Selecting islands and shoals for conservation based on biological and aesthetic criteria

USGS Publications Warehouse

Knutson, M.G.; Leopold, D.J.; Smardon, R.C.

1993-01-01

Consideration of biological quality has long been an important component of rating areas for conservation. Often these same areas are highly valued by people for aesthetic reasons, creating demands for housing and recreation that may conflict with protection plans for these habitats. Most methods of selecting land for conservation purposes use biological factors alone. For some land areas, analysis of aesthetic qualities is also important in describing the scenic value of undisturbed land. A method for prioritizing small islands and shoals based on both biological and visual quality factors is presented here. The study included 169 undeveloped islands and shoals a??0.8 ha in the Thousand Islands Region of the St. Lawrence River, New York. Criteria such as critical habitat for uncommon plant and animal species were considered together with visual quality and incorporated into a rating system that ranked the islands and shoals according to their priority for conservation management and protection from development. Biological factors were determined based on previous research and a field survey. Visual quality was determined by visual diagnostic criteria developed from public responses to photographs of a sample of islands. Variables such as elevation, soil depth, and type of plant community can be used to classify islands into different categories of visual quality but are unsuccessful in classifying islands into categories of overall biological quality.

Classifying Radio Galaxies with the Convolutional Neural Network

NASA Astrophysics Data System (ADS)

Aniyan, A. K.; Thorat, K.

2017-06-01

We present the application of a deep machine learning technique to classify radio images of extended sources on a morphological basis using convolutional neural networks (CNN). In this study, we have taken the case of the Fanaroff-Riley (FR) class of radio galaxies as well as radio galaxies with bent-tailed morphology. We have used archival data from the Very Large Array (VLA)—Faint Images of the Radio Sky at Twenty Centimeters survey and existing visually classified samples available in the literature to train a neural network for morphological classification of these categories of radio sources. Our training sample size for each of these categories is ˜200 sources, which has been augmented by rotated versions of the same. Our study shows that CNNs can classify images of the FRI and FRII and bent-tailed radio galaxies with high accuracy (maximum precision at 95%) using well-defined samples and a “fusion classifier,” which combines the results of binary classifications, while allowing for a mechanism to find sources with unusual morphologies. The individual precision is highest for bent-tailed radio galaxies at 95% and is 91% and 75% for the FRI and FRII classes, respectively, whereas the recall is highest for FRI and FRIIs at 91% each, while the bent-tailed class has a recall of 79%. These results show that our results are comparable to that of manual classification, while being much faster. Finally, we discuss the computational and data-related challenges associated with the morphological classification of radio galaxies with CNNs.

Malware analysis using visualized image matrices.

PubMed

Han, KyoungSoo; Kang, BooJoong; Im, Eul Gyu

2014-01-01

This paper proposes a novel malware visual analysis method that contains not only a visualization method to convert binary files into images, but also a similarity calculation method between these images. The proposed method generates RGB-colored pixels on image matrices using the opcode sequences extracted from malware samples and calculates the similarities for the image matrices. Particularly, our proposed methods are available for packed malware samples by applying them to the execution traces extracted through dynamic analysis. When the images are generated, we can reduce the overheads by extracting the opcode sequences only from the blocks that include the instructions related to staple behaviors such as functions and application programming interface (API) calls. In addition, we propose a technique that generates a representative image for each malware family in order to reduce the number of comparisons for the classification of unknown samples and the colored pixel information in the image matrices is used to calculate the similarities between the images. Our experimental results show that the image matrices of malware can effectively be used to classify malware families both statically and dynamically with accuracy of 0.9896 and 0.9732, respectively.

Visualization and classification of physiological failure modes in ensemble hemorrhage simulation

NASA Astrophysics Data System (ADS)

Zhang, Song; Pruett, William Andrew; Hester, Robert

2015-01-01

In an emergency situation such as hemorrhage, doctors need to predict which patients need immediate treatment and care. This task is difficult because of the diverse response to hemorrhage in human population. Ensemble physiological simulations provide a means to sample a diverse range of subjects and may have a better chance of containing the correct solution. However, to reveal the patterns and trends from the ensemble simulation is a challenging task. We have developed a visualization framework for ensemble physiological simulations. The visualization helps users identify trends among ensemble members, classify ensemble member into subpopulations for analysis, and provide prediction to future events by matching a new patient's data to existing ensembles. We demonstrated the effectiveness of the visualization on simulated physiological data. The lessons learned here can be applied to clinically-collected physiological data in the future.

Classification of Malaysia aromatic rice using multivariate statistical analysis

NASA Astrophysics Data System (ADS)

Abdullah, A. H.; Adom, A. H.; Shakaff, A. Y. Md; Masnan, M. J.; Zakaria, A.; Rahim, N. A.; Omar, O.

2015-05-01

Aromatic rice (Oryza sativa L.) is considered as the best quality premium rice. The varieties are preferred by consumers because of its preference criteria such as shape, colour, distinctive aroma and flavour. The price of aromatic rice is higher than ordinary rice due to its special needed growth condition for instance specific climate and soil. Presently, the aromatic rice quality is identified by using its key elements and isotopic variables. The rice can also be classified via Gas Chromatography Mass Spectrometry (GC-MS) or human sensory panels. However, the uses of human sensory panels have significant drawbacks such as lengthy training time, and prone to fatigue as the number of sample increased and inconsistent. The GC-MS analysis techniques on the other hand, require detailed procedures, lengthy analysis and quite costly. This paper presents the application of in-house developed Electronic Nose (e-nose) to classify new aromatic rice varieties. The e-nose is used to classify the variety of aromatic rice based on the samples odour. The samples were taken from the variety of rice. The instrument utilizes multivariate statistical data analysis, including Principal Component Analysis (PCA), Linear Discriminant Analysis (LDA) and K-Nearest Neighbours (KNN) to classify the unknown rice samples. The Leave-One-Out (LOO) validation approach is applied to evaluate the ability of KNN to perform recognition and classification of the unspecified samples. The visual observation of the PCA and LDA plots of the rice proves that the instrument was able to separate the samples into different clusters accordingly. The results of LDA and KNN with low misclassification error support the above findings and we may conclude that the e-nose is successfully applied to the classification of the aromatic rice varieties.

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

Abdullah, A. H.; Adom, A. H.; Shakaff, A. Y. Md

Aromatic rice (Oryza sativa L.) is considered as the best quality premium rice. The varieties are preferred by consumers because of its preference criteria such as shape, colour, distinctive aroma and flavour. The price of aromatic rice is higher than ordinary rice due to its special needed growth condition for instance specific climate and soil. Presently, the aromatic rice quality is identified by using its key elements and isotopic variables. The rice can also be classified via Gas Chromatography Mass Spectrometry (GC-MS) or human sensory panels. However, the uses of human sensory panels have significant drawbacks such as lengthy trainingmore » time, and prone to fatigue as the number of sample increased and inconsistent. The GC–MS analysis techniques on the other hand, require detailed procedures, lengthy analysis and quite costly. This paper presents the application of in-house developed Electronic Nose (e-nose) to classify new aromatic rice varieties. The e-nose is used to classify the variety of aromatic rice based on the samples odour. The samples were taken from the variety of rice. The instrument utilizes multivariate statistical data analysis, including Principal Component Analysis (PCA), Linear Discriminant Analysis (LDA) and K-Nearest Neighbours (KNN) to classify the unknown rice samples. The Leave-One-Out (LOO) validation approach is applied to evaluate the ability of KNN to perform recognition and classification of the unspecified samples. The visual observation of the PCA and LDA plots of the rice proves that the instrument was able to separate the samples into different clusters accordingly. The results of LDA and KNN with low misclassification error support the above findings and we may conclude that the e-nose is successfully applied to the classification of the aromatic rice varieties.« less

Accurate determination of imaging modality using an ensemble of text- and image-based classifiers.

PubMed

Kahn, Charles E; Kalpathy-Cramer, Jayashree; Lam, Cesar A; Eldredge, Christina E

2012-02-01

Imaging modality can aid retrieval of medical images for clinical practice, research, and education. We evaluated whether an ensemble classifier could outperform its constituent individual classifiers in determining the modality of figures from radiology journals. Seventeen automated classifiers analyzed 77,495 images from two radiology journals. Each classifier assigned one of eight imaging modalities--computed tomography, graphic, magnetic resonance imaging, nuclear medicine, positron emission tomography, photograph, ultrasound, or radiograph-to each image based on visual and/or textual information. Three physicians determined the modality of 5,000 randomly selected images as a reference standard. A "Simple Vote" ensemble classifier assigned each image to the modality that received the greatest number of individual classifiers' votes. A "Weighted Vote" classifier weighted each individual classifier's vote based on performance over a training set. For each image, this classifier's output was the imaging modality that received the greatest weighted vote score. We measured precision, recall, and F score (the harmonic mean of precision and recall) for each classifier. Individual classifiers' F scores ranged from 0.184 to 0.892. The simple vote and weighted vote classifiers correctly assigned 4,565 images (F score, 0.913; 95% confidence interval, 0.905-0.921) and 4,672 images (F score, 0.934; 95% confidence interval, 0.927-0.941), respectively. The weighted vote classifier performed significantly better than all individual classifiers. An ensemble classifier correctly determined the imaging modality of 93% of figures in our sample. The imaging modality of figures published in radiology journals can be determined with high accuracy, which will improve systems for image retrieval.

Label-free capture of breast cancer cells spiked in buffy coats using carbon nanotube antibody micro-arrays

NASA Astrophysics Data System (ADS)

Khosravi, Farhad; Trainor, Patrick; Rai, Shesh N.; Kloecker, Goetz; Wickstrom, Eric; Panchapakesan, Balaji

2016-04-01

We demonstrate the rapid and label-free capture of breast cancer cells spiked in buffy coats using nanotube-antibody micro-arrays. Single wall carbon nanotube arrays were manufactured using photo-lithography, metal deposition, and etching techniques. Anti-epithelial cell adhesion molecule (EpCAM) antibodies were functionalized to the surface of the nanotube devices using 1-pyrene-butanoic acid succinimidyl ester functionalization method. Following functionalization, plain buffy coat and MCF7 cell spiked buffy coats were adsorbed on to the nanotube device and electrical signatures were recorded for differences in interaction between samples. A statistical classifier for the ‘liquid biopsy’ was developed to create a predictive model based on dynamic time warping to classify device electrical signals that corresponded to plain (control) or spiked buffy coats (case). In training test, the device electrical signals originating from buffy versus spiked buffy samples were classified with ˜100% sensitivity, ˜91% specificity and ˜96% accuracy. In the blinded test, the signals were classified with ˜91% sensitivity, ˜82% specificity and ˜86% accuracy. A heatmap was generated to visually capture the relationship between electrical signatures and the sample condition. Confocal microscopic analysis of devices that were classified as spiked buffy coats based on their electrical signatures confirmed the presence of cancer cells, their attachment to the device and overexpression of EpCAM receptors. The cell numbers were counted to be ˜1-17 cells per 5 μl per device suggesting single cell sensitivity in spiked buffy coats that is scalable to higher volumes using the micro-arrays.

Classifying Radio Galaxies with the Convolutional Neural Network

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

Aniyan, A. K.; Thorat, K.

We present the application of a deep machine learning technique to classify radio images of extended sources on a morphological basis using convolutional neural networks (CNN). In this study, we have taken the case of the Fanaroff–Riley (FR) class of radio galaxies as well as radio galaxies with bent-tailed morphology. We have used archival data from the Very Large Array (VLA)—Faint Images of the Radio Sky at Twenty Centimeters survey and existing visually classified samples available in the literature to train a neural network for morphological classification of these categories of radio sources. Our training sample size for each of these categoriesmore » is ∼200 sources, which has been augmented by rotated versions of the same. Our study shows that CNNs can classify images of the FRI and FRII and bent-tailed radio galaxies with high accuracy (maximum precision at 95%) using well-defined samples and a “fusion classifier,” which combines the results of binary classifications, while allowing for a mechanism to find sources with unusual morphologies. The individual precision is highest for bent-tailed radio galaxies at 95% and is 91% and 75% for the FRI and FRII classes, respectively, whereas the recall is highest for FRI and FRIIs at 91% each, while the bent-tailed class has a recall of 79%. These results show that our results are comparable to that of manual classification, while being much faster. Finally, we discuss the computational and data-related challenges associated with the morphological classification of radio galaxies with CNNs.« less

A Novel Locally Linear KNN Method With Applications to Visual Recognition.

PubMed

Liu, Qingfeng; Liu, Chengjun

2017-09-01

A locally linear K Nearest Neighbor (LLK) method is presented in this paper with applications to robust visual recognition. Specifically, the concept of an ideal representation is first presented, which improves upon the traditional sparse representation in many ways. The objective function based on a host of criteria for sparsity, locality, and reconstruction is then optimized to derive a novel representation, which is an approximation to the ideal representation. The novel representation is further processed by two classifiers, namely, an LLK-based classifier and a locally linear nearest mean-based classifier, for visual recognition. The proposed classifiers are shown to connect to the Bayes decision rule for minimum error. Additional new theoretical analysis is presented, such as the nonnegative constraint, the group regularization, and the computational efficiency of the proposed LLK method. New methods such as a shifted power transformation for improving reliability, a coefficients' truncating method for enhancing generalization, and an improved marginal Fisher analysis method for feature extraction are proposed to further improve visual recognition performance. Extensive experiments are implemented to evaluate the proposed LLK method for robust visual recognition. In particular, eight representative data sets are applied for assessing the performance of the LLK method for various visual recognition applications, such as action recognition, scene recognition, object recognition, and face recognition.

What’s in a drop? Correlating observations and outcomes to guide macromolecular crystallization experiments

PubMed Central

Luft, Joseph R.; Wolfley, Jennifer R.; Snell, Edward H.

2011-01-01

Observations of crystallization experiments are classified as specific outcomes and integrated through a phase diagram to visualize solubility and thereby direct subsequent experiments. Specific examples are taken from our high-throughput crystallization laboratory which provided a broad scope of data from 20 million crystallization experiments on 12,500 different biological macromolecules. The methods and rationale are broadly and generally applicable in any crystallization laboratory. Through a combination of incomplete factorial sampling of crystallization cocktails, standard outcome classifications, visualization of outcomes as they relate chemically and application of a simple phase diagram approach we demonstrate how to logically design subsequent crystallization experiments. PMID:21643490

Objects Classification by Learning-Based Visual Saliency Model and Convolutional Neural Network.

PubMed

Li, Na; Zhao, Xinbo; Yang, Yongjia; Zou, Xiaochun

2016-01-01

Humans can easily classify different kinds of objects whereas it is quite difficult for computers. As a hot and difficult problem, objects classification has been receiving extensive interests with broad prospects. Inspired by neuroscience, deep learning concept is proposed. Convolutional neural network (CNN) as one of the methods of deep learning can be used to solve classification problem. But most of deep learning methods, including CNN, all ignore the human visual information processing mechanism when a person is classifying objects. Therefore, in this paper, inspiring the completed processing that humans classify different kinds of objects, we bring forth a new classification method which combines visual attention model and CNN. Firstly, we use the visual attention model to simulate the processing of human visual selection mechanism. Secondly, we use CNN to simulate the processing of how humans select features and extract the local features of those selected areas. Finally, not only does our classification method depend on those local features, but also it adds the human semantic features to classify objects. Our classification method has apparently advantages in biology. Experimental results demonstrated that our method made the efficiency of classification improve significantly.

Visual feature extraction and establishment of visual tags in the intelligent visual internet of things

NASA Astrophysics Data System (ADS)

Zhao, Yiqun; Wang, Zhihui

2015-12-01

The Internet of things (IOT) is a kind of intelligent networks which can be used to locate, track, identify and supervise people and objects. One of important core technologies of intelligent visual internet of things ( IVIOT) is the intelligent visual tag system. In this paper, a research is done into visual feature extraction and establishment of visual tags of the human face based on ORL face database. Firstly, we use the principal component analysis (PCA) algorithm for face feature extraction, then adopt the support vector machine (SVM) for classifying and face recognition, finally establish a visual tag for face which is already classified. We conducted a experiment focused on a group of people face images, the result show that the proposed algorithm have good performance, and can show the visual tag of objects conveniently.

Using the concept of pseudo amino acid composition to predict resistance gene against Xanthomonas oryzae pv. oryzae in rice: an approach from chaos games representation.

PubMed

Jingbo, Xia; Silan, Zhang; Feng, Shi; Huijuan, Xiong; Xuehai, Hu; Xiaohui, Niu; Zhi, Li

2011-09-07

To evaluate the possibility of an unknown protein to be a resistant gene against Xanthomonas oryzae pv. oryzae, a different mode of pseudo amino acid composition (PseAAC) is proposed to formulate the protein samples by integrating the amino acid composition, as well as the Chaos games representation (CGR) method. Some numerical comparisons of triangle, quadrangle and 12-vertex polygon CGR are carried to evaluate the efficiency of using these fractal figures in classifiers. The numerical results show that among the three polygon methods, triangle method owns a good fractal visualization and performs the best in the classifier construction. By using triangle + 12-vertex polygon CGR as the mathematical feature, the classifier achieves 98.13% in Jackknife test and MCC achieves 0.8462. Copyright © 2011 Elsevier Ltd. All rights reserved.

Malware Analysis Using Visualized Image Matrices

PubMed Central

Im, Eul Gyu

2014-01-01

This paper proposes a novel malware visual analysis method that contains not only a visualization method to convert binary files into images, but also a similarity calculation method between these images. The proposed method generates RGB-colored pixels on image matrices using the opcode sequences extracted from malware samples and calculates the similarities for the image matrices. Particularly, our proposed methods are available for packed malware samples by applying them to the execution traces extracted through dynamic analysis. When the images are generated, we can reduce the overheads by extracting the opcode sequences only from the blocks that include the instructions related to staple behaviors such as functions and application programming interface (API) calls. In addition, we propose a technique that generates a representative image for each malware family in order to reduce the number of comparisons for the classification of unknown samples and the colored pixel information in the image matrices is used to calculate the similarities between the images. Our experimental results show that the image matrices of malware can effectively be used to classify malware families both statically and dynamically with accuracy of 0.9896 and 0.9732, respectively. PMID:25133202

Causes of blindness and visual impairment in Pakistan. The Pakistan national blindness and visual impairment survey

PubMed Central

Dineen, B; Bourne, R R A; Jadoon, Z; Shah, S P; Khan, M A; Foster, A; Gilbert, C E; Khan, M D

2007-01-01

Objective To determine the causes of blindness and visual impairment in adults (⩾30 years old) in Pakistan, and to explore socio‐demographic variations in cause. Methods A multi‐stage, stratified, cluster random sampling survey was used to select a nationally representative sample of adults. Each subject was interviewed, had their visual acuity measured and underwent autorefraction and fundus/optic disc examination. Those with a visual acuity of <6/12 in either eye underwent a more detailed ophthalmic examination. Causes of visual impairment were classified according to the accepted World Health Organization (WHO) methodology. An exploration of demographic variables was conducted using regression modeling. Results A sample of 16 507 adults (95.5% of those enumerated) was examined. Cataract was the most common cause of blindness (51.5%; defined as <3/60 in the better eye on presentation) followed by corneal opacity (11.8%), uncorrected aphakia (8.6%) and glaucoma (7.1%). Posterior capsular opacification accounted for 3.6% of blindness. Among the moderately visually impaired (<6/18 to ⩾6/60), refractive error was the most common cause (43%), followed by cataract (42%). Refractive error as a cause of severe visual impairment/blindness was significantly higher in rural dwellers than in urban dwellers (odds ratio (OR) 3.5, 95% CI 1.1 to 11.7). Significant provincial differences were also identified. Overall we estimate that 85.5% of causes were avoidable and that 904 000 adults in Pakistan have cataract (<6/60) requiring surgical intervention. Conclusions This comprehensive survey provides reliable estimates of the causes of blindness and visual impairment in Pakistan. Despite expanded surgical services, cataract still accounts for over half of the cases of blindness in Pakistan. One in eight blind adults has visual loss from sequelae of cataract surgery. Services for refractive errors need to be further expanded and integrated into eye care services, particularly those serving rural populations. PMID:17229806

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.

CANDELS Visual Classifications: Scheme, Data Release, and First Results

NASA Technical Reports Server (NTRS)

Kartaltepe, Jeyhan S.; Mozena, Mark; Kocevski, Dale; McIntosh, Daniel H.; Lotz, Jennifer; Bell, Eric F.; Faber, Sandy; Ferguson, Henry; Koo, David; Bassett, Robert;

A Catalog of Visually Classified Galaxies in the Local (z ∼ 0.01) Universe

NASA Astrophysics Data System (ADS)

Ann, H. B.; Seo, Mira; Ha, D. K.

2015-04-01

The morphological types of 5836 galaxies were classified by a visual inspection of color images using the Sloan Digital Sky Survey Data Release 7 to produce a morphology catalog of a representative sample of local galaxies with z\\lt 0.01. The sample galaxies are almost complete for galaxies brighter than {{r}pet}=17.77. Our classification system is basically the same as that of the Third Reference Catalog of Bright Galaxies with some simplifications for giant galaxies. On the other hand, we distinguish the fine features of dwarf elliptical (dE)-like galaxies to classify five subtypes: dE, blue-cored dwarf ellipticals, dwarf spheroidals (dSph), blue dwarf ellipticals (dEblue), and dwarf lenticulars (dS0). In addition, we note the presence of nucleation in dE, dSph, and dS0. Elliptical galaxies and lenticular galaxies contribute only ∼ 1.5 and ∼ 4.9% of local galaxies, respectively, whereas spirals and irregulars contribute ∼ 32.1 and ∼ 42.8%, respectively. The dEblue galaxies, which are a recently discovered population of galaxies, contribute a significant fraction of dwarf galaxies. There seem to be structural differences between dSph and dE galaxies. The dSph galaxies are fainter and bluer with a shallower surface brightness gradient than dE galaxies. They also have a lower fraction of galaxies with small axis ratios (b/a≲ 0.4) than dE galaxies. The mean projected distance to the nearest neighbor galaxy is ∼260 kpc. About 1% of local galaxies have no neighbors with comparable luminosity within a projected distance of 2 Mpc.

Automated in vivo identification of fungal infection on human scalp using optical coherence tomography and machine learning

NASA Astrophysics Data System (ADS)

Dubey, Kavita; Srivastava, Vishal; Singh Mehta, Dalip

2018-04-01

Early identification of fungal infection on the human scalp is crucial for avoiding hair loss. The diagnosis of fungal infection on the human scalp is based on a visual assessment by trained experts or doctors. Optical coherence tomography (OCT) has the ability to capture fungal infection information from the human scalp with a high resolution. In this study, we present a fully automated, non-contact, non-invasive optical method for rapid detection of fungal infections based on the extracted features from A-line and B-scan images of OCT. A multilevel ensemble machine model is designed to perform automated classification, which shows the superiority of our classifier to the best classifier based on the features extracted from OCT images. In this study, 60 samples (30 fungal, 30 normal) were imaged by OCT and eight features were extracted. The classification algorithm had an average sensitivity, specificity and accuracy of 92.30, 90.90 and 91.66%, respectively, for identifying fungal and normal human scalps. This remarkable classifying ability makes the proposed model readily applicable to classifying the human scalp.

CpG island methylation profile in non-invasive oral rinse samples is predictive of oral and pharyngeal carcinoma.

PubMed

Langevin, Scott M; Eliot, Melissa; Butler, Rondi A; Cheong, Agnes; Zhang, Xiang; McClean, Michael D; Koestler, Devin C; Kelsey, Karl T

2015-01-01

There are currently no screening tests in routine use for oral and pharyngeal cancer beyond visual inspection and palpation, which are provided on an opportunistic basis, indicating a need for development of novel methods for early detection, particularly in high-risk populations. We sought to address this need through comprehensive interrogation of CpG island methylation in oral rinse samples. We used the Infinium HumanMethylation450 BeadArray to interrogate DNA methylation in oral rinse samples collected from 154 patients with incident oral or pharyngeal carcinoma prior to treatment and 72 cancer-free control subjects. Subjects were randomly allocated to either a training or a testing set. For each subject, average methylation was calculated for each CpG island represented on the array. We applied a semi-supervised recursively partitioned mixture model to the CpG island methylation data to identify a classifier for prediction of case status in the training set. We then applied the resultant classifier to the testing set for validation and to assess the predictive accuracy. We identified a methylation classifier comprised of 22 CpG islands, which predicted oral and pharyngeal carcinoma with a high degree of accuracy (AUC = 0.92, 95 % CI 0.86, 0.98). This novel methylation panel is a strong predictor of oral and pharyngeal carcinoma case status in oral rinse samples and may have utility in early detection and post-treatment follow-up.

Visual terrain mapping for traversable path planning of mobile robots

NASA Astrophysics Data System (ADS)

Shirkhodaie, Amir; Amrani, Rachida; Tunstel, Edward W.

2004-10-01

In this paper, we have primarily discussed technical challenges and navigational skill requirements of mobile robots for traversability path planning in natural terrain environments similar to Mars surface terrains. We have described different methods for detection of salient terrain features based on imaging texture analysis techniques. We have also presented three competing techniques for terrain traversability assessment of mobile robots navigating in unstructured natural terrain environments. These three techniques include: a rule-based terrain classifier, a neural network-based terrain classifier, and a fuzzy-logic terrain classifier. Each proposed terrain classifier divides a region of natural terrain into finite sub-terrain regions and classifies terrain condition exclusively within each sub-terrain region based on terrain visual clues. The Kalman Filtering technique is applied for aggregative fusion of sub-terrain assessment results. The last two terrain classifiers are shown to have remarkable capability for terrain traversability assessment of natural terrains. We have conducted a comparative performance evaluation of all three terrain classifiers and presented the results in this paper.

Soft computing-based terrain visual sensing and data fusion for unmanned ground robotic systems

NASA Astrophysics Data System (ADS)

Shirkhodaie, Amir

2006-05-01

In this paper, we have primarily discussed technical challenges and navigational skill requirements of mobile robots for traversability path planning in natural terrain environments similar to Mars surface terrains. We have described different methods for detection of salient terrain features based on imaging texture analysis techniques. We have also presented three competing techniques for terrain traversability assessment of mobile robots navigating in unstructured natural terrain environments. These three techniques include: a rule-based terrain classifier, a neural network-based terrain classifier, and a fuzzy-logic terrain classifier. Each proposed terrain classifier divides a region of natural terrain into finite sub-terrain regions and classifies terrain condition exclusively within each sub-terrain region based on terrain visual clues. The Kalman Filtering technique is applied for aggregative fusion of sub-terrain assessment results. The last two terrain classifiers are shown to have remarkable capability for terrain traversability assessment of natural terrains. We have conducted a comparative performance evaluation of all three terrain classifiers and presented the results in this paper.

Exploring Verbal, Visual and Schematic Learners' Static and Dynamic Mental Images of Scientific Species and Processes in Relation to Their Spatial Ability

ERIC Educational Resources Information Center

Al-Balushi, Sulaiman M.; Coll, Richard Kevin

2013-01-01

The current study compared different learners' static and dynamic mental images of unseen scientific species and processes in relation to their spatial ability. Learners were classified into verbal, visual and schematic. Dynamic images were classified into: appearing/disappearing, linear-movement, and rotation. Two types of scientific entities and…

CANDELS Visual Classifications: Scheme, Data Release, and First Results

NASA Astrophysics Data System (ADS)

Kartaltepe, Jeyhan S.; Mozena, Mark; Kocevski, Dale; McIntosh, Daniel H.; Lotz, Jennifer; Bell, Eric F.; Faber, Sandy; Ferguson, Harry; Koo, David; Bassett, Robert; Bernyk, Maksym; Blancato, Kirsten; Bournaud, Frederic; Cassata, Paolo; Castellano, Marco; Cheung, Edmond; Conselice, Christopher J.; Croton, Darren; Dahlen, Tomas; de Mello, Duilia F.; DeGroot, Laura; Donley, Jennifer; Guedes, Javiera; Grogin, Norman; Hathi, Nimish; Hilton, Matt; Hollon, Brett; Koekemoer, Anton; Liu, Nick; Lucas, Ray A.; Martig, Marie; McGrath, Elizabeth; McPartland, Conor; Mobasher, Bahram; Morlock, Alice; O'Leary, Erin; Peth, Mike; Pforr, Janine; Pillepich, Annalisa; Rosario, David; Soto, Emmaris; Straughn, Amber; Telford, Olivia; Sunnquist, Ben; Trump, Jonathan; Weiner, Benjamin; Wuyts, Stijn; Inami, Hanae; Kassin, Susan; Lani, Caterina; Poole, Gregory B.; Rizer, Zachary

2015-11-01

We have undertaken an ambitious program to visually classify all galaxies in the five CANDELS fields down to H < 24.5 involving the dedicated efforts of over 65 individual classifiers. Once completed, we expect to have detailed morphological classifications for over 50,000 galaxies spanning 0 < z < 4 over all the fields, with classifications from 3 to 5 independent classifiers for each galaxy. Here, we present our detailed visual classification scheme, which was designed to cover a wide range of CANDELS science goals. This scheme includes the basic Hubble sequence types, but also includes a detailed look at mergers and interactions, the clumpiness of galaxies, k-corrections, and a variety of other structural properties. In this paper, we focus on the first field to be completed—GOODS-S, which has been classified at various depths. The wide area coverage spanning the full field (wide+deep+ERS) includes 7634 galaxies that have been classified by at least three different people. In the deep area of the field, 2534 galaxies have been classified by at least five different people at three different depths. With this paper, we release to the public all of the visual classifications in GOODS-S along with the Perl/Tk GUI that we developed to classify galaxies. We present our initial results here, including an analysis of our internal consistency and comparisons among multiple classifiers as well as a comparison to the Sérsic index. We find that the level of agreement among classifiers is quite good (>70% across the full magnitude range) and depends on both the galaxy magnitude and the galaxy type, with disks showing the highest level of agreement (>50%) and irregulars the lowest (<10%). A comparison of our classifications with the Sérsic index and rest-frame colors shows a clear separation between disk and spheroid populations. Finally, we explore morphological k-corrections between the V-band and H-band observations and find that a small fraction (84 galaxies in total) are classified as being very different between these two bands. These galaxies typically have very clumpy and extended morphology or are very faint in the V-band.

Differences in visual vs. verbal memory impairments as a result of focal temporal lobe damage in patients with traumatic brain injury.

PubMed

Ariza, Mar; Pueyo, Roser; Junqué, Carme; Mataró, María; Poca, María Antonia; Mena, Maria Pau; Sahuquillo, Juan

2006-09-01

The aim of the present study was to determine whether the type of lesion in a sample of moderate and severe traumatic brain injury (TBI) was related to material-specific memory impairment. Fifty-nine patients with TBI were classified into three groups according to whether the site of the lesion was right temporal, left temporal or diffuse. Six-months post-injury, visual (Warrington's Facial Recognition Memory Test and Rey's Complex Figure Test) and verbal (Rey's Auditory Verbal Learning Test) memories were assessed. Visual memory deficits assessed by facial memory were associated with right temporal lobe lesion, whereas verbal memory performance assessed with a list of words was related to left temporal lobe lesion. The group with diffuse injury showed both verbal and visual memory impairment. These results suggest a material-specific memory impairment in moderate and severe TBI after focal temporal lesions and a non-specific memory impairment after diffuse damage.

Level-2 Milestone 4797: Early Users on Max, Sequoia Visualization Cluster

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

Cupps, Kim C.

This report documents the fact that an early user has run successfully on Max, the Sequoia visualization cluster, ASC L2 milestone 4797: Early Users on Sequoia Visualization System (Max), due December 31, 2013. The Max visualization and data analysis cluster will provide Sequoia users with compute cycles and an interactive option for data exploration and analysis. The system will be integrated in the first quarter of FY14 and the system is expected to be moved to the classified network by the second quarter of FY14. The goal of this milestone is to have early users running their visualization and datamore » analysis work on the Max cluster on the classified network.« less

Unsupervised Gaussian Mixture-Model With Expectation Maximization for Detecting Glaucomatous Progression in Standard Automated Perimetry Visual Fields.

PubMed

Yousefi, Siamak; Balasubramanian, Madhusudhanan; Goldbaum, Michael H; Medeiros, Felipe A; Zangwill, Linda M; Weinreb, Robert N; Liebmann, Jeffrey M; Girkin, Christopher A; Bowd, Christopher

2016-05-01

To validate Gaussian mixture-model with expectation maximization (GEM) and variational Bayesian independent component analysis mixture-models (VIM) for detecting glaucomatous progression along visual field (VF) defect patterns (GEM-progression of patterns (POP) and VIM-POP). To compare GEM-POP and VIM-POP with other methods. GEM and VIM models separated cross-sectional abnormal VFs from 859 eyes and normal VFs from 1117 eyes into abnormal and normal clusters. Clusters were decomposed into independent axes. The confidence limit (CL) of stability was established for each axis with a set of 84 stable eyes. Sensitivity for detecting progression was assessed in a sample of 83 eyes with known progressive glaucomatous optic neuropathy (PGON). Eyes were classified as progressed if any defect pattern progressed beyond the CL of stability. Performance of GEM-POP and VIM-POP was compared to point-wise linear regression (PLR), permutation analysis of PLR (PoPLR), and linear regression (LR) of mean deviation (MD), and visual field index (VFI). Sensitivity and specificity for detecting glaucomatous VFs were 89.9% and 93.8%, respectively, for GEM and 93.0% and 97.0%, respectively, for VIM. Receiver operating characteristic (ROC) curve areas for classifying progressed eyes were 0.82 for VIM-POP, 0.86 for GEM-POP, 0.81 for PoPLR, 0.69 for LR of MD, and 0.76 for LR of VFI. GEM-POP was significantly more sensitive to PGON than PoPLR and linear regression of MD and VFI in our sample, while providing localized progression information. Detection of glaucomatous progression can be improved by assessing longitudinal changes in localized patterns of glaucomatous defect identified by unsupervised machine learning.

Lagrangian methods of cosmic web classification

NASA Astrophysics Data System (ADS)

Fisher, J. D.; Faltenbacher, A.; Johnson, M. S. T.

2016-05-01

The cosmic web defines the large-scale distribution of matter we see in the Universe today. Classifying the cosmic web into voids, sheets, filaments and nodes allows one to explore structure formation and the role environmental factors have on halo and galaxy properties. While existing studies of cosmic web classification concentrate on grid-based methods, this work explores a Lagrangian approach where the V-web algorithm proposed by Hoffman et al. is implemented with techniques borrowed from smoothed particle hydrodynamics. The Lagrangian approach allows one to classify individual objects (e.g. particles or haloes) based on properties of their nearest neighbours in an adaptive manner. It can be applied directly to a halo sample which dramatically reduces computational cost and potentially allows an application of this classification scheme to observed galaxy samples. Finally, the Lagrangian nature admits a straightforward inclusion of the Hubble flow negating the necessity of a visually defined threshold value which is commonly employed by grid-based classification methods.

Parametric embedding for class visualization.

PubMed

Iwata, Tomoharu; Saito, Kazumi; Ueda, Naonori; Stromsten, Sean; Griffiths, Thomas L; Tenenbaum, Joshua B

2007-09-01

We propose a new method, parametric embedding (PE), that embeds objects with the class structure into a low-dimensional visualization space. PE takes as input a set of class conditional probabilities for given data points and tries to preserve the structure in an embedding space by minimizing a sum of Kullback-Leibler divergences, under the assumption that samples are generated by a gaussian mixture with equal covariances in the embedding space. PE has many potential uses depending on the source of the input data, providing insight into the classifier's behavior in supervised, semisupervised, and unsupervised settings. The PE algorithm has a computational advantage over conventional embedding methods based on pairwise object relations since its complexity scales with the product of the number of objects and the number of classes. We demonstrate PE by visualizing supervised categorization of Web pages, semisupervised categorization of digits, and the relations of words and latent topics found by an unsupervised algorithm, latent Dirichlet allocation.

Nondestructive Analysis of Apollo Samples by Micro-CT and Micro-XRF Analysis: A PET Style Examination

NASA Technical Reports Server (NTRS)

Zeigler, Ryan A.

2014-01-01

An integral part of any sample return mission is the initial description and classification of returned samples by the preliminary examination team (PET). The goal of a PET is to characterize and classify the returned samples, making this information available to the general research community who can then conduct more in-depth studies on the samples. A PET strives to minimize the impact their work has on the sample suite, which often limits the PET work to largely visual measurements and observations like optical microscopy. More modern techniques can also be utilized by future PET to nondestructively characterize astromaterials in a more rigorous way. Here we present our recent analyses of Apollo samples 14321 and 14305 by micro-CT and micro-XRF (respectively), assess the potential for discovery of "new" Apollo samples for scientific study, and evaluate the usefulness of these techniques in future PET efforts.

Observers' cognitive states modulate how visual inputs relate to gaze control.

PubMed

Kardan, Omid; Henderson, John M; Yourganov, Grigori; Berman, Marc G

2016-09-01

Previous research has shown that eye-movements change depending on both the visual features of our environment, and the viewer's top-down knowledge. One important question that is unclear is the degree to which the visual goals of the viewer modulate how visual features of scenes guide eye-movements. Here, we propose a systematic framework to investigate this question. In our study, participants performed 3 different visual tasks on 135 scenes: search, memorization, and aesthetic judgment, while their eye-movements were tracked. Canonical correlation analyses showed that eye-movements were reliably more related to low-level visual features at fixations during the visual search task compared to the aesthetic judgment and scene memorization tasks. Different visual features also had different relevance to eye-movements between tasks. This modulation of the relationship between visual features and eye-movements by task was also demonstrated with classification analyses, where classifiers were trained to predict the viewing task based on eye movements and visual features at fixations. Feature loadings showed that the visual features at fixations could signal task differences independent of temporal and spatial properties of eye-movements. When classifying across participants, edge density and saliency at fixations were as important as eye-movements in the successful prediction of task, with entropy and hue also being significant, but with smaller effect sizes. When classifying within participants, brightness and saturation were also significant contributors. Canonical correlation and classification results, together with a test of moderation versus mediation, suggest that the cognitive state of the observer moderates the relationship between stimulus-driven visual features and eye-movements. (PsycINFO Database Record (c) 2016 APA, all rights reserved).

Naive scoring of human sleep based on a hidden Markov model of the electroencephalogram.

PubMed

Yaghouby, Farid; Modur, Pradeep; Sunderam, Sridhar

2014-01-01

Clinical sleep scoring involves tedious visual review of overnight polysomnograms by a human expert. Many attempts have been made to automate the process by training computer algorithms such as support vector machines and hidden Markov models (HMMs) to replicate human scoring. Such supervised classifiers are typically trained on scored data and then validated on scored out-of-sample data. Here we describe a methodology based on HMMs for scoring an overnight sleep recording without the benefit of a trained initial model. The number of states in the data is not known a priori and is optimized using a Bayes information criterion. When tested on a 22-subject database, this unsupervised classifier agreed well with human scores (mean of Cohen's kappa > 0.7). The HMM also outperformed other unsupervised classifiers (Gaussian mixture models, k-means, and linkage trees), that are capable of naive classification but do not model dynamics, by a significant margin (p < 0.05).

VizieR Online Data Catalog: Optically red galaxies in H-ATLAS/GAMA (Dariush+, 2016)

NASA Astrophysics Data System (ADS)

Dariush, A.; Dib, S.; Hony, S.; Smith, D. J. B.; Zhukovska, S.; Dunne, L.; Eales, S.; Andrae, E.; Baes, M.; Baldry, I.; Bauer, A.; Bland-Hawthorn, J.; Brough, S.; Bourne, N.; Cava, A.; Clements, D.; Cluver, M.; Cooray, A.; de Zotti, G.; Driver, S.; Grootes, M. W.; Hopkins, A. M.; Hopwood, R.; Kaviraj, S.; Kelvin, L.; Lara-Lopez, M. A.; Liske, J.; Loveday, J.; Maddox, S.; Madore, B.; Michalowski, M. J.; Pearson, C.; Popescu, C.; Robotham, A.; Rowlands, K.; Seibert, M.; Shabani, F.; Smith, M. W. L.; Taylor, E. N.; Tuffs, R.; Valiante, E.; Virdee, J. S.

2016-09-01

We use data from the H-ATLAS phase 1 version 3.0 internal release which contains the IDs of >5σ SPIRE detections at 250um. We define two sub-samples of red and blue galaxies based on NUV-r colours. The morphology of all 117 red galaxies were examined from their SDSS r-band images, following independent visual inspection by three team members. Galaxies were classified into three categories of elliptical (E), spiral (S) and uncertain (U). (2 data files).

Visual modifications on the P300 speller BCI paradigm

NASA Astrophysics Data System (ADS)

Salvaris, M.; Sepulveda, F.

2009-08-01

The best known P300 speller brain-computer interface (BCI) paradigm is the Farwell and Donchin paradigm. In this paper, various changes to the visual aspects of this protocol are explored as well as their effects on classification. Changes to the dimensions of the symbols, the distance between the symbols and the colours used were tested. The purpose of the present work was not to achieve the highest possible accuracy results, but to ascertain whether these simple modifications to the visual protocol will provide classification differences between them and what these differences will be. Eight subjects were used, with each subject carrying out a total of six different experiments. In each experiment, the user spelt a total of 39 characters. Two types of classifiers were trained and tested to determine whether the results were classifier dependant. These were a support vector machine (SVM) with a radial basis function (RBF) kernel and Fisher's linear discriminant (FLD). The single-trial classification results and multiple-trial classification results were recorded and compared. Although no visual protocol was the best for all subjects, the best performances, across both classifiers, were obtained with the white background (WB) visual protocol. The worst performance was obtained with the small symbol size (SSS) visual protocol.

Interface Prostheses With Classifier-Feedback-Based User Training.

PubMed

Fang, Yinfeng; Zhou, Dalin; Li, Kairu; Liu, Honghai

2017-11-01

It is evident that user training significantly affects performance of pattern-recognition-based myoelectric prosthetic device control. Despite plausible classification accuracy on offline datasets, online accuracy usually suffers from the changes in physiological conditions and electrode displacement. The user ability in generating consistent electromyographic (EMG) patterns can be enhanced via proper user training strategies in order to improve online performance. This study proposes a clustering-feedback strategy that provides real-time feedback to users by means of a visualized online EMG signal input as well as the centroids of the training samples, whose dimensionality is reduced to minimal number by dimension reduction. Clustering feedback provides a criterion that guides users to adjust motion gestures and muscle contraction forces intentionally. The experiment results have demonstrated that hand motion recognition accuracy increases steadily along the progress of the clustering-feedback-based user training, while conventional classifier-feedback methods, i.e., label feedback, hardly achieve any improvement. The result concludes that the use of proper classifier feedback can accelerate the process of user training, and implies prosperous future for the amputees with limited or no experience in pattern-recognition-based prosthetic device manipulation.It is evident that user training significantly affects performance of pattern-recognition-based myoelectric prosthetic device control. Despite plausible classification accuracy on offline datasets, online accuracy usually suffers from the changes in physiological conditions and electrode displacement. The user ability in generating consistent electromyographic (EMG) patterns can be enhanced via proper user training strategies in order to improve online performance. This study proposes a clustering-feedback strategy that provides real-time feedback to users by means of a visualized online EMG signal input as well as the centroids of the training samples, whose dimensionality is reduced to minimal number by dimension reduction. Clustering feedback provides a criterion that guides users to adjust motion gestures and muscle contraction forces intentionally. The experiment results have demonstrated that hand motion recognition accuracy increases steadily along the progress of the clustering-feedback-based user training, while conventional classifier-feedback methods, i.e., label feedback, hardly achieve any improvement. The result concludes that the use of proper classifier feedback can accelerate the process of user training, and implies prosperous future for the amputees with limited or no experience in pattern-recognition-based prosthetic device manipulation.

OpenCL based machine learning labeling of biomedical datasets

NASA Astrophysics Data System (ADS)

Amoros, Oscar; Escalera, Sergio; Puig, Anna

2011-03-01

In this paper, we propose a two-stage labeling method of large biomedical datasets through a parallel approach in a single GPU. Diagnostic methods, structures volume measurements, and visualization systems are of major importance for surgery planning, intra-operative imaging and image-guided surgery. In all cases, to provide an automatic and interactive method to label or to tag different structures contained into input data becomes imperative. Several approaches to label or segment biomedical datasets has been proposed to discriminate different anatomical structures in an output tagged dataset. Among existing methods, supervised learning methods for segmentation have been devised to easily analyze biomedical datasets by a non-expert user. However, they still have some problems concerning practical application, such as slow learning and testing speeds. In addition, recent technological developments have led to widespread availability of multi-core CPUs and GPUs, as well as new software languages, such as NVIDIA's CUDA and OpenCL, allowing to apply parallel programming paradigms in conventional personal computers. Adaboost classifier is one of the most widely applied methods for labeling in the Machine Learning community. In a first stage, Adaboost trains a binary classifier from a set of pre-labeled samples described by a set of features. This binary classifier is defined as a weighted combination of weak classifiers. Each weak classifier is a simple decision function estimated on a single feature value. Then, at the testing stage, each weak classifier is independently applied on the features of a set of unlabeled samples. In this work, we propose an alternative representation of the Adaboost binary classifier. We use this proposed representation to define a new GPU-based parallelized Adaboost testing stage using OpenCL. We provide numerical experiments based on large available data sets and we compare our results to CPU-based strategies in terms of time and labeling speeds.

Image Statistics and the Representation of Material Properties in the Visual Cortex

PubMed Central

Baumgartner, Elisabeth; Gegenfurtner, Karl R.

2016-01-01

We explored perceived material properties (roughness, texturedness, and hardness) with a novel approach that compares perception, image statistics and brain activation, as measured with fMRI. We initially asked participants to rate 84 material images with respect to the above mentioned properties, and then scanned 15 of the participants with fMRI while they viewed the material images. The images were analyzed with a set of image statistics capturing their spatial frequency and texture properties. Linear classifiers were then applied to the image statistics as well as the voxel patterns of visually responsive voxels and early visual areas to discriminate between images with high and low perceptual ratings. Roughness and texturedness could be classified above chance level based on image statistics. Roughness and texturedness could also be classified based on the brain activation patterns in visual cortex, whereas hardness could not. Importantly, the agreement in classification based on image statistics and brain activation was also above chance level. Our results show that information about visual material properties is to a large degree contained in low-level image statistics, and that these image statistics are also partially reflected in brain activity patterns induced by the perception of material images. PMID:27582714

Image Statistics and the Representation of Material Properties in the Visual Cortex.

PubMed

Baumgartner, Elisabeth; Gegenfurtner, Karl R

2016-01-01

We explored perceived material properties (roughness, texturedness, and hardness) with a novel approach that compares perception, image statistics and brain activation, as measured with fMRI. We initially asked participants to rate 84 material images with respect to the above mentioned properties, and then scanned 15 of the participants with fMRI while they viewed the material images. The images were analyzed with a set of image statistics capturing their spatial frequency and texture properties. Linear classifiers were then applied to the image statistics as well as the voxel patterns of visually responsive voxels and early visual areas to discriminate between images with high and low perceptual ratings. Roughness and texturedness could be classified above chance level based on image statistics. Roughness and texturedness could also be classified based on the brain activation patterns in visual cortex, whereas hardness could not. Importantly, the agreement in classification based on image statistics and brain activation was also above chance level. Our results show that information about visual material properties is to a large degree contained in low-level image statistics, and that these image statistics are also partially reflected in brain activity patterns induced by the perception of material images.

Active Learning to Overcome Sample Selection Bias: Application to Photometric Variable Star Classification

NASA Astrophysics Data System (ADS)

Richards, Joseph W.; Starr, Dan L.; Brink, Henrik; Miller, Adam A.; Bloom, Joshua S.; Butler, Nathaniel R.; James, J. Berian; Long, James P.; Rice, John

2012-01-01

Despite the great promise of machine-learning algorithms to classify and predict astrophysical parameters for the vast numbers of astrophysical sources and transients observed in large-scale surveys, the peculiarities of the training data often manifest as strongly biased predictions on the data of interest. Typically, training sets are derived from historical surveys of brighter, more nearby objects than those from more extensive, deeper surveys (testing data). This sample selection bias can cause catastrophic errors in predictions on the testing data because (1) standard assumptions for machine-learned model selection procedures break down and (2) dense regions of testing space might be completely devoid of training data. We explore possible remedies to sample selection bias, including importance weighting, co-training, and active learning (AL). We argue that AL—where the data whose inclusion in the training set would most improve predictions on the testing set are queried for manual follow-up—is an effective approach and is appropriate for many astronomical applications. For a variable star classification problem on a well-studied set of stars from Hipparcos and Optical Gravitational Lensing Experiment, AL is the optimal method in terms of error rate on the testing data, beating the off-the-shelf classifier by 3.4% and the other proposed methods by at least 3.0%. To aid with manual labeling of variable stars, we developed a Web interface which allows for easy light curve visualization and querying of external databases. Finally, we apply AL to classify variable stars in the All Sky Automated Survey, finding dramatic improvement in our agreement with the ASAS Catalog of Variable Stars, from 65.5% to 79.5%, and a significant increase in the classifier's average confidence for the testing set, from 14.6% to 42.9%, after a few AL iterations.

VizioMetrics: Mining the Scientific Visual Literature

ERIC Educational Resources Information Center

Lee, Po-Shen

2017-01-01

Scientific results are communicated visually in the literature through diagrams, visualizations, and photographs. In this thesis, we developed a figure processing pipeline to classify more than 8 million figures from PubMed Central into different figure types and study the resulting patterns of visual information as they relate to scholarly…

Mid-level image representations for real-time heart view plane classification of echocardiograms.

PubMed

Penatti, Otávio A B; Werneck, Rafael de O; de Almeida, Waldir R; Stein, Bernardo V; Pazinato, Daniel V; Mendes Júnior, Pedro R; Torres, Ricardo da S; Rocha, Anderson

2015-11-01

In this paper, we explore mid-level image representations for real-time heart view plane classification of 2D echocardiogram ultrasound images. The proposed representations rely on bags of visual words, successfully used by the computer vision community in visual recognition problems. An important element of the proposed representations is the image sampling with large regions, drastically reducing the execution time of the image characterization procedure. Throughout an extensive set of experiments, we evaluate the proposed approach against different image descriptors for classifying four heart view planes. The results show that our approach is effective and efficient for the target problem, making it suitable for use in real-time setups. The proposed representations are also robust to different image transformations, e.g., downsampling, noise filtering, and different machine learning classifiers, keeping classification accuracy above 90%. Feature extraction can be performed in 30 fps or 60 fps in some cases. This paper also includes an in-depth review of the literature in the area of automatic echocardiogram view classification giving the reader a through comprehension of this field of study. Copyright © 2015 Elsevier Ltd. All rights reserved.

Automated classification of articular cartilage surfaces based on surface texture.

PubMed

Stachowiak, G P; Stachowiak, G W; Podsiadlo, P

2006-11-01

In this study the automated classification system previously developed by the authors was used to classify articular cartilage surfaces with different degrees of wear. This automated system classifies surfaces based on their texture. Plug samples of sheep cartilage (pins) were run on stainless steel discs under various conditions using a pin-on-disc tribometer. Testing conditions were specifically designed to produce different severities of cartilage damage due to wear. Environmental scanning electron microscope (SEM) (ESEM) images of cartilage surfaces, that formed a database for pattern recognition analysis, were acquired. The ESEM images of cartilage were divided into five groups (classes), each class representing different wear conditions or wear severity. Each class was first examined and assessed visually. Next, the automated classification system (pattern recognition) was applied to all classes. The results of the automated surface texture classification were compared to those based on visual assessment of surface morphology. It was shown that the texture-based automated classification system was an efficient and accurate method of distinguishing between various cartilage surfaces generated under different wear conditions. It appears that the texture-based classification method has potential to become a useful tool in medical diagnostics.

Galaxy Zoo: quantitative visual morphological classifications for 48 000 galaxies from CANDELS

NASA Astrophysics Data System (ADS)

Simmons, B. D.; Lintott, Chris; Willett, Kyle W.; Masters, Karen L.; Kartaltepe, Jeyhan S.; Häußler, Boris; Kaviraj, Sugata; Krawczyk, Coleman; Kruk, S. J.; McIntosh, Daniel H.; Smethurst, R. J.; Nichol, Robert C.; Scarlata, Claudia; Schawinski, Kevin; Conselice, Christopher J.; Almaini, Omar; Ferguson, Henry C.; Fortson, Lucy; Hartley, William; Kocevski, Dale; Koekemoer, Anton M.; Mortlock, Alice; Newman, Jeffrey A.; Bamford, Steven P.; Grogin, N. A.; Lucas, Ray A.; Hathi, Nimish P.; McGrath, Elizabeth; Peth, Michael; Pforr, Janine; Rizer, Zachary; Wuyts, Stijn; Barro, Guillermo; Bell, Eric F.; Castellano, Marco; Dahlen, Tomas; Dekel, Avishai; Ownsworth, Jamie; Faber, Sandra M.; Finkelstein, Steven L.; Fontana, Adriano; Galametz, Audrey; Grützbauch, Ruth; Koo, David; Lotz, Jennifer; Mobasher, Bahram; Mozena, Mark; Salvato, Mara; Wiklind, Tommy

2017-02-01

We present quantified visual morphologies of approximately 48 000 galaxies observed in three Hubble Space Telescope legacy fields by the Cosmic Assembly Near-infrared Deep Extragalactic Legacy Survey (CANDELS) and classified by participants in the Galaxy Zoo project. 90 per cent of galaxies have z ≤ 3 and are observed in rest-frame optical wavelengths by CANDELS. Each galaxy received an average of 40 independent classifications, which we combine into detailed morphological information on galaxy features such as clumpiness, bar instabilities, spiral structure, and merger and tidal signatures. We apply a consensus-based classifier weighting method that preserves classifier independence while effectively down-weighting significantly outlying classifications. After analysing the effect of varying image depth on reported classifications, we also provide depth-corrected classifications which both preserve the information in the deepest observations and also enable the use of classifications at comparable depths across the full survey. Comparing the Galaxy Zoo classifications to previous classifications of the same galaxies shows very good agreement; for some applications, the high number of independent classifications provided by Galaxy Zoo provides an advantage in selecting galaxies with a particular morphological profile, while in others the combination of Galaxy Zoo with other classifications is a more promising approach than using any one method alone. We combine the Galaxy Zoo classifications of `smooth' galaxies with parametric morphologies to select a sample of featureless discs at 1 ≤ z ≤ 3, which may represent a dynamically warmer progenitor population to the settled disc galaxies seen at later epochs.

A hybrid sensing approach for pure and adulterated honey classification.

PubMed

Subari, Norazian; Mohamad Saleh, Junita; Md Shakaff, Ali Yeon; Zakaria, Ammar

2012-10-17

This paper presents a comparison between data from single modality and fusion methods to classify Tualang honey as pure or adulterated using Linear Discriminant Analysis (LDA) and Principal Component Analysis (PCA) statistical classification approaches. Ten different brands of certified pure Tualang honey were obtained throughout peninsular Malaysia and Sumatera, Indonesia. Various concentrations of two types of sugar solution (beet and cane sugar) were used in this investigation to create honey samples of 20%, 40%, 60% and 80% adulteration concentrations. Honey data extracted from an electronic nose (e-nose) and Fourier Transform Infrared Spectroscopy (FTIR) were gathered, analyzed and compared based on fusion methods. Visual observation of classification plots revealed that the PCA approach able to distinct pure and adulterated honey samples better than the LDA technique. Overall, the validated classification results based on FTIR data (88.0%) gave higher classification accuracy than e-nose data (76.5%) using the LDA technique. Honey classification based on normalized low-level and intermediate-level FTIR and e-nose fusion data scored classification accuracies of 92.2% and 88.7%, respectively using the Stepwise LDA method. The results suggested that pure and adulterated honey samples were better classified using FTIR and e-nose fusion data than single modality data.

SDSS-IV MaNGA: stellar angular momentum of about 2300 galaxies: unveiling the bimodality of massive galaxy properties

NASA Astrophysics Data System (ADS)

Graham, Mark T.; Cappellari, Michele; Li, Hongyu; Mao, Shude; Bershady, Matthew A.; Bizyaev, Dmitry; Brinkmann, Jonathan; Brownstein, Joel R.; Bundy, Kevin; Drory, Niv; Law, David R.; Pan, Kaike; Thomas, Daniel; Wake, David A.; Weijmans, Anne-Marie; Westfall, Kyle B.; Yan, Renbin

2018-07-01

We measure λ _{R_e}, a proxy for galaxy specific stellar angular momentum within one effective radius, and the ellipticity, ɛ, for about 2300 galaxies of all morphological types observed with integral field spectroscopy as part of the Mapping Nearby Galaxies at Apache Point Observatory survey, the largest such sample to date. We use the (λ _{R_e}, ɛ ) diagram to separate early-type galaxies into fast and slow rotators. We also visually classify each galaxy according to its optical morphology and two-dimensional stellar velocity field. Comparing these classifications to quantitative λ _{R_e} measurements reveals tight relationships between angular momentum and galaxy structure. In order to account for atmospheric seeing, we use realistic models of galaxy kinematics to derive a general approximate analytic correction for λ _{R_e}. Thanks to the size of the sample and the large number of massive galaxies, we unambiguously detect a clear bimodality in the (λ _{R_e}, ɛ ) diagram which may result from fundamental differences in galaxy assembly history. There is a sharp secondary density peak inside the region of the diagram with low λ _{R_e} and ɛ < 0.4, previously suggested as the definition for slow rotators. Most of these galaxies are visually classified as non-regular rotators and have high velocity dispersion. The intrinsic bimodality must be stronger, as it tends to be smoothed by noise and inclination. The large sample of slow rotators allows us for the first time to unveil a secondary peak at ±90° in their distribution of the misalignments between the photometric and kinematic position angles. We confirm that genuine slow rotators start appearing above M ≥ 2 × 1011 M⊙ where a significant number of high-mass fast rotators also exist.

SDSS-IV MaNGA: Stellar angular momentum of about 2300 galaxies: unveiling the bimodality of massive galaxy properties

NASA Astrophysics Data System (ADS)

Graham, Mark T.; Cappellari, Michele; Li, Hongyu; Mao, Shude; Bershady, Matthew; Bizyaev, Dmitry; Brinkmann, Jonathan; Brownstein, Joel R.; Bundy, Kevin; Drory, Niv; Law, David R.; Pan, Kaike; Thomas, Daniel; Wake, David A.; Weijmans, Anne-Marie; Westfall, Kyle B.; Yan, Renbin

2018-03-01

We measure λ _{R_e}, a proxy for galaxy specific stellar angular momentum within one effective radius, and the ellipticity, ɛ, for about 2300 galaxies of all morphological types observed with integral field spectroscopy as part of the MaNGA survey, the largest such sample to date. We use the (λ _{R_e}, ɛ ) diagram to separate early-type galaxies into fast and slow rotators. We also visually classify each galaxy according to its optical morphology and two-dimensional stellar velocity field. Comparing these classifications to quantitative λ _{R_e} measurements reveals tight relationships between angular momentum and galaxy structure. In order to account for atmospheric seeing, we use realistic models of galaxy kinematics to derive a general approximate analytic correction for λ _{R_e}. Thanks to the size of the sample and the large number of massive galaxies, we unambiguously detect a clear bimodality in the (λ _{R_e}, ɛ ) diagram which may result from fundamental differences in galaxy assembly history. There is a sharp secondary density peak inside the region of the diagram with low λ _{R_e} and ɛ < 0.4, previously suggested as the definition for slow rotators. Most of these galaxies are visually classified as non-regular rotators and have high velocity dispersion. The intrinsic bimodality must be stronger, as it tends to be smoothed by noise and inclination. The large sample of slow rotators allows us for the first time to unveil a secondary peak at ±90○ in their distribution of the misalignments between the photometric and kinematic position angles. We confirm that genuine slow rotators start appearing above M ≥ 2 × 1011M⊙ where a significant number of high-mass fast rotators also exist.

Visual, Algebraic and Mixed Strategies in Visually Presented Linear Programming Problems.

ERIC Educational Resources Information Center

Shama, Gilli; Dreyfus, Tommy

1994-01-01

Identified and classified solution strategies of (n=49) 10th-grade students who were presented with linear programming problems in a predominantly visual setting in the form of a computerized game. Visual strategies were developed more frequently than either algebraic or mixed strategies. Appendix includes questionnaires. (Contains 11 references.)…

Landmark Image Retrieval by Jointing Feature Refinement and Multimodal Classifier Learning.

PubMed

Zhang, Xiaoming; Wang, Senzhang; Li, Zhoujun; Ma, Shuai; Xiaoming Zhang; Senzhang Wang; Zhoujun Li; Shuai Ma; Ma, Shuai; Zhang, Xiaoming; Wang, Senzhang; Li, Zhoujun

2018-06-01

Landmark retrieval is to return a set of images with their landmarks similar to those of the query images. Existing studies on landmark retrieval focus on exploiting the geometries of landmarks for visual similarity matches. However, the visual content of social images is of large diversity in many landmarks, and also some images share common patterns over different landmarks. On the other side, it has been observed that social images usually contain multimodal contents, i.e., visual content and text tags, and each landmark has the unique characteristic of both visual content and text content. Therefore, the approaches based on similarity matching may not be effective in this environment. In this paper, we investigate whether the geographical correlation among the visual content and the text content could be exploited for landmark retrieval. In particular, we propose an effective multimodal landmark classification paradigm to leverage the multimodal contents of social image for landmark retrieval, which integrates feature refinement and landmark classifier with multimodal contents by a joint model. The geo-tagged images are automatically labeled for classifier learning. Visual features are refined based on low rank matrix recovery, and multimodal classification combined with group sparse is learned from the automatically labeled images. Finally, candidate images are ranked by combining classification result and semantic consistence measuring between the visual content and text content. Experiments on real-world datasets demonstrate the superiority of the proposed approach as compared to existing methods.

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.

46 CFR 108.187 - Ventilation for brush type electric motors in classified spaces.

Code of Federal Regulations, 2010 CFR

2010-10-01

... 46 Shipping 4 2010-10-01 2010-10-01 false Ventilation for brush type electric motors in classified... Ventilation for brush type electric motors in classified spaces. Ventilation for brush type electric motors in... Electrical Equipment in Hazardous Locations”, except audible and visual alarms may be used if shutting down...

Classifying the Perceptual Interpretations of a Bistable Image Using EEG and Artificial Neural Networks

PubMed Central

Hramov, Alexander E.; Maksimenko, Vladimir A.; Pchelintseva, Svetlana V.; Runnova, Anastasiya E.; Grubov, Vadim V.; Musatov, Vyacheslav Yu.; Zhuravlev, Maksim O.; Koronovskii, Alexey A.; Pisarchik, Alexander N.

