using PCM-SABRE to reproduce the results of previously published works on breast cancer survival, we define a baseline for evaluating future attempts to predict cancer outcome with machine learning. We used PCM-SABRE to replicate previous work that describe predictive models of breast cancer recurrence, and tested the performance of all possible combinations of feature selection methods and data mining algorithms that was used in either of the works. We reconstructed the work of Chou et al. observing similar trends - superior performance of Probabilistic Neural Network (PNN) and logistic regression (LR) algorithms and inconclusive impact of feature pre-selection with the decision tree algorithm on subsequent analysis. PCM-SABRE is a software tool that provides an intuitive environment for rapid development of predictive models in cancer precision medicine.

Chi-square-based scoring function for categorization of MEDLINE citations.

PubMed

Kastrin, A; Peterlin, B; Hristovski, D

2010-01-01

Text categorization has been used in biomedical informatics for identifying documents containing relevant topics of interest. We developed a simple method that uses a chi-square-based scoring function to determine the likelihood of MEDLINE citations containing genetic relevant topic. Our procedure requires construction of a genetic and a nongenetic domain document corpus. We used MeSH descriptors assigned to MEDLINE citations for this categorization task. We compared frequencies of MeSH descriptors between two corpora applying chi-square test. A MeSH descriptor was considered to be a positive indicator if its relative observed frequency in the genetic domain corpus was greater than its relative observed frequency in the nongenetic domain corpus. The output of the proposed method is a list of scores for all the citations, with the highest score given to those citations containing MeSH descriptors typical for the genetic domain. Validation was done on a set of 734 manually annotated MEDLINE citations. It achieved predictive accuracy of 0.87 with 0.69 recall and 0.64 precision. We evaluated the method by comparing it to three machine-learning algorithms (support vector machines, decision trees, naïve Bayes). Although the differences were not statistically significantly different, results showed that our chi-square scoring performs as good as compared machine-learning algorithms. We suggest that the chi-square scoring is an effective solution to help categorize MEDLINE citations. The algorithm is implemented in the BITOLA literature-based discovery support system as a preprocessor for gene symbol disambiguation process.

Type 2 Diabetes Mellitus Screening and Risk Factors Using Decision Tree: Results of Data Mining.

PubMed

Habibi, Shafi; Ahmadi, Maryam; Alizadeh, Somayeh

2015-03-18

The aim of this study was to examine a predictive model using features related to the diabetes type 2 risk factors. The data were obtained from a database in a diabetes control system in Tabriz, Iran. The data included all people referred for diabetes screening between 2009 and 2011. The features considered as "Inputs" were: age, sex, systolic and diastolic blood pressure, family history of diabetes, and body mass index (BMI). Moreover, we used diagnosis as "Class". We applied the "Decision Tree" technique and "J48" algorithm in the WEKA (3.6.10 version) software to develop the model. After data preprocessing and preparation, we used 22,398 records for data mining. The model precision to identify patients was 0.717. The age factor was placed in the root node of the tree as a result of higher information gain. The ROC curve indicates the model function in identification of patients and those individuals who are healthy. The curve indicates high capability of the model, especially in identification of the healthy persons. We developed a model using the decision tree for screening T2DM which did not require laboratory tests for T2DM diagnosis.

Multiclassifier system with hybrid learning applied to the control of bioprosthetic hand.

PubMed

Kurzynski, Marek; Krysmann, Maciej; Trajdos, Pawel; Wolczowski, Andrzej

2016-02-01

In this paper the problem of recognition of the intended hand movements for the control of bio-prosthetic hand is addressed. The proposed method is based on recognition of electromiographic (EMG) and mechanomiographic (MMG) biosignals using a multiclassifier system (MCS) working in a two-level structure with a dynamic ensemble selection (DES) scheme and original concepts of competence function. Additionally, feedback information coming from bioprosthesis sensors on the correct/incorrect classification is applied to the adjustment of the combining mechanism during MCS operation through adaptive tuning competences of base classifiers depending on their decisions. Three MCS systems operating in decision tree structure and with different tuning algorithms are developed. In the MCS1 system, competence is uniformly allocated to each class belonging to the group indicated by the feedback signal. In the MCS2 system, the modification of competence depends on the node of decision tree at which a correct/incorrect classification is made. In the MCS3 system, the randomized model of classifier and the concept of cross-competence are used in the tuning procedure. Experimental investigations on the real data and computer-simulated procedure of generating feedback signals are performed. In these investigations classification accuracy of the MCS systems developed is compared and furthermore, the MCS systems are evaluated with respect to the effectiveness of the procedure of tuning competence. The results obtained indicate that modification of competence of base classifiers during the working phase essentially improves performance of the MCS system and that this improvement depends on the MCS system and tuning method used. Copyright © 2015 Elsevier Ltd. All rights reserved.

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.

A Theoretical Analysis of Why Hybrid Ensembles Work

PubMed Central

2017-01-01

Inspired by the group decision making process, ensembles or combinations of classifiers have been found favorable in a wide variety of application domains. Some researchers propose to use the mixture of two different types of classification algorithms to create a hybrid ensemble. Why does such an ensemble work? The question remains. Following the concept of diversity, which is one of the fundamental elements of the success of ensembles, we conduct a theoretical analysis of why hybrid ensembles work, connecting using different algorithms to accuracy gain. We also conduct experiments on classification performance of hybrid ensembles of classifiers created by decision tree and naïve Bayes classification algorithms, each of which is a top data mining algorithm and often used to create non-hybrid ensembles. Therefore, through this paper, we provide a complement to the theoretical foundation of creating and using hybrid ensembles. PMID:28255296

Tools of the Future: How Decision Tree Analysis Will Impact Mission Planning

NASA Technical Reports Server (NTRS)

Otterstatter, Matthew R.

2005-01-01

The universe is infinitely complex; however, the human mind has a finite capacity. The multitude of possible variables, metrics, and procedures in mission planning are far too many to address exhaustively. This is unfortunate because, in general, considering more possibilities leads to more accurate and more powerful results. To compensate, we can get more insightful results by employing our greatest tool, the computer. The power of the computer will be utilized through a technology that considers every possibility, decision tree analysis. Although decision trees have been used in many other fields, this is innovative for space mission planning. Because this is a new strategy, no existing software is able to completely accommodate all of the requirements. This was determined through extensive research and testing of current technologies. It was necessary to create original software, for which a short-term model was finished this summer. The model was built into Microsoft Excel to take advantage of the familiar graphical interface for user input, computation, and viewing output. Macros were written to automate the process of tree construction, optimization, and presentation. The results are useful and promising. If this tool is successfully implemented in mission planning, our reliance on old-fashioned heuristics, an error-prone shortcut for handling complexity, will be reduced. The computer algorithms involved in decision trees will revolutionize mission planning. The planning will be faster and smarter, leading to optimized missions with the potential for more valuable data.

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.

Technology transfer by means of fault tree synthesis

NASA Astrophysics Data System (ADS)

Batzias, Dimitris F.

2012-12-01

Since Fault Tree Analysis (FTA) attempts to model and analyze failure processes of engineering, it forms a common technique for good industrial practice. On the contrary, fault tree synthesis (FTS) refers to the methodology of constructing complex trees either from dentritic modules built ad hoc or from fault tress already used and stored in a Knowledge Base. In both cases, technology transfer takes place in a quasi-inductive mode, from partial to holistic knowledge. In this work, an algorithmic procedure, including 9 activity steps and 3 decision nodes is developed for performing effectively this transfer when the fault under investigation occurs within one of the latter stages of an industrial procedure with several stages in series. The main parts of the algorithmic procedure are: (i) the construction of a local fault tree within the corresponding production stage, where the fault has been detected, (ii) the formation of an interface made of input faults that might occur upstream, (iii) the fuzzy (to count for uncertainty) multicriteria ranking of these faults according to their significance, and (iv) the synthesis of an extended fault tree based on the construction of part (i) and on the local fault tree of the first-ranked fault in part (iii). An implementation is presented, referring to 'uneven sealing of Al anodic film', thus proving the functionality of the developed methodology.

Ensemble stump classifiers and gene expression signatures in lung cancer.

PubMed

Frey, Lewis; Edgerton, Mary; Fisher, Douglas; Levy, Shawn

2007-01-01

Microarray data sets for cancer tumor tissue generally have very few samples, each sample having thousands of probes (i.e., continuous variables). The sparsity of samples makes it difficult for machine learning techniques to discover probes relevant to the classification of tumor tissue. By combining data from different platforms (i.e., data sources), data sparsity is reduced, but this typically requires normalizing data from the different platforms, which can be non-trivial. This paper proposes a variant on the idea of ensemble learners to circumvent the need for normalization. To facilitate comprehension we build ensembles of very simple classifiers known as decision stumps--decision trees of one test each. The Ensemble Stump Classifier (ESC) identifies an mRNA signature having three probes and high accuracy for distinguishing between adenocarcinoma and squamous cell carcinoma of the lung across four data sets. In terms of accuracy, ESC outperforms a decision tree classifier on all four data sets, outperforms ensemble decision trees on three data sets, and simple stump classifiers on two data sets.

Analysis of the Westland Data Set

NASA Technical Reports Server (NTRS)

Wen, Fang; Willett, Peter; Deb, Somnath

2001-01-01

The "Westland" set of empirical accelerometer helicopter data with seeded and labeled faults is analyzed with the aim of condition monitoring. The autoregressive (AR) coefficients from a simple linear model encapsulate a great deal of information in a relatively few measurements; and it has also been found that augmentation of these by harmonic and other parameters call improve classification significantly. Several techniques have been explored, among these restricted Coulomb energy (RCE) networks, learning vector quantization (LVQ), Gaussian mixture classifiers and decision trees. A problem with these approaches, and in common with many classification paradigms, is that augmentation of the feature dimension can degrade classification ability. Thus, we also introduce the Bayesian data reduction algorithm (BDRA), which imposes a Dirichlet prior oil training data and is thus able to quantify probability of error in all exact manner, such that features may be discarded or coarsened appropriately.

Knowledge discovery with classification rules in a cardiovascular dataset.

PubMed

Podgorelec, Vili; Kokol, Peter; Stiglic, Milojka Molan; Hericko, Marjan; Rozman, Ivan

2005-12-01

In this paper we study an evolutionary machine learning approach to data mining and knowledge discovery based on the induction of classification rules. A method for automatic rules induction called AREX using evolutionary induction of decision trees and automatic programming is introduced. The proposed algorithm is applied to a cardiovascular dataset consisting of different groups of attributes which should possibly reveal the presence of some specific cardiovascular problems in young patients. A case study is presented that shows the use of AREX for the classification of patients and for discovering possible new medical knowledge from the dataset. The defined knowledge discovery loop comprises a medical expert's assessment of induced rules to drive the evolution of rule sets towards more appropriate solutions. The final result is the discovery of a possible new medical knowledge in the field of pediatric cardiology.

A tree-like Bayesian structure learning algorithm for small-sample datasets from complex biological model systems.

PubMed

Yin, Weiwei; Garimalla, Swetha; Moreno, Alberto; Galinski, Mary R; Styczynski, Mark P

2015-08-28

There are increasing efforts to bring high-throughput systems biology techniques to bear on complex animal model systems, often with a goal of learning about underlying regulatory network structures (e.g., gene regulatory networks). However, complex animal model systems typically have significant limitations on cohort sizes, number of samples, and the ability to perform follow-up and validation experiments. These constraints are particularly problematic for many current network learning approaches, which require large numbers of samples and may predict many more regulatory relationships than actually exist. Here, we test the idea that by leveraging the accuracy and efficiency of classifiers, we can construct high-quality networks that capture important interactions between variables in datasets with few samples. We start from a previously-developed tree-like Bayesian classifier and generalize its network learning approach to allow for arbitrary depth and complexity of tree-like networks. Using four diverse sample networks, we demonstrate that this approach performs consistently better at low sample sizes than the Sparse Candidate Algorithm, a representative approach for comparison because it is known to generate Bayesian networks with high positive predictive value. We develop and demonstrate a resampling-based approach to enable the identification of a viable root for the learned tree-like network, important for cases where the root of a network is not known a priori. We also develop and demonstrate an integrated resampling-based approach to the reduction of variable space for the learning of the network. Finally, we demonstrate the utility of this approach via the analysis of a transcriptional dataset of a malaria challenge in a non-human primate model system, Macaca mulatta, suggesting the potential to capture indicators of the earliest stages of cellular differentiation during leukopoiesis. We demonstrate that by starting from effective and efficient approaches for creating classifiers, we can identify interesting tree-like network structures with significant ability to capture the relationships in the training data. This approach represents a promising strategy for inferring networks with high positive predictive value under the constraint of small numbers of samples, meeting a need that will only continue to grow as more high-throughput studies are applied to complex model systems.

Problem Solving and Learning in a Natural Task Domain

DTIC Science & Technology

1988-09-01

algorithm is demonstrated in two further examples. For clarity, all examples present a single path through the causal model, rather than the tree ...Any implications are added to the list. EDSEL1 keeps recent chains of reasoning. The tree form of any explorations is retained for future reasoning...9) (CAUSE (CRANK CRANKSHAFT) (OVEVIENT CAMSHAFT ) 9) (CAUSE (CRANK CRANKSHAFT) (TUR:N DRIVESHAFT) 9) STARTER (CAUSE (SWITCH-ACTION SOLENOID ON

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

Sentiment analysis of Arabic tweets using text mining techniques

NASA Astrophysics Data System (ADS)

Al-Horaibi, Lamia; Khan, Muhammad Badruddin

2016-07-01

Sentiment analysis has become a flourishing field of text mining and natural language processing. Sentiment analysis aims to determine whether the text is written to express positive, negative, or neutral emotions about a certain domain. Most sentiment analysis researchers focus on English texts, with very limited resources available for other complex languages, such as Arabic. In this study, the target was to develop an initial model that performs satisfactorily and measures Arabic Twitter sentiment by using machine learning approach, Naïve Bayes and Decision Tree for classification algorithms. The datasets used contains more than 2,000 Arabic tweets collected from Twitter. We performed several experiments to check the performance of the two algorithms classifiers using different combinations of text-processing functions. We found that available facilities for Arabic text processing need to be made from scratch or improved to develop accurate classifiers. The small functionalities developed by us in a Python language environment helped improve the results and proved that sentiment analysis in the Arabic domain needs lot of work on the lexicon side.

Condition Monitoring for Helicopter Data. Appendix A

NASA Technical Reports Server (NTRS)

Wen, Fang; Willett, Peter; Deb, Somnath

2000-01-01

In this paper the classical "Westland" set of empirical accelerometer helicopter data is analyzed with the aim of condition monitoring for diagnostic purposes. The goal is to determine features for failure events from these data, via a proprietary signal processing toolbox, and to weigh these according to a variety of classification algorithms. As regards signal processing, it appears that the autoregressive (AR) coefficients from a simple linear model encapsulate a great deal of information in a relatively few measurements; it has also been found that augmentation of these by harmonic and other parameters can improve classification significantly. As regards classification, several techniques have been explored, among these restricted Coulomb energy (RCE) networks, learning vector quantization (LVQ), Gaussian mixture classifiers and decision trees. A problem with these approaches, and in common with many classification paradigms, is that augmentation of the feature dimension can degrade classification ability. Thus, we also introduce the Bayesian data reduction algorithm (BDRA), which imposes a Dirichlet prior on training data and is thus able to quantify probability of error in an exact manner, such that features may be discarded or coarsened appropriately.

Visual management of large scale data mining projects.

PubMed

Shah, I; Hunter, L

2000-01-01

This paper describes a unified framework for visualizing the preparations for, and results of, hundreds of machine learning experiments. These experiments were designed to improve the accuracy of enzyme functional predictions from sequence, and in many cases were successful. Our system provides graphical user interfaces for defining and exploring training datasets and various representational alternatives, for inspecting the hypotheses induced by various types of learning algorithms, for visualizing the global results, and for inspecting in detail results for specific training sets (functions) and examples (proteins). The visualization tools serve as a navigational aid through a large amount of sequence data and induced knowledge. They provided significant help in understanding both the significance and the underlying biological explanations of our successes and failures. Using these visualizations it was possible to efficiently identify weaknesses of the modular sequence representations and induction algorithms which suggest better learning strategies. The context in which our data mining visualization toolkit was developed was the problem of accurately predicting enzyme function from protein sequence data. Previous work demonstrated that approximately 6% of enzyme protein sequences are likely to be assigned incorrect functions on the basis of sequence similarity alone. In order to test the hypothesis that more detailed sequence analysis using machine learning techniques and modular domain representations could address many of these failures, we designed a series of more than 250 experiments using information-theoretic decision tree induction and naive Bayesian learning on local sequence domain representations of problematic enzyme function classes. In more than half of these cases, our methods were able to perfectly discriminate among various possible functions of similar sequences. We developed and tested our visualization techniques on this application.

Virtual Network Embedding via Monte Carlo Tree Search.

PubMed

Haeri, Soroush; Trajkovic, Ljiljana

2018-02-01

Network virtualization helps overcome shortcomings of the current Internet architecture. The virtualized network architecture enables coexistence of multiple virtual networks (VNs) on an existing physical infrastructure. VN embedding (VNE) problem, which deals with the embedding of VN components onto a physical network, is known to be -hard. In this paper, we propose two VNE algorithms: MaVEn-M and MaVEn-S. MaVEn-M employs the multicommodity flow algorithm for virtual link mapping while MaVEn-S uses the shortest-path algorithm. They formalize the virtual node mapping problem by using the Markov decision process (MDP) framework and devise action policies (node mappings) for the proposed MDP using the Monte Carlo tree search algorithm. Service providers may adjust the execution time of the MaVEn algorithms based on the traffic load of VN requests. The objective of the algorithms is to maximize the profit of infrastructure providers. We develop a discrete event VNE simulator to implement and evaluate performance of MaVEn-M, MaVEn-S, and several recently proposed VNE algorithms. We introduce profitability as a new performance metric that captures both acceptance and revenue to cost ratios. Simulation results show that the proposed algorithms find more profitable solutions than the existing algorithms. Given additional computation time, they further improve embedding solutions.

Theoretical validation of potential habitability via analytical and boosted tree methods: An optimistic study on recently discovered exoplanets

NASA Astrophysics Data System (ADS)

Saha, S.; Basak, S.; Safonova, M.; Bora, K.; Agrawal, S.; Sarkar, P.; Murthy, J.

2018-04-01

Seven Earth-sized planets, known as the TRAPPIST-1 system, was discovered with great fanfare in the last week of February 2017. Three of these planets are in the habitable zone of their star, making them potentially habitable planets (PHPs) a mere 40 light years away. The discovery of the closest potentially habitable planet to us just a year before - Proxima b and a realization that Earth-type planets in circumstellar habitable zones are a common occurrence provides the impetus to the existing pursuit for life outside the Solar System. The search for life has two goals essentially: looking for planets with Earth-like conditions (Earth similarity) and looking for the possibility of life in some form (habitability). An index was recently developed, the Cobb-Douglas Habitability Score (CDHS), based on Cobb-Douglas habitability production function (CD-HPF), which computes the habitability score by using measured and estimated planetary parameters. As an initial set, radius, density, escape velocity and surface temperature of a planet were used. The proposed metric, with exponents accounting for metric elasticity, is endowed with analytical properties that ensure global optima and can be scaled to accommodate a finite number of input parameters. We show here that the model is elastic, and the conditions on elasticity to ensure global maxima can scale as the number of predictor parameters increase. K-NN (K-Nearest Neighbor) classification algorithm, embellished with probabilistic herding and thresholding restriction, utilizes CDHS scores and labels exoplanets into appropriate classes via feature-learning methods yielding granular clusters of habitability. The algorithm works on top of a decision-theoretical model using the power of convex optimization and machine learning. The goal is to characterize the recently discovered exoplanets into an "Earth League" and several other classes based on their CDHS values. A second approach, based on a novel feature-learning and tree-building method classifies the same planets without computing the CDHS of the planets and produces a similar outcome. For this, we use XGBoosted trees. The convergence of the outcome of the two different approaches indicates the strength of the proposed solution scheme and the likelihood of the potential habitability of the recently announced discoveries.

A parallelized binary search tree

USDA-ARS?s Scientific Manuscript database

PTTRNFNDR is an unsupervised statistical learning algorithm that detects patterns in DNA sequences, protein sequences, or any natural language texts that can be decomposed into letters of a finite alphabet. PTTRNFNDR performs complex mathematical computations and its processing time increases when i...

A novel method for predicting kidney stone type using ensemble learning.

PubMed

Kazemi, Yassaman; Mirroshandel, Seyed Abolghasem

2018-01-01

The high morbidity rate associated with kidney stone disease, which is a silent killer, is one of the main concerns in healthcare systems all over the world. Advanced data mining techniques such as classification can help in the early prediction of this disease and reduce its incidence and associated costs. The objective of the present study is to derive a model for the early detection of the type of kidney stone and the most influential parameters with the aim of providing a decision-support system. Information was collected from 936 patients with nephrolithiasis at the kidney center of the Razi Hospital in Rasht from 2012 through 2016. The prepared dataset included 42 features. Data pre-processing was the first step toward extracting the relevant features. The collected data was analyzed with Weka software, and various data mining models were used to prepare a predictive model. Various data mining algorithms such as the Bayesian model, different types of Decision Trees, Artificial Neural Networks, and Rule-based classifiers were used in these models. We also proposed four models based on ensemble learning to improve the accuracy of each learning algorithm. In addition, a novel technique for combining individual classifiers in ensemble learning was proposed. In this technique, for each individual classifier, a weight is assigned based on our proposed genetic algorithm based method. The generated knowledge was evaluated using a 10-fold cross-validation technique based on standard measures. However, the assessment of each feature for building a predictive model was another significant challenge. The predictive strength of each feature for creating a reproducible outcome was also investigated. Regarding the applied models, parameters such as sex, acid uric condition, calcium level, hypertension, diabetes, nausea and vomiting, flank pain, and urinary tract infection (UTI) were the most vital parameters for predicting the chance of nephrolithiasis. The final ensemble-based model (with an accuracy of 97.1%) was a robust one and could be safely applied to future studies to predict the chances of developing nephrolithiasis. This model provides a novel way to study stone disease by deciphering the complex interaction among different biological variables, thus helping in an early identification and reduction in diagnosis time. Copyright © 2017 Elsevier B.V. All rights reserved.

Personalized Risk Prediction in Clinical Oncology Research: Applications and Practical Issues Using Survival Trees and Random Forests.

PubMed

Hu, Chen; Steingrimsson, Jon Arni

2018-01-01

A crucial component of making individualized treatment decisions is to accurately predict each patient's disease risk. In clinical oncology, disease risks are often measured through time-to-event data, such as overall survival and progression/recurrence-free survival, and are often subject to censoring. Risk prediction models based on recursive partitioning methods are becoming increasingly popular largely due to their ability to handle nonlinear relationships, higher-order interactions, and/or high-dimensional covariates. The most popular recursive partitioning methods are versions of the Classification and Regression Tree (CART) algorithm, which builds a simple interpretable tree structured model. With the aim of increasing prediction accuracy, the random forest algorithm averages multiple CART trees, creating a flexible risk prediction model. Risk prediction models used in clinical oncology commonly use both traditional demographic and tumor pathological factors as well as high-dimensional genetic markers and treatment parameters from multimodality treatments. In this article, we describe the most commonly used extensions of the CART and random forest algorithms to right-censored outcomes. We focus on how they differ from the methods for noncensored outcomes, and how the different splitting rules and methods for cost-complexity pruning impact these algorithms. We demonstrate these algorithms by analyzing a randomized Phase III clinical trial of breast cancer. We also conduct Monte Carlo simulations to compare the prediction accuracy of survival forests with more commonly used regression models under various scenarios. These simulation studies aim to evaluate how sensitive the prediction accuracy is to the underlying model specifications, the choice of tuning parameters, and the degrees of missing covariates.

ETHNOPRED: a novel machine learning method for accurate continental and sub-continental ancestry identification and population stratification correction.

PubMed

Hajiloo, Mohsen; Sapkota, Yadav; Mackey, John R; Robson, Paula; Greiner, Russell; Damaraju, Sambasivarao

2013-02-22

Population stratification is a systematic difference in allele frequencies between subpopulations. This can lead to spurious association findings in the case-control genome wide association studies (GWASs) used to identify single nucleotide polymorphisms (SNPs) associated with disease-linked phenotypes. Methods such as self-declared ancestry, ancestry informative markers, genomic control, structured association, and principal component analysis are used to assess and correct population stratification but each has limitations. We provide an alternative technique to address population stratification. We propose a novel machine learning method, ETHNOPRED, which uses the genotype and ethnicity data from the HapMap project to learn ensembles of disjoint decision trees, capable of accurately predicting an individual's continental and sub-continental ancestry. To predict an individual's continental ancestry, ETHNOPRED produced an ensemble of 3 decision trees involving a total of 10 SNPs, with 10-fold cross validation accuracy of 100% using HapMap II dataset. We extended this model to involve 29 disjoint decision trees over 149 SNPs, and showed that this ensemble has an accuracy of ≥ 99.9%, even if some of those 149 SNP values were missing. On an independent dataset, predominantly of Caucasian origin, our continental classifier showed 96.8% accuracy and improved genomic control's λ from 1.22 to 1.11. We next used the HapMap III dataset to learn classifiers to distinguish European subpopulations (North-Western vs. Southern), East Asian subpopulations (Chinese vs. Japanese), African subpopulations (Eastern vs. Western), North American subpopulations (European vs. Chinese vs. African vs. Mexican vs. Indian), and Kenyan subpopulations (Luhya vs. Maasai). In these cases, ETHNOPRED produced ensembles of 3, 39, 21, 11, and 25 disjoint decision trees, respectively involving 31, 502, 526, 242 and 271 SNPs, with 10-fold cross validation accuracy of 86.5% ± 2.4%, 95.6% ± 3.9%, 95.6% ± 2.1%, 98.3% ± 2.0%, and 95.9% ± 1.5%. However, ETHNOPRED was unable to produce a classifier that can accurately distinguish Chinese in Beijing vs. Chinese in Denver. ETHNOPRED is a novel technique for producing classifiers that can identify an individual's continental and sub-continental heritage, based on a small number of SNPs. We show that its learned classifiers are simple, cost-efficient, accurate, transparent, flexible, fast, applicable to large scale GWASs, and robust to missing values.

Application and Exploration of Big Data Mining in Clinical Medicine

PubMed Central

Zhang, Yue; Guo, Shu-Li; Han, Li-Na; Li, Tie-Ling

2016-01-01

Objective: To review theories and technologies of big data mining and their application in clinical medicine. Data Sources: Literatures published in English or Chinese regarding theories and technologies of big data mining and the concrete applications of data mining technology in clinical medicine were obtained from PubMed and Chinese Hospital Knowledge Database from 1975 to 2015. Study Selection: Original articles regarding big data mining theory/technology and big data mining's application in the medical field were selected. Results: This review characterized the basic theories and technologies of big data mining including fuzzy theory, rough set theory, cloud theory, Dempster–Shafer theory, artificial neural network, genetic algorithm, inductive learning theory, Bayesian network, decision tree, pattern recognition, high-performance computing, and statistical analysis. The application of big data mining in clinical medicine was analyzed in the fields of disease risk assessment, clinical decision support, prediction of disease development, guidance of rational use of drugs, medical management, and evidence-based medicine. Conclusion: Big data mining has the potential to play an important role in clinical medicine. PMID:26960378

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.

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

Acquisition of Inductive Biconditional Reasoning Skills: Training of Simultaneous and Sequential Processing.

ERIC Educational Resources Information Center

Lee, Seong-Soo

1982-01-01

Tenth-grade students (n=144) received training on one of three processing methods: coding-mapping (simultaneous), coding only, or decision tree (sequential). The induced simultaneous processing strategy worked optimally under rule learning, while the sequential strategy was difficult to induce and/or not optimal for rule-learning operations.…

The risk of disabling, surgery and reoperation in Crohn's disease - A decision tree-based approach to prognosis.

PubMed

Dias, Cláudia Camila; Pereira Rodrigues, Pedro; Fernandes, Samuel; Portela, Francisco; Ministro, Paula; Martins, Diana; Sousa, Paula; Lago, Paula; Rosa, Isadora; Correia, Luis; Moura Santos, Paula; Magro, Fernando

2017-01-01

Crohn's disease (CD) is a chronic inflammatory bowel disease known to carry a high risk of disabling and many times requiring surgical interventions. This article describes a decision-tree based approach that defines the CD patients' risk or undergoing disabling events, surgical interventions and reoperations, based on clinical and demographic variables. This multicentric study involved 1547 CD patients retrospectively enrolled and divided into two cohorts: a derivation one (80%) and a validation one (20%). Decision trees were built upon applying the CHAIRT algorithm for the selection of variables. Three-level decision trees were built for the risk of disabling and reoperation, whereas the risk of surgery was described in a two-level one. A receiver operating characteristic (ROC) analysis was performed, and the area under the curves (AUC) Was higher than 70% for all outcomes. The defined risk cut-off values show usefulness for the assessed outcomes: risk levels above 75% for disabling had an odds test positivity of 4.06 [3.50-4.71], whereas risk levels below 34% and 19% excluded surgery and reoperation with an odds test negativity of 0.15 [0.09-0.25] and 0.50 [0.24-1.01], respectively. Overall, patients with B2 or B3 phenotype had a higher proportion of disabling disease and surgery, while patients with later introduction of pharmacological therapeutic (1 months after initial surgery) had a higher proportion of reoperation. The decision-tree based approach used in this study, with demographic and clinical variables, has shown to be a valid and useful approach to depict such risks of disabling, surgery and reoperation.

Outsourcing medical data analyses: can technology overcome legal, privacy, and confidentiality issues?

PubMed

Brumen, Bostjan; Heričko, Marjan; Sevčnikar, Andrej; Završnik, Jernej; Hölbl, Marko

2013-12-16

Medical data are gold mines for deriving the knowledge that could change the course of a single patient's life or even the health of the entire population. A data analyst needs to have full access to relevant data, but full access may be denied by privacy and confidentiality of medical data legal regulations, especially when the data analyst is not affiliated with the data owner. Our first objective was to analyze the privacy and confidentiality issues and the associated regulations pertaining to medical data, and to identify technologies to properly address these issues. Our second objective was to develop a procedure to protect medical data in such a way that the outsourced analyst would be capable of doing analyses on protected data and the results would be comparable, if not the same, as if they had been done on the original data. Specifically, our hypothesis was there would not be a difference between the outsourced decision trees built on encrypted data and the ones built on original data. Using formal definitions, we developed an algorithm to protect medical data for outsourced analyses. The algorithm was applied to publicly available datasets (N=30) from the medical and life sciences fields. The analyses were performed on the original and the protected datasets and the results of the analyses were compared. Bootstrapped paired t tests for 2 dependent samples were used to test whether the mean differences in size, number of leaves, and the accuracy of the original and the encrypted decision trees were significantly different. The decision trees built on encrypted data were virtually the same as those built on original data. Out of 30 datasets, 100% of the trees had identical accuracy. The size of a tree and the number of leaves was different only once (1/30, 3%, P=.19). The proposed algorithm encrypts a file with plain text medical data into an encrypted file with the data protected in such a way that external data analyses are still possible. The results show that the results of analyses on original and on protected data are identical or comparably similar. The approach addresses the privacy and confidentiality issues that arise with medical data and is adherent to strict legal rules in the United States and Europe regarding the processing of the medical data.

Outsourcing Medical Data Analyses: Can Technology Overcome Legal, Privacy, and Confidentiality Issues?

PubMed Central

2013-01-01

Background Medical data are gold mines for deriving the knowledge that could change the course of a single patient’s life or even the health of the entire population. A data analyst needs to have full access to relevant data, but full access may be denied by privacy and confidentiality of medical data legal regulations, especially when the data analyst is not affiliated with the data owner. Objective Our first objective was to analyze the privacy and confidentiality issues and the associated regulations pertaining to medical data, and to identify technologies to properly address these issues. Our second objective was to develop a procedure to protect medical data in such a way that the outsourced analyst would be capable of doing analyses on protected data and the results would be comparable, if not the same, as if they had been done on the original data. Specifically, our hypothesis was there would not be a difference between the outsourced decision trees built on encrypted data and the ones built on original data. Methods Using formal definitions, we developed an algorithm to protect medical data for outsourced analyses. The algorithm was applied to publicly available datasets (N=30) from the medical and life sciences fields. The analyses were performed on the original and the protected datasets and the results of the analyses were compared. Bootstrapped paired t tests for 2 dependent samples were used to test whether the mean differences in size, number of leaves, and the accuracy of the original and the encrypted decision trees were significantly different. Results The decision trees built on encrypted data were virtually the same as those built on original data. Out of 30 datasets, 100% of the trees had identical accuracy. The size of a tree and the number of leaves was different only once (1/30, 3%, P=.19). Conclusions The proposed algorithm encrypts a file with plain text medical data into an encrypted file with the data protected in such a way that external data analyses are still possible. The results show that the results of analyses on original and on protected data are identical or comparably similar. The approach addresses the privacy and confidentiality issues that arise with medical data and is adherent to strict legal rules in the United States and Europe regarding the processing of the medical data. PMID:24342053

Icing detection from geostationary satellite data using machine learning approaches

NASA Astrophysics Data System (ADS)

Lee, J.; Ha, S.; Sim, S.; Im, J.

2015-12-01

Icing can cause a significant structural damage to aircraft during flight, resulting in various aviation accidents. Icing studies have been typically performed using two approaches: one is a numerical model-based approach and the other is a remote sensing-based approach. The model based approach diagnoses aircraft icing using numerical atmospheric parameters such as temperature, relative humidity, and vertical thermodynamic structure. This approach tends to over-estimate icing according to the literature. The remote sensing-based approach typically uses meteorological satellite/ground sensor data such as Geostationary Operational Environmental Satellite (GOES) and Dual-Polarization radar data. This approach detects icing areas by applying thresholds to parameters such as liquid water path and cloud optical thickness derived from remote sensing data. In this study, we propose an aircraft icing detection approach which optimizes thresholds for L1B bands and/or Cloud Optical Thickness (COT) from Communication, Ocean and Meteorological Satellite-Meteorological Imager (COMS MI) and newly launched Himawari-8 Advanced Himawari Imager (AHI) over East Asia. The proposed approach uses machine learning algorithms including decision trees (DT) and random forest (RF) for optimizing thresholds of L1B data and/or COT. Pilot Reports (PIREPs) from South Korea and Japan were used as icing reference data. Results show that RF produced a lower false alarm rate (1.5%) and a higher overall accuracy (98.8%) than DT (8.5% and 75.3%), respectively. The RF-based approach was also compared with the existing COMS MI and GOES-R icing mask algorithms. The agreements of the proposed approach with the existing two algorithms were 89.2% and 45.5%, respectively. The lower agreement with the GOES-R algorithm was possibly due to the high uncertainty of the cloud phase product from COMS MI.

An efficient ensemble learning method for gene microarray classification.

PubMed

Osareh, Alireza; Shadgar, Bita

2013-01-01

The gene microarray analysis and classification have demonstrated an effective way for the effective diagnosis of diseases and cancers. However, it has been also revealed that the basic classification techniques have intrinsic drawbacks in achieving accurate gene classification and cancer diagnosis. On the other hand, classifier ensembles have received increasing attention in various applications. Here, we address the gene classification issue using RotBoost ensemble methodology. This method is a combination of Rotation Forest and AdaBoost techniques which in turn preserve both desirable features of an ensemble architecture, that is, accuracy and diversity. To select a concise subset of informative genes, 5 different feature selection algorithms are considered. To assess the efficiency of the RotBoost, other nonensemble/ensemble techniques including Decision Trees, Support Vector Machines, Rotation Forest, AdaBoost, and Bagging are also deployed. Experimental results have revealed that the combination of the fast correlation-based feature selection method with ICA-based RotBoost ensemble is highly effective for gene classification. In fact, the proposed method can create ensemble classifiers which outperform not only the classifiers produced by the conventional machine learning but also the classifiers generated by two widely used conventional ensemble learning methods, that is, Bagging and AdaBoost.

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.

Automated detection of ventricular pre-excitation in pediatric 12-lead ECG.

PubMed

Gregg, Richard E; Zhou, Sophia H; Dubin, Anne M

2016-01-01

With increased interest in screening of young people for potential causes of sudden death, accurate automated detection of ventricular pre-excitation (VPE) or Wolff-Parkinson-White syndrome (WPW) in the pediatric resting ECG is important. Several recent studies have shown interobserver variability when reading screening ECGs and thus an accurate automated reading for this potential cause of sudden death is critical. We designed and tested an automated algorithm to detect pediatric VPE optimized for low prevalence. Digital ECGs with 12 leads or 15 leads (12-lead plus V3R, V4R and V7) were selected from multiple hospitals and separated into a testing and training database. Inclusion criterion was age less than 16 years. The reference for algorithm detection of VPE was cardiologist annotation of VPE for each ECG. The training database (n=772) consisted of VPE ECGs (n=37), normal ECGs (n=492) and a high concentration of conduction defects, RBBB (n=232) and LBBB (n=11). The testing database was a random sample (n=763). All ECGs were analyzed with the Philips DXL ECG Analysis algorithm for basic waveform measurements. Additional ECG features specific to VPE, mainly delta wave scoring, were calculated from the basic measurements and the average beat. A classifier based on decision tree bootstrap aggregation (tree bagger) was trained in multiple steps to select the number of decision trees and the 10 best features. The classifier accuracy was measured on the test database. The new algorithm detected pediatric VPE with a sensitivity of 78%, a specificity of 99.9%, a positive predictive value of 88% and negative predictive value of 99.7%. This new algorithm for detection of pediatric VPE performs well with a reasonable positive and negative predictive value despite the low prevalence in the general population. Copyright © 2016 Elsevier Inc. All rights reserved.

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.

Proposed hybrid-classifier ensemble algorithm to map snow cover area

NASA Astrophysics Data System (ADS)

Nijhawan, Rahul; Raman, Balasubramanian; Das, Josodhir

2018-01-01

Metaclassification ensemble approach is known to improve the prediction performance of snow-covered area. The methodology adopted in this case is based on neural network along with four state-of-art machine learning algorithms: support vector machine, artificial neural networks, spectral angle mapper, K-mean clustering, and a snow index: normalized difference snow index. An AdaBoost ensemble algorithm related to decision tree for snow-cover mapping is also proposed. According to available literature, these methods have been rarely used for snow-cover mapping. Employing the above techniques, a study was conducted for Raktavarn and Chaturangi Bamak glaciers, Uttarakhand, Himalaya using multispectral Landsat 7 ETM+ (enhanced thematic mapper) image. The study also compares the results with those obtained from statistical combination methods (majority rule and belief functions) and accuracies of individual classifiers. Accuracy assessment is performed by computing the quantity and allocation disagreement, analyzing statistic measures (accuracy, precision, specificity, AUC, and sensitivity) and receiver operating characteristic curves. A total of 225 combinations of parameters for individual classifiers were trained and tested on the dataset and results were compared with the proposed approach. It was observed that the proposed methodology produced the highest classification accuracy (95.21%), close to (94.01%) that was produced by the proposed AdaBoost ensemble algorithm. From the sets of observations, it was concluded that the ensemble of classifiers produced better results compared to individual classifiers.

Feature Selection with Conjunctions of Decision Stumps and Learning from Microarray Data.

PubMed

Shah, M; Marchand, M; Corbeil, J

2012-01-01

One of the objectives of designing feature selection learning algorithms is to obtain classifiers that depend on a small number of attributes and have verifiable future performance guarantees. There are few, if any, approaches that successfully address the two goals simultaneously. To the best of our knowledge, such algorithms that give theoretical bounds on the future performance have not been proposed so far in the context of the classification of gene expression data. In this work, we investigate the premise of learning a conjunction (or disjunction) of decision stumps in Occam's Razor, Sample Compression, and PAC-Bayes learning settings for identifying a small subset of attributes that can be used to perform reliable classification tasks. We apply the proposed approaches for gene identification from DNA microarray data and compare our results to those of the well-known successful approaches proposed for the task. We show that our algorithm not only finds hypotheses with a much smaller number of genes while giving competitive classification accuracy but also having tight risk guarantees on future performance, unlike other approaches. The proposed approaches are general and extensible in terms of both designing novel algorithms and application to other domains.

Intelligent deflection routing in buffer-less networks.

PubMed

Haeri, Soroush; Trajković, Ljiljana

2015-02-01

Deflection routing is employed to ameliorate packet loss caused by contention in buffer-less architectures such as optical burst-switched networks. The main goal of deflection routing is to successfully deflect a packet based only on a limited knowledge that network nodes possess about their environment. In this paper, we present a framework that introduces intelligence to deflection routing (iDef). iDef decouples the design of the signaling infrastructure from the underlying learning algorithm. It consists of a signaling and a decision-making module. Signaling module implements a feedback management protocol while the decision-making module implements a reinforcement learning algorithm. We also propose several learning-based deflection routing protocols, implement them in iDef using the ns-3 network simulator, and compare their performance.

Deep generative learning for automated EHR diagnosis of traditional Chinese medicine.

PubMed

Liang, Zhaohui; Liu, Jun; Ou, Aihua; Zhang, Honglai; Li, Ziping; Huang, Jimmy Xiangji

2018-05-04

Computer-aided medical decision-making (CAMDM) is the method to utilize massive EMR data as both empirical and evidence support for the decision procedure of healthcare activities. Well-developed information infrastructure, such as hospital information systems and disease surveillance systems, provides abundant data for CAMDM. However, the complexity of EMR data with abstract medical knowledge makes the conventional model incompetent for the analysis. Thus a deep belief networks (DBN) based model is proposed to simulate the information analysis and decision-making procedure in medical practice. The purpose of this paper is to evaluate a deep learning architecture as an effective solution for CAMDM. A two-step model is applied in our study. At the first step, an optimized seven-layer deep belief network (DBN) is applied as an unsupervised learning algorithm to perform model training to acquire feature representation. Then a support vector machine model is adopted to DBN at the second step of the supervised learning. There are two data sets used in the experiments. One is a plain text data set indexed by medical experts. The other is a structured dataset on primary hypertension. The data are randomly divided to generate the training set for the unsupervised learning and the testing set for the supervised learning. The model performance is evaluated by the statistics of mean and variance, the average precision and coverage on the data sets. Two conventional shallow models (support vector machine / SVM and decision tree / DT) are applied as the comparisons to show the superiority of our proposed approach. The deep learning (DBN + SVM) model outperforms simple SVM and DT on two data sets in terms of all the evaluation measures, which confirms our motivation that the deep model is good at capturing the key features with less dependence when the index is built up by manpower. Our study shows the two-step deep learning model achieves high performance for medical information retrieval over the conventional shallow models. It is able to capture the features of both plain text and the highly-structured database of EMR data. The performance of the deep model is superior to the conventional shallow learning models such as SVM and DT. It is an appropriate knowledge-learning model for information retrieval of EMR system. Therefore, deep learning provides a good solution to improve the performance of CAMDM systems. Copyright © 2018. Published by Elsevier B.V.

Using Induction to Refine Information Retrieval Strategies

NASA Technical Reports Server (NTRS)

Baudin, Catherine; Pell, Barney; Kedar, Smadar

1994-01-01

Conceptual information retrieval systems use structured document indices, domain knowledge and a set of heuristic retrieval strategies to match user queries with a set of indices describing the document's content. Such retrieval strategies increase the set of relevant documents retrieved (increase recall), but at the expense of returning additional irrelevant documents (decrease precision). Usually in conceptual information retrieval systems this tradeoff is managed by hand and with difficulty. This paper discusses ways of managing this tradeoff by the application of standard induction algorithms to refine the retrieval strategies in an engineering design domain. We gathered examples of query/retrieval pairs during the system's operation using feedback from a user on the retrieved information. We then fed these examples to the induction algorithm and generated decision trees that refine the existing set of retrieval strategies. We found that (1) induction improved the precision on a set of queries generated by another user, without a significant loss in recall, and (2) in an interactive mode, the decision trees pointed out flaws in the retrieval and indexing knowledge and suggested ways to refine the retrieval strategies.

HUMAN DECISIONS AND MACHINE PREDICTIONS.

PubMed

Kleinberg, Jon; Lakkaraju, Himabindu; Leskovec, Jure; Ludwig, Jens; Mullainathan, Sendhil

2018-02-01

Can machine learning improve human decision making? Bail decisions provide a good test case. Millions of times each year, judges make jail-or-release decisions that hinge on a prediction of what a defendant would do if released. The concreteness of the prediction task combined with the volume of data available makes this a promising machine-learning application. Yet comparing the algorithm to judges proves complicated. First, the available data are generated by prior judge decisions. We only observe crime outcomes for released defendants, not for those judges detained. This makes it hard to evaluate counterfactual decision rules based on algorithmic predictions. Second, judges may have a broader set of preferences than the variable the algorithm predicts; for instance, judges may care specifically about violent crimes or about racial inequities. We deal with these problems using different econometric strategies, such as quasi-random assignment of cases to judges. Even accounting for these concerns, our results suggest potentially large welfare gains: one policy simulation shows crime reductions up to 24.7% with no change in jailing rates, or jailing rate reductions up to 41.9% with no increase in crime rates. Moreover, all categories of crime, including violent crimes, show reductions; and these gains can be achieved while simultaneously reducing racial disparities. These results suggest that while machine learning can be valuable, realizing this value requires integrating these tools into an economic framework: being clear about the link between predictions and decisions; specifying the scope of payoff functions; and constructing unbiased decision counterfactuals. JEL Codes: C10 (Econometric and statistical methods and methodology), C55 (Large datasets: Modeling and analysis), K40 (Legal procedure, the legal system, and illegal behavior).

HUMAN DECISIONS AND MACHINE PREDICTIONS*

PubMed Central

Kleinberg, Jon; Lakkaraju, Himabindu; Leskovec, Jure; Ludwig, Jens; Mullainathan, Sendhil

2018-01-01

Can machine learning improve human decision making? Bail decisions provide a good test case. Millions of times each year, judges make jail-or-release decisions that hinge on a prediction of what a defendant would do if released. The concreteness of the prediction task combined with the volume of data available makes this a promising machine-learning application. Yet comparing the algorithm to judges proves complicated. First, the available data are generated by prior judge decisions. We only observe crime outcomes for released defendants, not for those judges detained. This makes it hard to evaluate counterfactual decision rules based on algorithmic predictions. Second, judges may have a broader set of preferences than the variable the algorithm predicts; for instance, judges may care specifically about violent crimes or about racial inequities. We deal with these problems using different econometric strategies, such as quasi-random assignment of cases to judges. Even accounting for these concerns, our results suggest potentially large welfare gains: one policy simulation shows crime reductions up to 24.7% with no change in jailing rates, or jailing rate reductions up to 41.9% with no increase in crime rates. Moreover, all categories of crime, including violent crimes, show reductions; and these gains can be achieved while simultaneously reducing racial disparities. These results suggest that while machine learning can be valuable, realizing this value requires integrating these tools into an economic framework: being clear about the link between predictions and decisions; specifying the scope of payoff functions; and constructing unbiased decision counterfactuals. JEL Codes: C10 (Econometric and statistical methods and methodology), C55 (Large datasets: Modeling and analysis), K40 (Legal procedure, the legal system, and illegal behavior) PMID:29755141

Comparative study of biodegradability prediction of chemicals using decision trees, functional trees, and logistic regression.

PubMed

Chen, Guangchao; Li, Xuehua; Chen, Jingwen; Zhang, Ya-Nan; Peijnenburg, Willie J G M

2014-12-01

Biodegradation is the principal environmental dissipation process of chemicals. As such, it is a dominant factor determining the persistence and fate of organic chemicals in the environment, and is therefore of critical importance to chemical management and regulation. In the present study, the authors developed in silico methods assessing biodegradability based on a large heterogeneous set of 825 organic compounds, using the techniques of the C4.5 decision tree, the functional inner regression tree, and logistic regression. External validation was subsequently carried out by 2 independent test sets of 777 and 27 chemicals. As a result, the functional inner regression tree exhibited the best predictability with predictive accuracies of 81.5% and 81.0%, respectively, on the training set (825 chemicals) and test set I (777 chemicals). Performance of the developed models on the 2 test sets was subsequently compared with that of the Estimation Program Interface (EPI) Suite Biowin 5 and Biowin 6 models, which also showed a better predictability of the functional inner regression tree model. The model built in the present study exhibits a reasonable predictability compared with existing models while possessing a transparent algorithm. Interpretation of the mechanisms of biodegradation was also carried out based on the models developed. © 2014 SETAC.

Land cover and land use mapping of the iSimangaliso Wetland Park, South Africa: comparison of oblique and orthogonal random forest algorithms

NASA Astrophysics Data System (ADS)

Bassa, Zaakirah; Bob, Urmilla; Szantoi, Zoltan; Ismail, Riyad

2016-01-01

In recent years, the popularity of tree-based ensemble methods for land cover classification has increased significantly. Using WorldView-2 image data, we evaluate the potential of the oblique random forest algorithm (oRF) to classify a highly heterogeneous protected area. In contrast to the random forest (RF) algorithm, the oRF algorithm builds multivariate trees by learning the optimal split using a supervised model. The oRF binary algorithm is adapted to a multiclass land cover and land use application using both the "one-against-one" and "one-against-all" combination approaches. Results show that the oRF algorithms are capable of achieving high classification accuracies (>80%). However, there was no statistical difference in classification accuracies obtained by the oRF algorithms and the more popular RF algorithm. For all the algorithms, user accuracies (UAs) and producer accuracies (PAs) >80% were recorded for most of the classes. Both the RF and oRF algorithms poorly classified the indigenous forest class as indicated by the low UAs and PAs. Finally, the results from this study advocate and support the utility of the oRF algorithm for land cover and land use mapping of protected areas using WorldView-2 image data.

Application of Boosting Regression Trees to Preliminary Cost Estimation in Building Construction Projects

PubMed Central

2015-01-01

Among the recent data mining techniques available, the boosting approach has attracted a great deal of attention because of its effective learning algorithm and strong boundaries in terms of its generalization performance. However, the boosting approach has yet to be used in regression problems within the construction domain, including cost estimations, but has been actively utilized in other domains. Therefore, a boosting regression tree (BRT) is applied to cost estimations at the early stage of a construction project to examine the applicability of the boosting approach to a regression problem within the construction domain. To evaluate the performance of the BRT model, its performance was compared with that of a neural network (NN) model, which has been proven to have a high performance in cost estimation domains. The BRT model has shown results similar to those of NN model using 234 actual cost datasets of a building construction project. In addition, the BRT model can provide additional information such as the importance plot and structure model, which can support estimators in comprehending the decision making process. Consequently, the boosting approach has potential applicability in preliminary cost estimations in a building construction project. PMID:26339227

Application of Boosting Regression Trees to Preliminary Cost Estimation in Building Construction Projects.

PubMed

Shin, Yoonseok

2015-01-01

Among the recent data mining techniques available, the boosting approach has attracted a great deal of attention because of its effective learning algorithm and strong boundaries in terms of its generalization performance. However, the boosting approach has yet to be used in regression problems within the construction domain, including cost estimations, but has been actively utilized in other domains. Therefore, a boosting regression tree (BRT) is applied to cost estimations at the early stage of a construction project to examine the applicability of the boosting approach to a regression problem within the construction domain. To evaluate the performance of the BRT model, its performance was compared with that of a neural network (NN) model, which has been proven to have a high performance in cost estimation domains. The BRT model has shown results similar to those of NN model using 234 actual cost datasets of a building construction project. In addition, the BRT model can provide additional information such as the importance plot and structure model, which can support estimators in comprehending the decision making process. Consequently, the boosting approach has potential applicability in preliminary cost estimations in a building construction project.