2017-01-01

In order to classify different human brain states related to visual perception of ambiguous images, we use an artificial neural network (ANN) to analyze multichannel EEG. The classifier built on the basis of a multilayer perceptron achieves up to 95% accuracy in classifying EEG patterns corresponding to two different interpretations of the Necker cube. The important feature of our classifier is that trained on one subject it can be used for the classification of EEG traces of other subjects. This result suggests the existence of common features in the EEG structure associated with distinct interpretations of bistable objects. We firmly believe that the significance of our results is not limited to visual perception of the Necker cube images; the proposed experimental approach and developed computational technique based on ANN can also be applied to study and classify different brain states using neurophysiological data recordings. This may give new directions for future research in the field of cognitive and pathological brain activity, and for the development of brain-computer interfaces. PMID:29255403

Mapping land use changes in the carboniferous region of Santa Catarina, report 2

NASA Technical Reports Server (NTRS)

Valeriano, D. D. (Principal Investigator); Bitencourtpereira, M. D.

1983-01-01

The techniques applied to MSS-LANDSAT data in the land-use mapping of Criciuma region (Santa Catarina state, Brazil) are presented along with the results of a classification accuracy estimate tested on the resulting map. The MSS-LANDSAT data digital processing involves noise suppression, features selection and a hybrid classifier. The accuracy test is made through comparisons with aerial photographs of sampled points. The utilization of digital processing to map the classes agricultural lands, forest lands and urban areas is recommended, while the coal refuse areas should be mapped visually.

Identification of Age-Related Macular Degeneration Using OCT Images

NASA Astrophysics Data System (ADS)

Arabi, Punal M., Dr; Krishna, Nanditha; Ashwini, V.; Prathibha, H. M.

2018-02-01

Age-related Macular Degeneration is the most leading retinal disease in the recent years. Macular degeneration occurs when the central portion of the retina, called macula deteriorates. As the deterioration occurs with the age, it is commonly referred as Age-related Macular Degeneration. This disease can be visualized by several imaging modalities such as Fundus imaging technique, Optical Coherence Tomography (OCT) technique and many other. Optical Coherence Tomography is the widely used technique for screening the Age-related Macular Degeneration disease, because it has an ability to detect the very minute changes in the retina. The Healthy and AMD affected OCT images are classified by extracting the Retinal Pigmented Epithelium (RPE) layer of the images using the image processing technique. The extracted layer is sampled, the no. of white pixels in each of the sample is counted and the mean value of the no. of pixels is calculated. The average mean value is calculated for both the Healthy and the AMD affected images and a threshold value is fixed and a decision rule is framed to classify the images of interest. The proposed method showed an accuracy of 75%.

Validation of the Preverbal Visual Assessment (PreViAs) questionnaire.

PubMed

García-Ormaechea, Inés; González, Inmaculada; Duplá, María; Andres, Eva; Pueyo, Victoria

2014-10-01

Visual cognitive integrative functions need to be evaluated by a behavioral assessment, which requires an experienced evaluator. The Preverbal Visual Assessment (PreViAs) questionnaire was designed to evaluate these functions, both in general pediatric population or in children with high risk of visual cognitive problems, through primary caregivers' answers. We aimed to validate the PreViAs questionnaire by comparing caregiver reports with results from a comprehensive clinical protocol. A total of 220 infants (<2 years old) were divided into two groups according to visual development, as determined by the clinical protocol. Their primary caregivers completed the PreViAs questionnaire, which consists of 30 questions related to one or more visual domains: visual attention, visual communication, visual-motor coordination, and visual processing. Questionnaire answers were compared with results of behavioral assessments performed by three pediatric ophthalmologists. Results of the clinical protocol classified 128 infants as having normal visual maturation, and 92 as having abnormal visual maturation. The specificity of PreViAs questionnaire was >80%, and sensitivity was 64%-79%. More than 80% of the infants were correctly classified, and test-retest reliability exceeded 0.9 for all domains. The PreViAs questionnaire is useful to detect abnormal visual maturation in infants from birth to 24months of age. It improves the anamnesis process in infants at risk of visual dysfunctions. Copyright © 2014. Published by Elsevier Ireland Ltd.

Towards exaggerated emphysema stereotypes

NASA Astrophysics Data System (ADS)

Chen, C.; Sørensen, L.; Lauze, F.; Igel, C.; Loog, M.; Feragen, A.; de Bruijne, M.; Nielsen, M.

2012-03-01

Classification is widely used in the context of medical image analysis and in order to illustrate the mechanism of a classifier, we introduce the notion of an exaggerated image stereotype based on training data and trained classifier. The stereotype of some image class of interest should emphasize/exaggerate the characteristic patterns in an image class and visualize the information the employed classifier relies on. This is useful for gaining insight into the classification and serves for comparison with the biological models of disease. In this work, we build exaggerated image stereotypes by optimizing an objective function which consists of a discriminative term based on the classification accuracy, and a generative term based on the class distributions. A gradient descent method based on iterated conditional modes (ICM) is employed for optimization. We use this idea with Fisher's linear discriminant rule and assume a multivariate normal distribution for samples within a class. The proposed framework is applied to computed tomography (CT) images of lung tissue with emphysema. The synthesized stereotypes illustrate the exaggerated patterns of lung tissue with emphysema, which is underpinned by three different quantitative evaluation methods.

A systematic comparison of different object-based classification techniques using high spatial resolution imagery in agricultural environments

NASA Astrophysics Data System (ADS)

Li, Manchun; Ma, Lei; Blaschke, Thomas; Cheng, Liang; Tiede, Dirk

2016-07-01

Geographic Object-Based Image Analysis (GEOBIA) is becoming more prevalent in remote sensing classification, especially for high-resolution imagery. Many supervised classification approaches are applied to objects rather than pixels, and several studies have been conducted to evaluate the performance of such supervised classification techniques in GEOBIA. However, these studies did not systematically investigate all relevant factors affecting the classification (segmentation scale, training set size, feature selection and mixed objects). In this study, statistical methods and visual inspection were used to compare these factors systematically in two agricultural case studies in China. The results indicate that Random Forest (RF) and Support Vector Machines (SVM) are highly suitable for GEOBIA classifications in agricultural areas and confirm the expected general tendency, namely that the overall accuracies decline with increasing segmentation scale. All other investigated methods except for RF and SVM are more prone to obtain a lower accuracy due to the broken objects at fine scales. In contrast to some previous studies, the RF classifiers yielded the best results and the k-nearest neighbor classifier were the worst results, in most cases. Likewise, the RF and Decision Tree classifiers are the most robust with or without feature selection. The results of training sample analyses indicated that the RF and adaboost. M1 possess a superior generalization capability, except when dealing with small training sample sizes. Furthermore, the classification accuracies were directly related to the homogeneity/heterogeneity of the segmented objects for all classifiers. Finally, it was suggested that RF should be considered in most cases for agricultural mapping.

A Visual Galaxy Classification Interface and its Classroom Application

NASA Astrophysics Data System (ADS)

Kautsch, Stefan J.; Phung, Chau; VanHilst, Michael; Castro, Victor H

2014-06-01

Galaxy morphology is an important topic in modern astronomy to understand questions concerning the evolution and formation of galaxies and their dark matter content. In order to engage students in exploring galaxy morphology, we developed a web-based, graphical interface that allows students to visually classify galaxy images according to various morphological types. The website is designed with HTML5, JavaScript, PHP, and a MySQL database. The classification interface provides hands-on research experience and training for students and interested clients, and allows them to contribute to studies of galaxy morphology. We present the first results of a pilot study and compare the visually classified types using our interface with that from automated classification routines.

Visual Problems and Reading. Number 4.

ERIC Educational Resources Information Center

Griffin, Margaret; Eberly, Donald W.

As one of a series commissioned by the National Reading Center to help inform all citizens about reading issues and to promote national functional literacy, this brochure is designed to acquaint readers with different forms of visual impairment, and describes their symptoms for easy recognition. Visual difficulties are classified into two major…

Visual Communication for Medicines: Malignant Assumptions and Benign Design?

ERIC Educational Resources Information Center

van der Waarde, Karel

2010-01-01

An area of visual communication that might be classified as a "design failure" is the visual presentation of information about "prescription-only medicines" for patients. This information is provided on packaging, leaflets, brochures, labels and websites. The practical issue is that there are problems in convincing patients to…

Residential scene classification for gridded population sampling in developing countries using deep convolutional neural networks on satellite imagery.

PubMed

Chew, Robert F; Amer, Safaa; Jones, Kasey; Unangst, Jennifer; Cajka, James; Allpress, Justine; Bruhn, Mark

2018-05-09

Conducting surveys in low- and middle-income countries is often challenging because many areas lack a complete sampling frame, have outdated census information, or have limited data available for designing and selecting a representative sample. Geosampling is a probability-based, gridded population sampling method that addresses some of these issues by using geographic information system (GIS) tools to create logistically manageable area units for sampling. GIS grid cells are overlaid to partition a country's existing administrative boundaries into area units that vary in size from 50 m × 50 m to 150 m × 150 m. To avoid sending interviewers to unoccupied areas, researchers manually classify grid cells as "residential" or "nonresidential" through visual inspection of aerial images. "Nonresidential" units are then excluded from sampling and data collection. This process of manually classifying sampling units has drawbacks since it is labor intensive, prone to human error, and creates the need for simplifying assumptions during calculation of design-based sampling weights. In this paper, we discuss the development of a deep learning classification model to predict whether aerial images are residential or nonresidential, thus reducing manual labor and eliminating the need for simplifying assumptions. On our test sets, the model performs comparable to a human-level baseline in both Nigeria (94.5% accuracy) and Guatemala (96.4% accuracy), and outperforms baseline machine learning models trained on crowdsourced or remote-sensed geospatial features. Additionally, our findings suggest that this approach can work well in new areas with relatively modest amounts of training data. Gridded population sampling methods like geosampling are becoming increasingly popular in countries with outdated or inaccurate census data because of their timeliness, flexibility, and cost. Using deep learning models directly on satellite images, we provide a novel method for sample frame construction that identifies residential gridded aerial units. In cases where manual classification of satellite images is used to (1) correct for errors in gridded population data sets or (2) classify grids where population estimates are unavailable, this methodology can help reduce annotation burden with comparable quality to human analysts.

CRF: detection of CRISPR arrays using random forest.

PubMed

Wang, Kai; Liang, Chun

2017-01-01

CRISPRs (clustered regularly interspaced short palindromic repeats) are particular repeat sequences found in wide range of bacteria and archaea genomes. Several tools are available for detecting CRISPR arrays in the genomes of both domains. Here we developed a new web-based CRISPR detection tool named CRF (CRISPR Finder by Random Forest). Different from other CRISPR detection tools, a random forest classifier was used in CRF to filter out invalid CRISPR arrays from all putative candidates and accordingly enhanced detection accuracy. In CRF, particularly, triplet elements that combine both sequence content and structure information were extracted from CRISPR repeats for classifier training. The classifier achieved high accuracy and sensitivity. Moreover, CRF offers a highly interactive web interface for robust data visualization that is not available among other CRISPR detection tools. After detection, the query sequence, CRISPR array architecture, and the sequences and secondary structures of CRISPR repeats and spacers can be visualized for visual examination and validation. CRF is freely available at http://bioinfolab.miamioh.edu/crf/home.php.

Comparison of Classifiers for Decoding Sensory and Cognitive Information from Prefrontal Neuronal Populations

PubMed Central

Astrand, Elaine; Enel, Pierre; Ibos, Guilhem; Dominey, Peter Ford; Baraduc, Pierre; Ben Hamed, Suliann

2014-01-01

Decoding neuronal information is important in neuroscience, both as a basic means to understand how neuronal activity is related to cerebral function and as a processing stage in driving neuroprosthetic effectors. Here, we compare the readout performance of six commonly used classifiers at decoding two different variables encoded by the spiking activity of the non-human primate frontal eye fields (FEF): the spatial position of a visual cue, and the instructed orientation of the animal's attention. While the first variable is exogenously driven by the environment, the second variable corresponds to the interpretation of the instruction conveyed by the cue; it is endogenously driven and corresponds to the output of internal cognitive operations performed on the visual attributes of the cue. These two variables were decoded using either a regularized optimal linear estimator in its explicit formulation, an optimal linear artificial neural network estimator, a non-linear artificial neural network estimator, a non-linear naïve Bayesian estimator, a non-linear Reservoir recurrent network classifier or a non-linear Support Vector Machine classifier. Our results suggest that endogenous information such as the orientation of attention can be decoded from the FEF with the same accuracy as exogenous visual information. All classifiers did not behave equally in the face of population size and heterogeneity, the available training and testing trials, the subject's behavior and the temporal structure of the variable of interest. In most situations, the regularized optimal linear estimator and the non-linear Support Vector Machine classifiers outperformed the other tested decoders. PMID:24466019

Prevalence of Staphylococcal Enterotoxins in Ready-to-Eat Foods Sold in Istanbul.

PubMed

Ulusoy, Beyza H; Çakmak Sancar, Burcu; Öztürk, Muhsin

2017-10-01

The aim of this study was to investigate the prevalence of staphylococcal enterotoxins (SEs) in ready-to-eat (RTE) foods sold in Istanbul, Turkey. A total of 5,241 samples were randomly collected from various caterers, hotels, and restaurants from 2014 to 2016. The samples were classified into four groups: (i) various cooked RTE meat and vegetable meals, (ii) various RTE salads, charcuterie, and cold appetizers, (iii) various cooked RTE bakery products (pasta, pastries, pizza, pita, ravioli, etc.), and (iv) any cooked RTE sweets and desserts (pudding, custard, cream, ashura, etc.). The samples were examined for the presence of SEs by 3M Tecra Staph Enterotoxin Visual Immunoassay method, which is a manual enzyme-linked immunosorbent assay method. Among all samples, only 1 (0.019%) RTE meal (vegetable meal with meat) was found to be contaminated with SEs, a good result in terms of staphylococcal food poisoning risk and public health.

Real-time decoding of the direction of covert visuospatial attention

NASA Astrophysics Data System (ADS)

Andersson, Patrik; Ramsey, Nick F.; Raemaekers, Mathijs; Viergever, Max A.; Pluim, Josien P. W.

2012-08-01

Brain-computer interfaces (BCIs) make it possible to translate a person’s intentions into actions without depending on the muscular system. Brain activity is measured and classified into commands, thereby creating a direct link between the mind and the environment, enabling, e.g., cursor control or navigation of a wheelchair or robot. Most BCI research is conducted with scalp EEG but recent developments move toward intracranial electrodes for paralyzed people. The vast majority of BCI studies focus on the motor system as the appropriate target for recording and decoding movement intentions. However, properties of the visual system may make the visual system an attractive and intuitive alternative. We report on a study investigating feasibility of decoding covert visuospatial attention in real time, exploiting the full potential of a 7 T MRI scanner to obtain the necessary signal quality, capitalizing on earlier fMRI studies indicating that covert visuospatial attention changes activity in the visual areas that respond to stimuli presented in the attended area of the visual field. Healthy volunteers were instructed to shift their attention from the center of the screen to one of four static targets in the periphery, without moving their eyes from the center. During the first part of the fMRI-run, the relevant brain regions were located using incremental statistical analysis. During the second part, the activity in these regions was extracted and classified, and the subject was given visual feedback of the result. Performance was assessed as the number of trials where the real-time classifier correctly identified the direction of attention. On average, 80% of trials were correctly classified (chance level <25%) based on a single image volume, indicating very high decoding performance. While we restricted the experiment to five attention target regions (four peripheral and one central), the number of directions can be higher provided the brain activity patterns can be distinguished. In summary, the visual system promises to be an effective target for BCI control.

Control of a visual keyboard using an electrocorticographic brain-computer interface.

PubMed

Krusienski, Dean J; Shih, Jerry J

2011-05-01

Brain-computer interfaces (BCIs) are devices that enable severely disabled people to communicate and interact with their environments using their brain waves. Most studies investigating BCI in humans have used scalp EEG as the source of electrical signals and focused on motor control of prostheses or computer cursors on a screen. The authors hypothesize that the use of brain signals obtained directly from the cortical surface will more effectively control a communication/spelling task compared to scalp EEG. A total of 6 patients with medically intractable epilepsy were tested for the ability to control a visual keyboard using electrocorticographic (ECOG) signals. ECOG data collected during a P300 visual task paradigm were preprocessed and used to train a linear classifier to subsequently predict the intended target letters. The classifier was able to predict the intended target character at or near 100% accuracy using fewer than 15 stimulation sequences in 5 of the 6 people tested. ECOG data from electrodes outside the language cortex contributed to the classifier and enabled participants to write words on a visual keyboard. This is a novel finding because previous invasive BCI research in humans used signals exclusively from the motor cortex to control a computer cursor or prosthetic device. These results demonstrate that ECOG signals from electrodes both overlying and outside the language cortex can reliably control a visual keyboard to generate language output without voice or limb movements.

Land-cover mapping of Red Rock Canyon National Conservation Area and Coyote Springs, Piute-Eldorado Valley, and Mormon Mesa Areas of Critical Environmental Concern, Clark County, Nevada

USGS Publications Warehouse

Smith, J. LaRue; Damar, Nancy A.; Charlet, David A.; Westenburg, Craig L.

2014-01-01

DigitalGlobe’s QuickBird satellite high-resolution multispectral imagery was classified by using Visual Learning Systems’ Feature Analyst feature extraction software to produce land-cover data sets for the Red Rock Canyon National Conservation Area and the Coyote Springs, Piute-Eldorado Valley, and Mormon Mesa Areas of Critical Environmental Concern in Clark County, Nevada. Over 1,000 vegetation field samples were collected at the stand level. The field samples were classified to the National Vegetation Classification Standard, Version 2 hierarchy at the alliance level and above. Feature extraction models were developed for vegetation on the basis of the spectral and spatial characteristics of selected field samples by using the Feature Analyst hierarchical learning process. Individual model results were merged to create one data set for the Red Rock Canyon National Conservation Area and one for each of the Areas of Critical Environmental Concern. Field sample points and photographs were used to validate and update the data set after model results were merged. Non-vegetation data layers, such as roads and disturbed areas, were delineated from the imagery and added to the final data sets. The resulting land-cover data sets are significantly more detailed than previously were available, both in resolution and in vegetation classes.

A Hybrid Sensing Approach for Pure and Adulterated Honey Classification

PubMed Central

Subari, Norazian; Saleh, Junita Mohamad; Shakaff, Ali Yeon Md; Zakaria, Ammar

2012-01-01

This paper presents a comparison between data from single modality and fusion methods to classify Tualang honey as pure or adulterated using Linear Discriminant Analysis (LDA) and Principal Component Analysis (PCA) statistical classification approaches. Ten different brands of certified pure Tualang honey were obtained throughout peninsular Malaysia and Sumatera, Indonesia. Various concentrations of two types of sugar solution (beet and cane sugar) were used in this investigation to create honey samples of 20%, 40%, 60% and 80% adulteration concentrations. Honey data extracted from an electronic nose (e-nose) and Fourier Transform Infrared Spectroscopy (FTIR) were gathered, analyzed and compared based on fusion methods. Visual observation of classification plots revealed that the PCA approach able to distinct pure and adulterated honey samples better than the LDA technique. Overall, the validated classification results based on FTIR data (88.0%) gave higher classification accuracy than e-nose data (76.5%) using the LDA technique. Honey classification based on normalized low-level and intermediate-level FTIR and e-nose fusion data scored classification accuracies of 92.2% and 88.7%, respectively using the Stepwise LDA method. The results suggested that pure and adulterated honey samples were better classified using FTIR and e-nose fusion data than single modality data. PMID:23202033

Visual classification of very fine-grained sediments: Evaluation through univariate and multivariate statistics

USGS Publications Warehouse

Hohn, M. Ed; Nuhfer, E.B.; Vinopal, R.J.; Klanderman, D.S.

1980-01-01

Classifying very fine-grained rocks through fabric elements provides information about depositional environments, but is subject to the biases of visual taxonomy. To evaluate the statistical significance of an empirical classification of very fine-grained rocks, samples from Devonian shales in four cored wells in West Virginia and Virginia were measured for 15 variables: quartz, illite, pyrite and expandable clays determined by X-ray diffraction; total sulfur, organic content, inorganic carbon, matrix density, bulk density, porosity, silt, as well as density, sonic travel time, resistivity, and ??-ray response measured from well logs. The four lithologic types comprised: (1) sharply banded shale, (2) thinly laminated shale, (3) lenticularly laminated shale, and (4) nonbanded shale. Univariate and multivariate analyses of variance showed that the lithologic classification reflects significant differences for the variables measured, difference that can be detected independently of stratigraphic effects. Little-known statistical methods found useful in this work included: the multivariate analysis of variance with more than one effect, simultaneous plotting of samples and variables on canonical variates, and the use of parametric ANOVA and MANOVA on ranked data. ?? 1980 Plenum Publishing Corporation.

Cognitive Visual Dysfunctions in Preterm Children with Periventricular Leukomalacia

ERIC Educational Resources Information Center

Fazzi, Elisa; Bova, Stefania; Giovenzana, Alessia; Signorini, Sabrina; Uggetti, Carla; Bianchi, Paolo

2009-01-01

Aim: Cognitive visual dysfunctions (CVDs) reflect an impairment of the capacity to process visual information. The question of whether CVDs might be classifiable according to the nature and distribution of the underlying brain damage is an intriguing one in child neuropsychology. Method: We studied 22 children born preterm (12 males, 10 females;…

Visual Imagery for Letters and Words. Final Report.

ERIC Educational Resources Information Center

Weber, Robert J.

In a series of six experiments, undergraduate college students visually imagined letters or words and then classified as rapidly as possible the imagined letters for some physical property such as vertical height. This procedure allowed for a preliminary assessment of the temporal parameters of visual imagination. The results delineate a number of…

Computer vision-based method for classification of wheat grains using artificial neural network.

PubMed

Sabanci, Kadir; Kayabasi, Ahmet; Toktas, Abdurrahim

2017-06-01

A simplified computer vision-based application using artificial neural network (ANN) depending on multilayer perceptron (MLP) for accurately classifying wheat grains into bread or durum is presented. The images of 100 bread and 100 durum wheat grains are taken via a high-resolution camera and subjected to pre-processing. The main visual features of four dimensions, three colors and five textures are acquired using image-processing techniques (IPTs). A total of 21 visual features are reproduced from the 12 main features to diversify the input population for training and testing the ANN model. The data sets of visual features are considered as input parameters of the ANN model. The ANN with four different input data subsets is modelled to classify the wheat grains into bread or durum. The ANN model is trained with 180 grains and its accuracy tested with 20 grains from a total of 200 wheat grains. Seven input parameters that are most effective on the classifying results are determined using the correlation-based CfsSubsetEval algorithm to simplify the ANN model. The results of the ANN model are compared in terms of accuracy rate. The best result is achieved with a mean absolute error (MAE) of 9.8 × 10 -6 by the simplified ANN model. This shows that the proposed classifier based on computer vision can be successfully exploited to automatically classify a variety of grains. © 2016 Society of Chemical Industry. © 2016 Society of Chemical Industry.

Self-supervised online metric learning with low rank constraint for scene categorization.

PubMed

Cong, Yang; Liu, Ji; Yuan, Junsong; Luo, Jiebo

2013-08-01

Conventional visual recognition systems usually train an image classifier in a bath mode with all training data provided in advance. However, in many practical applications, only a small amount of training samples are available in the beginning and many more would come sequentially during online recognition. Because the image data characteristics could change over time, it is important for the classifier to adapt to the new data incrementally. In this paper, we present an online metric learning method to address the online scene recognition problem via adaptive similarity measurement. Given a number of labeled data followed by a sequential input of unseen testing samples, the similarity metric is learned to maximize the margin of the distance among different classes of samples. By considering the low rank constraint, our online metric learning model not only can provide competitive performance compared with the state-of-the-art methods, but also guarantees convergence. A bi-linear graph is also defined to model the pair-wise similarity, and an unseen sample is labeled depending on the graph-based label propagation, while the model can also self-update using the more confident new samples. With the ability of online learning, our methodology can well handle the large-scale streaming video data with the ability of incremental self-updating. We evaluate our model to online scene categorization and experiments on various benchmark datasets and comparisons with state-of-the-art methods demonstrate the effectiveness and efficiency of our algorithm.

A Modified Hopfield Neural Network Algorithm (MHNNA) Using ALOS Image for Water Quality Mapping

PubMed Central

Kzar, Ahmed Asal; Mat Jafri, Mohd Zubir; Mutter, Kussay N.; Syahreza, Saumi

2015-01-01

Decreasing water pollution is a big problem in coastal waters. Coastal health of ecosystems can be affected by high concentrations of suspended sediment. In this work, a Modified Hopfield Neural Network Algorithm (MHNNA) was used with remote sensing imagery to classify the total suspended solids (TSS) concentrations in the waters of coastal Langkawi Island, Malaysia. The adopted remote sensing image is the Advanced Land Observation Satellite (ALOS) image acquired on 18 January 2010. Our modification allows the Hopfield neural network to convert and classify color satellite images. The samples were collected from the study area simultaneously with the acquiring of satellite imagery. The sample locations were determined using a handheld global positioning system (GPS). The TSS concentration measurements were conducted in a lab and used for validation (real data), classification, and accuracy assessments. Mapping was achieved by using the MHNNA to classify the concentrations according to their reflectance values in band 1, band 2, and band 3. The TSS map was color-coded for visual interpretation. The efficiency of the proposed algorithm was investigated by dividing the validation data into two groups. The first group was used as source samples for supervisor classification via the MHNNA. The second group was used to test the MHNNA efficiency. After mapping, the locations of the second group in the produced classes were detected. Next, the correlation coefficient (R) and root mean square error (RMSE) were calculated between the two groups, according to their corresponding locations in the classes. The MHNNA exhibited a higher R (0.977) and lower RMSE (2.887). In addition, we test the MHNNA with noise, where it proves its accuracy with noisy images over a range of noise levels. All results have been compared with a minimum distance classifier (Min-Dis). Therefore, TSS mapping of polluted water in the coastal Langkawi Island, Malaysia can be performed using the adopted MHNNA with remote sensing techniques (as based on ALOS images). PMID:26729148

Low Prevalence of Substandard and Falsified Antimalarial and Antibiotic Medicines in Public and Faith-Based Health Facilities of Southern Malawi

PubMed Central

Khuluza, Felix; Kigera, Stephen; Heide, Lutz

2017-01-01

Substandard and falsified antimalarial and antibiotic medicines represent a serious problem for public health, especially in low- and middle-income countries. However, information on the prevalence of poor-quality medicines is limited. In the present study, samples of six antimalarial and six antibiotic medicines were collected from 31 health facilities and drug outlets in southern Malawi. Random sampling was used in the selection of health facilities. For sample collection, an overt approach was used in licensed facilities, and a mystery shopper approach in nonlicensed outlets. One hundred and fifty-five samples were analyzed by visual and physical examination and by rapid prescreening tests, that is, disintegration testing and thin-layer chromatography using the GPHF-Minilab. Fifty-six of the samples were analyzed according to pharmacopeial monographs in a World Health Organization-prequalified quality control laboratory. Seven out-of-specification medicines were identified. One sample was classified as falsified, lacking the declared active ingredients, and containing other active ingredients instead. Three samples were classified as substandard with extreme deviations from the pharmacopeial standards, and three further samples as substandard with nonextreme deviations. Of the substandard medicines, three failed in dissolution testing, two in the assay for the content of the active pharmaceutical ingredient, and one failed in both dissolution testing and assay. Six of the seven out-of-specification medicines were from private facilities. Only one out-of-specification medicine was found within the samples from public and faith-based health facilities. Although the observed presence of substandard and falsified medicines in Malawi requires action, their low prevalence in public and faith-based health facilities is encouraging. PMID:28219993

Cross-Modal Decoding of Neural Patterns Associated with Working Memory: Evidence for Attention-Based Accounts of Working Memory

PubMed Central

Majerus, Steve; Cowan, Nelson; Péters, Frédéric; Van Calster, Laurens; Phillips, Christophe; Schrouff, Jessica

2016-01-01

Recent studies suggest common neural substrates involved in verbal and visual working memory (WM), interpreted as reflecting shared attention-based, short-term retention mechanisms. We used a machine-learning approach to determine more directly the extent to which common neural patterns characterize retention in verbal WM and visual WM. Verbal WM was assessed via a standard delayed probe recognition task for letter sequences of variable length. Visual WM was assessed via a visual array WM task involving the maintenance of variable amounts of visual information in the focus of attention. We trained a classifier to distinguish neural activation patterns associated with high- and low-visual WM load and tested the ability of this classifier to predict verbal WM load (high–low) from their associated neural activation patterns, and vice versa. We observed significant between-task prediction of load effects during WM maintenance, in posterior parietal and superior frontal regions of the dorsal attention network; in contrast, between-task prediction in sensory processing cortices was restricted to the encoding stage. Furthermore, between-task prediction of load effects was strongest in those participants presenting the highest capacity for the visual WM task. This study provides novel evidence for common, attention-based neural patterns supporting verbal and visual WM. PMID:25146374

Decoding brain responses to pixelized images in the primary visual cortex: implications for visual cortical prostheses

PubMed Central

Guo, Bing-bing; Zheng, Xiao-lin; Lu, Zhen-gang; Wang, Xing; Yin, Zheng-qin; Hou, Wen-sheng; Meng, Ming

2015-01-01

Visual cortical prostheses have the potential to restore partial vision. Still limited by the low-resolution visual percepts provided by visual cortical prostheses, implant wearers can currently only “see” pixelized images, and how to obtain the specific brain responses to different pixelized images in the primary visual cortex (the implant area) is still unknown. We conducted a functional magnetic resonance imaging experiment on normal human participants to investigate the brain activation patterns in response to 18 different pixelized images. There were 100 voxels in the brain activation pattern that were selected from the primary visual cortex, and voxel size was 4 mm × 4 mm × 4 mm. Multi-voxel pattern analysis was used to test if these 18 different brain activation patterns were specific. We chose a Linear Support Vector Machine (LSVM) as the classifier in this study. The results showed that the classification accuracies of different brain activation patterns were significantly above chance level, which suggests that the classifier can successfully distinguish the brain activation patterns. Our results suggest that the specific brain activation patterns to different pixelized images can be obtained in the primary visual cortex using a 4 mm × 4 mm × 4 mm voxel size and a 100-voxel pattern. PMID:26692860

Visual brain activity patterns classification with simultaneous EEG-fMRI: A multimodal approach.

PubMed

Ahmad, Rana Fayyaz; Malik, Aamir Saeed; Kamel, Nidal; Reza, Faruque; Amin, Hafeez Ullah; Hussain, Muhammad

2017-01-01

Classification of the visual information from the brain activity data is a challenging task. Many studies reported in the literature are based on the brain activity patterns using either fMRI or EEG/MEG only. EEG and fMRI considered as two complementary neuroimaging modalities in terms of their temporal and spatial resolution to map the brain activity. For getting a high spatial and temporal resolution of the brain at the same time, simultaneous EEG-fMRI seems to be fruitful. In this article, we propose a new method based on simultaneous EEG-fMRI data and machine learning approach to classify the visual brain activity patterns. We acquired EEG-fMRI data simultaneously on the ten healthy human participants by showing them visual stimuli. Data fusion approach is used to merge EEG and fMRI data. Machine learning classifier is used for the classification purposes. Results showed that superior classification performance has been achieved with simultaneous EEG-fMRI data as compared to the EEG and fMRI data standalone. This shows that multimodal approach improved the classification accuracy results as compared with other approaches reported in the literature. The proposed simultaneous EEG-fMRI approach for classifying the brain activity patterns can be helpful to predict or fully decode the brain activity patterns.

Classification of CT examinations for COPD visual severity analysis

NASA Astrophysics Data System (ADS)

Tan, Jun; Zheng, Bin; Wang, Xingwei; Pu, Jiantao; Gur, David; Sciurba, Frank C.; Leader, J. Ken

2012-03-01

In this study we present a computational method of CT examination classification into visual assessed emphysema severity. The visual severity categories ranged from 0 to 5 and were rated by an experienced radiologist. The six categories were none, trace, mild, moderate, severe and very severe. Lung segmentation was performed for every input image and all image features are extracted from the segmented lung only. We adopted a two-level feature representation method for the classification. Five gray level distribution statistics, six gray level co-occurrence matrix (GLCM), and eleven gray level run-length (GLRL) features were computed for each CT image depicted segment lung. Then we used wavelets decomposition to obtain the low- and high-frequency components of the input image, and again extract from the lung region six GLCM features and eleven GLRL features. Therefore our feature vector length is 56. The CT examinations were classified using the support vector machine (SVM) and k-nearest neighbors (KNN) and the traditional threshold (density mask) approach. The SVM classifier had the highest classification performance of all the methods with an overall sensitivity of 54.4% and a 69.6% sensitivity to discriminate "no" and "trace visually assessed emphysema. We believe this work may lead to an automated, objective method to categorically classify emphysema severity on CT exam.

A visual tracking method based on improved online multiple instance learning

NASA Astrophysics Data System (ADS)

He, Xianhui; Wei, Yuxing

2016-09-01

Visual tracking is an active research topic in the field of computer vision and has been well studied in the last decades. The method based on multiple instance learning (MIL) was recently introduced into the tracking task, which can solve the problem that template drift well. However, MIL method has relatively poor performance in running efficiency and accuracy, due to its strong classifiers updating strategy is complicated, and the speed of the classifiers update is not always same with the change of the targets' appearance. In this paper, we present a novel online effective MIL (EMIL) tracker. A new update strategy for strong classifier was proposed to improve the running efficiency of MIL method. In addition, to improve the t racking accuracy and stability of the MIL method, a new dynamic mechanism for learning rate renewal of the classifier and variable search window were proposed. Experimental results show that our method performs good performance under the complex scenes, with strong stability and high efficiency.

Antibody-supervised deep learning for quantification of tumor-infiltrating immune cells in hematoxylin and eosin stained breast cancer samples.

PubMed

Turkki, Riku; Linder, Nina; Kovanen, Panu E; Pellinen, Teijo; Lundin, Johan

2016-01-01

Immune cell infiltration in tumor is an emerging prognostic biomarker in breast cancer. The gold standard for quantification of immune cells in tissue sections is visual assessment through a microscope, which is subjective and semi-quantitative. In this study, we propose and evaluate an approach based on antibody-guided annotation and deep learning to quantify immune cell-rich areas in hematoxylin and eosin (H&E) stained samples. Consecutive sections of formalin-fixed parafin-embedded samples obtained from the primary tumor of twenty breast cancer patients were cut and stained with H&E and the pan-leukocyte CD45 antibody. The stained slides were digitally scanned, and a training set of immune cell-rich and cell-poor tissue regions was annotated in H&E whole-slide images using the CD45-expression as a guide. In analysis, the images were divided into small homogenous regions, superpixels, from which features were extracted using a pretrained convolutional neural network (CNN) and classified with a support of vector machine. The CNN approach was compared to texture-based classification and to visual assessments performed by two pathologists. In a set of 123,442 labeled superpixels, the CNN approach achieved an F-score of 0.94 (range: 0.92-0.94) in discrimination of immune cell-rich and cell-poor regions, as compared to an F-score of 0.88 (range: 0.87-0.89) obtained with the texture-based classification. When compared to visual assessment of 200 images, an agreement of 90% (κ = 0.79) to quantify immune infiltration with the CNN approach was achieved while the inter-observer agreement between pathologists was 90% (κ = 0.78). Our findings indicate that deep learning can be applied to quantify immune cell infiltration in breast cancer samples using a basic morphology staining only. A good discrimination of immune cell-rich areas was achieved, well in concordance with both leukocyte antigen expression and pathologists' visual assessment.

Accurate mask-based spatially regularized correlation filter for visual tracking

NASA Astrophysics Data System (ADS)

Gu, Xiaodong; Xu, Xinping

2017-01-01

Recently, discriminative correlation filter (DCF)-based trackers have achieved extremely successful results in many competitions and benchmarks. These methods utilize a periodic assumption of the training samples to efficiently learn a classifier. However, this assumption will produce unwanted boundary effects, which severely degrade the tracking performance. Correlation filters with limited boundaries and spatially regularized DCFs were proposed to reduce boundary effects. However, their methods used the fixed mask or predesigned weights function, respectively, which was unsuitable for large appearance variation. We propose an accurate mask-based spatially regularized correlation filter for visual tracking. Our augmented objective can reduce the boundary effect even in large appearance variation. In our algorithm, the masking matrix is converted into the regularized function that acts on the correlation filter in frequency domain, which makes the algorithm fast convergence. Our online tracking algorithm performs favorably against state-of-the-art trackers on OTB-2015 Benchmark in terms of efficiency, accuracy, and robustness.

Detailed Quantitative Classifications of Galaxy Morphology

NASA Astrophysics Data System (ADS)

Nair, Preethi

2018-01-01

Understanding the physical processes responsible for the growth of galaxies is one of the key challenges in extragalactic astronomy. The assembly history of a galaxy is imprinted in a galaxy’s detailed morphology. The bulge-to-total ratio of galaxies, the presence or absence of bars, rings, spiral arms, tidal tails etc, all have implications for the past merger, star formation, and feedback history of a galaxy. However, current quantitative galaxy classification schemes are only useful for broad binning. They cannot classify or exploit the wide variety of galaxy structures seen in nature. Therefore, comparisons of observations with theoretical predictions of secular structure formation have only been conducted on small samples of visually classified galaxies. However large samples are needed to disentangle the complex physical processes of galaxy formation. With the advent of large surveys, like the Sloan Digital Sky Survey (SDSS) and the upcoming Large Synoptic Survey Telescope (LSST) and WFIRST, the problem of statistics will be resolved. However, the need for a robust quantitative classification scheme will still remain. Here I will present early results on promising machine learning algorithms that are providing detailed classifications, identifying bars, rings, multi-armed spiral galaxies, and Hubble type.

Multi-voxel patterns of visual category representation during episodic encoding are predictive of subsequent memory

PubMed Central

Kuhl, Brice A.; Rissman, Jesse; Wagner, Anthony D.

2012-01-01

Successful encoding of episodic memories is thought to depend on contributions from prefrontal and temporal lobe structures. Neural processes that contribute to successful encoding have been extensively explored through univariate analyses of neuroimaging data that compare mean activity levels elicited during the encoding of events that are subsequently remembered vs. those subsequently forgotten. Here, we applied pattern classification to fMRI data to assess the degree to which distributed patterns of activity within prefrontal and temporal lobe structures elicited during the encoding of word-image pairs were diagnostic of the visual category (Face or Scene) of the encoded image. We then assessed whether representation of category information was predictive of subsequent memory. Classification analyses indicated that temporal lobe structures contained information robustly diagnostic of visual category. Information in prefrontal cortex was less diagnostic of visual category, but was nonetheless associated with highly reliable classifier-based evidence for category representation. Critically, trials associated with greater classifier-based estimates of category representation in temporal and prefrontal regions were associated with a higher probability of subsequent remembering. Finally, consideration of trial-by-trial variance in classifier-based measures of category representation revealed positive correlations between prefrontal and temporal lobe representations, with the strength of these correlations varying as a function of the category of image being encoded. Together, these results indicate that multi-voxel representations of encoded information can provide unique insights into how visual experiences are transformed into episodic memories. PMID:21925190

Hierarchy-associated semantic-rule inference framework for classifying indoor scenes

NASA Astrophysics Data System (ADS)

Yu, Dan; Liu, Peng; Ye, Zhipeng; Tang, Xianglong; Zhao, Wei

2016-03-01

Typically, the initial task of classifying indoor scenes is challenging, because the spatial layout and decoration of a scene can vary considerably. Recent efforts at classifying object relationships commonly depend on the results of scene annotation and predefined rules, making classification inflexible. Furthermore, annotation results are easily affected by external factors. Inspired by human cognition, a scene-classification framework was proposed using the empirically based annotation (EBA) and a match-over rule-based (MRB) inference system. The semantic hierarchy of images is exploited by EBA to construct rules empirically for MRB classification. The problem of scene classification is divided into low-level annotation and high-level inference from a macro perspective. Low-level annotation involves detecting the semantic hierarchy and annotating the scene with a deformable-parts model and a bag-of-visual-words model. In high-level inference, hierarchical rules are extracted to train the decision tree for classification. The categories of testing samples are generated from the parts to the whole. Compared with traditional classification strategies, the proposed semantic hierarchy and corresponding rules reduce the effect of a variable background and improve the classification performance. The proposed framework was evaluated on a popular indoor scene dataset, and the experimental results demonstrate its effectiveness.

Classification of visual and linguistic tasks using eye-movement features.

PubMed

Coco, Moreno I; Keller, Frank

2014-03-07

The role of the task has received special attention in visual-cognition research because it can provide causal explanations of goal-directed eye-movement responses. The dependency between visual attention and task suggests that eye movements can be used to classify the task being performed. A recent study by Greene, Liu, and Wolfe (2012), however, fails to achieve accurate classification of visual tasks based on eye-movement features. In the present study, we hypothesize that tasks can be successfully classified when they differ with respect to the involvement of other cognitive domains, such as language processing. We extract the eye-movement features used by Greene et al. as well as additional features from the data of three different tasks: visual search, object naming, and scene description. First, we demonstrated that eye-movement responses make it possible to characterize the goals of these tasks. Then, we trained three different types of classifiers and predicted the task participants performed with an accuracy well above chance (a maximum of 88% for visual search). An analysis of the relative importance of features for classification accuracy reveals that just one feature, i.e., initiation time, is sufficient for above-chance performance (a maximum of 79% accuracy in object naming). Crucially, this feature is independent of task duration, which differs systematically across the three tasks we investigated. Overall, the best task classification performance was obtained with a set of seven features that included both spatial information (e.g., entropy of attention allocation) and temporal components (e.g., total fixation on objects) of the eye-movement record. This result confirms the task-dependent allocation of visual attention and extends previous work by showing that task classification is possible when tasks differ in the cognitive processes involved (purely visual tasks such as search vs. communicative tasks such as scene description).

Deep learning for tissue microarray image-based outcome prediction in patients with colorectal cancer

NASA Astrophysics Data System (ADS)

Bychkov, Dmitrii; Turkki, Riku; Haglund, Caj; Linder, Nina; Lundin, Johan

2016-03-01

Recent advances in computer vision enable increasingly accurate automated pattern classification. In the current study we evaluate whether a convolutional neural network (CNN) can be trained to predict disease outcome in patients with colorectal cancer based on images of tumor tissue microarray samples. We compare the prognostic accuracy of CNN features extracted from the whole, unsegmented tissue microarray spot image, with that of CNN features extracted from the epithelial and non-epithelial compartments, respectively. The prognostic accuracy of visually assessed histologic grade is used as a reference. The image data set consists of digitized hematoxylin-eosin (H and E) stained tissue microarray samples obtained from 180 patients with colorectal cancer. The patient samples represent a variety of histological grades, have data available on a series of clinicopathological variables including long-term outcome and ground truth annotations performed by experts. The CNN features extracted from images of the epithelial tissue compartment significantly predicted outcome (hazard ratio (HR) 2.08; CI95% 1.04-4.16; area under the curve (AUC) 0.66) in a test set of 60 patients, as compared to the CNN features extracted from unsegmented images (HR 1.67; CI95% 0.84-3.31, AUC 0.57) and visually assessed histologic grade (HR 1.96; CI95% 0.99-3.88, AUC 0.61). As a conclusion, a deep-learning classifier can be trained to predict outcome of colorectal cancer based on images of H and E stained tissue microarray samples and the CNN features extracted from the epithelial compartment only resulted in a prognostic discrimination comparable to that of visually determined histologic grade.

Central corneal thickness and progression of the visual field and optic disc in glaucoma

PubMed Central

Chauhan, B C; Hutchison, D M; LeBlanc, R P; Artes, P H; Nicolela, M T

2005-01-01

Aims: To determine whether central corneal thickness (CCT) is a significant predictor of visual field and optic disc progression in open angle glaucoma. Methods: Data were obtained from a prospective study of glaucoma patients tested with static automated perimetry and confocal scanning laser tomography every 6 months. Progression was determined using a trend based approach called evidence of change (EOC) analysis in which sectoral ordinal scores based on the significance of regression coefficients of visual field pattern deviation and neuroretinal rim area over time are summed. Visual field progression was also determined using the event based glaucoma change probability (GCP) analysis using both total and pattern deviation. Results: The sample contained 101 eyes of 54 patients (mean (SD) age 56.5 (9.8) years) with a mean follow up of 9.2 (0.7) years and 20.7 (2.3) sets of examinations every 6 months. Lower CCT was associated with worse baseline visual fields and lower mean IOP in the follow up. In the longitudinal analysis CCT was not correlated with the EOC scores for visual field or optic disc change. In the GCP analyses, there was a tendency for groups classified as progressing to have lower CCT compared to non-progressing groups. In a multivariate analyses accounting for IOP, the opposite was found, whereby higher CCT was associated with visual field progression. None of the independent factors were predictive of optic disc progression. Conclusions: In this cohort of patients with established glaucoma, CCT was not a useful index in the risk assessment of visual field and optic disc progression. PMID:16024855

Piscine myocarditis virus (PMCV) in wild Atlantic salmon Salmo salar.

PubMed

Garseth, Ase Helen; Biering, Eirik; Tengs, Torstein

2012-12-27

Cardiomyopathy syndrome (CMS) is a severe cardiac disease of sea-farmed Atlantic salmon Salmo salar L., but CMS-like lesions have also been found in wild Atlantic salmon. In 2010 a double-stranded RNA virus of the Totiviridae family, provisionally named piscine myocarditis virus (PMCV), was described as the causative agent of CMS. In the present paper we report the first detection of PMCV in wild Atlantic salmon. The study is based on screening of 797 wild Atlantic salmon by real-time RT-PCR. The samples were collected from 35 different rivers along the coast of Norway, and all individuals included in the study were classified as wild, based on visual appearance and scale reading. Two samples tested positive during PCR analysis, and the results were confirmed by sequencing.

Comparison of clinical features and 3-month treatment response among three different choroidal thickness groups in polypoidal choroidal vasculopathy.

PubMed

Kong, Mingui; Kim, Sung Min; Ham, Don-Il

2017-01-01

Eyes with polypoidal choroidal vasculopathy (PCV) were recently reported to have various choroidal thickness, and choroidal thickness might be associated with visual outcome in the treatment of many retinal disorders. The range of subfoveal choroidal thickness (SFCT), clinical features, and 3-month treatment response among three groups having different range of SFCT were investigated in PCV eyes. In 78 treatment-naïve eyes with PCV, SFCT was measured using optical coherence tomography. Eyes were classified into thin, medium, and thick groups, using mean and one standard deviation of SFCT. Clinical features and imaging findings were compared among the three groups. Some eyes were treated with three consecutive monthly injection of anti-vascular endothelial growth factor (VEGF) as an initial treatment. They were also classified into three thickness groups, and the short-term post-treatment improvement in visual acuity and central retinal thickness were compared among groups. The mean SFCT was 271.9 ± 135.6 μm. Twelve, 53, and 13 eyes were classified into thin (<136.3 μm), medium (136.3-407.5 μm), and thick (>407.5 μm) groups, respectively. The thin group showed older age, lower visual acuity, and a higher prevalence of fundus tessellation than the other two groups (P <0.05). In multiple linear regression analyses, baseline BCVA was correlated with baseline SFCT. Forty-six eyes completed three consecutive anti-VEGF treatments. The thin group showed no visual improvement after treatment (P = 0.141), unlike the other two groups showing visual improvement (P<0.05). Eyes with PCV have a broad range of SFCT, and PCV eyes with a thin choroid manifest worse visual function than eyes with a medium or thick choroid.

Bag-of-features based medical image retrieval via multiple assignment and visual words weighting.

PubMed

Wang, Jingyan; Li, Yongping; Zhang, Ying; Wang, Chao; Xie, Honglan; Chen, Guoling; Gao, Xin

2011-11-01

Bag-of-features based approaches have become prominent for image retrieval and image classification tasks in the past decade. Such methods represent an image as a collection of local features, such as image patches and key points with scale invariant feature transform (SIFT) descriptors. To improve the bag-of-features methods, we first model the assignments of local descriptors as contribution functions, and then propose a novel multiple assignment strategy. Assuming the local features can be reconstructed by their neighboring visual words in a vocabulary, reconstruction weights can be solved by quadratic programming. The weights are then used to build contribution functions, resulting in a novel assignment method, called quadratic programming (QP) assignment. We further propose a novel visual word weighting method. The discriminative power of each visual word is analyzed by the sub-similarity function in the bin that corresponds to the visual word. Each sub-similarity function is then treated as a weak classifier. A strong classifier is learned by boosting methods that combine those weak classifiers. The weighting factors of the visual words are learned accordingly. We evaluate the proposed methods on medical image retrieval tasks. The methods are tested on three well-known data sets, i.e., the ImageCLEFmed data set, the 304 CT Set, and the basal-cell carcinoma image set. Experimental results demonstrate that the proposed QP assignment outperforms the traditional nearest neighbor assignment, the multiple assignment, and the soft assignment, whereas the proposed boosting based weighting strategy outperforms the state-of-the-art weighting methods, such as the term frequency weights and the term frequency-inverse document frequency weights.

Acetic Acid Detection Threshold in Synthetic Wine Samples of a Portable Electronic Nose

PubMed Central

Macías, Miguel Macías; Manso, Antonio García; Orellana, Carlos Javier García; Velasco, Horacio Manuel González; Caballero, Ramón Gallardo; Chamizo, Juan Carlos Peguero

2013-01-01

Wine quality is related to its intrinsic visual, taste, or aroma characteristics and is reflected in the price paid for that wine. One of the most important wine faults is the excessive concentration of acetic acid which can cause a wine to take on vinegar aromas and reduce its varietal character. Thereby it is very important for the wine industry to have methods, like electronic noses, for real-time monitoring the excessive concentration of acetic acid in wines. However, aroma characterization of alcoholic beverages with sensor array electronic noses is a difficult challenge due to the masking effect of ethanol. In this work, in order to detect the presence of acetic acid in synthetic wine samples (aqueous ethanol solution at 10% v/v) we use a detection unit which consists of a commercial electronic nose and a HSS32 auto sampler, in combination with a neural network classifier (MLP). To find the characteristic vector representative of the sample that we want to classify, first we select the sensors, and the section of the sensors response curves, where the probability of detecting the presence of acetic acid will be higher, and then we apply Principal Component Analysis (PCA) such that each sensor response curve is represented by the coefficients of its first principal components. Results show that the PEN3 electronic nose is able to detect and discriminate wine samples doped with acetic acid in concentrations equal or greater than 2 g/L. PMID:23262483

Feature extraction using convolutional neural network for classifying breast density in mammographic images

NASA Astrophysics Data System (ADS)

Thomaz, Ricardo L.; Carneiro, Pedro C.; Patrocinio, Ana C.

2017-03-01

Breast cancer is the leading cause of death for women in most countries. The high levels of mortality relate mostly to late diagnosis and to the direct proportionally relationship between breast density and breast cancer development. Therefore, the correct assessment of breast density is important to provide better screening for higher risk patients. However, in modern digital mammography the discrimination among breast densities is highly complex due to increased contrast and visual information for all densities. Thus, a computational system for classifying breast density might be a useful tool for aiding medical staff. Several machine-learning algorithms are already capable of classifying small number of classes with good accuracy. However, machinelearning algorithms main constraint relates to the set of features extracted and used for classification. Although well-known feature extraction techniques might provide a good set of features, it is a complex task to select an initial set during design of a classifier. Thus, we propose feature extraction using a Convolutional Neural Network (CNN) for classifying breast density by a usual machine-learning classifier. We used 307 mammographic images downsampled to 260x200 pixels to train a CNN and extract features from a deep layer. After training, the activation of 8 neurons from a deep fully connected layer are extracted and used as features. Then, these features are feedforward to a single hidden layer neural network that is cross-validated using 10-folds to classify among four classes of breast density. The global accuracy of this method is 98.4%, presenting only 1.6% of misclassification. However, the small set of samples and memory constraints required the reuse of data in both CNN and MLP-NN, therefore overfitting might have influenced the results even though we cross-validated the network. Thus, although we presented a promising method for extracting features and classifying breast density, a greater database is still required for evaluating the results.

Making Choices in Functional Vision Evaluations: "Noodles, Needles, and Haystacks."

ERIC Educational Resources Information Center

Bishop, V. E.

1988-01-01

An approach to functional vision evaluations clarifies the types of data collection and suggests protocols for three broad categories of visually handicapped children: "normal" school-age students, "normal" preschoolers, and multiply handicapped pupils. Visually impaired infants are classified with multiply handicapped pupils…

Cross-Modal Decoding of Neural Patterns Associated with Working Memory: Evidence for Attention-Based Accounts of Working Memory.

PubMed

Majerus, Steve; Cowan, Nelson; Péters, Frédéric; Van Calster, Laurens; Phillips, Christophe; Schrouff, Jessica

2016-01-01

Recent studies suggest common neural substrates involved in verbal and visual working memory (WM), interpreted as reflecting shared attention-based, short-term retention mechanisms. We used a machine-learning approach to determine more directly the extent to which common neural patterns characterize retention in verbal WM and visual WM. Verbal WM was assessed via a standard delayed probe recognition task for letter sequences of variable length. Visual WM was assessed via a visual array WM task involving the maintenance of variable amounts of visual information in the focus of attention. We trained a classifier to distinguish neural activation patterns associated with high- and low-visual WM load and tested the ability of this classifier to predict verbal WM load (high-low) from their associated neural activation patterns, and vice versa. We observed significant between-task prediction of load effects during WM maintenance, in posterior parietal and superior frontal regions of the dorsal attention network; in contrast, between-task prediction in sensory processing cortices was restricted to the encoding stage. Furthermore, between-task prediction of load effects was strongest in those participants presenting the highest capacity for the visual WM task. This study provides novel evidence for common, attention-based neural patterns supporting verbal and visual WM. © The Author 2014. Published by Oxford University Press. All rights reserved. For Permissions, please e-mail: journals.permissions@oup.com.

Refractive error and visual impairment in school children in Northern Ireland.

PubMed

O'Donoghue, L; McClelland, J F; Logan, N S; Rudnicka, A R; Owen, C G; Saunders, K J

2010-09-01

To describe the prevalence of refractive error (myopia and hyperopia) and visual impairment in a representative sample of white school children. The Northern Ireland Childhood Errors of Refraction study, a population-based cross-sectional study, examined 661 white 12-13-year-old and 392 white 6-7-year-old children between 2006 and 2008. Procedures included assessment of monocular logarithm of the minimum angle of resolution (logMAR), visual acuity (unaided and presenting) and binocular open-field cycloplegic (1% cyclopentolate) autorefraction. Myopia was defined as -0.50DS or more myopic spherical equivalent refraction (SER) in either eye, hyperopia as > or =+2.00DS SER in either eye if not previously classified as myopic. Visual impairment was defined as >0.30 logMAR units (equivalent to 6/12). Levels of myopia were 2.8% (95% CI 1.3% to 4.3%) in younger and 17.7% (95% CI 13.2% to 22.2%) in older children: corresponding levels of hyperopia were 26% (95% CI 20% to 33%) and 14.7% (95% CI 9.9% to 19.4%). The prevalence of presenting visual impairment in the better eye was 3.6% in 12-13-year-old children compared with 1.5% in 6-7-year-old children. Almost one in four children fails to bring their spectacles to school. This study is the first to provide robust population-based data on the prevalence of refractive error and visual impairment in Northern Irish school children. Strategies to improve compliance with spectacle wear are required.

Optical Coherence Tomography Machine Learning Classifiers for Glaucoma Detection: A Preliminary Study

PubMed Central

Burgansky-Eliash, Zvia; Wollstein, Gadi; Chu, Tianjiao; Ramsey, Joseph D.; Glymour, Clark; Noecker, Robert J.; Ishikawa, Hiroshi; Schuman, Joel S.

2007-01-01

Purpose Machine-learning classifiers are trained computerized systems with the ability to detect the relationship between multiple input parameters and a diagnosis. The present study investigated whether the use of machine-learning classifiers improves optical coherence tomography (OCT) glaucoma detection. Methods Forty-seven patients with glaucoma (47 eyes) and 42 healthy subjects (42 eyes) were included in this cross-sectional study. Of the glaucoma patients, 27 had early disease (visual field mean deviation [MD] ≥ −6 dB) and 20 had advanced glaucoma (MD < −6 dB). Machine-learning classifiers were trained to discriminate between glaucomatous and healthy eyes using parameters derived from OCT output. The classifiers were trained with all 38 parameters as well as with only 8 parameters that correlated best with the visual field MD. Five classifiers were tested: linear discriminant analysis, support vector machine, recursive partitioning and regression tree, generalized linear model, and generalized additive model. For the last two classifiers, a backward feature selection was used to find the minimal number of parameters that resulted in the best and most simple prediction. The cross-validated receiver operating characteristic (ROC) curve and accuracies were calculated. Results The largest area under the ROC curve (AROC) for glaucoma detection was achieved with the support vector machine using eight parameters (0.981). The sensitivity at 80% and 95% specificity was 97.9% and 92.5%, respectively. This classifier also performed best when judged by cross-validated accuracy (0.966). The best classification between early glaucoma and advanced glaucoma was obtained with the generalized additive model using only three parameters (AROC = 0.854). Conclusions Automated machine classifiers of OCT data might be useful for enhancing the utility of this technology for detecting glaucomatous abnormality. PMID:16249492

Bayes estimation on parameters of the single-class classifier. [for remotely sensed crop data

NASA Technical Reports Server (NTRS)

Lin, G. C.; Minter, T. C.

1976-01-01

Normal procedures used for designing a Bayes classifier to classify wheat as the major crop of interest require not only training samples of wheat but also those of nonwheat. Therefore, ground truth must be available for the class of interest plus all confusion classes. The single-class Bayes classifier classifies data into the class of interest or the class 'other' but requires training samples only from the class of interest. This paper will present a procedure for Bayes estimation on the mean vector, covariance matrix, and a priori probability of the single-class classifier using labeled samples from the class of interest and unlabeled samples drawn from the mixture density function.

Neural Representations of Physics Concepts.

PubMed

Mason, Robert A; Just, Marcel Adam

2016-06-01

We used functional MRI (fMRI) to assess neural representations of physics concepts (momentum, energy, etc.) in juniors, seniors, and graduate students majoring in physics or engineering. Our goal was to identify the underlying neural dimensions of these representations. Using factor analysis to reduce the number of dimensions of activation, we obtained four physics-related factors that were mapped to sets of voxels. The four factors were interpretable as causal motion visualization, periodicity, algebraic form, and energy flow. The individual concepts were identifiable from their fMRI signatures with a mean rank accuracy of .75 using a machine-learning (multivoxel) classifier. Furthermore, there was commonality in participants' neural representation of physics; a classifier trained on data from all but one participant identified the concepts in the left-out participant (mean accuracy = .71 across all nine participant samples). The findings indicate that abstract scientific concepts acquired in an educational setting evoke activation patterns that are identifiable and common, indicating that science education builds abstract knowledge using inherent, repurposed brain systems. © The Author(s) 2016.

Visual Field Function in School-Aged Children with Spastic Unilateral Cerebral Palsy Related to Different Patterns of Brain Damage

ERIC Educational Resources Information Center

Jacobson, Lena; Rydberg, Agneta; Eliasson, Ann-Christin; Kits, Annika; Flodmark, Olof

2010-01-01

Aim: To relate visual field function to brain morphology in children with unilateral cerebral palsy (CP). Method: Visual field function was assessed using the confrontation technique and Goldmann perimetry in 29 children (15 males, 14 females; age range 7-17y, median age 11y) with unilateral CP classified at Gross Motor Function Classification…

The Relationship between Walk Distance and Muscle Strength, Muscle Pain in Visually Disabled People

ERIC Educational Resources Information Center

Akyol, Betül

2018-01-01

The purpose of this study is to examine the relationship between six-minute walk test and muscle pain, muscle strength in visually disabled people. The study includes 50 visually disabled people, aged between 17, 21 ± 5,3. Participants were classified into three categories according to their degree of vision (B1, B2, B3). All participants were…

Rapid Assessment of Salivary MMP-8 and Periodontal Disease Using Lateral Flow Immunoassay

PubMed Central

Johnson, N.; Ebersole, J.L.; Kryscio, R.J.; Danaher, R. J.; Dawson, D.; Al-Sabbagh, M.; Miller, C.S.

2016-01-01

Objective This study determined the efficacy of a novel point-of-care immunoflow device (POCID) for detecting matrix metalloproteinase (MMP)-8 concentrations in oral fluids in comparison with a gold-standard laboratory-based immunoassay. Methods Oral rinse fluid and whole expectorated saliva samples were collected from 41 participants clinically classified as periodontally healthy or diseased. Samples were analyzed for MMP-8 by Luminex immunoassay and POCID. Photographed POCID results were assessed by optical scan and visually by two examiners. Data were analyzed by Pearson correlation and receiver operator characteristics. Results MMP-8 was readily detected by the POCID, and concentrations correlated well with Luminex for both saliva and rinse fluids (r=0.57–0.93). Thresholds that distinguished periodontitis from health were delineated from both the optical scans and visual reads of the POCID (sensitivity 0.7–0.9, specificity 0.5–0.7; p < 0.05). Conclusions Performance of this POCID for detecting MMP-8 in oral rinse fluid or saliva was excellent. These findings help demonstrate the utility of salivary biomarkers for distinguishing periodontal disease from health using a rapid point-of-care approach. PMID:27273425

Response time as a discriminator between true- and false-positive responses in suprathreshold perimetry.

PubMed

Artes, Paul H; McLeod, David; Henson, David B

2002-01-01

To report on differences between the latency distributions of responses to stimuli and to false-positive catch trials in suprathreshold perimetry. To describe an algorithm for defining response time windows and to report on its performance in discriminating between true- and false-positive responses on the basis of response time (RT). A sample of 435 largely inexperienced patients underwent suprathreshold visual field examination on a perimeter that was modified to record RTs. Data were analyzed from 60,500 responses to suprathreshold stimuli and from 523 false-positive responses to catch trials. False-positive responses had much more variable latencies than responses to suprathreshold stimuli. An algorithm defining RT windows on the basis of z-transformed individual latency samples correctly identified more than 70% of false-positive responses to catch trials, whereas fewer than 3% of responses to suprathreshold stimuli were classified as false-positive responses. Latency analysis can be used to detect a substantial proportion of false-positive responses in suprathreshold perimetry. Rejection of such responses may increase the reliability of visual field screening by reducing variability and bias in a small but clinically important proportion of patients.

Decoding grating orientation from microelectrode array recordings in monkey cortical area V4.