Smart City Mobility Application--Gradient Boosting Trees for Mobility Prediction and Analysis Based on Crowdsourced Data.

PubMed

Semanjski, Ivana; Gautama, Sidharta

2015-07-03

Mobility management represents one of the most important parts of the smart city concept. The way we travel, at what time of the day, for what purposes and with what transportation modes, have a pertinent impact on the overall quality of life in cities. To manage this process, detailed and comprehensive information on individuals' behaviour is needed as well as effective feedback/communication channels. In this article, we explore the applicability of crowdsourced data for this purpose. We apply a gradient boosting trees algorithm to model individuals' mobility decision making processes (particularly concerning what transportation mode they are likely to use). To accomplish this we rely on data collected from three sources: a dedicated smartphone application, a geographic information systems-based web interface and weather forecast data collected over a period of six months. The applicability of the developed model is seen as a potential platform for personalized mobility management in smart cities and a communication tool between the city (to steer the users towards more sustainable behaviour by additionally weighting preferred suggestions) and users (who can give feedback on the acceptability of the provided suggestions, by accepting or rejecting them, providing an additional input to the learning process).

Modeling the Swift BAT Trigger Algorithm with Machine Learning

NASA Technical Reports Server (NTRS)

Graff, Philip B.; Lien, Amy Y.; Baker, John G.; Sakamoto, Takanori

2015-01-01

To draw inferences about gamma-ray burst (GRB) source populations based on Swift observations, it is essential to understand the detection efficiency of the Swift burst alert telescope (BAT). This study considers the problem of modeling the Swift BAT triggering algorithm for long GRBs, a computationally expensive procedure, and models it using machine learning algorithms. A large sample of simulated GRBs from Lien et al. (2014) is used to train various models: random forests, boosted decision trees (with AdaBoost), support vector machines, and artificial neural networks. The best models have accuracies of approximately greater than 97% (approximately less than 3% error), which is a significant improvement on a cut in GRB flux which has an accuracy of 89:6% (10:4% error). These models are then used to measure the detection efficiency of Swift as a function of redshift z, which is used to perform Bayesian parameter estimation on the GRB rate distribution. We find a local GRB rate density of eta(sub 0) approximately 0.48(+0.41/-0.23) Gpc(exp -3) yr(exp -1) with power-law indices of eta(sub 1) approximately 1.7(+0.6/-0.5) and eta(sub 2) approximately -5.9(+5.7/-0.1) for GRBs above and below a break point of z(sub 1) approximately 6.8(+2.8/-3.2). This methodology is able to improve upon earlier studies by more accurately modeling Swift detection and using this for fully Bayesian model fitting. The code used in this is analysis is publicly available online.

Modeling the Swift Bat Trigger Algorithm with Machine Learning

NASA Technical Reports Server (NTRS)

Graff, Philip B.; Lien, Amy Y.; Baker, John G.; Sakamoto, Takanori

2016-01-01

To draw inferences about gamma-ray burst (GRB) source populations based on Swift observations, it is essential to understand the detection efficiency of the Swift burst alert telescope (BAT). This study considers the problem of modeling the Swift / BAT triggering algorithm for long GRBs, a computationally expensive procedure, and models it using machine learning algorithms. A large sample of simulated GRBs from Lien et al. is used to train various models: random forests, boosted decision trees (with AdaBoost), support vector machines, and artificial neural networks. The best models have accuracies of greater than or equal to 97 percent (less than or equal to 3 percent error), which is a significant improvement on a cut in GRB flux, which has an accuracy of 89.6 percent (10.4 percent error). These models are then used to measure the detection efficiency of Swift as a function of redshift z, which is used to perform Bayesian parameter estimation on the GRB rate distribution. We find a local GRB rate density of n (sub 0) approaching 0.48 (sup plus 0.41) (sub minus 0.23) per cubic gigaparsecs per year with power-law indices of n (sub 1) approaching 1.7 (sup plus 0.6) (sub minus 0.5) and n (sub 2) approaching minus 5.9 (sup plus 5.7) (sub minus 0.1) for GRBs above and below a break point of z (redshift) (sub 1) approaching 6.8 (sup plus 2.8) (sub minus 3.2). This methodology is able to improve upon earlier studies by more accurately modeling Swift detection and using this for fully Bayesian model fitting.

Performance comparison of machine learning algorithms and number of independent components used in fMRI decoding of belief vs. disbelief.

PubMed

Douglas, P K; Harris, Sam; Yuille, Alan; Cohen, Mark S

2011-05-15

Machine learning (ML) has become a popular tool for mining functional neuroimaging data, and there are now hopes of performing such analyses efficiently in real-time. Towards this goal, we compared accuracy of six different ML algorithms applied to neuroimaging data of persons engaged in a bivariate task, asserting their belief or disbelief of a variety of propositional statements. We performed unsupervised dimension reduction and automated feature extraction using independent component (IC) analysis and extracted IC time courses. Optimization of classification hyperparameters across each classifier occurred prior to assessment. Maximum accuracy was achieved at 92% for Random Forest, followed by 91% for AdaBoost, 89% for Naïve Bayes, 87% for a J48 decision tree, 86% for K*, and 84% for support vector machine. For real-time decoding applications, finding a parsimonious subset of diagnostic ICs might be useful. We used a forward search technique to sequentially add ranked ICs to the feature subspace. For the current data set, we determined that approximately six ICs represented a meaningful basis set for classification. We then projected these six IC spatial maps forward onto a later scanning session within subject. We then applied the optimized ML algorithms to these new data instances, and found that classification accuracy results were reproducible. Additionally, we compared our classification method to our previously published general linear model results on this same data set. The highest ranked IC spatial maps show similarity to brain regions associated with contrasts for belief > disbelief, and disbelief < belief. Copyright © 2010 Elsevier Inc. All rights reserved.

Intra- and interspecific variation in tropical tree and liana phenology derived from Unmanned Aerial Vehicle images

NASA Astrophysics Data System (ADS)

Bohlman, S.; Park, J.; Muller-Landau, H. C.; Rifai, S. W.; Dandois, J. P.

2017-12-01

Phenology is a critical driver of ecosystem processes. There is strong evidence that phenology is shifting in temperate ecosystems in response to climate change, but tropical tree and liana phenology remains poorly quantified and understood. A key challenge is that tropical forests contain hundreds of plant species with a wide variety of phenological patterns. Satellite-based observations, an important source of phenology data in northern latitudes, are hindered by frequent cloud cover in the tropics. To quantify phenology over a large number of individuals and species, we collected bi-weekly images from unmanned aerial vehicles (UAVs) in the well-studied 50-ha forest inventory plot on Barro Colorado Island, Panama. Between October 2014 and December 2015 and again in May 2015, we collected a total of 35 sets of UAV images, each with continuous coverage of the 50-ha plot, where every tree ≥ 1 cm DBH is mapped. Spectral, texture, and image information was extracted from the UAV images for individual tree crowns, which was then used as inputs for a machine learning algorithm to predict percent leaf and branch cover. We obtained the species identities of 2000 crowns in the images via field mapping. The objectives of this study are to (1) determined if machine learning algorithms, applied to UAV images, can effectively quantify changes in leaf cover, which we term "deciduousness; (2) determine how liana cover effects deciduousness and (3) test how well UAV-derived deciduousness patterns match satellite-derived temporal patterns. Machine learning algorithms trained on a variety of image parameters could effectively determine leaf cover, despite variation in lighting and viewing angles. Crowns with higher liana cover have less overall deciduousness (tree + liana together) than crowns with lower liana cover. Individual crown deciduousness, summed over all crowns measured in the 50-ha plot, showed a similar seasonal pattern as MODIS EVI composited over 10 years. However, MODIS EVI phenology was "greened" up earlier than UAV-based deciduousness, perhaps reflecting the new late dry season leaf flush that increases EVI but not overall leaf cover. We discuss how the potential mechanisms that explain variation among species and between trees and lianas and the consequences for these variation for ecosystem processes and modeling.

A simple and robust classification tree for differentiation between benign and malignant lesions in MR-mammography.

PubMed

Baltzer, Pascal A T; Dietzel, Matthias; Kaiser, Werner A

2013-08-01

In the face of multiple available diagnostic criteria in MR-mammography (MRM), a practical algorithm for lesion classification is needed. Such an algorithm should be as simple as possible and include only important independent lesion features to differentiate benign from malignant lesions. This investigation aimed to develop a simple classification tree for differential diagnosis in MRM. A total of 1,084 lesions in standardised MRM with subsequent histological verification (648 malignant, 436 benign) were investigated. Seventeen lesion criteria were assessed by 2 readers in consensus. Classification analysis was performed using the chi-squared automatic interaction detection (CHAID) method. Results include the probability for malignancy for every descriptor combination in the classification tree. A classification tree incorporating 5 lesion descriptors with a depth of 3 ramifications (1, root sign; 2, delayed enhancement pattern; 3, border, internal enhancement and oedema) was calculated. Of all 1,084 lesions, 262 (40.4 %) and 106 (24.3 %) could be classified as malignant and benign with an accuracy above 95 %, respectively. Overall diagnostic accuracy was 88.4 %. The classification algorithm reduced the number of categorical descriptors from 17 to 5 (29.4 %), resulting in a high classification accuracy. More than one third of all lesions could be classified with accuracy above 95 %. • A practical algorithm has been developed to classify lesions found in MR-mammography. • A simple decision tree consisting of five criteria reaches high accuracy of 88.4 %. • Unique to this approach, each classification is associated with a diagnostic certainty. • Diagnostic certainty of greater than 95 % is achieved in 34 % of all cases.

Estimation of State Transition Probabilities: A Neural Network Model

NASA Astrophysics Data System (ADS)

Saito, Hiroshi; Takiyama, Ken; Okada, Masato

2015-12-01

Humans and animals can predict future states on the basis of acquired knowledge. This prediction of the state transition is important for choosing the best action, and the prediction is only possible if the state transition probability has already been learned. However, how our brains learn the state transition probability is unknown. Here, we propose a simple algorithm for estimating the state transition probability by utilizing the state prediction error. We analytically and numerically confirmed that our algorithm is able to learn the probability completely with an appropriate learning rate. Furthermore, our learning rule reproduced experimentally reported psychometric functions and neural activities in the lateral intraparietal area in a decision-making task. Thus, our algorithm might describe the manner in which our brains learn state transition probabilities and predict future states.

Binary Decision Trees for Preoperative Periapical Cyst Screening Using Cone-beam Computed Tomography.

PubMed

Pitcher, Brandon; Alaqla, Ali; Noujeim, Marcel; Wealleans, James A; Kotsakis, Georgios; Chrepa, Vanessa

2017-03-01

Cone-beam computed tomographic (CBCT) analysis allows for 3-dimensional assessment of periradicular lesions and may facilitate preoperative periapical cyst screening. The purpose of this study was to develop and assess the predictive validity of a cyst screening method based on CBCT volumetric analysis alone or combined with designated radiologic criteria. Three independent examiners evaluated 118 presurgical CBCT scans from cases that underwent apicoectomies and had an accompanying gold standard histopathological diagnosis of either a cyst or granuloma. Lesion volume, density, and specific radiologic characteristics were assessed using specialized software. Logistic regression models with histopathological diagnosis as the dependent variable were constructed for cyst prediction, and receiver operating characteristic curves were used to assess the predictive validity of the models. A conditional inference binary decision tree based on a recursive partitioning algorithm was constructed to facilitate preoperative screening. Interobserver agreement was excellent for volume and density, but it varied from poor to good for the radiologic criteria. Volume and root displacement were strong predictors for cyst screening in all analyses. The binary decision tree classifier determined that if the volume of the lesion was >247 mm 3 , there was 80% probability of a cyst. If volume was <247 mm 3 and root displacement was present, cyst probability was 60% (78% accuracy). The good accuracy and high specificity of the decision tree classifier renders it a useful preoperative cyst screening tool that can aid in clinical decision making but not a substitute for definitive histopathological diagnosis after biopsy. Confirmatory studies are required to validate the present findings. Published by Elsevier Inc.

A High Performance Computing Approach to Tree Cover Delineation in 1-m NAIP Imagery Using a Probabilistic Learning Framework

NASA Technical Reports Server (NTRS)

Basu, Saikat; Ganguly, Sangram; Michaelis, Andrew; Votava, Petr; Roy, Anshuman; Mukhopadhyay, Supratik; Nemani, Ramakrishna

2015-01-01

Tree cover delineation is a useful instrument in deriving Above Ground Biomass (AGB) density estimates from Very High Resolution (VHR) airborne imagery data. Numerous algorithms have been designed to address this problem, but most of them do not scale to these datasets, which are of the order of terabytes. In this paper, we present a semi-automated probabilistic framework for the segmentation and classification of 1-m National Agriculture Imagery Program (NAIP) for tree-cover delineation for the whole of Continental United States, using a High Performance Computing Architecture. Classification is performed using a multi-layer Feedforward Backpropagation Neural Network and segmentation is performed using a Statistical Region Merging algorithm. The results from the classification and segmentation algorithms are then consolidated into a structured prediction framework using a discriminative undirected probabilistic graphical model based on Conditional Random Field, which helps in capturing the higher order contextual dependencies between neighboring pixels. Once the final probability maps are generated, the framework is updated and re-trained by relabeling misclassified image patches. This leads to a significant improvement in the true positive rates and reduction in false positive rates. The tree cover maps were generated for the whole state of California, spanning a total of 11,095 NAIP tiles covering a total geographical area of 163,696 sq. miles. The framework produced true positive rates of around 88% for fragmented forests and 74% for urban tree cover areas, with false positive rates lower than 2% for both landscapes. Comparative studies with the National Land Cover Data (NLCD) algorithm and the LiDAR canopy height model (CHM) showed the effectiveness of our framework for generating accurate high-resolution tree-cover maps.

A High Performance Computing Approach to Tree Cover Delineation in 1-m NAIP Imagery using a Probabilistic Learning Framework

NASA Astrophysics Data System (ADS)

Basu, S.; Ganguly, S.; Michaelis, A.; Votava, P.; Roy, A.; Mukhopadhyay, S.; Nemani, R. R.

2015-12-01

Tree cover delineation is a useful instrument in deriving Above Ground Biomass (AGB) density estimates from Very High Resolution (VHR) airborne imagery data. Numerous algorithms have been designed to address this problem, but most of them do not scale to these datasets which are of the order of terabytes. In this paper, we present a semi-automated probabilistic framework for the segmentation and classification of 1-m National Agriculture Imagery Program (NAIP) for tree-cover delineation for the whole of Continental United States, using a High Performance Computing Architecture. Classification is performed using a multi-layer Feedforward Backpropagation Neural Network and segmentation is performed using a Statistical Region Merging algorithm. The results from the classification and segmentation algorithms are then consolidated into a structured prediction framework using a discriminative undirected probabilistic graphical model based on Conditional Random Field, which helps in capturing the higher order contextual dependencies between neighboring pixels. Once the final probability maps are generated, the framework is updated and re-trained by relabeling misclassified image patches. This leads to a significant improvement in the true positive rates and reduction in false positive rates. The tree cover maps were generated for the whole state of California, spanning a total of 11,095 NAIP tiles covering a total geographical area of 163,696 sq. miles. The framework produced true positive rates of around 88% for fragmented forests and 74% for urban tree cover areas, with false positive rates lower than 2% for both landscapes. Comparative studies with the National Land Cover Data (NLCD) algorithm and the LiDAR canopy height model (CHM) showed the effectiveness of our framework for generating accurate high-resolution tree-cover maps.

VEGETATION COVER ANALYSIS OF HAZARDOUS WASTE SITES IN UTAH AND ARIZONA USING HYPERSPECTRAL REMOTE SENSING

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

Serrato, M.; Jungho, I.; Jensen, J.

2012-01-17

Remote sensing technology can provide a cost-effective tool for monitoring hazardous waste sites. This study investigated the usability of HyMap airborne hyperspectral remote sensing data (126 bands at 2.3 x 2.3 m spatial resolution) to characterize the vegetation at U.S. Department of Energy uranium processing sites near Monticello, Utah and Monument Valley, Arizona. Grass and shrub species were mixed on an engineered disposal cell cover at the Monticello site while shrub species were dominant in the phytoremediation plantings at the Monument Valley site. The specific objectives of this study were to: (1) estimate leaf-area-index (LAI) of the vegetation using threemore » different methods (i.e., vegetation indices, red-edge positioning (REP), and machine learning regression trees), and (2) map the vegetation cover using machine learning decision trees based on either the scaled reflectance data or mixture tuned matched filtering (MTMF)-derived metrics and vegetation indices. Regression trees resulted in the best calibration performance of LAI estimation (R{sup 2} > 0.80). The use of REPs failed to accurately predict LAI (R{sup 2} < 0.2). The use of the MTMF-derived metrics (matched filter scores and infeasibility) and a range of vegetation indices in decision trees improved the vegetation mapping when compared to the decision tree classification using just the scaled reflectance. Results suggest that hyperspectral imagery are useful for characterizing biophysical characteristics (LAI) and vegetation cover on capped hazardous waste sites. However, it is believed that the vegetation mapping would benefit from the use of 1 higher spatial resolution hyperspectral data due to the small size of many of the vegetation patches (< 1m) found on the sites.« less

Variations in the Intragene Methylation Profiles Hallmark Induced Pluripotency

PubMed Central

Druzhkov, Pavel; Zolotykh, Nikolay; Meyerov, Iosif; Alsaedi, Ahmed; Shutova, Maria; Ivanchenko, Mikhail; Zaikin, Alexey

2015-01-01

We demonstrate the potential of differentiating embryonic and induced pluripotent stem cells by the regularized linear and decision tree machine learning classification algorithms, based on a number of intragene methylation measures. The resulting average accuracy of classification has been proven to be above 95%, which overcomes the earlier achievements. We propose a constructive and transparent method of feature selection based on classifier accuracy. Enrichment analysis reveals statistically meaningful presence of stemness group and cancer discriminating genes among the selected best classifying features. These findings stimulate the further research on the functional consequences of these differences in methylation patterns. The presented approach can be broadly used to discriminate the cells of different phenotype or in different state by their methylation profiles, identify groups of genes constituting multifeature classifiers, and assess enrichment of these groups by the sets of genes with a functionality of interest. PMID:26618180

Automated Assessment of Patients' Self-Narratives for Posttraumatic Stress Disorder Screening Using Natural Language Processing and Text Mining.

PubMed

He, Qiwei; Veldkamp, Bernard P; Glas, Cees A W; de Vries, Theo

2017-03-01

Patients' narratives about traumatic experiences and symptoms are useful in clinical screening and diagnostic procedures. In this study, we presented an automated assessment system to screen patients for posttraumatic stress disorder via a natural language processing and text-mining approach. Four machine-learning algorithms-including decision tree, naive Bayes, support vector machine, and an alternative classification approach called the product score model-were used in combination with n-gram representation models to identify patterns between verbal features in self-narratives and psychiatric diagnoses. With our sample, the product score model with unigrams attained the highest prediction accuracy when compared with practitioners' diagnoses. The addition of multigrams contributed most to balancing the metrics of sensitivity and specificity. This article also demonstrates that text mining is a promising approach for analyzing patients' self-expression behavior, thus helping clinicians identify potential patients from an early stage.

Enhancement Of Reading Accuracy By Multiple Data Integration

NASA Astrophysics Data System (ADS)

Lee, Kangsuk

1989-07-01

In this paper, a multiple sensor integration technique with neural network learning algorithms is presented which can enhance the reading accuracy of the hand-written numerals. Many document reading applications involve hand-written numerals in a predetermined location on a form, and in many cases, critical data is redundantly described. The amount of a personal check is one such case which is written redundantly in numerals and in alphabetical form. Information from two optical character recognition modules, one specialized for digits and one for words, is combined to yield an enhanced recognition of the amount. The combination can be accomplished by a decision tree with "if-then" rules, but by simply fusing two or more sets of sensor data in a single expanded neural net, the same functionality can be expected with a much reduced system cost. Experimental results of fusing two neural nets to enhance overall recognition performance using a controlled data set are presented.

Machine learning in soil classification.

PubMed

Bhattacharya, B; Solomatine, D P

2006-03-01

In a number of engineering problems, e.g. in geotechnics, petroleum engineering, etc. intervals of measured series data (signals) are to be attributed a class maintaining the constraint of contiguity and standard classification methods could be inadequate. Classification in this case needs involvement of an expert who observes the magnitude and trends of the signals in addition to any a priori information that might be available. In this paper, an approach for automating this classification procedure is presented. Firstly, a segmentation algorithm is developed and applied to segment the measured signals. Secondly, the salient features of these segments are extracted using boundary energy method. Based on the measured data and extracted features to assign classes to the segments classifiers are built; they employ Decision Trees, ANN and Support Vector Machines. The methodology was tested in classifying sub-surface soil using measured data from Cone Penetration Testing and satisfactory results were obtained.

Genetic algorithm based fuzzy control of spacecraft autonomous rendezvous

NASA Technical Reports Server (NTRS)

Karr, C. L.; Freeman, L. M.; Meredith, D. L.

1990-01-01

The U.S. Bureau of Mines is currently investigating ways to combine the control capabilities of fuzzy logic with the learning capabilities of genetic algorithms. Fuzzy logic allows for the uncertainty inherent in most control problems to be incorporated into conventional expert systems. Although fuzzy logic based expert systems have been used successfully for controlling a number of physical systems, the selection of acceptable fuzzy membership functions has generally been a subjective decision. High performance fuzzy membership functions for a fuzzy logic controller that manipulates a mathematical model simulating the autonomous rendezvous of spacecraft are learned using a genetic algorithm, a search technique based on the mechanics of natural genetics. The membership functions learned by the genetic algorithm provide for a more efficient fuzzy logic controller than membership functions selected by the authors for the rendezvous problem. Thus, genetic algorithms are potentially an effective and structured approach for learning fuzzy membership functions.

Career Path Suggestion using String Matching and Decision Trees

NASA Astrophysics Data System (ADS)

Nagpal, Akshay; P. Panda, Supriya

2015-05-01

High school and college graduates seemingly are often battling for the courses they should major in order to achieve their target career. In this paper, we worked on suggesting a career path to a graduate to reach his/her dream career given the current educational status. Firstly, we collected the career data of professionals and academicians from various career fields and compiled the data set by using the necessary information from the data. Further, this was used as the basis to suggest the most appropriate career path for the person given his/her current educational status. Decision trees and string matching algorithms were employed to suggest the appropriate career path for a person. Finally, an analysis of the result has been done directing to further improvements in the model.

A Walk on the Wild Side: Adventures with Project Learning Tree. A Gifted Science Unit for Grades 1-5.

ERIC Educational Resources Information Center

Hestad, Marsha; Avellone, Kathy

This 9-week curriculum unit on trees is designed for gifted students in grades 1-5. The lessons are designed for 40-minute classes meeting two or three times a week and stress the development of creative thinking skills, creative problem solving and decision making skills, and critical and logical thinking skills. Each of the 12 lesson plans…

The Extrapolation of Elementary Sequences

NASA Technical Reports Server (NTRS)

Laird, Philip; Saul, Ronald

1992-01-01

We study sequence extrapolation as a stream-learning problem. Input examples are a stream of data elements of the same type (integers, strings, etc.), and the problem is to construct a hypothesis that both explains the observed sequence of examples and extrapolates the rest of the stream. A primary objective -- and one that distinguishes this work from previous extrapolation algorithms -- is that the same algorithm be able to extrapolate sequences over a variety of different types, including integers, strings, and trees. We define a generous family of constructive data types, and define as our learning bias a stream language called elementary stream descriptions. We then give an algorithm that extrapolates elementary descriptions over constructive datatypes and prove that it learns correctly. For freely-generated types, we prove a polynomial time bound on descriptions of bounded complexity. An especially interesting feature of this work is the ability to provide quantitative measures of confidence in competing hypotheses, using a Bayesian model of prediction.

a Rough Set Decision Tree Based Mlp-Cnn for Very High Resolution Remotely Sensed Image Classification

NASA Astrophysics Data System (ADS)

Zhang, C.; Pan, X.; Zhang, S. Q.; Li, H. P.; Atkinson, P. M.

2017-09-01

Recent advances in remote sensing have witnessed a great amount of very high resolution (VHR) images acquired at sub-metre spatial resolution. These VHR remotely sensed data has post enormous challenges in processing, analysing and classifying them effectively due to the high spatial complexity and heterogeneity. Although many computer-aid classification methods that based on machine learning approaches have been developed over the past decades, most of them are developed toward pixel level spectral differentiation, e.g. Multi-Layer Perceptron (MLP), which are unable to exploit abundant spatial details within VHR images. This paper introduced a rough set model as a general framework to objectively characterize the uncertainty in CNN classification results, and further partition them into correctness and incorrectness on the map. The correct classification regions of CNN were trusted and maintained, whereas the misclassification areas were reclassified using a decision tree with both CNN and MLP. The effectiveness of the proposed rough set decision tree based MLP-CNN was tested using an urban area at Bournemouth, United Kingdom. The MLP-CNN, well capturing the complementarity between CNN and MLP through the rough set based decision tree, achieved the best classification performance both visually and numerically. Therefore, this research paves the way to achieve fully automatic and effective VHR image classification.

Regularised extreme learning machine with misclassification cost and rejection cost for gene expression data classification.

PubMed

Lu, Huijuan; Wei, Shasha; Zhou, Zili; Miao, Yanzi; Lu, Yi

2015-01-01

The main purpose of traditional classification algorithms on bioinformatics application is to acquire better classification accuracy. However, these algorithms cannot meet the requirement that minimises the average misclassification cost. In this paper, a new algorithm of cost-sensitive regularised extreme learning machine (CS-RELM) was proposed by using probability estimation and misclassification cost to reconstruct the classification results. By improving the classification accuracy of a group of small sample which higher misclassification cost, the new CS-RELM can minimise the classification cost. The 'rejection cost' was integrated into CS-RELM algorithm to further reduce the average misclassification cost. By using Colon Tumour dataset and SRBCT (Small Round Blue Cells Tumour) dataset, CS-RELM was compared with other cost-sensitive algorithms such as extreme learning machine (ELM), cost-sensitive extreme learning machine, regularised extreme learning machine, cost-sensitive support vector machine (SVM). The results of experiments show that CS-RELM with embedded rejection cost could reduce the average cost of misclassification and made more credible classification decision than others.