PubMed

Manyakov, Nikolay V; Van Hulle, Marc M

2010-04-01

We propose an invasive brain-machine interface (BMI) that decodes the orientation of a visual grating from spike train recordings made with a 96 microelectrodes array chronically implanted into the prelunate gyrus (area V4) of a rhesus monkey. The orientation is decoded irrespective of the grating's spatial frequency. Since pyramidal cells are less prominent in visual areas, compared to (pre)motor areas, the recordings contain spikes with smaller amplitudes, compared to the noise level. Hence, rather than performing spike decoding, feature selection algorithms are applied to extract the required information for the decoder. Two types of feature selection procedures are compared, filter and wrapper. The wrapper is combined with a linear discriminant analysis classifier, and the filter is followed by a radial-basis function support vector machine classifier. In addition, since we have a multiclass classification problen, different methods for combining pairwise classifiers are compared.

Detecting Strengths and Weaknesses in Learning Mathematics through a Model Classifying Mathematical Skills

ERIC Educational Resources Information Center

Karagiannakis, Giannis N.; Baccaglini-Frank, Anna E.; Roussos, Petros

2016-01-01

Through a review of the literature on mathematical learning disabilities (MLD) and low achievement in mathematics (LA) we have proposed a model classifying mathematical skills involved in learning mathematics into four domains (Core number, Memory, Reasoning, and Visual-spatial). In this paper we present a new experimental computer-based battery…

Classifying seismic waveforms from scratch: a case study in the alpine environment

NASA Astrophysics Data System (ADS)

Hammer, C.; Ohrnberger, M.; Fäh, D.

2013-01-01

Nowadays, an increasing amount of seismic data is collected by daily observatory routines. The basic step for successfully analyzing those data is the correct detection of various event types. However, the visually scanning process is a time-consuming task. Applying standard techniques for detection like the STA/LTA trigger still requires the manual control for classification. Here, we present a useful alternative. The incoming data stream is scanned automatically for events of interest. A stochastic classifier, called hidden Markov model, is learned for each class of interest enabling the recognition of highly variable waveforms. In contrast to other automatic techniques as neural networks or support vector machines the algorithm allows to start the classification from scratch as soon as interesting events are identified. Neither the tedious process of collecting training samples nor a time-consuming configuration of the classifier is required. An approach originally introduced for the volcanic task force action allows to learn classifier properties from a single waveform example and some hours of background recording. Besides a reduction of required workload this also enables to detect very rare events. Especially the latter feature provides a milestone point for the use of seismic devices in alpine warning systems. Furthermore, the system offers the opportunity to flag new signal classes that have not been defined before. We demonstrate the application of the classification system using a data set from the Swiss Seismological Survey achieving very high recognition rates. In detail we document all refinements of the classifier providing a step-by-step guide for the fast set up of a well-working classification system.

How large a training set is needed to develop a classifier for microarray data?

PubMed

Dobbin, Kevin K; Zhao, Yingdong; Simon, Richard M

2008-01-01

A common goal of gene expression microarray studies is the development of a classifier that can be used to divide patients into groups with different prognoses, or with different expected responses to a therapy. These types of classifiers are developed on a training set, which is the set of samples used to train a classifier. The question of how many samples are needed in the training set to produce a good classifier from high-dimensional microarray data is challenging. We present a model-based approach to determining the sample size required to adequately train a classifier. It is shown that sample size can be determined from three quantities: standardized fold change, class prevalence, and number of genes or features on the arrays. Numerous examples and important experimental design issues are discussed. The method is adapted to address ex post facto determination of whether the size of a training set used to develop a classifier was adequate. An interactive web site for performing the sample size calculations is provided. We showed that sample size calculations for classifier development from high-dimensional microarray data are feasible, discussed numerous important considerations, and presented examples.

The identification of van Hiele level students on the topic of space analytic geometry

NASA Astrophysics Data System (ADS)

Yudianto, E.; Sunardi; Sugiarti, T.; Susanto; Suharto; Trapsilasiwi, D.

2018-03-01

Geometry topics are still considered difficult by most students. Therefore, this study focused on the identification of students related to van Hiele levels. The task used from result of the development of questions related to analytical geometry of space. The results of the work involving 78 students who worked on these questions covered 11.54% (nine students) classified on a visual level; 5.13% (four students) on analysis level; 1.28% (one student) on informal deduction level; 2.56% (two students) on deduction and 2.56% (two students) on rigor level, and 76.93% (sixty students) classified on the pre-visualization level.

Multiple-object tracking as a tool for parametrically modulating memory reactivation

PubMed Central

Poppenk, J.; Norman, K.A.

2017-01-01

Converging evidence supports the “non-monotonic plasticity” hypothesis that although complete retrieval may strengthen memories, partial retrieval weakens them. Yet, the classic experimental paradigms used to study effects of partial retrieval are not ideally suited to doing so, because they lack the parametric control needed to ensure that the memory is activated to the appropriate degree (i.e., that there is some retrieval, but not enough to cause memory strengthening). Here we present a novel procedure designed to accommodate this need. After participants learned a list of word-scene associates, they completed a cued mental visualization task that was combined with a multiple-object tracking (MOT) procedure, which we selected for its ability to interfere with mental visualization in a parametrically adjustable way (by varying the number of MOT targets). We also used fMRI data to successfully train an “associative recall” classifier for use in this task: this classifier revealed greater memory reactivation during trials in which associative memories were cued while participants tracked one, rather than five MOT targets. However, the classifier was insensitive to task difficulty when recall was not taking place, suggesting it had indeed tracked memory reactivation rather than task difficulty per se. Consistent with the classifier findings, participants’ introspective ratings of visualization vividness were modulated by MOT task difficulty. In addition, we observed reduced classifier output and slowing of responses in a post-reactivation memory test, consistent with the hypothesis that partial reactivation, induced by MOT, weakened memory. These results serve as a “proof of concept” that MOT can be used to parametrically modulate memory retrieval – a property that may prove useful in future investigation of partial retrieval effects, e.g., in closed-loop experiments. PMID:28387587

22 CFR 125.5 - Exemptions for plant visits.

Code of Federal Regulations, 2010 CFR

2010-04-01

... license is not required for the oral and visual disclosure of unclassified technical data during the..., production or manufacture of any other defense articles. In the case of visits involving classified... of the Directorate of Defense Trade Controls is not required for the disclosure of oral and visual...

Computer-aided Classification of Mammographic Masses Using Visually Sensitive Image Features

PubMed Central

Wang, Yunzhi; Aghaei, Faranak; Zarafshani, Ali; Qiu, Yuchen; Qian, Wei; Zheng, Bin

2017-01-01

Purpose To develop a new computer-aided diagnosis (CAD) scheme that computes visually sensitive image features routinely used by radiologists to develop a machine learning classifier and distinguish between the malignant and benign breast masses detected from digital mammograms. Methods An image dataset including 301 breast masses was retrospectively selected. From each segmented mass region, we computed image features that mimic five categories of visually sensitive features routinely used by radiologists in reading mammograms. We then selected five optimal features in the five feature categories and applied logistic regression models for classification. A new CAD interface was also designed to show lesion segmentation, computed feature values and classification score. Results Areas under ROC curves (AUC) were 0.786±0.026 and 0.758±0.027 when to classify mass regions depicting on two view images, respectively. By fusing classification scores computed from two regions, AUC increased to 0.806±0.025. Conclusion This study demonstrated a new approach to develop CAD scheme based on 5 visually sensitive image features. Combining with a “visual aid” interface, CAD results may be much more easily explainable to the observers and increase their confidence to consider CAD generated classification results than using other conventional CAD approaches, which involve many complicated and visually insensitive texture features. PMID:27911353

YOUNG STELLAR OBJECTS IN THE GOULD BELT

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

Dunham, Michael M.; Allen, Lori E.; Evans II, Neal J.

2015-09-15

We present the full catalog of Young Stellar Objects (YSOs) identified in the 18 molecular clouds surveyed by the Spitzer Space Telescope “cores to disks” (c2d) and “Gould Belt” (GB) Legacy surveys. Using standard techniques developed by the c2d project, we identify 3239 candidate YSOs in the 18 clouds, 2966 of which survive visual inspection and form our final catalog of YSOs in the GB. We compile extinction corrected spectral energy distributions for all 2966 YSOs and calculate and tabulate the infrared spectral index, bolometric luminosity, and bolometric temperature for each object. We find that 326 (11%), 210 (7%), 1248more » (42%), and 1182 (40%) are classified as Class 0 + I, Flat-spectrum, Class II, and Class III, respectively, and show that the Class III sample suffers from an overall contamination rate by background Asymptotic Giant Branch stars between 25% and 90%. Adopting standard assumptions, we derive durations of 0.40–0.78 Myr for Class 0 + I YSOs and 0.26–0.50 Myr for Flat-spectrum YSOs, where the ranges encompass uncertainties in the adopted assumptions. Including information from (sub)millimeter wavelengths, one-third of the Class 0 + I sample is classified as Class 0, leading to durations of 0.13–0.26 Myr (Class 0) and 0.27–0.52 Myr (Class I). We revisit infrared color–color diagrams used in the literature to classify YSOs and propose minor revisions to classification boundaries in these diagrams. Finally, we show that the bolometric temperature is a poor discriminator between Class II and Class III YSOs.« less

Influence of cognitive style and interstimulus interval on the hemispheric processing of tactile stimuli.

PubMed

Minagawa, N; Kashu, K

1989-06-01

16 adult subjects performed a tactile recognition task. According to our 1984 study, half of the subjects were classified as having a left hemispheric preference for the processing of visual stimuli, while the other half were classified as having a right hemispheric preference for the processing of visual stimuli. The present task was conducted according to the S1-S2 matching paradigm. The standard stimulus was a readily recognizable object and was presented tactually to either the left or right hand of each subject. The comparison stimulus was an object-picture and was presented visually by slide in a tachistoscope. The interstimulus interval was .05 sec. or 2.5 sec. Analysis indicated that the left-preference group showed right-hand superiority, and the right-preference group showed left-hand superiority. The notion of individual hemisphericity was supported in tactile processing.

Classification of buildings mold threat using electronic nose

NASA Astrophysics Data System (ADS)

Łagód, Grzegorz; Suchorab, Zbigniew; Guz, Łukasz; Sobczuk, Henryk

2017-07-01

Mold is considered to be one of the most important features of Sick Building Syndrome and is an important problem in current building industry. In many cases it is caused by the rising moisture of building envelopes surface and exaggerated humidity of indoor air. Concerning historical buildings it is mostly caused by outdated raising techniques among that is absence of horizontal isolation against moisture and hygroscopic materials applied for construction. Recent buildings also suffer problem of mold risk which is caused in many cases by hermetization leading to improper performance of gravitational ventilation systems that make suitable conditions for mold development. Basing on our research there is proposed a method of buildings mold threat classification using electronic nose, based on a gas sensors array which consists of MOS sensors (metal oxide semiconductor). Used device is frequently applied for air quality assessment in environmental engineering branches. Presented results show the interpretation of e-nose readouts of indoor air sampled in rooms threatened with mold development in comparison with clean reference rooms and synthetic air. Obtained multivariate data were processed, visualized and classified using a PCA (Principal Component Analysis) and ANN (Artificial Neural Network) methods. Described investigation confirmed that electronic nose - gas sensors array supported with data processing enables to classify air samples taken from different rooms affected with mold.

Association of Visual Acuity and Cognitive Impairment in Older Individuals: Fujiwara-kyo Eye Study.

PubMed

Mine, Masashi; Miyata, Kimie; Morikawa, Masayuki; Nishi, Tomo; Okamoto, Nozomi; Kawasaki, Ryo; Yamashita, Hidetoshi; Kurumatani, Norio; Ogata, Nahoko

2016-01-01

Both visual impairment and cognitive impairment are essential factors that determine the quality of life in the aged population. The aim of this study was to determine if a correlation existed between visual acuity and cognitive impairment in an elderly Japanese population. The Fujiwara-kyo Eye Study was a cross-sectional study of individuals aged ≥68 years who lived in Nara Prefecture of Japan. Participants underwent ophthalmological examinations and cognitive function test. A mild visual impairment was defined as having a best corrected visual acuity (BCVA) >0.2 logarithm of the minimum angle of resolution (logMAR) units in the better eye. Cognitive impairment was defined as having a Mini-Mental State Examination (MMSE) score of ≤23 points. A total to 2818 individuals completed the examinations. The mean age of the participants was 76.3 ± 4.8 years (mean ± standard deviation). The mean BCVA of the better eye was -0.02 ± 0.13 logMAR units and 6.6% subjects were classified as being mildly visually impaired. The mean MMSE score was 27.3 ± 2.3 and 5.7% subjects were classified as being cognitively impaired. The proportion of subjects with cognitive or moderate visual impairment increased with age, and there was a significant correlation between the visual acuity and MMSE score (r = -0.10, p < 0.0001). Subjects with mild visual impairments had 2.4 times higher odds of having cognitive impairment than those without visual impairment (odds ratio 2.4, 95% confidence interval, 1.5-3.8, p < 0.001) after adjusting for age, sex, and length of education. We conclude that it may be important to maintain good visual acuity to reduce the risk of having cognitive impairment.

Evaluation of Food Freshness and Locality by Odor Sensor

NASA Astrophysics Data System (ADS)

Koike, Takayuki; Shimada, Koji; Kamimura, Hironobu; Kaneki, Noriaki

The aim of this study was to investigate whether food freshness and locality can be classified using a food evaluation system consisting four SnO2-semiconductor gas sensors and a solid phase column, into which collecting aroma materials. The temperature of sensors was periodically changed to be in unsteady state and thus, the sensor information was increased. The parameters (in quefrency band) were extracted from sensor information using cepstrum analysis that enable to separate superimposed information on sinusoidal wave. The quefrency was used as parameters for principal component and discriminant analyses (PCA and DCA) to detect food freshness and food localities. We used three kinds of strawberries, people can perceive its odors, passed from one to three days after harvest, and kelps and Ceylon tea, people are hardly to perceive its odor, corrected from five areas as sample. Then, the deterioration of strawberries and localities of kelps and Ceylon teas were visually evaluated using the numerical analyses. While the deteriorations were classified using PCA or DCA, the localities were classified only by DCA. The findings indicate that, although odorant intensity influenced the method detecting food quality, the quefrency obtained from odorant information using cepstrum analysis were available to detect the difference in the freshness and the localities of foods.

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

Springmeyer, R R; Brugger, E; Cook, R

The Data group provides data analysis and visualization support to its customers. This consists primarily of the development and support of VisIt, a data analysis and visualization tool. Support ranges from answering questions about the tool, providing classes on how to use the tool, and performing data analysis and visualization for customers. The Information Management and Graphics Group supports and develops tools that enhance our ability to access, display, and understand large, complex data sets. Activities include applying visualization software for large scale data exploration; running video production labs on two networks; supporting graphics libraries and tools for end users;more » maintaining PowerWalls and assorted other displays; and developing software for searching and managing scientific data. Researchers in the Center for Applied Scientific Computing (CASC) work on various projects including the development of visualization techniques for large scale data exploration that are funded by the ASC program, among others. The researchers also have LDRD projects and collaborations with other lab researchers, academia, and industry. The IMG group is located in the Terascale Simulation Facility, home to Dawn, Atlas, BGL, and others, which includes both classified and unclassified visualization theaters, a visualization computer floor and deployment workshop, and video production labs. We continued to provide the traditional graphics group consulting and video production support. We maintained five PowerWalls and many other displays. We deployed a 576-node Opteron/IB cluster with 72 TB of memory providing a visualization production server on our classified network. We continue to support a 128-node Opteron/IB cluster providing a visualization production server for our unclassified systems and an older 256-node Opteron/IB cluster for the classified systems, as well as several smaller clusters to drive the PowerWalls. The visualization production systems includes NFS servers to provide dedicated storage for data analysis and visualization. The ASC projects have delivered new versions of visualization and scientific data management tools to end users and continue to refine them. VisIt had 4 releases during the past year, ending with VisIt 2.0. We released version 2.4 of Hopper, a Java application for managing and transferring files. This release included a graphical disk usage view which works on all types of connections and an aggregated copy feature for quickly transferring massive datasets quickly and efficiently to HPSS. We continue to use and develop Blockbuster and Telepath. Both the VisIt and IMG teams were engaged in a variety of movie production efforts during the past year in addition to the development tasks.« less

Supporting High School Student Accomplishment of Biology Content Using Interactive Computer-Based Curricular Case Studies

NASA Astrophysics Data System (ADS)

Oliver, Joseph Steve; Hodges, Georgia W.; Moore, James N.; Cohen, Allan; Jang, Yoonsun; Brown, Scott A.; Kwon, Kyung A.; Jeong, Sophia; Raven, Sara P.; Jurkiewicz, Melissa; Robertson, Tom P.

2017-11-01

Research into the efficacy of modules featuring dynamic visualizations, case studies, and interactive learning environments is reported here. This quasi-experimental 2-year study examined the implementation of three interactive computer-based instructional modules within a curricular unit covering cellular biology concepts in an introductory high school biology course. The modules featured dynamic visualizations and focused on three processes that underlie much of cellular biology: diffusion, osmosis, and filtration. Pre-tests and post-tests were used to assess knowledge growth across the unit. A mixture Rasch model analysis of the post-test data revealed two groups of students. In both years of the study, a large proportion of the students were classified as low-achieving based on their pre-test scores. The use of the modules in the Cell Unit in year 2 was associated with a much larger proportion of the students having transitioned to the high-achieving group than in year 1. In year 2, the same teachers taught the same concepts as year 1 but incorporated the interactive computer-based modules into the cell biology unit of the curriculum. In year 2, 67% of students initially classified as low-achieving were classified as high-achieving at the end of the unit. Examination of responses to assessments embedded within the modules as well as post-test items linked transition to the high-achieving group with correct responses to items that both referenced the visualization and the contextualization of that visualization within the module. This study points to the importance of dynamic visualization within contextualized case studies as a means to support student knowledge acquisition in biology.

Believing is Seeing: Visual Conventions in Barr's Classification of the "Feeble-Minded"

ERIC Educational Resources Information Center

Elks, Martin A.

2004-01-01

The eugenics era (c. 1900?1930) produced a strong desire among mental retardation professionals to recognize and control "the feeble-minded." Some eugenicists believed it was possible to classify individuals visually by learning to recognize what they believed to be observable characteristics of idiocy and imbecility. In this paper I used…

Visual or Auditory Processing Style and Strategy Effectiveness.

ERIC Educational Resources Information Center

Weed, Keri; Ryan, Ellen Bouchard

In a study that investigated differences in the processing styles of beginning readers, a Pictograph Sentence Memory Test (PSMT) was administered to first and second grade students to determine their processing style as well as to assess instructional effects. Based on their responses to the PSMT, the children were classified as either visual or…

Inventory of Electronic Mobility Aids for Persons with Visual Impairments: A Literature Review

ERIC Educational Resources Information Center

Roentgen, Uta R.; Gelderblom, Gert Jan; Soede, Mathijs; de Witte, Luc P.

2008-01-01

This literature review of existing electronic mobility aids for persons who are visually impaired and recent developments in this field identified and classified 146 products, systems, and devices. The 21 that are currently available that can be used without environmental adaptation are described in functional terms. (Contains 2 tables.)

Visualization of dietary patterns and their associations with age-related macular degeneration

USDA-ARS?s Scientific Manuscript database

PURPOSE: We aimed to visualize the relationship of predominant dietary patterns and their associations with AMD. METHODS: A total of 8103 eyes from 4088 participants in the baseline Age-Related Eye Disease Study (AREDS) were classified into three groups: control (n=2739), early AMD (n=4599), and adv...

Lung texture classification using bag of visual words

NASA Astrophysics Data System (ADS)

Asherov, Marina; Diamant, Idit; Greenspan, Hayit

2014-03-01

Interstitial lung diseases (ILD) refer to a group of more than 150 parenchymal lung disorders. High-Resolution Computed Tomography (HRCT) is the most essential imaging modality of ILD diagnosis. Nonetheless, classification of various lung tissue patterns caused by ILD is still regarded as a challenging task. The current study focuses on the classification of five most common categories of lung tissues of ILD in HRCT images: normal, emphysema, ground glass, fibrosis and micronodules. The objective of the research is to classify an expert-given annotated region of interest (AROI) using a bag of visual words (BoVW) framework. The images are divided into small patches and a collection of representative patches are defined as visual words. This procedure, termed dictionary construction, is performed for each individual lung texture category. The assumption is that different lung textures are represented by a different visual word distribution. The classification is performed using an SVM classifier with histogram intersection kernel. In the experiments, we use a dataset of 1018 AROIs from 95 patients. Classification using a leave-one-patient-out cross validation (LOPO CV) is used. Current classification accuracy obtained is close to 80%.

Principal component analysis study of visual and verbal metaphoric comprehension in children with autism and learning disabilities.

PubMed

Mashal, Nira; Kasirer, Anat

2012-01-01

This research extends previous studies regarding the metaphoric competence of autistic and learning disable children on different measures of visual and verbal non-literal language comprehension, as well as cognitive abilities that include semantic knowledge, executive functions, similarities, and reading fluency. Thirty seven children with autism (ASD), 20 children with learning disabilities (LD), and 21 typically developed (TD) children participated in the study. Principal components analysis was used to examine the interrelationship among the various tests in each group. Results showed different patterns in the data according to group. In particular, the results revealed that there is no dichotomy between visual and verbal metaphors in TD children but rather metaphor are classified according to their familiarity level. In the LD group visual metaphors were classified independently of the verbal metaphors. Verbal metaphoric understanding in the ASD group resembled the LD group. In addition, our results revealed the relative weakness of the ASD and LD children in suppressing irrelevant information. Copyright © 2011 Elsevier Ltd. All rights reserved.

Antibody-supervised deep learning for quantification of tumor-infiltrating immune cells in hematoxylin and eosin stained breast cancer samples

PubMed Central

Turkki, Riku; Linder, Nina; Kovanen, Panu E.; Pellinen, Teijo; Lundin, Johan

2016-01-01

Background: Immune cell infiltration in tumor is an emerging prognostic biomarker in breast cancer. The gold standard for quantification of immune cells in tissue sections is visual assessment through a microscope, which is subjective and semi-quantitative. In this study, we propose and evaluate an approach based on antibody-guided annotation and deep learning to quantify immune cell-rich areas in hematoxylin and eosin (H&E) stained samples. Methods: Consecutive sections of formalin-fixed parafin-embedded samples obtained from the primary tumor of twenty breast cancer patients were cut and stained with H&E and the pan-leukocyte CD45 antibody. The stained slides were digitally scanned, and a training set of immune cell-rich and cell-poor tissue regions was annotated in H&E whole-slide images using the CD45-expression as a guide. In analysis, the images were divided into small homogenous regions, superpixels, from which features were extracted using a pretrained convolutional neural network (CNN) and classified with a support of vector machine. The CNN approach was compared to texture-based classification and to visual assessments performed by two pathologists. Results: In a set of 123,442 labeled superpixels, the CNN approach achieved an F-score of 0.94 (range: 0.92–0.94) in discrimination of immune cell-rich and cell-poor regions, as compared to an F-score of 0.88 (range: 0.87–0.89) obtained with the texture-based classification. When compared to visual assessment of 200 images, an agreement of 90% (κ = 0.79) to quantify immune infiltration with the CNN approach was achieved while the inter-observer agreement between pathologists was 90% (κ = 0.78). Conclusions: Our findings indicate that deep learning can be applied to quantify immune cell infiltration in breast cancer samples using a basic morphology staining only. A good discrimination of immune cell-rich areas was achieved, well in concordance with both leukocyte antigen expression and pathologists’ visual assessment. PMID:27688929

Comparison of visual receptive fields in the dorsolateral prefrontal cortex and ventral intraparietal area in macaques.

PubMed

Viswanathan, Pooja; Nieder, Andreas

2017-12-01

The concept of receptive field (RF) describes the responsiveness of neurons to sensory space. Neurons in the primate association cortices have long been known to be spatially selective but a detailed characterisation and direct comparison of RFs between frontal and parietal association cortices are missing. We sampled the RFs of a large number of neurons from two interconnected areas of the frontal and parietal lobes, the dorsolateral prefrontal cortex (dlPFC) and ventral intraparietal area (VIP), of rhesus monkeys by systematically presenting a moving bar during passive fixation. We found that more than half of neurons in both areas showed spatial selectivity. Single neurons in both areas could be assigned to five classes according to the spatial response patterns: few non-uniform RFs with multiple discrete response maxima could be dissociated from the vast majority of uniform RFs showing a single maximum; the latter were further classified into full-field and confined foveal, contralateral and ipsilateral RFs. Neurons in dlPFC showed a preference for the contralateral visual space and collectively encoded the contralateral visual hemi-field. In contrast, VIP neurons preferred central locations, predominantly covering the foveal visual space. Putative pyramidal cells with broad-spiking waveforms in PFC had smaller RFs than putative interneurons showing narrow-spiking waveforms, but distributed similarly across the visual field. In VIP, however, both putative pyramidal cells and interneurons had similar RFs at similar eccentricities. We provide a first, thorough characterisation of visual RFs in two reciprocally connected areas of a fronto-parietal cortical network. © 2017 Federation of European Neuroscience Societies and John Wiley & Sons Ltd.

Exploring geo-tagged photos for land cover validation with deep learning

NASA Astrophysics Data System (ADS)

Xing, Hanfa; Meng, Yuan; Wang, Zixuan; Fan, Kaixuan; Hou, Dongyang

2018-07-01

Land cover validation plays an important role in the process of generating and distributing land cover thematic maps, which is usually implemented by high cost of sample interpretation with remotely sensed images or field survey. With an increasing availability of geo-tagged landscape photos, the automatic photo recognition methodologies, e.g., deep learning, can be effectively utilised for land cover applications. However, they have hardly been utilised in validation processes, as challenges remain in sample selection and classification for highly heterogeneous photos. This study proposed an approach to employ geo-tagged photos for land cover validation by using the deep learning technology. The approach first identified photos automatically based on the VGG-16 network. Then, samples for validation were selected and further classified by considering photos distribution and classification probabilities. The implementations were conducted for the validation of the GlobeLand30 land cover product in a heterogeneous area, western California. Experimental results represented promises in land cover validation, given that GlobeLand30 showed an overall accuracy of 83.80% with classified samples, which was close to the validation result of 80.45% based on visual interpretation. Additionally, the performances of deep learning based on ResNet-50 and AlexNet were also quantified, revealing no substantial differences in final validation results. The proposed approach ensures geo-tagged photo quality, and supports the sample classification strategy by considering photo distribution, with accuracy improvement from 72.07% to 79.33% compared with solely considering the single nearest photo. Consequently, the presented approach proves the feasibility of deep learning technology on land cover information identification of geo-tagged photos, and has a great potential to support and improve the efficiency of land cover validation.

Basic visual dysfunction allows classification of patients with schizophrenia with exceptional accuracy.

PubMed

González-Hernández, J A; Pita-Alcorta, C; Padrón, A; Finalé, A; Galán, L; Martínez, E; Díaz-Comas, L; Samper-González, J A; Lencer, R; Marot, M

2014-10-01

Basic visual dysfunctions are commonly reported in schizophrenia; however their value as diagnostic tools remains uncertain. This study reports a novel electrophysiological approach using checkerboard visual evoked potentials (VEP). Sources of spectral resolution VEP-components C1, P1 and N1 were estimated by LORETA, and the band-effects (BSE) on these estimated sources were explored in each subject. BSEs were Z-transformed for each component and relationships with clinical variables were assessed. Clinical effects were evaluated by ROC-curves and predictive values. Forty-eight patients with schizophrenia (SZ) and 55 healthy controls participated in the study. For each of the 48 patients, the three VEP components were localized to both dorsal and ventral brain areas and also deviated from a normal distribution. P1 and N1 deviations were independent of treatment, illness chronicity or gender. Results from LORETA also suggest that deficits in thalamus, posterior cingulum, precuneus, superior parietal and medial occipitotemporal areas were associated with symptom severity. While positive symptoms were more strongly related to sensory processing deficits (P1), negative symptoms were more strongly related to perceptual processing dysfunction (N1). Clinical validation revealed positive and negative predictive values for correctly classifying SZ of 100% and 77%, respectively. Classification in an additional independent sample of 30 SZ corroborated these results. In summary, this novel approach revealed basic visual dysfunctions in all patients with schizophrenia, suggesting these visual dysfunctions represent a promising candidate as a biomarker for schizophrenia. Copyright © 2014 Elsevier B.V. All rights reserved.

A Visual Analog Scale to assess anxiety in children during anesthesia induction (VAS-I): Results supporting its validity in a sample of day care surgery patients.

PubMed

Berghmans, Johan M; Poley, Marten J; van der Ende, Jan; Weber, Frank; Van de Velde, Marc; Adriaenssens, Peter; Himpe, Dirk; Verhulst, Frank C; Utens, Elisabeth

2017-09-01

The modified Yale Preoperative Anxiety Scale is widely used to assess children's anxiety during induction of anesthesia, but requires training and its administration is time-consuming. A Visual Analog Scale, in contrast, requires no training, is easy-to-use and quickly completed. The aim of this study was to evaluate a Visual Analog Scale as a tool to assess anxiety during induction of anesthesia and to determine cut-offs to distinguish between anxious and nonanxious children. Four hundred and one children (1.5-16 years) scheduled for daytime surgery were included. Children's anxiety during induction was rated by parents and anesthesiologists on a Visual Analog Scale and by a trained observer on the modified Yale Preoperative Anxiety Scale. Psychometric properties assessed were: (i) concurrent validity (correlations between parents' and anesthesiologists' Visual Analog Scale and modified Yale Preoperative Anxiety Scale scores); (ii) construct validity (differences between subgroups according to the children's age and the parents' anxiety as assessed by the State-Trait Anxiety Inventory); (iii) cross-informant agreement using Bland-Altman analysis; (iv) cut-offs to distinguish between anxious and nonanxious children (reference: modified Yale Preoperative Anxiety Scale ≥30). Correlations between parents' and anesthesiologists' Visual Analog Scale and modified Yale Preoperative Anxiety Scale scores were strong (0.68 and 0.73, respectively). Visual Analog Scale scores were higher for children ≤5 years compared to children aged ≥6. Visual Analog Scale scores of children of high-anxious parents were higher than those of low-anxious parents. The mean difference between parents' and anesthesiologists' Visual Analog Scale scores was 3.6, with 95% limits of agreement (-56.1 to 63.3). To classify anxious children, cut-offs for parents (≥37 mm) and anesthesiologists (≥30 mm) were established. The present data provide preliminary data for the validity of a Visual Analog Scale to assess children's anxiety during induction. © 2017 John Wiley & Sons Ltd.

AutoBD: Automated Bi-Level Description for Scalable Fine-Grained Visual Categorization.

PubMed

Yao, Hantao; Zhang, Shiliang; Yan, Chenggang; Zhang, Yongdong; Li, Jintao; Tian, Qi

Compared with traditional image classification, fine-grained visual categorization is a more challenging task, because it targets to classify objects belonging to the same species, e.g. , classify hundreds of birds or cars. In the past several years, researchers have made many achievements on this topic. However, most of them are heavily dependent on the artificial annotations, e.g., bounding boxes, part annotations, and so on . The requirement of artificial annotations largely hinders the scalability and application. Motivated to release such dependence, this paper proposes a robust and discriminative visual description named Automated Bi-level Description (AutoBD). "Bi-level" denotes two complementary part-level and object-level visual descriptions, respectively. AutoBD is "automated," because it only requires the image-level labels of training images and does not need any annotations for testing images. Compared with the part annotations labeled by the human, the image-level labels can be easily acquired, which thus makes AutoBD suitable for large-scale visual categorization. Specifically, the part-level description is extracted by identifying the local region saliently representing the visual distinctiveness. The object-level description is extracted from object bounding boxes generated with a co-localization algorithm. Although only using the image-level labels, AutoBD outperforms the recent studies on two public benchmark, i.e. , classification accuracy achieves 81.6% on CUB-200-2011 and 88.9% on Car-196, respectively. On the large-scale Birdsnap data set, AutoBD achieves the accuracy of 68%, which is currently the best performance to the best of our knowledge.Compared with traditional image classification, fine-grained visual categorization is a more challenging task, because it targets to classify objects belonging to the same species, e.g. , classify hundreds of birds or cars. In the past several years, researchers have made many achievements on this topic. However, most of them are heavily dependent on the artificial annotations, e.g., bounding boxes, part annotations, and so on . The requirement of artificial annotations largely hinders the scalability and application. Motivated to release such dependence, this paper proposes a robust and discriminative visual description named Automated Bi-level Description (AutoBD). "Bi-level" denotes two complementary part-level and object-level visual descriptions, respectively. AutoBD is "automated," because it only requires the image-level labels of training images and does not need any annotations for testing images. Compared with the part annotations labeled by the human, the image-level labels can be easily acquired, which thus makes AutoBD suitable for large-scale visual categorization. Specifically, the part-level description is extracted by identifying the local region saliently representing the visual distinctiveness. The object-level description is extracted from object bounding boxes generated with a co-localization algorithm. Although only using the image-level labels, AutoBD outperforms the recent studies on two public benchmark, i.e. , classification accuracy achieves 81.6% on CUB-200-2011 and 88.9% on Car-196, respectively. On the large-scale Birdsnap data set, AutoBD achieves the accuracy of 68%, which is currently the best performance to the best of our knowledge.

A Fuzzy Integral Ensemble Method in Visual P300 Brain-Computer Interface.

PubMed

Cavrini, Francesco; Bianchi, Luigi; Quitadamo, Lucia Rita; Saggio, Giovanni

2016-01-01

We evaluate the possibility of application of combination of classifiers using fuzzy measures and integrals to Brain-Computer Interface (BCI) based on electroencephalography. In particular, we present an ensemble method that can be applied to a variety of systems and evaluate it in the context of a visual P300-based BCI. Offline analysis of data relative to 5 subjects lets us argue that the proposed classification strategy is suitable for BCI. Indeed, the achieved performance is significantly greater than the average of the base classifiers and, broadly speaking, similar to that of the best one. Thus the proposed methodology allows realizing systems that can be used by different subjects without the need for a preliminary configuration phase in which the best classifier for each user has to be identified. Moreover, the ensemble is often capable of detecting uncertain situations and turning them from misclassifications into abstentions, thereby improving the level of safety in BCI for environmental or device control.

An Automated Classification Technique for Detecting Defects in Battery Cells

NASA Technical Reports Server (NTRS)

McDowell, Mark; Gray, Elizabeth

2006-01-01

Battery cell defect classification is primarily done manually by a human conducting a visual inspection to determine if the battery cell is acceptable for a particular use or device. Human visual inspection is a time consuming task when compared to an inspection process conducted by a machine vision system. Human inspection is also subject to human error and fatigue over time. We present a machine vision technique that can be used to automatically identify defective sections of battery cells via a morphological feature-based classifier using an adaptive two-dimensional fast Fourier transformation technique. The initial area of interest is automatically classified as either an anode or cathode cell view as well as classified as an acceptable or a defective battery cell. Each battery cell is labeled and cataloged for comparison and analysis. The result is the implementation of an automated machine vision technique that provides a highly repeatable and reproducible method of identifying and quantifying defects in battery cells.

The audiovisual structure of onomatopoeias: An intrusion of real-world physics in lexical creation.

PubMed

Taitz, Alan; Assaneo, M Florencia; Elisei, Natalia; Trípodi, Mónica; Cohen, Laurent; Sitt, Jacobo D; Trevisan, Marcos A

2018-01-01

Sound-symbolic word classes are found in different cultures and languages worldwide. These words are continuously produced to code complex information about events. Here we explore the capacity of creative language to transport complex multisensory information in a controlled experiment, where our participants improvised onomatopoeias from noisy moving objects in audio, visual and audiovisual formats. We found that consonants communicate movement types (slide, hit or ring) mainly through the manner of articulation in the vocal tract. Vowels communicate shapes in visual stimuli (spiky or rounded) and sound frequencies in auditory stimuli through the configuration of the lips and tongue. A machine learning model was trained to classify movement types and used to validate generalizations of our results across formats. We implemented the classifier with a list of cross-linguistic onomatopoeias simple actions were correctly classified, while different aspects were selected to build onomatopoeias of complex actions. These results show how the different aspects of complex sensory information are coded and how they interact in the creation of novel onomatopoeias.

Quantification and Visualization of Variation in Anatomical Trees

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

Amenta, Nina; Datar, Manasi; Dirksen, Asger

This paper presents two approaches to quantifying and visualizing variation in datasets of trees. The first approach localizes subtrees in which significant population differences are found through hypothesis testing and sparse classifiers on subtree features. The second approach visualizes the global metric structure of datasets through low-distortion embedding into hyperbolic planes in the style of multidimensional scaling. A case study is made on a dataset of airway trees in relation to Chronic Obstructive Pulmonary Disease.

A prototype system based on visual interactive SDM called VGC

NASA Astrophysics Data System (ADS)

Jia, Zelu; Liu, Yaolin; Liu, Yanfang

2009-10-01

In many application domains, data is collected and referenced by its geo-spatial location. Spatial data mining, or the discovery of interesting patterns in such databases, is an important capability in the development of database systems. Spatial data mining recently emerges from a number of real applications, such as real-estate marketing, urban planning, weather forecasting, medical image analysis, road traffic accident analysis, etc. It demands for efficient solutions for many new, expensive, and complicated problems. For spatial data mining of large data sets to be effective, it is also important to include humans in the data exploration process and combine their flexibility, creativity, and general knowledge with the enormous storage capacity and computational power of today's computers. Visual spatial data mining applies human visual perception to the exploration of large data sets. Presenting data in an interactive, graphical form often fosters new insights, encouraging the information and validation of new hypotheses to the end of better problem-solving and gaining deeper domain knowledge. In this paper a visual interactive spatial data mining prototype system (visual geo-classify) based on VC++6.0 and MapObject2.0 are designed and developed, the basic algorithms of the spatial data mining is used decision tree and Bayesian networks, and data classify are used training and learning and the integration of the two to realize. The result indicates it's a practical and extensible visual interactive spatial data mining tool.

Soy sauce classification by geographic region and fermentation based on artificial neural network and genetic algorithm.

PubMed

Xu, Libin; Li, Yang; Xu, Ning; Hu, Yong; Wang, Chao; He, Jianjun; Cao, Yueze; Chen, Shigui; Li, Dongsheng

2014-12-24

This work demonstrated the possibility of using artificial neural networks to classify soy sauce from China. The aroma profiles of different soy sauce samples were differentiated using headspace solid-phase microextraction. The soy sauce samples were analyzed by gas chromatography-mass spectrometry, and 22 and 15 volatile aroma compounds were selected for sensitivity analysis to classify the samples by fermentation and geographic region, respectively. The 15 selected samples can be classified by fermentation and geographic region with a prediction success rate of 100%. Furans and phenols represented the variables with the greatest contribution in classifying soy sauce samples by fermentation and geographic region, respectively.

Comparative Characterization of Crofelemer Samples Using Data Mining and Machine Learning Approaches With Analytical Stability Data Sets.

PubMed

Nariya, Maulik K; Kim, Jae Hyun; Xiong, Jian; Kleindl, Peter A; Hewarathna, Asha; Fisher, Adam C; Joshi, Sangeeta B; Schöneich, Christian; Forrest, M Laird; Middaugh, C Russell; Volkin, David B; Deeds, Eric J

2017-11-01

There is growing interest in generating physicochemical and biological analytical data sets to compare complex mixture drugs, for example, products from different manufacturers. In this work, we compare various crofelemer samples prepared from a single lot by filtration with varying molecular weight cutoffs combined with incubation for different times at different temperatures. The 2 preceding articles describe experimental data sets generated from analytical characterization of fractionated and degraded crofelemer samples. In this work, we use data mining techniques such as principal component analysis and mutual information scores to help visualize the data and determine discriminatory regions within these large data sets. The mutual information score identifies chemical signatures that differentiate crofelemer samples. These signatures, in many cases, would likely be missed by traditional data analysis tools. We also found that supervised learning classifiers robustly discriminate samples with around 99% classification accuracy, indicating that mathematical models of these physicochemical data sets are capable of identifying even subtle differences in crofelemer samples. Data mining and machine learning techniques can thus identify fingerprint-type attributes of complex mixture drugs that may be used for comparative characterization of products. Copyright © 2017 American Pharmacists Association®. All rights reserved.

Separability of Abstract-Category and Specific-Exemplar Visual Object Subsystems: Evidence from fMRI Pattern Analysis

PubMed Central

McMenamin, Brenton W.; Deason, Rebecca G.; Steele, Vaughn R.; Koutstaal, Wilma; Marsolek, Chad J.

2014-01-01

Previous research indicates that dissociable neural subsystems underlie abstract-category (AC) recognition and priming of objects (e.g., cat, piano) and specific-exemplar (SE) recognition and priming of objects (e.g., a calico cat, a different calico cat, a grand piano, etc.). However, the degree of separability between these subsystems is not known, despite the importance of this issue for assessing relevant theories. Visual object representations are widely distributed in visual cortex, thus a multivariate pattern analysis (MVPA) approach to analyzing functional magnetic resonance imaging (fMRI) data may be critical for assessing the separability of different kinds of visual object processing. Here we examined the neural representations of visual object categories and visual object exemplars using multi-voxel pattern analyses of brain activity elicited in visual object processing areas during a repetition-priming task. In the encoding phase, participants viewed visual objects and the printed names of other objects. In the subsequent test phase, participants identified objects that were either same-exemplar primed, different-exemplar primed, word-primed, or unprimed. In visual object processing areas, classifiers were trained to distinguish same-exemplar primed objects from word-primed objects. Then, the abilities of these classifiers to discriminate different-exemplar primed objects and word-primed objects (reflecting AC priming) and to discriminate same-exemplar primed objects and different-exemplar primed objects (reflecting SE priming) was assessed. Results indicated that (a) repetition priming in occipital-temporal regions is organized asymmetrically, such that AC priming is more prevalent in the left hemisphere and SE priming is more prevalent in the right hemisphere, and (b) AC and SE subsystems are weakly modular, not strongly modular or unified. PMID:25528436

Separability of abstract-category and specific-exemplar visual object subsystems: evidence from fMRI pattern analysis.

PubMed

McMenamin, Brenton W; Deason, Rebecca G; Steele, Vaughn R; Koutstaal, Wilma; Marsolek, Chad J

2015-02-01

Previous research indicates that dissociable neural subsystems underlie abstract-category (AC) recognition and priming of objects (e.g., cat, piano) and specific-exemplar (SE) recognition and priming of objects (e.g., a calico cat, a different calico cat, a grand piano, etc.). However, the degree of separability between these subsystems is not known, despite the importance of this issue for assessing relevant theories. Visual object representations are widely distributed in visual cortex, thus a multivariate pattern analysis (MVPA) approach to analyzing functional magnetic resonance imaging (fMRI) data may be critical for assessing the separability of different kinds of visual object processing. Here we examined the neural representations of visual object categories and visual object exemplars using multi-voxel pattern analyses of brain activity elicited in visual object processing areas during a repetition-priming task. In the encoding phase, participants viewed visual objects and the printed names of other objects. In the subsequent test phase, participants identified objects that were either same-exemplar primed, different-exemplar primed, word-primed, or unprimed. In visual object processing areas, classifiers were trained to distinguish same-exemplar primed objects from word-primed objects. Then, the abilities of these classifiers to discriminate different-exemplar primed objects and word-primed objects (reflecting AC priming) and to discriminate same-exemplar primed objects and different-exemplar primed objects (reflecting SE priming) was assessed. Results indicated that (a) repetition priming in occipital-temporal regions is organized asymmetrically, such that AC priming is more prevalent in the left hemisphere and SE priming is more prevalent in the right hemisphere, and (b) AC and SE subsystems are weakly modular, not strongly modular or unified. Copyright © 2014 Elsevier Inc. All rights reserved.

Objective automated quantification of fluorescence signal in histological sections of rat lens.

PubMed

Talebizadeh, Nooshin; Hagström, Nanna Zhou; Yu, Zhaohua; Kronschläger, Martin; Söderberg, Per; Wählby, Carolina

2017-08-01

Visual quantification and classification of fluorescent signals is the gold standard in microscopy. The purpose of this study was to develop an automated method to delineate cells and to quantify expression of fluorescent signal of biomarkers in each nucleus and cytoplasm of lens epithelial cells in a histological section. A region of interest representing the lens epithelium was manually demarcated in each input image. Thereafter, individual cell nuclei within the region of interest were automatically delineated based on watershed segmentation and thresholding with an algorithm developed in Matlab™. Fluorescence signal was quantified within nuclei, cytoplasms and juxtaposed backgrounds. The classification of cells as labelled or not labelled was based on comparison of the fluorescence signal within cells with local background. The classification rule was thereafter optimized as compared with visual classification of a limited dataset. The performance of the automated classification was evaluated by asking 11 independent blinded observers to classify all cells (n = 395) in one lens image. Time consumed by the automatic algorithm and visual classification of cells was recorded. On an average, 77% of the cells were correctly classified as compared with the majority vote of the visual observers. The average agreement among visual observers was 83%. However, variation among visual observers was high, and agreement between two visual observers was as low as 71% in the worst case. Automated classification was on average 10 times faster than visual scoring. The presented method enables objective and fast detection of lens epithelial cells and quantification of expression of fluorescent signal with an accuracy comparable with the variability among visual observers. © 2017 International Society for Advancement of Cytometry. © 2017 International Society for Advancement of Cytometry.

Natural course of visual field loss in patients with Type 2 Usher syndrome.

PubMed

Fishman, Gerald A; Bozbeyoglu, Simge; Massof, Robert W; Kimberling, William

2007-06-01

To evaluate the natural course of visual field loss in patients with Type 2 Usher syndrome and different patterns of visual field loss. Fifty-eight patients with Type 2 Usher syndrome who had at least three visual field measurements during a period of at least 3 years were studied. Kinetic visual fields measured on a standard calibrated Goldmann perimeter with II4e and V4e targets were analyzed. The visual field areas in both eyes were determined by planimetry with the use of a digitalizing tablet and computer software and expressed in square inches. The data for each visual field area measurement were transformed to a natural log unit. Using a mixed model regression analysis, values for the half-life of field loss (time during which half of the remaining field area is lost) were estimated. Three different patterns of visual field loss were identified, and the half-life time for each pattern of loss was calculated. Of the 58 patients, 11 were classified as having pattern type I, 12 with pattern type II, and 14 with pattern type III. Of 21 patients whose visual field loss was so advanced that they could not be classified, 15 showed only a small residual central field (Group A) and 6 showed a residual central field with a peripheral island (Group B). The average half-life times varied between 3.85 and 7.37 for the II4e test target and 4.59 to 6.42 for the V4e target. There was no statistically significant difference in the half-life times between the various patterns of field loss or for the test targets. The average half-life times for visual field loss in patients with Usher syndrome Type 2 were statistically similar among those patients with different patterns of visual field loss. These findings will be useful for counseling patients with Type 2 Usher syndrome as to their prognosis for anticipated visual field loss.

A catalog of galaxy morphology and photometric redshift

NASA Astrophysics Data System (ADS)

Paul, Nicholas; Shamir, Lior

2018-01-01

Morphology carries important information about the physical characteristics of a galaxy. Here we used machine learning to produce a catalog of ~3,000,000 SDSS galaxies classified by their broad morphology into spiral and elliptical galaxies. Comparison of the catalog to Galaxy Zooshows that the catalog contains a subset of 1.7*10^6 galaxies classified with the same level of consistency as the debiased “superclean” sub-sample. In addition to the morphology, we also computed the photometric redshifts of the galaxies. Several pattern recognition algorithms and variable selection strategies were tested, and the best accuracy of mean absolute error of ~0.0062 was achieved by using random forest with a combination of manually and automatically selected variables. The catalog shows that for redshift lower than 0.085 galaxies that visually look spiral become more prevalent as the redshift gets higher. For redshift greater than 0.085 galaxies thatvisually look elliptical become more prevalent. The catalog as well as the source code used to produce it is publicly available athttps://figshare.com/articles/Morphology_and_photometric_redshift_catalog/4833593 .

Manifold regularized multitask learning for semi-supervised multilabel image classification.

PubMed

Luo, Yong; Tao, Dacheng; Geng, Bo; Xu, Chao; Maybank, Stephen J

2013-02-01

It is a significant challenge to classify images with multiple labels by using only a small number of labeled samples. One option is to learn a binary classifier for each label and use manifold regularization to improve the classification performance by exploring the underlying geometric structure of the data distribution. However, such an approach does not perform well in practice when images from multiple concepts are represented by high-dimensional visual features. Thus, manifold regularization is insufficient to control the model complexity. In this paper, we propose a manifold regularized multitask learning (MRMTL) algorithm. MRMTL learns a discriminative subspace shared by multiple classification tasks by exploiting the common structure of these tasks. It effectively controls the model complexity because different tasks limit one another's search volume, and the manifold regularization ensures that the functions in the shared hypothesis space are smooth along the data manifold. We conduct extensive experiments, on the PASCAL VOC'07 dataset with 20 classes and the MIR dataset with 38 classes, by comparing MRMTL with popular image classification algorithms. The results suggest that MRMTL is effective for image classification.

Rapid pupil-based assessment of glaucomatous damage.

PubMed

Chen, Yanjun; Wyatt, Harry J; Swanson, William H; Dul, Mitchell W

2008-06-01

To investigate the ability of a technique employing pupillometry and functionally-shaped stimuli to assess loss of visual function due to glaucomatous optic neuropathy. Pairs of large stimuli, mirror images about the horizontal meridian, were displayed alternately in the upper and lower visual field. Pupil diameter was recorded and analyzed in terms of the "contrast balance" (relative sensitivity to the upper and lower stimuli), and the pupil constriction amplitude to upper and lower stimuli separately. A group of 40 patients with glaucoma was tested twice in a first session, and twice more in a second session, 1 to 3 weeks later. A group of 40 normal subjects was tested with the same protocol. Results for the normal subjects indicated functional symmetry in upper/lower retina, on average. Contrast balance results for the patients with glaucoma differed from normal: half the normal subjects had contrast balance within 0.06 log unit of equality and 80% had contrast balance within 0.1 log unit. Half the patients had contrast balances more than 0.1 log unit from equality. Patient contrast balances were moderately correlated with predictions from perimetric data (r = 0.37, p < 0.00001). Contrast balances correctly classified visual field damage in 28 patients (70%), and response amplitudes correctly classified 24 patients (60%). When contrast balance and response amplitude were combined, receiver operating characteristic area for discriminating glaucoma from normal was 0.83. Pupillary evaluation of retinal asymmetry provides a rapid method for detecting and classifying visual field defects. In this patient population, classification agreed with perimetry in 70% of eyes.

Rapid Pupil-Based Assessment of Glaucomatous Damage

PubMed Central

Chen, Yanjun; Wyatt, Harry J.; Swanson, William H.; Dul, Mitchell W.

2010-01-01

Purpose To investigate the ability of a technique employing pupillometry and functionally-shaped stimuli to assess loss of visual function due to glaucomatous optic neuropathy. Methods Pairs of large stimuli, mirror images about the horizontal meridian, were displayed alternately in the upper and lower visual field. Pupil diameter was recorded and analyzed in terms of the “contrast balance” (relative sensitivity to the upper and lower stimuli), and the pupil constriction amplitude to upper and lower stimuli separately. A group of 40 patients with glaucoma was tested twice in a first session, and twice more in a second session, 1 to 3 weeks later. A group of 40 normal subjects was tested with the same protocol. Results Results for the normal subjects indicated functional symmetry in upper/lower retina, on average. Contrast balance results for the patients with glaucoma differed from normal: half the normal subjects had contrast balance within 0.06 log unit of equality and 80% had contrast balance within 0.1 log unit. Half the patients had contrast balances more than 0.1 log unit from equality. Patient contrast balances were moderately correlated with predictions from perimetric data (r = 0.37, p < 0.00001). Contrast balances correctly classified visual field damage in 28 patients (70%), and response amplitudes correctly classified 24 patients (60%). When contrast balance and response amplitude were combined, receiver operating characteristic area for discriminating glaucoma from normal was 0.83. Conclusions Pupillary evaluation of retinal asymmetry provides a rapid method for detecting and classifying visual field defects. In this patient population, classification agreed with perimetry in 70% of eyes. PMID:18521026

Predicting membrane protein types using various decision tree classifiers based on various modes of general PseAAC for imbalanced datasets.

PubMed

Sankari, E Siva; Manimegalai, D

2017-12-21

Predicting membrane protein types is an important and challenging research area in bioinformatics and proteomics. Traditional biophysical methods are used to classify membrane protein types. Due to large exploration of uncharacterized protein sequences in databases, traditional methods are very time consuming, expensive and susceptible to errors. Hence, it is highly desirable to develop a robust, reliable, and efficient method to predict membrane protein types. Imbalanced datasets and large datasets are often handled well by decision tree classifiers. Since imbalanced datasets are taken, the performance of various decision tree classifiers such as Decision Tree (DT), Classification And Regression Tree (CART), C4.5, Random tree, REP (Reduced Error Pruning) tree, ensemble methods such as Adaboost, RUS (Random Under Sampling) boost, Rotation forest and Random forest are analysed. Among the various decision tree classifiers Random forest performs well in less time with good accuracy of 96.35%. Another inference is RUS boost decision tree classifier is able to classify one or two samples in the class with very less samples while the other classifiers such as DT, Adaboost, Rotation forest and Random forest are not sensitive for the classes with fewer samples. Also the performance of decision tree classifiers is compared with SVM (Support Vector Machine) and Naive Bayes classifier. Copyright © 2017 Elsevier Ltd. All rights reserved.

Zooniverse: Combining Human and Machine Classifiers for the Big Survey Era

NASA Astrophysics Data System (ADS)

Fortson, Lucy; Wright, Darryl; Beck, Melanie; Lintott, Chris; Scarlata, Claudia; Dickinson, Hugh; Trouille, Laura; Willi, Marco; Laraia, Michael; Boyer, Amy; Veldhuis, Marten; Zooniverse

2018-01-01

Many analyses of astronomical data sets, ranging from morphological classification of galaxies to identification of supernova candidates, have relied on humans to classify data into distinct categories. Crowdsourced galaxy classifications via the Galaxy Zoo project provided a solution that scaled visual classification for extant surveys by harnessing the combined power of thousands of volunteers. However, the much larger data sets anticipated from upcoming surveys will require a different approach. Automated classifiers using supervised machine learning have improved considerably over the past decade but their increasing sophistication comes at the expense of needing ever more training data. Crowdsourced classification by human volunteers is a critical technique for obtaining these training data. But several improvements can be made on this zeroth order solution. Efficiency gains can be achieved by implementing a “cascade filtering” approach whereby the task structure is reduced to a set of binary questions that are more suited to simpler machines while demanding lower cognitive loads for humans.Intelligent subject retirement based on quantitative metrics of volunteer skill and subject label reliability also leads to dramatic improvements in efficiency. We note that human and machine classifiers may retire subjects differently leading to trade-offs in performance space. Drawing on work with several Zooniverse projects including Galaxy Zoo and Supernova Hunter, we will present recent findings from experiments that combine cohorts of human and machine classifiers. We show that the most efficient system results when appropriate subsets of the data are intelligently assigned to each group according to their particular capabilities.With sufficient online training, simple machines can quickly classify “easy” subjects, leaving more difficult (and discovery-oriented) tasks for volunteers. We also find humans achieve higher classification purity while samples produced by machines are typically more complete. These findings set the stage for further investigations, with the ultimate goal of efficiently and accurately labeling the wide range of data classes that will arise from the planned large astronomical surveys.

Automatic lip reading by using multimodal visual features

NASA Astrophysics Data System (ADS)

Takahashi, Shohei; Ohya, Jun

2013-12-01

Since long time ago, speech recognition has been researched, though it does not work well in noisy places such as in the car or in the train. In addition, people with hearing-impaired or difficulties in hearing cannot receive benefits from speech recognition. To recognize the speech automatically, visual information is also important. People understand speeches from not only audio information, but also visual information such as temporal changes in the lip shape. A vision based speech recognition method could work well in noisy places, and could be useful also for people with hearing disabilities. In this paper, we propose an automatic lip-reading method for recognizing the speech by using multimodal visual information without using any audio information such as speech recognition. First, the ASM (Active Shape Model) is used to track and detect the face and lip in a video sequence. Second, the shape, optical flow and spatial frequencies of the lip features are extracted from the lip detected by ASM. Next, the extracted multimodal features are ordered chronologically so that Support Vector Machine is performed in order to learn and classify the spoken words. Experiments for classifying several words show promising results of this proposed method.

Association of Visual Acuity and Cognitive Impairment in Older Individuals: Fujiwara-kyo Eye Study

PubMed Central

Mine, Masashi; Miyata, Kimie; Morikawa, Masayuki; Nishi, Tomo; Okamoto, Nozomi; Kawasaki, Ryo; Yamashita, Hidetoshi; Kurumatani, Norio; Ogata, Nahoko

2016-01-01

Abstract Both visual impairment and cognitive impairment are essential factors that determine the quality of life in the aged population. The aim of this study was to determine if a correlation existed between visual acuity and cognitive impairment in an elderly Japanese population. The Fujiwara-kyo Eye Study was a cross-sectional study of individuals aged ≥68 years who lived in Nara Prefecture of Japan. Participants underwent ophthalmological examinations and cognitive function test. A mild visual impairment was defined as having a best corrected visual acuity (BCVA) >0.2 logarithm of the minimum angle of resolution (logMAR) units in the better eye. Cognitive impairment was defined as having a Mini-Mental State Examination (MMSE) score of ≤23 points. A total to 2818 individuals completed the examinations. The mean age of the participants was 76.3 ± 4.8 years (mean ± standard deviation). The mean BCVA of the better eye was −0.02 ± 0.13 logMAR units and 6.6% subjects were classified as being mildly visually impaired. The mean MMSE score was 27.3 ± 2.3 and 5.7% subjects were classified as being cognitively impaired. The proportion of subjects with cognitive or moderate visual impairment increased with age, and there was a significant correlation between the visual acuity and MMSE score (r = −0.10, p < 0.0001). Subjects with mild visual impairments had 2.4 times higher odds of having cognitive impairment than those without visual impairment (odds ratio 2.4, 95% confidence interval, 1.5–3.8, p < 0.001) after adjusting for age, sex, and length of education. We conclude that it may be important to maintain good visual acuity to reduce the risk of having cognitive impairment. PMID:27610269

Consensus Classification Using Non-Optimized Classifiers.

PubMed

Brownfield, Brett; Lemos, Tony; Kalivas, John H

2018-04-03

Classifying samples into categories is a common problem in analytical chemistry and other fields. Classification is usually based on only one method, but numerous classifiers are available with some being complex, such as neural networks, and others are simple, such as k nearest neighbors. Regardless, most classification schemes require optimization of one or more tuning parameters for best classification accuracy, sensitivity, and specificity. A process not requiring exact selection of tuning parameter values would be useful. To improve classification, several ensemble approaches have been used in past work to combine classification results from multiple optimized single classifiers. The collection of classifications for a particular sample are then combined by a fusion process such as majority vote to form the final classification. Presented in this Article is a method to classify a sample by combining multiple classification methods without specifically classifying the sample by each method, that is, the classification methods are not optimized. The approach is demonstrated on three analytical data sets. The first is a beer authentication set with samples measured on five instruments, allowing fusion of multiple instruments by three ways. The second data set is composed of textile samples from three classes based on Raman spectra. This data set is used to demonstrate the ability to classify simultaneously with different data preprocessing strategies, thereby reducing the need to determine the ideal preprocessing method, a common prerequisite for accurate classification. The third data set contains three wine cultivars for three classes measured at 13 unique chemical and physical variables. In all cases, fusion of nonoptimized classifiers improves classification. Also presented are atypical uses of Procrustes analysis and extended inverted signal correction (EISC) for distinguishing sample similarities to respective classes.

Galactic satellite systems: radial distribution and environment dependence of galaxy morphology

NASA Astrophysics Data System (ADS)

Ann, H. B.; Park, Changbom; Choi, Yun-Young

2008-09-01

We have studied the radial distribution of the early (E/S0) and late (S/Irr) types of satellites around bright host galaxies. We made a volume-limited sample of 4986 satellites brighter than Mr = -18.0 associated with 2254 hosts brighter than Mr = -19.0 from the Sloan Digital Sky Survey Data Release 5 sample. The morphology of satellites is determined by an automated morphology classifier, but the host galaxies are visually classified. We found segregation of satellite morphology as a function of the projected distance from the host galaxy. The amplitude and shape of the early-type satellite fraction profile are found to depend on the host luminosity. This is the morphology-radius/density relation at the galactic scale. There is a strong tendency for morphology conformity between the host galaxy and its satellites. The early-type fraction of satellites hosted by early-type galaxies is systematically larger than that of late-type hosts, and is a strong function of the distance from the host galaxies. Fainter satellites are more vulnerable to the morphology transformation effects of hosts. Dependence of satellite morphology on the large-scale background density was detected. The fraction of early-type satellites increases in high-density regions for both early- and late-type hosts. It is argued that the conformity in morphology of galactic satellite system is mainly originated by the hydrodynamical and radiative effects of hosts on satellites.

Performance of wavelet analysis and neural networks for pathological voices identification

NASA Astrophysics Data System (ADS)

Salhi, Lotfi; Talbi, Mourad; Abid, Sabeur; Cherif, Adnane

2011-09-01

Within the medical environment, diverse techniques exist to assess the state of the voice of the patient. The inspection technique is inconvenient for a number of reasons, such as its high cost, the duration of the inspection, and above all, the fact that it is an invasive technique. This study focuses on a robust, rapid and accurate system for automatic identification of pathological voices. This system employs non-invasive, non-expensive and fully automated method based on hybrid approach: wavelet transform analysis and neural network classifier. First, we present the results obtained in our previous study while using classic feature parameters. These results allow visual identification of pathological voices. Second, quantified parameters drifting from the wavelet analysis are proposed to characterise the speech sample. On the other hand, a system of multilayer neural networks (MNNs) has been developed which carries out the automatic detection of pathological voices. The developed method was evaluated using voice database composed of recorded voice samples (continuous speech) from normophonic or dysphonic speakers. The dysphonic speakers were patients of a National Hospital 'RABTA' of Tunis Tunisia and a University Hospital in Brussels, Belgium. Experimental results indicate a success rate ranging between 75% and 98.61% for discrimination of normal and pathological voices using the proposed parameters and neural network classifier. We also compared the average classification rate based on the MNN, Gaussian mixture model and support vector machines.