A review on machine learning principles for multi-view biological data integration.

PubMed

Li, Yifeng; Wu, Fang-Xiang; Ngom, Alioune

2018-03-01

Driven by high-throughput sequencing techniques, modern genomic and clinical studies are in a strong need of integrative machine learning models for better use of vast volumes of heterogeneous information in the deep understanding of biological systems and the development of predictive models. How data from multiple sources (called multi-view data) are incorporated in a learning system is a key step for successful analysis. In this article, we provide a comprehensive review on omics and clinical data integration techniques, from a machine learning perspective, for various analyses such as prediction, clustering, dimension reduction and association. We shall show that Bayesian models are able to use prior information and model measurements with various distributions; tree-based methods can either build a tree with all features or collectively make a final decision based on trees learned from each view; kernel methods fuse the similarity matrices learned from individual views together for a final similarity matrix or learning model; network-based fusion methods are capable of inferring direct and indirect associations in a heterogeneous network; matrix factorization models have potential to learn interactions among features from different views; and a range of deep neural networks can be integrated in multi-modal learning for capturing the complex mechanism of biological systems.

Online adaptive decision trees: pattern classification and function approximation.

PubMed

Basak, Jayanta

2006-09-01

Recently we have shown that decision trees can be trained in the online adaptive (OADT) mode (Basak, 2004), leading to better generalization score. OADTs were bottlenecked by the fact that they are able to handle only two-class classification tasks with a given structure. In this article, we provide an architecture based on OADT, ExOADT, which can handle multiclass classification tasks and is able to perform function approximation. ExOADT is structurally similar to OADT extended with a regression layer. We also show that ExOADT is capable not only of adapting the local decision hyperplanes in the nonterminal nodes but also has the potential of smoothly changing the structure of the tree depending on the data samples. We provide the learning rules based on steepest gradient descent for the new model ExOADT. Experimentally we demonstrate the effectiveness of ExOADT in the pattern classification and function approximation tasks. Finally, we briefly discuss the relationship of ExOADT with other classification models.

Fast Nonparametric Machine Learning Algorithms for High-Dimensional Massive Data and Applications

DTIC Science & Technology

2006-03-01

know the probability of that from Lemma 2. Using the union bound, we know that for any query q, the probability that i-am-feeling-lucky search algorithm...and each point in a d-dimensional space, a naive k-NN search needs to do a linear scan of T for every single query q, and thus the computational time...algorithm based on partition trees with priority search , and give an expected query time O((1/)d log n). But the constant in the O((1/)d log n

Acute Mental Discomfort Associated with Suicide Behavior in a Clinical Sample of Patients with Affective Disorders: Ascertaining Critical Variables Using Artificial Intelligence Tools.

PubMed

Morales, Susana; Barros, Jorge; Echávarri, Orietta; García, Fabián; Osses, Alex; Moya, Claudia; Maino, María Paz; Fischman, Ronit; Núñez, Catalina; Szmulewicz, Tita; Tomicic, Alemka

2017-01-01

In efforts to develop reliable methods to detect the likelihood of impending suicidal behaviors, we have proposed the following. To gain a deeper understanding of the state of suicide risk by determining the combination of variables that distinguishes between groups with and without suicide risk. A study involving 707 patients consulting for mental health issues in three health centers in Greater Santiago, Chile. Using 345 variables, an analysis was carried out with artificial intelligence tools, Cross Industry Standard Process for Data Mining processes, and decision tree techniques. The basic algorithm was top-down, and the most suitable division produced by the tree was selected by using the lowest Gini index as a criterion and by looping it until the condition of belonging to the group with suicidal behavior was fulfilled. Four trees distinguishing the groups were obtained, of which the elements of one were analyzed in greater detail, since this tree included both clinical and personality variables. This specific tree consists of six nodes without suicide risk and eight nodes with suicide risk (tree decision 01, accuracy 0.674, precision 0.652, recall 0.678, specificity 0.670, F measure 0.665, receiver operating characteristic (ROC) area under the curve (AUC) 73.35%; tree decision 02, accuracy 0.669, precision 0.642, recall 0.694, specificity 0.647, F measure 0.667, ROC AUC 68.91%; tree decision 03, accuracy 0.681, precision 0.675, recall 0.638, specificity 0.721, F measure, 0.656, ROC AUC 65.86%; tree decision 04, accuracy 0.714, precision 0.734, recall 0.628, specificity 0.792, F measure 0.677, ROC AUC 58.85%). This study defines the interactions among a group of variables associated with suicidal ideation and behavior. By using these variables, it may be possible to create a quick and easy-to-use tool. As such, psychotherapeutic interventions could be designed to mitigate the impact of these variables on the emotional state of individuals, thereby reducing eventual risk of suicide. Such interventions may reinforce psychological well-being, feelings of self-worth, and reasons for living, for each individual in certain groups of patients.

Combining macula clinical signs and patient characteristics for age-related macular degeneration diagnosis: a machine learning approach.

PubMed

Fraccaro, Paolo; Nicolo, Massimo; Bonetto, Monica; Giacomini, Mauro; Weller, Peter; Traverso, Carlo Enrico; Prosperi, Mattia; OSullivan, Dympna

2015-01-27

To investigate machine learning methods, ranging from simpler interpretable techniques to complex (non-linear) "black-box" approaches, for automated diagnosis of Age-related Macular Degeneration (AMD). Data from healthy subjects and patients diagnosed with AMD or other retinal diseases were collected during routine visits via an Electronic Health Record (EHR) system. Patients' attributes included demographics and, for each eye, presence/absence of major AMD-related clinical signs (soft drusen, retinal pigment epitelium, defects/pigment mottling, depigmentation area, subretinal haemorrhage, subretinal fluid, macula thickness, macular scar, subretinal fibrosis). Interpretable techniques known as white box methods including logistic regression and decision trees as well as less interpreitable techniques known as black box methods, such as support vector machines (SVM), random forests and AdaBoost, were used to develop models (trained and validated on unseen data) to diagnose AMD. The gold standard was confirmed diagnosis of AMD by physicians. Sensitivity, specificity and area under the receiver operating characteristic (AUC) were used to assess performance. Study population included 487 patients (912 eyes). In terms of AUC, random forests, logistic regression and adaboost showed a mean performance of (0.92), followed by SVM and decision trees (0.90). All machine learning models identified soft drusen and age as the most discriminating variables in clinicians' decision pathways to diagnose AMD. Both black-box and white box methods performed well in identifying diagnoses of AMD and their decision pathways. Machine learning models developed through the proposed approach, relying on clinical signs identified by retinal specialists, could be embedded into EHR to provide physicians with real time (interpretable) support.

Research on AHP decision algorithms based on BP algorithm

NASA Astrophysics Data System (ADS)

Ma, Ning; Guan, Jianhe

2017-10-01

Decision making is the thinking activity that people choose or judge, and scientific decision-making has always been a hot issue in the field of research. Analytic Hierarchy Process (AHP) is a simple and practical multi-criteria and multi-objective decision-making method that combines quantitative and qualitative and can show and calculate the subjective judgment in digital form. In the process of decision analysis using AHP method, the rationality of the two-dimensional judgment matrix has a great influence on the decision result. However, in dealing with the real problem, the judgment matrix produced by the two-dimensional comparison is often inconsistent, that is, it does not meet the consistency requirements. BP neural network algorithm is an adaptive nonlinear dynamic system. It has powerful collective computing ability and learning ability. It can perfect the data by constantly modifying the weights and thresholds of the network to achieve the goal of minimizing the mean square error. In this paper, the BP algorithm is used to deal with the consistency of the two-dimensional judgment matrix of the AHP.

Development and Validation of a Primary Care-Based Family Health History and Decision Support Program (MeTree)

PubMed Central

Orlando, Lori A.; Buchanan, Adam H.; Hahn, Susan E.; Christianson, Carol A.; Powell, Karen P.; Skinner, Celette Sugg; Chesnut, Blair; Blach, Colette; Due, Barbara; Ginsburg, Geoffrey S.; Henrich, Vincent C.

2016-01-01

INTRODUCTION Family health history is a strong predictor of disease risk. To reduce the morbidity and mortality of many chronic diseases, risk-stratified evidence-based guidelines strongly encourage the collection and synthesis of family health history to guide selection of primary prevention strategies. However, the collection and synthesis of such information is not well integrated into clinical practice. To address barriers to collection and use of family health histories, the Genomedical Connection developed and validated MeTree, a Web-based, patient-facing family health history collection and clinical decision support tool. MeTree is designed for integration into primary care practices as part of the genomic medicine model for primary care. METHODS We describe the guiding principles, operational characteristics, algorithm development, and coding used to develop MeTree. Validation was performed through stakeholder cognitive interviewing, a genetic counseling pilot program, and clinical practice pilot programs in 2 community-based primary care clinics. RESULTS Stakeholder feedback resulted in changes to MeTree’s interface and changes to the phrasing of clinical decision support documents. The pilot studies resulted in the identification and correction of coding errors and the reformatting of clinical decision support documents. MeTree’s strengths in comparison with other tools are its seamless integration into clinical practice and its provision of action-oriented recommendations guided by providers’ needs. LIMITATIONS The tool was validated in a small cohort. CONCLUSION MeTree can be integrated into primary care practices to help providers collect and synthesize family health history information from patients with the goal of improving adherence to risk-stratified evidence-based guidelines. PMID:24044145

Multi-agent simulation of generation expansion in electricity markets.

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

Botterud, A; Mahalik, M. R.; Veselka, T. D.

2007-06-01

We present a new multi-agent model of generation expansion in electricity markets. The model simulates generation investment decisions of decentralized generating companies (GenCos) interacting in a complex, multidimensional environment. A probabilistic dispatch algorithm calculates prices and profits for new candidate units in different future states of the system. Uncertainties in future load, hydropower conditions, and competitors actions are represented in a scenario tree, and decision analysis is used to identify the optimal expansion decision for each individual GenCo. We test the model using real data for the Korea power system under different assumptions about market design, market concentration, and GenCo'smore » assumed expectations about their competitors investment decisions.« less

Identification of individuals with ADHD using the Dean-Woodcock sensory motor battery and a boosted tree algorithm.

PubMed

Finch, Holmes W; Davis, Andrew; Dean, Raymond S

2015-03-01

The accurate and early identification of individuals with pervasive conditions such as attention deficit hyperactivity disorder (ADHD) is crucial to ensuring that they receive appropriate and timely assistance and treatment. Heretofore, identification of such individuals has proven somewhat difficult, typically involving clinical decision making based on descriptions and observations of behavior, in conjunction with the administration of cognitive assessments. The present study reports on the use of a sensory motor battery in conjunction with a recursive partitioning computer algorithm, boosted trees, to develop a prediction heuristic for identifying individuals with ADHD. Results of the study demonstrate that this method is able to do so with accuracy rates of over 95 %, much higher than the popular logistic regression model against which it was compared. Implications of these results for practice are provided.

ETHNOPRED: a novel machine learning method for accurate continental and sub-continental ancestry identification and population stratification correction

PubMed Central

2013-01-01

Background Population stratification is a systematic difference in allele frequencies between subpopulations. This can lead to spurious association findings in the case–control genome wide association studies (GWASs) used to identify single nucleotide polymorphisms (SNPs) associated with disease-linked phenotypes. Methods such as self-declared ancestry, ancestry informative markers, genomic control, structured association, and principal component analysis are used to assess and correct population stratification but each has limitations. We provide an alternative technique to address population stratification. Results We propose a novel machine learning method, ETHNOPRED, which uses the genotype and ethnicity data from the HapMap project to learn ensembles of disjoint decision trees, capable of accurately predicting an individual’s continental and sub-continental ancestry. To predict an individual’s continental ancestry, ETHNOPRED produced an ensemble of 3 decision trees involving a total of 10 SNPs, with 10-fold cross validation accuracy of 100% using HapMap II dataset. We extended this model to involve 29 disjoint decision trees over 149 SNPs, and showed that this ensemble has an accuracy of ≥ 99.9%, even if some of those 149 SNP values were missing. On an independent dataset, predominantly of Caucasian origin, our continental classifier showed 96.8% accuracy and improved genomic control’s λ from 1.22 to 1.11. We next used the HapMap III dataset to learn classifiers to distinguish European subpopulations (North-Western vs. Southern), East Asian subpopulations (Chinese vs. Japanese), African subpopulations (Eastern vs. Western), North American subpopulations (European vs. Chinese vs. African vs. Mexican vs. Indian), and Kenyan subpopulations (Luhya vs. Maasai). In these cases, ETHNOPRED produced ensembles of 3, 39, 21, 11, and 25 disjoint decision trees, respectively involving 31, 502, 526, 242 and 271 SNPs, with 10-fold cross validation accuracy of 86.5% ± 2.4%, 95.6% ± 3.9%, 95.6% ± 2.1%, 98.3% ± 2.0%, and 95.9% ± 1.5%. However, ETHNOPRED was unable to produce a classifier that can accurately distinguish Chinese in Beijing vs. Chinese in Denver. Conclusions ETHNOPRED is a novel technique for producing classifiers that can identify an individual’s continental and sub-continental heritage, based on a small number of SNPs. We show that its learned classifiers are simple, cost-efficient, accurate, transparent, flexible, fast, applicable to large scale GWASs, and robust to missing values. PMID:23432980

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.

Diagnostic and Remedial Learning Strategy Based on Conceptual Graphs

ERIC Educational Resources Information Center

Jong, BinShyan; Lin, TsongWuu; Wu, YuLung; Chan, Teyi

2004-01-01

Numerous scholars have applied conceptual graphs for explanatory purposes. This study devised the Remedial-Instruction Decisive path (RID path) algorithm for diagnosing individual student learning situation. This study focuses on conceptual graphs. According to the concepts learned by students and the weight values of relations among these…

Machine Learning Techniques for Prediction of Early Childhood Obesity.

PubMed

Dugan, T M; Mukhopadhyay, S; Carroll, A; Downs, S

2015-01-01

This paper aims to predict childhood obesity after age two, using only data collected prior to the second birthday by a clinical decision support system called CHICA. Analyses of six different machine learning methods: RandomTree, RandomForest, J48, ID3, Naïve Bayes, and Bayes trained on CHICA data show that an accurate, sensitive model can be created. Of the methods analyzed, the ID3 model trained on the CHICA dataset proved the best overall performance with accuracy of 85% and sensitivity of 89%. Additionally, the ID3 model had a positive predictive value of 84% and a negative predictive value of 88%. The structure of the tree also gives insight into the strongest predictors of future obesity in children. Many of the strongest predictors seen in the ID3 modeling of the CHICA dataset have been independently validated in the literature as correlated with obesity, thereby supporting the validity of the model. This study demonstrated that data from a production clinical decision support system can be used to build an accurate machine learning model to predict obesity in children after age two.

Relabeling exchange method (REM) for learning in neural networks

NASA Astrophysics Data System (ADS)

Wu, Wen; Mammone, Richard J.

1994-02-01

The supervised training of neural networks require the use of output labels which are usually arbitrarily assigned. In this paper it is shown that there is a significant difference in the rms error of learning when `optimal' label assignment schemes are used. We have investigated two efficient random search algorithms to solve the relabeling problem: the simulated annealing and the genetic algorithm. However, we found them to be computationally expensive. Therefore we shall introduce a new heuristic algorithm called the Relabeling Exchange Method (REM) which is computationally more attractive and produces optimal performance. REM has been used to organize the optimal structure for multi-layered perceptrons and neural tree networks. The method is a general one and can be implemented as a modification to standard training algorithms. The motivation of the new relabeling strategy is based on the present interpretation of dyslexia as an encoding problem.

Equilibrium point control of a monkey arm simulator by a fast learning tree structured artificial neural network.

PubMed

Dornay, M; Sanger, T D

1993-01-01

A planar 17 muscle model of the monkey's arm based on realistic biomechanical measurements was simulated on a Symbolics Lisp Machine. The simulator implements the equilibrium point hypothesis for the control of arm movements. Given initial and final desired positions, it generates a minimum-jerk desired trajectory of the hand and uses the backdriving algorithm to determine an appropriate sequence of motor commands to the muscles (Flash 1987; Mussa-Ivaldi et al. 1991; Dornay 1991b). These motor commands specify a temporal sequence of stable (attractive) equilibrium positions which lead to the desired hand movement. A strong disadvantage of the simulator is that it has no memory of previous computations. Determining the desired trajectory using the minimum-jerk model is instantaneous, but the laborious backdriving algorithm is slow, and can take up to one hour for some trajectories. The complexity of the required computations makes it a poor model for biological motor control. We propose a computationally simpler and more biologically plausible method for control which achieves the benefits of the backdriving algorithm. A fast learning, tree-structured network (Sanger 1991c) was trained to remember the knowledge obtained by the backdriving algorithm. The neural network learned the nonlinear mapping from a 2-dimensional cartesian planar hand position (x,y) to a 17-dimensional motor command space (u1, . . ., u17). Learning 20 training trajectories, each composed of 26 sample points [[x,y], [u1, . . ., u17] took only 20 min on a Sun-4 Sparc workstation. After the learning stage, new, untrained test trajectories as well as the original trajectories of the hand were given to the neural network as input. The network calculated the required motor commands for these movements. The resulting movements were close to the desired ones for both the training and test cases.

Comparisons between physics-based, engineering, and statistical learning models for outdoor sound propagation.

PubMed

Hart, Carl R; Reznicek, Nathan J; Wilson, D Keith; Pettit, Chris L; Nykaza, Edward T

2016-05-01

Many outdoor sound propagation models exist, ranging from highly complex physics-based simulations to simplified engineering calculations, and more recently, highly flexible statistical learning methods. Several engineering and statistical learning models are evaluated by using a particular physics-based model, namely, a Crank-Nicholson parabolic equation (CNPE), as a benchmark. Narrowband transmission loss values predicted with the CNPE, based upon a simulated data set of meteorological, boundary, and source conditions, act as simulated observations. In the simulated data set sound propagation conditions span from downward refracting to upward refracting, for acoustically hard and soft boundaries, and low frequencies. Engineering models used in the comparisons include the ISO 9613-2 method, Harmonoise, and Nord2000 propagation models. Statistical learning methods used in the comparisons include bagged decision tree regression, random forest regression, boosting regression, and artificial neural network models. Computed skill scores are relative to sound propagation in a homogeneous atmosphere over a rigid ground. Overall skill scores for the engineering noise models are 0.6%, -7.1%, and 83.8% for the ISO 9613-2, Harmonoise, and Nord2000 models, respectively. Overall skill scores for the statistical learning models are 99.5%, 99.5%, 99.6%, and 99.6% for bagged decision tree, random forest, boosting, and artificial neural network regression models, respectively.

Instruction-matrix-based genetic programming.

PubMed

Li, Gang; Wang, Jin Feng; Lee, Kin Hong; Leung, Kwong-Sak

2008-08-01

In genetic programming (GP), evolving tree nodes separately would reduce the huge solution space. However, tree nodes are highly interdependent with respect to their fitness. In this paper, we propose a new GP framework, namely, instruction-matrix (IM)-based GP (IMGP), to handle their interactions. IMGP maintains an IM to evolve tree nodes and subtrees separately. IMGP extracts program trees from an IM and updates the IM with the information of the extracted program trees. As the IM actually keeps most of the information of the schemata of GP and evolves the schemata directly, IMGP is effective and efficient. Our experimental results on benchmark problems have verified that IMGP is not only better than those of canonical GP in terms of the qualities of the solutions and the number of program evaluations, but they are also better than some of the related GP algorithms. IMGP can also be used to evolve programs for classification problems. The classifiers obtained have higher classification accuracies than four other GP classification algorithms on four benchmark classification problems. The testing errors are also comparable to or better than those obtained with well-known classifiers. Furthermore, an extended version, called condition matrix for rule learning, has been used successfully to handle multiclass classification problems.

A comparison between skeleton and bounding box models for falling direction recognition

NASA Astrophysics Data System (ADS)

Narupiyakul, Lalita; Srisrisawang, Nitikorn

2017-12-01

Falling is an injury that can lead to a serious medical condition in every range of the age of people. However, in the case of elderly, the risk of serious injury is much higher. Due to the fact that one way of preventing serious injury is to treat the fallen person as soon as possible, several works attempted to implement different algorithms to recognize the fall. Our work compares the performance of two models based on features extraction: (i) Body joint data (Skeleton Data) which are the joint's positions in 3 axes and (ii) Bounding box (Box-size Data) covering all body joints. Machine learning algorithms that were chosen are Decision Tree (DT), Naïve Bayes (NB), K-nearest neighbors (KNN), Linear discriminant analysis (LDA), Voting Classification (VC), and Gradient boosting (GB). The results illustrate that the models trained with Skeleton data are performed far better than those trained with Box-size data (with an average accuracy of 94-81% and 80-75%, respectively). KNN shows the best performance in both Body joint model and Bounding box model. In conclusion, KNN with Body joint model performs the best among the others.

11.2 YIP Human In the Loop Statistical RelationalLearners

DTIC Science & Technology

2017-10-23

learning formalisms including inverse reinforcement learning [4] and statistical relational learning [7, 5, 8]. We have also applied our algorithms in...one introduced for label preferences. 4 Figure 2: Active Advice Seeking for Inverse Reinforcement Learning. active advice seeking is in selecting the...learning tasks. 1.2.1 Sequential Decision-Making Our previous work on advice for inverse reinforcement learning (IRL) defined advice as action

Using PPI network autocorrelation in hierarchical multi-label classification trees for gene function prediction.

PubMed

Stojanova, Daniela; Ceci, Michelangelo; Malerba, Donato; Dzeroski, Saso

2013-09-26

Ontologies and catalogs of gene functions, such as the Gene Ontology (GO) and MIPS-FUN, assume that functional classes are organized hierarchically, that is, general functions include more specific ones. This has recently motivated the development of several machine learning algorithms for gene function prediction that leverages on this hierarchical organization where instances may belong to multiple classes. In addition, it is possible to exploit relationships among examples, since it is plausible that related genes tend to share functional annotations. Although these relationships have been identified and extensively studied in the area of protein-protein interaction (PPI) networks, they have not received much attention in hierarchical and multi-class gene function prediction. Relations between genes introduce autocorrelation in functional annotations and violate the assumption that instances are independently and identically distributed (i.i.d.), which underlines most machine learning algorithms. Although the explicit consideration of these relations brings additional complexity to the learning process, we expect substantial benefits in predictive accuracy of learned classifiers. This article demonstrates the benefits (in terms of predictive accuracy) of considering autocorrelation in multi-class gene function prediction. We develop a tree-based algorithm for considering network autocorrelation in the setting of Hierarchical Multi-label Classification (HMC). We empirically evaluate the proposed algorithm, called NHMC (Network Hierarchical Multi-label Classification), on 12 yeast datasets using each of the MIPS-FUN and GO annotation schemes and exploiting 2 different PPI networks. The results clearly show that taking autocorrelation into account improves the predictive performance of the learned models for predicting gene function. Our newly developed method for HMC takes into account network information in the learning phase: When used for gene function prediction in the context of PPI networks, the explicit consideration of network autocorrelation increases the predictive performance of the learned models. Overall, we found that this holds for different gene features/ descriptions, functional annotation schemes, and PPI networks: Best results are achieved when the PPI network is dense and contains a large proportion of function-relevant interactions.

Modeling flash floods in ungauged mountain catchments of China: A decision tree learning approach for parameter regionalization

NASA Astrophysics Data System (ADS)

Ragettli, S.; Zhou, J.; Wang, H.; Liu, C.; Guo, L.

2017-12-01

Flash floods in small mountain catchments are one of the most frequent causes of loss of life and property from natural hazards in China. Hydrological models can be a useful tool for the anticipation of these events and the issuing of timely warnings. One of the main challenges of setting up such a system is finding appropriate model parameter values for ungauged catchments. Previous studies have shown that the transfer of parameter sets from hydrologically similar gauged catchments is one of the best performing regionalization methods. However, a remaining key issue is the identification of suitable descriptors of similarity. In this study, we use decision tree learning to explore parameter set transferability in the full space of catchment descriptors. For this purpose, a semi-distributed rainfall-runoff model is set up for 35 catchments in ten Chinese provinces. Hourly runoff data from in total 858 storm events are used to calibrate the model and to evaluate the performance of parameter set transfers between catchments. We then present a novel technique that uses the splitting rules of classification and regression trees (CART) for finding suitable donor catchments for ungauged target catchments. The ability of the model to detect flood events in assumed ungauged catchments is evaluated in series of leave-one-out tests. We show that CART analysis increases the probability of detection of 10-year flood events in comparison to a conventional measure of physiographic-climatic similarity by up to 20%. Decision tree learning can outperform other regionalization approaches because it generates rules that optimally consider spatial proximity and physical similarity. Spatial proximity can be used as a selection criteria but is skipped in the case where no similar gauged catchments are in the vicinity. We conclude that the CART regionalization concept is particularly suitable for implementation in sparsely gauged and topographically complex environments where a proximity-based regionalization concept is not applicable.

Efficient discovery of risk patterns in medical data.

PubMed

Li, Jiuyong; Fu, Ada Wai-chee; Fahey, Paul

2009-01-01

This paper studies a problem of efficiently discovering risk patterns in medical data. Risk patterns are defined by a statistical metric, relative risk, which has been widely used in epidemiological research. To avoid fruitless search in the complete exploration of risk patterns, we define optimal risk pattern set to exclude superfluous patterns, i.e. complicated patterns with lower relative risk than their corresponding simpler form patterns. We prove that mining optimal risk pattern sets conforms an anti-monotone property that supports an efficient mining algorithm. We propose an efficient algorithm for mining optimal risk pattern sets based on this property. We also propose a hierarchical structure to present discovered patterns for the easy perusal by domain experts. The proposed approach is compared with two well-known rule discovery methods, decision tree and association rule mining approaches on benchmark data sets and applied to a real world application. The proposed method discovers more and better quality risk patterns than a decision tree approach. The decision tree method is not designed for such applications and is inadequate for pattern exploring. The proposed method does not discover a large number of uninteresting superfluous patterns as an association mining approach does. The proposed method is more efficient than an association rule mining method. A real world case study shows that the method reveals some interesting risk patterns to medical practitioners. The proposed method is an efficient approach to explore risk patterns. It quickly identifies cohorts of patients that are vulnerable to a risk outcome from a large data set. The proposed method is useful for exploratory study on large medical data to generate and refine hypotheses. The method is also useful for designing medical surveillance systems.

A study of malware detection on smart mobile devices

NASA Astrophysics Data System (ADS)

Yu, Wei; Zhang, Hanlin; Xu, Guobin

2013-05-01

The growing in use of smart mobile devices for everyday applications has stimulated the spread of mobile malware, especially on popular mobile platforms. As a consequence, malware detection becomes ever more critical in sustaining the mobile market and providing a better user experience. In this paper, we review the existing malware and detection schemes. Using real-world malware samples with known signatures, we evaluate four popular commercial anti-virus tools and our data shows that these tools can achieve high detection accuracy. To deal with the new malware with unknown signatures, we study the anomaly based detection using decision tree algorithm. We evaluate the effectiveness of our detection scheme using malware and legitimate software samples. Our data shows that the detection scheme using decision tree can achieve a detection rate up to 90% and a false positive rate as low as 10%.

Heart failure analysis dashboard for patient's remote monitoring combining multiple artificial intelligence technologies.

PubMed

Guidi, G; Pettenati, M C; Miniati, R; Iadanza, E

2012-01-01

In this paper we describe an Heart Failure analysis Dashboard that, combined with a handy device for the automatic acquisition of a set of patient's clinical parameters, allows to support telemonitoring functions. The Dashboard's intelligent core is a Computer Decision Support System designed to assist the clinical decision of non-specialist caring personnel, and it is based on three functional parts: Diagnosis, Prognosis, and Follow-up management. Four Artificial Intelligence-based techniques are compared for providing diagnosis function: a Neural Network, a Support Vector Machine, a Classification Tree and a Fuzzy Expert System whose rules are produced by a Genetic Algorithm. State of the art algorithms are used to support a score-based prognosis function. The patient's Follow-up is used to refine the diagnosis.

Systematic methods for knowledge acquisition and expert system development

NASA Technical Reports Server (NTRS)

Belkin, Brenda L.; Stengel, Robert F.

1991-01-01

Nine cooperating rule-based systems, collectively called AUTOCREW which were designed to automate functions and decisions associated with a combat aircraft's subsystems, are discussed. The organization of tasks within each system is described; performance metrics were developed to evaluate the workload of each rule base and to assess the cooperation between the rule bases. Simulation and comparative workload results for two mission scenarios are given. The scenarios are inbound surface-to-air-missile attack on the aircraft and pilot incapacitation. The methodology used to develop the AUTOCREW knowledge bases is summarized. Issues involved in designing the navigation sensor selection expert in AUTOCREW's NAVIGATOR knowledge base are discussed in detail. The performance of seven navigation systems aiding a medium-accuracy INS was investigated using Kalman filter covariance analyses. A navigation sensor management (NSM) expert system was formulated from covariance simulation data using the analysis of variance (ANOVA) method and the ID3 algorithm. ANOVA results show that statistically different position accuracies are obtained when different navaids are used, the number of navaids aiding the INS is varied, the aircraft's trajectory is varied, and the performance history is varied. The ID3 algorithm determines the NSM expert's classification rules in the form of decision trees. The performance of these decision trees was assessed on two arbitrary trajectories, and the results demonstrate that the NSM expert adapts to new situations and provides reasonable estimates of the expected hybrid performance.

Classification of Learning Styles in Virtual Learning Environment Using J48 Decision Tree

ERIC Educational Resources Information Center

Maaliw, Renato R. III; Ballera, Melvin A.

2017-01-01

The usage of data mining has dramatically increased over the past few years and the education sector is leveraging this field in order to analyze and gain intuitive knowledge in terms of the vast accumulated data within its confines. The primary objective of this study is to compare the results of different classification techniques such as Naïve…

Exact Algorithms for Duplication-Transfer-Loss Reconciliation with Non-Binary Gene Trees.

PubMed

Kordi, Misagh; Bansal, Mukul S

2017-06-01

Duplication-Transfer-Loss (DTL) reconciliation is a powerful method for studying gene family evolution in the presence of horizontal gene transfer. DTL reconciliation seeks to reconcile gene trees with species trees by postulating speciation, duplication, transfer, and loss events. Efficient algorithms exist for finding optimal DTL reconciliations when the gene tree is binary. In practice, however, gene trees are often non-binary due to uncertainty in the gene tree topologies, and DTL reconciliation with non-binary gene trees is known to be NP-hard. In this paper, we present the first exact algorithms for DTL reconciliation with non-binary gene trees. Specifically, we (i) show that the DTL reconciliation problem for non-binary gene trees is fixed-parameter tractable in the maximum degree of the gene tree, (ii) present an exponential-time, but in-practice efficient, algorithm to track and enumerate all optimal binary resolutions of a non-binary input gene tree, and (iii) apply our algorithms to a large empirical data set of over 4700 gene trees from 100 species to study the impact of gene tree uncertainty on DTL-reconciliation and to demonstrate the applicability and utility of our algorithms. The new techniques and algorithms introduced in this paper will help biologists avoid incorrect evolutionary inferences caused by gene tree uncertainty.

Optimization of matrix tablets controlled drug release using Elman dynamic neural networks and decision trees.

PubMed

Petrović, Jelena; Ibrić, Svetlana; Betz, Gabriele; Đurić, Zorica

2012-05-30

The main objective of the study was to develop artificial intelligence methods for optimization of drug release from matrix tablets regardless of the matrix type. Static and dynamic artificial neural networks of the same topology were developed to model dissolution profiles of different matrix tablets types (hydrophilic/lipid) using formulation composition, compression force used for tableting and tablets porosity and tensile strength as input data. Potential application of decision trees in discovering knowledge from experimental data was also investigated. Polyethylene oxide polymer and glyceryl palmitostearate were used as matrix forming materials for hydrophilic and lipid matrix tablets, respectively whereas selected model drugs were diclofenac sodium and caffeine. Matrix tablets were prepared by direct compression method and tested for in vitro dissolution profiles. Optimization of static and dynamic neural networks used for modeling of drug release was performed using Monte Carlo simulations or genetic algorithms optimizer. Decision trees were constructed following discretization of data. Calculated difference (f(1)) and similarity (f(2)) factors for predicted and experimentally obtained dissolution profiles of test matrix tablets formulations indicate that Elman dynamic neural networks as well as decision trees are capable of accurate predictions of both hydrophilic and lipid matrix tablets dissolution profiles. Elman neural networks were compared to most frequently used static network, Multi-layered perceptron, and superiority of Elman networks have been demonstrated. Developed methods allow simple, yet very precise way of drug release predictions for both hydrophilic and lipid matrix tablets having controlled drug release. Copyright © 2012 Elsevier B.V. All rights reserved.

Learning relative values in the striatum induces violations of normative decision making

PubMed Central

Klein, Tilmann A.; Ullsperger, Markus; Jocham, Gerhard

2017-01-01

To decide optimally between available options, organisms need to learn the values associated with these options. Reinforcement learning models offer a powerful explanation of how these values are learnt from experience. However, human choices often violate normative principles. We suggest that seemingly counterintuitive decisions may arise as a natural consequence of the learning mechanisms deployed by humans. Here, using fMRI and a novel behavioural task, we show that, when suddenly switched to novel choice contexts, participants’ choices are incongruent with values learnt by standard learning algorithms. Instead, behaviour is compatible with the decisions of an agent learning how good an option is relative to an option with which it had previously been paired. Striatal activity exhibits the characteristics of a prediction error used to update such relative option values. Our data suggest that choices can be biased by a tendency to learn option values with reference to the available alternatives. PMID:28631734

Model-Based Reinforcement Learning under Concurrent Schedules of Reinforcement in Rodents

ERIC Educational Resources Information Center

Huh, Namjung; Jo, Suhyun; Kim, Hoseok; Sul, Jung Hoon; Jung, Min Whan

2009-01-01

Reinforcement learning theories postulate that actions are chosen to maximize a long-term sum of positive outcomes based on value functions, which are subjective estimates of future rewards. In simple reinforcement learning algorithms, value functions are updated only by trial-and-error, whereas they are updated according to the decision-maker's…

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.

Introducing StatHand: A Cross-Platform Mobile Application to Support Students' Statistical Decision Making.

PubMed

Allen, Peter J; Roberts, Lynne D; Baughman, Frank D; Loxton, Natalie J; Van Rooy, Dirk; Rock, Adam J; Finlay, James

2016-01-01

Although essential to professional competence in psychology, quantitative research methods are a known area of weakness for many undergraduate psychology students. Students find selecting appropriate statistical tests and procedures for different types of research questions, hypotheses and data types particularly challenging, and these skills are not often practiced in class. Decision trees (a type of graphic organizer) are known to facilitate this decision making process, but extant trees have a number of limitations. Furthermore, emerging research suggests that mobile technologies offer many possibilities for facilitating learning. It is within this context that we have developed StatHand, a free cross-platform application designed to support students' statistical decision making. Developed with the support of the Australian Government Office for Learning and Teaching, StatHand guides users through a series of simple, annotated questions to help them identify a statistical test or procedure appropriate to their circumstances. It further offers the guidance necessary to run these tests and procedures, then interpret and report their results. In this Technology Report we will overview the rationale behind StatHand, before describing the feature set of the application. We will then provide guidelines for integrating StatHand into the research methods curriculum, before concluding by outlining our road map for the ongoing development and evaluation of StatHand.

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

Recursive algorithms for phylogenetic tree counting.

PubMed

Gavryushkina, Alexandra; Welch, David; Drummond, Alexei J

2013-10-28

In Bayesian phylogenetic inference we are interested in distributions over a space of trees. The number of trees in a tree space is an important characteristic of the space and is useful for specifying prior distributions. When all samples come from the same time point and no prior information available on divergence times, the tree counting problem is easy. However, when fossil evidence is used in the inference to constrain the tree or data are sampled serially, new tree spaces arise and counting the number of trees is more difficult. We describe an algorithm that is polynomial in the number of sampled individuals for counting of resolutions of a constraint tree assuming that the number of constraints is fixed. We generalise this algorithm to counting resolutions of a fully ranked constraint tree. We describe a quadratic algorithm for counting the number of possible fully ranked trees on n sampled individuals. We introduce a new type of tree, called a fully ranked tree with sampled ancestors, and describe a cubic time algorithm for counting the number of such trees on n sampled individuals. These algorithms should be employed for Bayesian Markov chain Monte Carlo inference when fossil data are included or data are serially sampled.

Proposal of a Clinical Decision Tree Algorithm Using Factors Associated with Severe Dengue Infection.

PubMed

Tamibmaniam, Jayashamani; Hussin, Narwani; Cheah, Wee Kooi; Ng, Kee Sing; Muninathan, Prema

2016-01-01

WHO's new classification in 2009: dengue with or without warning signs and severe dengue, has necessitated large numbers of admissions to hospitals of dengue patients which in turn has been imposing a huge economical and physical burden on many hospitals around the globe, particularly South East Asia and Malaysia where the disease has seen a rapid surge in numbers in recent years. Lack of a simple tool to differentiate mild from life threatening infection has led to unnecessary hospitalization of dengue patients. We conducted a single-centre, retrospective study involving serologically confirmed dengue fever patients, admitted in a single ward, in Hospital Kuala Lumpur, Malaysia. Data was collected for 4 months from February to May 2014. Socio demography, co-morbidity, days of illness before admission, symptoms, warning signs, vital signs and laboratory result were all recorded. Descriptive statistics was tabulated and simple and multiple logistic regression analysis was done to determine significant risk factors associated with severe dengue. 657 patients with confirmed dengue were analysed, of which 59 (9.0%) had severe dengue. Overall, the commonest warning sign were vomiting (36.1%) and abdominal pain (32.1%). Previous co-morbid, vomiting, diarrhoea, pleural effusion, low systolic blood pressure, high haematocrit, low albumin and high urea were found as significant risk factors for severe dengue using simple logistic regression. However the significant risk factors for severe dengue with multiple logistic regressions were only vomiting, pleural effusion, and low systolic blood pressure. Using those 3 risk factors, we plotted an algorithm for predicting severe dengue. When compared to the classification of severe dengue based on the WHO criteria, the decision tree algorithm had a sensitivity of 0.81, specificity of 0.54, positive predictive value of 0.16 and negative predictive of 0.96. The decision tree algorithm proposed in this study showed high sensitivity and NPV in predicting patients with severe dengue that may warrant admission. This tool upon further validation study can be used to help clinicians decide on further managing a patient upon first encounter. It also will have a substantial impact on health resources as low risk patients can be managed as outpatients hence reserving the scarce hospital beds and medical resources for other patients in need.

SDIA: A dynamic situation driven information fusion algorithm for cloud environment

NASA Astrophysics Data System (ADS)

Guo, Shuhang; Wang, Tong; Wang, Jian

2017-09-01

Information fusion is an important issue in information integration domain. In order to form an extensive information fusion technology under the complex and diverse situations, a new information fusion algorithm is proposed. Firstly, a fuzzy evaluation model of tag utility was proposed that can be used to count the tag entropy. Secondly, a ubiquitous situation tag tree model is proposed to define multidimensional structure of information situation. Thirdly, the similarity matching between the situation models is classified into three types: the tree inclusion, the tree embedding, and the tree compatibility. Next, in order to reduce the time complexity of the tree compatible matching algorithm, a fast and ordered tree matching algorithm is proposed based on the node entropy, which is used to support the information fusion by ubiquitous situation. Since the algorithm revolve from the graph theory of disordered tree matching algorithm, it can improve the information fusion present recall rate and precision rate in the situation. The information fusion algorithm is compared with the star and the random tree matching algorithm, and the difference between the three algorithms is analyzed in the view of isomorphism, which proves the innovation and applicability of the algorithm.

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.

MLViS: A Web Tool for Machine Learning-Based Virtual Screening in Early-Phase of Drug Discovery and Development

PubMed Central

Korkmaz, Selcuk; Zararsiz, Gokmen; Goksuluk, Dincer

2015-01-01

Virtual screening is an important step in early-phase of drug discovery process. Since there are thousands of compounds, this step should be both fast and effective in order to distinguish drug-like and nondrug-like molecules. Statistical machine learning methods are widely used in drug discovery studies for classification purpose. Here, we aim to develop a new tool, which can classify molecules as drug-like and nondrug-like based on various machine learning methods, including discriminant, tree-based, kernel-based, ensemble and other algorithms. To construct this tool, first, performances of twenty-three different machine learning algorithms are compared by ten different measures, then, ten best performing algorithms have been selected based on principal component and hierarchical cluster analysis results. Besides classification, this application has also ability to create heat map and dendrogram for visual inspection of the molecules through hierarchical cluster analysis. Moreover, users can connect the PubChem database to download molecular information and to create two-dimensional structures of compounds. This application is freely available through www.biosoft.hacettepe.edu.tr/MLViS/. PMID:25928885

Coalescent-based species tree inference from gene tree topologies under incomplete lineage sorting by maximum likelihood.

PubMed

Wu, Yufeng

2012-03-01

Incomplete lineage sorting can cause incongruence between the phylogenetic history of genes (the gene tree) and that of the species (the species tree), which can complicate the inference of phylogenies. In this article, I present a new coalescent-based algorithm for species tree inference with maximum likelihood. I first describe an improved method for computing the probability of a gene tree topology given a species tree, which is much faster than an existing algorithm by Degnan and Salter (2005). Based on this method, I develop a practical algorithm that takes a set of gene tree topologies and infers species trees with maximum likelihood. This algorithm searches for the best species tree by starting from initial species trees and performing heuristic search to obtain better trees with higher likelihood. This algorithm, called STELLS (which stands for Species Tree InfErence with Likelihood for Lineage Sorting), has been implemented in a program that is downloadable from the author's web page. The simulation results show that the STELLS algorithm is more accurate than an existing maximum likelihood method for many datasets, especially when there is noise in gene trees. I also show that the STELLS algorithm is efficient and can be applied to real biological datasets. © 2011 The Author. Evolution© 2011 The Society for the Study of Evolution.

UAVs Task and Motion Planning in the Presence of Obstacles and Prioritized Targets

PubMed Central

Gottlieb, Yoav; Shima, Tal

2015-01-01

The intertwined task assignment and motion planning problem of assigning a team of fixed-winged unmanned aerial vehicles to a set of prioritized targets in an environment with obstacles is addressed. It is assumed that the targets’ locations and initial priorities are determined using a network of unattended ground sensors used to detect potential threats at restricted zones. The targets are characterized by a time-varying level of importance, and timing constraints must be fulfilled before a vehicle is allowed to visit a specific target. It is assumed that the vehicles are carrying body-fixed sensors and, thus, are required to approach a designated target while flying straight and level. The fixed-winged aerial vehicles are modeled as Dubins vehicles, i.e., having a constant speed and a minimum turning radius constraint. The investigated integrated problem of task assignment and motion planning is posed in the form of a decision tree, and two search algorithms are proposed: an exhaustive algorithm that improves over run time and provides the minimum cost solution, encoded in the tree, and a greedy algorithm that provides a quick feasible solution. To satisfy the target’s visitation timing constraint, a path elongation motion planning algorithm amidst obstacles is provided. Using simulations, the performance of the algorithms is compared, evaluated and exemplified. PMID:26610522

In silico prediction of Tetrahymena pyriformis toxicity for diverse industrial chemicals with substructure pattern recognition and machine learning methods.

PubMed

Cheng, Feixiong; Shen, Jie; Yu, Yue; Li, Weihua; Liu, Guixia; Lee, Philip W; Tang, Yun

2011-03-01

There is an increasing need for the rapid safety assessment of chemicals by both industries and regulatory agencies throughout the world. In silico techniques are practical alternatives in the environmental hazard assessment. It is especially true to address the persistence, bioaccumulative and toxicity potentials of organic chemicals. Tetrahymena pyriformis toxicity is often used as a toxic endpoint. In this study, 1571 diverse unique chemicals were collected from the literature and composed of the largest diverse data set for T. pyriformis toxicity. Classification predictive models of T. pyriformis toxicity were developed by substructure pattern recognition and different machine learning methods, including support vector machine (SVM), C4.5 decision tree, k-nearest neighbors and random forest. The results of a 5-fold cross-validation showed that the SVM method performed better than other algorithms. The overall predictive accuracies of the SVM classification model with radial basis functions kernel was 92.2% for the 5-fold cross-validation and 92.6% for the external validation set, respectively. Furthermore, several representative substructure patterns for characterizing T. pyriformis toxicity were also identified via the information gain analysis methods. Copyright © 2010 Elsevier Ltd. All rights reserved.

Evolutionary image simplification for lung nodule classification with convolutional neural networks.

PubMed

Lückehe, Daniel; von Voigt, Gabriele

2018-05-29

Understanding decisions of deep learning techniques is important. Especially in the medical field, the reasons for a decision in a classification task are as crucial as the pure classification results. In this article, we propose a new approach to compute relevant parts of a medical image. Knowing the relevant parts makes it easier to understand decisions. In our approach, a convolutional neural network is employed to learn structures of images of lung nodules. Then, an evolutionary algorithm is applied to compute a simplified version of an unknown image based on the learned structures by the convolutional neural network. In the simplified version, irrelevant parts are removed from the original image. In the results, we show simplified images which allow the observer to focus on the relevant parts. In these images, more than 50% of the pixels are simplified. The simplified pixels do not change the meaning of the images based on the learned structures by the convolutional neural network. An experimental analysis shows the potential of the approach. Besides the examples of simplified images, we analyze the run time development. Simplified images make it easier to focus on relevant parts and to find reasons for a decision. The combination of an evolutionary algorithm employing a learned convolutional neural network is well suited for the simplification task. From a research perspective, it is interesting which areas of the images are simplified and which parts are taken as relevant.

Asynchronous Gossip for Averaging and Spectral Ranking

NASA Astrophysics Data System (ADS)

Borkar, Vivek S.; Makhijani, Rahul; Sundaresan, Rajesh

2014-08-01

We consider two variants of the classical gossip algorithm. The first variant is a version of asynchronous stochastic approximation. We highlight a fundamental difficulty associated with the classical asynchronous gossip scheme, viz., that it may not converge to a desired average, and suggest an alternative scheme based on reinforcement learning that has guaranteed convergence to the desired average. We then discuss a potential application to a wireless network setting with simultaneous link activation constraints. The second variant is a gossip algorithm for distributed computation of the Perron-Frobenius eigenvector of a nonnegative matrix. While the first variant draws upon a reinforcement learning algorithm for an average cost controlled Markov decision problem, the second variant draws upon a reinforcement learning algorithm for risk-sensitive control. We then discuss potential applications of the second variant to ranking schemes, reputation networks, and principal component analysis.

A Comparison of different learning models used in Data Mining for Medical Data

NASA Astrophysics Data System (ADS)

Srimani, P. K.; Koti, Manjula Sanjay

2011-12-01

The present study aims at investigating the different Data mining learning models for different medical data sets and to give practical guidelines to select the most appropriate algorithm for a specific medical data set. In practical situations, it is absolutely necessary to take decisions with regard to the appropriate models and parameters for diagnosis and prediction problems. Learning models and algorithms are widely implemented for rule extraction and the prediction of system behavior. In this paper, some of the well-known Machine Learning(ML) systems are investigated for different methods and are tested on five medical data sets. The practical criteria for evaluating different learning models are presented and the potential benefits of the proposed methodology for diagnosis and learning are suggested.

Bayesian Networks for Modeling Dredging Decisions

DTIC Science & Technology

2011-10-01

change scenarios. Arctic Expert elicitation Netica Bacon et al . 2002 Identify factors that might lead to a change in land use from farming to...tree) algorithms developed by Lauritzen and Spiegelhalter (1988) and Jensen et al . (1990). Statistical inference is simply the process of...causality when constructing a Bayesian network (Kjaerulff and Madsen 2008, Darwiche 2009, Marcot et al . 2006). A knowledge representation approach is the

Cosmic string detection with tree-based machine learning

NASA Astrophysics Data System (ADS)

Vafaei Sadr, A.; Farhang, M.; Movahed, S. M. S.; Bassett, B.; Kunz, M.

2018-07-01

We explore the use of random forest and gradient boosting, two powerful tree-based machine learning algorithms, for the detection of cosmic strings in maps of the cosmic microwave background (CMB), through their unique Gott-Kaiser-Stebbins effect on the temperature anisotropies. The information in the maps is compressed into feature vectors before being passed to the learning units. The feature vectors contain various statistical measures of the processed CMB maps that boost cosmic string detectability. Our proposed classifiers, after training, give results similar to or better than claimed detectability levels from other methods for string tension, Gμ. They can make 3σ detection of strings with Gμ ≳ 2.1 × 10-10 for noise-free, 0.9'-resolution CMB observations. The minimum detectable tension increases to Gμ ≳ 3.0 × 10-8 for a more realistic, CMB S4-like (II) strategy, improving over previous results.

Cosmic String Detection with Tree-Based Machine Learning

NASA Astrophysics Data System (ADS)

Vafaei Sadr, A.; Farhang, M.; Movahed, S. M. S.; Bassett, B.; Kunz, M.

2018-05-01

We explore the use of random forest and gradient boosting, two powerful tree-based machine learning algorithms, for the detection of cosmic strings in maps of the cosmic microwave background (CMB), through their unique Gott-Kaiser-Stebbins effect on the temperature anisotropies. The information in the maps is compressed into feature vectors before being passed to the learning units. The feature vectors contain various statistical measures of the processed CMB maps that boost cosmic string detectability. Our proposed classifiers, after training, give results similar to or better than claimed detectability levels from other methods for string tension, Gμ. They can make 3σ detection of strings with Gμ ≳ 2.1 × 10-10 for noise-free, 0.9΄-resolution CMB observations. The minimum detectable tension increases to Gμ ≳ 3.0 × 10-8 for a more realistic, CMB S4-like (II) strategy, improving over previous results.

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.

A decision tree-based on-line preventive control strategy for power system transient instability prevention

NASA Astrophysics Data System (ADS)

Xu, Yan; Dong, Zhao Yang; Zhang, Rui; Wong, Kit Po

2014-02-01

Maintaining transient stability is a basic requirement for secure power system operations. Preventive control deals with modifying the system operating point to withstand probable contingencies. In this article, a decision tree (DT)-based on-line preventive control strategy is proposed for transient instability prevention of power systems. Given a stability database, a distance-based feature estimation algorithm is first applied to identify the critical generators, which are then used as features to develop a DT. By interpreting the splitting rules of DT, preventive control is realised by formulating the rules in a standard optimal power flow model and solving it. The proposed method is transparent in control mechanism, on-line computation compatible and convenient to deal with multi-contingency. The effectiveness and efficiency of the method has been verified on New England 10-machine 39-bus test system.

Study on Ecological Risk Assessment of Guangxi Coastal Zone Based on 3s Technology

NASA Astrophysics Data System (ADS)

Zhong, Z.; Luo, H.; Ling, Z. Y.; Huang, Y.; Ning, W. Y.; Tang, Y. B.; Shao, G. Z.

2018-05-01

This paper takes Guangxi coastal zone as the study area, following the standards of land use type, divides the coastal zone of ecological landscape into seven kinds of natural wetland landscape types such as woodland, farmland, grassland, water, urban land and wetlands. Using TM data of 2000-2015 such 15 years, with the CART decision tree algorithm, for analysis the characteristic of types of landscape's remote sensing image and build decision tree rules of landscape classification to extract information classification. Analyzing of the evolution process of the landscape pattern in Guangxi coastal zone in nearly 15 years, we may understand the distribution characteristics and change rules. Combined with the natural disaster data, we use of landscape index and the related risk interference degree and construct ecological risk evaluation model in Guangxi coastal zone for ecological risk assessment results of Guangxi coastal zone.