Integrated terrain mapping with digital Landsat images in Queensland, Australia

USGS Publications Warehouse

Robinove, Charles Joseph

1979-01-01

Mapping with Landsat images usually is done by selecting single types of features, such as soils, vegetation, or rocks, and creating visually interpreted or digitally classified maps of each feature. Individual maps can then be overlaid on or combined with other maps to characterize the terrain. Integrated terrain mapping combines several terrain features into each map unit which, in many cases, is more directly related to uses of the land and to methods of land management than the single features alone. Terrain brightness, as measured by the multispectral scanners in Landsat 1 and 2, represents an integration of reflectance from the terrain features within the scanner's instantaneous field of view and is therefore more correlatable with integrated terrain units than with differentiated ones, such as rocks, soils, and vegetation. A test of the feasibilty of the technique of mapping integrated terrain units was conducted in a part of southwestern Queensland, Australia, in cooperation with scientists of the Queensland Department of Primary Industries. The primary purpose was to test the use of digital classification techniques to create a 'land systems map' usable for grazing land management. A recently published map of 'land systems' in the area (made by aerial photograph interpretation and ground surveys), which are integrated terrain units composed of vegetation, soil, topography, and geomorphic features, was used as a basis for comparison with digitally classified Landsat multispectral images. The land systems, in turn, each have a specific grazing capacity for cattle (expressed in beasts per km 2 ) which is estimated following analysis of both research results and property carrying capacities. Landsat images, in computer-compatible tape form, were first contrast-stretched to increase their visual interpretability, and digitally classified by the parallelepiped method into distinct spectral classes to determine their correspondence to the land systems classes and to areally smaller, but readily recognizable, 'land units.' Many land systems appeared as distinct spectral classes or as acceptably homogeneous combinations of several spectral classes. The digitally classified map corresponded to the general geographic patterns of many of the land systems. Statistical correlation of the digitally classified map and the published map was not possible because the published map showed only land systems whereas the digitally classified map showed some land units as well as systems. The general correspondence of spectral classes to the integrated terrain units means that the digital mapping of the units may precede fieldwork and act as a guide to field sampling and detailed terrain unit description as well as measuring of the location, area, and extent of each unit. Extension of the Landsat mapping and classification technique to other arid and semi-arid regions of the world may be feasible.

In multiple situational light settings, visual observation for skin colour assessment is comparable with colorimeter measurement.

PubMed

Wright, C Y; Wilkes, M; du Plessis, J L; Reeder, A I; Albers, P N

2016-08-01

Finding inexpensive and reliable techniques for assessing skin colour is important, given that it is related to several adverse human health outcomes. Visual observation is considered a subjective approach assessment and, even when made by trained assessor, concern has been raised about the need for controlled lighting in the study venue. The aim of this study is to determine whether visual skin colour assessments correlate with objective skin colour measurements in study venues with different lighting types and configurations. Two trained investigators, with confirmed visual acuity, visually classified the inner, upper arm skin colour of 556 adults using Munsell(®) colour classifications converted to Individual Typology Angle (°ITA) values based on published data. Skin colour at the same anatomic site was also measured using a colorimeter. Each participant was assessed in one of 10 different buildings, each with a different study day. Munsell(®) -derived °ITA values were compared to colorimeter °ITA values for the full sample and by building/day. We found a strong positive, monotonic correlation between Munsell(®) derived °ITA values and colorimeter °ITA values for all participants (Spearman ρ = 0.8585, P < 0.001). Similar relationships were found when Munsell(®) and colorimeter °ITA values were compared for participants assessed in the same building for all 10 buildings (Spearman ρ values ranged from 0.797 to 0.934, all correlations were statistically significant at P < 0.001). It is possible to visually assess individual skin colour in multiple situational lighting settings and retrieve results that are comparable with objective measurements of skin colour. This was true for individuals of varying population groups and skin pigmentation. © 2015 John Wiley & Sons A/S. Published by John Wiley & Sons Ltd.

Liquid-Based Medium Used to Prepare Cytological Breast Nipple Fluid Improves the Quality of Cellular Samples Automatic Collection

PubMed Central

Zonta, Marco Antonio; Velame, Fernanda; Gema, Samara; Filassi, Jose Roberto; Longatto-Filho, Adhemar

2014-01-01

Background Breast cancer is the second cause of death in women worldwide. The spontaneous breast nipple discharge may contain cells that can be analyzed for malignancy. Halo® Mamo Cyto Test (HMCT) was recently developed as an automated system indicated to aspirate cells from the breast ducts. The objective of this study was to standardize the methodology of sampling and sample preparation of nipple discharge obtained by the automated method Halo breast test and perform cytological evaluation in samples preserved in liquid medium (SurePath™). Methods We analyzed 564 nipple fluid samples, from women between 20 and 85 years old, without history of breast disease and neoplasia, no pregnancy, and without gynecologic medical history, collected by HMCT method and preserved in two different vials with solutions for transport. Results From 306 nipple fluid samples from method 1, 199 (65%) were classified as unsatisfactory (class 0), 104 (34%) samples were classified as benign findings (class II), and three (1%) were classified as undetermined to neoplastic cells (class III). From 258 samples analyzed in method 2, 127 (49%) were classified as class 0, 124 (48%) were classified as class II, and seven (2%) were classified as class III. Conclusion Our study suggests an improvement in the quality and quantity of cellular samples when the association of the two methodologies is performed, Halo breast test and the method in liquid medium. PMID:29147397

Selective visual attention in object detection processes

NASA Astrophysics Data System (ADS)

Paletta, Lucas; Goyal, Anurag; Greindl, Christian

2003-03-01

Object detection is an enabling technology that plays a key role in many application areas, such as content based media retrieval. Attentive cognitive vision systems are here proposed where the focus of attention is directed towards the most relevant target. The most promising information is interpreted in a sequential process that dynamically makes use of knowledge and that enables spatial reasoning on the local object information. The presented work proposes an innovative application of attention mechanisms for object detection which is most general in its understanding of information and action selection. The attentive detection system uses a cascade of increasingly complex classifiers for the stepwise identification of regions of interest (ROIs) and recursively refined object hypotheses. While the most coarse classifiers are used to determine first approximations on a region of interest in the input image, more complex classifiers are used for more refined ROIs to give more confident estimates. Objects are modelled by local appearance based representations and in terms of posterior distributions of the object samples in eigenspace. The discrimination function to discern between objects is modeled by a radial basis functions (RBF) network that has been compared with alternative networks and been proved consistent and superior to other artifical neural networks for appearance based object recognition. The experiments were led for the automatic detection of brand objects in Formula One broadcasts within the European Commission's cognitive vision project DETECT.

Human Actions Analysis: Templates Generation, Matching and Visualization Applied to Motion Capture of Highly-Skilled Karate Athletes

PubMed Central

Piekarczyk, Marcin; Ogiela, Marek R.

2017-01-01

The aim of this paper is to propose and evaluate the novel method of template generation, matching, comparing and visualization applied to motion capture (kinematic) analysis. To evaluate our approach, we have used motion capture recordings (MoCap) of two highly-skilled black belt karate athletes consisting of 560 recordings of various karate techniques acquired with wearable sensors. We have evaluated the quality of generated templates; we have validated the matching algorithm that calculates similarities and differences between various MoCap data; and we have examined visualizations of important differences and similarities between MoCap data. We have concluded that our algorithms works the best when we are dealing with relatively short (2–4 s) actions that might be averaged and aligned with the dynamic time warping framework. In practice, the methodology is designed to optimize the performance of some full body techniques performed in various sport disciplines, for example combat sports and martial arts. We can also use this approach to generate templates or to compare the correct performance of techniques between various top sportsmen in order to generate a knowledge base of reference MoCap videos. The motion template generated by our method can be used for action recognition purposes. We have used the DTW classifier with angle-based features to classify various karate kicks. We have performed leave-one-out action recognition for the Shorin-ryu and Oyama karate master separately. In this case, 100% actions were correctly classified. In another experiment, we used templates generated from Oyama master recordings to classify Shorin-ryu master recordings and vice versa. In this experiment, the overall recognition rate was 94.2%, which is a very good result for this type of complex action. PMID:29125560

A comprehensive statistical classifier of foci in the cell transformation assay for carcinogenicity testing.

PubMed

Callegaro, Giulia; Malkoc, Kasja; Corvi, Raffaella; Urani, Chiara; Stefanini, Federico M

2017-12-01

The identification of the carcinogenic risk of chemicals is currently mainly based on animal studies. The in vitro Cell Transformation Assays (CTAs) are a promising alternative to be considered in an integrated approach. CTAs measure the induction of foci of transformed cells. CTAs model key stages of the in vivo neoplastic process and are able to detect both genotoxic and some non-genotoxic compounds, being the only in vitro method able to deal with the latter. Despite their favorable features, CTAs can be further improved, especially reducing the possible subjectivity arising from the last phase of the protocol, namely visual scoring of foci using coded morphological features. By taking advantage of digital image analysis, the aim of our work is to translate morphological features into statistical descriptors of foci images, and to use them to mimic the classification performances of the visual scorer to discriminate between transformed and non-transformed foci. Here we present a classifier based on five descriptors trained on a dataset of 1364 foci, obtained with different compounds and concentrations. Our classifier showed accuracy, sensitivity and specificity equal to 0.77 and an area under the curve (AUC) of 0.84. The presented classifier outperforms a previously published model. Copyright © 2017 Elsevier Ltd. All rights reserved.

The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets.

PubMed

Saito, Takaya; Rehmsmeier, Marc

2015-01-01

Binary classifiers are routinely evaluated with performance measures such as sensitivity and specificity, and performance is frequently illustrated with Receiver Operating Characteristics (ROC) plots. Alternative measures such as positive predictive value (PPV) and the associated Precision/Recall (PRC) plots are used less frequently. Many bioinformatics studies develop and evaluate classifiers that are to be applied to strongly imbalanced datasets in which the number of negatives outweighs the number of positives significantly. While ROC plots are visually appealing and provide an overview of a classifier's performance across a wide range of specificities, one can ask whether ROC plots could be misleading when applied in imbalanced classification scenarios. We show here that the visual interpretability of ROC plots in the context of imbalanced datasets can be deceptive with respect to conclusions about the reliability of classification performance, owing to an intuitive but wrong interpretation of specificity. PRC plots, on the other hand, can provide the viewer with an accurate prediction of future classification performance due to the fact that they evaluate the fraction of true positives among positive predictions. Our findings have potential implications for the interpretation of a large number of studies that use ROC plots on imbalanced datasets.

Modality-Driven Classification and Visualization of Ensemble Variance

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

Bensema, Kevin; Gosink, Luke; Obermaier, Harald

Advances in computational power now enable domain scientists to address conceptual and parametric uncertainty by running simulations multiple times in order to sufficiently sample the uncertain input space. While this approach helps address conceptual and parametric uncertainties, the ensemble datasets produced by this technique present a special challenge to visualization researchers as the ensemble dataset records a distribution of possible values for each location in the domain. Contemporary visualization approaches that rely solely on summary statistics (e.g., mean and variance) cannot convey the detailed information encoded in ensemble distributions that are paramount to ensemble analysis; summary statistics provide no informationmore » about modality classification and modality persistence. To address this problem, we propose a novel technique that classifies high-variance locations based on the modality of the distribution of ensemble predictions. Additionally, we develop a set of confidence metrics to inform the end-user of the quality of fit between the distribution at a given location and its assigned class. We apply a similar method to time-varying ensembles to illustrate the relationship between peak variance and bimodal or multimodal behavior. These classification schemes enable a deeper understanding of the behavior of the ensemble members by distinguishing between distributions that can be described by a single tendency and distributions which reflect divergent trends in the ensemble.« less

FonaDyn - A system for real-time analysis of the electroglottogram, over the voice range

NASA Astrophysics Data System (ADS)

Ternström, Sten; Johansson, Dennis; Selamtzis, Andreas

2018-01-01

From soft to loud and low to high, the mechanisms of human voice have many degrees of freedom, making it difficult to assess phonation from the acoustic signal alone. FonaDyn is a research tool that combines acoustics with electroglottography (EGG). It characterizes and visualizes in real time the dynamics of EGG waveforms, using statistical clustering of the cycle-synchronous EGG Fourier components, and their sample entropy. The prevalence and stability of different EGG waveshapes are mapped as colored regions into a so-called voice range profile, without needing pre-defined thresholds or categories. With appropriately 'trained' clusters, FonaDyn can classify and map voice regimes. This is of potential scientific, clinical and pedagogical interest.

A convolutional neural network neutrino event classifier

DOE PAGES

Aurisano, A.; Radovic, A.; Rocco, D.; ...

2016-09-01

Here, convolutional neural networks (CNNs) have been widely applied in the computer vision community to solve complex problems in image recognition and analysis. We describe an application of the CNN technology to the problem of identifying particle interactions in sampling calorimeters used commonly in high energy physics and high energy neutrino physics in particular. Following a discussion of the core concepts of CNNs and recent innovations in CNN architectures related to the field of deep learning, we outline a specific application to the NOvA neutrino detector. This algorithm, CVN (Convolutional Visual Network) identifies neutrino interactions based on their topology withoutmore » the need for detailed reconstruction and outperforms algorithms currently in use by the NOvA collaboration.« less

A convolutional neural network neutrino event classifier

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

Aurisano, A.; Radovic, A.; Rocco, D.

Here, convolutional neural networks (CNNs) have been widely applied in the computer vision community to solve complex problems in image recognition and analysis. We describe an application of the CNN technology to the problem of identifying particle interactions in sampling calorimeters used commonly in high energy physics and high energy neutrino physics in particular. Following a discussion of the core concepts of CNNs and recent innovations in CNN architectures related to the field of deep learning, we outline a specific application to the NOvA neutrino detector. This algorithm, CVN (Convolutional Visual Network) identifies neutrino interactions based on their topology withoutmore » the need for detailed reconstruction and outperforms algorithms currently in use by the NOvA collaboration.« less

Automated analysis and reannotation of subcellular locations in confocal images from the Human Protein Atlas.

PubMed

Li, Jieyue; Newberg, Justin Y; Uhlén, Mathias; Lundberg, Emma; Murphy, Robert F

2012-01-01

The Human Protein Atlas contains immunofluorescence images showing subcellular locations for thousands of proteins. These are currently annotated by visual inspection. In this paper, we describe automated approaches to analyze the images and their use to improve annotation. We began by training classifiers to recognize the annotated patterns. By ranking proteins according to the confidence of the classifier, we generated a list of proteins that were strong candidates for reexamination. In parallel, we applied hierarchical clustering to group proteins and identified proteins whose annotations were inconsistent with the remainder of the proteins in their cluster. These proteins were reexamined by the original annotators, and a significant fraction had their annotations changed. The results demonstrate that automated approaches can provide an important complement to visual annotation.

Classification deficits in Alzheimer's disease with special reference to living and nonliving things.

PubMed

Montanes, P; Goldblum, M C; Boller, F

1996-08-01

The present study was conducted to assess the hypothesis that visual similarity between exemplars within a semantic category may affect differentially the recognition process of living and nonliving things, according to task demands, in patients with semantic memory disorders. Thirty-nine Alzheimer's patients and 39 normal elderly subjects were presented with a task in which they had to classify pictures and words, depicting either living or nonliving things, at two levels of classification: subordinate (e.g., mammals versus birds or tools versus vehicles) and attribute (e.g., wild versus domestic animals or fast versus slow vehicles). Contrary to previous results (Montañes, Goldblum, & Boller, 1995) in a naming task, but as expected, living things were better classified than nonliving ones by both controls and patients. As expected, classifications at the subordinate level also gave rise to better performance than classifications at the attribute level. Although (and somewhat unexpectedly) no advantage of picture over word classification emerged, some effects consistent with the hypothesis that visual similarity affects picture classification emerged, in particular within a subgroup of patients with predominant verbal deficits and the most severe semantic memory disorders. This subgroup obtained a better score on classification of pictures than of words depicting living items (that share many visual features) when classification is at the subordinate level (for which visual similarity is a reliable clue to classification), but met with major difficulties when classifying those pictures at the attribute level (for which shared visual features are not reliable clues to classification). These results emphasize the fact that some "normal" effects specific to items in living and nonliving categories have to be considered among the factors causing selective category-specific deficits in patients, as well as their relevance in achieving tasks which require either differentiation between competing exemplars in the same semantic category (naming) or detection of resemblance between those exemplars (categorization).

Comparison of Random Forest, k-Nearest Neighbor, and Support Vector Machine Classifiers for Land Cover Classification Using Sentinel-2 Imagery

PubMed Central

Thanh Noi, Phan; Kappas, Martin

2017-01-01

In previous classification studies, three non-parametric classifiers, Random Forest (RF), k-Nearest Neighbor (kNN), and Support Vector Machine (SVM), were reported as the foremost classifiers at producing high accuracies. However, only a few studies have compared the performances of these classifiers with different training sample sizes for the same remote sensing images, particularly the Sentinel-2 Multispectral Imager (MSI). In this study, we examined and compared the performances of the RF, kNN, and SVM classifiers for land use/cover classification using Sentinel-2 image data. An area of 30 × 30 km2 within the Red River Delta of Vietnam with six land use/cover types was classified using 14 different training sample sizes, including balanced and imbalanced, from 50 to over 1250 pixels/class. All classification results showed a high overall accuracy (OA) ranging from 90% to 95%. Among the three classifiers and 14 sub-datasets, SVM produced the highest OA with the least sensitivity to the training sample sizes, followed consecutively by RF and kNN. In relation to the sample size, all three classifiers showed a similar and high OA (over 93.85%) when the training sample size was large enough, i.e., greater than 750 pixels/class or representing an area of approximately 0.25% of the total study area. The high accuracy was achieved with both imbalanced and balanced datasets. PMID:29271909

Comparison of Random Forest, k-Nearest Neighbor, and Support Vector Machine Classifiers for Land Cover Classification Using Sentinel-2 Imagery.

PubMed

Thanh Noi, Phan; Kappas, Martin

2017-12-22

In previous classification studies, three non-parametric classifiers, Random Forest (RF), k-Nearest Neighbor (kNN), and Support Vector Machine (SVM), were reported as the foremost classifiers at producing high accuracies. However, only a few studies have compared the performances of these classifiers with different training sample sizes for the same remote sensing images, particularly the Sentinel-2 Multispectral Imager (MSI). In this study, we examined and compared the performances of the RF, kNN, and SVM classifiers for land use/cover classification using Sentinel-2 image data. An area of 30 × 30 km² within the Red River Delta of Vietnam with six land use/cover types was classified using 14 different training sample sizes, including balanced and imbalanced, from 50 to over 1250 pixels/class. All classification results showed a high overall accuracy (OA) ranging from 90% to 95%. Among the three classifiers and 14 sub-datasets, SVM produced the highest OA with the least sensitivity to the training sample sizes, followed consecutively by RF and kNN. In relation to the sample size, all three classifiers showed a similar and high OA (over 93.85%) when the training sample size was large enough, i.e., greater than 750 pixels/class or representing an area of approximately 0.25% of the total study area. The high accuracy was achieved with both imbalanced and balanced datasets.

An expert support system for breast cancer diagnosis using color wavelet features.

PubMed

Issac Niwas, S; Palanisamy, P; Chibbar, Rajni; Zhang, W J

2012-10-01

Breast cancer diagnosis can be done through the pathologic assessments of breast tissue samples such as core needle biopsy technique. The result of analysis on this sample by pathologist is crucial for breast cancer patient. In this paper, nucleus of tissue samples are investigated after decomposition by means of the Log-Gabor wavelet on HSV color domain and an algorithm is developed to compute the color wavelet features. These features are used for breast cancer diagnosis using Support Vector Machine (SVM) classifier algorithm. The ability of properly trained SVM is to correctly classify patterns and make them particularly suitable for use in an expert system that aids in the diagnosis of cancer tissue samples. The results are compared with other multivariate classifiers such as Naïves Bayes classifier and Artificial Neural Network. The overall accuracy of the proposed method using SVM classifier will be further useful for automation in cancer diagnosis.

Sweep visually evoked potentials and visual findings in children with West syndrome.

PubMed

de Freitas Dotto, Patrícia; Cavascan, Nívea Nunes; Berezovsky, Adriana; Sacai, Paula Yuri; Rocha, Daniel Martins; Pereira, Josenilson Martins; Salomão, Solange Rios

2014-03-01

West syndrome (WS) is a type of early childhood epilepsy characterized by progressive neurological development deterioration that includes vision. To demonstrate the clinical importance of grating visual acuity thresholds (GVA) measurement by sweep visually evoked potentials technique (sweep-VEP) as a reliable tool for evaluation of the visual cortex status in WS children. This is a retrospective study of the best-corrected binocular GVA and ophthalmological features of WS children referred for the Laboratory of Clinical Electrophysiology of Vision of UNIFESP from 1998 to 2012 (Committee on Ethics in Research of UNIFESP n° 0349/08). The GVA deficit was calculated by subtracting binocular GVA score (logMAR units) of each patient from the median values of age norms from our own lab and classified as mild (0.1-0.39 logMAR), moderate (0.40-0.80 logMAR) or severe (>0.81 logMAR). Associated ophthalmological features were also described. Data from 30 WS children (age from 6 to 108 months, median = 14.5 months, mean ± SD = 22.0 ± 22.1 months; 19 male) were analyzed. The majority presented severe GVA deficit (0.15-1.44 logMAR; mean ± SD = 0.82 ± 0.32 logMAR; median = 0.82 logMAR), poor visual behavior, high prevalence of strabismus and great variability in ocular positioning. The GVA deficit did not vary according to gender (P = .8022), WS type (P = .908), birth age (P = .2881), perinatal oxygenation (P = .7692), visual behavior (P = .8789), ocular motility (P = .1821), nystagmus (P = .2868), risk of drug-induced retinopathy (P = .4632) and participation in early visual stimulation therapy (P = .9010). The sweep-VEP technique is a reliable tool to classify visual system impairment in WS children, in agreement with the poor visual behavior exhibited by them. Copyright © 2013 European Paediatric Neurology Society. Published by Elsevier Ltd. All rights reserved.

Analyzing tree-shape anatomical structures using topological descriptors of branching and ensemble of classifiers.

PubMed

Skoura, Angeliki; Bakic, Predrag R; Megalooikonomou, Vasilis

2013-01-01

The analysis of anatomical tree-shape structures visualized in medical images provides insight into the relationship between tree topology and pathology of the corresponding organs. In this paper, we propose three methods to extract descriptive features of the branching topology; the asymmetry index, the encoding of branching patterns using a node labeling scheme and an extension of the Sholl analysis. Based on these descriptors, we present classification schemes for tree topologies with respect to the underlying pathology. Moreover, we present a classifier ensemble approach which combines the predictions of the individual classifiers to optimize the classification accuracy. We applied the proposed methodology to a dataset of x-ray galactograms, medical images which visualize the breast ductal tree, in order to recognize images with radiological findings regarding breast cancer. The experimental results demonstrate the effectiveness of the proposed framework compared to state-of-the-art techniques suggesting that the proposed descriptors provide more valuable information regarding the topological patterns of ductal trees and indicating the potential of facilitating early breast cancer diagnosis.

Analyzing tree-shape anatomical structures using topological descriptors of branching and ensemble of classifiers

PubMed Central

Skoura, Angeliki; Bakic, Predrag R.; Megalooikonomou, Vasilis

2014-01-01

The analysis of anatomical tree-shape structures visualized in medical images provides insight into the relationship between tree topology and pathology of the corresponding organs. In this paper, we propose three methods to extract descriptive features of the branching topology; the asymmetry index, the encoding of branching patterns using a node labeling scheme and an extension of the Sholl analysis. Based on these descriptors, we present classification schemes for tree topologies with respect to the underlying pathology. Moreover, we present a classifier ensemble approach which combines the predictions of the individual classifiers to optimize the classification accuracy. We applied the proposed methodology to a dataset of x-ray galactograms, medical images which visualize the breast ductal tree, in order to recognize images with radiological findings regarding breast cancer. The experimental results demonstrate the effectiveness of the proposed framework compared to state-of-the-art techniques suggesting that the proposed descriptors provide more valuable information regarding the topological patterns of ductal trees and indicating the potential of facilitating early breast cancer diagnosis. PMID:25414850

Differences in multiple-target visual search performance between non-professional and professional searchers due to decision-making criteria.

PubMed

Biggs, Adam T; Mitroff, Stephen R

2015-11-01

Professional visual searches, such as those conducted by airport security personnel, often demand highly accurate performance. As many factors can hinder accuracy, it is critical to understand the potential influences. Here, we examined how explicit decision-making criteria might affect multiple-target search performance. Non-professional searchers (college undergraduates) and professional searchers (airport security officers) classified trials as 'safe' or 'dangerous', in one of two conditions. Those in the 'one = dangerous' condition classified trials as dangerous if they found one or two targets, and those in the 'one = safe' condition only classified trials as dangerous if they found two targets. The data suggest an important role of context that may be mediated by experience; non-professional searchers were more likely to miss a second target in the one = dangerous condition (i.e., when finding a second found target did not change the classification), whereas professional searchers were more likely to miss a second in the one = safe condition. © 2014 The British Psychological Society.

Functional Interaction Network Construction and Analysis for Disease Discovery.

PubMed

Wu, Guanming; Haw, Robin

2017-01-01

Network-based approaches project seemingly unrelated genes or proteins onto a large-scale network context, therefore providing a holistic visualization and analysis platform for genomic data generated from high-throughput experiments, reducing the dimensionality of data via using network modules and increasing the statistic analysis power. Based on the Reactome database, the most popular and comprehensive open-source biological pathway knowledgebase, we have developed a highly reliable protein functional interaction network covering around 60 % of total human genes and an app called ReactomeFIViz for Cytoscape, the most popular biological network visualization and analysis platform. In this chapter, we describe the detailed procedures on how this functional interaction network is constructed by integrating multiple external data sources, extracting functional interactions from human curated pathway databases, building a machine learning classifier called a Naïve Bayesian Classifier, predicting interactions based on the trained Naïve Bayesian Classifier, and finally constructing the functional interaction database. We also provide an example on how to use ReactomeFIViz for performing network-based data analysis for a list of genes.

Urine cell-based DNA methylation classifier for monitoring bladder cancer.

PubMed

van der Heijden, Antoine G; Mengual, Lourdes; Ingelmo-Torres, Mercedes; Lozano, Juan J; van Rijt-van de Westerlo, Cindy C M; Baixauli, Montserrat; Geavlete, Bogdan; Moldoveanud, Cristian; Ene, Cosmin; Dinney, Colin P; Czerniak, Bogdan; Schalken, Jack A; Kiemeney, Lambertus A L M; Ribal, Maria J; Witjes, J Alfred; Alcaraz, Antonio

2018-01-01

Current standard methods used to detect and monitor bladder cancer (BC) are invasive or have low sensitivity. This study aimed to develop a urine methylation biomarker classifier for BC monitoring and validate this classifier in patients in follow-up for bladder cancer (PFBC). Voided urine samples ( N  = 725) from BC patients, controls, and PFBC were prospectively collected in four centers. Finally, 626 urine samples were available for analysis. DNA was extracted from the urinary cells and bisulfite modificated, and methylation status was analyzed using pyrosequencing. Cytology was available from a subset of patients ( N  = 399). In the discovery phase, seven selected genes from the literature ( CDH13 , CFTR , NID2 , SALL3 , TMEFF2 , TWIST1 , and VIM2 ) were studied in 111 BC and 57 control samples. This training set was used to develop a gene classifier by logistic regression and was validated in 458 PFBC samples (173 with recurrence). A three-gene methylation classifier containing CFTR , SALL3 , and TWIST1 was developed in the training set (AUC 0.874). The classifier achieved an AUC of 0.741 in the validation series. Cytology results were available for 308 samples from the validation set. Cytology achieved AUC 0.696 whereas the classifier in this subset of patients reached an AUC 0.768. Combining the methylation classifier with cytology results achieved an AUC 0.86 in the validation set, with a sensitivity of 96%, a specificity of 40%, and a positive and negative predictive value of 56 and 92%, respectively. The combination of the three-gene methylation classifier and cytology results has high sensitivity and high negative predictive value in a real clinical scenario (PFBC). The proposed classifier is a useful test for predicting BC recurrence and decrease the number of cystoscopies in the follow-up of BC patients. If only patients with a positive combined classifier result would be cystoscopied, 36% of all cystoscopies can be prevented.

Quantifying the development of user-generated art during 2001–2010

PubMed Central

Yazdani, Mehrdad; Chow, Jay; Manovich, Lev

2017-01-01

One of the main questions in the humanities is how cultures and artistic expressions change over time. While a number of researchers have used quantitative computational methods to study historical changes in literature, music, and cinema, our paper offers the first quantitative analysis of historical changes in visual art created by users of a social online network. We propose a number of computational methods for the analysis of temporal development of art images. We then apply these methods to a sample of 270,000 artworks created between 2001 and 2010 by users of the largest social network for art—DeviantArt (www.deviantart.com). We investigate changes in subjects, techniques, sizes, proportions and also selected visual characteristics of images. Because these artworks are classified by their creators into two general categories—Traditional Art and Digital Art—we are also able to investigate if the use of digital tools has had a significant effect on the content and form of artworks. Our analysis reveals a number of gradual and systematic changes over a ten-year period in artworks belonging to both categories. PMID:28792494

Quantifying the development of user-generated art during 2001-2010.

PubMed

Yazdani, Mehrdad; Chow, Jay; Manovich, Lev

2017-01-01

One of the main questions in the humanities is how cultures and artistic expressions change over time. While a number of researchers have used quantitative computational methods to study historical changes in literature, music, and cinema, our paper offers the first quantitative analysis of historical changes in visual art created by users of a social online network. We propose a number of computational methods for the analysis of temporal development of art images. We then apply these methods to a sample of 270,000 artworks created between 2001 and 2010 by users of the largest social network for art-DeviantArt (www.deviantart.com). We investigate changes in subjects, techniques, sizes, proportions and also selected visual characteristics of images. Because these artworks are classified by their creators into two general categories-Traditional Art and Digital Art-we are also able to investigate if the use of digital tools has had a significant effect on the content and form of artworks. Our analysis reveals a number of gradual and systematic changes over a ten-year period in artworks belonging to both categories.

Evaluation of Skylab (EREP) data for forest and rangeland surveys. [Georgia, South Dakota, Colorado, and California

NASA Technical Reports Server (NTRS)

Aldrich, R. C. (Principal Investigator); Dana, R. W.; Greentree, W. J.; Roberts, E. H.; Norick, N. X.; Waite, T. H.; Francis, R. E.; Driscoll, R. S.; Weber, F. P.

1975-01-01

The author has identified the following significant results. Four widely separated sites (near Augusta, Georgia; Lead, South Dakota; Manitou, Colorado; and Redding, California) were selected as typical sites for forest inventory, forest stress, rangeland inventory, and atmospheric and solar measurements, respectively. Results indicated that Skylab S190B color photography is good for classification of Level 1 forest and nonforest land (90 to 95 percent correct) and could be used as a data base for sampling by small and medium scale photography using regression techniques. The accuracy of Level 2 forest and nonforest classes, however, varied from fair to poor. Results of plant community classification tests indicate that both visual and microdensitometric techniques can separate deciduous, conifirous, and grassland classes to the region level in the Ecoclass hierarchical classification system. There was no consistency in classifying tree categories at the series level by visual photointerpretation. The relationship between ground measurements and large scale photo measurements of foliar cover had a correlation coefficient of greater than 0.75. Some of the relationships, however, were site dependent.

Microarray gene expression profiling using core biopsies of renal neoplasia.

PubMed

Rogers, Craig G; Ditlev, Jonathon A; Tan, Min-Han; Sugimura, Jun; Qian, Chao-Nan; Cooper, Jeff; Lane, Brian; Jewett, Michael A; Kahnoski, Richard J; Kort, Eric J; Teh, Bin T

2009-01-01

We investigate the feasibility of using microarray gene expression profiling technology to analyze core biopsies of renal tumors for classification of tumor histology. Core biopsies were obtained ex-vivo from 7 renal tumors-comprised of four histological subtypes-following radical nephrectomy using 18-gauge biopsy needles. RNA was isolated from these samples and, in the case of biopsy samples, amplified by in vitro transcription. Microarray analysis was then used to quantify the mRNA expression patterns in these samples relative to non-diseased renal tissue mRNA. Genes with significant variation across all non-biopsy tumor samples were identified, and the relationship between tumor and biopsy samples in terms of expression levels of these genes was then quantified in terms of Euclidean distance, and visualized by complete linkage clustering. Final pathologic assessment of kidney tumors demonstrated clear cell renal cell carcinoma (4), oncocytoma (1), angiomyolipoma (1) and adrenalcortical carcinoma (1). Five of the seven biopsy samples were most similar in terms of gene expression to the resected tumors from which they were derived in terms of Euclidean distance. All seven biopsies were assigned to the correct histological class by hierarchical clustering. We demonstrate the feasibility of gene expression profiling of core biopsies of renal tumors to classify tumor histology.

Microarray gene expression profiling using core biopsies of renal neoplasia

PubMed Central

Rogers, Craig G.; Ditlev, Jonathon A.; Tan, Min-Han; Sugimura, Jun; Qian, Chao-Nan; Cooper, Jeff; Lane, Brian; Jewett, Michael A.; Kahnoski, Richard J.; Kort, Eric J.; Teh, Bin T.

2009-01-01

We investigate the feasibility of using microarray gene expression profiling technology to analyze core biopsies of renal tumors for classification of tumor histology. Core biopsies were obtained ex-vivo from 7 renal tumors—comprised of four histological subtypes—following radical nephrectomy using 18-gauge biopsy needles. RNA was isolated from these samples and, in the case of biopsy samples, amplified by in vitro transcription. Microarray analysis was then used to quantify the mRNA expression patterns in these samples relative to non-diseased renal tissue mRNA. Genes with significant variation across all non-biopsy tumor samples were identified, and the relationship between tumor and biopsy samples in terms of expression levels of these genes was then quantified in terms of Euclidean distance, and visualized by complete linkage clustering. Final pathologic assessment of kidney tumors demonstrated clear cell renal cell carcinoma (4), oncocytoma (1), angiomyolipoma (1) and adrenalcortical carcinoma (1). Five of the seven biopsy samples were most similar in terms of gene expression to the resected tumors from which they were derived in terms of Euclidean distance. All seven biopsies were assigned to the correct histological class by hierarchical clustering. We demonstrate the feasibility of gene expression profiling of core biopsies of renal tumors to classify tumor histology. PMID:19966938

Deep learning classification in asteroseismology using an improved neural network: results on 15 000 Kepler red giants and applications to K2 and TESS data

NASA Astrophysics Data System (ADS)

Hon, Marc; Stello, Dennis; Yu, Jie

2018-05-01

Deep learning in the form of 1D convolutional neural networks have previously been shown to be capable of efficiently classifying the evolutionary state of oscillating red giants into red giant branch stars and helium-core burning stars by recognizing visual features in their asteroseismic frequency spectra. We elaborate further on the deep learning method by developing an improved convolutional neural network classifier. To make our method useful for current and future space missions such as K2, TESS, and PLATO, we train classifiers that are able to classify the evolutionary states of lower frequency resolution spectra expected from these missions. Additionally, we provide new classifications for 8633 Kepler red giants, out of which 426 have previously not been classified using asteroseismology. This brings the total to 14983 Kepler red giants classified with our new neural network. We also verify that our classifiers are remarkably robust to suboptimal data, including low signal-to-noise and incorrect training truth labels.

Confidence Preserving Machine for Facial Action Unit Detection

PubMed Central

Zeng, Jiabei; Chu, Wen-Sheng; De la Torre, Fernando; Cohn, Jeffrey F.; Xiong, Zhang

2016-01-01

Facial action unit (AU) detection from video has been a long-standing problem in automated facial expression analysis. While progress has been made, accurate detection of facial AUs remains challenging due to ubiquitous sources of errors, such as inter-personal variability, pose, and low-intensity AUs. In this paper, we refer to samples causing such errors as hard samples, and the remaining as easy samples. To address learning with the hard samples, we propose the Confidence Preserving Machine (CPM), a novel two-stage learning framework that combines multiple classifiers following an “easy-to-hard” strategy. During the training stage, CPM learns two confident classifiers. Each classifier focuses on separating easy samples of one class from all else, and thus preserves confidence on predicting each class. During the testing stage, the confident classifiers provide “virtual labels” for easy test samples. Given the virtual labels, we propose a quasi-semi-supervised (QSS) learning strategy to learn a person-specific (PS) classifier. The QSS strategy employs a spatio-temporal smoothness that encourages similar predictions for samples within a spatio-temporal neighborhood. In addition, to further improve detection performance, we introduce two CPM extensions: iCPM that iteratively augments training samples to train the confident classifiers, and kCPM that kernelizes the original CPM model to promote nonlinearity. Experiments on four spontaneous datasets GFT [15], BP4D [56], DISFA [42], and RU-FACS [3] illustrate the benefits of the proposed CPM models over baseline methods and state-of-the-art semisupervised learning and transfer learning methods. PMID:27479964

Audio-visual imposture

NASA Astrophysics Data System (ADS)

Karam, Walid; Mokbel, Chafic; Greige, Hanna; Chollet, Gerard

2006-05-01

A GMM based audio visual speaker verification system is described and an Active Appearance Model with a linear speaker transformation system is used to evaluate the robustness of the verification. An Active Appearance Model (AAM) is used to automatically locate and track a speaker's face in a video recording. A Gaussian Mixture Model (GMM) based classifier (BECARS) is used for face verification. GMM training and testing is accomplished on DCT based extracted features of the detected faces. On the audio side, speech features are extracted and used for speaker verification with the GMM based classifier. Fusion of both audio and video modalities for audio visual speaker verification is compared with face verification and speaker verification systems. To improve the robustness of the multimodal biometric identity verification system, an audio visual imposture system is envisioned. It consists of an automatic voice transformation technique that an impostor may use to assume the identity of an authorized client. Features of the transformed voice are then combined with the corresponding appearance features and fed into the GMM based system BECARS for training. An attempt is made to increase the acceptance rate of the impostor and to analyzing the robustness of the verification system. Experiments are being conducted on the BANCA database, with a prospect of experimenting on the newly developed PDAtabase developed within the scope of the SecurePhone project.

Sensory and rapid instrumental methods as a combined tool for quality control of cooked ham.

PubMed

Barbieri, Sara; Soglia, Francesca; Palagano, Rosa; Tesini, Federica; Bendini, Alessandra; Petracci, Massimiliano; Cavani, Claudio; Gallina Toschi, Tullia

2016-11-01

In this preliminary investigation, different commercial categories of Italian cooked pork hams have been characterized using an integrated approach based on both sensory and fast instrumental measurements. For these purposes, Italian products belonging to different categories (cooked ham, "selected" cooked ham and "high quality" cooked ham) were evaluated by sensory descriptive analysis and by the application of rapid tools such as image analysis by an "electronic eye" and texture analyzer. The panel of trained assessors identified and evaluated 10 sensory descriptors able to define the quality of the products. Statistical analysis highlighted that sensory characteristics related to appearance and texture were the most significant in discriminating samples belonged to the highest (high quality cooked hams) and the lowest (cooked hams) quality of the product whereas the selected cooked hams, showed intermediate characteristics. In particular, high quality samples were characterized, above all, by the highest intensity of pink intensity, typical appearance and cohesiveness, and, at the same time, by the lowest intensity of juiciness; standard cooked ham samples showed the lowest intensity of all visual attributes and the highest value of juiciness, whereas the intermediate category (selected cooked ham) was not discriminated from the other. Also physical-rheological parameters measured by electronic eye and texture analyzer were effective in classifying samples. In particular, the PLS model built with data obtained from the electronic eye showed a satisfactory performance in terms of prediction of the pink intensity and presence of fat attributes evaluated during the sensory visual phase. This study can be considered a first application of this combined approach that could represent a suitable and fast method to verify if the meat product purchased by consumer match its description in terms of compliance with the claimed quality.

Development of visual peak selection system based on multi-ISs normalization algorithm to apply to methamphetamine impurity profiling.

PubMed

Lee, Hun Joo; Han, Eunyoung; Lee, Jaesin; Chung, Heesun; Min, Sung-Gi

2016-11-01

The aim of this study is to improve resolution of impurity peaks using a newly devised normalization algorithm for multi-internal standards (ISs) and to describe a visual peak selection system (VPSS) for efficient support of impurity profiling. Drug trafficking routes, location of manufacture, or synthetic route can be identified from impurities in seized drugs. In the analysis of impurities, different chromatogram profiles are obtained from gas chromatography and used to examine similarities between drug samples. The data processing method using relative retention time (RRT) calculated by a single internal standard is not preferred when many internal standards are used and many chromatographic peaks present because of the risk of overlapping between peaks and difficulty in classifying impurities. In this study, impurities in methamphetamine (MA) were extracted by liquid-liquid extraction (LLE) method using ethylacetate containing 4 internal standards and analyzed by gas chromatography-flame ionization detection (GC-FID). The newly developed VPSS consists of an input module, a conversion module, and a detection module. The input module imports chromatograms collected from GC and performs preprocessing, which is converted with a normalization algorithm in the conversion module, and finally the detection module detects the impurities in MA samples using a visualized zoning user interface. The normalization algorithm in the conversion module was used to convert the raw data from GC-FID. The VPSS with the built-in normalization algorithm can effectively detect different impurities in samples even in complex matrices and has high resolution keeping the time sequence of chromatographic peaks the same as that of the RRT method. The system can widen a full range of chromatograms so that the peaks of impurities were better aligned for easy separation and classification. The resolution, accuracy, and speed of impurity profiling showed remarkable improvement. Copyright © 2016 Elsevier Ireland Ltd. All rights reserved.

Night-shift work and risk of compromised visual acuity among the workers in an electronics manufacturing company.

PubMed

Lin, Yu-Cheng; Ho, Kuo-Jung

2018-01-01

To evaluate the association between night-shift work exposure and visual health, this cross-sectional study utilized visual acuity, a surrogate measure for visual function, as a parameter, and performed an analysis comparing visual acuity between daytime and nighttime employees in an electronics manufacturing company. Data of personal histories, occupational records, physical examinations and blood tests was obtained from the electronic health records of workers. The total of 8280 workers including 3098 women and 5182 men, wearing their own daily used eyeglasses, were included in the final analysis. The mean age of the sample population was 34.7 years old (standard deviation = 5.4 years). All workers were divided into 3 work categories - consistent daytime worker (CDW), day-shift worker (DSW) and night-shift worker (NSW). The check-up results of glasses-corrected visual acuity (c-VA) were utilized to classify individuals as good (≥ 1.2, both eyes) and inadequate (< 0.8, the better eye) c-VA. Consistent daytime workers had the highest rate of good c-VA (42.5% vs. 25.1% DSW and 21.1% NSW, p = 0.047). Night-shift workers had the highest rate of inadequate c-VA (CDW, DSW and NSW: 2.6%, 6.2%, and 7.6%, p = 0.03) among all employees. After controlling for covariates, NSW were found at an increased risk for inadequate c-VA (adjusted odds ratio (ORa) = 2.7, 95% confidence interval (CI): 2.0-3.6, vs. CDW), and less likely to have good c-VA (ORa = 0.4, 95% CI: 0.4-0.5, vs. CDW). Night-shift work is moderately associated with compromised visual acuity of employees in this electronics manufacturing company. Int J Occup Med Environ Health 2018;31(1):71-79. This work is available in Open Access model and licensed under a CC BY-NC 3.0 PL license.

Comparison of Pixel-Based and Object-Based Classification Using Parameters and Non-Parameters Approach for the Pattern Consistency of Multi Scale Landcover

NASA Astrophysics Data System (ADS)

Juniati, E.; Arrofiqoh, E. N.

2017-09-01

Information extraction from remote sensing data especially land cover can be obtained by digital classification. In practical some people are more comfortable using visual interpretation to retrieve land cover information. However, it is highly influenced by subjectivity and knowledge of interpreter, also takes time in the process. Digital classification can be done in several ways, depend on the defined mapping approach and assumptions on data distribution. The study compared several classifiers method for some data type at the same location. The data used Landsat 8 satellite imagery, SPOT 6 and Orthophotos. In practical, the data used to produce land cover map in 1:50,000 map scale for Landsat, 1:25,000 map scale for SPOT and 1:5,000 map scale for Orthophotos, but using visual interpretation to retrieve information. Maximum likelihood Classifiers (MLC) which use pixel-based and parameters approach applied to such data, and also Artificial Neural Network classifiers which use pixel-based and non-parameters approach applied too. Moreover, this study applied object-based classifiers to the data. The classification system implemented is land cover classification on Indonesia topographic map. The classification applied to data source, which is expected to recognize the pattern and to assess consistency of the land cover map produced by each data. Furthermore, the study analyse benefits and limitations the use of methods.

[Progressive visual agnosia].

PubMed

Sugimoto, Azusa; Futamura, Akinori; Kawamura, Mitsuru

2011-10-01

Progressive visual agnosia was discovered in the 20th century following the discovery of classical non-progressive visual agnosia. In contrast to the classical type, which is caused by cerebral vascular disease or traumatic injury, progressive visual agnosia is a symptom of neurological degeneration. The condition of progressive visual loss, including visual agnosia, and posterior cerebral atrophy was named posterior cortical atrophy (PCA) by Benson et al. (1988). Progressive visual agnosia is also observed in semantic dementia (SD) and other degenerative diseases, but there is a difference in the subtype of visual agnosia associated with these diseases. Lissauer (1890) classified visual agnosia into apperceptive and associative types, and it in most cases, PCA is associated with the apperceptive type. However, SD patients exhibit symptoms of associative visual agnosia before changing to those of semantic memory disorder. Insights into progressive visual agnosia have helped us understand the visual system and discover how we "perceive" the outer world neuronally, with regard to consciousness. Although PCA is a type of atypical dementia, its diagnosis is important to enable patients to live better lives with appropriate functional support.

[The relationship between eyeball structure and visual acuity in high myopia].

PubMed

Liu, Yi-Chang; Xia, Wen-Tao; Zhu, Guang-You; Zhou, Xing-Tao; Fan, Li-Hua; Liu, Rui-Jue; Chen, Jie-Min

2010-06-01

To explore the relationship between eyeball structure and visual acuity in high myopia. Totally, 152 people (283 eyeballs) with different levels of myopia were tested for visual acuity, axial length, and fundus. All cases were classified according to diopter, axial length, and fundus. The relationships between diopter, axial length, fundus and visual acuity were studied. The mathematical models were established for visual acuity and eyeball structure markers. The visual acuity showed a moderate correlation with fundus class, comus, axial length and diopter ([r] > 0.4, P < 0.000 1). The visual acuity in people with the axial length longer than 30.00 mm, diopter above -20.00 D and fundus in 4th class were mostly below 0.5. The mathematical models were established by visual acuity and eyeball structure markers. The visual acuity should decline with axial length extension, diopter deepening and pathological deterioration of fundus. To detect the structure changes by combining different kinds of objective methods can help to assess and to judge the vision in high myopia.

Non-proliferative diabetic retinopathy symptoms detection and classification using neural network.

PubMed

Al-Jarrah, Mohammad A; Shatnawi, Hadeel

2017-08-01

Diabetic retinopathy (DR) causes blindness in the working age for people with diabetes in most countries. The increasing number of people with diabetes worldwide suggests that DR will continue to be major contributors to vision loss. Early detection of retinopathy progress in individuals with diabetes is critical for preventing visual loss. Non-proliferative DR (NPDR) is an early stage of DR. Moreover, NPDR can be classified into mild, moderate and severe. This paper proposes a novel morphology-based algorithm for detecting retinal lesions and classifying each case. First, the proposed algorithm detects the three DR lesions, namely haemorrhages, microaneurysms and exudates. Second, we defined and extracted a set of features from detected lesions. The set of selected feature emulates what physicians looked for in classifying NPDR case. Finally, we designed an artificial neural network (ANN) classifier with three layers to classify NPDR to normal, mild, moderate and severe. Bayesian regularisation and resilient backpropagation algorithms are used to train ANN. The accuracy for the proposed classifiers based on Bayesian regularisation and resilient backpropagation algorithms are 96.6 and 89.9, respectively. The obtained results are compared with results of the recent published classifier. Our proposed classifier outperforms the best in terms of sensitivity and specificity.

Centre-based restricted nearest feature plane with angle classifier for face recognition

NASA Astrophysics Data System (ADS)

Tang, Linlin; Lu, Huifen; Zhao, Liang; Li, Zuohua

2017-10-01

An improved classifier based on the nearest feature plane (NFP), called the centre-based restricted nearest feature plane with the angle (RNFPA) classifier, is proposed for the face recognition problems here. The famous NFP uses the geometrical information of samples to increase the number of training samples, but it increases the computation complexity and it also has an inaccuracy problem coursed by the extended feature plane. To solve the above problems, RNFPA exploits a centre-based feature plane and utilizes a threshold of angle to restrict extended feature space. By choosing the appropriate angle threshold, RNFPA can improve the performance and decrease computation complexity. Experiments in the AT&T face database, AR face database and FERET face database are used to evaluate the proposed classifier. Compared with the original NFP classifier, the nearest feature line (NFL) classifier, the nearest neighbour (NN) classifier and some other improved NFP classifiers, the proposed one achieves competitive performance.

Acoustic Seafloor Classification near the Duanqiao hydrothermal field at the Southwest Indian Ridge from Multibeam Backscatter Data

NASA Astrophysics Data System (ADS)

Wang, A.; Tao, C.; Xu, Y.; Zhang, G.; Liao, S.

2016-12-01

The inactive Duanqiao hydrothermal field is located on the 50.5°E SWIR axial high with a shallow depth of about 1700 meters. Seafloor morphology of the area surrounding the field is relatively flat, which exerts less influence on multibeam backscatter data than rugged terrains do. Therefore, it is an ideal experimental area to conduct seafloor classification utilizing multibeam sonar. This paper dealt with a backscatter analysis of Simrad EM120 multibeam sonar data, acquired during the Chinese DY115-34 cruise near the Duanqiao hydrothermal field, and comprehensively studied types and distribution characteristics of seafloor substrate by combining with visual interpretations and TV-Grab Samples. Firstly, a mosaic was built to analyze backscatter distribution after multibeam backscatter data were fully processed using Geocoder engine on CARIS HIPS&SIPS software. Prior information was gained by analyzing the link between the processed backscatter data and the visual interpretations of two deep-tow video survey lines. Among the two survey lines, one corresponds to sediment-dominated seafloor and the other corresponds to pillow basalt-dominated seafloor. Then, backscatter data of the mosaic were classified statistically to identify three types of seafloor: soft substrate, medium-hard substrate and hard substrate. Compared with visual interpretations and TV-Grab Samples, these three seafloor types were interpreted as sediment, breccia and pillow basalt, respectively. Finally, a seafloor classification map was generated. According to the results, we discovered two distinguished distribution characteristics of seafloor substrate: 1. there is a transition from pillow basalt-dominated seafloor to sediment-dominated seafloor away from the SWIR axis; 2. the Duanqiao hydrothermal field is mostly outcropped by pillow basalts and locally covered by breccias and sediments, the reason of which is probably that this field is a relatively recent volcanic area.

Fluorescent polymer sensor array for detection and discrimination of explosives in water.

PubMed

Woodka, Marc D; Schnee, Vincent P; Polcha, Michael P

2010-12-01

A fluorescent polymer sensor array (FPSA) was made from commercially available fluorescent polymers coated onto glass beads and was tested to assess the ability of the array to discriminate between different analytes in aqueous solution. The array was challenged with exposures to 17 different analytes, including the explosives trinitrotoluene (TNT), tetryl, and RDX, various explosive-related compounds (ERCs), and nonexplosive electron-withdrawing compounds (EWCs). The array exhibited a natural selectivity toward EWCs, while the non-electron-withdrawing explosive 1,3,5-trinitroperhydro-1,3,5-triazine (RDX) produced no response. Response signatures were visualized by principal component analysis (PCA), and classified by linear discriminant analysis (LDA). RDX produced the same response signature as the sampled blanks and was classified accordingly. The array exhibited excellent discrimination toward all other compounds, with the exception of the isomers of nitrotoluene and aminodinitrotoluene. Of particular note was the ability of the array to discriminate between the three isomers of dinitrobenzene. The natural selectivity of the FPSA toward EWCs, plus the ability of the FPSA to discriminate between different EWCs, could be used to design a sensor with a low false alarm rate and an excellent ability to discriminate between explosives and explosive-related compounds.

The use of UV-visible reflectance spectroscopy as an objective tool to evaluate pearl quality.

PubMed

Agatonovic-Kustrin, Snezana; Morton, David W

2012-07-01

Assessing the quality of pearls involves the use of various tools and methods, which are mainly visual and often quite subjective. Pearls are normally classified by origin and are then graded by luster, nacre thickness, surface quality, size, color and shape. The aim of this study was to investigate the capacity of Artificial Neural Networks (ANNs) to classify and estimate the quality of 27 different pearls from their UV-Visible spectra. Due to the opaque nature of pearls, spectroscopy measurements were performed using the Diffuse Reflectance UV-Visible spectroscopy technique. The spectra were acquired at two different locations on each pearl sample in order to assess surface homogeneity. The spectral data (inputs) were smoothed to reduce the noise, fed into ANNs and correlated to the pearl's quality/grading criteria (outputs). The developed ANNs were successful in predicting pearl type, mollusk growing species, possible luster and color enhancing, donor condition/type, recipient/host color, donor color, pearl luster, pearl color, origin. The results of this study shows that the developed UV-Vis spectroscopy-ANN method could be used as a more objective method of assessing pearl quality (grading) and may become a valuable tool for the pearl grading industry.

Neural network based visualization of collaborations in a citizen science project

NASA Astrophysics Data System (ADS)

Morais, Alessandra M. M.; Santos, Rafael D. C.; Raddick, M. Jordan

2014-05-01

Citizen science projects are those in which volunteers are asked to collaborate in scientific projects, usually by volunteering idle computer time for distributed data processing efforts or by actively labeling or classifying information - shapes of galaxies, whale sounds, historical records are all examples of citizen science projects in which users access a data collecting system to label or classify images and sounds. In order to be successful, a citizen science project must captivate users and keep them interested on the project and on the science behind it, increasing therefore the time the users spend collaborating with the project. Understanding behavior of citizen scientists and their interaction with the data collection systems may help increase the involvement of the users, categorize them accordingly to different parameters, facilitate their collaboration with the systems, design better user interfaces, and allow better planning and deployment of similar projects and systems. Users behavior can be actively monitored or derived from their interaction with the data collection systems. Records of the interactions can be analyzed using visualization techniques to identify patterns and outliers. In this paper we present some results on the visualization of more than 80 million interactions of almost 150 thousand users with the Galaxy Zoo I citizen science project. Visualization of the attributes extracted from their behaviors was done with a clustering neural network (the Self-Organizing Map) and a selection of icon- and pixel-based techniques. These techniques allows the visual identification of groups of similar behavior in several different ways.

Decoding conjunctions of direction-of-motion and binocular disparity from human visual cortex.

PubMed

Seymour, Kiley J; Clifford, Colin W G

2012-05-01

Motion and binocular disparity are two features in our environment that share a common correspondence problem. Decades of psychophysical research dedicated to understanding stereopsis suggest that these features interact early in human visual processing to disambiguate depth. Single-unit recordings in the monkey also provide evidence for the joint encoding of motion and disparity across much of the dorsal visual stream. Here, we used functional MRI and multivariate pattern analysis to examine where in the human brain conjunctions of motion and disparity are encoded. Subjects sequentially viewed two stimuli that could be distinguished only by their conjunctions of motion and disparity. Specifically, each stimulus contained the same feature information (leftward and rightward motion and crossed and uncrossed disparity) but differed exclusively in the way these features were paired. Our results revealed that a linear classifier could accurately decode which stimulus a subject was viewing based on voxel activation patterns throughout the dorsal visual areas and as early as V2. This decoding success was conditional on some voxels being individually sensitive to the unique conjunctions comprising each stimulus, thus a classifier could not rely on independent information about motion and binocular disparity to distinguish these conjunctions. This study expands on evidence that disparity and motion interact at many levels of human visual processing, particularly within the dorsal stream. It also lends support to the idea that stereopsis is subserved by early mechanisms also tuned to direction of motion.

Effect of separate sampling on classification accuracy.

PubMed

Shahrokh Esfahani, Mohammad; Dougherty, Edward R

2014-01-15

Measurements are commonly taken from two phenotypes to build a classifier, where the number of data points from each class is predetermined, not random. In this 'separate sampling' scenario, the data cannot be used to estimate the class prior probabilities. Moreover, predetermined class sizes can severely degrade classifier performance, even for large samples. We employ simulations using both synthetic and real data to show the detrimental effect of separate sampling on a variety of classification rules. We establish propositions related to the effect on the expected classifier error owing to a sampling ratio different from the population class ratio. From these we derive a sample-based minimax sampling ratio and provide an algorithm for approximating it from the data. We also extend to arbitrary distributions the classical population-based Anderson linear discriminant analysis minimax sampling ratio derived from the discriminant form of the Bayes classifier. All the codes for synthetic data and real data examples are written in MATLAB. A function called mmratio, whose output is an approximation of the minimax sampling ratio of a given dataset, is also written in MATLAB. All the codes are available at: http://gsp.tamu.edu/Publications/supplementary/shahrokh13b.

Recognition Using Hybrid Classifiers.

PubMed

Osadchy, Margarita; Keren, Daniel; Raviv, Dolev

2016-04-01

A canonical problem in computer vision is category recognition (e.g., find all instances of human faces, cars etc., in an image). Typically, the input for training a binary classifier is a relatively small sample of positive examples, and a huge sample of negative examples, which can be very diverse, consisting of images from a large number of categories. The difficulty of the problem sharply increases with the dimension and size of the negative example set. We propose to alleviate this problem by applying a "hybrid" classifier, which replaces the negative samples by a prior, and then finds a hyperplane which separates the positive samples from this prior. The method is extended to kernel space and to an ensemble-based approach. The resulting binary classifiers achieve an identical or better classification rate than SVM, while requiring far smaller memory and lower computational complexity to train and apply.

A two-dimensional matrix image based feature extraction method for classification of sEMG: A comparative analysis based on SVM, KNN and RBF-NN.

PubMed

Wen, Tingxi; Zhang, Zhongnan; Qiu, Ming; Zeng, Ming; Luo, Weizhen

2017-01-01

The computer mouse is an important human-computer interaction device. But patients with physical finger disability are unable to operate this device. Surface EMG (sEMG) can be monitored by electrodes on the skin surface and is a reflection of the neuromuscular activities. Therefore, we can control limbs auxiliary equipment by utilizing sEMG classification in order to help the physically disabled patients to operate the mouse. To develop a new a method to extract sEMG generated by finger motion and apply novel features to classify sEMG. A window-based data acquisition method was presented to extract signal samples from sEMG electordes. Afterwards, a two-dimensional matrix image based feature extraction method, which differs from the classical methods based on time domain or frequency domain, was employed to transform signal samples to feature maps used for classification. In the experiments, sEMG data samples produced by the index and middle fingers at the click of a mouse button were separately acquired. Then, characteristics of the samples were analyzed to generate a feature map for each sample. Finally, the machine learning classification algorithms (SVM, KNN, RBF-NN) were employed to classify these feature maps on a GPU. The study demonstrated that all classifiers can identify and classify sEMG samples effectively. In particular, the accuracy of the SVM classifier reached up to 100%. The signal separation method is a convenient, efficient and quick method, which can effectively extract the sEMG samples produced by fingers. In addition, unlike the classical methods, the new method enables to extract features by enlarging sample signals' energy appropriately. The classical machine learning classifiers all performed well by using these features.

Distributed Neural Processing Predictors of Multi-dimensional Properties of Affect

PubMed Central

Bush, Keith A.; Inman, Cory S.; Hamann, Stephan; Kilts, Clinton D.; James, G. Andrew

2017-01-01

Recent evidence suggests that emotions have a distributed neural representation, which has significant implications for our understanding of the mechanisms underlying emotion regulation and dysregulation as well as the potential targets available for neuromodulation-based emotion therapeutics. This work adds to this evidence by testing the distribution of neural representations underlying the affective dimensions of valence and arousal using representational models that vary in both the degree and the nature of their distribution. We used multi-voxel pattern classification (MVPC) to identify whole-brain patterns of functional magnetic resonance imaging (fMRI)-derived neural activations that reliably predicted dimensional properties of affect (valence and arousal) for visual stimuli viewed by a normative sample (n = 32) of demographically diverse, healthy adults. Inter-subject leave-one-out cross-validation showed whole-brain MVPC significantly predicted (p < 0.001) binarized normative ratings of valence (positive vs. negative, 59% accuracy) and arousal (high vs. low, 56% accuracy). We also conducted group-level univariate general linear modeling (GLM) analyses to identify brain regions whose response significantly differed for the contrasts of positive versus negative valence or high versus low arousal. Multivoxel pattern classifiers using voxels drawn from all identified regions of interest (all-ROIs) exhibited mixed performance; arousal was predicted significantly better than chance but worse than the whole-brain classifier, whereas valence was not predicted significantly better than chance. Multivoxel classifiers derived using individual ROIs generally performed no better than chance. Although performance of the all-ROI classifier improved with larger ROIs (generated by relaxing the clustering threshold), performance was still poorer than the whole-brain classifier. These findings support a highly distributed model of neural processing for the affective dimensions of valence and arousal. Finally, joint error analyses of the MVPC hyperplanes encoding valence and arousal identified regions within the dimensional affect space where multivoxel classifiers exhibited the greatest difficulty encoding brain states – specifically, stimuli of moderate arousal and high or low valence. In conclusion, we highlight new directions for characterizing affective processing for mechanistic and therapeutic applications in affective neuroscience. PMID:28959198

Support Vector Machine and Artificial Neural Network Models for the Classification of Grapevine Varieties Using a Portable NIR Spectrophotometer.

PubMed

Gutiérrez, Salvador; Tardaguila, Javier; Fernández-Novales, Juan; Diago, María P

2015-01-01

The identification of different grapevine varieties, currently attended using visual ampelometry, DNA analysis and very recently, by hyperspectral analysis under laboratory conditions, is an issue of great importance in the wine industry. This work presents support vector machine and artificial neural network's modelling for grapevine varietal classification from in-field leaf spectroscopy. Modelling was attempted at two scales: site-specific and a global scale. Spectral measurements were obtained on the near-infrared (NIR) spectral range between 1600 to 2400 nm under field conditions in a non-destructive way using a portable spectrophotometer. For the site specific approach, spectra were collected from the adaxial side of 400 individual leaves of 20 grapevine (Vitis vinifera L.) varieties one week after veraison. For the global model, two additional sets of spectra were collected one week before harvest from two different vineyards in another vintage, each one consisting on 48 measurement from individual leaves of six varieties. Several combinations of spectra scatter correction and smoothing filtering were studied. For the training of the models, support vector machines and artificial neural networks were employed using the pre-processed spectra as input and the varieties as the classes of the models. The results from the pre-processing study showed that there was no influence whether using scatter correction or not. Also, a second-degree derivative with a window size of 5 Savitzky-Golay filtering yielded the highest outcomes. For the site-specific model, with 20 classes, the best results from the classifiers thrown an overall score of 87.25% of correctly classified samples. These results were compared under the same conditions with a model trained using partial least squares discriminant analysis, which showed a worse performance in every case. For the global model, a 6-class dataset involving samples from three different vineyards, two years and leaves monitored at post-veraison and harvest was also built up, reaching a 77.08% of correctly classified samples. The outcomes obtained demonstrate the capability of using a reliable method for fast, in-field, non-destructive grapevine varietal classification that could be very useful in viticulture and wine industry, either global or site-specific.