Personalization algorithm for real-time activity recognition using PDA, wireless motion bands, and binary decision tree.

PubMed

Pärkkä, Juha; Cluitmans, Luc; Ermes, Miikka

2010-09-01

Inactive and sedentary lifestyle is a major problem in many industrialized countries today. Automatic recognition of type of physical activity can be used to show the user the distribution of his daily activities and to motivate him into more active lifestyle. In this study, an automatic activity-recognition system consisting of wireless motion bands and a PDA is evaluated. The system classifies raw sensor data into activity types online. It uses a decision tree classifier, which has low computational cost and low battery consumption. The classifier parameters can be personalized online by performing a short bout of an activity and by telling the system which activity is being performed. Data were collected with seven volunteers during five everyday activities: lying, sitting/standing, walking, running, and cycling. The online system can detect these activities with overall 86.6% accuracy and with 94.0% accuracy after classifier personalization.

An approach for automated fault diagnosis based on a fuzzy decision tree and boundary analysis of a reconstructed phase space.

PubMed

Aydin, Ilhan; Karakose, Mehmet; Akin, Erhan

2014-03-01

Although reconstructed phase space is one of the most powerful methods for analyzing a time series, it can fail in fault diagnosis of an induction motor when the appropriate pre-processing is not performed. Therefore, boundary analysis based a new feature extraction method in phase space is proposed for diagnosis of induction motor faults. The proposed approach requires the measurement of one phase current signal to construct the phase space representation. Each phase space is converted into an image, and the boundary of each image is extracted by a boundary detection algorithm. A fuzzy decision tree has been designed to detect broken rotor bars and broken connector faults. The results indicate that the proposed approach has a higher recognition rate than other methods on the same dataset. © 2013 ISA Published by ISA All rights reserved.

A Comparative Study to Predict Student’s Performance Using Educational Data Mining Techniques

NASA Astrophysics Data System (ADS)

Uswatun Khasanah, Annisa; Harwati

2017-06-01

Student’s performance prediction is essential to be conducted for a university to prevent student fail. Number of student drop out is one of parameter that can be used to measure student performance and one important point that must be evaluated in Indonesia university accreditation. Data Mining has been widely used to predict student’s performance, and data mining that applied in this field usually called as Educational Data Mining. This study conducted Feature Selection to select high influence attributes with student performance in Department of Industrial Engineering Universitas Islam Indonesia. Then, two popular classification algorithm, Bayesian Network and Decision Tree, were implemented and compared to know the best prediction result. The outcome showed that student’s attendance and GPA in the first semester were in the top rank from all Feature Selection methods, and Bayesian Network is outperforming Decision Tree since it has higher accuracy rate.

Neural Correlates of Temporal Credit Assignment in the Parietal Lobe

PubMed Central

Eisenberg, Ian; Gottlieb, Jacqueline

2014-01-01

Empirical studies of decision making have typically assumed that value learning is governed by time, such that a reward prediction error arising at a specific time triggers temporally-discounted learning for all preceding actions. However, in natural behavior, goals must be acquired through multiple actions, and each action can have different significance for the final outcome. As is recognized in computational research, carrying out multi-step actions requires the use of credit assignment mechanisms that focus learning on specific steps, but little is known about the neural correlates of these mechanisms. To investigate this question we recorded neurons in the monkey lateral intraparietal area (LIP) during a serial decision task where two consecutive eye movement decisions led to a final reward. The underlying decision trees were structured such that the two decisions had different relationships with the final reward, and the optimal strategy was to learn based on the final reward at one of the steps (the “F” step) but ignore changes in this reward at the remaining step (the “I” step). In two distinct contexts, the F step was either the first or the second in the sequence, controlling for effects of temporal discounting. We show that LIP neurons had the strongest value learning and strongest post-decision responses during the transition after the F step regardless of the serial position of this step. Thus, the neurons encode correlates of temporal credit assignment mechanisms that allocate learning to specific steps independently of temporal discounting. PMID:24523935

Do we face a fourth paradigm shift in medicine--algorithms in education?

PubMed

Eitel, F; Kanz, K G; Hortig, E; Tesche, A

2000-08-01

Medicine has evolved toward rationalization since the Enlightenment, favouring quantitative measures. Now, a paradigm shift toward control through formalization can be observed in health care whose structures and processes are subjected to increasing standardization. However, educational reforms and curricula do not yet adequately respond to this shift. The aim of this article is to describe innovative approaches in medical education for adapting to these changes. The study design is a descriptive case report relying on a literature review and on a reform project's evaluation. Concept mapping is used to graphically represent relationships among concepts, i.e. defined terms from educational literature. Definitions of 'concept map', 'guideline' and 'algorithm' are presented. A prototypical algorithm for organizational decision making in the project's instructional design is shown. Evaluation results of intrinsic learning motivation are demonstrated: intrinsic learning motivation depends upon students' perception of their competence exhibiting path coefficients varying from 0.42 to 0.51. Perception of competence varies with the type of learning environment. An innovative educational format, called 'evidence-based learning (EBL)' is deduced from these findings and described here. Effects of formalization consist of structuring decision making about implementation of different learning environments or about minimizing variance in teaching or learning. Unintended effects of formalization such as implementation problems and bureaucracy are discussed. Formalized tools for designing medical education are available. Specific instructional designs influence students' learning motivation. Concept maps are suitable for controlling educational quality, thus enabling the paradigm shift in medical education.

Policy Tree Optimization for Adaptive Management of Water Resources Systems

NASA Astrophysics Data System (ADS)

Herman, J. D.; Giuliani, M.

2016-12-01

Water resources systems must cope with irreducible uncertainty in supply and demand, requiring policy alternatives capable of adapting to a range of possible future scenarios. Recent studies have developed adaptive policies based on "signposts" or "tipping points", which are threshold values of indicator variables that signal a change in policy. However, there remains a need for a general method to optimize the choice of indicators and their threshold values in a way that is easily interpretable for decision makers. Here we propose a conceptual framework and computational algorithm to design adaptive policies as a tree structure (i.e., a hierarchical set of logical rules) using a simulation-optimization approach based on genetic programming. We demonstrate the approach using Folsom Reservoir, California as a case study, in which operating policies must balance the risk of both floods and droughts. Given a set of feature variables, such as reservoir level, inflow observations and forecasts, and time of year, the resulting policy defines the conditions under which flood control and water supply hedging operations should be triggered. Importantly, the tree-based rule sets are easy to interpret for decision making, and can be compared to historical operating policies to understand the adaptations needed under possible climate change scenarios. Several remaining challenges are discussed, including the empirical convergence properties of the method, and extensions to irreversible decisions such as infrastructure. Policy tree optimization, and corresponding open-source software, provide a generalizable, interpretable approach to designing adaptive policies under uncertainty for water resources systems.

Finding Frequent Closed Itemsets in Sliding Window in Linear Time

NASA Astrophysics Data System (ADS)

Chen, Junbo; Zhou, Bo; Chen, Lu; Wang, Xinyu; Ding, Yiqun

One of the most well-studied problems in data mining is computing the collection of frequent itemsets in large transactional databases. Since the introduction of the famous Apriori algorithm [14], many others have been proposed to find the frequent itemsets. Among such algorithms, the approach of mining closed itemsets has raised much interest in data mining community. The algorithms taking this approach include TITANIC [8], CLOSET+[6], DCI-Closed [4], FCI-Stream [3], GC-Tree [15], TGC-Tree [16] etc. Among these algorithms, FCI-Stream, GC-Tree and TGC-Tree are online algorithms work under sliding window environments. By the performance evaluation in [16], GC-Tree [15] is the fastest one. In this paper, an improved algorithm based on GC-Tree is proposed, the computational complexity of which is proved to be a linear combination of the average transaction size and the average closed itemset size. The algorithm is based on the essential theorem presented in Sect. 4.2. Empirically, the new algorithm is several orders of magnitude faster than the state of art algorithm, GC-Tree.

Hemodynamic and oxygen transport patterns for outcome prediction, therapeutic goals, and clinical algorithms to improve outcome. Feasibility of artificial intelligence to customize algorithms.

PubMed

Shoemaker, W C; Patil, R; Appel, P L; Kram, H B

1992-11-01

A generalized decision tree or clinical algorithm for treatment of high-risk elective surgical patients was developed from a physiologic model based on empirical data. First, a large data bank was used to do the following: (1) describe temporal hemodynamic and oxygen transport patterns that interrelate cardiac, pulmonary, and tissue perfusion functions in survivors and nonsurvivors; (2) define optimal therapeutic goals based on the supranormal oxygen transport values of high-risk postoperative survivors; (3) compare the relative effectiveness of alternative therapies in a wide variety of clinical and physiologic conditions; and (4) to develop criteria for titration of therapy to the endpoints of the supranormal optimal goals using cardiac index (CI), oxygen delivery (DO2), and oxygen consumption (VO2) as proxy outcome measures. Second, a general purpose algorithm was generated from these data and tested in preoperatively randomized clinical trials of high-risk surgical patients. Improved outcome was demonstrated with this generalized algorithm. The concept that the supranormal values represent compensations that have survival value has been corroborated by several other groups. We now propose a unique approach to refine the generalized algorithm to develop customized algorithms and individualized decision analysis for each patient's unique problems. The present article describes a preliminary evaluation of the feasibility of artificial intelligence techniques to accomplish individualized algorithms that may further improve patient care and outcome.

Machine Learning of Fault Friction

NASA Astrophysics Data System (ADS)

Johnson, P. A.; Rouet-Leduc, B.; Hulbert, C.; Marone, C.; Guyer, R. A.

2017-12-01

We are applying machine learning (ML) techniques to continuous acoustic emission (AE) data from laboratory earthquake experiments. Our goal is to apply explicit ML methods to this acoustic datathe AE in order to infer frictional properties of a laboratory fault. The experiment is a double direct shear apparatus comprised of fault blocks surrounding fault gouge comprised of glass beads or quartz powder. Fault characteristics are recorded, including shear stress, applied load (bulk friction = shear stress/normal load) and shear velocity. The raw acoustic signal is continuously recorded. We rely on explicit decision tree approaches (Random Forest and Gradient Boosted Trees) that allow us to identify important features linked to the fault friction. A training procedure that employs both the AE and the recorded shear stress from the experiment is first conducted. Then, testing takes place on data the algorithm has never seen before, using only the continuous AE signal. We find that these methods provide rich information regarding frictional processes during slip (Rouet-Leduc et al., 2017a; Hulbert et al., 2017). In addition, similar machine learning approaches predict failure times, as well as slip magnitudes in some cases. We find that these methods work for both stick slip and slow slip experiments, for periodic slip and for aperiodic slip. We also derive a fundamental relationship between the AE and the friction describing the frictional behavior of any earthquake slip cycle in a given experiment (Rouet-Leduc et al., 2017b). Our goal is to ultimately scale these approaches to Earth geophysical data to probe fault friction. References Rouet-Leduc, B., C. Hulbert, N. Lubbers, K. Barros, C. Humphreys and P. A. Johnson, Machine learning predicts laboratory earthquakes, in review (2017). https://arxiv.org/abs/1702.05774Rouet-LeDuc, B. et al., Friction Laws Derived From the Acoustic Emissions of a Laboratory Fault by Machine Learning (2017), AGU Fall Meeting Session S025: Earthquake source: from the laboratory to the fieldHulbert, C., Characterizing slow slip applying machine learning (2017), AGU Fall Meeting Session S019: Slow slip, Tectonic Tremor, and the Brittle-to-Ductile Transition Zone: What mechanisms control the diversity of slow and fast earthquakes?

Ontology based decision system for breast cancer diagnosis

NASA Astrophysics Data System (ADS)

Trabelsi Ben Ameur, Soumaya; Cloppet, Florence; Wendling, Laurent; Sellami, Dorra

2018-04-01

In this paper, we focus on analysis and diagnosis of breast masses inspired by expert concepts and rules. Accordingly, a Bag of Words is built based on the ontology of breast cancer diagnosis, accurately described in the Breast Imaging Reporting and Data System. To fill the gap between low level knowledge and expert concepts, a semantic annotation is developed using a machine learning tool. Then, breast masses are classified into benign or malignant according to expert rules implicitly modeled with a set of classifiers (KNN, ANN, SVM and Decision Tree). This semantic context of analysis offers a frame where we can include external factors and other meta-knowledge such as patient risk factors as well as exploiting more than one modality. Based on MRI and DECEDM modalities, our developed system leads a recognition rate of 99.7% with Decision Tree where an improvement of 24.7 % is obtained owing to semantic analysis.

Lessons learned from Applications of a Decision Tree for Confronting Climate Change Uncertainty - the Short Term and the Long Term

NASA Astrophysics Data System (ADS)

Ray, P. A.; Wi, S.; Bonzanigo, L.; Taner, M. U.; Rodriguez, D.; Garcia, L.; Brown, C.

2016-12-01

The Decision Tree for Confronting Climate Change Uncertainty is a hierarchical, staged framework for accomplishing climate change risk management in water resources system investments. Since its development for the World Bank Water Group two years ago, the framework has been applied to pilot demonstration projects in Nepal (hydropower generation), Mexico (water supply), Kenya (multipurpose reservoir operation), and Indonesia (flood risks to dam infrastructure). An important finding of the Decision Tree demonstration projects has been the need to present the risks/opportunities of climate change to stakeholders and investors in proportion to risks/opportunities and hazards of other kinds. This presentation will provide an overview of tools and techniques used to quantify risks/opportunities to each of the project types listed above, with special attention to those found most useful for exploration of the risk space. Careful exploration of the risk/opportunity space shows that some interventions would be better taken now, whereas risks/opportunities of other types would be better instituted incrementally in order to maintain reversibility and flexibility. A number of factors contribute to the robustness/flexibility tradeoff: available capital, magnitude and imminence of potential risk/opportunity, modular (or not) character of investment, and risk aversion of the decision maker, among others. Finally, in each case, nuance was required in the translation of Decision Tree findings into actionable policy recommendations. Though the narrative of stakeholder solicitation, engagement, and ultimate partnership is unique to each case, summary lessons are available from the portfolio that can serve as a guideline to the community of climate change risk managers.

Predicting Tillage Patterns in the Tiffin River Watershed Using Remote Sensing Methods

NASA Astrophysics Data System (ADS)

Brooks, C.; McCarty, J. L.; Dean, D. B.; Mann, B. F.

2012-12-01

Previous research in tillage mapping has focused primarily on utilizing low to no-cost, moderate (30 m to 15 m) resolution satellite data. Successful data processing techniques published in the scientific literature have focused on extracting and/or classifying tillage patterns through manipulation of spectral bands. For instance, Daughtry et al. (2005) evaluated several spectral indices for crop residue cover using satellite multispectral and hyperspectral data and to categorize soil tillage intensity in agricultural fields. A weak to moderate relationship between Landsat Thematic Mapper (TM) indices and crop residue cover was found; similar results were reported in Minnesota. Building on the findings from the scientific literature and previous work done by MTRI in the heavily agricultural Tiffin watershed of northwest Ohio and southeast Michigan, a decision tree classifier approach (also referred to as a classification tree) was used, linking several satellite data to on-the-ground tillage information in order to boost classification results. This approach included five tillage indices and derived products. A decision tree methodology enabled the development of statistically optimized (i.e., minimizing misclassification rates) classification algorithms at various desired time steps: monthly, seasonally, and annual over the 2006-2010 time period. Due to their flexibility, processing speed, and availability within all major remote sensing and statistical software packages, decision trees can ingest several data inputs from multiple sensors and satellite products, selecting only the bands, band ratios, indices, and products that further reduce misclassification errors. The project team created crop-specific tillage pattern classification trees whereby a training data set (~ 50% of available ground data) was created for production of the actual decision tree and a validation data set was set aside (~ 50% of available ground data) in order to assess the accuracy of the classification. A seasonal time step was used, optimizing a decision tree based on seasonal ground data for tillage patterns and satellite data and products for years 2006 through 2010. Annual crop type maps derived by the project team and the USDA Cropland Data Layer project was used an input to understand locations of corn, soybeans, wheat, etc. on a yearly basis. As previously stated, the robustness of the decision tree approach is the ability to implement various satellite data and products across temporal, spectral, and spatial resolutions, thereby improving the resulting classification and providing a reliable method that is not sensor-dependent. Tillage pattern classification from satellite imagery is not a simple task and has proven a challenge to previous researchers investigating this remote sensing topic. The team's decision tree method produced a practical, usable output within a focused project time period. Daughtry, C.S.T., Hunt Jr., E.R., Doraiswamy, P.C., McMurtrey III, J.E. 2005. Remote sensing the spatial distribution of crop residues. Agron. J. 97, 864-871.

Discriminant forest classification method and system

DOEpatents

Chen, Barry Y.; Hanley, William G.; Lemmond, Tracy D.; Hiller, Lawrence J.; Knapp, David A.; Mugge, Marshall J.

2012-11-06

A hybrid machine learning methodology and system for classification that combines classical random forest (RF) methodology with discriminant analysis (DA) techniques to provide enhanced classification capability. A DA technique which uses feature measurements of an object to predict its class membership, such as linear discriminant analysis (LDA) or Andersen-Bahadur linear discriminant technique (AB), is used to split the data at each node in each of its classification trees to train and grow the trees and the forest. When training is finished, a set of n DA-based decision trees of a discriminant forest is produced for use in predicting the classification of new samples of unknown class.

Bioinformatics algorithm based on a parallel implementation of a machine learning approach using transducers

NASA Astrophysics Data System (ADS)

Roche-Lima, Abiel; Thulasiram, Ruppa K.

2012-02-01

Finite automata, in which each transition is augmented with an output label in addition to the familiar input label, are considered finite-state transducers. Transducers have been used to analyze some fundamental issues in bioinformatics. Weighted finite-state transducers have been proposed to pairwise alignments of DNA and protein sequences; as well as to develop kernels for computational biology. Machine learning algorithms for conditional transducers have been implemented and used for DNA sequence analysis. Transducer learning algorithms are based on conditional probability computation. It is calculated by using techniques, such as pair-database creation, normalization (with Maximum-Likelihood normalization) and parameters optimization (with Expectation-Maximization - EM). These techniques are intrinsically costly for computation, even worse when are applied to bioinformatics, because the databases sizes are large. In this work, we describe a parallel implementation of an algorithm to learn conditional transducers using these techniques. The algorithm is oriented to bioinformatics applications, such as alignments, phylogenetic trees, and other genome evolution studies. Indeed, several experiences were developed using the parallel and sequential algorithm on Westgrid (specifically, on the Breeze cluster). As results, we obtain that our parallel algorithm is scalable, because execution times are reduced considerably when the data size parameter is increased. Another experience is developed by changing precision parameter. In this case, we obtain smaller execution times using the parallel algorithm. Finally, number of threads used to execute the parallel algorithm on the Breezy cluster is changed. In this last experience, we obtain as result that speedup is considerably increased when more threads are used; however there is a convergence for number of threads equal to or greater than 16.

An algorithm for computing the gene tree probability under the multispecies coalescent and its application in the inference of population tree

PubMed Central

2016-01-01

Motivation: Gene tree represents the evolutionary history of gene lineages that originate from multiple related populations. Under the multispecies coalescent model, lineages may coalesce outside the species (population) boundary. Given a species tree (with branch lengths), the gene tree probability is the probability of observing a specific gene tree topology under the multispecies coalescent model. There are two existing algorithms for computing the exact gene tree probability. The first algorithm is due to Degnan and Salter, where they enumerate all the so-called coalescent histories for the given species tree and the gene tree topology. Their algorithm runs in exponential time in the number of gene lineages in general. The second algorithm is the STELLS algorithm (2012), which is usually faster but also runs in exponential time in almost all the cases. Results: In this article, we present a new algorithm, called CompactCH, for computing the exact gene tree probability. This new algorithm is based on the notion of compact coalescent histories: multiple coalescent histories are represented by a single compact coalescent history. The key advantage of our new algorithm is that it runs in polynomial time in the number of gene lineages if the number of populations is fixed to be a constant. The new algorithm is more efficient than the STELLS algorithm both in theory and in practice when the number of populations is small and there are multiple gene lineages from each population. As an application, we show that CompactCH can be applied in the inference of population tree (i.e. the population divergence history) from population haplotypes. Simulation results show that the CompactCH algorithm enables efficient and accurate inference of population trees with much more haplotypes than a previous approach. Availability: The CompactCH algorithm is implemented in the STELLS software package, which is available for download at http://www.engr.uconn.edu/ywu/STELLS.html. Contact: ywu@engr.uconn.edu Supplementary information: Supplementary data are available at Bioinformatics online. PMID:27307621

Decision tree-based method for integrating gene expression, demographic, and clinical data to determine disease endotypes

PubMed Central

2013-01-01

Background Complex diseases are often difficult to diagnose, treat and study due to the multi-factorial nature of the underlying etiology. Large data sets are now widely available that can be used to define novel, mechanistically distinct disease subtypes (endotypes) in a completely data-driven manner. However, significant challenges exist with regard to how to segregate individuals into suitable subtypes of the disease and understand the distinct biological mechanisms of each when the goal is to maximize the discovery potential of these data sets. Results A multi-step decision tree-based method is described for defining endotypes based on gene expression, clinical covariates, and disease indicators using childhood asthma as a case study. We attempted to use alternative approaches such as the Student’s t-test, single data domain clustering and the Modk-prototypes algorithm, which incorporates multiple data domains into a single analysis and none performed as well as the novel multi-step decision tree method. This new method gave the best segregation of asthmatics and non-asthmatics, and it provides easy access to all genes and clinical covariates that distinguish the groups. Conclusions The multi-step decision tree method described here will lead to better understanding of complex disease in general by allowing purely data-driven disease endotypes to facilitate the discovery of new mechanisms underlying these diseases. This application should be considered a complement to ongoing efforts to better define and diagnose known endotypes. When coupled with existing methods developed to determine the genetics of gene expression, these methods provide a mechanism for linking genetics and exposomics data and thereby accounting for both major determinants of disease. PMID:24188919

Application of data mining approaches to drug delivery.

PubMed

Ekins, Sean; Shimada, Jun; Chang, Cheng

2006-11-30

Computational approaches play a key role in all areas of the pharmaceutical industry from data mining, experimental and clinical data capture to pharmacoeconomics and adverse events monitoring. They will likely continue to be indispensable assets along with a growing library of software applications. This is primarily due to the increasingly massive amount of biology, chemistry and clinical data, which is now entering the public domain mainly as a result of NIH and commercially funded projects. We are therefore in need of new methods for mining this mountain of data in order to enable new hypothesis generation. The computational approaches include, but are not limited to, database compilation, quantitative structure activity relationships (QSAR), pharmacophores, network visualization models, decision trees, machine learning algorithms and multidimensional data visualization software that could be used to improve drug delivery after mining public and/or proprietary data. We will discuss some areas of unmet needs in the area of data mining for drug delivery that can be addressed with new software tools or databases of relevance to future pharmaceutical projects.

Predictive analysis and data mining among the employment of fresh graduate students in HEI

NASA Astrophysics Data System (ADS)

Rahman, Nor Azziaty Abdul; Tan, Kian Lam; Lim, Chen Kim

2017-10-01

Management of higher education have a problem in producing 100% of graduates who can meet the needs of industry while industry is also facing the problem of finding skilled graduates who suit their needs partly due to the lack of an effective method in assessing problem solving skills as well as weaknesses in the assessment of problem-solving skills. The purpose of this paper is to propose a suitable classification model that can be used in making prediction and assessment of the attributes of the student's dataset to meet the selection criteria of work demanded by the industry of the graduates in the academic field. Supervised and unsupervised Machine Learning Algorithms were used in this research where; K-Nearest Neighbor, Naïve Bayes, Decision Tree, Neural Network, Logistic Regression and Support Vector Machine. The proposed model will help the university management to make a better long-term plans for producing graduates who are skilled, knowledgeable and fulfill the industry needs as well.

Reinforcement learning and decision making in monkeys during a competitive game.

PubMed

Lee, Daeyeol; Conroy, Michelle L; McGreevy, Benjamin P; Barraclough, Dominic J

2004-12-01

Animals living in a dynamic environment must adjust their decision-making strategies through experience. To gain insights into the neural basis of such adaptive decision-making processes, we trained monkeys to play a competitive game against a computer in an oculomotor free-choice task. The animal selected one of two visual targets in each trial and was rewarded only when it selected the same target as the computer opponent. To determine how the animal's decision-making strategy can be affected by the opponent's strategy, the computer opponent was programmed with three different algorithms that exploited different aspects of the animal's choice and reward history. When the computer selected its targets randomly with equal probabilities, animals selected one of the targets more often, violating the prediction of probability matching, and their choices were systematically influenced by the choice history of the two players. When the computer exploited only the animal's choice history but not its reward history, animal's choice became more independent of its own choice history but was still related to the choice history of the opponent. This bias was substantially reduced, but not completely eliminated, when the computer used the choice history of both players in making its predictions. These biases were consistent with the predictions of reinforcement learning, suggesting that the animals sought optimal decision-making strategies using reinforcement learning algorithms.

Merged or monolithic? Using machine-learning to reconstruct the dynamical history of simulated star clusters

NASA Astrophysics Data System (ADS)

Pasquato, Mario; Chung, Chul

2016-05-01

Context. Machine-learning (ML) solves problems by learning patterns from data with limited or no human guidance. In astronomy, ML is mainly applied to large observational datasets, e.g. for morphological galaxy classification. Aims: We apply ML to gravitational N-body simulations of star clusters that are either formed by merging two progenitors or evolved in isolation, planning to later identify globular clusters (GCs) that may have a history of merging from observational data. Methods: We create mock-observations from simulated GCs, from which we measure a set of parameters (also called features in the machine-learning field). After carrying out dimensionality reduction on the feature space, the resulting datapoints are fed in to various classification algorithms. Using repeated random subsampling validation, we check whether the groups identified by the algorithms correspond to the underlying physical distinction between mergers and monolithically evolved simulations. Results: The three algorithms we considered (C5.0 trees, k-nearest neighbour, and support-vector machines) all achieve a test misclassification rate of about 10% without parameter tuning, with support-vector machines slightly outperforming the others. The first principal component of feature space correlates with cluster concentration. If we exclude it from the regression, the performance of the algorithms is only slightly reduced.