Machine learning and dyslexia: Classification of individual structural neuro-imaging scans of students with and without dyslexia.

PubMed

Tamboer, P; Vorst, H C M; Ghebreab, S; Scholte, H S

2016-01-01

Meta-analytic studies suggest that dyslexia is characterized by subtle and spatially distributed variations in brain anatomy, although many variations failed to be significant after corrections of multiple comparisons. To circumvent issues of significance which are characteristic for conventional analysis techniques, and to provide predictive value, we applied a machine learning technique--support vector machine--to differentiate between subjects with and without dyslexia. In a sample of 22 students with dyslexia (20 women) and 27 students without dyslexia (25 women) (18-21 years), a classification performance of 80% (p < 0.001; d-prime = 1.67) was achieved on the basis of differences in gray matter (sensitivity 82%, specificity 78%). The voxels that were most reliable for classification were found in the left occipital fusiform gyrus (LOFG), in the right occipital fusiform gyrus (ROFG), and in the left inferior parietal lobule (LIPL). Additionally, we found that classification certainty (e.g. the percentage of times a subject was correctly classified) correlated with severity of dyslexia (r = 0.47). Furthermore, various significant correlations were found between the three anatomical regions and behavioural measures of spelling, phonology and whole-word-reading. No correlations were found with behavioural measures of short-term memory and visual/attentional confusion. These data indicate that the LOFG, ROFG and the LIPL are neuro-endophenotype and potentially biomarkers for types of dyslexia related to reading, spelling and phonology. In a second and independent sample of 876 young adults of a general population, the trained classifier of the first sample was tested, resulting in a classification performance of 59% (p = 0.07; d-prime = 0.65). This decline in classification performance resulted from a large percentage of false alarms. This study provided support for the use of machine learning in anatomical brain imaging.

Transferring genomics to the clinic: distinguishing Burkitt and diffuse large B cell lymphomas.

PubMed

Sha, Chulin; Barrans, Sharon; Care, Matthew A; Cunningham, David; Tooze, Reuben M; Jack, Andrew; Westhead, David R

2015-01-01

Classifiers based on molecular criteria such as gene expression signatures have been developed to distinguish Burkitt lymphoma and diffuse large B cell lymphoma, which help to explore the intermediate cases where traditional diagnosis is difficult. Transfer of these research classifiers into a clinical setting is challenging because there are competing classifiers in the literature based on different methodology and gene sets with no clear best choice; classifiers based on one expression measurement platform may not transfer effectively to another; and, classifiers developed using fresh frozen samples may not work effectively with the commonly used and more convenient formalin fixed paraffin-embedded samples used in routine diagnosis. Here we thoroughly compared two published high profile classifiers developed on data from different Affymetrix array platforms and fresh-frozen tissue, examining their transferability and concordance. Based on this analysis, a new Burkitt and diffuse large B cell lymphoma classifier (BDC) was developed and employed on Illumina DASL data from our own paraffin-embedded samples, allowing comparison with the diagnosis made in a central haematopathology laboratory and evaluation of clinical relevance. We show that both previous classifiers can be recapitulated using very much smaller gene sets than originally employed, and that the classification result is closely dependent on the Burkitt lymphoma criteria applied in the training set. The BDC classification on our data exhibits high agreement (~95 %) with the original diagnosis. A simple outcome comparison in the patients presenting intermediate features on conventional criteria suggests that the cases classified as Burkitt lymphoma by BDC have worse response to standard diffuse large B cell lymphoma treatment than those classified as diffuse large B cell lymphoma. In this study, we comprehensively investigate two previous Burkitt lymphoma molecular classifiers, and implement a new gene expression classifier, BDC, that works effectively on paraffin-embedded samples and provides useful information for treatment decisions. The classifier is available as a free software package under the GNU public licence within the R statistical software environment through the link http://www.bioinformatics.leeds.ac.uk/labpages/softwares/ or on github https://github.com/Sharlene/BDC.

CoBOP: Electro-Optic Identification Laser Line Sean Sensors

DTIC Science & Technology

1998-01-01

Electro - Optic Identification Sensors Project[1] is to develop and demonstrate high resolution underwater electro - optic (EO) imaging sensors, and associated image processing/analysis methods, for rapid visual identification of mines and mine-like contacts (MLCs). Identification of MLCs is a pressing Fleet need. During MCM operations, sonar contacts are classified as mine-like if they are sufficiently similar to signatures of mines. Each contact classified as mine-like must be identified as a mine or not a mine. During MCM operations in littoral areas,

Development of a Low-Cost, Noninvasive, Portable Visual Speech Recognition Program.

PubMed

Kohlberg, Gavriel D; Gal, Ya'akov Kobi; Lalwani, Anil K

2016-09-01

Loss of speech following tracheostomy and laryngectomy severely limits communication to simple gestures and facial expressions that are largely ineffective. To facilitate communication in these patients, we seek to develop a low-cost, noninvasive, portable, and simple visual speech recognition program (VSRP) to convert articulatory facial movements into speech. A Microsoft Kinect-based VSRP was developed to capture spatial coordinates of lip movements and translate them into speech. The articulatory speech movements associated with 12 sentences were used to train an artificial neural network classifier. The accuracy of the classifier was then evaluated on a separate, previously unseen set of articulatory speech movements. The VSRP was successfully implemented and tested in 5 subjects. It achieved an accuracy rate of 77.2% (65.0%-87.6% for the 5 speakers) on a 12-sentence data set. The mean time to classify an individual sentence was 2.03 milliseconds (1.91-2.16). We have demonstrated the feasibility of a low-cost, noninvasive, portable VSRP based on Kinect to accurately predict speech from articulation movements in clinically trivial time. This VSRP could be used as a novel communication device for aphonic patients. © The Author(s) 2016.

Visual saliency detection based on in-depth analysis of sparse representation

NASA Astrophysics Data System (ADS)

Wang, Xin; Shen, Siqiu; Ning, Chen

2018-03-01

Visual saliency detection has been receiving great attention in recent years since it can facilitate a wide range of applications in computer vision. A variety of saliency models have been proposed based on different assumptions within which saliency detection via sparse representation is one of the newly arisen approaches. However, most existing sparse representation-based saliency detection methods utilize partial characteristics of sparse representation, lacking of in-depth analysis. Thus, they may have limited detection performance. Motivated by this, this paper proposes an algorithm for detecting visual saliency based on in-depth analysis of sparse representation. A number of discriminative dictionaries are first learned with randomly sampled image patches by means of inner product-based dictionary atom classification. Then, the input image is partitioned into many image patches, and these patches are classified into salient and nonsalient ones based on the in-depth analysis of sparse coding coefficients. Afterward, sparse reconstruction errors are calculated for the salient and nonsalient patch sets. By investigating the sparse reconstruction errors, the most salient atoms, which tend to be from the most salient region, are screened out and taken away from the discriminative dictionaries. Finally, an effective method is exploited for saliency map generation with the reduced dictionaries. Comprehensive evaluations on publicly available datasets and comparisons with some state-of-the-art approaches demonstrate the effectiveness of the proposed algorithm.

Visual field progression in glaucoma: total versus pattern deviation analyses.

PubMed

Artes, Paul H; Nicolela, Marcelo T; LeBlanc, Raymond P; Chauhan, Balwantray C

2005-12-01

To compare visual field progression with total and pattern deviation analyses in a prospective longitudinal study of patients with glaucoma and healthy control subjects. A group of 101 patients with glaucoma (168 eyes) with early to moderately advanced visual field loss at baseline (average mean deviation [MD], -3.9 dB) and no clinical evidence of media opacity were selected from a prospective longitudinal study on visual field progression in glaucoma. Patients were examined with static automated perimetry at 6-month intervals for a median follow-up of 9 years. At each test location, change was established with event and trend analyses of total and pattern deviation. The event analyses compared each follow-up test to a baseline obtained from averaging the first two tests, and visual field progression was defined as deterioration beyond the 5th percentile of test-retest variability at three test locations, observed on three consecutive tests. The trend analyses were based on point-wise linear regression, and visual field progression was defined as statistically significant deterioration (P < 5%) worse than -1 dB/year at three locations, confirmed by independently omitting the last and the penultimate observation. The incidence and the time-to-progression were compared between total and pattern deviation analyses. To estimate the specificity of the progression analyses, identical criteria were applied to visual fields obtained in 102 healthy control subjects, and the rate of visual field improvement was established in the patients with glaucoma and the healthy control subjects. With both event and trend methods, pattern deviation analyses classified approximately 15% fewer eyes as having progressed than did the total deviation analyses. In eyes classified as progressing by both the total and pattern deviation methods, total deviation analyses tended to detect progression earlier than the pattern deviation analyses. A comparison of the changes observed in MD and the visual fields' general height (estimated by the 85th percentile of the total deviation values) confirmed that change in the glaucomatous eyes almost always comprised a diffuse component. Pattern deviation analyses of progression may therefore underestimate the true amount of glaucomatous visual field progression. Pattern deviation analyses of visual field progression may underestimate visual field progression in glaucoma, particularly when there is no clinical evidence of increasing media opacity. Clinicians should have access to both total and pattern deviation analyses to make informed decisions on visual field progression in glaucoma.

Audio-visual interactions in environment assessment.

PubMed

Preis, Anna; Kociński, Jędrzej; Hafke-Dys, Honorata; Wrzosek, Małgorzata

2015-08-01

The aim of the study was to examine how visual and audio information influences audio-visual environment assessment. Original audio-visual recordings were made at seven different places in the city of Poznań. Participants of the psychophysical experiments were asked to rate, on a numerical standardized scale, the degree of comfort they would feel if they were in such an environment. The assessments of audio-visual comfort were carried out in a laboratory in four different conditions: (a) audio samples only, (b) original audio-visual samples, (c) video samples only, and (d) mixed audio-visual samples. The general results of this experiment showed a significant difference between the investigated conditions, but not for all the investigated samples. There was a significant improvement in comfort assessment when visual information was added (in only three out of 7 cases), when conditions (a) and (b) were compared. On the other hand, the results show that the comfort assessment of audio-visual samples could be changed by manipulating the audio rather than the video part of the audio-visual sample. Finally, it seems, that people could differentiate audio-visual representations of a given place in the environment based rather of on the sound sources' compositions than on the sound level. Object identification is responsible for both landscape and soundscape grouping. Copyright © 2015. Published by Elsevier B.V.

Local classifier weighting by quadratic programming.

PubMed

Cevikalp, Hakan; Polikar, Robi

2008-10-01

It has been widely accepted that the classification accuracy can be improved by combining outputs of multiple classifiers. However, how to combine multiple classifiers with various (potentially conflicting) decisions is still an open problem. A rich collection of classifier combination procedures -- many of which are heuristic in nature -- have been developed for this goal. In this brief, we describe a dynamic approach to combine classifiers that have expertise in different regions of the input space. To this end, we use local classifier accuracy estimates to weight classifier outputs. Specifically, we estimate local recognition accuracies of classifiers near a query sample by utilizing its nearest neighbors, and then use these estimates to find the best weights of classifiers to label the query. The problem is formulated as a convex quadratic optimization problem, which returns optimal nonnegative classifier weights with respect to the chosen objective function, and the weights ensure that locally most accurate classifiers are weighted more heavily for labeling the query sample. Experimental results on several data sets indicate that the proposed weighting scheme outperforms other popular classifier combination schemes, particularly on problems with complex decision boundaries. Hence, the results indicate that local classification-accuracy-based combination techniques are well suited for decision making when the classifiers are trained by focusing on different regions of the input space.

An exploratory study of a text classification framework for Internet-based surveillance of emerging epidemics

PubMed Central

Torii, Manabu; Yin, Lanlan; Nguyen, Thang; Mazumdar, Chand T.; Liu, Hongfang; Hartley, David M.; Nelson, Noele P.

2014-01-01

Purpose Early detection of infectious disease outbreaks is crucial to protecting the public health of a society. Online news articles provide timely information on disease outbreaks worldwide. In this study, we investigated automated detection of articles relevant to disease outbreaks using machine learning classifiers. In a real-life setting, it is expensive to prepare a training data set for classifiers, which usually consists of manually labeled relevant and irrelevant articles. To mitigate this challenge, we examined the use of randomly sampled unlabeled articles as well as labeled relevant articles. Methods Naïve Bayes and Support Vector Machine (SVM) classifiers were trained on 149 relevant and 149 or more randomly sampled unlabeled articles. Diverse classifiers were trained by varying the number of sampled unlabeled articles and also the number of word features. The trained classifiers were applied to 15 thousand articles published over 15 days. Top-ranked articles from each classifier were pooled and the resulting set of 1337 articles was reviewed by an expert analyst to evaluate the classifiers. Results Daily averages of areas under ROC curves (AUCs) over the 15-day evaluation period were 0.841 and 0.836, respectively, for the naïve Bayes and SVM classifier. We referenced a database of disease outbreak reports to confirm that this evaluation data set resulted from the pooling method indeed covered incidents recorded in the database during the evaluation period. Conclusions The proposed text classification framework utilizing randomly sampled unlabeled articles can facilitate a cost-effective approach to training machine learning classifiers in a real-life Internet-based biosurveillance project. We plan to examine this framework further using larger data sets and using articles in non-English languages. PMID:21134784

Interpreting Black-Box Classifiers Using Instance-Level Visual Explanations

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

Tamagnini, Paolo; Krause, Josua W.; Dasgupta, Aritra

2017-05-14

To realize the full potential of machine learning in diverse real- world domains, it is necessary for model predictions to be readily interpretable and actionable for the human in the loop. Analysts, who are the users but not the developers of machine learning models, often do not trust a model because of the lack of transparency in associating predictions with the underlying data space. To address this problem, we propose Rivelo, a visual analytic interface that enables analysts to understand the causes behind predictions of binary classifiers by interactively exploring a set of instance-level explanations. These explanations are model-agnostic, treatingmore » a model as a black box, and they help analysts in interactively probing the high-dimensional binary data space for detecting features relevant to predictions. We demonstrate the utility of the interface with a case study analyzing a random forest model on the sentiment of Yelp reviews about doctors.« less

Use of Unlabeled Samples for Mitigating the Hughes Phenomenon

NASA Technical Reports Server (NTRS)

Landgrebe, David A.; Shahshahani, Behzad M.

1993-01-01

The use of unlabeled samples in improving the performance of classifiers is studied. When the number of training samples is fixed and small, additional feature measurements may reduce the performance of a statistical classifier. It is shown that by using unlabeled samples, estimates of the parameters can be improved and therefore this phenomenon may be mitigated. Various methods for using unlabeled samples are reviewed and experimental results are provided.

The Influence of Restricted Visual Feedback on Dribbling Performance in Youth Soccer Players.

PubMed

Fransen, Job; Lovell, Thomas W J; Bennett, Kyle J M; Deprez, Dieter; Deconinck, Frederik J A; Lenoir, Matthieu; Coutts, Aaron J

2017-04-01

The aim of the current study was to examine the influence of restricted visual feedback using stroboscopic eyewear on the dribbling performance of youth soccer players. Three dribble test conditions were used in a within-subjects design to measure the effect of restricted visual feedback on soccer dribbling performance in 189 youth soccer players (age: 10-18 y) classified as fast, average or slow dribblers. The results showed that limiting visual feedback increased dribble test times across all abilities. Furthermore, the largest performance decrement between stroboscopic and full vision conditions was in fast dribblers, showing that fast dribblers were most affected by reduced visual information. This may be due to a greater dependency on visual feedback at increased speeds, which may limit the ability to maintain continuous control of the ball. These findings may have important implications for the development of soccer dribbling ability.

Personality dimensions of people who suffer from visual stress.

PubMed

Hollis, J; Allen, P M; Fleischmann, D; Aulak, R

2007-11-01

Personality dimensions of participants who suffer from visual stress were compared with those of normal participants using the Eysenck Personality Inventory. Extraversion-Introversion scores showed no significant differences between the participants who suffered visual stress and those who were classified as normal. By contrast, significant differences were found between the normal participants and those with visual stress in respect of Neuroticism-Stability. These differences accord with Eysenck's personality theory which states that those who score highly on the neuroticism scale do so because they have a neurological system with a low threshold such that their neurological system is easily activated by external stimuli. The findings also relate directly to the theory of visual stress proposed by Wilkins which postulates that visual stress results from an excess of neural activity. The data may indicate that the excess activity is likely to be localised at particular neurological regions or neural processes.

Self-organizing neural integration of pose-motion features for human action recognition

PubMed Central

Parisi, German I.; Weber, Cornelius; Wermter, Stefan

2015-01-01

The visual recognition of complex, articulated human movements is fundamental for a wide range of artificial systems oriented toward human-robot communication, action classification, and action-driven perception. These challenging tasks may generally involve the processing of a huge amount of visual information and learning-based mechanisms for generalizing a set of training actions and classifying new samples. To operate in natural environments, a crucial property is the efficient and robust recognition of actions, also under noisy conditions caused by, for instance, systematic sensor errors and temporarily occluded persons. Studies of the mammalian visual system and its outperforming ability to process biological motion information suggest separate neural pathways for the distinct processing of pose and motion features at multiple levels and the subsequent integration of these visual cues for action perception. We present a neurobiologically-motivated approach to achieve noise-tolerant action recognition in real time. Our model consists of self-organizing Growing When Required (GWR) networks that obtain progressively generalized representations of sensory inputs and learn inherent spatio-temporal dependencies. During the training, the GWR networks dynamically change their topological structure to better match the input space. We first extract pose and motion features from video sequences and then cluster actions in terms of prototypical pose-motion trajectories. Multi-cue trajectories from matching action frames are subsequently combined to provide action dynamics in the joint feature space. Reported experiments show that our approach outperforms previous results on a dataset of full-body actions captured with a depth sensor, and ranks among the best results for a public benchmark of domestic daily actions. PMID:26106323

Predicting Vision-Related Disability in Glaucoma.

PubMed

Abe, Ricardo Y; Diniz-Filho, Alberto; Costa, Vital P; Wu, Zhichao; Medeiros, Felipe A

2018-01-01

To present a new methodology for investigating predictive factors associated with development of vision-related disability in glaucoma. Prospective, observational cohort study. Two hundred thirty-six patients with glaucoma followed up for an average of 4.3±1.5 years. Vision-related disability was assessed by the 25-item National Eye Institute Visual Function Questionnaire (NEI VFQ-25) at baseline and at the end of follow-up. A latent transition analysis model was used to categorize NEI VFQ-25 results and to estimate the probability of developing vision-related disability during follow-up. Patients were tested with standard automated perimetry (SAP) at 6-month intervals, and evaluation of rates of visual field change was performed using mean sensitivity (MS) of the integrated binocular visual field. Baseline disease severity, rate of visual field loss, and duration of follow-up were investigated as predictive factors for development of disability during follow-up. The relationship between baseline and rates of visual field deterioration and the probability of vision-related disability developing during follow-up. At baseline, 67 of 236 (28%) glaucoma patients were classified as disabled based on NEI VFQ-25 results, whereas 169 (72%) were classified as nondisabled. Patients classified as nondisabled at baseline had 14.2% probability of disability developing during follow-up. Rates of visual field loss as estimated by integrated binocular MS were almost 4 times faster for those in whom disability developed versus those in whom it did not (-0.78±1.00 dB/year vs. -0.20±0.47 dB/year, respectively; P < 0.001). In the multivariate model, each 1-dB lower baseline binocular MS was associated with 34% higher odds of disability developing over time (odds ratio [OR], 1.34; 95% confidence interval [CI], 1.06-1.70; P = 0.013). In addition, each 0.5-dB/year faster rate of loss of binocular MS during follow-up was associated with a more than 3.5 times increase in the risk of disability developing (OR, 3.58; 95% CI, 1.56-8.23; P = 0.003). A new methodology for classification and analysis of change in patient-reported quality-of-life outcomes allowed construction of models for predicting vision-related disability in glaucoma. Copyright © 2017 American Academy of Ophthalmology. Published by Elsevier Inc. All rights reserved.

Spatial decoupling of targets and flashing stimuli for visual brain-computer interfaces

NASA Astrophysics Data System (ADS)

Waytowich, Nicholas R.; Krusienski, Dean J.

2015-06-01

Objective. Recently, paradigms using code-modulated visual evoked potentials (c-VEPs) have proven to achieve among the highest information transfer rates for noninvasive brain-computer interfaces (BCIs). One issue with current c-VEP paradigms, and visual-evoked paradigms in general, is that they require direct foveal fixation of the flashing stimuli. These interfaces are often visually unpleasant and can be irritating and fatiguing to the user, thus adversely impacting practical performance. In this study, a novel c-VEP BCI paradigm is presented that attempts to perform spatial decoupling of the targets and flashing stimuli using two distinct concepts: spatial separation and boundary positioning. Approach. For the paradigm, the flashing stimuli form a ring that encompasses the intended non-flashing targets, which are spatially separated from the stimuli. The user fixates on the desired target, which is classified using the changes to the EEG induced by the flashing stimuli located in the non-foveal visual field. Additionally, a subset of targets is also positioned at or near the stimulus boundaries, which decouples targets from direct association with a single stimulus. This allows a greater number of target locations for a fixed number of flashing stimuli. Main results. Results from 11 subjects showed practical classification accuracies for the non-foveal condition, with comparable performance to the direct-foveal condition for longer observation lengths. Online results from 5 subjects confirmed the offline results with an average accuracy across subjects of 95.6% for a 4-target condition. The offline analysis also indicated that targets positioned at or near the boundaries of two stimuli could be classified with the same accuracy as traditional superimposed (non-boundary) targets. Significance. The implications of this research are that c-VEPs can be detected and accurately classified to achieve comparable BCI performance without requiring potentially irritating direct foveation of flashing stimuli. Furthermore, this study shows that it is possible to increase the number of targets beyond the number of stimuli without degrading performance. Given the superior information transfer rate of c-VEP paradigms, these results can lead to the development of more practical and ergonomic BCIs.

Deep Neural Networks Rival the Representation of Primate IT Cortex for Core Visual Object Recognition

PubMed Central

Cadieu, Charles F.; Hong, Ha; Yamins, Daniel L. K.; Pinto, Nicolas; Ardila, Diego; Solomon, Ethan A.; Majaj, Najib J.; DiCarlo, James J.

2014-01-01

The primate visual system achieves remarkable visual object recognition performance even in brief presentations, and under changes to object exemplar, geometric transformations, and background variation (a.k.a. core visual object recognition). This remarkable performance is mediated by the representation formed in inferior temporal (IT) cortex. In parallel, recent advances in machine learning have led to ever higher performing models of object recognition using artificial deep neural networks (DNNs). It remains unclear, however, whether the representational performance of DNNs rivals that of the brain. To accurately produce such a comparison, a major difficulty has been a unifying metric that accounts for experimental limitations, such as the amount of noise, the number of neural recording sites, and the number of trials, and computational limitations, such as the complexity of the decoding classifier and the number of classifier training examples. In this work, we perform a direct comparison that corrects for these experimental limitations and computational considerations. As part of our methodology, we propose an extension of “kernel analysis” that measures the generalization accuracy as a function of representational complexity. Our evaluations show that, unlike previous bio-inspired models, the latest DNNs rival the representational performance of IT cortex on this visual object recognition task. Furthermore, we show that models that perform well on measures of representational performance also perform well on measures of representational similarity to IT, and on measures of predicting individual IT multi-unit responses. Whether these DNNs rely on computational mechanisms similar to the primate visual system is yet to be determined, but, unlike all previous bio-inspired models, that possibility cannot be ruled out merely on representational performance grounds. PMID:25521294

Gas chimney detection based on improving the performance of combined multilayer perceptron and support vector classifier

NASA Astrophysics Data System (ADS)

Hashemi, H.; Tax, D. M. J.; Duin, R. P. W.; Javaherian, A.; de Groot, P.

2008-11-01

Seismic object detection is a relatively new field in which 3-D bodies are visualized and spatial relationships between objects of different origins are studied in order to extract geologic information. In this paper, we propose a method for finding an optimal classifier with the help of a statistical feature ranking technique and combining different classifiers. The method, which has general applicability, is demonstrated here on a gas chimney detection problem. First, we evaluate a set of input seismic attributes extracted at locations labeled by a human expert using regularized discriminant analysis (RDA). In order to find the RDA score for each seismic attribute, forward and backward search strategies are used. Subsequently, two non-linear classifiers: multilayer perceptron (MLP) and support vector classifier (SVC) are run on the ranked seismic attributes. Finally, to capitalize on the intrinsic differences between both classifiers, the MLP and SVC results are combined using logical rules of maximum, minimum and mean. The proposed method optimizes the ranked feature space size and yields the lowest classification error in the final combined result. We will show that the logical minimum reveals gas chimneys that exhibit both the softness of MLP and the resolution of SVC classifiers.

A consensus prognostic gene expression classifier for ER positive breast cancer

PubMed Central

Teschendorff, Andrew E; Naderi, Ali; Barbosa-Morais, Nuno L; Pinder, Sarah E; Ellis, Ian O; Aparicio, Sam; Brenton, James D; Caldas, Carlos

2006-01-01

Background A consensus prognostic gene expression classifier is still elusive in heterogeneous diseases such as breast cancer. Results Here we perform a combined analysis of three major breast cancer microarray data sets to hone in on a universally valid prognostic molecular classifier in estrogen receptor (ER) positive tumors. Using a recently developed robust measure of prognostic separation, we further validate the prognostic classifier in three external independent cohorts, confirming the validity of our molecular classifier in a total of 877 ER positive samples. Furthermore, we find that molecular classifiers may not outperform classical prognostic indices but that they can be used in hybrid molecular-pathological classification schemes to improve prognostic separation. Conclusion The prognostic molecular classifier presented here is the first to be valid in over 877 ER positive breast cancer samples and across three different microarray platforms. Larger multi-institutional studies will be needed to fully determine the added prognostic value of molecular classifiers when combined with standard prognostic factors. PMID:17076897

Combination of laser-induced breakdown spectroscopy and Raman spectroscopy for multivariate classification of bacteria

NASA Astrophysics Data System (ADS)

Prochazka, D.; Mazura, M.; Samek, O.; Rebrošová, K.; Pořízka, P.; Klus, J.; Prochazková, P.; Novotný, J.; Novotný, K.; Kaiser, J.

2018-01-01

In this work, we investigate the impact of data provided by complementary laser-based spectroscopic methods on multivariate classification accuracy. Discrimination and classification of five Staphylococcus bacterial strains and one strain of Escherichia coli is presented. The technique that we used for measurements is a combination of Raman spectroscopy and Laser-Induced Breakdown Spectroscopy (LIBS). Obtained spectroscopic data were then processed using Multivariate Data Analysis algorithms. Principal Components Analysis (PCA) was selected as the most suitable technique for visualization of bacterial strains data. To classify the bacterial strains, we used Neural Networks, namely a supervised version of Kohonen's self-organizing maps (SOM). We were processing results in three different ways - separately from LIBS measurements, from Raman measurements, and we also merged data from both mentioned methods. The three types of results were then compared. By applying the PCA to Raman spectroscopy data, we observed that two bacterial strains were fully distinguished from the rest of the data set. In the case of LIBS data, three bacterial strains were fully discriminated. Using a combination of data from both methods, we achieved the complete discrimination of all bacterial strains. All the data were classified with a high success rate using SOM algorithm. The most accurate classification was obtained using a combination of data from both techniques. The classification accuracy varied, depending on specific samples and techniques. As for LIBS, the classification accuracy ranged from 45% to 100%, as for Raman Spectroscopy from 50% to 100% and in case of merged data, all samples were classified correctly. Based on the results of the experiments presented in this work, we can assume that the combination of Raman spectroscopy and LIBS significantly enhances discrimination and classification accuracy of bacterial species and strains. The reason is the complementarity in obtained chemical information while using these two methods.

Aggressive Bimodal Communication in Domestic Dogs, Canis familiaris.

PubMed

Déaux, Éloïse C; Clarke, Jennifer A; Charrier, Isabelle

2015-01-01

Evidence of animal multimodal signalling is widespread and compelling. Dogs' aggressive vocalisations (growls and barks) have been extensively studied, but without any consideration of the simultaneously produced visual displays. In this study we aimed to categorize dogs' bimodal aggressive signals according to the redundant/non-redundant classification framework. We presented dogs with unimodal (audio or visual) or bimodal (audio-visual) stimuli and measured their gazing and motor behaviours. Responses did not qualitatively differ between the bimodal and two unimodal contexts, indicating that acoustic and visual signals provide redundant information. We could not further classify the signal as 'equivalent' or 'enhancing' as we found evidence for both subcategories. We discuss our findings in relation to the complex signal framework, and propose several hypotheses for this signal's function.

Brain-computer interface on the basis of EEG system Encephalan

NASA Astrophysics Data System (ADS)

Maksimenko, Vladimir; Badarin, Artem; Nedaivozov, Vladimir; Kirsanov, Daniil; Hramov, Alexander

2018-04-01

We have proposed brain-computer interface (BCI) for the estimation of the brain response on the presented visual tasks. Proposed BCI is based on the EEG recorder Encephalan-EEGR-19/26 (Medicom MTD, Russia) supplemented by a special home-made developed acquisition software. BCI is tested during experimental session while subject is perceiving the bistable visual stimuli and classifying them according to the interpretation. We have subjected the participant to the different external conditions and observed the significant decrease in the response, associated with the perceiving the bistable visual stimuli, during the presence of distraction. Based on the obtained results we have proposed possibility to use of BCI for estimation of the human alertness during solving the tasks required substantial visual attention.

Efficient Multi-Concept Visual Classifier Adaptation in Changing Environments

DTIC Science & Technology

2016-09-01

yet to be discussed in existing supervised multi-concept visual perception systems used in robotics applications.1,5–7 Anno - tation of images is...Autonomous robot navigation in highly populated pedestrian zones. J Field Robotics. 2015;32(4):565–589. 3. Milella A, Reina G, Underwood J . A self...learning framework for statistical ground classification using RADAR and monocular vision. J Field Robotics. 2015;32(1):20–41. 4. Manjanna S, Dudek G

Lesion classification using clinical and visual data fusion by multiple kernel learning

NASA Astrophysics Data System (ADS)

Kisilev, Pavel; Hashoul, Sharbell; Walach, Eugene; Tzadok, Asaf

2014-03-01

To overcome operator dependency and to increase diagnosis accuracy in breast ultrasound (US), a lot of effort has been devoted to developing computer-aided diagnosis (CAD) systems for breast cancer detection and classification. Unfortunately, the efficacy of such CAD systems is limited since they rely on correct automatic lesions detection and localization, and on robustness of features computed based on the detected areas. In this paper we propose a new approach to boost the performance of a Machine Learning based CAD system, by combining visual and clinical data from patient files. We compute a set of visual features from breast ultrasound images, and construct the textual descriptor of patients by extracting relevant keywords from patients' clinical data files. We then use the Multiple Kernel Learning (MKL) framework to train SVM based classifier to discriminate between benign and malignant cases. We investigate different types of data fusion methods, namely, early, late, and intermediate (MKL-based) fusion. Our database consists of 408 patient cases, each containing US images, textual description of complaints and symptoms filled by physicians, and confirmed diagnoses. We show experimentally that the proposed MKL-based approach is superior to other classification methods. Even though the clinical data is very sparse and noisy, its MKL-based fusion with visual features yields significant improvement of the classification accuracy, as compared to the image features only based classifier.

Towards intraoperative surgical margin assessment and visualization using bioimpedance properties of the tissue

NASA Astrophysics Data System (ADS)

Khan, Shadab; Mahara, Aditya; Hyams, Elias S.; Schned, Alan; Halter, Ryan

2015-03-01

Prostate cancer (PCa) has a high 10-year recurrence rate, making PCa the second leading cause of cancer-specific mortality among men in the USA. PCa recurrences are often predicted by assessing the status of surgical margins (SM) with positive surgical margins (PSM) increasing the chances of biochemical recurrence by 2-4 times. To this end, an SM assessment system using Electrical Impedance Spectroscopy (EIS) was developed with a microendoscopic probe. This system measures the tissue bioimpedance over a range of frequencies (1 kHz to 1MHz), and computes a Composite Impedance Metric (CIM). CIM can be used to classify tissue as benign or cancerous. The system was used to collect the impedance spectra from excised prostates, which were obtained from men undergoing radical prostatectomy. The data revealed statistically significant (p<0.05) differences in the impedance properties of the benign and tumorous tissues, and between different tissue morphologies. To visualize the results of SM-assessment, a visualization tool using da Vinci stereo laparoscope is being developed. Together with the visualization tool, the EIS-based SM assessment system can be potentially used to intraoperatively classify tissues and display the results on the surgical console with a video feed of the surgical site, thereby augmenting a surgeon's view of the site and providing a potential solution to the intraoperative SM assessment needs.

Classification of binary intentions for individuals with impaired oculomotor function: ‘eyes-closed’ SSVEP-based brain-computer interface (BCI)

NASA Astrophysics Data System (ADS)

Lim, Jeong-Hwan; Hwang, Han-Jeong; Han, Chang-Hee; Jung, Ki-Young; Im, Chang-Hwan

2013-04-01

Objective. Some patients suffering from severe neuromuscular diseases have difficulty controlling not only their bodies but also their eyes. Since these patients have difficulty gazing at specific visual stimuli or keeping their eyes open for a long time, they are unable to use the typical steady-state visual evoked potential (SSVEP)-based brain-computer interface (BCI) systems. In this study, we introduce a new paradigm for SSVEP-based BCI, which can be potentially suitable for disabled individuals with impaired oculomotor function. Approach. The proposed electroencephalography (EEG)-based BCI system allows users to express their binary intentions without needing to open their eyes. A pair of glasses with two light emitting diodes flickering at different frequencies was used to present visual stimuli to participants with their eyes closed, and we classified the recorded EEG patterns in the online experiments conducted with five healthy participants and one patient with severe amyotrophic lateral sclerosis (ALS). Main results. Through offline experiments performed with 11 participants, we confirmed that human SSVEP could be modulated by visual selective attention to a specific light stimulus penetrating through the eyelids. Furthermore, the recorded EEG patterns could be classified with accuracy high enough for use in a practical BCI system. After customizing the parameters of the proposed SSVEP-based BCI paradigm based on the offline analysis results, binary intentions of five healthy participants were classified in real time. The average information transfer rate of our online experiments reached 10.83 bits min-1. A preliminary online experiment conducted with an ALS patient showed a classification accuracy of 80%. Significance. The results of our offline and online experiments demonstrated the feasibility of our proposed SSVEP-based BCI paradigm. It is expected that our ‘eyes-closed’ SSVEP-based BCI system can be potentially used for communication of disabled individuals with impaired oculomotor function.

Classification of binary intentions for individuals with impaired oculomotor function: 'eyes-closed' SSVEP-based brain-computer interface (BCI).

PubMed

Lim, Jeong-Hwan; Hwang, Han-Jeong; Han, Chang-Hee; Jung, Ki-Young; Im, Chang-Hwan

2013-04-01

Some patients suffering from severe neuromuscular diseases have difficulty controlling not only their bodies but also their eyes. Since these patients have difficulty gazing at specific visual stimuli or keeping their eyes open for a long time, they are unable to use the typical steady-state visual evoked potential (SSVEP)-based brain-computer interface (BCI) systems. In this study, we introduce a new paradigm for SSVEP-based BCI, which can be potentially suitable for disabled individuals with impaired oculomotor function. The proposed electroencephalography (EEG)-based BCI system allows users to express their binary intentions without needing to open their eyes. A pair of glasses with two light emitting diodes flickering at different frequencies was used to present visual stimuli to participants with their eyes closed, and we classified the recorded EEG patterns in the online experiments conducted with five healthy participants and one patient with severe amyotrophic lateral sclerosis (ALS). Through offline experiments performed with 11 participants, we confirmed that human SSVEP could be modulated by visual selective attention to a specific light stimulus penetrating through the eyelids. Furthermore, the recorded EEG patterns could be classified with accuracy high enough for use in a practical BCI system. After customizing the parameters of the proposed SSVEP-based BCI paradigm based on the offline analysis results, binary intentions of five healthy participants were classified in real time. The average information transfer rate of our online experiments reached 10.83 bits min(-1). A preliminary online experiment conducted with an ALS patient showed a classification accuracy of 80%. The results of our offline and online experiments demonstrated the feasibility of our proposed SSVEP-based BCI paradigm. It is expected that our 'eyes-closed' SSVEP-based BCI system can be potentially used for communication of disabled individuals with impaired oculomotor function.

A Survey of Colormaps in Visualization

PubMed Central

Zhou, Liang; Hansen, Charles D.

2016-01-01

Colormaps are a vital method for users to gain insights into data in a visualization. With a good choice of colormaps, users are able to acquire information in the data more effectively and efficiently. In this survey, we attempt to provide readers with a comprehensive review of colormap generation techniques and provide readers a taxonomy which is helpful for finding appropriate techniques to use for their data and applications. Specifically, we first briefly introduce the basics of color spaces including color appearance models. In the core of our paper, we survey colormap generation techniques, including the latest advances in the field by grouping these techniques into four classes: procedural methods, user-study based methods, rule-based methods, and data-driven methods; we also include a section on methods that are beyond pure data comprehension purposes. We then classify colormapping techniques into a taxonomy for readers to quickly identify the appropriate techniques they might use. Furthermore, a representative set of visualization techniques that explicitly discuss the use of colormaps is reviewed and classified based on the nature of the data in these applications. Our paper is also intended to be a reference of colormap choices for readers when they are faced with similar data and/or tasks. PMID:26513793

The influence of motivational and mood states on visual attention: A quantification of systematic differences and casual changes in subjects' focus of attention.

PubMed

Hüttermann, Stefanie; Memmert, Daniel

2015-01-01

A great number of studies have shown that different motivational and mood states can influence human attentional processes in a variety of ways. Yet, none of these studies have reliably quantified the exact changes of the attentional focus in order to be able to compare attentional performances based on different motivational and mood influences and, beyond that, to evaluate their effectivity. In two studies, we explored subjects' differences in the breadth and distribution of attention as a function of motivational and mood manipulations. In Study 1, motivational orientation was classified in terms of regulatory focus (promotion vs. prevention) and in Study 2, mood was classified in terms of valence (positive vs. negative). Study 1 found a 10% wider distribution of the visual attention in promotion-oriented subjects compared to prevention-oriented ones. The results in Study 2 reveal a widening of the subjects' visual attentional breadth when listening to happy music by 22% and a narrowing by 36% when listening to melancholic music. In total, the findings show that systematic differences and casual changes in the shape and scope of focused attention may be associated with different motivational and mood states.

Soundwalk approach to identify urban soundscapes individually.

PubMed

Jeon, Jin Yong; Hong, Joo Young; Lee, Pyoung Jik

2013-07-01

This study proposes a soundwalk procedure for evaluating urban soundscapes. Previous studies, which adopted soundwalk methodologies for investigating participants' responses to visual and acoustic environments, were analyzed considering type, evaluation position, measurement, and subjective assessment. An individual soundwalk procedure was then developed based on asking individual subjects to walk and select evaluation positions where they perceived any positive or negative characteristics of the urban soundscape. A case study was performed in urban spaces and the results were compared with those of the group soundwalk to validate the individual soundwalk procedure. Thirty subjects (15 architects and 15 acousticians) participated in the soundwalk. During the soundwalk, the subjects selected a total of 196 positions, and those were classified into 4 groups. It was found that soundscape perceptions were dominated by acoustic comfort, visual images, and openness. It was also revealed that perceived elements of the acoustic environment and visual image differed across classified soundscape groups, and there was a difference between architects and acousticians in terms of how they described their impressions of the soundscape elements. The results show that the individual soundwalk procedure has advantages for measuring diverse subjective responses and for obtaining the perceived elements of the urban soundscape.

Integrating Human and Machine Intelligence in Galaxy Morphology Classification Tasks

NASA Astrophysics Data System (ADS)

Beck, Melanie Renee

The large flood of data flowing from observatories presents significant challenges to astronomy and cosmology--challenges that will only be magnified by projects currently under development. Growth in both volume and velocity of astrophysics data is accelerating: whereas the Sloan Digital Sky Survey (SDSS) has produced 60 terabytes of data in the last decade, the upcoming Large Synoptic Survey Telescope (LSST) plans to register 30 terabytes per night starting in the year 2020. Additionally, the Euclid Mission will acquire imaging for 5 x 107 resolvable galaxies. The field of galaxy evolution faces a particularly challenging future as complete understanding often cannot be reached without analysis of detailed morphological galaxy features. Historically, morphological analysis has relied on visual classification by astronomers, accessing the human brains capacity for advanced pattern recognition. However, this accurate but inefficient method falters when confronted with many thousands (or millions) of images. In the SDSS era, efforts to automate morphological classifications of galaxies (e.g., Conselice et al., 2000; Lotz et al., 2004) are reasonably successful and can distinguish between elliptical and disk-dominated galaxies with accuracies of 80%. While this is statistically very useful, a key problem with these methods is that they often cannot say which 80% of their samples are accurate. Furthermore, when confronted with the more complex task of identifying key substructure within galaxies, automated classification algorithms begin to fail. The Galaxy Zoo project uses a highly innovative approach to solving the scalability problem of visual classification. Displaying images of SDSS galaxies to volunteers via a simple and engaging web interface, www.galaxyzoo.org asks people to classify images by eye. Within the first year hundreds of thousands of members of the general public had classified each of the 1 million SDSS galaxies an average of 40 times. Galaxy Zoo thus solved both the visual classification problem of time efficiency and improved accuracy by producing a distribution of independent classifications for each galaxy. While crowd-sourced galaxy classifications have proven their worth, challenges remain before establishing this method as a critical and standard component of the data processing pipelines for the next generation of surveys. In particular, though innovative, crowd-sourcing techniques do not have the capacity to handle the data volume and rates expected in the next generation of surveys. These algorithms will be delegated to handle the majority of the classification tasks, freeing citizen scientists to contribute their efforts on subtler and more complex assignments. This thesis presents 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 days of GZ2 project time while reproducing labels derived from GZ2 classification data with 95.7% 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 a factor of 11.4 increase in the classification rate, classifying 210,803 galaxies in just 32 days of GZ2 project time with 93.1% 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.

Real-time scalable visual analysis on mobile devices

NASA Astrophysics Data System (ADS)

Pattath, Avin; Ebert, David S.; May, Richard A.; Collins, Timothy F.; Pike, William

2008-02-01

Interactive visual presentation of information can help an analyst gain faster and better insight from data. When combined with situational or context information, visualization on mobile devices is invaluable to in-field responders and investigators. However, several challenges are posed by the form-factor of mobile devices in developing such systems. In this paper, we classify these challenges into two broad categories - issues in general mobile computing and issues specific to visual analysis on mobile devices. Using NetworkVis and Infostar as example systems, we illustrate some of the techniques that we employed to overcome many of the identified challenges. NetworkVis is an OpenVG-based real-time network monitoring and visualization system developed for Windows Mobile devices. Infostar is a flash-based interactive, real-time visualization application intended to provide attendees access to conference information. Linked time-synchronous visualization, stylus/button-based interactivity, vector graphics, overview-context techniques, details-on-demand and statistical information display are some of the highlights of these applications.

Comparison of Munsell(®) color chart assessments with primary schoolchildren's self-reported skin color.

PubMed

Wright, C Y; Reeder, A I; Gray, A R; Hammond, V A

2015-11-01

Skin color is related to human health outcomes, including the risks of skin cancer and vitamin D insufficiency. Self-perceptions of skin color may influence health behaviours, including the adoption of practices protective against harmful solar ultraviolet radiation levels. Misperception of personal risk may have negative health implications. The aim of this study is to determine whether Munsell(®) color chart assessments align with child self-reported skin color. Two-trained investigators, with assessed color acuity, visually classified student inner upper arm constitutive skin color. The Munsell(®) classifications obtained were converted to Individual Typology Angle (ITA) values and respective Del Bino skin color categories after spectrocolorimeter measurements based on published values/data. As part of a written questionnaire on sun protection knowledge, attitudes, and behaviours, self-completed in class time, students classified their end of winter skin color. Student self-reports were compared with the ITA-based Del Bino classifications. A total of 477 New Zealand primary students attending 27 randomly selected schools from five geographic regions. The main measures were self-reported skin color and visually observed skin color. A monotonic association was observed between the distribution of spectrophotometer ITA scores obtained for Munsell(®) tiles and child self-reports of skin color, providing some evidence for the validity of self-report among New Zealand primary school children, although the lighter colored ITA defined groups were most numerous in this study sample. Statistically significant differences in ITA scores were found by ethnicity, self-reported skin color, and geographic residence (P < 0.001). Certain Munsell(®) color tiles were frequently selected as providing a best match to skin color. Assessment using Munsell(®) color charts was simple, inexpensive, and practical for field use and acceptable to children. The results suggest that this method may prove useful for making comparisons with other studies using visual tools to assess skin color. Alignment between the ITA distribution derived from the Munsell(®) assessment and child skin color self-reports could probably be improved, particularly with the addition of another 'light'/'white' color category in the self-report instrument. © 2015 John Wiley & Sons A/S. Published by John Wiley & Sons Ltd.

The value of intraoperative ultrasonography during the resection of relapsed irradiated malignant gliomas in the brain.

PubMed

Mursch, Kay; Scholz, Martin; Brück, Wolfgang; Behnke-Mursch, Julianne

2017-01-01

The aim of this study was to investigate whether intraoperative ultrasonography (IOUS) helped the surgeon navigate towards the tumor as seen in preoperative magnetic resonance imaging and whether IOUS was able to distinguish between tumor margins and the surrounding tissue. Twenty-five patients suffering from high-grade gliomas who were previously treated by surgery and radiotherapy were included. Intraoperatively, two histopathologic samples were obtained a sample of unequivocal tumor tissue (according to anatomical landmarks and the surgeon's visual and tactile impressions) and a small tissue sample obtained using a navigated needle when the surgeon decided to stop the resection. This specimen was considered to be a boundary specimen, where no tumor tissue was apparent. The decision to take the second sample was not influenced by IOUS. The effect of IOUS was analyzed semi-quantitatively. All 25 samples of unequivocal tumor tissue were histopathologically classified as tumor tissue and were hyperechoic on IOUS. Of the boundary specimens, eight were hypoechoic. Only one harbored tumor tissue (P=0.150). Seventeen boundaries were moderately hyperechoic, and these samples contained all possible histological results (i.e., tumor, infiltration, or no tumor). During surgery performed on relapsed, irradiated, high-grade gliomas, IOUS provided a reliable method of navigating towards the core of the tumor. At borders, it did not reliably distinguish between remnants or tumor-free tissue, but hypoechoic areas seldom contained tumor tissue.

Distributed neural signatures of natural audiovisual speech and music in the human auditory cortex.

PubMed

Salmi, Juha; Koistinen, Olli-Pekka; Glerean, Enrico; Jylänki, Pasi; Vehtari, Aki; Jääskeläinen, Iiro P; Mäkelä, Sasu; Nummenmaa, Lauri; Nummi-Kuisma, Katarina; Nummi, Ilari; Sams, Mikko

2017-08-15

During a conversation or when listening to music, auditory and visual information are combined automatically into audiovisual objects. However, it is still poorly understood how specific type of visual information shapes neural processing of sounds in lifelike stimulus environments. Here we applied multi-voxel pattern analysis to investigate how naturally matching visual input modulates supratemporal cortex activity during processing of naturalistic acoustic speech, singing and instrumental music. Bayesian logistic regression classifiers with sparsity-promoting priors were trained to predict whether the stimulus was audiovisual or auditory, and whether it contained piano playing, speech, or singing. The predictive performances of the classifiers were tested by leaving one participant at a time for testing and training the model using the remaining 15 participants. The signature patterns associated with unimodal auditory stimuli encompassed distributed locations mostly in the middle and superior temporal gyrus (STG/MTG). A pattern regression analysis, based on a continuous acoustic model, revealed that activity in some of these MTG and STG areas were associated with acoustic features present in speech and music stimuli. Concurrent visual stimulus modulated activity in bilateral MTG (speech), lateral aspect of right anterior STG (singing), and bilateral parietal opercular cortex (piano). Our results suggest that specific supratemporal brain areas are involved in processing complex natural speech, singing, and piano playing, and other brain areas located in anterior (facial speech) and posterior (music-related hand actions) supratemporal cortex are influenced by related visual information. Those anterior and posterior supratemporal areas have been linked to stimulus identification and sensory-motor integration, respectively. Copyright © 2017 Elsevier Inc. All rights reserved.

The CommonGround Visual Paradigm for Biosurveillance

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

Livnat, Yarden; Jurrus, Elizabeth R.; Gundlapalli, Adi V.

2013-06-14

Biosurveillance is a critical area in the intelligence community for real-time detection of disease outbreaks. Identifying epidemics enables analysts to detect and monitor disease outbreaks that might be spread from natural causes or from possible biological warfare attacks. Containing these events and disseminating alerts requires the ability to rapidly find, classify and track harmful biological signatures. In this paper, we describe a novel visual paradigm to conduct biosurveillance using an Infectious Disease Weather Map. Our system provides a visual common ground in which users can view, explore and discover emerging concepts and correlations such as symptoms, syndromes, pathogens, and geographicmore » locations.« less

[The 8-year follow-up study for clinical diagnostic potentials of frequency-doubling technology perimetry for perimetrically normal eyes of open-angle glaucoma patients with unilateral visual field loss].

PubMed

Fan, X; Wu, L L; Xiao, G G; Ma, Z Z; Liu, F

2018-03-11

Objective: To analyze potentials of frequency-doubling technology perimetry (FDP) for diagnosing open-angle glaucoma (OAG) in perimetrically normal eyes of OAG patients diagnosed with standard automated perimetry (SAP) and relating factors from abnormalities on FDP to visual field loss on SAP. Methods: A prospective cohort study. Sixty-eight eyes of 68 OAG patients visiting the ophthalmic clinic of Peking University Third Hospital during November 2003 and October 2007 [32 primary open-angle glaucoma patients and 36 normal tension glaucoma patients, 32 males and 36 females, with an average age of (59±13) years] with unilateral field loss detected by SAP (Octopus101 tG2 program) were examined with the FDP N-30 threshold program (Humphrey Instruments) at baseline. Two groups, FDP positive group and FDP negative group, were divided based on the FDP results, and visual field examinations were followed by a series of SAP examinations for the perimetrically normal eyes over 8 years. During the follow-up, the difference of the converting rate of SAP tests between the two groups was analyzed. Differences between "convertors" and "non-convertors" of SAP tests in the FDP positive group, such as the cup-to-disk ratio and glaucomatous optic neuropathy rate, were also compared with the independent-sample t test or Wilcoxon two-sample test for continuous variable data and the χ(2) test or Fisher exact test for classified variable data and rates. Results: Forty-eight perimetrically normal eyes of 48 participants had complete data and a qualifying follow-up. Baseline FDP results were positive in 33 eyes and negative in 15 eyes. Of the eyes with positive FDP results, 22 eyes developed abnormal SAP results after 4.0 to 90.0 months (median 14.5 months) , whereas none of the eyes with negative FDP results developed abnormal SAP results. For perimetrically normal eyes in the FDP positive group, "converters" showed a greater cup-to-disk ratio (0.73±0.09 vs . 0.63±0.14, Wilcoxon two-sample test, P= 0.011) and more eyes with glaucomatous optic neuropathy (19/22 vs . 4/11, Fisher exact test, P= 0.006). Conclusions: In perimetrically normal eyes of OAG patients, FDP could detect visual field loss of these eyes and predict to some extent future visual field loss on SAP. Severity of glaucomatous optic neuropathy at baseline is related to converting from abnormalities on FDP to visual field loss on SAP. (Chin J Ophthalmol, 2018, 54: 177-183) .

Local feature saliency classifier for real-time intrusion monitoring

NASA Astrophysics Data System (ADS)

Buch, Norbert; Velastin, Sergio A.

2014-07-01

We propose a texture saliency classifier to detect people in a video frame by identifying salient texture regions. The image is classified into foreground and background in real time. No temporal image information is used during the classification. The system is used for the task of detecting people entering a sterile zone, which is a common scenario for visual surveillance. Testing is performed on the Imagery Library for Intelligent Detection Systems sterile zone benchmark dataset of the United Kingdom's Home Office. The basic classifier is extended by fusing its output with simple motion information, which significantly outperforms standard motion tracking. A lower detection time can be achieved by combining texture classification with Kalman filtering. The fusion approach running at 10 fps gives the highest result of F1=0.92 for the 24-h test dataset. The paper concludes with a detailed analysis of the computation time required for the different parts of the algorithm.

Sampling methods, dispersion patterns, and fixed precision sequential sampling plans for western flower thrips (Thysanoptera: Thripidae) and cotton fleahoppers (Hemiptera: Miridae) in cotton.

PubMed

Parajulee, M N; Shrestha, R B; Leser, J F

2006-04-01

A 2-yr field study was conducted to examine the effectiveness of two sampling methods (visual and plant washing techniques) for western flower thrips, Frankliniella occidentalis (Pergande), and five sampling methods (visual, beat bucket, drop cloth, sweep net, and vacuum) for cotton fleahopper, Pseudatomoscelis seriatus (Reuter), in Texas cotton, Gossypium hirsutum (L.), and to develop sequential sampling plans for each pest. The plant washing technique gave similar results to the visual method in detecting adult thrips, but the washing technique detected significantly higher number of thrips larvae compared with the visual sampling. Visual sampling detected the highest number of fleahoppers followed by beat bucket, drop cloth, vacuum, and sweep net sampling, with no significant difference in catch efficiency between vacuum and sweep net methods. However, based on fixed precision cost reliability, the sweep net sampling was the most cost-effective method followed by vacuum, beat bucket, drop cloth, and visual sampling. Taylor's Power Law analysis revealed that the field dispersion patterns of both thrips and fleahoppers were aggregated throughout the crop growing season. For thrips management decision based on visual sampling (0.25 precision), 15 plants were estimated to be the minimum sample size when the estimated population density was one thrips per plant, whereas the minimum sample size was nine plants when thrips density approached 10 thrips per plant. The minimum visual sample size for cotton fleahoppers was 16 plants when the density was one fleahopper per plant, but the sample size decreased rapidly with an increase in fleahopper density, requiring only four plants to be sampled when the density was 10 fleahoppers per plant. Sequential sampling plans were developed and validated with independent data for both thrips and cotton fleahoppers.

Age determination of bottled Chinese rice wine by VIS-NIR spectroscopy

NASA Astrophysics Data System (ADS)

Yu, Haiyan; Lin, Tao; Ying, Yibin; Pan, Xingxiang

2006-10-01

The feasibility of non-invasive visible and near infrared (VIS-NIR) spectroscopy for determining wine age (1, 2, 3, 4, and 5 years) of Chinese rice wine was investigated. Samples of Chinese rice wine were analyzed in 600 mL square brown glass bottles with side length of approximately 64 mm at room temperature. VIS-NIR spectra of 100 bottled Chinese rice wine samples were collected in transmission mode in the wavelength range of 350-1200 nm by a fiber spectrometer system. Discriminant models were developed based on discriminant analysis (DA) together with raw, first and second derivative spectra. The concentration of alcoholic degree, total acid, and °Brix was determined to validate the NIR results. The calibration result for raw spectra was better than that for first and second derivative spectra. The percentage of samples correctly classified for raw spectra was 98%. For 1-, 2-, and 3-year-old sample groups, the sample were all correctly classified, and for 4- and 5-year-old sample groups, the percentage of samples correctly classified was 92.9%, respectively. In validation analysis, the percentage of samples correctly classified was 100%. The results demonstrated that VIS-NIR spectroscopic technique could be used as a non-invasive, rapid and reliable method for predicting wine age of bottled Chinese rice wine.

Fuzziness-based active learning framework to enhance hyperspectral image classification performance for discriminative and generative classifiers

PubMed Central

2018-01-01

Hyperspectral image classification with a limited number of training samples without loss of accuracy is desirable, as collecting such data is often expensive and time-consuming. However, classifiers trained with limited samples usually end up with a large generalization error. To overcome the said problem, we propose a fuzziness-based active learning framework (FALF), in which we implement the idea of selecting optimal training samples to enhance generalization performance for two different kinds of classifiers, discriminative and generative (e.g. SVM and KNN). The optimal samples are selected by first estimating the boundary of each class and then calculating the fuzziness-based distance between each sample and the estimated class boundaries. Those samples that are at smaller distances from the boundaries and have higher fuzziness are chosen as target candidates for the training set. Through detailed experimentation on three publically available datasets, we showed that when trained with the proposed sample selection framework, both classifiers achieved higher classification accuracy and lower processing time with the small amount of training data as opposed to the case where the training samples were selected randomly. Our experiments demonstrate the effectiveness of our proposed method, which equates favorably with the state-of-the-art methods. PMID:29304512

Computer-assisted visual interactive recognition and its prospects of implementation over the Internet

NASA Astrophysics Data System (ADS)

Zou, Jie; Gattani, Abhishek

2005-01-01

When completely automated systems don't yield acceptable accuracy, many practical pattern recognition systems involve the human either at the beginning (pre-processing) or towards the end (handling rejects). We believe that it may be more useful to involve the human throughout the recognition process rather than just at the beginning or end. We describe a methodology of interactive visual recognition for human-centered low-throughput applications, Computer Assisted Visual InterActive Recognition (CAVIAR), and discuss the prospects of implementing CAVIAR over the Internet. The novelty of CAVIAR is image-based interaction through a domain-specific parameterized geometrical model, which reduces the semantic gap between humans and computers. The user may interact with the computer anytime that she considers its response unsatisfactory. The interaction improves the accuracy of the classification features by improving the fit of the computer-proposed model. The computer makes subsequent use of the parameters of the improved model to refine not only its own statistical model-fitting process, but also its internal classifier. The CAVIAR methodology was applied to implement a flower recognition system. The principal conclusions from the evaluation of the system include: 1) the average recognition time of the CAVIAR system is significantly shorter than that of the unaided human; 2) its accuracy is significantly higher than that of the unaided machine; 3) it can be initialized with as few as one training sample per class and still achieve high accuracy; and 4) it demonstrates a self-learning ability. We have also implemented a Mobile CAVIAR system, where a pocket PC, as a client, connects to a server through wireless communication. The motivation behind a mobile platform for CAVIAR is to apply the methodology in a human-centered pervasive environment, where the user can seamlessly interact with the system for classifying field-data. Deploying CAVIAR to a networked mobile platform poses the challenge of classifying field images and programming under constraints of display size, network bandwidth, processor speed, and memory size. Editing of the computer-proposed model is performed on the handheld while statistical model fitting and classification take place on the server. The possibility that the user can easily take several photos of the object poses an interesting information fusion problem. The advantage of the Internet is that the patterns identified by different users can be pooled together to benefit all peer users. When users identify patterns with CAVIAR in a networked setting, they also collect training samples and provide opportunities for machine learning from their intervention. CAVIAR implemented over the Internet provides a perfect test bed for, and extends, the concept of Open Mind Initiative proposed by David Stork. Our experimental evaluation focuses on human time, machine and human accuracy, and machine learning. We devoted much effort to evaluating the use of our image-based user interface and on developing principles for the evaluation of interactive pattern recognition system. The Internet architecture and Mobile CAVIAR methodology have many applications. We are exploring in the directions of teledermatology, face recognition, and education.

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.

Spectroscopic study of honey from Apis mellifera from different regions in Mexico

NASA Astrophysics Data System (ADS)

Frausto-Reyes, C.; Casillas-Peñuelas, R.; Quintanar-Stephano, JL; Macías-López, E.; Bujdud-Pérez, JM; Medina-Ramírez, I.

2017-05-01

The objective of this study was to analyze by Raman and UV-Vis-NIR Spectroscopic techniques, Mexican honey from Apis Mellífera, using representative samples with different botanic origins (unifloral and multifloral) and diverse climates. Using Raman spectroscopy together with principal components analysis, the results obtained represent the possibility to use them for determination of floral origin of honey, independently of the region of sampling. For this, the effect of heat up the honey was analyzed in relation that it was possible to greatly reduce the fluorescence background in Raman spectra, which allowed the visualization of fructose and glucose peaks. Using UV-Vis-NIR, spectroscopy, a characteristic spectrum profile of transmittance was obtained for each honey type. In addition, to have an objective characterization of color, a CIE Yxy and CIE L*a*b* colorimetric register was realized for each honey type. Applying the principal component analysis and their correlation with chromaticity coordinates allowed classifying the honey samples in one plot as: cutoff wavelength, maximum transmittance, tones and lightness. The results show that it is possible to obtain a spectroscopic record of honeys with specific characteristics by reducing the effects of fluorescence.

Correcting Classifiers for Sample Selection Bias in Two-Phase Case-Control Studies

PubMed Central

Theis, Fabian J.

2017-01-01

Epidemiological studies often utilize stratified data in which rare outcomes or exposures are artificially enriched. This design can increase precision in association tests but distorts predictions when applying classifiers on nonstratified data. Several methods correct for this so-called sample selection bias, but their performance remains unclear especially for machine learning classifiers. With an emphasis on two-phase case-control studies, we aim to assess which corrections to perform in which setting and to obtain methods suitable for machine learning techniques, especially the random forest. We propose two new resampling-based methods to resemble the original data and covariance structure: stochastic inverse-probability oversampling and parametric inverse-probability bagging. We compare all techniques for the random forest and other classifiers, both theoretically and on simulated and real data. Empirical results show that the random forest profits from only the parametric inverse-probability bagging proposed by us. For other classifiers, correction is mostly advantageous, and methods perform uniformly. We discuss consequences of inappropriate distribution assumptions and reason for different behaviors between the random forest and other classifiers. In conclusion, we provide guidance for choosing correction methods when training classifiers on biased samples. For random forests, our method outperforms state-of-the-art procedures if distribution assumptions are roughly fulfilled. We provide our implementation in the R package sambia. PMID:29312464

An orientation soil survey at the Pebble Cu-Au-Mo porphyry deposit, Alaska

USGS Publications Warehouse

Smith, Steven M.; Eppinger, Robert G.; Fey, David L.; Kelley, Karen D.; Giles, S.A.

2009-01-01

Soil samples were collected in 2007 and 2008 along three traverses across the giant Pebble Cu-Au-Mo porphyry deposit. Within each soil pit, four subsamples were collected following recommended protocols for each of ten commonly-used and proprietary leach/digestion techniques. The significance of geochemical patterns generated by these techniques was classified by visual inspection of plots showing individual element concentration by each analytical method along the 2007 traverse. A simple matrix by element versus method, populated with a value based on the significance classification, provides a method for ranking the utility of methods and elements at this deposit. The interpretation of a complex multi-element dataset derived from multiple analytical techniques is challenging. An example of vanadium results from a single leach technique is used to illustrate the several possible interpretations of the data.