An adaptive deep Q-learning strategy for handwritten digit recognition.

PubMed

Qiao, Junfei; Wang, Gongming; Li, Wenjing; Chen, Min

2018-02-22

Handwritten digits recognition is a challenging problem in recent years. Although many deep learning-based classification algorithms are studied for handwritten digits recognition, the recognition accuracy and running time still need to be further improved. In this paper, an adaptive deep Q-learning strategy is proposed to improve accuracy and shorten running time for handwritten digit recognition. The adaptive deep Q-learning strategy combines the feature-extracting capability of deep learning and the decision-making of reinforcement learning to form an adaptive Q-learning deep belief network (Q-ADBN). First, Q-ADBN extracts the features of original images using an adaptive deep auto-encoder (ADAE), and the extracted features are considered as the current states of Q-learning algorithm. Second, Q-ADBN receives Q-function (reward signal) during recognition of the current states, and the final handwritten digits recognition is implemented by maximizing the Q-function using Q-learning algorithm. Finally, experimental results from the well-known MNIST dataset show that the proposed Q-ADBN has a superiority to other similar methods in terms of accuracy and running time. Copyright © 2018 Elsevier Ltd. All rights reserved.

Putting Priors in Mixture Density Mercer Kernels

NASA Technical Reports Server (NTRS)

Srivastava, Ashok N.; Schumann, Johann; Fischer, Bernd

2004-01-01

This paper presents a new methodology for automatic knowledge driven data mining based on the theory of Mercer Kernels, which are highly nonlinear symmetric positive definite mappings from the original image space to a very high, possibly infinite dimensional feature space. We describe a new method called Mixture Density Mercer Kernels to learn kernel function directly from data, rather than using predefined kernels. These data adaptive kernels can en- code prior knowledge in the kernel using a Bayesian formulation, thus allowing for physical information to be encoded in the model. We compare the results with existing algorithms on data from the Sloan Digital Sky Survey (SDSS). The code for these experiments has been generated with the AUTOBAYES tool, which automatically generates efficient and documented C/C++ code from abstract statistical model specifications. The core of the system is a schema library which contains template for learning and knowledge discovery algorithms like different versions of EM, or numeric optimization methods like conjugate gradient methods. The template instantiation is supported by symbolic- algebraic computations, which allows AUTOBAYES to find closed-form solutions and, where possible, to integrate them into the code. The results show that the Mixture Density Mercer-Kernel described here outperforms tree-based classification in distinguishing high-redshift galaxies from low- redshift galaxies by approximately 16% on test data, bagged trees by approximately 7%, and bagged trees built on a much larger sample of data by approximately 2%.

A data mining approach to optimize pellets manufacturing process based on a decision tree algorithm.

PubMed

Ronowicz, Joanna; Thommes, Markus; Kleinebudde, Peter; Krysiński, Jerzy

2015-06-20

The present study is focused on the thorough analysis of cause-effect relationships between pellet formulation characteristics (pellet composition as well as process parameters) and the selected quality attribute of the final product. The shape using the aspect ratio value expressed the quality of pellets. A data matrix for chemometric analysis consisted of 224 pellet formulations performed by means of eight different active pharmaceutical ingredients and several various excipients, using different extrusion/spheronization process conditions. The data set contained 14 input variables (both formulation and process variables) and one output variable (pellet aspect ratio). A tree regression algorithm consistent with the Quality by Design concept was applied to obtain deeper understanding and knowledge of formulation and process parameters affecting the final pellet sphericity. The clear interpretable set of decision rules were generated. The spehronization speed, spheronization time, number of holes and water content of extrudate have been recognized as the key factors influencing pellet aspect ratio. The most spherical pellets were achieved by using a large number of holes during extrusion, a high spheronizer speed and longer time of spheronization. The described data mining approach enhances knowledge about pelletization process and simultaneously facilitates searching for the optimal process conditions which are necessary to achieve ideal spherical pellets, resulting in good flow characteristics. This data mining approach can be taken into consideration by industrial formulation scientists to support rational decision making in the field of pellets technology. Copyright © 2015 Elsevier B.V. All rights reserved.

Learning relevant features of data with multi-scale tensor networks

NASA Astrophysics Data System (ADS)

Miles Stoudenmire, E.

2018-07-01

Inspired by coarse-graining approaches used in physics, we show how similar algorithms can be adapted for data. The resulting algorithms are based on layered tree tensor networks and scale linearly with both the dimension of the input and the training set size. Computing most of the layers with an unsupervised algorithm, then optimizing just the top layer for supervised classification of the MNIST and fashion MNIST data sets gives very good results. We also discuss mixing a prior guess for supervised weights together with an unsupervised representation of the data, yielding a smaller number of features nevertheless able to give good performance.

Artificial intelligence within the chemical laboratory.

PubMed

Winkel, P

1994-01-01

Various techniques within the area of artificial intelligence such as expert systems and neural networks may play a role during the problem-solving processes within the clinical biochemical laboratory. Neural network analysis provides a non-algorithmic approach to information processing, which results in the ability of the computer to form associations and to recognize patterns or classes among data. It belongs to the machine learning techniques which also include probabilistic techniques such as discriminant function analysis and logistic regression and information theoretical techniques. These techniques may be used to extract knowledge from example patients to optimize decision limits and identify clinically important laboratory quantities. An expert system may be defined as a computer program that can give advice in a well-defined area of expertise and is able to explain its reasoning. Declarative knowledge consists of statements about logical or empirical relationships between things. Expert systems typically separate declarative knowledge residing in a knowledge base from the inference engine: an algorithm that dynamically directs and controls the system when it searches its knowledge base. A tool is an expert system without a knowledge base. The developer of an expert system uses a tool by entering knowledge into the system. Many, if not the majority of problems encountered at the laboratory level are procedural. A problem is procedural if it is possible to write up a step-by-step description of the expert's work or if it can be represented by a decision tree. To solve problems of this type only small expert system tools and/or conventional programming are required.(ABSTRACT TRUNCATED AT 250 WORDS)

Diagnosis of pulmonary hypertension from magnetic resonance imaging-based computational models and decision tree analysis.

PubMed

Lungu, Angela; Swift, Andrew J; Capener, David; Kiely, David; Hose, Rod; Wild, Jim M

2016-06-01

Accurately identifying patients with pulmonary hypertension (PH) using noninvasive methods is challenging, and right heart catheterization (RHC) is the gold standard. Magnetic resonance imaging (MRI) has been proposed as an alternative to echocardiography and RHC in the assessment of cardiac function and pulmonary hemodynamics in patients with suspected PH. The aim of this study was to assess whether machine learning using computational modeling techniques and image-based metrics of PH can improve the diagnostic accuracy of MRI in PH. Seventy-two patients with suspected PH attending a referral center underwent RHC and MRI within 48 hours. Fifty-seven patients were diagnosed with PH, and 15 had no PH. A number of functional and structural cardiac and cardiovascular markers derived from 2 mathematical models and also solely from MRI of the main pulmonary artery and heart were integrated into a classification algorithm to investigate the diagnostic utility of the combination of the individual markers. A physiological marker based on the quantification of wave reflection in the pulmonary artery was shown to perform best individually, but optimal diagnostic performance was found by the combination of several image-based markers. Classifier results, validated using leave-one-out cross validation, demonstrated that combining computation-derived metrics reflecting hemodynamic changes in the pulmonary vasculature with measurement of right ventricular morphology and function, in a decision support algorithm, provides a method to noninvasively diagnose PH with high accuracy (92%). The high diagnostic accuracy of these MRI-based model parameters may reduce the need for RHC in patients with suspected PH.

Partial dependence of breast tumor malignancy on ultrasound image features derived from boosted trees

NASA Astrophysics Data System (ADS)

Yang, Wei; Zhang, Su; Li, Wenying; Chen, Yaqing; Lu, Hongtao; Chen, Wufan; Chen, Yazhu

2010-04-01

Various computerized features extracted from breast ultrasound images are useful in assessing the malignancy of breast tumors. However, the underlying relationship between the computerized features and tumor malignancy may not be linear in nature. We use the decision tree ensemble trained by the cost-sensitive boosting algorithm to approximate the target function for malignancy assessment and to reflect this relationship qualitatively. Partial dependence plots are employed to explore and visualize the effect of features on the output of the decision tree ensemble. In the experiments, 31 image features are extracted to quantify the sonographic characteristics of breast tumors. Patient age is used as an external feature because of its high clinical importance. The area under the receiver-operating characteristic curve of the tree ensembles can reach 0.95 with sensitivity of 0.95 (61/64) at the associated specificity 0.74 (77/104). The partial dependence plots of the four most important features are demonstrated to show the influence of the features on malignancy, and they are in accord with the empirical observations. The results can provide visual and qualitative references on the computerized image features for physicians, and can be useful for enhancing the interpretability of computer-aided diagnosis systems for breast ultrasound.

Efficient cost-sensitive human-machine collaboration for offline signature verification

NASA Astrophysics Data System (ADS)

Coetzer, Johannes; Swanepoel, Jacques; Sabourin, Robert

2012-01-01

We propose a novel strategy for the optimal combination of human and machine decisions in a cost-sensitive environment. The proposed algorithm should be especially beneficial to financial institutions where off-line signatures, each associated with a specific transaction value, require authentication. When presented with a collection of genuine and fraudulent training signatures, produced by so-called guinea pig writers, the proficiency of a workforce of human employees and a score-generating machine can be estimated and represented in receiver operating characteristic (ROC) space. Using a set of Boolean fusion functions, the majority vote decision of the human workforce is combined with each threshold-specific machine-generated decision. The performance of the candidate ensembles is estimated and represented in ROC space, after which only the optimal ensembles and associated decision trees are retained. When presented with a questioned signature linked to an arbitrary writer, the system first uses the ROC-based cost gradient associated with the transaction value to select the ensemble that minimises the expected cost, and then uses the corresponding decision tree to authenticate the signature in question. We show that, when utilising the entire human workforce, the incorporation of a machine streamlines the authentication process and decreases the expected cost for all operating conditions.

Neural correlates of forward planning in a spatial decision task in humans

PubMed Central

Simon, Dylan Alexander; Daw, Nathaniel D.

2011-01-01

Although reinforcement learning (RL) theories have been influential in characterizing the brain’s mechanisms for reward-guided choice, the predominant temporal difference (TD) algorithm cannot explain many flexible or goal-directed actions that have been demonstrated behaviorally. We investigate such actions by contrasting an RL algorithm that is model-based, in that it relies on learning a map or model of the task and planning within it, to traditional model-free TD learning. To distinguish these approaches in humans, we used fMRI in a continuous spatial navigation task, in which frequent changes to the layout of the maze forced subjects continually to relearn their favored routes, thereby exposing the RL mechanisms employed. We sought evidence for the neural substrates of such mechanisms by comparing choice behavior and BOLD signals to decision variables extracted from simulations of either algorithm. Both choices and value-related BOLD signals in striatum, though most often associated with TD learning, were better explained by the model-based theory. Further, predecessor quantities for the model-based value computation were correlated with BOLD signals in the medial temporal lobe and frontal cortex. These results point to a significant extension of both the computational and anatomical substrates for RL in the brain. PMID:21471389

Development of a computer-based clinical decision support tool for selecting appropriate rehabilitation interventions for injured workers.

PubMed

Gross, Douglas P; Zhang, Jing; Steenstra, Ivan; Barnsley, Susan; Haws, Calvin; Amell, Tyler; McIntosh, Greg; Cooper, Juliette; Zaiane, Osmar

2013-12-01

To develop a classification algorithm and accompanying computer-based clinical decision support tool to help categorize injured workers toward optimal rehabilitation interventions based on unique worker characteristics. Population-based historical cohort design. Data were extracted from a Canadian provincial workers' compensation database on all claimants undergoing work assessment between December 2009 and January 2011. Data were available on: (1) numerous personal, clinical, occupational, and social variables; (2) type of rehabilitation undertaken; and (3) outcomes following rehabilitation (receiving time loss benefits or undergoing repeat programs). Machine learning, concerned with the design of algorithms to discriminate between classes based on empirical data, was the foundation of our approach to build a classification system with multiple independent and dependent variables. The population included 8,611 unique claimants. Subjects were predominantly employed (85 %) males (64 %) with diagnoses of sprain/strain (44 %). Baseline clinician classification accuracy was high (ROC = 0.86) for selecting programs that lead to successful return-to-work. Classification performance for machine learning techniques outperformed the clinician baseline classification (ROC = 0.94). The final classifiers were multifactorial and included the variables: injury duration, occupation, job attachment status, work status, modified work availability, pain intensity rating, self-rated occupational disability, and 9 items from the SF-36 Health Survey. The use of machine learning classification techniques appears to have resulted in classification performance better than clinician decision-making. The final algorithm has been integrated into a computer-based clinical decision support tool that requires additional validation in a clinical sample.

Spatial modeling and classification of corneal shape.

PubMed

Marsolo, Keith; Twa, Michael; Bullimore, Mark A; Parthasarathy, Srinivasan

2007-03-01

One of the most promising applications of data mining is in biomedical data used in patient diagnosis. Any method of data analysis intended to support the clinical decision-making process should meet several criteria: it should capture clinically relevant features, be computationally feasible, and provide easily interpretable results. In an initial study, we examined the feasibility of using Zernike polynomials to represent biomedical instrument data in conjunction with a decision tree classifier to distinguish between the diseased and non-diseased eyes. Here, we provide a comprehensive follow-up to that work, examining a second representation, pseudo-Zernike polynomials, to determine whether they provide any increase in classification accuracy. We compare the fidelity of both methods using residual root-mean-square (rms) error and evaluate accuracy using several classifiers: neural networks, C4.5 decision trees, Voting Feature Intervals, and Naïve Bayes. We also examine the effect of several meta-learning strategies: boosting, bagging, and Random Forests (RFs). We present results comparing accuracy as it relates to dataset and transformation resolution over a larger, more challenging, multi-class dataset. They show that classification accuracy is similar for both data transformations, but differs by classifier. We find that the Zernike polynomials provide better feature representation than the pseudo-Zernikes and that the decision trees yield the best balance of classification accuracy and interpretability.

Machine Learning in the Presence of an Adversary: Attacking and Defending the SpamBayes Spam Filter

DTIC Science & Technology

2008-05-20

Machine learning techniques are often used for decision making in security critical applications such as intrusion detection and spam filtering...filter. The defenses shown in this thesis are able to work against the attacks developed against SpamBayes and are sufficiently generic to be easily extended into other statistical machine learning algorithms.

The use of decision tree induction and artificial neural networks for recognizing the geochemical distribution patterns of LREE in the Choghart deposit, Central Iran

NASA Astrophysics Data System (ADS)

Zaremotlagh, S.; Hezarkhani, A.

2017-04-01

Some evidences of rare earth elements (REE) concentrations are found in iron oxide-apatite (IOA) deposits which are located in Central Iranian microcontinent. There are many unsolved problems about the origin and metallogenesis of IOA deposits in this district. Although it is considered that felsic magmatism and mineralization were simultaneous in the district, interaction of multi-stage hydrothermal-magmatic processes within the Early Cambrian volcano-sedimentary sequence probably caused some epigenetic mineralizations. Secondary geological processes (e.g., multi-stage mineralization, alteration, and weathering) have affected on variations of major elements and possible redistribution of REE in IOA deposits. Hence, the geochemical behaviors and distribution patterns of REE are expected to be complicated in different zones of these deposits. The aim of this paper is recognizing LREE distribution patterns based on whole-rock chemical compositions and automatic discovery of their geochemical rules. For this purpose, the pattern recognition techniques including decision tree and neural network were applied on a high-dimensional geochemical dataset from Choghart IOA deposit. Because some data features were irrelevant or redundant in recognizing the distribution patterns of each LREE, a greedy attribute subset selection technique was employed to select the best subset of predictors used in classification tasks. The decision trees (CART algorithm) were pruned optimally to more accurately categorize independent test data than unpruned ones. The most effective classification rules were extracted from the pruned tree to describe the meaningful relationships between the predictors and different concentrations of LREE. A feed-forward artificial neural network was also applied to reliably predict the influence of various rock compositions on the spatial distribution patterns of LREE with a better performance than the decision tree induction. The findings of this study could be effectively used to visualize the LREE distribution patterns as geochemical maps.

First Time Rapid and Accurate Detection of Massive Number of Metal Absorption Lines in the Early Universe Using Deep Neural Network

NASA Astrophysics Data System (ADS)

Zhao, Yinan; Ge, Jian; Yuan, Xiaoyong; Li, Xiaolin; Zhao, Tiffany; Wang, Cindy

2018-01-01

Metal absorption line systems in the distant quasar spectra have been used as one of the most powerful tools to probe gas content in the early Universe. The MgII λλ 2796, 2803 doublet is one of the most popular metal absorption lines and has been used to trace gas and global star formation at redshifts between ~0.5 to 2.5. In the past, machine learning algorithms have been used to detect absorption lines systems in the large sky survey, such as Principle Component Analysis, Gaussian Process and decision tree, but the overall detection process is not only complicated, but also time consuming. It usually takes a few months to go through the entire quasar spectral dataset from each of the Sloan Digital Sky Survey (SDSS) data release. In this work, we applied the deep neural network, or “ deep learning” algorithms, in the most recently SDSS DR14 quasar spectra and were able to randomly search 20000 quasar spectra and detect 2887 strong Mg II absorption features in just 9 seconds. Our detection algorithms were verified with previously released DR12 and DR7 data and published Mg II catalog and the detection accuracy is 90%. This is the first time that deep neural network has demonstrated its promising power in both speed and accuracy in replacing tedious, repetitive human work in searching for narrow absorption patterns in a big dataset. We will present our detection algorithms and also statistical results of the newly detected Mg II absorption lines.

Forecasting of the development of professional medical equipment engineering based on neuro-fuzzy algorithms

NASA Astrophysics Data System (ADS)

Vaganova, E. V.; Syryamkin, M. V.

2015-11-01

The purpose of the research is the development of evolutionary algorithms for assessments of promising scientific directions. The main attention of the present study is paid to the evaluation of the foresight possibilities for identification of technological peaks and emerging technologies in professional medical equipment engineering in Russia and worldwide on the basis of intellectual property items and neural network modeling. An automated information system consisting of modules implementing various classification methods for accuracy of the forecast improvement and the algorithm of construction of neuro-fuzzy decision tree have been developed. According to the study result, modern trends in this field will focus on personalized smart devices, telemedicine, bio monitoring, «e-Health» and «m-Health» technologies.

Finding Minimum-Power Broadcast Trees for Wireless Networks

NASA Technical Reports Server (NTRS)

Arabshahi, Payman; Gray, Andrew; Das, Arindam; El-Sharkawi, Mohamed; Marks, Robert, II

2004-01-01

Some algorithms have been devised for use in a method of constructing tree graphs that represent connections among the nodes of a wireless communication network. These algorithms provide for determining the viability of any given candidate connection tree and for generating an initial set of viable trees that can be used in any of a variety of search algorithms (e.g., a genetic algorithm) to find a tree that enables the network to broadcast from a source node to all other nodes while consuming the minimum amount of total power. The method yields solutions better than those of a prior algorithm known as the broadcast incremental power algorithm, albeit at a slightly greater computational cost.

A Swarm Optimization approach for clinical knowledge mining.

PubMed

Christopher, J Jabez; Nehemiah, H Khanna; Kannan, A

2015-10-01

Rule-based classification is a typical data mining task that is being used in several medical diagnosis and decision support systems. The rules stored in the rule base have an impact on classification efficiency. Rule sets that are extracted with data mining tools and techniques are optimized using heuristic or meta-heuristic approaches in order to improve the quality of the rule base. In this work, a meta-heuristic approach called Wind-driven Swarm Optimization (WSO) is used. The uniqueness of this work lies in the biological inspiration that underlies the algorithm. WSO uses Jval, a new metric, to evaluate the efficiency of a rule-based classifier. Rules are extracted from decision trees. WSO is used to obtain different permutations and combinations of rules whereby the optimal ruleset that satisfies the requirement of the developer is used for predicting the test data. The performance of various extensions of decision trees, namely, RIPPER, PART, FURIA and Decision Tables are analyzed. The efficiency of WSO is also compared with the traditional Particle Swarm Optimization. Experiments were carried out with six benchmark medical datasets. The traditional C4.5 algorithm yields 62.89% accuracy with 43 rules for liver disorders dataset where as WSO yields 64.60% with 19 rules. For Heart disease dataset, C4.5 is 68.64% accurate with 98 rules where as WSO is 77.8% accurate with 34 rules. The normalized standard deviation for accuracy of PSO and WSO are 0.5921 and 0.5846 respectively. WSO provides accurate and concise rulesets. PSO yields results similar to that of WSO but the novelty of WSO lies in its biological motivation and it is customization for rule base optimization. The trade-off between the prediction accuracy and the size of the rule base is optimized during the design and development of rule-based clinical decision support system. The efficiency of a decision support system relies on the content of the rule base and classification accuracy. Copyright © 2015 Elsevier Ireland Ltd. All rights reserved.

Identifying and classifying water hyacinth (Eichhornia crassipes) using the HyMap sensor

NASA Astrophysics Data System (ADS)

Rajapakse, Sepalika S.; Khanna, Shruti; Andrew, Margaret E.; Ustin, Susan L.; Lay, Mui

2006-08-01

In recent years, the impact of aquatic invasive species on biodiversity has become a major global concern. In the Sacramento-San Joaquin Delta region in the Central Valley of California, USA, dense infestations of the invasive aquatic emergent weed, water hyacinth (Eichhornia crassipes) interfere with ecosystem functioning. This silent invader constantly encroaches into waterways, eventually making them unusable by people and uninhabitable to aquatic fauna. Quantifying and mapping invasive plant species in aquatic ecosystems is important for efficient management and implementation of mitigation measures. This paper evaluates the ability of hyperspectral imagery, acquired using the HyMap sensor, for mapping water hyacinth in the Sacramento-San Joaquin Delta region. Classification was performed on sixty-four flightlines acquired over the study site using a decision tree which incorporated Spectral Angle Mapper (SAM) algorithm, absorption feature parameters in the spectral region between 0.4 and 2.5μm, and spectral endmembers. The total image dataset was 130GB. Spectral signatures of other emergent aquatic species like pennywort (Hydrocotyle ranunculoides) and water primrose (Ludwigia peploides) showed close similarity with the water hyacinth spectrum, however, the decision tree successfully discriminated water hyacinth from other emergent aquatic vegetation species. The classification algorithm showed high accuracy (κ value = 0.8) in discriminating water hyacinth.

Investigating the Link Between Radiologists Gaze, Diagnostic Decision, and Image Content

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

Tourassi, Georgia; Voisin, Sophie; Paquit, Vincent C

2013-01-01

Objective: To investigate machine learning for linking image content, human perception, cognition, and error in the diagnostic interpretation of mammograms. Methods: Gaze data and diagnostic decisions were collected from six radiologists who reviewed 20 screening mammograms while wearing a head-mounted eye-tracker. Texture analysis was performed in mammographic regions that attracted radiologists attention and in all abnormal regions. Machine learning algorithms were investigated to develop predictive models that link: (i) image content with gaze, (ii) image content and gaze with cognition, and (iii) image content, gaze, and cognition with diagnostic error. Both group-based and individualized models were explored. Results: By poolingmore » the data from all radiologists machine learning produced highly accurate predictive models linking image content, gaze, cognition, and error. Merging radiologists gaze metrics and cognitive opinions with computer-extracted image features identified 59% of the radiologists diagnostic errors while confirming 96.2% of their correct diagnoses. The radiologists individual errors could be adequately predicted by modeling the behavior of their peers. However, personalized tuning appears to be beneficial in many cases to capture more accurately individual behavior. Conclusions: Machine learning algorithms combining image features with radiologists gaze data and diagnostic decisions can be effectively developed to recognize cognitive and perceptual errors associated with the diagnostic interpretation of mammograms.« less

A controllable sensor management algorithm capable of learning

NASA Astrophysics Data System (ADS)

Osadciw, Lisa A.; Veeramacheneni, Kalyan K.

2005-03-01

Sensor management technology progress is challenged by the geographic space it spans, the heterogeneity of the sensors, and the real-time timeframes within which plans controlling the assets are executed. This paper presents a new sensor management paradigm and demonstrates its application in a sensor management algorithm designed for a biometric access control system. This approach consists of an artificial intelligence (AI) algorithm focused on uncertainty measures, which makes the high level decisions to reduce uncertainties and interfaces with the user, integrated cohesively with a bottom up evolutionary algorithm, which optimizes the sensor network"s operation as determined by the AI algorithm. The sensor management algorithm presented is composed of a Bayesian network, the AI algorithm component, and a swarm optimization algorithm, the evolutionary algorithm. Thus, the algorithm can change its own performance goals in real-time and will modify its own decisions based on observed measures within the sensor network. The definition of the measures as well as the Bayesian network determine the robustness of the algorithm and its utility in reacting dynamically to changes in the global system.