Investigation of environmental change pattern in Japan

NASA Technical Reports Server (NTRS)

Maruyasu, T.; Ochiai, H.; Sugimori, Y.; Shoji, D.; Takeda, K.; Tsuchiya, K.; Nakajima, I.; Nakano, T.; Hayashi, S.; Horikawa, S. (Principal Investigator)

1976-01-01

The author has identified the following significant results. A detailed land use classification for a large urban area of Tokyo was made using MSS digital data. It was found that residential, commercial, industrial, and wooded areas and grasslands can be successfully classified. A mesoscale vortex associated with large ocean current, Kuroshio, which is a rare phenomenon, was recognized visually through the analysis of MSS data. It was found that this vortex affects the effluent patterns of rivers. Lava flowing from Sakurajima Volcano was clearly classified for three major erruptions (1779, 1914, and 1946) using MSS data.

Visual rehabilitation: visual scanning, multisensory stimulation and vision restoration trainings

PubMed Central

Dundon, Neil M.; Bertini, Caterina; Làdavas, Elisabetta; Sabel, Bernhard A.; Gall, Carolin

2015-01-01

Neuropsychological training methods of visual rehabilitation for homonymous vision loss caused by postchiasmatic damage fall into two fundamental paradigms: “compensation” and “restoration”. Existing methods can be classified into three groups: Visual Scanning Training (VST), Audio-Visual Scanning Training (AViST) and Vision Restoration Training (VRT). VST and AViST aim at compensating vision loss by training eye scanning movements, whereas VRT aims at improving lost vision by activating residual visual functions by training light detection and discrimination of visual stimuli. This review discusses the rationale underlying these paradigms and summarizes the available evidence with respect to treatment efficacy. The issues raised in our review should help guide clinical care and stimulate new ideas for future research uncovering the underlying neural correlates of the different treatment paradigms. We propose that both local “within-system” interactions (i.e., relying on plasticity within peri-lesional spared tissue) and changes in more global “between-system” networks (i.e., recruiting alternative visual pathways) contribute to both vision restoration and compensatory rehabilitation, which ultimately have implications for the rehabilitation of cognitive functions. PMID:26283935

Simulation techniques for estimating error in the classification of normal patterns

NASA Technical Reports Server (NTRS)

Whitsitt, S. J.; Landgrebe, D. A.

1974-01-01

Methods of efficiently generating and classifying samples with specified multivariate normal distributions were discussed. Conservative confidence tables for sample sizes are given for selective sampling. Simulation results are compared with classified training data. Techniques for comparing error and separability measure for two normal patterns are investigated and used to display the relationship between the error and the Chernoff bound.

Determination of Minimum Training Sample Size for Microarray-Based Cancer Outcome Prediction–An Empirical Assessment

PubMed Central

Cheng, Ningtao; Wu, Leihong; Cheng, Yiyu

2013-01-01

The promise of microarray technology in providing prediction classifiers for cancer outcome estimation has been confirmed by a number of demonstrable successes. However, the reliability of prediction results relies heavily on the accuracy of statistical parameters involved in classifiers. It cannot be reliably estimated with only a small number of training samples. Therefore, it is of vital importance to determine the minimum number of training samples and to ensure the clinical value of microarrays in cancer outcome prediction. We evaluated the impact of training sample size on model performance extensively based on 3 large-scale cancer microarray datasets provided by the second phase of MicroArray Quality Control project (MAQC-II). An SSNR-based (scale of signal-to-noise ratio) protocol was proposed in this study for minimum training sample size determination. External validation results based on another 3 cancer datasets confirmed that the SSNR-based approach could not only determine the minimum number of training samples efficiently, but also provide a valuable strategy for estimating the underlying performance of classifiers in advance. Once translated into clinical routine applications, the SSNR-based protocol would provide great convenience in microarray-based cancer outcome prediction in improving classifier reliability. PMID:23861920

MRIQC: Advancing the automatic prediction of image quality in MRI from unseen sites

PubMed Central

2017-01-01

Quality control of MRI is essential for excluding problematic acquisitions and avoiding bias in subsequent image processing and analysis. Visual inspection is subjective and impractical for large scale datasets. Although automated quality assessments have been demonstrated on single-site datasets, it is unclear that solutions can generalize to unseen data acquired at new sites. Here, we introduce the MRI Quality Control tool (MRIQC), a tool for extracting quality measures and fitting a binary (accept/exclude) classifier. Our tool can be run both locally and as a free online service via the OpenNeuro.org portal. The classifier is trained on a publicly available, multi-site dataset (17 sites, N = 1102). We perform model selection evaluating different normalization and feature exclusion approaches aimed at maximizing across-site generalization and estimate an accuracy of 76%±13% on new sites, using leave-one-site-out cross-validation. We confirm that result on a held-out dataset (2 sites, N = 265) also obtaining a 76% accuracy. Even though the performance of the trained classifier is statistically above chance, we show that it is susceptible to site effects and unable to account for artifacts specific to new sites. MRIQC performs with high accuracy in intra-site prediction, but performance on unseen sites leaves space for improvement which might require more labeled data and new approaches to the between-site variability. Overcoming these limitations is crucial for a more objective quality assessment of neuroimaging data, and to enable the analysis of extremely large and multi-site samples. PMID:28945803

A BHR Composite Network-Based Visualization Method for Deformation Risk Level of Underground Space

PubMed Central

Zheng, Wei; Zhang, Xiaoya; Lu, Qi

2015-01-01

This study proposes a visualization processing method for the deformation risk level of underground space. The proposed method is based on a BP-Hopfield-RGB (BHR) composite network. Complex environmental factors are integrated in the BP neural network. Dynamic monitoring data are then automatically classified in the Hopfield network. The deformation risk level is combined with the RGB color space model and is displayed visually in real time, after which experiments are conducted with the use of an ultrasonic omnidirectional sensor device for structural deformation monitoring. The proposed method is also compared with some typical methods using a benchmark dataset. Results show that the BHR composite network visualizes the deformation monitoring process in real time and can dynamically indicate dangerous zones. PMID:26011618

Aggressive Bimodal Communication in Domestic Dogs, Canis familiaris

PubMed Central

Déaux, Éloïse C.; Clarke, Jennifer A.; Charrier, Isabelle

2015-01-01

Evidence of animal multimodal signalling is widespread and compelling. Dogs’ aggressive vocalisations (growls and barks) have been extensively studied, but without any consideration of the simultaneously produced visual displays. In this study we aimed to categorize dogs’ bimodal aggressive signals according to the redundant/non-redundant classification framework. We presented dogs with unimodal (audio or visual) or bimodal (audio-visual) stimuli and measured their gazing and motor behaviours. Responses did not qualitatively differ between the bimodal and two unimodal contexts, indicating that acoustic and visual signals provide redundant information. We could not further classify the signal as ‘equivalent’ or ‘enhancing’ as we found evidence for both subcategories. We discuss our findings in relation to the complex signal framework, and propose several hypotheses for this signal’s function. PMID:26571266

Similarity-dissimilarity plot for visualization of high dimensional data in biomedical pattern classification.

PubMed

Arif, Muhammad

2012-06-01

In pattern classification problems, feature extraction is an important step. Quality of features in discriminating different classes plays an important role in pattern classification problems. In real life, pattern classification may require high dimensional feature space and it is impossible to visualize the feature space if the dimension of feature space is greater than four. In this paper, we have proposed a Similarity-Dissimilarity plot which can project high dimensional space to a two dimensional space while retaining important characteristics required to assess the discrimination quality of the features. Similarity-dissimilarity plot can reveal information about the amount of overlap of features of different classes. Separable data points of different classes will also be visible on the plot which can be classified correctly using appropriate classifier. Hence, approximate classification accuracy can be predicted. Moreover, it is possible to know about whom class the misclassified data points will be confused by the classifier. Outlier data points can also be located on the similarity-dissimilarity plot. Various examples of synthetic data are used to highlight important characteristics of the proposed plot. Some real life examples from biomedical data are also used for the analysis. The proposed plot is independent of number of dimensions of the feature space.

Image visualization of hyperspectral spectrum for LWIR

NASA Astrophysics Data System (ADS)

Chong, Eugene; Jeong, Young-Su; Lee, Jai-Hoon; Park, Dong Jo; Kim, Ju Hyun

2015-07-01

The image visualization of a real-time hyperspectral spectrum in the long-wave infrared (LWIR) range of 900-1450 cm-1 by a color-matching function is addressed. It is well known that the absorption spectra of main toxic industrial chemical (TIC) and chemical warfare agent (CWA) clouds are detected in this spectral region. Furthermore, a significant spectral peak due to various background species and unknown targets are also present. However, those are dismissed as noise, resulting in utilization limit. Herein, we applied a color-matching function that uses the information from hyperspectral data, which is emitted from the materials and surfaces of artificial or natural backgrounds in the LWIR region. This information was used to classify and differentiate the background signals from the targeted substances, and the results were visualized as image data without additional visual equipment. The tristimulus value based visualization information can quickly identify the background species and target in real-time detection in LWIR.

Automatic classification of visual evoked potentials based on wavelet decomposition

NASA Astrophysics Data System (ADS)

Stasiakiewicz, Paweł; Dobrowolski, Andrzej P.; Tomczykiewicz, Kazimierz

2017-04-01

Diagnosis of part of the visual system, that is responsible for conducting compound action potential, is generally based on visual evoked potentials generated as a result of stimulation of the eye by external light source. The condition of patient's visual path is assessed by set of parameters that describe the time domain characteristic extremes called waves. The decision process is compound therefore diagnosis significantly depends on experience of a doctor. The authors developed a procedure - based on wavelet decomposition and linear discriminant analysis - that ensures automatic classification of visual evoked potentials. The algorithm enables to assign individual case to normal or pathological class. The proposed classifier has a 96,4% sensitivity at 10,4% probability of false alarm in a group of 220 cases and area under curve ROC equals to 0,96 which, from the medical point of view, is a very good result.

Predicting invertebrate assemblage composition from harvesting pressure and environmental characteristics on tropical reef flats

NASA Astrophysics Data System (ADS)

Jimenez, H.; Dumas, P.; Ponton, D.; Ferraris, J.

2012-03-01

Invertebrates represent an essential component of coral reef ecosystems; they are ecologically important and a major resource, but their assemblages remain largely unknown, particularly on Pacific islands. Understanding their distribution and building predictive models of community composition as a function of environmental variables therefore constitutes a key issue for resource management. The goal of this study was to define and classify the main environmental factors influencing tropical invertebrate distributions in New Caledonian reef flats and to test the resulting predictive model. Invertebrate assemblages were sampled by visual counting during 2 years and 2 seasons, then coupled to different environmental conditions (habitat composition, hydrodynamics and sediment characteristics) and harvesting status (MPA vs. non-MPA and islets vs. coastal flats). Environmental conditions were described by a principal component analysis (PCA), and contributing variables were selected. Permutational analysis of variance (PERMANOVA) was used to test the effects of different factors (status, flat, year and season) on the invertebrate assemblage composition. Multivariate regression trees (MRT) were then used to hierarchically classify the effects of environmental and harvesting variables. MRT model explained at least 60% of the variation in structure of invertebrate communities. Results highlighted the influence of status (MPA vs. non-MPA) and location (islet vs. coastal flat), followed by habitat composition, organic matter content, hydrodynamics and sampling year. Predicted assemblages defined by indicator families were very different for each environment-exploitation scenario and correctly matched a calibration data matrix. Predictions from MRT including both environmental variables and harvesting pressure can be useful for management of invertebrates in coral reef environments.

A novel modular ANN architecture for efficient monitoring of gases/odours in real-time

NASA Astrophysics Data System (ADS)

Mishra, A.; Rajput, N. S.

2018-04-01

Data pre-processing is tremendously used for enhanced classification of gases. However, it suppresses the concentration variances of different gas samples. A classical solution of using single artificial neural network (ANN) architecture is also inefficient and renders degraded quantification. In this paper, a novel modular ANN design has been proposed to provide an efficient and scalable solution in real–time. Here, two separate ANN blocks viz. classifier block and quantifier block have been used to provide efficient and scalable gas monitoring in real—time. The classifier ANN consists of two stages. In the first stage, the Net 1-NDSRT has been trained to transform raw sensor responses into corresponding virtual multi-sensor responses using normalized difference sensor response transformation (NDSRT). These responses have been fed to the second stage (i.e., Net 2-classifier ). The Net 2-classifier has been trained to classify various gas samples to their respective class. Further, the quantifier block has parallel ANN modules, multiplexed to quantify each gas. Therefore, the classifier ANN decides class and quantifier ANN decides the exact quantity of the gas/odor present in the respective sample of that class.

Active machine learning for rapid landslide inventory mapping with VHR satellite images (Invited)

NASA Astrophysics Data System (ADS)

Stumpf, A.; Lachiche, N.; Malet, J.; Kerle, N.; Puissant, A.

2013-12-01

VHR satellite images have become a primary source for landslide inventory mapping after major triggering events such as earthquakes and heavy rainfalls. Visual image interpretation is still the prevailing standard method for operational purposes but is time-consuming and not well suited to fully exploit the increasingly better supply of remote sensing data. Recent studies have addressed the development of more automated image analysis workflows for landslide inventory mapping. In particular object-oriented approaches that account for spatial and textural image information have been demonstrated to be more adequate than pixel-based classification but manually elaborated rule-based classifiers are difficult to adapt under changing scene characteristics. Machine learning algorithm allow learning classification rules for complex image patterns from labelled examples and can be adapted straightforwardly with available training data. In order to reduce the amount of costly training data active learning (AL) has evolved as a key concept to guide the sampling for many applications. The underlying idea of AL is to initialize a machine learning model with a small training set, and to subsequently exploit the model state and data structure to iteratively select the most valuable samples that should be labelled by the user. With relatively few queries and labelled samples, an AL strategy yields higher accuracies than an equivalent classifier trained with many randomly selected samples. This study addressed the development of an AL method for landslide mapping from VHR remote sensing images with special consideration of the spatial distribution of the samples. Our approach [1] is based on the Random Forest algorithm and considers the classifier uncertainty as well as the variance of potential sampling regions to guide the user towards the most valuable sampling areas. The algorithm explicitly searches for compact regions and thereby avoids a spatially disperse sampling pattern inherent to most other AL methods. The accuracy, the sampling time and the computational runtime of the algorithm were evaluated on multiple satellite images capturing recent large scale landslide events. Sampling between 1-4% of the study areas the accuracies between 74% and 80% were achieved, whereas standard sampling schemes yielded only accuracies between 28% and 50% with equal sampling costs. Compared to commonly used point-wise AL algorithm the proposed approach significantly reduces the number of iterations and hence the computational runtime. Since the user can focus on relatively few compact areas (rather than on hundreds of distributed points) the overall labeling time is reduced by more than 50% compared to point-wise queries. An experimental evaluation of multiple expert mappings demonstrated strong relationships between the uncertainties of the experts and the machine learning model. It revealed that the achieved accuracies are within the range of the inter-expert disagreement and that it will be indispensable to consider ground truth uncertainties to truly achieve further enhancements in the future. The proposed method is generally applicable to a wide range of optical satellite images and landslide types. [1] A. Stumpf, N. Lachiche, J.-P. Malet, N. Kerle, and A. Puissant, Active learning in the spatial domain for remote sensing image classification, IEEE Transactions on Geosciece and Remote Sensing. 2013, DOI 10.1109/TGRS.2013.2262052.

Effective Sequential Classifier Training for SVM-Based Multitemporal Remote Sensing Image Classification

NASA Astrophysics Data System (ADS)

Guo, Yiqing; Jia, Xiuping; Paull, David

2018-06-01

The explosive availability of remote sensing images has challenged supervised classification algorithms such as Support Vector Machines (SVM), as training samples tend to be highly limited due to the expensive and laborious task of ground truthing. The temporal correlation and spectral similarity between multitemporal images have opened up an opportunity to alleviate this problem. In this study, a SVM-based Sequential Classifier Training (SCT-SVM) approach is proposed for multitemporal remote sensing image classification. The approach leverages the classifiers of previous images to reduce the required number of training samples for the classifier training of an incoming image. For each incoming image, a rough classifier is firstly predicted based on the temporal trend of a set of previous classifiers. The predicted classifier is then fine-tuned into a more accurate position with current training samples. This approach can be applied progressively to sequential image data, with only a small number of training samples being required from each image. Experiments were conducted with Sentinel-2A multitemporal data over an agricultural area in Australia. Results showed that the proposed SCT-SVM achieved better classification accuracies compared with two state-of-the-art model transfer algorithms. When training data are insufficient, the overall classification accuracy of the incoming image was improved from 76.18% to 94.02% with the proposed SCT-SVM, compared with those obtained without the assistance from previous images. These results demonstrate that the leverage of a priori information from previous images can provide advantageous assistance for later images in multitemporal image classification.

Detection of meca gene from methicillin resistant staphylococcus aureus isolates of north sumatera

NASA Astrophysics Data System (ADS)

Septiani Nasution, Gabriella; Suryanto, Dwi; Lia Kusumawati, R.

2018-03-01

Methicillin Resistant Staphylococcus aureus (MRSA) is a major pathogen associated with hospital-acquired infections (nosocomial infections). MRSA is a type of S. aureus resistant to the sub-group of beta-lactam antibiotics such as penicillin, cephalosporin, monobactam, and carbapenem. MRSA is resistant because of genetic changes caused by exposure to irrational antibiotic therapy. This study aimed to detect mecA gene in North Sumatra isolates of MRSA and to determine the pattern of antibiotic resistance in S.aureus isolates classified as MRSA by Vitek 2 Compact in the Central Public Hospital Haji Adam Malik, Medan. Samples were 40 isolates of S. aureus classified as MRSA obtained from clinical microbiology specimens. DNA isolation of the isolates was conducted by a method of freeze-thaw cycling. Amplification of mecA gene was done by PCR technique using specific primer for the gene. PCR products were visualized using mini-gel electrophoresis. The results showed that all MRSA isolates showed to have 533 bp band of mecA. Antibiotics test of Vitek 2 Compact showed that despite all isolates were resistant to beta-lactam antibiotics groups; the isolates showed multidrug resistant to other common antibiotics, such as aminoglycosides, macrolides, and fluoroquinolones. However, they were still sensitive to vancomycin (82.5% isolates), linezolid (97.5% isolates), and tigecycline (100% isolates).

Social Behaviour of Captive Belugas, Delphinapterus Leucas.

NASA Astrophysics Data System (ADS)

Recchia, Cheri Anne

1994-01-01

Focal-animal sampling techniques developed for investigating social behaviour of terrestrial animals were adapted for studying captive belugas, providing quantitative descriptions of social relationships among individuals. Five groups of captive belugas were observed, allowing a cross -sectional view of sociality in groups of diverse sizes and compositions. Inter-individual distances were used to quantify patterns of spatial association. A set of social behaviours for which actor and recipient could be identified was defined to characterize dyadic interactions. The mother-calf pair spent more time together, and interacted more often than adults. The calf maintained proximity with his mother; larger adults generally maintained proximity with smaller adults. Among adults, larger groups performed more kinds of behaviours and interacted at higher rates than smaller groups. Within dyads, the larger whale performed more aggressive behaviours and the smaller whale more submissive behaviours. Clear dominance relations existed in three groups, with larger whales dominant to smaller whales. Vocalizations of three groups were classified subjectively, based on aural impressions and visual inspection of spectrograms, but most signals appeared graded. Statistical analyses of measured acoustic features confirmed subjective impressions that vocalizations could not be classified into discrete and homogeneous categories. (Copies available exclusively from MIT Libraries, Rm. 14-0551, Cambridge, MA 02139-4307. Ph. 617-553-5668; Fax 617-253-1690.).

The Use of UV-Visible Reflectance Spectroscopy as an Objective Tool to Evaluate Pearl Quality

PubMed Central

Agatonovic-Kustrin, Snezana; Morton, David W.

2012-01-01

Assessing the quality of pearls involves the use of various tools and methods, which are mainly visual and often quite subjective. Pearls are normally classified by origin and are then graded by luster, nacre thickness, surface quality, size, color and shape. The aim of this study was to investigate the capacity of Artificial Neural Networks (ANNs) to classify and estimate the quality of 27 different pearls from their UV-Visible spectra. Due to the opaque nature of pearls, spectroscopy measurements were performed using the Diffuse Reflectance UV-Visible spectroscopy technique. The spectra were acquired at two different locations on each pearl sample in order to assess surface homogeneity. The spectral data (inputs) were smoothed to reduce the noise, fed into ANNs and correlated to the pearl’s quality/grading criteria (outputs). The developed ANNs were successful in predicting pearl type, mollusk growing species, possible luster and color enhancing, donor condition/type, recipient/host color, donor color, pearl luster, pearl color, origin. The results of this study shows that the developed UV-Vis spectroscopy-ANN method could be used as a more objective method of assessing pearl quality (grading) and may become a valuable tool for the pearl grading industry. PMID:22851919

Molecular differential diagnosis of follicular thyroid carcinoma and adenoma based on gene expression profiling by using formalin-fixed paraffin-embedded tissues

PubMed Central

2013-01-01

Background Differential diagnosis between malignant follicular thyroid cancer (FTC) and benign follicular thyroid adenoma (FTA) is a great challenge for even an experienced pathologist and requires special effort. Molecular markers may potentially support a differential diagnosis between FTC and FTA in postoperative specimens. The purpose of this study was to derive molecular support for differential post-operative diagnosis, in the form of a simple multigene mRNA-based classifier that would differentiate between FTC and FTA tissue samples. Methods A molecular classifier was created based on a combined analysis of two microarray datasets (using 66 thyroid samples). The performance of the classifier was assessed using an independent dataset comprising 71 formalin-fixed paraffin-embedded (FFPE) samples (31 FTC and 40 FTA), which were analysed by quantitative real-time PCR (qPCR). In addition, three other microarray datasets (62 samples) were used to confirm the utility of the classifier. Results Five of 8 genes selected from training datasets (ELMO1, EMCN, ITIH5, KCNAB1, SLCO2A1) were amplified by qPCR in FFPE material from an independent sample set. Three other genes did not amplify in FFPE material, probably due to low abundance. All 5 analysed genes were downregulated in FTC compared to FTA. The sensitivity and specificity of the 5-gene classifier tested on the FFPE dataset were 71% and 72%, respectively. Conclusions The proposed approach could support histopathological examination: 5-gene classifier may aid in molecular discrimination between FTC and FTA in FFPE material. PMID:24099521

Expert consensus statement to guide the evidence-based classification of Paralympic athletes with vision impairment: a Delphi study.

PubMed

Ravensbergen, H J C Rianne; Mann, D L; Kamper, S J

2016-04-01

Paralympic sports are required to develop evidence-based systems that allocate athletes into 'classes' on the basis of the impact of their impairment on sport performance. However, sports for athletes with vision impairment (VI) classify athletes solely based on the WHO criteria for low vision and blindness. One key barrier to evidence-based classification is the absence of guidance on how to address classification issues unique to VI sport. The aim of this study was to reach expert consensus on how issues specific to VI sport should be addressed in evidence-based classification. A four-round Delphi study was conducted with 25 participants who had expertise as a coach, athlete, classifier and/or administrator in Paralympic sport for VI athletes. The experts agreed that the current method of classification does not fulfil the requirements of Paralympic classification, and that the system should be different for each sport to account for the sports' unique visual demands. Instead of relying only on tests of visual acuity and visual field, the panel agreed that additional tests are required to better account for the impact of impairment on sport performance. There was strong agreement that all athletes should not be required to wear a blindfold as a means of equalising the impairment during competition. There is strong support within the Paralympic movement to change the way that VI athletes are classified. This consensus statement provides clear guidance on how the most important issues specific to VI should be addressed, removing key barriers to the development of evidence-based classification. Published by the BMJ Publishing Group Limited. For permission to use (where not already granted under a licence) please go to http://www.bmj.com/company/products-services/rights-and-licensing/

The method for detecting small lesions in medical image based on sliding window

NASA Astrophysics Data System (ADS)

Han, Guilai; Jiao, Yuan

2016-10-01

At present, the research on computer-aided diagnosis includes the sample image segmentation, extracting visual features, generating the classification model by learning, and according to the model generated to classify and judge the inspected images. However, this method has a large scale of calculation and speed is slow. And because medical images are usually low contrast, when the traditional image segmentation method is applied to the medical image, there is a complete failure. As soon as possible to find the region of interest, improve detection speed, this topic attempts to introduce the current popular visual attention model into small lesions detection. However, Itti model is mainly for natural images. But the effect is not ideal when it is used to medical images which usually are gray images. Especially in the early stages of some cancers, the focus of a disease in the whole image is not the most significant region and sometimes is very difficult to be found. But these lesions are prominent in the local areas. This paper proposes a visual attention mechanism based on sliding window, and use sliding window to calculate the significance of a local area. Combined with the characteristics of the lesion, select the features of gray, entropy, corner and edge to generate a saliency map. Then the significant region is segmented and distinguished. This method reduces the difficulty of image segmentation, and improves the detection accuracy of small lesions, and it has great significance to early discovery, early diagnosis and treatment of cancers.

Decoding and reconstructing color from responses in human visual cortex.

PubMed

Brouwer, Gijs Joost; Heeger, David J

2009-11-04

How is color represented by spatially distributed patterns of activity in visual cortex? Functional magnetic resonance imaging responses to several stimulus colors were analyzed with multivariate techniques: conventional pattern classification, a forward model of idealized color tuning, and principal component analysis (PCA). Stimulus color was accurately decoded from activity in V1, V2, V3, V4, and VO1 but not LO1, LO2, V3A/B, or MT+. The conventional classifier and forward model yielded similar accuracies, but the forward model (unlike the classifier) also reliably reconstructed novel stimulus colors not used to train (specify parameters of) the model. The mean responses, averaged across voxels in each visual area, were not reliably distinguishable for the different stimulus colors. Hence, each stimulus color was associated with a unique spatially distributed pattern of activity, presumably reflecting the color selectivity of cortical neurons. Using PCA, a color space was derived from the covariation, across voxels, in the responses to different colors. In V4 and VO1, the first two principal component scores (main source of variation) of the responses revealed a progression through perceptual color space, with perceptually similar colors evoking the most similar responses. This was not the case for any of the other visual cortical areas, including V1, although decoding was most accurate in V1. This dissociation implies a transformation from the color representation in V1 to reflect perceptual color space in V4 and VO1.

Prevalence and causes of blindness in an urban area of Paraguay.

PubMed

Yaacov-Peña, Fernando; Jure, David; Ocampos, José; Samudio, Margarita; Furtado, João Marcello; Carter, Marissa; Lansingh, Van Charles

2012-10-01

To determine the prevalence and causes of blindness in Piribebuy, Paraguay. A population based study was conducted from September to November 2007 in Piribebuy, Paraguay. Based on the city map, seven clusters were randomly selected, containing 22 to 36 squares (423 to 578 houses) each, where all subjects > 40 years old who agreed to participate were included in the study. Presenting vision acuity (VA) was obtained for each eye, with 'E' Snellen charts 6 meters far from the patient with appropriate light. Eyes with VA<20/60 were also tested with the pinhole. Objective and subjective refraction was performed, followed by examination of anterior segment under the slit-lamp, Goldmann applanation tonometry, and pupil dilatation with 0.5% tropicamide plus 0.5% phenylephrine, followed by evaluation of the posterior pole. Best corrected visual acuity was used to classify the patients as follows: blindness was defined as visual acuity of the better eye <20/400, low vision as 20/400

WHIDE—a web tool for visual data mining colocation patterns in multivariate bioimages

PubMed Central

Kölling, Jan; Langenkämper, Daniel; Abouna, Sylvie; Khan, Michael; Nattkemper, Tim W.

2012-01-01

Motivation: Bioimaging techniques rapidly develop toward higher resolution and dimension. The increase in dimension is achieved by different techniques such as multitag fluorescence imaging, Matrix Assisted Laser Desorption / Ionization (MALDI) imaging or Raman imaging, which record for each pixel an N-dimensional intensity array, representing local abundances of molecules, residues or interaction patterns. The analysis of such multivariate bioimages (MBIs) calls for new approaches to support users in the analysis of both feature domains: space (i.e. sample morphology) and molecular colocation or interaction. In this article, we present our approach WHIDE (Web-based Hyperbolic Image Data Explorer) that combines principles from computational learning, dimension reduction and visualization in a free web application. Results: We applied WHIDE to a set of MBI recorded using the multitag fluorescence imaging Toponome Imaging System. The MBI show field of view in tissue sections from a colon cancer study and we compare tissue from normal/healthy colon with tissue classified as tumor. Our results show, that WHIDE efficiently reduces the complexity of the data by mapping each of the pixels to a cluster, referred to as Molecular Co-Expression Phenotypes and provides a structural basis for a sophisticated multimodal visualization, which combines topology preserving pseudocoloring with information visualization. The wide range of WHIDE's applicability is demonstrated with examples from toponome imaging, high content screens and MALDI imaging (shown in the Supplementary Material). Availability and implementation: The WHIDE tool can be accessed via the BioIMAX website http://ani.cebitec.uni-bielefeld.de/BioIMAX/; Login: whidetestuser; Password: whidetest. Supplementary information: Supplementary data are available at Bioinformatics online. Contact: tim.nattkemper@uni-bielefeld.de PMID:22390938

A Kinect-Based Real-Time Compressive Tracking Prototype System for Amphibious Spherical Robots

PubMed Central

Pan, Shaowu; Shi, Liwei; Guo, Shuxiang

2015-01-01

A visual tracking system is essential as a basis for visual servoing, autonomous navigation, path planning, robot-human interaction and other robotic functions. To execute various tasks in diverse and ever-changing environments, a mobile robot requires high levels of robustness, precision, environmental adaptability and real-time performance of the visual tracking system. In keeping with the application characteristics of our amphibious spherical robot, which was proposed for flexible and economical underwater exploration in 2012, an improved RGB-D visual tracking algorithm is proposed and implemented. Given the limited power source and computational capabilities of mobile robots, compressive tracking (CT), which is the effective and efficient algorithm that was proposed in 2012, was selected as the basis of the proposed algorithm to process colour images. A Kalman filter with a second-order motion model was implemented to predict the state of the target and select candidate patches or samples for the CT tracker. In addition, a variance ratio features shift (VR-V) tracker with a Kalman estimation mechanism was used to process depth images. Using a feedback strategy, the depth tracking results were used to assist the CT tracker in updating classifier parameters at an adaptive rate. In this way, most of the deficiencies of CT, including drift and poor robustness to occlusion and high-speed target motion, were partly solved. To evaluate the proposed algorithm, a Microsoft Kinect sensor, which combines colour and infrared depth cameras, was adopted for use in a prototype of the robotic tracking system. The experimental results with various image sequences demonstrated the effectiveness, robustness and real-time performance of the tracking system. PMID:25856331

A Kinect-based real-time compressive tracking prototype system for amphibious spherical robots.

PubMed

Pan, Shaowu; Shi, Liwei; Guo, Shuxiang

2015-04-08

A visual tracking system is essential as a basis for visual servoing, autonomous navigation, path planning, robot-human interaction and other robotic functions. To execute various tasks in diverse and ever-changing environments, a mobile robot requires high levels of robustness, precision, environmental adaptability and real-time performance of the visual tracking system. In keeping with the application characteristics of our amphibious spherical robot, which was proposed for flexible and economical underwater exploration in 2012, an improved RGB-D visual tracking algorithm is proposed and implemented. Given the limited power source and computational capabilities of mobile robots, compressive tracking (CT), which is the effective and efficient algorithm that was proposed in 2012, was selected as the basis of the proposed algorithm to process colour images. A Kalman filter with a second-order motion model was implemented to predict the state of the target and select candidate patches or samples for the CT tracker. In addition, a variance ratio features shift (VR-V) tracker with a Kalman estimation mechanism was used to process depth images. Using a feedback strategy, the depth tracking results were used to assist the CT tracker in updating classifier parameters at an adaptive rate. In this way, most of the deficiencies of CT, including drift and poor robustness to occlusion and high-speed target motion, were partly solved. To evaluate the proposed algorithm, a Microsoft Kinect sensor, which combines colour and infrared depth cameras, was adopted for use in a prototype of the robotic tracking system. The experimental results with various image sequences demonstrated the effectiveness, robustness and real-time performance of the tracking system.

Methodology for cork plank characterization (Quercus suber L.) by near-infrared spectroscopy and image analysis

NASA Astrophysics Data System (ADS)

Prades, Cristina; García-Olmo, Juan; Romero-Prieto, Tomás; García de Ceca, José L.; López-Luque, Rafael

2010-06-01

The procedures used today to characterize cork plank for the manufacture of cork bottle stoppers continue to be based on a traditional, manual method that is highly subjective. Furthermore, there is no specific legislation regarding cork classification. The objective of this viability study is to assess the potential of near-infrared spectroscopy (NIRS) technology for characterizing cork plank according to the following variables: aspect or visual quality, porosity, moisture and geographical origin. In order to calculate the porosity coefficient, an image analysis program was specifically developed in Visual Basic language for a desktop scanner. A set comprising 170 samples from two geographical areas of Andalusia (Spain) was classified into eight quality classes by visual inspection. Spectra were obtained in the transverse and tangential sections of the cork planks using an NIRSystems 6500 SY II reflectance spectrophotometer. The quantitative calibrations showed cross-validation coefficients of determination of 0.47 for visual quality, 0.69 for porosity and 0.66 for moisture. The results obtained using NIRS technology are promising considering the heterogeneity and variability of a natural product such as cork in spite of the fact that the standard error of cross validation (SECV) in the quantitative analysis is greater than the standard error of laboratory (SEL) for the three variables. The qualitative analysis regarding geographical origin achieved very satisfactory results. Applying these methods in industry will permit quality control procedures to be automated, as well as establishing correlations between the different classification systems currently used in the sector. These methods can be implemented in the cork chain of custody certification and will also provide a certainly more objective tool for assessing the economic value of the product.

Neuronal responses to face-like stimuli in the monkey pulvinar.

PubMed

Nguyen, Minh Nui; Hori, Etsuro; Matsumoto, Jumpei; Tran, Anh Hai; Ono, Taketoshi; Nishijo, Hisao

2013-01-01

The pulvinar nuclei appear to function as the subcortical visual pathway that bypasses the striate cortex, rapidly processing coarse facial information. We investigated responses from monkey pulvinar neurons during a delayed non-matching-to-sample task, in which monkeys were required to discriminate five categories of visual stimuli [photos of faces with different gaze directions, line drawings of faces, face-like patterns (three dark blobs on a bright oval), eye-like patterns and simple geometric patterns]. Of 401 neurons recorded, 165 neurons responded differentially to the visual stimuli. These visual responses were suppressed by scrambling the images. Although these neurons exhibited a broad response latency distribution, face-like patterns elicited responses with the shortest latencies (approximately 50 ms). Multidimensional scaling analysis indicated that the pulvinar neurons could specifically encode face-like patterns during the first 50-ms period after stimulus onset and classify the stimuli into one of the five different categories during the next 50-ms period. The amount of stimulus information conveyed by the pulvinar neurons and the number of stimulus-differentiating neurons were consistently higher during the second 50-ms period than during the first 50-ms period. These results suggest that responsiveness to face-like patterns during the first 50-ms period might be attributed to ascending inputs from the superior colliculus or the retina, while responsiveness to the five different stimulus categories during the second 50-ms period might be mediated by descending inputs from cortical regions. These findings provide neurophysiological evidence for pulvinar involvement in social cognition and, specifically, rapid coarse facial information processing. © 2012 Federation of European Neuroscience Societies and Blackwell Publishing Ltd.

Prevalence and Visual Outcomes of Cataract Surgery in Rural South India: A Cross-Sectional Study.

PubMed

Paul, P; Kuriakose, T; John, J; Raju, R; George, K; Amritanand, A; Doss, P A; Muliyil, J

2016-10-01

To determine the prevalence of cataract surgery and postoperative vision-related outcomes, especially with respect to sex, socioeconomic status (SES) and site of first contact with eye care, in a rural area of South India. In a population-based cross-sectional survey of 5530 individuals aged 50 years or older from 10 villages selected by cluster sampling, individuals who had undergone cataract surgery in one or both eyes were identified. Consenting participants were administered a questionnaire, underwent vision assessment and ophthalmic examination. Outcomes were classified as good if visual acuity of the operated eye was 6/18 or better, fair if worse than 6/18 but better than or equal to 6/60, and poor if worse than 6/60. Prevalence of cataract surgery in this age group (771 persons) was 13.9% (95% confidence interval, CI, 13.0-14.9%). In the 1112 eyes of 749 persons studied, at presentation, 53.1% (95% CI 50.1-56.1%) of operated eyes had good, 38.1% (95% CI 35.2-41.0%) had fair, and 8.8% (95% CI 7.1-10.5%) had poor outcomes. With pinhole, 75.2% (95% CI 72.6-77.8%) had good, 17.2% (95% CI 14.9-19.5%) had fair, and 7.4% (95% CI 5.8-9.0%) had poor outcomes. In 76.3% of eyes with fair and poor presenting outcomes we detected an avoidable cause for the suboptimal visual acuity. Place of surgery and duration since surgery of 3 years or more were risk factors for blindness, while SES, sex and site of first eye care contact were not. The high prevalence of avoidable causes of visual impairment in this rural setting indicates the scope for preventive strategies.

Morphology and Structures of Nearby Dwarf Galaxies

NASA Astrophysics Data System (ADS)

Seo, Mira; Ann, HongBae

2015-08-01

We performed an analysis of the structure of nearby dwarf galaxies based on a 2-dimensional decomposition of galaxy images using GALFIT. The present sample consists of ~1,100 dwarf galaxies with redshift less than z = 0.01, which is is derived from the morphology catalog of the Visually classified galaxies in the local universe (Ann, Seo, and Ha 2015). In this catalog, dwarf galaxies are divided into 5 subtypes: dS0, dE, dSph, dEbc, dEblue with distinction of the presence of nucleation in dE, dSph, and dS0. We found that dSph and dEblue galaxies are fainter than other subtypes of dwarf galaxies. In most cases, single component, represented by the Sersic profile with n=1~1.5, well describes the luminosity distribution of dwarf galaxies in the present sample. However, a significant fraction of dS0, dEbc, and dEbue galaxies show sub-structures such as spiral arms and rings. We will discuss the morphology dependent evolutionary history of the local dwarf galaxies.

A SPECTROSCOPIC SURVEY OF MASSIVE STARS IN M31 AND M33

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

Massey, Philip; Neugent, Kathryn F.; Smart, Brianna M., E-mail: phil.massey@lowell.edu, E-mail: kneugent@lowell.edu, E-mail: bsmart@astro.wisc.edu

We describe our spectroscopic follow-up to the Local Group Galaxy Survey (LGGS) photometry of M31 and M33. We have obtained new spectroscopy of 1895 stars, allowing us to classify 1496 of them for the first time. Our study has identified many foreground stars, and established membership for hundreds of early- and mid-type supergiants. We have also found nine new candidate luminous blue variables and a previously unrecognized Wolf–Rayet star. We republish the LGGS M31 and M33 catalogs with improved coordinates, and including spectroscopy from the literature and our new results. The spectroscopy in this paper is responsible for the vastmore » majority of the stellar classifications in these two nearby spiral neighbors. The most luminous (and hence massive) of the stars in our sample are early-type B supergiants, as expected; the more massive O stars are more rare and fainter visually, and thus mostly remain unobserved so far. The majority of the unevolved stars in our sample are in the 20–40 M {sub ⊙} range.« less

Galaxy Zoo: Infrared and Optical Morphology

NASA Astrophysics Data System (ADS)

Carla Shanahan, Jesse; Lintott, Chris; Zoo, Galaxy

2018-01-01

We present the detailed, visual morphologies of approximately 60,000 galaxies observed by the UKIRT Infrared Deep Sky Survey and then classified by participants in the Galaxy Zoo project. Our sample is composed entirely of nearby objects with redshifts of z ≤ 0.3, which enables us to robustly analyze their morphological characteristics including smoothness, bulge properties, spiral structure, and evidence of bars or rings. The determination of these features is made via a consensus-based analysis of the Galaxy Zoo project data in which inconsistent and outlying classifications are statistically down-weighted. We then compare these classifications of infrared morphology to the objects’ optical classifications in the Galaxy Zoo 2 release (Willett et al. 2013). It is already known that morphology is an effective tool for uncovering a galaxy’s dynamical past, and previous studies have shown significant correlations with physical characteristics such as stellar mass distribution and star formation history. We show that majority of the sample has agreement or expected differences between the optical and infrared classifications, but also present a preliminary analysis of a subsample of objects with striking discrepancies.

Optimal spatiotemporal representation of multichannel EEG for recognition of brain states associated with distinct visual stimulus

NASA Astrophysics Data System (ADS)

Hramov, Alexander; Musatov, Vyacheslav Yu.; Runnova, Anastasija E.; Efremova, Tatiana Yu.; Koronovskii, Alexey A.; Pisarchik, Alexander N.

2018-04-01

In the paper we propose an approach based on artificial neural networks for recognition of different human brain states associated with distinct visual stimulus. Based on the developed numerical technique and the analysis of obtained experimental multichannel EEG data, we optimize the spatiotemporal representation of multichannel EEG to provide close to 97% accuracy in recognition of the EEG brain states during visual perception. Different interpretations of an ambiguous image produce different oscillatory patterns in the human EEG with similar features for every interpretation. Since these features are inherent to all subjects, a single artificial network can classify with high quality the associated brain states of other subjects.

Web accessibility support for visually impaired users using link content analysis.

PubMed

Iwata, Hajime; Kobayashi, Naofumi; Tachibana, Kenji; Shirogane, Junko; Fukazawa, Yoshiaki

2013-12-01

Web pages are used for a variety of purposes. End users must understand dynamically changing content and sequentially follow page links to find desired material, requiring significant time and effort. However, for visually impaired users using screen readers, it can be difficult to find links to web pages when link text and alternative text descriptions are inappropriate. Our method supports the discovery of content by analyzing 8 categories of link types, and allows visually impaired users to be aware of the content represented by links in advance. This facilitates end users access to necessary information on web pages. Our method of classifying web page links is therefore effective as a means of evaluating accessibility.

A blood-based proteomic classifier for the molecular characterization of pulmonary nodules.

PubMed

Li, Xiao-jun; Hayward, Clive; Fong, Pui-Yee; Dominguez, Michel; Hunsucker, Stephen W; Lee, Lik Wee; McLean, Matthew; Law, Scott; Butler, Heather; Schirm, Michael; Gingras, Olivier; Lamontagne, Julie; Allard, Rene; Chelsky, Daniel; Price, Nathan D; Lam, Stephen; Massion, Pierre P; Pass, Harvey; Rom, William N; Vachani, Anil; Fang, Kenneth C; Hood, Leroy; Kearney, Paul

2013-10-16

Each year, millions of pulmonary nodules are discovered by computed tomography and subsequently biopsied. Because most of these nodules are benign, many patients undergo unnecessary and costly invasive procedures. We present a 13-protein blood-based classifier that differentiates malignant and benign nodules with high confidence, thereby providing a diagnostic tool to avoid invasive biopsy on benign nodules. Using a systems biology strategy, we identified 371 protein candidates and developed a multiple reaction monitoring (MRM) assay for each. The MRM assays were applied in a three-site discovery study (n = 143) on plasma samples from patients with benign and stage IA lung cancer matched for nodule size, age, gender, and clinical site, producing a 13-protein classifier. The classifier was validated on an independent set of plasma samples (n = 104), exhibiting a negative predictive value (NPV) of 90%. Validation performance on samples from a nondiscovery clinical site showed an NPV of 94%, indicating the general effectiveness of the classifier. A pathway analysis demonstrated that the classifier proteins are likely modulated by a few transcription regulators (NF2L2, AHR, MYC, and FOS) that are associated with lung cancer, lung inflammation, and oxidative stress networks. The classifier score was independent of patient nodule size, smoking history, and age, which are risk factors used for clinical management of pulmonary nodules. Thus, this molecular test provides a potential complementary tool to help physicians in lung cancer diagnosis.

Relationship between socioeconomic deprivation 
or urban/rural residence and visual acuity before cataract surgery in Northern Scotland.

PubMed

Chua, Paul Y; Mustafa, Mohammed S; Scott, Neil W; Kumarasamy, Manjula; Azuara-Blanco, Augusto

2013-01-01

To evaluate the influence of socioeconomic factors on visual acuity before cataract surgery. 
 The medical case notes of 240 consecutive patients listed for cataract surgery from January 1, 2010, at Grampian University Hospital, Aberdeen, were reviewed retrospectively. Patients with ocular comorbidity were excluded. Demographics, postal codes, and visual acuity were recorded. Scottish Index of Multiple Deprivation was used to determine the deprivation rank. Home location was classified as urban or rural. The effect of these parameters on preoperative visual acuity was investigated using chi-square tests or Fisher exact test as appropriate. 
 A total of 184 patients (mean 75 years) were included. A total of 127 (69%) patients had visual acuity of 6/12 or better. An association was found between affluence and preoperative visual acuity of 6/12 or better (χ2trend = 4.97, p = 0.03), with a significant rising trend across quintile of deprivation. There was no evidence to suggest association between geographical region and preoperative visual acuity (p = 0.63). 
 Affluence was associated with good visual acuity (6/12 or better) before cataract surgery. There was no difference in preoperative visual acuity between rural and urban populations.

Feature genes in metastatic breast cancer identified by MetaDE and SVM classifier methods.

PubMed

Tuo, Youlin; An, Ning; Zhang, Ming

2018-03-01

The aim of the present study was to investigate the feature genes in metastatic breast cancer samples. A total of 5 expression profiles of metastatic breast cancer samples were downloaded from the Gene Expression Omnibus database, which were then analyzed using the MetaQC and MetaDE packages in R language. The feature genes between metastasis and non‑metastasis samples were screened under the threshold of P<0.05. Based on the protein‑protein interactions (PPIs) in the Biological General Repository for Interaction Datasets, Human Protein Reference Database and Biomolecular Interaction Network Database, the PPI network of the feature genes was constructed. The feature genes identified by topological characteristics were then used for support vector machine (SVM) classifier training and verification. The accuracy of the SVM classifier was then evaluated using another independent dataset from The Cancer Genome Atlas database. Finally, function and pathway enrichment analyses for genes in the SVM classifier were performed. A total of 541 feature genes were identified between metastatic and non‑metastatic samples. The top 10 genes with the highest betweenness centrality values in the PPI network of feature genes were Nuclear RNA Export Factor 1, cyclin‑dependent kinase 2 (CDK2), myelocytomatosis proto‑oncogene protein (MYC), Cullin 5, SHC Adaptor Protein 1, Clathrin heavy chain, Nucleolin, WD repeat domain 1, proteasome 26S subunit non‑ATPase 2 and telomeric repeat binding factor 2. The cyclin‑dependent kinase inhibitor 1A (CDKN1A), E2F transcription factor 1 (E2F1), and MYC interacted with CDK2. The SVM classifier constructed by the top 30 feature genes was able to distinguish metastatic samples from non‑metastatic samples [correct rate, specificity, positive predictive value and negative predictive value >0.89; sensitivity >0.84; area under the receiver operating characteristic curve (AUROC) >0.96]. The verification of the SVM classifier in an independent dataset (35 metastatic samples and 143 non‑metastatic samples) revealed an accuracy of 94.38% and AUROC of 0.958. Cell cycle associated functions and pathways were the most significant terms of the 30 feature genes. A SVM classifier was constructed to assess the possibility of breast cancer metastasis, which presented high accuracy in several independent datasets. CDK2, CDKN1A, E2F1 and MYC were indicated as the potential feature genes in metastatic breast cancer.

Model-based analysis of pattern motion processing in mouse primary visual cortex

PubMed Central

Muir, Dylan R.; Roth, Morgane M.; Helmchen, Fritjof; Kampa, Björn M.

2015-01-01

Neurons in sensory areas of neocortex exhibit responses tuned to specific features of the environment. In visual cortex, information about features such as edges or textures with particular orientations must be integrated to recognize a visual scene or object. Connectivity studies in rodent cortex have revealed that neurons make specific connections within sub-networks sharing common input tuning. In principle, this sub-network architecture enables local cortical circuits to integrate sensory information. However, whether feature integration indeed occurs locally in rodent primary sensory areas has not been examined directly. We studied local integration of sensory features in primary visual cortex (V1) of the mouse by presenting drifting grating and plaid stimuli, while recording the activity of neuronal populations with two-photon calcium imaging. Using a Bayesian model-based analysis framework, we classified single-cell responses as being selective for either individual grating components or for moving plaid patterns. Rather than relying on trial-averaged responses, our model-based framework takes into account single-trial responses and can easily be extended to consider any number of arbitrary predictive models. Our analysis method was able to successfully classify significantly more responses than traditional partial correlation (PC) analysis, and provides a rigorous statistical framework to rank any number of models and reject poorly performing models. We also found a large proportion of cells that respond strongly to only one stimulus class. In addition, a quarter of selectively responding neurons had more complex responses that could not be explained by any simple integration model. Our results show that a broad range of pattern integration processes already take place at the level of V1. This diversity of integration is consistent with processing of visual inputs by local sub-networks within V1 that are tuned to combinations of sensory features. PMID:26300738

Near visual acuity for everyday activities with accommodative and monofocal intraocular lenses.

PubMed

Sanders, Donald R; Sanders, Monica L

2007-10-01

To determine the levels of functional near visual acuity required for everyday social reading activities and to compare the levels to those attained with accommodative and monofocal intraocular lenses (LOLs). Font size equivalencies of an Early Treatment Diabetic Retinopathy Study near chart and a variety of commonly read print objects were determined and correlated to the findings of distance-corrected near vision measurements with 2 accommodative (Tetraflex, 1CU) and 1 monofocal (Acrysof MA30) IOLs. The smallest print objects studied were sweetener packets with type between 20/40 (Jaeger [J] 5) and 20/50 (J6). Type in classified ads, stock quotations, and pocket bibles was 20/50 (J6), type in a telephone directory was 20/63 (J8), and type in standard newspapers, journals, and magazines was 20/80 (J9). Tested monocularly, 88% of Tetraflex, 40% of ICU, and 7% of Acrysof MA30 eyes had distance-corrected near vision sufficient to read newspaper and telephone directory print, and 63% of Tetraflex, 30% of 1CU, and 0% of Acrysof MA30 eyes could read classified ads, stock quotations, and pocket bibles, respectively. Tested binocularly after bilateral implantation, 96% of Tetraflex patients could read telephone directory print and 89% could read ads, stock quotations, and pocket bibles. Functional near visual acuity is not equivalent to the bottom-line objective at 20/20 (J1) near visual acuity. No print size was found at or smaller than 20/40 (J5), indicating that a requirement of nearly perfect near visual acuity, while desirable, may not be necessary for patients' social reading needs for accommodative IOLs.

Verbal Dominant Memory Impairment and Low Risk for Post-operative Memory Worsening in Both Left and Right Temporal Lobe Epilepsy Associated with Hippocampal Sclerosis.

PubMed

Khalil, Amr Farid; Iwasaki, Masaki; Nishio, Yoshiyuki; Jin, Kazutaka; Nakasato, Nobukazu; Tominaga, Teiji

2016-11-15

Post-operative memory changes after temporal lobe surgery have been established mainly by group analysis of cognitive outcome. This study investigated individual patient-based memory outcome in surgically-treated patients with mesial temporal lobe epilepsy (TLE). This study included 84 consecutive patients with intractable TLE caused by unilateral hippocampal sclerosis (HS) who underwent epilepsy surgery (47 females, 41 left [Lt] TLE). Memory functions were evaluated with the Wechsler Memory Scale-Revised before and at 1 year after surgery. Pre-operative memory function was classified into three patterns: verbal dominant memory impairment (Verb-D), visual dominant impairment (Vis-D), and no material-specific impairment. Post-operative changes in verbal and visual memory indices were classified into meaningful improvement, worsening, or no significant changes. Pre-operative patterns and post-operative changes in verbal and visual memory function were compared between the Lt and right (Rt) TLE groups. Pre-operatively, Verb-D was the most common type of impairment in both the Lt and Rt TLE groups (65.9 and 48.8%), and verbal memory indices were lower than visual memory indices, especially in the Lt compared with Rt TLE group. Vis-D was observed only in 11.6% of Rt and 7.3% of Lt TLE patients. Post-operatively, meaningful improvement of memory indices was observed in 23.3-36.6% of the patients, and the memory improvement was equivalent between Lt and Rt TLE groups and between verbal and visual materials. In conclusion, Verb-D is most commonly observed in patients with both the Lt and Rt TLE associated with HS. Hippocampectomy can improve memory indices in such patients regardless of the side of surgery and the function impaired.

Visual Processing in Rapid-Chase Systems: Image Processing, Attention, and Awareness

PubMed Central

Schmidt, Thomas; Haberkamp, Anke; Veltkamp, G. Marina; Weber, Andreas; Seydell-Greenwald, Anna; Schmidt, Filipp

2011-01-01

Visual stimuli can be classified so rapidly that their analysis may be based on a single sweep of feedforward processing through the visuomotor system. Behavioral criteria for feedforward processing can be evaluated in response priming tasks where speeded pointing or keypress responses are performed toward target stimuli which are preceded by prime stimuli. We apply this method to several classes of complex stimuli. (1) When participants classify natural images into animals or non-animals, the time course of their pointing responses indicates that prime and target signals remain strictly sequential throughout all processing stages, meeting stringent behavioral criteria for feedforward processing (rapid-chase criteria). (2) Such priming effects are boosted by selective visual attention for positions, shapes, and colors, in a way consistent with bottom-up enhancement of visuomotor processing, even when primes cannot be consciously identified. (3) Speeded processing of phobic images is observed in participants specifically fearful of spiders or snakes, suggesting enhancement of feedforward processing by long-term perceptual learning. (4) When the perceived brightness of primes in complex displays is altered by means of illumination or transparency illusions, priming effects in speeded keypress responses can systematically contradict subjective brightness judgments, such that one prime appears brighter than the other but activates motor responses as if it was darker. We propose that response priming captures the output of the first feedforward pass of visual signals through the visuomotor system, and that this output lacks some characteristic features of more elaborate, recurrent processing. This way, visuomotor measures may become dissociated from several aspects of conscious vision. We argue that “fast” visuomotor measures predominantly driven by feedforward processing should supplement “slow” psychophysical measures predominantly based on visual awareness. PMID:21811484

Temporal lobe epilepsy: quantitative MR volumetry in detection of hippocampal atrophy.

PubMed

Farid, Nikdokht; Girard, Holly M; Kemmotsu, Nobuko; Smith, Michael E; Magda, Sebastian W; Lim, Wei Y; Lee, Roland R; McDonald, Carrie R

2012-08-01

To determine the ability of fully automated volumetric magnetic resonance (MR) imaging to depict hippocampal atrophy (HA) and to help correctly lateralize the seizure focus in patients with temporal lobe epilepsy (TLE). This study was conducted with institutional review board approval and in compliance with HIPAA regulations. Volumetric MR imaging data were analyzed for 34 patients with TLE and 116 control subjects. Structural volumes were calculated by using U.S. Food and Drug Administration-cleared software for automated quantitative MR imaging analysis (NeuroQuant). Results of quantitative MR imaging were compared with visual detection of atrophy, and, when available, with histologic specimens. Receiver operating characteristic analyses were performed to determine the optimal sensitivity and specificity of quantitative MR imaging for detecting HA and asymmetry. A linear classifier with cross validation was used to estimate the ability of quantitative MR imaging to help lateralize the seizure focus. Quantitative MR imaging-derived hippocampal asymmetries discriminated patients with TLE from control subjects with high sensitivity (86.7%-89.5%) and specificity (92.2%-94.1%). When a linear classifier was used to discriminate left versus right TLE, hippocampal asymmetry achieved 94% classification accuracy. Volumetric asymmetries of other subcortical structures did not improve classification. Compared with invasive video electroencephalographic recordings, lateralization accuracy was 88% with quantitative MR imaging and 85% with visual inspection of volumetric MR imaging studies but only 76% with visual inspection of clinical MR imaging studies. Quantitative MR imaging can depict the presence and laterality of HA in TLE with accuracy rates that may exceed those achieved with visual inspection of clinical MR imaging studies. Thus, quantitative MR imaging may enhance standard visual analysis, providing a useful and viable means for translating volumetric analysis into clinical practice.

GIS based 3D visualization of subsurface and surface lineaments / faults and their geological significance, northern tamil nadu, India

NASA Astrophysics Data System (ADS)

Saravanavel, J.; Ramasamy, S. M.

2014-11-01

The study area falls in the southern part of the Indian Peninsular comprising hard crystalline rocks of Archaeozoic and Proterozoic Era. In the present study, the GIS based 3D visualizations of gravity, magnetic, resistivity and topographic datasets were made and therefrom the basement lineaments, shallow subsurface lineaments and surface lineaments/faults were interpreted. These lineaments were classified as category-1 i.e. exclusively surface lineaments, category-2 i.e. surface lineaments having connectivity with shallow subsurface lineaments and category-3 i.e. surface lineaments having connectivity with shallow subsurface lineaments and basement lineaments. These three classified lineaments were analyzed in conjunction with known mineral occurrences and historical seismicity of the study area in GIS environment. The study revealed that the category-3 NNE-SSW to NE-SW lineaments have greater control over the mineral occurrences and the N-S, NNE-SSW and NE-SW, faults/lineaments control the seismicities in the study area.

Female Genital Mutilation: A Visual Reference and Learning Tool for Health Care Professionals.

PubMed

Abdulcadir, Jasmine; Catania, Lucrezia; Hindin, Michelle Jane; Say, Lale; Petignat, Patrick; Abdulcadir, Omar

2016-11-01

Female genital mutilation comprises all procedures that involve partial or total removal of the external female genitalia or injury to the female genital organs for nonmedical reasons. Health care providers for women and girls living with female genital mutilation have reported difficulties in recognizing, classifying, and recording female genital mutilation, which can adversely affect treatment of complications and discussions of the prevention of the practice in future generations. According to the World Health Organization, female genital mutilation is classified into four types, subdivided into subtypes. An agreed-upon classification of female genital mutilation is important for clinical practice, management, recording, and reporting, as well as for research on prevalence, trends, and consequences of female genital mutilation. We provide a visual reference and learning tool for health care professionals. The tool can be consulted by caregivers when unsure on the type of female genital mutilation diagnosed and used for training and surveys for monitoring the prevalence of female genital mutilation types and subtypes.

Stackable differential mobility analyzer for aerosol measurement

DOEpatents

Cheng, Meng-Dawn [Oak Ridge, TN; Chen, Da-Ren [Creve Coeur, MO

2007-05-08

A multi-stage differential mobility analyzer (MDMA) for aerosol measurements includes a first electrode or grid including at least one inlet or injection slit for receiving an aerosol including charged particles for analysis. A second electrode or grid is spaced apart from the first electrode. The second electrode has at least one sampling outlet disposed at a plurality different distances along its length. A volume between the first and the second electrode or grid between the inlet or injection slit and a distal one of the plurality of sampling outlets forms a classifying region, the first and second electrodes for charging to suitable potentials to create an electric field within the classifying region. At least one inlet or injection slit in the second electrode receives a sheath gas flow into an upstream end of the classifying region, wherein each sampling outlet functions as an independent DMA stage and classifies different size ranges of charged particles based on electric mobility simultaneously.

Combining features from ERP components in single-trial EEG for discriminating four-category visual objects.

PubMed

Wang, Changming; Xiong, Shi; Hu, Xiaoping; Yao, Li; Zhang, Jiacai

2012-10-01

Categorization of images containing visual objects can be successfully recognized using single-trial electroencephalograph (EEG) measured when subjects view images. Previous studies have shown that task-related information contained in event-related potential (ERP) components could discriminate two or three categories of object images. In this study, we investigated whether four categories of objects (human faces, buildings, cats and cars) could be mutually discriminated using single-trial EEG data. Here, the EEG waveforms acquired while subjects were viewing four categories of object images were segmented into several ERP components (P1, N1, P2a and P2b), and then Fisher linear discriminant analysis (Fisher-LDA) was used to classify EEG features extracted from ERP components. Firstly, we compared the classification results using features from single ERP components, and identified that the N1 component achieved the highest classification accuracies. Secondly, we discriminated four categories of objects using combining features from multiple ERP components, and showed that combination of ERP components improved four-category classification accuracies by utilizing the complementarity of discriminative information in ERP components. These findings confirmed that four categories of object images could be discriminated with single-trial EEG and could direct us to select effective EEG features for classifying visual objects.

A Population-based survey of the prevalence and types of glaucoma in Nigeria: results from the Nigeria National Blindness and Visual Impairment Survey.

PubMed

Kyari, Fatima; Entekume, Gabriel; Rabiu, Mansur; Spry, Paul; Wormald, Richard; Nolan, Winifred; Murthy, Gudlavalleti V S; Gilbert, Clare E

2015-12-12

Glaucoma is the leading cause of irreversible blindness worldwide. There tends to be a lower reporting of glaucoma in Africa compared to other blinding conditions in global burden data. Research findings of glaucoma in Nigeria will significantly increase our understanding of glaucoma in Nigeria, in people of the West African diaspora and similar population groups. We determined the prevalence and types of glaucoma in Nigeria from the Nigeria National Blindness and Visual Impairment cross-sectional Survey of adults aged ≥40 years. Multistage stratified cluster random sampling with probability-proportional-to-size procedures were used to select a nationally representative sample of 15,027 persons aged ≥40 years. Participants had logMAR visual acuity measurement, FDT visual function testing, autorefraction, A-scan biometry and optic disc assessment. Participants with visual acuity of worse than 6/12 or suspicious optic discs had detailed examination including Goldmann applanation tonometry, gonioscopy and fundus photography. Disc images were graded by Moorfields Eye Hospital Reading Centre. Glaucoma was defined using International Society of Geographical and Epidemiological Ophthalmology criteria; and classified into primary open-angle or primary angle-closure or secondary glaucoma. Diagnosis of glaucoma was based on ISGEO classification. The type of glaucoma was determined by gonioscopy. A total of 13,591 participants in 305 clusters were examined (response rate 90.4 %). Optic disc grading was available for 25,289 (93 %) eyes of 13,081 (96 %) participants. There were 682 participants with glaucoma; a prevalence of 5.02 % (95 % CI 4.60-5.47). Among those with definite primary glaucoma that had gonioscopy (n = 243), open-angle glaucoma was more common (86 %) than angle-closure glaucoma (14 %). 8 % of glaucoma was secondary with the commonest causes being couching (38 %), trauma (21 %) and uveitis (19 %). Only 5.6 % (38/682) of participants with glaucoma knew they had the condition. One in every 5 persons with glaucoma (136;20 %) was blind i.e., visual acuity worse than 3/60. Nigeria has a high prevalence of glaucoma which is largely open-angle glaucoma. A high proportion of those affected are blind. Secondary glaucoma was mostly as a consequence of procedures for cataract. Public health control strategies and high quality glaucoma care service will be required to reduce morbidity and blindness from glaucoma.

Automatic Approach to Morphological Classification of Galaxies With Analysis of Galaxy Populations in Clusters

NASA Astrophysics Data System (ADS)

Sultanova, Madina; Barkhouse, Wayne; Rude, Cody

2018-01-01

The classification of galaxies based on their morphology is a field in astrophysics that aims to understand galaxy formation and evolution based on their physical differences. Whether structural differences are due to internal factors or a result of local environment, the dominate mechanism that determines galaxy type needs to be robustly quantified in order to have a thorough grasp of the origin of the different types of galaxies. The main subject of my Ph.D. dissertation is to explore the use of computers to automatically classify and analyze large numbers of galaxies according to their morphology, and to analyze sub-samples of galaxies selected by type to understand galaxy formation in various environments. I have developed a computer code to classify galaxies by measuring five parameters from their images in FITS format. The code was trained and tested using visually classified SDSS galaxies from Galaxy Zoo and the EFIGI data set. I apply my morphology software to numerous galaxies from diverse data sets. Among the data analyzed are the 15 Abell galaxy clusters (0.03 < z < 0.184) from Rude et al. 2017 (in preparation), which were observed by the Canada-France-Hawaii Telescope. Additionally, I studied 57 galaxy clusters from Barkhouse et al. (2007), 77 clusters from the WINGS survey (Fasano et al. 2006), and the six Hubble Space Telescope (HST) Frontier Field galaxy clusters. The high resolution of HST allows me to compare distant clusters with those nearby to look for evolutionary changes in the galaxy cluster population. I use the results from the software to examine the properties (e.g. luminosity functions, radial dependencies, star formation rates) of selected galaxies. Due to the large amount of data that will be available from wide-area surveys in the future, the use of computer software to classify and analyze the morphology of galaxies will be extremely important in terms of efficiency. This research aims to contribute to the solution of this problem.

The cognitive science of visual-spatial displays: implications for design.

PubMed

Hegarty, Mary

2011-07-01

This paper reviews cognitive science perspectives on the design of visual-spatial displays and introduces the other papers in this topic. It begins by classifying different types of visual-spatial displays, followed by a discussion of ways in which visual-spatial displays augment cognition and an overview of the perceptual and cognitive processes involved in using displays. The paper then argues for the importance of cognitive science methods to the design of visual displays and reviews some of the main principles of display design that have emerged from these approaches to date. Cognitive scientists have had good success in characterizing the performance of well-defined tasks with relatively simple visual displays, but many challenges remain in understanding the use of complex displays for ill-defined tasks. Current research exemplified by the papers in this topic extends empirical approaches to new displays and domains, informs the development of general principles of graphic design, and addresses current challenges in display design raised by the recent explosion in availability of complex data sets and new technologies for visualizing and interacting with these data. Copyright © 2011 Cognitive Science Society, Inc.

A survey of supervised machine learning models for mobile-phone based pathogen identification and classification

NASA Astrophysics Data System (ADS)

Ceylan Koydemir, Hatice; Feng, Steve; Liang, Kyle; Nadkarni, Rohan; Tseng, Derek; Benien, Parul; Ozcan, Aydogan

2017-03-01

Giardia lamblia causes a disease known as giardiasis, which results in diarrhea, abdominal cramps, and bloating. Although conventional pathogen detection methods used in water analysis laboratories offer high sensitivity and specificity, they are time consuming, and need experts to operate bulky equipment and analyze the samples. Here we present a field-portable and cost-effective smartphone-based waterborne pathogen detection platform that can automatically classify Giardia cysts using machine learning. Our platform enables the detection and quantification of Giardia cysts in one hour, including sample collection, labeling, filtration, and automated counting steps. We evaluated the performance of three prototypes using Giardia-spiked water samples from different sources (e.g., reagent-grade, tap, non-potable, and pond water samples). We populated a training database with >30,000 cysts and estimated our detection sensitivity and specificity using 20 different classifier models, including decision trees, nearest neighbor classifiers, support vector machines (SVMs), and ensemble classifiers, and compared their speed of training and classification, as well as predicted accuracies. Among them, cubic SVM, medium Gaussian SVM, and bagged-trees were the most promising classifier types with accuracies of 94.1%, 94.2%, and 95%, respectively; we selected the latter as our preferred classifier for the detection and enumeration of Giardia cysts that are imaged using our mobile-phone fluorescence microscope. Without the need for any experts or microbiologists, this field-portable pathogen detection platform can present a useful tool for water quality monitoring in resource-limited-settings.

A new integrated dual time-point amyloid PET/MRI data analysis method.

PubMed

Cecchin, Diego; Barthel, Henryk; Poggiali, Davide; Cagnin, Annachiara; Tiepolt, Solveig; Zucchetta, Pietro; Turco, Paolo; Gallo, Paolo; Frigo, Anna Chiara; Sabri, Osama; Bui, Franco

2017-11-01

In the initial evaluation of patients with suspected dementia and Alzheimer's disease, there is no consensus on how to perform semiquantification of amyloid in such a way that it: (1) facilitates visual qualitative interpretation, (2) takes the kinetic behaviour of the tracer into consideration particularly with regard to at least partially correcting for blood flow dependence, (3) analyses the amyloid load based on accurate parcellation of cortical and subcortical areas, (4) includes partial volume effect correction (PVEC), (5) includes MRI-derived topographical indexes, (6) enables application to PET/MRI images and PET/CT images with separately acquired MR images, and (7) allows automation. A method with all of these characteristics was retrospectively tested in 86 subjects who underwent amyloid ( 18 F-florbetaben) PET/MRI in a clinical setting (using images acquired 90-110 min after injection, 53 were classified visually as amyloid-negative and 33 as amyloid-positive). Early images after tracer administration were acquired between 0 and 10 min after injection, and later images were acquired between 90 and 110 min after injection. PVEC of the PET data was carried out using the geometric transfer matrix method. Parametric images and some regional output parameters, including two innovative "dual time-point" indexes, were obtained. Subjects classified visually as amyloid-positive showed a sparse tracer uptake in the primary sensory, motor and visual areas in accordance with the isocortical stage of the topographic distribution of the amyloid plaque (Braak stages V/VI). In patients classified visually as amyloid-negative, the method revealed detectable levels of tracer uptake in the basal portions of the frontal and temporal lobes, areas that are known to be sites of early deposition of amyloid plaques that probably represented early accumulation (Braak stage A) that is typical of normal ageing. There was a strong correlation between age and the indexes of the new dual time-point amyloid imaging method in amyloid-negative patients. The method can be considered a valuable tool in both routine clinical practice and in the research setting as it will standardize data regarding amyloid deposition. It could potentially also be used to identify early amyloid plaque deposition in younger subjects in whom treatment could theoretically be more effective.

The Level of Vision Necessary for Competitive Performance in Rifle Shooting: Setting the Standards for Paralympic Shooting with Vision Impairment.

PubMed

Allen, Peter M; Latham, Keziah; Mann, David L; Ravensbergen, Rianne H J C; Myint, Joy

2016-01-01

The aim of this study was to investigate the level of vision impairment (VI) that would reduce performance in shooting; to guide development of entry criteria to visually impaired (VI) shooting. Nineteen international-level shooters without VI took part in the study. Participants shot an air rifle, while standing, toward a regulation target placed at the end of a 10 m shooting range. Cambridge simulation glasses were used to simulate six different levels of VI. Visual acuity (VA) and contrast sensitivity (CS) were assessed along with shooting performance in each of seven conditions of simulated impairment and compared to that with habitual vision. Shooting performance was evaluated by calculating each individual's average score in every level of simulated VI and normalizing this score by expressing it as a percentage of the baseline performance achieved with habitual vision. Receiver Operating Characteristic curves were constructed to evaluate the ability of different VA and CS cut-off criteria to appropriately classify these athletes as achieving 'expected' or 'below expected' shooting results based on their performance with different levels of VA and CS. Shooting performance remained relatively unaffected by mild decreases in VA and CS, but quickly deteriorated with more moderate losses. The ability of visual function measurements to classify shooting performance was good, with 78% of performances appropriately classified using a cut-off of 0.53 logMAR and 74% appropriately classified using a cut-off of 0.83 logCS. The current inclusion criteria for VI shooting (1.0 logMAR) is conservative, maximizing the chance of including only those with an impairment that does impact performance, but potentially excluding some who do have a genuine impairment in the sport. A lower level of impairment would include more athletes who do have a genuine impairment but would potentially include those who do not actually have an impairment that impacts performance in the sport. An impairment to CS could impact performance in the sport and might be considered in determining eligibility to take part in VI competition.

The Level of Vision Necessary for Competitive Performance in Rifle Shooting: Setting the Standards for Paralympic Shooting with Vision Impairment

PubMed Central

Allen, Peter M.; Latham, Keziah; Mann, David L.; Ravensbergen, Rianne H. J. C.; Myint, Joy

2016-01-01

The aim of this study was to investigate the level of vision impairment (VI) that would reduce performance in shooting; to guide development of entry criteria to visually impaired (VI) shooting. Nineteen international-level shooters without VI took part in the study. Participants shot an air rifle, while standing, toward a regulation target placed at the end of a 10 m shooting range. Cambridge simulation glasses were used to simulate six different levels of VI. Visual acuity (VA) and contrast sensitivity (CS) were assessed along with shooting performance in each of seven conditions of simulated impairment and compared to that with habitual vision. Shooting performance was evaluated by calculating each individual’s average score in every level of simulated VI and normalizing this score by expressing it as a percentage of the baseline performance achieved with habitual vision. Receiver Operating Characteristic curves were constructed to evaluate the ability of different VA and CS cut-off criteria to appropriately classify these athletes as achieving ‘expected’ or ‘below expected’ shooting results based on their performance with different levels of VA and CS. Shooting performance remained relatively unaffected by mild decreases in VA and CS, but quickly deteriorated with more moderate losses. The ability of visual function measurements to classify shooting performance was good, with 78% of performances appropriately classified using a cut-off of 0.53 logMAR and 74% appropriately classified using a cut-off of 0.83 logCS. The current inclusion criteria for VI shooting (1.0 logMAR) is conservative, maximizing the chance of including only those with an impairment that does impact performance, but potentially excluding some who do have a genuine impairment in the sport. A lower level of impairment would include more athletes who do have a genuine impairment but would potentially include those who do not actually have an impairment that impacts performance in the sport. An impairment to CS could impact performance in the sport and might be considered in determining eligibility to take part in VI competition. PMID:27877150

Classification of THz pulse signals using two-dimensional cross-correlation feature extraction and non-linear classifiers.

PubMed

Siuly; Yin, Xiaoxia; Hadjiloucas, Sillas; Zhang, Yanchun

2016-04-01

This work provides a performance comparison of four different machine learning classifiers: multinomial logistic regression with ridge estimators (MLR) classifier, k-nearest neighbours (KNN), support vector machine (SVM) and naïve Bayes (NB) as applied to terahertz (THz) transient time domain sequences associated with pixelated images of different powder samples. The six substances considered, although have similar optical properties, their complex insertion loss at the THz part of the spectrum is significantly different because of differences in both their frequency dependent THz extinction coefficient as well as differences in their refractive index and scattering properties. As scattering can be unquantifiable in many spectroscopic experiments, classification solely on differences in complex insertion loss can be inconclusive. The problem is addressed using two-dimensional (2-D) cross-correlations between background and sample interferograms, these ensure good noise suppression of the datasets and provide a range of statistical features that are subsequently used as inputs to the above classifiers. A cross-validation procedure is adopted to assess the performance of the classifiers. Firstly the measurements related to samples that had thicknesses of 2mm were classified, then samples at thicknesses of 4mm, and after that 3mm were classified and the success rate and consistency of each classifier was recorded. In addition, mixtures having thicknesses of 2 and 4mm as well as mixtures of 2, 3 and 4mm were presented simultaneously to all classifiers. This approach provided further cross-validation of the classification consistency of each algorithm. The results confirm the superiority in classification accuracy and robustness of the MLR (least accuracy 88.24%) and KNN (least accuracy 90.19%) algorithms which consistently outperformed the SVM (least accuracy 74.51%) and NB (least accuracy 56.86%) classifiers for the same number of feature vectors across all studies. The work establishes a general methodology for assessing the performance of other hyperspectral dataset classifiers on the basis of 2-D cross-correlations in far-infrared spectroscopy or other parts of the electromagnetic spectrum. It also advances the wider proliferation of automated THz imaging systems across new application areas e.g., biomedical imaging, industrial processing and quality control where interpretation of hyperspectral images is still under development. Copyright © 2016 Elsevier Ireland Ltd. All rights reserved.

Active Self-Paced Learning for Cost-Effective and Progressive Face Identification.

PubMed

Lin, Liang; Wang, Keze; Meng, Deyu; Zuo, Wangmeng; Zhang, Lei

2018-01-01

This paper aims to develop a novel cost-effective framework for face identification, which progressively maintains a batch of classifiers with the increasing face images of different individuals. By naturally combining two recently rising techniques: active learning (AL) and self-paced learning (SPL), our framework is capable of automatically annotating new instances and incorporating them into training under weak expert recertification. We first initialize the classifier using a few annotated samples for each individual, and extract image features using the convolutional neural nets. Then, a number of candidates are selected from the unannotated samples for classifier updating, in which we apply the current classifiers ranking the samples by the prediction confidence. In particular, our approach utilizes the high-confidence and low-confidence samples in the self-paced and the active user-query way, respectively. The neural nets are later fine-tuned based on the updated classifiers. Such heuristic implementation is formulated as solving a concise active SPL optimization problem, which also advances the SPL development by supplementing a rational dynamic curriculum constraint. The new model finely accords with the "instructor-student-collaborative" learning mode in human education. The advantages of this proposed framework are two-folds: i) The required number of annotated samples is significantly decreased while the comparable performance is guaranteed. A dramatic reduction of user effort is also achieved over other state-of-the-art active learning techniques. ii) The mixture of SPL and AL effectively improves not only the classifier accuracy compared to existing AL/SPL methods but also the robustness against noisy data. We evaluate our framework on two challenging datasets, which include hundreds of persons under diverse conditions, and demonstrate very promising results. Please find the code of this project at: http://hcp.sysu.edu.cn/projects/aspl/.

Classification and identification of molecules through factor analysis method based on terahertz spectroscopy

NASA Astrophysics Data System (ADS)

Huang, Jianglou; Liu, Jinsong; Wang, Kejia; Yang, Zhengang; Liu, Xiaming

2018-06-01

By means of factor analysis approach, a method of molecule classification is built based on the measured terahertz absorption spectra of the molecules. A data matrix can be obtained by sampling the absorption spectra at different frequency points. The data matrix is then decomposed into the product of two matrices: a weight matrix and a characteristic matrix. By using the K-means clustering to deal with the weight matrix, these molecules can be classified. A group of samples (spirobenzopyran, indole, styrene derivatives and inorganic salts) has been prepared, and measured via a terahertz time-domain spectrometer. These samples are classified with 75% accuracy compared to that directly classified via their molecular formulas.

INFLUENCE OF INTRAMUSCULAR FAT LEVEL ON ORGANOLEPTIC, PHYSICAL, AND CHEMICAL CHARACTERISTICS OF IRRADIATED PORK MUSCLE

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

Whitehair, L.A.

1962-01-01

A study was conducted to evaluate the influence of marbling on certain organoleptic, physical, and chemical characteristics of precooked and irradiated pork loin muscle (longissimus dorsi). The study consisted of two separate phases. Loins utilized in Phase I were selected by visual appraisal and categorized into three distinct marbling level scores. A high temperature, short time blanching treatment was used for proteolytic enzyme inactivation. Phase II loins were selected and classified into three marbling levels by both visual appraisal amd ether extraction analysis of total fat. A low temperature, long time heat treatment was used for enzyme inactivation. Samples weremore » packed under vacuum in rigid containers and irradiated at a dosage level of 4.5 megarads gamma radiation. Non-irradiated samples were stored at -65 deg F. Irradiated and control samples were evaluated at periodic intervals by a panel. Physical and chemical analyses were made initially on samples representing each treatment and subsequently at the termination of each storage period. Organoleptic results indicated that degree of marbling did not influence preference ratings of plain radiosterilized longissimus dorsi muscle (pork). However, irradiated longissimus dorsi (pork) sandwich items with lower marbling scores were consistently preferred over highly marbled, irradiated sandwich items. Non-irradiated longissimus dorsi samples were preferred to irradiated longissimus dorsi samples in all tests. The short term-high temperature method of blanching used in Phase I resulted in products of slightly superior quality to those of Phase II, which possessed softer, slightly drier texture characteristics. The practical storage life of irradiated samples under the conditions was approximately 150 days. Hunter color values were increased by radiation treatment. Irradiated longissimus dorsi samples developed a characteristic pink-red color. Mechanical tenderness values in both irradiated and non-irradiated samples were lowered significantly by higher levels of marbling. Expressible moisture values of irradiated samples were lower than those of control samples. The values increased with advancing storage time. Iodine numbers of lower marbling scores (both irradiated and non-irradiated samplcs) exceeded those of highly marbled samples. T.B.A. number values were lower in irradiated samples of Phase I. The values were increased with respect to increased levels of marbling in Phase II. Values increased steadily with advancing storage time in both phases. pH values were elevated by irradiation treatment, marbling level, and storage time in Phase I. The differences were not observed for Phase II samples. Bacteriological assays indicated that irradiated samples were commercially sterile. Extremely low numbers of Micrococci were found. (Dissertation Abstr., 23: No. 4)« less

Detection and recognition of simple spatial forms

NASA Technical Reports Server (NTRS)

Watson, A. B.

1983-01-01

A model of human visual sensitivity to spatial patterns is constructed. The model predicts the visibility and discriminability of arbitrary two-dimensional monochrome images. The image is analyzed by a large array of linear feature sensors, which differ in spatial frequency, phase, orientation, and position in the visual field. All sensors have one octave frequency bandwidths, and increase in size linearly with eccentricity. Sensor responses are processed by an ideal Bayesian classifier, subject to uncertainty. The performance of the model is compared to that of the human observer in detecting and discriminating some simple images.

3D Feature Extraction for Unstructured Grids

NASA Technical Reports Server (NTRS)

Silver, Deborah

1996-01-01

Visualization techniques provide tools that help scientists identify observed phenomena in scientific simulation. To be useful, these tools must allow the user to extract regions, classify and visualize them, abstract them for simplified representations, and track their evolution. Object Segmentation provides a technique to extract and quantify regions of interest within these massive datasets. This article explores basic algorithms to extract coherent amorphous regions from two-dimensional and three-dimensional scalar unstructured grids. The techniques are applied to datasets from Computational Fluid Dynamics and those from Finite Element Analysis.

ERGONOMICS ABSTRACTS 48983-49619.

ERIC Educational Resources Information Center

Ministry of Technology, London (England). Warren Spring Lab.

THE LITERATURE OF ERGONOMICS, OR BIOTECHNOLOGY, IS CLASSIFIED INTO 15 AREAS--METHODS, SYSTEMS OF MEN AND MACHINES, VISUAL AND AUDITORY AND OTHER INPUTS AND PROCESSES, INPUT CHANNELS, BODY MEASUREMENTS, DESIGN OF CONTROLS AND INTEGRATION WITH DISPLAYS, LAYOUT OF PANELS AND CONSOLES, DESIGN OF WORK SPACE, CLOTHING AND PERSONAL EQUIPMENT, SPECIAL…

32 CFR 2001.53 - Open storage areas.

Code of Federal Regulations, 2010 CFR

2010-07-01

...) Windows. (1) All windows which might reasonably afford visual observation of classified activities within the facility shall be made opaque or equipped with blinds, drapes, or other coverings. (2) Windows... from forced entry. The protection provided to the windows need be no stronger than the strength of the...

Methods, Tools and Current Perspectives in Proteogenomics *

PubMed Central

Ruggles, Kelly V.; Krug, Karsten; Wang, Xiaojing; Clauser, Karl R.; Wang, Jing; Payne, Samuel H.; Fenyö, David; Zhang, Bing; Mani, D. R.

2017-01-01

With combined technological advancements in high-throughput next-generation sequencing and deep mass spectrometry-based proteomics, proteogenomics, i.e. the integrative analysis of proteomic and genomic data, has emerged as a new research field. Early efforts in the field were focused on improving protein identification using sample-specific genomic and transcriptomic sequencing data. More recently, integrative analysis of quantitative measurements from genomic and proteomic studies have identified novel insights into gene expression regulation, cell signaling, and disease. Many methods and tools have been developed or adapted to enable an array of integrative proteogenomic approaches and in this article, we systematically classify published methods and tools into four major categories, (1) Sequence-centric proteogenomics; (2) Analysis of proteogenomic relationships; (3) Integrative modeling of proteogenomic data; and (4) Data sharing and visualization. We provide a comprehensive review of methods and available tools in each category and highlight their typical applications. PMID:28456751

Optimized color decomposition of localized whole slide images and convolutional neural network for intermediate prostate cancer classification

NASA Astrophysics Data System (ADS)

Zhou, Naiyun; Gao, Yi

2017-03-01

This paper presents a fully automatic approach to grade intermediate prostate malignancy with hematoxylin and eosin-stained whole slide images. Deep learning architectures such as convolutional neural networks have been utilized in the domain of histopathology for automated carcinoma detection and classification. However, few work show its power in discriminating intermediate Gleason patterns, due to sporadic distribution of prostate glands on stained surgical section samples. We propose optimized hematoxylin decomposition on localized images, followed by convolutional neural network to classify Gleason patterns 3+4 and 4+3 without handcrafted features or gland segmentation. Crucial glands morphology and structural relationship of nuclei are extracted twice in different color space by the multi-scale strategy to mimic pathologists' visual examination. Our novel classification scheme evaluated on 169 whole slide images yielded a 70.41% accuracy and corresponding area under the receiver operating characteristic curve of 0.7247.

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.

Discrimination of transgenic soybean seeds by terahertz spectroscopy

NASA Astrophysics Data System (ADS)

Liu, Wei; Liu, Changhong; Chen, Feng; Yang, Jianbo; Zheng, Lei

2016-10-01

Discrimination of genetically modified organisms is increasingly demanded by legislation and consumers worldwide. The feasibility of a non-destructive discrimination of glyphosate-resistant and conventional soybean seeds and their hybrid descendants was examined by terahertz time-domain spectroscopy system combined with chemometrics. Principal component analysis (PCA), least squares-support vector machines (LS-SVM) and PCA-back propagation neural network (PCA-BPNN) models with the first and second derivative and standard normal variate (SNV) transformation pre-treatments were applied to classify soybean seeds based on genotype. Results demonstrated clear differences among glyphosate-resistant, hybrid descendants and conventional non-transformed soybean seeds could easily be visualized with an excellent classification (accuracy was 88.33% in validation set) using the LS-SVM and the spectra with SNV pre-treatment. The results indicated that THz spectroscopy techniques together with chemometrics would be a promising technique to distinguish transgenic soybean seeds from non-transformed seeds with high efficiency and without any major sample preparation.

A data-mining framework for exploring the multi-relation between fish species and water quality through self-organizing map.

PubMed

Tsai, Wen-Ping; Huang, Shih-Pin; Cheng, Su-Ting; Shao, Kwang-Tsao; Chang, Fi-John

2017-02-01

The steep slopes of rivers can easily lead to large variations in river water quality during typhoon seasons in Taiwan, which may poses significant impacts on riverine eco-hydrological environments. This study aims to investigate the relationship between fish communities and water quality by using artificial neural networks (ANNs) for comprehending the upstream eco-hydrological system in northern Taiwan. We collected a total of 276 heterogeneous datasets with 8 water quality parameters and 25 fish species from 10 sampling sites. The self-organizing feature map (SOM) was used to cluster, analyze and visualize the heterogeneous datasets. Furthermore, the structuring index (SI) was adopted to determine the relative importance of each input variable of the SOM and identify the indicator factors. The clustering results showed that the SOM could suitably reflect the spatial characteristics of fishery sampling sites. Besides, the patterns of water quality parameters and fish species could be distinguishably (visually) classified into three eco-water quality groups: 1) typical upstream freshwater fishes that depended the most on dissolved oxygen (DO); 2) typical middle-lower reach riverine freshwater fishes that depended the most on total phosphorus (TP) and ammonia nitrogen; and 3) low lands or pond (reservoirs) freshwater fishes that depended the most on water temperature, suspended solids and chemical oxygen demand. According to the results of the SI, the representative indicators of water quality parameters and fish species consisted of DO, TP and Onychostoma barbatulum. This grouping result suggested that the methodology can be used as a guiding reference to comprehensively relate ecology to water quality. Our methods offer a cost-effective alternative to more traditional methods for identifying key water quality factors relating to fish species. In addition, visualizing the constructed topological maps of the SOM could produce detailed inter-relation between water quality and the fish species of stream habitat units. Copyright © 2016 Elsevier B.V. All rights reserved.

Classifier performance prediction for computer-aided diagnosis using a limited dataset.

PubMed

Sahiner, Berkman; Chan, Heang-Ping; Hadjiiski, Lubomir

2008-04-01

In a practical classifier design problem, the true population is generally unknown and the available sample is finite-sized. A common approach is to use a resampling technique to estimate the performance of the classifier that will be trained with the available sample. We conducted a Monte Carlo simulation study to compare the ability of the different resampling techniques in training the classifier and predicting its performance under the constraint of a finite-sized sample. The true population for the two classes was assumed to be multivariate normal distributions with known covariance matrices. Finite sets of sample vectors were drawn from the population. The true performance of the classifier is defined as the area under the receiver operating characteristic curve (AUC) when the classifier designed with the specific sample is applied to the true population. We investigated methods based on the Fukunaga-Hayes and the leave-one-out techniques, as well as three different types of bootstrap methods, namely, the ordinary, 0.632, and 0.632+ bootstrap. The Fisher's linear discriminant analysis was used as the classifier. The dimensionality of the feature space was varied from 3 to 15. The sample size n2 from the positive class was varied between 25 and 60, while the number of cases from the negative class was either equal to n2 or 3n2. Each experiment was performed with an independent dataset randomly drawn from the true population. Using a total of 1000 experiments for each simulation condition, we compared the bias, the variance, and the root-mean-squared error (RMSE) of the AUC estimated using the different resampling techniques relative to the true AUC (obtained from training on a finite dataset and testing on the population). Our results indicated that, under the study conditions, there can be a large difference in the RMSE obtained using different resampling methods, especially when the feature space dimensionality is relatively large and the sample size is small. Under this type of conditions, the 0.632 and 0.632+ bootstrap methods have the lowest RMSE, indicating that the difference between the estimated and the true performances obtained using the 0.632 and 0.632+ bootstrap will be statistically smaller than those obtained using the other three resampling methods. Of the three bootstrap methods, the 0.632+ bootstrap provides the lowest bias. Although this investigation is performed under some specific conditions, it reveals important trends for the problem of classifier performance prediction under the constraint of a limited dataset.

Foreign object detection via texture recognition and a neural classifier

NASA Astrophysics Data System (ADS)

Patel, Devesh; Hannah, I.; Davies, E. R.

1993-10-01

It is rate to find pieces of stone, wood, metal, or glass in food packets, but when they occur, these foreign objects (FOs) cause distress to the consumer and concern to the manufacturer. Using x-ray imaging to detect FOs within food bags, hard contaminants such as stone or metal appear darker, whereas soft contaminants such as wood or rubber appear slightly lighter than the food substrate. In this paper we concentrate on the detection of soft contaminants such as small pieces of wood in bags of frozen corn kernels. Convolution masks are used to generate textural features which are then classified into corresponding homogeneous regions on the image using an artificial neural network (ANN) classifier. The separate ANN outputs are combined using a majority operator, and region discrepancies are removed by a median filter. Comparisons with classical classifiers showed the ANN approach to have the best overall combination of characteristics for our particular problem. The detected boundaries are in good agreement with the visually perceived segmentations.

Relevance Vector Machine and Support Vector Machine Classifier Analysis of Scanning Laser Polarimetry Retinal Nerve Fiber Layer Measurements

PubMed Central

Bowd, Christopher; Medeiros, Felipe A.; Zhang, Zuohua; Zangwill, Linda M.; Hao, Jiucang; Lee, Te-Won; Sejnowski, Terrence J.; Weinreb, Robert N.; Goldbaum, Michael H.

2010-01-01

Purpose To classify healthy and glaucomatous eyes using relevance vector machine (RVM) and support vector machine (SVM) learning classifiers trained on retinal nerve fiber layer (RNFL) thickness measurements obtained by scanning laser polarimetry (SLP). Methods Seventy-two eyes of 72 healthy control subjects (average age = 64.3 ± 8.8 years, visual field mean deviation =−0.71 ± 1.2 dB) and 92 eyes of 92 patients with glaucoma (average age = 66.9 ± 8.9 years, visual field mean deviation =−5.32 ± 4.0 dB) were imaged with SLP with variable corneal compensation (GDx VCC; Laser Diagnostic Technologies, San Diego, CA). RVM and SVM learning classifiers were trained and tested on SLP-determined RNFL thickness measurements from 14 standard parameters and 64 sectors (approximately 5.6° each) obtained in the circumpapillary area under the instrument-defined measurement ellipse (total 78 parameters). Tenfold cross-validation was used to train and test RVM and SVM classifiers on unique subsets of the full 164-eye data set and areas under the receiver operating characteristic (AUROC) curve for the classification of eyes in the test set were generated. AUROC curve results from RVM and SVM were compared to those for 14 SLP software-generated global and regional RNFL thickness parameters. Also reported was the AUROC curve for the GDx VCC software-generated nerve fiber indicator (NFI). Results The AUROC curves for RVM and SVM were 0.90 and 0.91, respectively, and increased to 0.93 and 0.94 when the training sets were optimized with sequential forward and backward selection (resulting in reduced dimensional data sets). AUROC curves for optimized RVM and SVM were significantly larger than those for all individual SLP parameters. The AUROC curve for the NFI was 0.87. Conclusions Results from RVM and SVM trained on SLP RNFL thickness measurements are similar and provide accurate classification of glaucomatous and healthy eyes. RVM may be preferable to SVM, because it provides a Bayesian-derived probability of glaucoma as an output. These results suggest that these machine learning classifiers show good potential for glaucoma diagnosis. PMID:15790898

Planning schistosomiasis control: investigation of alternative sampling strategies for Schistosoma mansoni to target mass drug administration of praziquantel in East Africa.

PubMed

Sturrock, Hugh J W; Gething, Pete W; Ashton, Ruth A; Kolaczinski, Jan H; Kabatereine, Narcis B; Brooker, Simon

2011-09-01

In schistosomiasis control, there is a need to geographically target treatment to populations at high risk of morbidity. This paper evaluates alternative sampling strategies for surveys of Schistosoma mansoni to target mass drug administration in Kenya and Ethiopia. Two main designs are considered: lot quality assurance sampling (LQAS) of children from all schools; and a geostatistical design that samples a subset of schools and uses semi-variogram analysis and spatial interpolation to predict prevalence in the remaining unsurveyed schools. Computerized simulations are used to investigate the performance of sampling strategies in correctly classifying schools according to treatment needs and their cost-effectiveness in identifying high prevalence schools. LQAS performs better than geostatistical sampling in correctly classifying schools, but at a cost with a higher cost per high prevalence school correctly classified. It is suggested that the optimal surveying strategy for S. mansoni needs to take into account the goals of the control programme and the financial and drug resources available.

Strategies for Interactive Visualization of Large Scale Climate Simulations

NASA Astrophysics Data System (ADS)

Xie, J.; Chen, C.; Ma, K.; Parvis

2011-12-01

With the advances in computational methods and supercomputing technology, climate scientists are able to perform large-scale simulations at unprecedented resolutions. These simulations produce data that are time-varying, multivariate, and volumetric, and the data may contain thousands of time steps with each time step having billions of voxels and each voxel recording dozens of variables. Visualizing such time-varying 3D data to examine correlations between different variables thus becomes a daunting task. We have been developing strategies for interactive visualization and correlation analysis of multivariate data. The primary task is to find connection and correlation among data. Given the many complex interactions among the Earth's oceans, atmosphere, land, ice and biogeochemistry, and the sheer size of observational and climate model data sets, interactive exploration helps identify which processes matter most for a particular climate phenomenon. We may consider time-varying data as a set of samples (e.g., voxels or blocks), each of which is associated with a vector of representative or collective values over time. We refer to such a vector as a temporal curve. Correlation analysis thus operates on temporal curves of data samples. A temporal curve can be treated as a two-dimensional function where the two dimensions are time and data value. It can also be treated as a point in the high-dimensional space. In this case, to facilitate effective analysis, it is often necessary to transform temporal curve data from the original space to a space of lower dimensionality. Clustering and segmentation of temporal curve data in the original or transformed space provides us a way to categorize and visualize data of different patterns, which reveals connection or correlation of data among different variables or at different spatial locations. We have employed the power of GPU to enable interactive correlation visualization for studying the variability and correlations of a single or a pair of variables. It is desired to create a succinct volume classification that summarizes the connection among all correlation volumes with respect to various reference locations. Providing a reference location must correspond to a voxel position, the number of correlation volumes equals the total number of voxels. A brute-force solution takes all correlation volumes as the input and classifies their corresponding voxels according to their correlation volumes' distance. For large-scale time-varying multivariate data, calculating all these correlation volumes on-the-fly and analyzing the relationships among them is not feasible. We have developed a sampling-based approach for volume classification in order to reduce the computation cost of computing the correlation volumes. Users are able to employ their domain knowledge in selecting important samples. The result is a static view that captures the essence of correlation relationships; i.e., for all voxels in the same cluster, their corresponding correlation volumes are similar. This sampling-based approach enables us to obtain an approximation of correlation relations in a cost-effective manner, thus leading to a scalable solution to investigate large-scale data sets. These techniques empower climate scientists to study large data from their simulations.

Sociodemographic status of severely disabled and visually impaired elderly people in Turkey.

PubMed

Kıvanç, Sertaç Argun; Akova-Budak, Berna; Olcaysü, Osman Okan; Çevik, Sadık Görkem

2016-02-01

To identify the prevalence of ophthalmologic diseases in elderly patients who had been classified as severely disabled and to identify the ophthalmologic conditions leading to visual impairment and blindness. The medical records of 2806 patients who had applied to the Health Board of the Erzurum Region Training and Research Hospital between January 2011 and December 2012 were reviewed. One hundred ninety-nine patients aged >64 years who were classified as severely disabled with disability rates of over 50%, and who were unable to care for themselves or to move and/or communicate without help were included in the study. The most frequently seen disabilities were neurological (47.2%) and those resulting from eye diseases (17.1%). The most common ophthalmologic diseases were cataract, glaucoma, and age-related macular degeneration. The mean right and left eye visual acuities were 1.17 ± 1.10 logMAR and 1.13 ± 1.0 logMAR, respectively. Of the 60 patients with ophthalmologic diseases or conditions, 33 were blind (visual acuity worse than 20/400) and 10 were visually impaired (visual acuity worse than 20/70 but better than 20/400). Cataracts were the main cause of blindness. The mean age of the patients who were still being followed up at the time of application to the disability board was significantly lower than that of the others (p =0.015). Seventy-nine percent of the blind patients were from rural areas, and 88% of these had no regular follow-up. Among the blind and visually impaired, significantly more patients from urban areas had social security insurance (SSI) than those from rural areas (p =0.043). Nearly 64% of the blind patients were women. The follow-up rate was significantly lower in women (p =0.025). According to multinomial logistic regression analysis, the visually impaired and blind patients were more likely to have lower follow-up rates than the other types of severely disabled patients (OR: 0.231, 95% Cl: 0.077-0.688, p=0.009). Blindness gives rise to severe disability, and the most common ophthalmologic diseases that cause severe disabilities in elderly patients are cataract, glaucoma, and age-related macular degeneration. Sociodemographic factors that may affect the accessibility of visually impaired and blind people to health services include their place of residence and gender.

[MicroRNA Target Prediction Based on Support Vector Machine Ensemble Classification Algorithm of Under-sampling Technique].

PubMed

Chen, Zhiru; Hong, Wenxue

2016-02-01

Considering the low accuracy of prediction in the positive samples and poor overall classification effects caused by unbalanced sample data of MicroRNA (miRNA) target, we proposes a support vector machine (SVM)-integration of under-sampling and weight (IUSM) algorithm in this paper, an under-sampling based on the ensemble learning algorithm. The algorithm adopts SVM as learning algorithm and AdaBoost as integration framework, and embeds clustering-based under-sampling into the iterative process, aiming at reducing the degree of unbalanced distribution of positive and negative samples. Meanwhile, in the process of adaptive weight adjustment of the samples, the SVM-IUSM algorithm eliminates the abnormal ones in negative samples with robust sample weights smoothing mechanism so as to avoid over-learning. Finally, the prediction of miRNA target integrated classifier is achieved with the combination of multiple weak classifiers through the voting mechanism. The experiment revealed that the SVM-IUSW, compared with other algorithms on unbalanced dataset collection, could not only improve the accuracy of positive targets and the overall effect of classification, but also enhance the generalization ability of miRNA target classifier.

Literature review of visual representation of the results of benefit-risk assessments of medicinal products.

PubMed

Hallgreen, Christine E; Mt-Isa, Shahrul; Lieftucht, Alfons; Phillips, Lawrence D; Hughes, Diana; Talbot, Susan; Asiimwe, Alex; Downey, Gerald; Genov, Georgy; Hermann, Richard; Noel, Rebecca; Peters, Ruth; Micaleff, Alain; Tzoulaki, Ioanna; Ashby, Deborah

2016-03-01

The PROTECT Benefit-Risk group is dedicated to research in methods for continuous benefit-risk monitoring of medicines, including the presentation of the results, with a particular emphasis on graphical methods. A comprehensive review was performed to identify visuals used for medical risk and benefit-risk communication. The identified visual displays were grouped into visual types, and each visual type was appraised based on five criteria: intended audience, intended message, knowledge required to understand the visual, unintentional messages that may be derived from the visual and missing information that may be needed to understand the visual. Sixty-six examples of visual formats were identified from the literature and classified into 14 visual types. We found that there is not one single visual format that is consistently superior to others for the communication of benefit-risk information. In addition, we found that most of the drawbacks found in the visual formats could be considered general to visual communication, although some appear more relevant to specific formats and should be considered when creating visuals for different audiences depending on the exact message to be communicated. We have arrived at recommendations for the use of visual displays for benefit-risk communication. The recommendation refers to the creation of visuals. We outline four criteria to determine audience-visual compatibility and consider these to be a key task in creating any visual. Next we propose specific visual formats of interest, to be explored further for their ability to address nine different types of benefit-risk analysis information. Copyright © 2015 John Wiley & Sons, Ltd.

The decision tree classifier - Design and potential. [for Landsat-1 data

NASA Technical Reports Server (NTRS)

Hauska, H.; Swain, P. H.

1975-01-01

A new classifier has been developed for the computerized analysis of remote sensor data. The decision tree classifier is essentially a maximum likelihood classifier using multistage decision logic. It is characterized by the fact that an unknown sample can be classified into a class using one or several decision functions in a successive manner. The classifier is applied to the analysis of data sensed by Landsat-1 over Kenosha Pass, Colorado. The classifier is illustrated by a tree diagram which for processing purposes is encoded as a string of symbols such that there is a unique one-to-one relationship between string and decision tree.

Automated Assessment of Dynamic Knee Valgus and Risk of Knee Injury During the Single Leg Squat

PubMed Central

Lee, Alexander; Raina, Sachin; Kulić, Dana

2017-01-01

Many clinical assessment protocols of the lower limb rely on the evaluation of functional movement tests such as the single leg squat (SLS), which are often assessed visually. Visual assessment is subjective and depends on the experience of the clinician. In this paper, an inertial measurement unit (IMU)-based method for automated assessment of squat quality is proposed to provide clinicians with a quantitative measure of SLS performance. A set of three IMUs was used to estimate the joint angles, velocities, and accelerations of the squatting leg. Statistical time domain features were generated from these measurements. The most informative features were used for classifier training. A data set of SLS performed by healthy participants was collected and labeled by three expert clinical raters using two different labeling criteria: “observed amount of knee valgus” and “overall risk of injury”. The results showed that both flexion at the hip and knee, as well as hip and ankle internal rotation are discriminative features, and that participants with “poor” squats bend the hip and knee less than those with better squat performance. Furthermore, improved classification performance is achieved for females by training separate classifiers stratified by gender. Classification results showed excellent accuracy, 95.7 % for classifying squat quality as “poor” or “good” and 94.6% for differentiating between high and no risk of injury. PMID:29204327

Perceptual category learning of photographic and painterly stimuli in rhesus macaques (Macaca mulatta) and humans

PubMed Central

Jensen, Greg; Terrace, Herbert

2017-01-01

Humans are highly adept at categorizing visual stimuli, but studies of human categorization are typically validated by verbal reports. This makes it difficult to perform comparative studies of categorization using non-human animals. Interpretation of comparative studies is further complicated by the possibility that animal performance may merely reflect reinforcement learning, whereby discrete features act as discriminative cues for categorization. To assess and compare how humans and monkeys classified visual stimuli, we trained 7 rhesus macaques and 41 human volunteers to respond, in a specific order, to four simultaneously presented stimuli at a time, each belonging to a different perceptual category. These exemplars were drawn at random from large banks of images, such that the stimuli presented changed on every trial. Subjects nevertheless identified and ordered these changing stimuli correctly. Three monkeys learned to order naturalistic photographs; four others, close-up sections of paintings with distinctive styles. Humans learned to order both types of stimuli. All subjects classified stimuli at levels substantially greater than that predicted by chance or by feature-driven learning alone, even when stimuli changed on every trial. However, humans more closely resembled monkeys when classifying the more abstract painting stimuli than the photographic stimuli. This points to a common classification strategy in both species, one that humans can rely on in the absence of linguistic labels for categories. PMID:28961270

Assimilative Domain Proficiency and Performance in Chemistry Coursework

ERIC Educational Resources Information Center

Byrnes, Scott William

2010-01-01

The assimilation and synthesis of knowledge is essential for students to be successful in chemistry, yet not all students synthesize knowledge as intended. The study used the Learning Preference Checklist to classify students into one of three learning modalities--visual, auditory, or kinesthetic (VAK). It also used the Kolb Learning Style…

Acquiring Visual Classifiers from Human Imagination

DTIC Science & Technology

2014-01-01

the most popular sport in India is cricket , which is played with a red ball, and popular sports in the United States are American football and...that people from different countries have inside their head. Indians seem to imagine a red ball, which is the standard color for a cricket ball and

Vector coding of wavelet-transformed images

NASA Astrophysics Data System (ADS)

Zhou, Jun; Zhi, Cheng; Zhou, Yuanhua

1998-09-01

Wavelet, as a brand new tool in signal processing, has got broad recognition. Using wavelet transform, we can get octave divided frequency band with specific orientation which combines well with the properties of Human Visual System. In this paper, we discuss the classified vector quantization method for multiresolution represented image.

Survey on Classifying Human Actions Through Visual Sensors

DTIC Science & Technology

2011-05-04

47] Herrera, A., Beck , A., Bell, D., Miller, P., Wu, Q., Yan, W., “Behaviour Analysis and Prediction in Image Sequences Using Rough Sets...report TR-97-021, University of Berkeley, 1998 [83] DARPA Mind’s Eye Broad Agency Announcement, DARPA- BAA -10-53, 2010 www.darpa.mil/tcto/docs

Visualizing a Taxonomy for Virtual Worlds

ERIC Educational Resources Information Center

Downey, Steve

2012-01-01

Since the mid-1990s, however, the popularity, diversity, and application of virtual worlds have spread rapidly. As a result, existing taxonomies and topologies increasingly are becoming less effective at being able to classify and organize the growing diversification of content available in today's virtual worlds. This article presents the…

Visible and near-infrared hyperspectral imaging for cooking loss classification of fresh broiler breast fillets

USDA-ARS?s Scientific Manuscript database

Cooking loss (CL) is a critical quality attribute directly relating to meat juiciness. The potential of the hyperspectral imaging (HSI) technique was investigated for non-invasively classifying and visualizing the CL of fresh broiler breast meat. Hyperspectral images of total 75 fresh broiler breast...

Congenital Blindness Leads to Enhanced Vibrotactile Perception

ERIC Educational Resources Information Center

Wan, Catherine Y.; Wood, Amanda G.; Reutens, David C.; Wilson, Sarah J.

2010-01-01

Previous studies have shown that in comparison with the sighted, blind individuals display superior non-visual perceptual abilities and differ in brain organisation. In this study, we investigated the performance of blind and sighted participants on a vibrotactile discrimination task. Thirty-three blind participants were classified into one of…

Common Ground: An Interactive Visual Exploration and Discovery for Complex Health Data

DTIC Science & Technology

2015-04-01

working with Intermountain Healthcare on a new rich dataset extracted directly from medical notes using natural language processing ( NLP ) algorithms...probabilities based on a state- of-the-art NLP classifiers. At that stage the data did not include geographic information or temporal information but we

Towards multispectral endoscopic imaging of cardiac lesion assessment and classification for cardiac ablation therapy

NASA Astrophysics Data System (ADS)

Park, Soo Young; Singh-Moon, Rajinder P.; Hendon, Christine P.

2018-02-01

Pulmonary vein (PV) isolation is a critical procedure for the treatment and termination of atrial fibrillation (AF). The success of such treatment depends on the extent of tissue damage, where partial lesions can allow abnormal electrical conduction and risk relapse of AF. Proper evaluation of lesion delivery and ablation line continuity remains challenging with current techniques and in part limit procedural efficacy. A tool for direct visualization of endo-myocardial lesions in vivo could potentially reduce ambiguity in treatment location and extent and improve the overall fidelity of lesion sets. In this work, we introduce a method for wide-field visualization of myocardial tissue including the discernment of ablated and non-ablated regions using an endoscopic multispectral imaging system (EMIS). The system was designed to fit the working channel of most commercial sheathes (<4 Fr) and supported quadruple-wavelength reflectance imaging through a flexible fiber-bundle. A total of 50 endocardial lesions were created and imaged on nine swine hearts, ex vivo in addition to 15 lesions on human LA samples near PV regions. A pixel-wise linear discriminant analysis algorithm was developed to classify regions of ablation treatment based on calibrated EMI maps. Results show good agreement of treatment severity and spatial extent compared to post-hoc tissue vital staining.

Semantic attributes for people's appearance description: an appearance modality for video surveillance applications

NASA Astrophysics Data System (ADS)

Frikha, Mayssa; Fendri, Emna; Hammami, Mohamed

2017-09-01

Using semantic attributes such as gender, clothes, and accessories to describe people's appearance is an appealing modeling method for video surveillance applications. We proposed a midlevel appearance signature based on extracting a list of nameable semantic attributes describing the body in uncontrolled acquisition conditions. Conventional approaches extract the same set of low-level features to learn the semantic classifiers uniformly. Their critical limitation is the inability to capture the dominant visual characteristics for each trait separately. The proposed approach consists of extracting low-level features in an attribute-adaptive way by automatically selecting the most relevant features for each attribute separately. Furthermore, relying on a small training-dataset would easily lead to poor performance due to the large intraclass and interclass variations. We annotated large scale people images collected from different person reidentification benchmarks covering a large attribute sample and reflecting the challenges of uncontrolled acquisition conditions. These annotations were gathered into an appearance semantic attribute dataset that contains 3590 images annotated with 14 attributes. Various experiments prove that carefully designed features for learning the visual characteristics for an attribute provide an improvement of the correct classification accuracy and a reduction of both spatial and temporal complexities against state-of-the-art approaches.

Detecting Visually Observable Disease Symptoms from Faces.

PubMed

Wang, Kuan; Luo, Jiebo

2016-12-01

Recent years have witnessed an increasing interest in the application of machine learning to clinical informatics and healthcare systems. A significant amount of research has been done on healthcare systems based on supervised learning. In this study, we present a generalized solution to detect visually observable symptoms on faces using semi-supervised anomaly detection combined with machine vision algorithms. We rely on the disease-related statistical facts to detect abnormalities and classify them into multiple categories to narrow down the possible medical reasons of detecting. Our method is in contrast with most existing approaches, which are limited by the availability of labeled training data required for supervised learning, and therefore offers the major advantage of flagging any unusual and visually observable symptoms.

Functions of graphemic and phonemic codes in visual word-recognition.

PubMed

Meyer, D E; Schvaneveldt, R W; Ruddy, M G

1974-03-01

Previous investigators have argued that printed words are recognized directly from visual representations and/or phonological representations obtained through phonemic recoding. The present research tested these hypotheses by manipulating graphemic and phonemic relations within various pairs of letter strings. Ss in two experiments classified the pairs as words or nonwords. Reaction times and error rates were relatively small for word pairs (e.g., BRIBE-TRIBE) that were both graphemically, and phonemically similar. Graphemic similarity alone inhibited performance on other word pairs (e.g., COUCH-TOUCH). These and other results suggest that phonological representations play a significant role in visual word recognition and that there is a dependence between successive phonemic-encoding operations. An encoding-bias model is proposed to explain the data.

SemVisM: semantic visualizer for medical image

NASA Astrophysics Data System (ADS)

Landaeta, Luis; La Cruz, Alexandra; Baranya, Alexander; Vidal, María.-Esther

2015-01-01

SemVisM is a toolbox that combines medical informatics and computer graphics tools for reducing the semantic gap between low-level features and high-level semantic concepts/terms in the images. This paper presents a novel strategy for visualizing medical data annotated semantically, combining rendering techniques, and segmentation algorithms. SemVisM comprises two main components: i) AMORE (A Modest vOlume REgister) to handle input data (RAW, DAT or DICOM) and to initially annotate the images using terms defined on medical ontologies (e.g., MesH, FMA or RadLex), and ii) VOLPROB (VOlume PRObability Builder) for generating the annotated volumetric data containing the classified voxels that belong to a particular tissue. SemVisM is built on top of the semantic visualizer ANISE.1

A Prototype SSVEP Based Real Time BCI Gaming System

PubMed Central

Martišius, Ignas

2016-01-01

Although brain-computer interface technology is mainly designed with disabled people in mind, it can also be beneficial to healthy subjects, for example, in gaming or virtual reality systems. In this paper we discuss the typical architecture, paradigms, requirements, and limitations of electroencephalogram-based gaming systems. We have developed a prototype three-class brain-computer interface system, based on the steady state visually evoked potentials paradigm and the Emotiv EPOC headset. An online target shooting game, implemented in the OpenViBE environment, has been used for user feedback. The system utilizes wave atom transform for feature extraction, achieving an average accuracy of 78.2% using linear discriminant analysis classifier, 79.3% using support vector machine classifier with a linear kernel, and 80.5% using a support vector machine classifier with a radial basis function kernel. PMID:27051414

A Prototype SSVEP Based Real Time BCI Gaming System.

PubMed

Martišius, Ignas; Damaševičius, Robertas

2016-01-01

Although brain-computer interface technology is mainly designed with disabled people in mind, it can also be beneficial to healthy subjects, for example, in gaming or virtual reality systems. In this paper we discuss the typical architecture, paradigms, requirements, and limitations of electroencephalogram-based gaming systems. We have developed a prototype three-class brain-computer interface system, based on the steady state visually evoked potentials paradigm and the Emotiv EPOC headset. An online target shooting game, implemented in the OpenViBE environment, has been used for user feedback. The system utilizes wave atom transform for feature extraction, achieving an average accuracy of 78.2% using linear discriminant analysis classifier, 79.3% using support vector machine classifier with a linear kernel, and 80.5% using a support vector machine classifier with a radial basis function kernel.

Measures and Models for Estimating and Predicting Cognitive Fatigue

NASA Technical Reports Server (NTRS)

Trejo, Leonard J.; Kochavi, Rebekah; Kubitz, Karla; Montgomery, Leslie D.; Rosipal, Roman; Matthews, Bryan

2004-01-01

We analyzed EEG and ERPs in a fatiguing mental task and created statistical models for single subjects. Seventeen subjects (4 F, 18-38 y) viewed 4-digit problems (e.g., 3+5-2+7=15) on a computer, solved the problems, and pressed keys to respond (intertrial interval = 1 s). Subjects performed until either they felt exhausted or three hours had elapsed. Re- and post-task measures of mood (Activation Deactivation Adjective Checklist, Visual Analogue Mood Scale) confirmed that fatigue increased and energy decreased over time. We tested response times (RT); amplitudes of ERP components N1, P2, P300, readiness potentials; and amplitudes of frontal theta and parietal alpha rhythms for change as a function of time. For subjects who completed 3 h (n=9) we analyzed 12 15-min blocks. For subjects who completed at least 1.5 h (n=17), we analyzed the first-, middle-, and last 100 error-free trials. Mean RT rose from 6.7 s to 8.5 s over time. We found no changes in the amplitudes of ERP components. In both analyses, amplitudes of frontal theta and parietal alpha rose by 30% or more over time. We used 30-channel EEG frequency spectra to model the effects of time in single subjects using a kernel partial least squares classifier. We classified 3.5s EEG segments as being from the first 100 or the last 100 trials, using random sub-samples of each class. Test set accuracies ranged from 63.9% to 99.6% correct. Only 2 of 17 subjects had mean accuracies lower than 80%. The results suggest that EEG accurately classifies periods of cognitive fatigue in 90% of subjects.

Grounding grammatical categories: attention bias in hand space influences grammatical congruency judgment of Chinese nominal classifiers.

PubMed

Lobben, Marit; D'Ascenzo, Stefania

2015-01-01

Embodied cognitive theories predict that linguistic conceptual representations are grounded and continually represented in real world, sensorimotor experiences. However, there is an on-going debate on whether this also holds for abstract concepts. Grammar is the archetype of abstract knowledge, and therefore constitutes a test case against embodied theories of language representation. Former studies have largely focussed on lexical-level embodied representations. In the present study we take the grounding-by-modality idea a step further by using reaction time (RT) data from the linguistic processing of nominal classifiers in Chinese. We take advantage of an independent body of research, which shows that attention in hand space is biased. Specifically, objects near the hand consistently yield shorter RTs as a function of readiness for action on graspable objects within reaching space, and the same biased attention inhibits attentional disengagement. We predicted that this attention bias would equally apply to the graspable object classifier but not to the big object classifier. Chinese speakers (N = 22) judged grammatical congruency of classifier-noun combinations in two conditions: graspable object classifier and big object classifier. We found that RTs for the graspable object classifier were significantly faster in congruent combinations, and significantly slower in incongruent combinations, than the big object classifier. There was no main effect on grammatical violations, but rather an interaction effect of classifier type. Thus, we demonstrate here grammatical category-specific effects pertaining to the semantic content and by extension the visual and tactile modality of acquisition underlying the acquisition of these categories. We conclude that abstract grammatical categories are subjected to the same mechanisms as general cognitive and neurophysiological processes and may therefore be grounded.

Grounding grammatical categories: attention bias in hand space influences grammatical congruency judgment of Chinese nominal classifiers

PubMed Central

Lobben, Marit; D’Ascenzo, Stefania

2015-01-01

Embodied cognitive theories predict that linguistic conceptual representations are grounded and continually represented in real world, sensorimotor experiences. However, there is an on-going debate on whether this also holds for abstract concepts. Grammar is the archetype of abstract knowledge, and therefore constitutes a test case against embodied theories of language representation. Former studies have largely focussed on lexical-level embodied representations. In the present study we take the grounding-by-modality idea a step further by using reaction time (RT) data from the linguistic processing of nominal classifiers in Chinese. We take advantage of an independent body of research, which shows that attention in hand space is biased. Specifically, objects near the hand consistently yield shorter RTs as a function of readiness for action on graspable objects within reaching space, and the same biased attention inhibits attentional disengagement. We predicted that this attention bias would equally apply to the graspable object classifier but not to the big object classifier. Chinese speakers (N = 22) judged grammatical congruency of classifier-noun combinations in two conditions: graspable object classifier and big object classifier. We found that RTs for the graspable object classifier were significantly faster in congruent combinations, and significantly slower in incongruent combinations, than the big object classifier. There was no main effect on grammatical violations, but rather an interaction effect of classifier type. Thus, we demonstrate here grammatical category-specific effects pertaining to the semantic content and by extension the visual and tactile modality of acquisition underlying the acquisition of these categories. We conclude that abstract grammatical categories are subjected to the same mechanisms as general cognitive and neurophysiological processes and may therefore be grounded. PMID:26379611

Estimating age ratios and size of pacific walrus herds on coastal haulouts using video imaging.

PubMed

Monson, Daniel H; Udevitz, Mark S; Jay, Chadwick V

2013-01-01

During Arctic summers, sea ice provides resting habitat for Pacific walruses as it drifts over foraging areas in the eastern Chukchi Sea. Climate-driven reductions in sea ice have recently created ice-free conditions in the Chukchi Sea by late summer causing walruses to rest at coastal haulouts along the Chukotka and Alaska coasts, which provides an opportunity to study walruses at relatively accessible locations. Walrus age can be determined from the ratio of tusk length to snout dimensions. We evaluated use of images obtained from a gyro-stabilized video system mounted on a helicopter flying at high altitudes (to avoid disturbance) to classify the sex and age of walruses hauled out on Alaska beaches in 2010-2011. We were able to classify 95% of randomly selected individuals to either an 8- or 3-category age class, and we found measurement-based age classifications were more repeatable than visual classifications when using images presenting the correct head profile. Herd density at coastal haulouts averaged 0.88 walruses/m(2) (std. err. = 0.02), herd size ranged from 8,300 to 19,400 (CV 0.03-0.06) and we documented ∼30,000 animals along ∼1 km of beach in 2011. Within the herds, dependent walruses (0-2 yr-olds) tended to be located closer to water, and this tendency became more pronounced as the herd spent more time on the beach. Therefore, unbiased estimation of herd age-ratios will require a sampling design that allows for spatial and temporal structuring. In addition, randomly sampling walruses available at the edge of the herd for other purposes (e.g., tagging, biopsying) will not sample walruses with an age structure representative of the herd. Sea ice losses are projected to continue, and population age structure data collected with aerial videography at coastal haulouts may provide demographic information vital to ongoing efforts to understand effects of climate change on this species.

Estimating age ratios and size of Pacific walrus herds on coastal haulouts using video imaging

USGS Publications Warehouse

Monson, Daniel H.; Udevitz, Mark S.; Jay, Chadwick V.

2013-01-01

During Arctic summers, sea ice provides resting habitat for Pacific walruses as it drifts over foraging areas in the eastern Chukchi Sea. Climate-driven reductions in sea ice have recently created ice-free conditions in the Chukchi Sea by late summer causing walruses to rest at coastal haulouts along the Chukotka and Alaska coasts, which provides an opportunity to study walruses at relatively accessible locations. Walrus age can be determined from the ratio of tusk length to snout dimensions. We evaluated use of images obtained from a gyro-stabilized video system mounted on a helicopter flying at high altitudes (to avoid disturbance) to classify the sex and age of walruses hauled out on Alaska beaches in 2010–2011. We were able to classify 95% of randomly selected individuals to either an 8- or 3-category age class, and we found measurement-based age classifications were more repeatable than visual classifications when using images presenting the correct head profile. Herd density at coastal haulouts averaged 0.88 walruses/m2 (std. err. = 0.02), herd size ranged from 8,300 to 19,400 (CV 0.03–0.06) and we documented ~30,000 animals along ~1 km of beach in 2011. Within the herds, dependent walruses (0–2 yr-olds) tended to be located closer to water, and this tendency became more pronounced as the herd spent more time on the beach. Therefore, unbiased estimation of herd age-ratios will require a sampling design that allows for spatial and temporal structuring. In addition, randomly sampling walruses available at the edge of the herd for other purposes (e.g., tagging, biopsying) will not sample walruses with an age structure representative of the herd. Sea ice losses are projected to continue, and population age structure data collected with aerial videography at coastal haulouts may provide demographic information vital to ongoing efforts to understand effects of climate change on this species.

Estimating Age Ratios and Size of Pacific Walrus Herds on Coastal Haulouts using Video Imaging

PubMed Central

Monson, Daniel H.; Udevitz, Mark S.; Jay, Chadwick V.

2013-01-01

During Arctic summers, sea ice provides resting habitat for Pacific walruses as it drifts over foraging areas in the eastern Chukchi Sea. Climate-driven reductions in sea ice have recently created ice-free conditions in the Chukchi Sea by late summer causing walruses to rest at coastal haulouts along the Chukotka and Alaska coasts, which provides an opportunity to study walruses at relatively accessible locations. Walrus age can be determined from the ratio of tusk length to snout dimensions. We evaluated use of images obtained from a gyro-stabilized video system mounted on a helicopter flying at high altitudes (to avoid disturbance) to classify the sex and age of walruses hauled out on Alaska beaches in 2010–2011. We were able to classify 95% of randomly selected individuals to either an 8- or 3-category age class, and we found measurement-based age classifications were more repeatable than visual classifications when using images presenting the correct head profile. Herd density at coastal haulouts averaged 0.88 walruses/m2 (std. err. = 0.02), herd size ranged from 8,300 to 19,400 (CV 0.03–0.06) and we documented ∼30,000 animals along ∼1 km of beach in 2011. Within the herds, dependent walruses (0–2 yr-olds) tended to be located closer to water, and this tendency became more pronounced as the herd spent more time on the beach. Therefore, unbiased estimation of herd age-ratios will require a sampling design that allows for spatial and temporal structuring. In addition, randomly sampling walruses available at the edge of the herd for other purposes (e.g., tagging, biopsying) will not sample walruses with an age structure representative of the herd. Sea ice losses are projected to continue, and population age structure data collected with aerial videography at coastal haulouts may provide demographic information vital to ongoing efforts to understand effects of climate change on this species. PMID:23936106

Machine learning and dyslexia: Classification of individual structural neuro-imaging scans of students with and without dyslexia

PubMed Central

Tamboer, P.; Vorst, H.C.M.; Ghebreab, S.; Scholte, H.S.

2016-01-01

Meta-analytic studies suggest that dyslexia is characterized by subtle and spatially distributed variations in brain anatomy, although many variations failed to be significant after corrections of multiple comparisons. To circumvent issues of significance which are characteristic for conventional analysis techniques, and to provide predictive value, we applied a machine learning technique – support vector machine – to differentiate between subjects with and without dyslexia. In a sample of 22 students with dyslexia (20 women) and 27 students without dyslexia (25 women) (18–21 years), a classification performance of 80% (p < 0.001; d-prime = 1.67) was achieved on the basis of differences in gray matter (sensitivity 82%, specificity 78%). The voxels that were most reliable for classification were found in the left occipital fusiform gyrus (LOFG), in the right occipital fusiform gyrus (ROFG), and in the left inferior parietal lobule (LIPL). Additionally, we found that classification certainty (e.g. the percentage of times a subject was correctly classified) correlated with severity of dyslexia (r = 0.47). Furthermore, various significant correlations were found between the three anatomical regions and behavioural measures of spelling, phonology and whole-word-reading. No correlations were found with behavioural measures of short-term memory and visual/attentional confusion. These data indicate that the LOFG, ROFG and the LIPL are neuro-endophenotype and potentially biomarkers for types of dyslexia related to reading, spelling and phonology. In a second and independent sample of 876 young adults of a general population, the trained classifier of the first sample was tested, resulting in a classification performance of 59% (p = 0.07; d-prime = 0.65). This decline in classification performance resulted from a large percentage of false alarms. This study provided support for the use of machine learning in anatomical brain imaging. PMID:27114899

Retinal phenotypic characterization of patients with ABCA4 retinopathydue to the homozygous p.Ala1773Val mutation

PubMed Central

López-Rubio, Salvador; Chacon-Camacho, Oscar F.; Matsui, Rodrigo; Guadarrama-Vallejo, Dalia; Astiazarán, Mirena C.