Development of an algorithm to provide awareness in choosing study designs for inclusion in systematic reviews of healthcare interventions: a method study

PubMed Central

Peinemann, Frank; Kleijnen, Jos

2015-01-01

Objectives To develop an algorithm that aims to provide guidance and awareness for choosing multiple study designs in systematic reviews of healthcare interventions. Design Method study: (1) To summarise the literature base on the topic. (2) To apply the integration of various study types in systematic reviews. (3) To devise decision points and outline a pragmatic decision tree. (4) To check the plausibility of the algorithm by backtracking its pathways in four systematic reviews. Results (1) The results of our systematic review of the published literature have already been published. (2) We recaptured the experience from our four previously conducted systematic reviews that required the integration of various study types. (3) We chose length of follow-up (long, short), frequency of events (rare, frequent) and types of outcome as decision points (death, disease, discomfort, disability, dissatisfaction) and aligned the study design labels according to the Cochrane Handbook. We also considered practical or ethical concerns, and the problem of unavailable high-quality evidence. While applying the algorithm, disease-specific circumstances and aims of interventions should be considered. (4) We confirmed the plausibility of the pathways of the algorithm. Conclusions We propose that the algorithm can assist to bring seminal features of a systematic review with multiple study designs to the attention of anyone who is planning to conduct a systematic review. It aims to increase awareness and we think that it may reduce the time burden on review authors and may contribute to the production of a higher quality review. PMID:26289450

Ensemble candidate classification for the LOTAAS pulsar survey

NASA Astrophysics Data System (ADS)

Tan, C. M.; Lyon, R. J.; Stappers, B. W.; Cooper, S.; Hessels, J. W. T.; Kondratiev, V. I.; Michilli, D.; Sanidas, S.

2018-03-01

One of the biggest challenges arising from modern large-scale pulsar surveys is the number of candidates generated. Here, we implemented several improvements to the machine learning (ML) classifier previously used by the LOFAR Tied-Array All-Sky Survey (LOTAAS) to look for new pulsars via filtering the candidates obtained during periodicity searches. To assist the ML algorithm, we have introduced new features which capture the frequency and time evolution of the signal and improved the signal-to-noise calculation accounting for broad profiles. We enhanced the ML classifier by including a third class characterizing RFI instances, allowing candidates arising from RFI to be isolated, reducing the false positive return rate. We also introduced a new training data set used by the ML algorithm that includes a large sample of pulsars misclassified by the previous classifier. Lastly, we developed an ensemble classifier comprised of five different Decision Trees. Taken together these updates improve the pulsar recall rate by 2.5 per cent, while also improving the ability to identify pulsars with wide pulse profiles, often misclassified by the previous classifier. The new ensemble classifier is also able to reduce the percentage of false positive candidates identified from each LOTAAS pointing from 2.5 per cent (˜500 candidates) to 1.1 per cent (˜220 candidates).

Neural correlates of strategic reasoning during competitive games.

PubMed

Seo, Hyojung; Cai, Xinying; Donahue, Christopher H; Lee, Daeyeol

2014-10-17

Although human and animal behaviors are largely shaped by reinforcement and punishment, choices in social settings are also influenced by information about the knowledge and experience of other decision-makers. During competitive games, monkeys increased their payoffs by systematically deviating from a simple heuristic learning algorithm and thereby countering the predictable exploitation by their computer opponent. Neurons in the dorsomedial prefrontal cortex (dmPFC) signaled the animal's recent choice and reward history that reflected the computer's exploitative strategy. The strength of switching signals in the dmPFC also correlated with the animal's tendency to deviate from the heuristic learning algorithm. Therefore, the dmPFC might provide control signals for overriding simple heuristic learning algorithms based on the inferred strategies of the opponent. Copyright © 2014, American Association for the Advancement of Science.

A learning-based autonomous driver: emulate human driver's intelligence in low-speed car following

NASA Astrophysics Data System (ADS)

Wei, Junqing; Dolan, John M.; Litkouhi, Bakhtiar

2010-04-01

In this paper, an offline learning mechanism based on the genetic algorithm is proposed for autonomous vehicles to emulate human driver behaviors. The autonomous driving ability is implemented based on a Prediction- and Cost function-Based algorithm (PCB). PCB is designed to emulate a human driver's decision process, which is modeled as traffic scenario prediction and evaluation. This paper focuses on using a learning algorithm to optimize PCB with very limited training data, so that PCB can have the ability to predict and evaluate traffic scenarios similarly to human drivers. 80 seconds of human driving data was collected in low-speed (< 30miles/h) car-following scenarios. In the low-speed car-following tests, PCB was able to perform more human-like carfollowing after learning. A more general 120 kilometer-long simulation showed that PCB performs robustly even in scenarios that are not part of the training set.

Web-based health services and clinical decision support.

PubMed

Jegelevicius, Darius; Marozas, Vaidotas; Lukosevicius, Arunas; Patasius, Martynas

2004-01-01

The purpose of this study was the development of a Web-based e-health service for comprehensive assistance and clinical decision support. The service structure consists of a Web server, a PHP-based Web interface linked to a clinical SQL database, Java applets for interactive manipulation and visualization of signals and a Matlab server linked with signal and data processing algorithms implemented by Matlab programs. The service ensures diagnostic signal- and image analysis-sbased clinical decision support. By using the discussed methodology, a pilot service for pathology specialists for automatic calculation of the proliferation index has been developed. Physicians use a simple Web interface for uploading the pictures under investigation to the server; subsequently a Java applet interface is used for outlining the region of interest and, after processing on the server, the requested proliferation index value is calculated. There is also an "expert corner", where experts can submit their index estimates and comments on particular images, which is especially important for system developers. These expert evaluations are used for optimization and verification of automatic analysis algorithms. Decision support trials have been conducted for ECG and ophthalmology ultrasonic investigations of intraocular tumor differentiation. Data mining algorithms have been applied and decision support trees constructed. These services are under implementation by a Web-based system too. The study has shown that the Web-based structure ensures more effective, flexible and accessible services compared with standalone programs and is very convenient for biomedical engineers and physicians, especially in the development phase.

Predicting a small molecule-kinase interaction map: A machine learning approach

PubMed Central

2011-01-01

Background We present a machine learning approach to the problem of protein ligand interaction prediction. We focus on a set of binding data obtained from 113 different protein kinases and 20 inhibitors. It was attained through ATP site-dependent binding competition assays and constitutes the first available dataset of this kind. We extract information about the investigated molecules from various data sources to obtain an informative set of features. Results A Support Vector Machine (SVM) as well as a decision tree algorithm (C5/See5) is used to learn models based on the available features which in turn can be used for the classification of new kinase-inhibitor pair test instances. We evaluate our approach using different feature sets and parameter settings for the employed classifiers. Moreover, the paper introduces a new way of evaluating predictions in such a setting, where different amounts of information about the binding partners can be assumed to be available for training. Results on an external test set are also provided. Conclusions In most of the cases, the presented approach clearly outperforms the baseline methods used for comparison. Experimental results indicate that the applied machine learning methods are able to detect a signal in the data and predict binding affinity to some extent. For SVMs, the binding prediction can be improved significantly by using features that describe the active site of a kinase. For C5, besides diversity in the feature set, alignment scores of conserved regions turned out to be very useful. PMID:21708012

Understanding the Scalability of Bayesian Network Inference Using Clique Tree Growth Curves

NASA Technical Reports Server (NTRS)

Mengshoel, Ole J.

2010-01-01

One of the main approaches to performing computation in Bayesian networks (BNs) is clique tree clustering and propagation. The clique tree approach consists of propagation in a clique tree compiled from a Bayesian network, and while it was introduced in the 1980s, there is still a lack of understanding of how clique tree computation time depends on variations in BN size and structure. In this article, we improve this understanding by developing an approach to characterizing clique tree growth as a function of parameters that can be computed in polynomial time from BNs, specifically: (i) the ratio of the number of a BN s non-root nodes to the number of root nodes, and (ii) the expected number of moral edges in their moral graphs. Analytically, we partition the set of cliques in a clique tree into different sets, and introduce a growth curve for the total size of each set. For the special case of bipartite BNs, there are two sets and two growth curves, a mixed clique growth curve and a root clique growth curve. In experiments, where random bipartite BNs generated using the BPART algorithm are studied, we systematically increase the out-degree of the root nodes in bipartite Bayesian networks, by increasing the number of leaf nodes. Surprisingly, root clique growth is well-approximated by Gompertz growth curves, an S-shaped family of curves that has previously been used to describe growth processes in biology, medicine, and neuroscience. We believe that this research improves the understanding of the scaling behavior of clique tree clustering for a certain class of Bayesian networks; presents an aid for trade-off studies of clique tree clustering using growth curves; and ultimately provides a foundation for benchmarking and developing improved BN inference and machine learning algorithms.

Problem decomposition by mutual information and force-based clustering

NASA Astrophysics Data System (ADS)

Otero, Richard Edward

The scale of engineering problems has sharply increased over the last twenty years. Larger coupled systems, increasing complexity, and limited resources create a need for methods that automatically decompose problems into manageable sub-problems by discovering and leveraging problem structure. The ability to learn the coupling (inter-dependence) structure and reorganize the original problem could lead to large reductions in the time to analyze complex problems. Such decomposition methods could also provide engineering insight on the fundamental physics driving problem solution. This work forwards the current state of the art in engineering decomposition through the application of techniques originally developed within computer science and information theory. The work describes the current state of automatic problem decomposition in engineering and utilizes several promising ideas to advance the state of the practice. Mutual information is a novel metric for data dependence and works on both continuous and discrete data. Mutual information can measure both the linear and non-linear dependence between variables without the limitations of linear dependence measured through covariance. Mutual information is also able to handle data that does not have derivative information, unlike other metrics that require it. The value of mutual information to engineering design work is demonstrated on a planetary entry problem. This study utilizes a novel tool developed in this work for planetary entry system synthesis. A graphical method, force-based clustering, is used to discover related sub-graph structure as a function of problem structure and links ranked by their mutual information. This method does not require the stochastic use of neural networks and could be used with any link ranking method currently utilized in the field. Application of this method is demonstrated on a large, coupled low-thrust trajectory problem. Mutual information also serves as the basis for an alternative global optimizer, called MIMIC, which is unrelated to Genetic Algorithms. Advancement to the current practice demonstrates the use of MIMIC as a global method that explicitly models problem structure with mutual information, providing an alternate method for globally searching multi-modal domains. By leveraging discovered problem inter- dependencies, MIMIC may be appropriate for highly coupled problems or those with large function evaluation cost. This work introduces a useful addition to the MIMIC algorithm that enables its use on continuous input variables. By leveraging automatic decision tree generation methods from Machine Learning and a set of randomly generated test problems, decision trees for which method to apply are also created, quantifying decomposition performance over a large region of the design space.

Reinforcement learning techniques for controlling resources in power networks

NASA Astrophysics Data System (ADS)

Kowli, Anupama Sunil

As power grids transition towards increased reliance on renewable generation, energy storage and demand response resources, an effective control architecture is required to harness the full functionalities of these resources. There is a critical need for control techniques that recognize the unique characteristics of the different resources and exploit the flexibility afforded by them to provide ancillary services to the grid. The work presented in this dissertation addresses these needs. Specifically, new algorithms are proposed, which allow control synthesis in settings wherein the precise distribution of the uncertainty and its temporal statistics are not known. These algorithms are based on recent developments in Markov decision theory, approximate dynamic programming and reinforcement learning. They impose minimal assumptions on the system model and allow the control to be "learned" based on the actual dynamics of the system. Furthermore, they can accommodate complex constraints such as capacity and ramping limits on generation resources, state-of-charge constraints on storage resources, comfort-related limitations on demand response resources and power flow limits on transmission lines. Numerical studies demonstrating applications of these algorithms to practical control problems in power systems are discussed. Results demonstrate how the proposed control algorithms can be used to improve the performance and reduce the computational complexity of the economic dispatch mechanism in a power network. We argue that the proposed algorithms are eminently suitable to develop operational decision-making tools for large power grids with many resources and many sources of uncertainty.

Discovery of new rheumatoid arthritis biomarkers using the surface-enhanced laser desorption/ionization time-of-flight mass spectrometry ProteinChip approach.

PubMed

de Seny, Dominique; Fillet, Marianne; Meuwis, Marie-Alice; Geurts, Pierre; Lutteri, Laurence; Ribbens, Clio; Bours, Vincent; Wehenkel, Louis; Piette, Jacques; Malaise, Michel; Merville, Marie-Paule

2005-12-01

To identify serum protein biomarkers specific for rheumatoid arthritis (RA), using surface-enhanced laser desorption/ionization time-of-flight mass spectrometry (SELDI-TOF-MS) technology. A total of 103 serum samples from patients and healthy controls were analyzed. Thirty-four of the patients had a diagnosis of RA, based on the American College of Rheumatology criteria. The inflammation control group comprised 20 patients with psoriatic arthritis (PsA), 9 with asthma, and 10 with Crohn's disease. The noninflammation control group comprised 14 patients with knee osteoarthritis and 16 healthy control subjects. Serum protein profiles were obtained by SELDI-TOF-MS and compared in order to identify new biomarkers specific for RA. Data were analyzed by a machine learning algorithm called decision tree boosting, according to different preprocessing steps. The most discriminative mass/charge (m/z) values serving as potential biomarkers for RA were identified on arrays for both patients with RA versus controls and patients with RA versus patients with PsA. From among several candidates, the following peaks were highlighted: m/z values of 2,924 (RA versus controls on H4 arrays), 10,832 and 11,632 (RA versus controls on CM10 arrays), 4,824 (RA versus PsA on H4 arrays), and 4,666 (RA versus PsA on CM10 arrays). Positive results of proteomic analysis were associated with positive results of the anti-cyclic citrullinated peptide test. Our observations suggested that the 10,832 peak could represent myeloid-related protein 8. SELDI-TOF-MS technology allows rapid analysis of many serum samples, and use of decision tree boosting analysis as the main statistical method allowed us to propose a pattern of protein peaks specific for RA.

The use of the decision tree technique and image cytometry to characterize aggressiveness in World Health Organization (WHO) grade II superficial transitional cell carcinomas of the bladder.

PubMed

Decaestecker, C; van Velthoven, R; Petein, M; Janssen, T; Salmon, I; Pasteels, J L; van Ham, P; Schulman, C; Kiss, R

1996-03-01

The aggressiveness of human bladder tumours can be assessed by means of various classification systems, including the one proposed by the World Health Organization (WHO). According to the WHO classification, three levels of malignancy are identified as grades I (low), II (intermediate), and III (high). This classification system operates satisfactorily for two of the three grades in forecasting clinical progression, most grade I tumours being associated with good prognoses and most grade III with bad. In contrast, the grade II group is very heterogeneous in terms of their clinical behaviour. The present study used two computer-assisted methods to investigate whether it is possible to sub-classify grade II tumours: computer-assisted microscope analysis (image cytometry) of Feulgen-stained nuclei and the Decision Tree Technique. This latter technique belongs to the Supervised Learning Algorithm and enables an objective assessment to be made of the diagnostic value associated with a given parameter. The combined use of these two methods in a series of 292 superficial transitional cell carcinomas shows that it is possible to identify one subgroup of grade II tumours which behave clinically like grade I tumours and a second subgroup which behaves clinically like grade III tumours. Of the nine ploidy-related parameters computed by means of image cytometry [the DNA index (DI), DNA histogram type (DHT), and the percentages of diploid, hyperdiploid, triploid, hypertriploid, tetraploid, hypertetraploid, and polyploid cell nuclei], it was the percentage of hyperdiploid and hypertetraploid cell nuclei which enabled identification, rather than conventional parameters such as the DI or the DHT.

ECG signal performance de-noising assessment based on threshold tuning of dual-tree wavelet transform.

PubMed

El B'charri, Oussama; Latif, Rachid; Elmansouri, Khalifa; Abenaou, Abdenbi; Jenkal, Wissam

2017-02-07

Since the electrocardiogram (ECG) signal has a low frequency and a weak amplitude, it is sensitive to miscellaneous mixed noises, which may reduce the diagnostic accuracy and hinder the physician's correct decision on patients. The dual tree wavelet transform (DT-WT) is one of the most recent enhanced versions of discrete wavelet transform. However, threshold tuning on this method for noise removal from ECG signal has not been investigated yet. In this work, we shall provide a comprehensive study on the impact of the choice of threshold algorithm, threshold value, and the appropriate wavelet decomposition level to evaluate the ECG signal de-noising performance. A set of simulations is performed on both synthetic and real ECG signals to achieve the promised results. First, the synthetic ECG signal is used to observe the algorithm response. The evaluation results of synthetic ECG signal corrupted by various types of noise has showed that the modified unified threshold and wavelet hyperbolic threshold de-noising method is better in realistic and colored noises. The tuned threshold is then used on real ECG signals from the MIT-BIH database. The results has shown that the proposed method achieves higher performance than the ordinary dual tree wavelet transform into all kinds of noise removal from ECG signal. The simulation results indicate that the algorithm is robust for all kinds of noises with varying degrees of input noise, providing a high quality clean signal. Moreover, the algorithm is quite simple and can be used in real time ECG monitoring.

Precision assessment of some supervised and unsupervised algorithms for genotype discrimination in the genus Pisum using SSR molecular data.

PubMed

Nasiri, Jaber; Naghavi, Mohammad Reza; Kayvanjoo, Amir Hossein; Nasiri, Mojtaba; Ebrahimi, Mansour

2015-03-07

For the first time, prediction accuracies of some supervised and unsupervised algorithms were evaluated in an SSR-based DNA fingerprinting study of a pea collection containing 20 cultivars and 57 wild samples. In general, according to the 10 attribute weighting models, the SSR alleles of PEAPHTAP-2 and PSBLOX13.2-1 were the two most important attributes to generate discrimination among eight different species and subspecies of genus Pisum. In addition, K-Medoids unsupervised clustering run on Chi squared dataset exhibited the best prediction accuracy (83.12%), while the lowest accuracy (25.97%) gained as K-Means model ran on FCdb database. Irrespective of some fluctuations, the overall accuracies of tree induction models were significantly high for many algorithms, and the attributes PSBLOX13.2-3 and PEAPHTAP could successfully detach Pisum fulvum accessions and cultivars from the others when two selected decision trees were taken into account. Meanwhile, the other used supervised algorithms exhibited overall reliable accuracies, even though in some rare cases, they gave us low amounts of accuracies. Our results, altogether, demonstrate promising applications of both supervised and unsupervised algorithms to provide suitable data mining tools regarding accurate fingerprinting of different species and subspecies of genus Pisum, as a fundamental priority task in breeding programs of the crop. Copyright © 2015 Elsevier Ltd. All rights reserved.

A study of fuzzy logic ensemble system performance on face recognition problem

NASA Astrophysics Data System (ADS)

Polyakova, A.; Lipinskiy, L.

2017-02-01

Some problems are difficult to solve by using a single intelligent information technology (IIT). The ensemble of the various data mining (DM) techniques is a set of models which are able to solve the problem by itself, but the combination of which allows increasing the efficiency of the system as a whole. Using the IIT ensembles can improve the reliability and efficiency of the final decision, since it emphasizes on the diversity of its components. The new method of the intellectual informational technology ensemble design is considered in this paper. It is based on the fuzzy logic and is designed to solve the classification and regression problems. The ensemble consists of several data mining algorithms: artificial neural network, support vector machine and decision trees. These algorithms and their ensemble have been tested by solving the face recognition problems. Principal components analysis (PCA) is used for feature selection.

Model-Based Design of Tree WSNs for Decentralized Detection.

PubMed

Tantawy, Ashraf; Koutsoukos, Xenofon; Biswas, Gautam

2015-08-20

The classical decentralized detection problem of finding the optimal decision rules at the sensor and fusion center, as well as variants that introduce physical channel impairments have been studied extensively in the literature. The deployment of WSNs in decentralized detection applications brings new challenges to the field. Protocols for different communication layers have to be co-designed to optimize the detection performance. In this paper, we consider the communication network design problem for a tree WSN. We pursue a system-level approach where a complete model for the system is developed that captures the interactions between different layers, as well as different sensor quality measures. For network optimization, we propose a hierarchical optimization algorithm that lends itself to the tree structure, requiring only local network information. The proposed design approach shows superior performance over several contentionless and contention-based network design approaches.

Genetic Fuzzy Trees for Intelligent Control of Unmanned Combat Aerial Vehicles

NASA Astrophysics Data System (ADS)

Ernest, Nicholas D.

Fuzzy Logic Control is a powerful tool that has found great success in a variety of applications. This technique relies less on complex mathematics and more "expert knowledge" of a system to bring about high-performance, resilient, and efficient control through linguistic classification of inputs and outputs and if-then rules. Genetic Fuzzy Systems (GFSs) remove the need of this expert knowledge and instead rely on a Genetic Algorithm (GA) and have similarly found great success. However, the combination of these methods suffer severely from scalability; the number of rules required to control the system increases exponentially with the number of states the inputs and outputs can take. Therefor GFSs have thus far not been applicable to complex, artificial intelligence type problems. The novel Genetic Fuzzy Tree (GFT) method breaks down complex problems hierarchically, makes sub-decisions when possible, and thus greatly reduces the burden on the GA. This development significantly changes the field of possible applications for GFSs. Within this study, this is demonstrated through applying this technique to a difficult air combat problem. Looking forward to an autonomous Unmanned Combat Aerial Vehicle (UCAV) in the 2030 time-frame, it becomes apparent that the mission, flight, and ground controls will utilize the emerging paradigm of Intelligent Systems (IS); namely, the ability to learn, adapt, exhibit robustness in uncertain situations, make sense of the data collected in real-time and extrapolate when faced with scenarios significantly different from those used in training. LETHA (Learning Enhanced Tactical Handling Algorithm) was created to develop intelligent controllers for these advanced unmanned craft as the first GFT. A simulation space referred to as HADES (Hoplological Autonomous Defend and Engage Simulation) was created in which LETHA can train the UCAVs. Equipped with advanced sensors, a limited supply of Self-Defense Missiles (SDMs), and a recharging Laser Weapon System (LWS), these UCAVs can navigate a mission space, counter enemy threats, cope with losses in communications, and destroy mission-critical targets. Monte Carlo simulations of the resulting controllers were tested in mission scenarios that are distinct from the training scenarios to determine the training effectiveness in new environments and the presence of deep learning. Despite an incredibly large solution space, LETHA has demonstrated remarkable effectiveness in training intelligent controllers for the UCAV squadron and shown robustness to drastically changing states, uncertainty, and limited information while maintaining extreme levels of computational efficiency.

Studies of the DIII-D disruption database using Machine Learning algorithms

NASA Astrophysics Data System (ADS)

Rea, Cristina; Granetz, Robert; Meneghini, Orso

2017-10-01

A Random Forests Machine Learning algorithm, trained on a large database of both disruptive and non-disruptive DIII-D discharges, predicts disruptive behavior in DIII-D with about 90% of accuracy. Several algorithms have been tested and Random Forests was found superior in performances for this particular task. Over 40 plasma parameters are included in the database, with data for each of the parameters taken from 500k time slices. We focused on a subset of non-dimensional plasma parameters, deemed to be good predictors based on physics considerations. Both binary (disruptive/non-disruptive) and multi-label (label based on the elapsed time before disruption) classification problems are investigated. The Random Forests algorithm provides insight on the available dataset by ranking the relative importance of the input features. It is found that q95 and Greenwald density fraction (n/nG) are the most relevant parameters for discriminating between DIII-D disruptive and non-disruptive discharges. A comparison with the Gradient Boosted Trees algorithm is shown and the first results coming from the application of regression algorithms are presented. Work supported by the US Department of Energy under DE-FC02-04ER54698, DE-SC0014264 and DE-FG02-95ER54309.

Comparative Study on the Different Testing Techniques in Tree Classification for Detecting the Learning Motivation

NASA Astrophysics Data System (ADS)

Juliane, C.; Arman, A. A.; Sastramihardja, H. S.; Supriana, I.

2017-03-01

Having motivation to learn is a successful requirement in a learning process, and needs to be maintained properly. This study aims to measure learning motivation, especially in the process of electronic learning (e-learning). Here, data mining approach was chosen as a research method. For the testing process, the accuracy comparative study on the different testing techniques was conducted, involving Cross Validation and Percentage Split. The best accuracy was generated by J48 algorithm with a percentage split technique reaching at 92.19 %. This study provided an overview on how to detect the presence of learning motivation in the context of e-learning. It is expected to be good contribution for education, and to warn the teachers for whom they have to provide motivation.

Polynomial-Time Algorithms for Building a Consensus MUL-Tree

PubMed Central

Cui, Yun; Jansson, Jesper

2012-01-01

Abstract A multi-labeled phylogenetic tree, or MUL-tree, is a generalization of a phylogenetic tree that allows each leaf label to be used many times. MUL-trees have applications in biogeography, the study of host–parasite cospeciation, gene evolution studies, and computer science. Here, we consider the problem of inferring a consensus MUL-tree that summarizes a given set of conflicting MUL-trees, and present the first polynomial-time algorithms for solving it. In particular, we give a straightforward, fast algorithm for building a strict consensus MUL-tree for any input set of MUL-trees with identical leaf label multisets, as well as a polynomial-time algorithm for building a majority rule consensus MUL-tree for the special case where every leaf label occurs at most twice. We also show that, although it is NP-hard to find a majority rule consensus MUL-tree in general, the variant that we call the singular majority rule consensus MUL-tree can be constructed efficiently whenever it exists. PMID:22963134

Polynomial-time algorithms for building a consensus MUL-tree.

PubMed

Cui, Yun; Jansson, Jesper; Sung, Wing-Kin

2012-09-01

A multi-labeled phylogenetic tree, or MUL-tree, is a generalization of a phylogenetic tree that allows each leaf label to be used many times. MUL-trees have applications in biogeography, the study of host-parasite cospeciation, gene evolution studies, and computer science. Here, we consider the problem of inferring a consensus MUL-tree that summarizes a given set of conflicting MUL-trees, and present the first polynomial-time algorithms for solving it. In particular, we give a straightforward, fast algorithm for building a strict consensus MUL-tree for any input set of MUL-trees with identical leaf label multisets, as well as a polynomial-time algorithm for building a majority rule consensus MUL-tree for the special case where every leaf label occurs at most twice. We also show that, although it is NP-hard to find a majority rule consensus MUL-tree in general, the variant that we call the singular majority rule consensus MUL-tree can be constructed efficiently whenever it exists.