2018-01-01

Purpose To describe the retinal clinical features of a group of Mexican patients with Stargardt disease carrying the uncommon p.Ala1773Val founder mutation in ABCA4. Methods Ten patients carrying the p.Ala1773Val mutation, nine of them homozygously, were included. Visual function studies included best-corrected visual acuity, electroretinography, Goldmann kinetic visual fields, and full-field electroretinography (ERG). In addition, imaging studies, such as optical coherence tomography (OCT), short-wave autofluorescence imaging, and quantitative analyses of hypofluorescence, were performed in each patient. Results Best-corrected visual acuities ranged from 20/200 to 4/200. The median age of the patients at diagnosis was 23.3 years. The majority of the patients had photophobia and nyctalopia, and were classified as Fishman stage 4 (widespread choriocapillaris atrophy, resorption of flecks, and greatly reduced ERG amplitudes). An atypical retinal pigmentation pattern was observed in the patients, and the majority showed cone-rod dystrophy on full-field ERG. In vivo retinal microstructure assessment with OCT demonstrated central retinal thinning, variable loss of photoreceptors, and three different patterns of structural retinal degeneration. Two dissimilar patterns of abnormal autofluorescence were observed. No apparent age-related differences in the pattern of retinal degeneration were observed. Conclusions The results indicate that this particular mutation in ABCA4 is associated with a severe retinal phenotype and thus, could be classified as null. Careful phenotyping of patients carrying specific mutations in ABCA4 is essential to enhance our understanding of disease expression linked to particular mutations and the resulting genotype–phenotype correlations. PMID:29422768

Multispectral image analysis for object recognition and classification

NASA Astrophysics Data System (ADS)

Viau, C. R.; Payeur, P.; Cretu, A.-M.

2016-05-01

Computer and machine vision applications are used in numerous fields to analyze static and dynamic imagery in order to assist or automate decision-making processes. Advancements in sensor technologies now make it possible to capture and visualize imagery at various wavelengths (or bands) of the electromagnetic spectrum. Multispectral imaging has countless applications in various fields including (but not limited to) security, defense, space, medical, manufacturing and archeology. The development of advanced algorithms to process and extract salient information from the imagery is a critical component of the overall system performance. The fundamental objective of this research project was to investigate the benefits of combining imagery from the visual and thermal bands of the electromagnetic spectrum to improve the recognition rates and accuracy of commonly found objects in an office setting. A multispectral dataset (visual and thermal) was captured and features from the visual and thermal images were extracted and used to train support vector machine (SVM) classifiers. The SVM's class prediction ability was evaluated separately on the visual, thermal and multispectral testing datasets.

Object oriented classification of high resolution data for inventory of horticultural crops

NASA Astrophysics Data System (ADS)

Hebbar, R.; Ravishankar, H. M.; Trivedi, S.; Subramoniam, S. R.; Uday, R.; Dadhwal, V. K.

2014-11-01

High resolution satellite images are associated with large variance and thus, per pixel classifiers often result in poor accuracy especially in delineation of horticultural crops. In this context, object oriented techniques are powerful and promising methods for classification. In the present study, a semi-automatic object oriented feature extraction model has been used for delineation of horticultural fruit and plantation crops using Erdas Objective Imagine. Multi-resolution data from Resourcesat LISS-IV and Cartosat-1 have been used as source data in the feature extraction model. Spectral and textural information along with NDVI were used as inputs for generation of Spectral Feature Probability (SFP) layers using sample training pixels. The SFP layers were then converted into raster objects using threshold and clump function resulting in pixel probability layer. A set of raster and vector operators was employed in the subsequent steps for generating thematic layer in the vector format. This semi-automatic feature extraction model was employed for classification of major fruit and plantations crops viz., mango, banana, citrus, coffee and coconut grown under different agro-climatic conditions. In general, the classification accuracy of about 75-80 per cent was achieved for these crops using object based classification alone and the same was further improved using minimal visual editing of misclassified areas. A comparison of on-screen visual interpretation with object oriented approach showed good agreement. It was observed that old and mature plantations were classified more accurately while young and recently planted ones (3 years or less) showed poor classification accuracy due to mixed spectral signature, wider spacing and poor stands of plantations. The results indicated the potential use of object oriented approach for classification of high resolution data for delineation of horticultural fruit and plantation crops. The present methodology is applicable at local levels and future development is focused on up-scaling the methodology for generation of fruit and plantation crop maps at regional and national level which is important for creation of database for overall horticultural crop development.

Mapping the Dynamics of Surface Water Extent 1999-2015 with Landsat 5, 7, and 8 Archives

NASA Astrophysics Data System (ADS)

Pickens, A. H.; Hansen, M.; Hancher, M.; Potapov, P.

2016-12-01

Surface water extent fluctuates through both seasons and years due to changes in climatic conditions and human extraction and impoundments. This study maps the presence of surface water every month since January 1999, evaluates the detection reliability, visualizes the trends, and explores future applications. The Global Land Analysis and Discovery group at the University of Maryland developed a 30-m mask of persistent water during the growing seasons of 2000-2012 in conjunction with the Global Forest Change product published by Hansen et al. in 2013. A total of 654,178 Landsat 7 scenes were used for the study. Persistent water was defined as all pixels with water classified in more than 50% of observations over the study period. We validated this mask by stratifying and comparing against a random sample of 135 RapidEye, single-date images at 5-m resolution. It was found to have estimated user's and producer's accuracies of 94% and 88%, respectively. This estimated error is due primarily to temporal differences, such as dam construction, and to mixed water-land pixels along water body edges and narrow rivers. In order to investigate temporal extent dynamics, we expanded our analysis of surface water to classify every Landsat 5, 7, and 8 scene since 1999, augmented with elevation data from SRTM and ASTER, via a series of decision trees applied using Google Earth Engine. The water and land observations are aggregated per each month of each year. We developed a model to visualize the dynamic trend in surface water presence since 1999, either per month or annually as shown below. This model can be used directly to assess the seasonal and inter-annual trends globally or regionally, or the raw monthly counts can be used for more intensive hydrological analysis and as inputs for other related studies such as wetland mapping.

Use of Lot Quality Assurance Sampling to Ascertain Levels of Drug Resistant Tuberculosis in Western Kenya

PubMed Central

Cohen, Ted; Zignol, Matteo; Nyakan, Edwin; Hedt-Gauthier, Bethany L.; Gardner, Adrian; Kamle, Lydia; Injera, Wilfred; Carter, E. Jane

2016-01-01

Objective To classify the prevalence of multi-drug resistant tuberculosis (MDR-TB) in two different geographic settings in western Kenya using the Lot Quality Assurance Sampling (LQAS) methodology. Design The prevalence of drug resistance was classified among treatment-naïve smear positive TB patients in two settings, one rural and one urban. These regions were classified as having high or low prevalence of MDR-TB according to a static, two-way LQAS sampling plan selected to classify high resistance regions at greater than 5% resistance and low resistance regions at less than 1% resistance. Results This study classified both the urban and rural settings as having low levels of TB drug resistance. Out of the 105 patients screened in each setting, two patients were diagnosed with MDR-TB in the urban setting and one patient was diagnosed with MDR-TB in the rural setting. An additional 27 patients were diagnosed with a variety of mono- and poly- resistant strains. Conclusion Further drug resistance surveillance using LQAS may help identify the levels and geographical distribution of drug resistance in Kenya and may have applications in other countries in the African Region facing similar resource constraints. PMID:27167381

Use of Lot Quality Assurance Sampling to Ascertain Levels of Drug Resistant Tuberculosis in Western Kenya.

PubMed

Jezmir, Julia; Cohen, Ted; Zignol, Matteo; Nyakan, Edwin; Hedt-Gauthier, Bethany L; Gardner, Adrian; Kamle, Lydia; Injera, Wilfred; Carter, E Jane

2016-01-01

To classify the prevalence of multi-drug resistant tuberculosis (MDR-TB) in two different geographic settings in western Kenya using the Lot Quality Assurance Sampling (LQAS) methodology. The prevalence of drug resistance was classified among treatment-naïve smear positive TB patients in two settings, one rural and one urban. These regions were classified as having high or low prevalence of MDR-TB according to a static, two-way LQAS sampling plan selected to classify high resistance regions at greater than 5% resistance and low resistance regions at less than 1% resistance. This study classified both the urban and rural settings as having low levels of TB drug resistance. Out of the 105 patients screened in each setting, two patients were diagnosed with MDR-TB in the urban setting and one patient was diagnosed with MDR-TB in the rural setting. An additional 27 patients were diagnosed with a variety of mono- and poly- resistant strains. Further drug resistance surveillance using LQAS may help identify the levels and geographical distribution of drug resistance in Kenya and may have applications in other countries in the African Region facing similar resource constraints.

AUTOCLASSIFICATION OF THE VARIABLE 3XMM SOURCES USING THE RANDOM FOREST MACHINE LEARNING ALGORITHM

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

Farrell, Sean A.; Murphy, Tara; Lo, Kitty K., E-mail: s.farrell@physics.usyd.edu.au

In the current era of large surveys and massive data sets, autoclassification of astrophysical sources using intelligent algorithms is becoming increasingly important. In this paper we present the catalog of variable sources in the Third XMM-Newton Serendipitous Source catalog (3XMM) autoclassified using the Random Forest machine learning algorithm. We used a sample of manually classified variable sources from the second data release of the XMM-Newton catalogs (2XMMi-DR2) to train the classifier, obtaining an accuracy of ∼92%. We also evaluated the effectiveness of identifying spurious detections using a sample of spurious sources, achieving an accuracy of ∼95%. Manual investigation of amore » random sample of classified sources confirmed these accuracy levels and showed that the Random Forest machine learning algorithm is highly effective at automatically classifying 3XMM sources. Here we present the catalog of classified 3XMM variable sources. We also present three previously unidentified unusual sources that were flagged as outlier sources by the algorithm: a new candidate supergiant fast X-ray transient, a 400 s X-ray pulsar, and an eclipsing 5 hr binary system coincident with a known Cepheid.« less

Deep versus periventricular white matter lesions and cognitive function in a community sample of middle-aged participants.

PubMed

Soriano-Raya, Juan José; Miralbell, Júlia; López-Cancio, Elena; Bargalló, Núria; Arenillas, Juan Francisco; Barrios, Maite; Cáceres, Cynthia; Toran, Pere; Alzamora, Maite; Dávalos, Antoni; Mataró, Maria

2012-09-01

The association of cerebral white matter lesions (WMLs) with cognitive status is not well understood in middle-aged individuals. Our aim was to determine the specific contribution of periventricular hyperintensities (PVHs) and deep white matter hyperintensities (DWMHs) to cognitive function in a community sample of asymptomatic participants aged 50 to 65 years. One hundred stroke- and dementia-free adults completed a comprehensive neuropsychological battery and brain MRI protocol. Participants were classified according to PVH and DWMH scores (Fazekas scale). We dichotomized our sample into low grade WMLs (participants without or with mild lesions) and high grade WMLs (participants with moderate or severe lesions). Analyses were performed separately in PVH and DWMH groups. High grade DWMHs were associated with significantly lower scores in executive functioning (-0.45 standard deviations [SD]), attention (-0.42 SD), verbal fluency (-0.68 SD), visual memory (-0.52 SD), visuospatial skills (-0.79 SD), and psychomotor speed (-0.46 SD). Further analyses revealed that high grade DWMHs were also associated with a three- to fourfold increased risk of impaired scores (i.e.,<1.5 SD) in executive functioning, verbal fluency, visuospatial skills, and psychomotor speed. Our findings suggest that only DWMHs, not PVHs, are related to diminished cognitive function in middle-aged individuals. (JINS, 2012, 18, 1-12).

Persistent and Repetitive Visual Disturbances in Migraine: A Review.

PubMed

Schankin, Christoph J; Viana, Michele; Goadsby, Peter J

2017-01-01

Visual disturbances in migraineurs, such as visual aura, are typically episodic, that is, associated with the headache attack, and overlaid by head pain and other symptoms that impact the patient. In some patients, however, visual symptoms are dominant due to frequency (migraine aura status), duration (persistent migraine aura and other persistent positive visual phenomena), or complexity (visual snow syndrome). These syndromes are more rare and challenging to classify in clinical practice resulting in a lack of systematic studies on pathophysiology and treatment. We aim at describing clinical features and pathophysiological concepts of typical migraine aura with a focus on cortical spreading depression and differentiation from non-typical migraine aura. Additionally, we discuss nomenclature and the specifics of migraine aura status, persistent migraine aura, persistent positive visual phenomena, visual snow, and other migrainous visual disturbances. The term migraine with prolonged aura might be a useful bridge between typical aura and persistent aura. Further studies would be necessary to assess whether a return of the classification category eventually helps diagnosing or treating patients more effectively. A practical approach is presented to help the treating physician to assign the correct diagnosis and to choose a medication for treatment that has been successful in case reports of these rare but disabling conditions. © 2016 American Headache Society.

Stackable differential mobility analyzer for aerosol measurement

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

Cheng, Meng-Dawn; Chen, Da-Ren

2007-05-08

A multi-stage differential mobility analyzer (MDMA) for aerosol measurements includes a first electrode or grid including at least one inlet or injection slit for receiving an aerosol including charged particles for analysis. A second electrode or grid is spaced apart from the first electrode. The second electrode has at least one sampling outlet disposed at a plurality different distances along its length. A volume between the first and the second electrode or grid between the inlet or injection slit and a distal one of the plurality of sampling outlets forms a classifying region, the first and second electrodes for chargingmore » to suitable potentials to create an electric field within the classifying region. At least one inlet or injection slit in the second electrode receives a sheath gas flow into an upstream end of the classifying region, wherein each sampling outlet functions as an independent DMA stage and classifies different size ranges of charged particles based on electric mobility simultaneously.« less

Predicting Classifier Performance with Limited Training Data: Applications to Computer-Aided Diagnosis in Breast and Prostate Cancer

PubMed Central

Basavanhally, Ajay; Viswanath, Satish; Madabhushi, Anant

2015-01-01

Clinical trials increasingly employ medical imaging data in conjunction with supervised classifiers, where the latter require large amounts of training data to accurately model the system. Yet, a classifier selected at the start of the trial based on smaller and more accessible datasets may yield inaccurate and unstable classification performance. In this paper, we aim to address two common concerns in classifier selection for clinical trials: (1) predicting expected classifier performance for large datasets based on error rates calculated from smaller datasets and (2) the selection of appropriate classifiers based on expected performance for larger datasets. We present a framework for comparative evaluation of classifiers using only limited amounts of training data by using random repeated sampling (RRS) in conjunction with a cross-validation sampling strategy. Extrapolated error rates are subsequently validated via comparison with leave-one-out cross-validation performed on a larger dataset. The ability to predict error rates as dataset size increases is demonstrated on both synthetic data as well as three different computational imaging tasks: detecting cancerous image regions in prostate histopathology, differentiating high and low grade cancer in breast histopathology, and detecting cancerous metavoxels in prostate magnetic resonance spectroscopy. For each task, the relationships between 3 distinct classifiers (k-nearest neighbor, naive Bayes, Support Vector Machine) are explored. Further quantitative evaluation in terms of interquartile range (IQR) suggests that our approach consistently yields error rates with lower variability (mean IQRs of 0.0070, 0.0127, and 0.0140) than a traditional RRS approach (mean IQRs of 0.0297, 0.0779, and 0.305) that does not employ cross-validation sampling for all three datasets. PMID:25993029

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.

A qualitative signature for early diagnosis of hepatocellular carcinoma based on relative expression orderings.

PubMed

Ao, Lu; Zhang, Zimei; Guan, Qingzhou; Guo, Yating; Guo, You; Zhang, Jiahui; Lv, Xingwei; Huang, Haiyan; Zhang, Huarong; Wang, Xianlong; Guo, Zheng

2018-04-23

Currently, using biopsy specimens to confirm suspicious liver lesions of early hepatocellular carcinoma are not entirely reliable because of insufficient sampling amount and inaccurate sampling location. It is necessary to develop a signature to aid early hepatocellular carcinoma diagnosis using biopsy specimens even when the sampling location is inaccurate. Based on the within-sample relative expression orderings of gene pairs, we identified a simple qualitative signature to distinguish both hepatocellular carcinoma and adjacent non-tumour tissues from cirrhosis tissues of non-hepatocellular carcinoma patients. A signature consisting of 19 gene pairs was identified in the training data sets and validated in 2 large collections of samples from biopsy and surgical resection specimens. For biopsy specimens, 95.7% of 141 hepatocellular carcinoma tissues and all (100%) of 108 cirrhosis tissues of non-hepatocellular carcinoma patients were correctly classified. Especially, all (100%) of 60 hepatocellular carcinoma adjacent normal tissues and 77.5% of 80 hepatocellular carcinoma adjacent cirrhosis tissues were classified to hepatocellular carcinoma. For surgical resection specimens, 99.7% of 733 hepatocellular carcinoma specimens were correctly classified to hepatocellular carcinoma, while 96.1% of 254 hepatocellular carcinoma adjacent cirrhosis tissues and 95.9% of 538 hepatocellular carcinoma adjacent normal tissues were classified to hepatocellular carcinoma. In contrast, 17.0% of 47 cirrhosis from non-hepatocellular carcinoma patients waiting for liver transplantation were classified to hepatocellular carcinoma, indicating that some patients with long-lasting cirrhosis could have already gained hepatocellular carcinoma characteristics. The signature can distinguish both hepatocellular carcinoma tissues and tumour-adjacent tissues from cirrhosis tissues of non-hepatocellular carcinoma patients even using inaccurately sampled biopsy specimens, which can aid early diagnosis of hepatocellular carcinoma. © 2018 The Authors. Liver International Published by John Wiley & Sons Ltd.

Drought Management Activities of the National Drought Mitigation Center (NDMC): Contributions Toward a Global Drought Early Warning System (GDEWS)

NASA Astrophysics Data System (ADS)

Stumpf, A.; Lachiche, N.; Malet, J.; Kerle, N.; Puissant, A.

2011-12-01

VHR satellite images have become a primary source for landslide inventory mapping after major triggering events such as earthquakes and heavy rainfalls. Visual image interpretation is still the prevailing standard method for operational purposes but is time-consuming and not well suited to fully exploit the increasingly better supply of remote sensing data. Recent studies have addressed the development of more automated image analysis workflows for landslide inventory mapping. In particular object-oriented approaches that account for spatial and textural image information have been demonstrated to be more adequate than pixel-based classification but manually elaborated rule-based classifiers are difficult to adapt under changing scene characteristics. Machine learning algorithm allow learning classification rules for complex image patterns from labelled examples and can be adapted straightforwardly with available training data. In order to reduce the amount of costly training data active learning (AL) has evolved as a key concept to guide the sampling for many applications. The underlying idea of AL is to initialize a machine learning model with a small training set, and to subsequently exploit the model state and data structure to iteratively select the most valuable samples that should be labelled by the user. With relatively few queries and labelled samples, an AL strategy yields higher accuracies than an equivalent classifier trained with many randomly selected samples. This study addressed the development of an AL method for landslide mapping from VHR remote sensing images with special consideration of the spatial distribution of the samples. Our approach [1] is based on the Random Forest algorithm and considers the classifier uncertainty as well as the variance of potential sampling regions to guide the user towards the most valuable sampling areas. The algorithm explicitly searches for compact regions and thereby avoids a spatially disperse sampling pattern inherent to most other AL methods. The accuracy, the sampling time and the computational runtime of the algorithm were evaluated on multiple satellite images capturing recent large scale landslide events. Sampling between 1-4% of the study areas the accuracies between 74% and 80% were achieved, whereas standard sampling schemes yielded only accuracies between 28% and 50% with equal sampling costs. Compared to commonly used point-wise AL algorithm the proposed approach significantly reduces the number of iterations and hence the computational runtime. Since the user can focus on relatively few compact areas (rather than on hundreds of distributed points) the overall labeling time is reduced by more than 50% compared to point-wise queries. An experimental evaluation of multiple expert mappings demonstrated strong relationships between the uncertainties of the experts and the machine learning model. It revealed that the achieved accuracies are within the range of the inter-expert disagreement and that it will be indispensable to consider ground truth uncertainties to truly achieve further enhancements in the future. The proposed method is generally applicable to a wide range of optical satellite images and landslide types. [1] A. Stumpf, N. Lachiche, J.-P. Malet, N. Kerle, and A. Puissant, Active learning in the spatial domain for remote sensing image classification, IEEE Transactions on Geosciece and Remote Sensing. 2013, DOI 10.1109/TGRS.2013.2262052.

What you see is what you expect: rapid scene understanding benefits from prior experience.

PubMed

Greene, Michelle R; Botros, Abraham P; Beck, Diane M; Fei-Fei, Li

2015-05-01

Although we are able to rapidly understand novel scene images, little is known about the mechanisms that support this ability. Theories of optimal coding assert that prior visual experience can be used to ease the computational burden of visual processing. A consequence of this idea is that more probable visual inputs should be facilitated relative to more unlikely stimuli. In three experiments, we compared the perceptions of highly improbable real-world scenes (e.g., an underwater press conference) with common images matched for visual and semantic features. Although the two groups of images could not be distinguished by their low-level visual features, we found profound deficits related to the improbable images: Observers wrote poorer descriptions of these images (Exp. 1), had difficulties classifying the images as unusual (Exp. 2), and even had lower sensitivity to detect these images in noise than to detect their more probable counterparts (Exp. 3). Taken together, these results place a limit on our abilities for rapid scene perception and suggest that perception is facilitated by prior visual experience.

Fuzzy Classification of High Resolution Remote Sensing Scenes Using Visual Attention Features.

PubMed

Li, Linyi; Xu, Tingbao; Chen, Yun

2017-01-01

In recent years the spatial resolutions of remote sensing images have been improved greatly. However, a higher spatial resolution image does not always lead to a better result of automatic scene classification. Visual attention is an important characteristic of the human visual system, which can effectively help to classify remote sensing scenes. In this study, a novel visual attention feature extraction algorithm was proposed, which extracted visual attention features through a multiscale process. And a fuzzy classification method using visual attention features (FC-VAF) was developed to perform high resolution remote sensing scene classification. FC-VAF was evaluated by using remote sensing scenes from widely used high resolution remote sensing images, including IKONOS, QuickBird, and ZY-3 images. FC-VAF achieved more accurate classification results than the others according to the quantitative accuracy evaluation indices. We also discussed the role and impacts of different decomposition levels and different wavelets on the classification accuracy. FC-VAF improves the accuracy of high resolution scene classification and therefore advances the research of digital image analysis and the applications of high resolution remote sensing images.

Fuzzy Classification of High Resolution Remote Sensing Scenes Using Visual Attention Features

PubMed Central

Xu, Tingbao; Chen, Yun

2017-01-01

In recent years the spatial resolutions of remote sensing images have been improved greatly. However, a higher spatial resolution image does not always lead to a better result of automatic scene classification. Visual attention is an important characteristic of the human visual system, which can effectively help to classify remote sensing scenes. In this study, a novel visual attention feature extraction algorithm was proposed, which extracted visual attention features through a multiscale process. And a fuzzy classification method using visual attention features (FC-VAF) was developed to perform high resolution remote sensing scene classification. FC-VAF was evaluated by using remote sensing scenes from widely used high resolution remote sensing images, including IKONOS, QuickBird, and ZY-3 images. FC-VAF achieved more accurate classification results than the others according to the quantitative accuracy evaluation indices. We also discussed the role and impacts of different decomposition levels and different wavelets on the classification accuracy. FC-VAF improves the accuracy of high resolution scene classification and therefore advances the research of digital image analysis and the applications of high resolution remote sensing images. PMID:28761440

A young woman with visual hallucinations, delusions of persecution and a history of performing arson with possible three-generation Fahr disease.

PubMed

Shirahama, M; Akiyoshi, J; Ishitobi, Y; Tanaka, Y; Tsuru, J; Matsushita, H; Hanada, H; Kodama, K

2010-01-01

Fahr disease (FD) is a rare neurological and psychiatric disorder. The disease is classified by intracranial calcification of the basal ganglia with the globus pallidus region being particularly affected. We examined a young woman with visual hallucinations, delusions of persecution and a history of performing arson with possible third-generation FD. Case report of third-generation FD. A 23-year-old woman was arrested for two arsons: i) The patient exhibited progressive psychotic symptoms, including visual hallucinations, delusion of injury, irritability, lability of mood, mental retardation and visual disorders and ii) Computed tomography (CT) imaging demonstrated bilateral calcifications of the basal ganglia (globus pallidus) in the patient, her mother and her grandmother. We found a family with a three-generation history of FD who exhibited calcification in the brain and mental retardation. Compared to her mother, the patient described here displayed anticipation of disease onset.

[Functional amblyopia].

PubMed

Avram, Elena; Stănilă, Adriana

2013-01-01

Amblyopia is a disorder of the visual system that represents unilateral or bi-lateral reduction of visual acuity in which an organic cause cannot be detected. The illness represents a syndrome of visual deficits, not only a deterioration of visual acuity. This syndrome includes: presence of crowding phenomena, contrast sensitivity deterioration, deficits in accommodation, deterioration of spatial orientation and ocular motility dysfunction. Depending on its etiology, amblyopia is classified into four main types: strabismic amblyopia, anisometropic amblyopia, isoametropic amblyopia and stimulus deprivation amblyopia. To successfully treat the "lazy eye" it is essential to remove the amblyopic factor with techniques addressing each disturbing factor. Techniques used for treating amblyopia include: occlusion, optical penalty or pharmacological, therapy with Levodopa and computer vision therapy. Amblyopia treatment is lengthy and it is very important to counsel not only the child but the whole family and to establish a relationship of trust between doctor and patient in order to get high treatment compliance and high child motivation.

Proactive interference from items previously stored in visual working memory.

PubMed

Makovski, Tal; Jiang, Yuhong V

2008-01-01

This study investigates the fate of information that was previously stored in visual working memory but that is no longer needed. Previous research has found inconsistent results, with some showing effective release of irrelevant information and others showing proactive interference. Using change detection tasks of colors or shapes, we show that participants tend to falsely classify a changed item as "no change" if it matches one of the memory items on the preceding trial. The interference is spatially specific: Memory for the preceding trial interferes more if it matches the feature value and the location of a test item than if it does not. Interference results from retaining information in visual working memory, since it is absent when items on the preceding trials are passively viewed, or are attended but not memorized. We conclude that people cannot fully eliminate unwanted visual information from current working memory tasks.

Multiclass classification of microarray data samples with a reduced number of genes

PubMed Central

2011-01-01

Background Multiclass classification of microarray data samples with a reduced number of genes is a rich and challenging problem in Bioinformatics research. The problem gets harder as the number of classes is increased. In addition, the performance of most classifiers is tightly linked to the effectiveness of mandatory gene selection methods. Critical to gene selection is the availability of estimates about the maximum number of genes that can be handled by any classification algorithm. Lack of such estimates may lead to either computationally demanding explorations of a search space with thousands of dimensions or classification models based on gene sets of unrestricted size. In the former case, unbiased but possibly overfitted classification models may arise. In the latter case, biased classification models unable to support statistically significant findings may be obtained. Results A novel bound on the maximum number of genes that can be handled by binary classifiers in binary mediated multiclass classification algorithms of microarray data samples is presented. The bound suggests that high-dimensional binary output domains might favor the existence of accurate and sparse binary mediated multiclass classifiers for microarray data samples. Conclusions A comprehensive experimental work shows that the bound is indeed useful to induce accurate and sparse multiclass classifiers for microarray data samples. PMID:21342522

Extracting duration information in a picture category decoding task using hidden Markov Models

NASA Astrophysics Data System (ADS)

Pfeiffer, Tim; Heinze, Nicolai; Frysch, Robert; Deouell, Leon Y.; Schoenfeld, Mircea A.; Knight, Robert T.; Rose, Georg

2016-04-01

Objective. Adapting classifiers for the purpose of brain signal decoding is a major challenge in brain-computer-interface (BCI) research. In a previous study we showed in principle that hidden Markov models (HMM) are a suitable alternative to the well-studied static classifiers. However, since we investigated a rather straightforward task, advantages from modeling of the signal could not be assessed. Approach. Here, we investigate a more complex data set in order to find out to what extent HMMs, as a dynamic classifier, can provide useful additional information. We show for a visual decoding problem that besides category information, HMMs can simultaneously decode picture duration without an additional training required. This decoding is based on a strong correlation that we found between picture duration and the behavior of the Viterbi paths. Main results. Decoding accuracies of up to 80% could be obtained for category and duration decoding with a single classifier trained on category information only. Significance. The extraction of multiple types of information using a single classifier enables the processing of more complex problems, while preserving good training results even on small databases. Therefore, it provides a convenient framework for online real-life BCI utilizations.

NASA GES DISC Level 2 Aerosol Analysis and Visualization Services

NASA Technical Reports Server (NTRS)

Wei, Jennifer; Petrenko, Maksym; Ichoku, Charles; Yang, Wenli; Johnson, James; Zhao, Peisheng; Kempler, Steve

2015-01-01

Overview of NASA GES DISC Level 2 aerosol analysis and visualization services: DQViz (Data Quality Visualization)MAPSS (Multi-sensor Aerosol Products Sampling System), and MAPSS_Explorer (Multi-sensor Aerosol Products Sampling System Explorer).

Using complex auditory-visual samples to produce emergent relations in children with autism.

PubMed

Groskreutz, Nicole C; Karsina, Allen; Miguel, Caio F; Groskreutz, Mark P

2010-03-01

Six participants with autism learned conditional relations between complex auditory-visual sample stimuli (dictated words and pictures) and simple visual comparisons (printed words) using matching-to-sample training procedures. Pre- and posttests examined potential stimulus control by each element of the complex sample when presented individually and emergence of additional conditional relations and oral labeling. Tests revealed class-consistent performance for all participants following training.

Hybrid Radar Emitter Recognition Based on Rough k-Means Classifier and Relevance Vector Machine

PubMed Central

Yang, Zhutian; Wu, Zhilu; Yin, Zhendong; Quan, Taifan; Sun, Hongjian

2013-01-01

Due to the increasing complexity of electromagnetic signals, there exists a significant challenge for recognizing radar emitter signals. In this paper, a hybrid recognition approach is presented that classifies radar emitter signals by exploiting the different separability of samples. The proposed approach comprises two steps, namely the primary signal recognition and the advanced signal recognition. In the former step, a novel rough k-means classifier, which comprises three regions, i.e., certain area, rough area and uncertain area, is proposed to cluster the samples of radar emitter signals. In the latter step, the samples within the rough boundary are used to train the relevance vector machine (RVM). Then RVM is used to recognize the samples in the uncertain area; therefore, the classification accuracy is improved. Simulation results show that, for recognizing radar emitter signals, the proposed hybrid recognition approach is more accurate, and presents lower computational complexity than traditional approaches. PMID:23344380

Identification of usual interstitial pneumonia pattern using RNA-Seq and machine learning: challenges and solutions.

PubMed

Choi, Yoonha; Liu, Tiffany Ting; Pankratz, Daniel G; Colby, Thomas V; Barth, Neil M; Lynch, David A; Walsh, P Sean; Raghu, Ganesh; Kennedy, Giulia C; Huang, Jing

2018-05-09

We developed a classifier using RNA sequencing data that identifies the usual interstitial pneumonia (UIP) pattern for the diagnosis of idiopathic pulmonary fibrosis. We addressed significant challenges, including limited sample size, biological and technical sample heterogeneity, and reagent and assay batch effects. We identified inter- and intra-patient heterogeneity, particularly within the non-UIP group. The models classified UIP on transbronchial biopsy samples with a receiver-operating characteristic area under the curve of ~ 0.9 in cross-validation. Using in silico mixed samples in training, we prospectively defined a decision boundary to optimize specificity at ≥85%. The penalized logistic regression model showed greater reproducibility across technical replicates and was chosen as the final model. The final model showed sensitivity of 70% and specificity of 88% in the test set. We demonstrated that the suggested methodologies appropriately addressed challenges of the sample size, disease heterogeneity and technical batch effects and developed a highly accurate and robust classifier leveraging RNA sequencing for the classification of UIP.

Molecular Characterization of Hypoderma SPP. in Domestic Ruminants from Turkey and Pakistan.

PubMed

Ahmed, Haroon; Simsek, Sami; Saki, Cem Ecmel; Kesik, Harun Kaya; Kilinc, Seyma Gunyakti

2017-08-01

The aim of this study was to determine the morphological and molecular characterization of Hypoderma spp. in cattle and yak from provinces in Turkey and Pakistan. In total, 78 Hypoderma larvae were collected from slaughtered animals in Turkey and Pakistan from October 2015 to January 2016. Thirty-eight of these 78 Hypoderma larvae were morphologically classified as third instar larvae (L3s) of Hypoderma bovis, 37 were classified as Hypoderma lineatum, and 3 were classified as suspected or unidentified. The restriction enzyme TaqI was used to differentiate the Hypoderma spp. by polymerase chain reaction (PCR)-restriction fragment length polymorphism (RFLP). According to the sequences and the PCR-RFLP results, all larval samples from cattle from Turkey were classified as H. bovis, except for 1 sample classified as H. lineatum. All Hypoderma larvae from Pakistan were classified as H. lineatum from cattle and as Hypoderma sinense from yak. This study provides the first molecular characterization of H. lineatum (cattle) and H. sinense (yak) in Pakistan based on PCR-RFLP and sequencing results.

Visual-somatosensory integration and balance: evidence for psychophysical integrative differences in aging.

PubMed

Mahoney, Jeannette R; Holtzer, Roee; Verghese, Joe

2014-01-01

Research detailing multisensory integration (MSI) processes in aging and their association with clinically relevant outcomes is virtually non-existent. To our knowledge, the relationship between MSI and balance has not been well-established in aging. Given known alterations in unisensory processing with increasing age, the aims of the current study were to determine differential behavioral patterns of MSI in aging and investigate whether MSI was significantly associated with balance and fall-risk. Seventy healthy older adults (M = 75 years; 58% female) participated in the current study. Participants were instructed to make speeded responses to visual, somatosensory, and visual-somatosensory (VS) stimuli. Based on reaction times (RTs) to all stimuli, participants were classified into one of two groups (MSI or NO MSI), depending on their MSI RT benefit. Static balance was assessed using mean unipedal stance time. Overall, results revealed that RTs to VS stimuli were significantly shorter than those elicited to constituent unisensory conditions. Further, the current experimental design afforded differential patterns of multisensory processing, with 75% of the elderly sample demonstrating multisensory enhancements. Interestingly, 25% of older adults did not demonstrate multisensory RT facilitation; a finding that was attributed to extremely fast RTs overall and specifically in response to somatosensory inputs. Individuals in the NO MSI group maintained significantly better unipedal stance times and reported less falls, compared to elders in the MSI group. This study reveals the existence of differential patterns of multisensory processing in aging, while describing the clinical translational value of MSI enhancements in predicting balance and falls risk.

Visual-Somatosensory Integration and Balance: Evidence for Psychophysical Integrative Differences in Aging

PubMed Central

Mahoney, Jeannette R.; Holtzer, Roee; Verghese, Joe

2014-01-01

Research detailing multisensory integration (MSI) processes in aging and their association with clinically relevant outcomes is virtually non-existent. To our knowledge, the relationship between MSI and balance has not been well-established in aging. Given known alterations in unisensory processing with increasing age, the aims of the current study were to determine differential behavioral patterns of MSI in aging and investigate whether MSI was significantly associated with balance and fall-risk. Seventy healthy older adults (M = 75 years; 58% female) participated in the current study. Participants were instructed to make speeded responses to visual, somatosensory, and visual-somatosensory (VS) stimuli. Based on reaction times (RTs) to all stimuli, participants were classified into one of two groups (MSI or NO MSI), depending on their MSI RT benefit. Static balance was assessed using mean unipedal stance time. Overall, results revealed that RTs to VS stimuli were significantly shorter than those elicited to constituent unisensory conditions. Further, the current experimental design afforded differential patterns of multisensory processing, with 75% of the elderly sample demonstrating multisensory enhancements. Interestingly, 25% of older adults did not demonstrate multisensory RT facilitation; a finding that was attributed to extremely fast RTs overall and specifically in response to somatosensory inputs. Individuals in the NO MSI group maintained significantly better unipedal stance times and reported less falls, compared to elders in the MSI group. This study reveals the existence of differential patterns of multisensory processing in aging, while describing the clinical translational value of MSI enhancements in predicting balance and falls risk. PMID:25102664

Demographics of Isolated Galaxies along the Hubble Sequence

NASA Astrophysics Data System (ADS)

Khim, Hong-geun; Park, Jongwon; Seo, Seong-Woo; Lee, Jaehyun; Smith, Rory; Yi, Sukyoung K.

2015-09-01

Isolated galaxies in low-density regions are significant in the sense that they are least affected by the hierarchical pattern of galaxy growth and interactions with perturbers, at least for the last few gigayears. To form a comprehensive picture of the star-formation history of isolated galaxies, we constructed a catalog of isolated galaxies and their comparison sample in relatively denser environments. The galaxies are drawn from the Sloan Digital Sky Survey Data Release 7 in the redshift range of 0.025\\lt z\\lt 0.044. We performed a visual inspection and classified their morphology following the Hubble classification scheme. For the spectroscopic study, we make use of the catalog provided by Oh et al. in 2011. We confirm most of the earlier understanding on isolated galaxies. The most remarkable additional results are as follows. Isolated galaxies are dominantly late type with the morphology distribution (E:S0:S:Irr) = (9.9:11.3:77.6:1.2)%. The frequency of elliptical galaxies among isolated galaxies is only a third of that of the comparison sample. Most of the photometric and spectroscopic properties are surprisingly similar between the isolated and comparison samples. However, early-type isolated galaxies are less massive by 50% and younger (by Hβ) by 20% than their counterparts in the comparison sample. This can be explained as a result of different merger and star-formation histories for differing environments in the hierarchical merger paradigm. We provide an online catalog for the list and properties of our sample galaxies.

Behavior analysis for elderly care using a network of low-resolution visual sensors

NASA Astrophysics Data System (ADS)

Eldib, Mohamed; Deboeverie, Francis; Philips, Wilfried; Aghajan, Hamid

2016-07-01

Recent advancements in visual sensor technologies have made behavior analysis practical for in-home monitoring systems. The current in-home monitoring systems face several challenges: (1) visual sensor calibration is a difficult task and not practical in real-life because of the need for recalibration when the visual sensors are moved accidentally by a caregiver or the senior citizen, (2) privacy concerns, and (3) the high hardware installation cost. We propose to use a network of cheap low-resolution visual sensors (30×30 pixels) for long-term behavior analysis. The behavior analysis starts by visual feature selection based on foreground/background detection to track the motion level in each visual sensor. Then a hidden Markov model (HMM) is used to estimate the user's locations without calibration. Finally, an activity discovery approach is proposed using spatial and temporal contexts. We performed experiments on 10 months of real-life data. We show that the HMM approach outperforms the k-nearest neighbor classifier against ground truth for 30 days. Our framework is able to discover 13 activities of daily livings (ADL parameters). More specifically, we analyze mobility patterns and some of the key ADL parameters to detect increasing or decreasing health conditions.

Bag-of-visual-ngrams for histopathology image classification

NASA Astrophysics Data System (ADS)

López-Monroy, A. Pastor; Montes-y-Gómez, Manuel; Escalante, Hugo Jair; Cruz-Roa, Angel; González, Fabio A.

2013-11-01

This paper describes an extension of the Bag-of-Visual-Words (BoVW) representation for image categorization (IC) of histophatology images. This representation is one of the most used approaches in several high-level computer vision tasks. However, the BoVW representation has an important limitation: the disregarding of spatial information among visual words. This information may be useful to capture discriminative visual-patterns in specific computer vision tasks. In order to overcome this problem we propose the use of visual n-grams. N-grams based-representations are very popular in the field of natural language processing (NLP), in particular within text mining and information retrieval. We propose building a codebook of n-grams and then representing images by histograms of visual n-grams. We evaluate our proposal in the challenging task of classifying histopathology images. The novelty of our proposal lies in the fact that we use n-grams as attributes for a classification model (together with visual-words, i.e., 1-grams). This is common practice within NLP, although, to the best of our knowledge, this idea has not been explored yet within computer vision. We report experimental results in a database of histopathology images where our proposed method outperforms the traditional BoVWs formulation.

Acoustic mapping and classification of benthic habitat using unsupervised learning in artificial reef water

NASA Astrophysics Data System (ADS)

Li, Dong; Tang, Cheng; Xia, Chunlei; Zhang, Hua

2017-02-01

Artificial reefs (ARs) are effective means to maintain fishery resources and to restore ecological environment in coastal waters. ARs have been widely constructed along the Chinese coast. However, understanding of benthic habitats in the vicinity of ARs is limited, hindering effective fisheries and aquacultural management. Multibeam echosounder (MBES) is an advanced acoustic instrument capable of efficiently generating large-scale maps of benthic environments at fine resolutions. The objective of this study is to develop a technical approach to characterize, classify, and map shallow coastal areas with ARs using an MBES. An automated classification method is designed and tested to process bathymetric and backscatter data from MBES and transform the variables into simple, easily visualized maps. To reduce the redundancy in acoustic variables, a principal component analysis (PCA) is used to condense the highly collinear dataset. An acoustic benthic map of bottom sediments is classified using an iterative self-organizing data analysis technique (ISODATA). The approach is tested with MBES surveys in a 1.15 km2 fish farm with a high density of ARs off the Yantai coast in northern China. Using this method, 3 basic benthic habitats (sandy bottom, muddy sediments, and ARs) are distinguished. The results of the classification are validated using sediment samples and underwater surveys. Our study shows that the use of MBES is an effective method for acoustic mapping and classification of ARs.

Value of artisanal simulators to train veterinary students in performing invasive ultrasound-guided procedures.

PubMed

Hage, Maria Cristina F N S; Massaferro, Ana Beatriz; Lopes, Érika Rondon; Beraldo, Carolina Mariano; Daniel, Jéssika

2016-03-01

Pericardial effusion can lead to cardiac tamponade, which endangers an animal's life. Ultrasound-guided pericardiocentesis is used to remove abnormal liquid; however, it requires technical expertise. In veterinary medical education, the opportunity to teach this procedure to save lives during emergencies is rare; therefore, simulators are recommended for this practice. The present study aimed to create a model that can be made "at home" at low cost for ultrasound-guided pericardiocentesis training and to gather feedback about this model through questionnaires given to the participants. Eighteen professionals and thirty-six students were introduced to the simulator in pairs. After the simulation training session, participants filled out the questionnaire. Participants considered the model strong in the following areas: visualization of the pericardium, the heart, fluid in the pericardium, and fluid decrease during fictitious pericardiocentesis and its realism. They considered the model weak or moderate in the following areas: visualization of the surrounding tissues, difficulty of pericardial puncture, and visualization of the catheter. The professionals classified the realism of the experimental heart as moderate, whereas the undergraduate students classified it as strong. All participants believed that the experimental model could be useful in preparing for a future real situation. This model fulfills the need for a practical, realistic, and cost-effective model for ultrasound-guided pericardiocentesis training. Copyright © 2016 The American Physiological Society.

Control system of hexacopter using color histogram footprint and convolutional neural network

NASA Astrophysics Data System (ADS)

Ruliputra, R. N.; Darma, S.

2017-07-01

The development of unmanned aerial vehicles (UAV) has been growing rapidly in recent years. The use of logic thinking which is implemented into the program algorithms is needed to make a smart system. By using visual input from a camera, UAV is able to fly autonomously by detecting a target. However, some weaknesses arose as usage in the outdoor environment might change the target's color intensity. Color histogram footprint overcomes the problem because it divides color intensity into separate bins that make the detection tolerant to the slight change of color intensity. Template matching compare its detection result with a template of the reference image to determine the target position and use it to position the vehicle in the middle of the target with visual feedback control based on Proportional-Integral-Derivative (PID) controller. Color histogram footprint method localizes the target by calculating the back projection of its histogram. It has an average success rate of 77 % from a distance of 1 meter. It can position itself in the middle of the target by using visual feedback control with an average positioning time of 73 seconds. After the hexacopter is in the middle of the target, Convolutional Neural Networks (CNN) classifies a number contained in the target image to determine a task depending on the classified number, either landing, yawing, or return to launch. The recognition result shows an optimum success rate of 99.2 %.

Effect of finite sample size on feature selection and classification: a simulation study.

PubMed

Way, Ted W; Sahiner, Berkman; Hadjiiski, Lubomir M; Chan, Heang-Ping

2010-02-01

The small number of samples available for training and testing is often the limiting factor in finding the most effective features and designing an optimal computer-aided diagnosis (CAD) system. Training on a limited set of samples introduces bias and variance in the performance of a CAD system relative to that trained with an infinite sample size. In this work, the authors conducted a simulation study to evaluate the performances of various combinations of classifiers and feature selection techniques and their dependence on the class distribution, dimensionality, and the training sample size. The understanding of these relationships will facilitate development of effective CAD systems under the constraint of limited available samples. Three feature selection techniques, the stepwise feature selection (SFS), sequential floating forward search (SFFS), and principal component analysis (PCA), and two commonly used classifiers, Fisher's linear discriminant analysis (LDA) and support vector machine (SVM), were investigated. Samples were drawn from multidimensional feature spaces of multivariate Gaussian distributions with equal or unequal covariance matrices and unequal means, and with equal covariance matrices and unequal means estimated from a clinical data set. Classifier performance was quantified by the area under the receiver operating characteristic curve Az. The mean Az values obtained by resubstitution and hold-out methods were evaluated for training sample sizes ranging from 15 to 100 per class. The number of simulated features available for selection was chosen to be 50, 100, and 200. It was found that the relative performance of the different combinations of classifier and feature selection method depends on the feature space distributions, the dimensionality, and the available training sample sizes. The LDA and SVM with radial kernel performed similarly for most of the conditions evaluated in this study, although the SVM classifier showed a slightly higher hold-out performance than LDA for some conditions and vice versa for other conditions. PCA was comparable to or better than SFS and SFFS for LDA at small samples sizes, but inferior for SVM with polynomial kernel. For the class distributions simulated from clinical data, PCA did not show advantages over the other two feature selection methods. Under this condition, the SVM with radial kernel performed better than the LDA when few training samples were available, while LDA performed better when a large number of training samples were available. None of the investigated feature selection-classifier combinations provided consistently superior performance under the studied conditions for different sample sizes and feature space distributions. In general, the SFFS method was comparable to the SFS method while PCA may have an advantage for Gaussian feature spaces with unequal covariance matrices. The performance of the SVM with radial kernel was better than, or comparable to, that of the SVM with polynomial kernel under most conditions studied.

PRROC: computing and visualizing precision-recall and receiver operating characteristic curves in R.

PubMed

Grau, Jan; Grosse, Ivo; Keilwagen, Jens

2015-08-01

Precision-recall (PR) and receiver operating characteristic (ROC) curves are valuable measures of classifier performance. Here, we present the R-package PRROC, which allows for computing and visualizing both PR and ROC curves. In contrast to available R-packages, PRROC allows for computing PR and ROC curves and areas under these curves for soft-labeled data using a continuous interpolation between the points of PR curves. In addition, PRROC provides a generic plot function for generating publication-quality graphics of PR and ROC curves. © The Author 2015. Published by Oxford University Press.

Visualization techniques for malware behavior analysis

NASA Astrophysics Data System (ADS)

Grégio, André R. A.; Santos, Rafael D. C.

2011-06-01

Malware spread via Internet is a great security threat, so studying their behavior is important to identify and classify them. Using SSDT hooking we can obtain malware behavior by running it in a controlled environment and capturing interactions with the target operating system regarding file, process, registry, network and mutex activities. This generates a chain of events that can be used to compare them with other known malware. In this paper we present a simple approach to convert malware behavior into activity graphs and show some visualization techniques that can be used to analyze malware behavior, individually or grouped.

A fuzzy measure approach to motion frame analysis for scene detection. M.S. Thesis - Houston Univ.

NASA Technical Reports Server (NTRS)

Leigh, Albert B.; Pal, Sankar K.

1992-01-01

This paper addresses a solution to the problem of scene estimation of motion video data in the fuzzy set theoretic framework. Using fuzzy image feature extractors, a new algorithm is developed to compute the change of information in each of two successive frames to classify scenes. This classification process of raw input visual data can be used to establish structure for correlation. The algorithm attempts to fulfill the need for nonlinear, frame-accurate access to video data for applications such as video editing and visual document archival/retrieval systems in multimedia environments.

New massive members of Cygnus OB2

NASA Astrophysics Data System (ADS)

Berlanas, S. R.; Herrero, A.; Comerón, F.; Pasquali, A.; Motta, C. Bertelli; Sota, A.

2018-04-01

Context. The Cygnus complex is one of the most powerful star forming regions at a close distance from the Sun ( 1.4 kpc). Its richest OB association Cygnus OB2 is known to harbor many tens of O-type stars and hundreds of B-type stars, providing a large homogeneous population of OB stars that can be analyzed. Many studies of its massive population have been developed in the last decades, although the total number of OB stars is still incomplete. Aim. Our aim is to increase the sample of O and B members of Cygnus OB2 and its surroundings by spectroscopically classifying 61 candidates as possible OB-type members of Cygnus OB2, using new intermediate resolution spectroscopy. Methods: We have obtained intermediate resolution (R 5000) spectra for all of the OB-type candidates between 2013 and 2017. We thus performed a spectral classification of the sample using HeI-II and metal lines rates, as well as the Marxist Ghost Buster (MGB) software for O-type stars and the IACOB standards catalog for B-type stars. Results: From the whole sample of 61 candidates, we have classified 42 stars as new massive OB-type stars, earlier than B3, in Cygnus OB2 and surroundings, including 11 O-type stars. The other candidates are discarded as they display later spectral types inconsistent with membership in the association. We have also obtained visual extinctions for all the new confirmed massive OB members, placing them in a Hertzsprung-Russell Diagram using calibrations for Teff and luminosity. Finally, we have studied the age and extinction distribution of our sample within the region. Conclusions: We have obtained new blue intermediate-resolution spectra suitable for spectral classification of 61 OB candidates in Cygnus OB2 and surroundings. The confirmation of 42 new OB massive stars (earlier than B3) in the region allows us to increase the young massive population known in the field. We have also confirmed the correlation between age and Galactic longitude previously found in the region. We conclude that many O and early B stars at B > 16 mag are still undiscovered in Cygnus.

Crossmodal Statistical Binding of Temporal Information and Stimuli Properties Recalibrates Perception of Visual Apparent Motion

PubMed Central

Zhang, Yi; Chen, Lihan

2016-01-01

Recent studies of brain plasticity that pertain to time perception have shown that fast training of temporal discrimination in one modality, for example, the auditory modality, can improve performance of temporal discrimination in another modality, such as the visual modality. We here examined whether the perception of visual Ternus motion could be recalibrated through fast crossmodal statistical binding of temporal information and stimuli properties binding. We conducted two experiments, composed of three sessions each: pre-test, learning, and post-test. In both the pre-test and the post-test, participants classified the Ternus display as either “element motion” or “group motion.” For the training session in Experiment 1, we constructed two types of temporal structures, in which two consecutively presented sound beeps were dominantly (80%) flanked by one leading visual Ternus frame and by one lagging visual Ternus frame (VAAV) or dominantly inserted by two Ternus visual frames (AVVA). Participants were required to respond which interval (auditory vs. visual) was longer. In Experiment 2, we presented only a single auditory–visual pair but with similar temporal configurations as in Experiment 1, and asked participants to perform an audio–visual temporal order judgment. The results of these two experiments support that statistical binding of temporal information and stimuli properties can quickly and selectively recalibrate the sensitivity of perceiving visual motion, according to the protocols of the specific bindings. PMID:27065910

Kraft pulp from budworm-infested jack pine

Treesearch

J. Y. Zhu; Gary C. Myers

2006-01-01

This study evaluated the quality of kraft pulp from bud-worm-infested jack pine. The logs were classified as merchantable live, suspect, or merchantable dead. Raw materials were evaluated through visual inspection, analysis of the chemical composition, SilviScan measurement of the density, and measurement of the tracheid length. Unbleached pulps were then refined using...

22 CFR 125.2 - Exports of unclassified technical data.

Code of Federal Regulations, 2010 CFR

2010-04-01

..., visual or documentary disclosure of technical data by U.S. persons to foreign persons. A license is... 22 Foreign Relations 1 2010-04-01 2010-04-01 false Exports of unclassified technical data. 125.2... THE EXPORT OF TECHNICAL DATA AND CLASSIFIED DEFENSE ARTICLES § 125.2 Exports of unclassified technical...

22 CFR 125.2 - Exports of unclassified technical data.

Code of Federal Regulations, 2013 CFR

2013-04-01

..., visual or documentary disclosure of technical data by U.S. persons to foreign persons. A license is... 22 Foreign Relations 1 2013-04-01 2013-04-01 false Exports of unclassified technical data. 125.2... THE EXPORT OF TECHNICAL DATA AND CLASSIFIED DEFENSE ARTICLES § 125.2 Exports of unclassified technical...

22 CFR 125.2 - Exports of unclassified technical data.

Code of Federal Regulations, 2011 CFR

2011-04-01

..., visual or documentary disclosure of technical data by U.S. persons to foreign persons. A license is... 22 Foreign Relations 1 2011-04-01 2011-04-01 false Exports of unclassified technical data. 125.2... THE EXPORT OF TECHNICAL DATA AND CLASSIFIED DEFENSE ARTICLES § 125.2 Exports of unclassified technical...

22 CFR 125.2 - Exports of unclassified technical data.

Code of Federal Regulations, 2014 CFR

2014-04-01

..., visual or documentary disclosure of technical data by U.S. persons to foreign persons. A license is... 22 Foreign Relations 1 2014-04-01 2014-04-01 false Exports of unclassified technical data. 125.2... THE EXPORT OF TECHNICAL DATA AND CLASSIFIED DEFENSE ARTICLES § 125.2 Exports of unclassified technical...

Beginning Readers Activate Semantics from Sub-Word Orthography

ERIC Educational Resources Information Center

Nation, Kate; Cocksey, Joanne

2009-01-01

Two experiments assessed whether 7-year-old children activate semantic information from sub-word orthography. Children made category decisions to visually-presented words, some of which contained an embedded word (e.g., "hip" in s"hip"). In Experiment 1 children were slower and less accurate to classify words if they contained an embedded word…

32 CFR 811.6 - Visual information product/material loans.

Code of Federal Regulations, 2010 CFR

2010-07-01

... Section 811.6 National Defense Department of Defense (Continued) DEPARTMENT OF THE AIR FORCE SALES AND... product/material loans. (a) You may request unclassified and classified copies of current Air Force productions and loans of DoD and other Federal productions from JVISDA, ATTN: ASQV-JVIA-T-AS, Bldg. 3, Bay 3...

32 CFR 811.6 - Visual information product/material loans.

Code of Federal Regulations, 2011 CFR

2011-07-01

... Section 811.6 National Defense Department of Defense (Continued) DEPARTMENT OF THE AIR FORCE SALES AND... product/material loans. (a) You may request unclassified and classified copies of current Air Force productions and loans of DoD and other Federal productions from JVISDA, ATTN: ASQV-JVIA-T-AS, Bldg. 3, Bay 3...

Learning about Minerals through the Art of Jewelry Making: A Multicultural Science Connection

ERIC Educational Resources Information Center

Russell, Melody L.; Tripp, L. Octavia

2010-01-01

This article presents an activity that focuses on helping students investigate the formation of rocks, minerals, and gemstones. Students describe visual, textual, and physical properties of various specimens of minerals. Using compare and contrast skills, students can classify the primary types of rock, ask questions about the Earth's inner…

Effects of Stimulus Duration and Choice Delay on Visual Categorization in Pigeons

ERIC Educational Resources Information Center

Lazareva, Olga F.; Wasserman, Edward A.

2009-01-01

We [Lazareva, O. F., Freiburger, K. L., & Wasserman, E. A. (2004). "Pigeons concurrently categorize photographs at both basic and superordinate levels." "Psychonomic Bulletin and Review," 11, 1111-1117] previously trained four pigeons to classify color photographs into their basic-level categories (cars, chairs, flowers, or people) or into their…

Decoding magnetoencephalographic rhythmic activity using spectrospatial information.

PubMed

Kauppi, Jukka-Pekka; Parkkonen, Lauri; Hari, Riitta; Hyvärinen, Aapo

2013-12-01

We propose a new data-driven decoding method called Spectral Linear Discriminant Analysis (Spectral LDA) for the analysis of magnetoencephalography (MEG). The method allows investigation of changes in rhythmic neural activity as a result of different stimuli and tasks. The introduced classification model only assumes that each "brain state" can be characterized as a combination of neural sources, each of which shows rhythmic activity at one or several frequency bands. Furthermore, the model allows the oscillation frequencies to be different for each such state. We present decoding results from 9 subjects in a four-category classification problem defined by an experiment involving randomly alternating epochs of auditory, visual and tactile stimuli interspersed with rest periods. The performance of Spectral LDA was very competitive compared with four alternative classifiers based on different assumptions concerning the organization of rhythmic brain activity. In addition, the spectral and spatial patterns extracted automatically on the basis of trained classifiers showed that Spectral LDA offers a novel and interesting way of analyzing spectrospatial oscillatory neural activity across the brain. All the presented classification methods and visualization tools are freely available as a Matlab toolbox. © 2013.

Automatic Screening and Grading of Age-Related Macular Degeneration from Texture Analysis of Fundus Images

PubMed Central

Phan, Thanh Vân; Seoud, Lama; Chakor, Hadi; Cheriet, Farida

2016-01-01

Age-related macular degeneration (AMD) is a disease which causes visual deficiency and irreversible blindness to the elderly. In this paper, an automatic classification method for AMD is proposed to perform robust and reproducible assessments in a telemedicine context. First, a study was carried out to highlight the most relevant features for AMD characterization based on texture, color, and visual context in fundus images. A support vector machine and a random forest were used to classify images according to the different AMD stages following the AREDS protocol and to evaluate the features' relevance. Experiments were conducted on a database of 279 fundus images coming from a telemedicine platform. The results demonstrate that local binary patterns in multiresolution are the most relevant for AMD classification, regardless of the classifier used. Depending on the classification task, our method achieves promising performances with areas under the ROC curve between 0.739 and 0.874 for screening and between 0.469 and 0.685 for grading. Moreover, the proposed automatic AMD classification system is robust with respect to image quality. PMID:27190636

Florbetapir (F18-AV-45) PET to assess amyloid burden in Alzheimer's disease dementia, mild cognitive impairment, and normal aging.

PubMed

Johnson, Keith A; Sperling, Reisa A; Gidicsin, Christopher M; Carmasin, Jeremy S; Maye, Jacqueline E; Coleman, Ralph E; Reiman, Eric M; Sabbagh, Marwan N; Sadowsky, Carl H; Fleisher, Adam S; Murali Doraiswamy, P; Carpenter, Alan P; Clark, Christopher M; Joshi, Abhinay D; Lu, Ming; Grundman, Michel; Mintun, Mark A; Pontecorvo, Michel J; Skovronsky, Daniel M

2013-10-01

To evaluate the performance characteristics of florbetapir F18 positron emission tomography (PET) in patients with Alzheimer's disease (AD), mild cognitive impairment (MCI), and healthy control subjects (HCs). Florbetapir PET was acquired in 184 subjects (45 AD patients, 60 MCI patients, and 79 HCs) within a multicenter phase 2 study. Amyloid burden was assessed visually and quantitatively, and was classified as positive or negative. Florbetapir PET was rated visually amyloid positive in 76% of AD patients, 38% of MCI patients, and 14% of HCs. Eighty-four percent of AD patients, 45% of MCI patients, and 23% of HCs were classified as amyloid positive using a quantitative threshold. Amyloid positivity and mean cortical amyloid burden were associated with age and apolipoprotein E ε4 carrier status. : The data are consistent with expected rates of amyloid positivity among individuals with clinical diagnoses of AD and MCI, and indicate the potential value of florbetapir F18 PET as an adjunct to clinical diagnosis. Copyright © 2013 The Alzheimer's Association. Published by Elsevier Inc. All rights reserved.

Minimum distance classification in remote sensing

NASA Technical Reports Server (NTRS)

Wacker, A. G.; Landgrebe, D. A.

1972-01-01

The utilization of minimum distance classification methods in remote sensing problems, such as crop species identification, is considered. Literature concerning both minimum distance classification problems and distance measures is reviewed. Experimental results are presented for several examples. The objective of these examples is to: (a) compare the sample classification accuracy of a minimum distance classifier, with the vector classification accuracy of a maximum likelihood classifier, and (b) compare the accuracy of a parametric minimum distance classifier with that of a nonparametric one. Results show the minimum distance classifier performance is 5% to 10% better than that of the maximum likelihood classifier. The nonparametric classifier is only slightly better than the parametric version.

Classification of Traffic Related Short Texts to Analyse Road Problems in Urban Areas

NASA Astrophysics Data System (ADS)

Saldana-Perez, A. M. M.; Moreno-Ibarra, M.; Tores-Ruiz, M.

2017-09-01

The Volunteer Geographic Information (VGI) can be used to understand the urban dynamics. In the classification of traffic related short texts to analyze road problems in urban areas, a VGI data analysis is done over a social media's publications, in order to classify traffic events at big cities that modify the movement of vehicles and people through the roads, such as car accidents, traffic and closures. The classification of traffic events described in short texts is done by applying a supervised machine learning algorithm. In the approach users are considered as sensors which describe their surroundings and provide their geographic position at the social network. The posts are treated by a text mining process and classified into five groups. Finally, the classified events are grouped in a data corpus and geo-visualized in the study area, to detect the places with more vehicular problems.

Study design in high-dimensional classification analysis.

PubMed

Sánchez, Brisa N; Wu, Meihua; Song, Peter X K; Wang, Wen

2016-10-01

Advances in high throughput technology have accelerated the use of hundreds to millions of biomarkers to construct classifiers that partition patients into different clinical conditions. Prior to classifier development in actual studies, a critical need is to determine the sample size required to reach a specified classification precision. We develop a systematic approach for sample size determination in high-dimensional (large [Formula: see text] small [Formula: see text]) classification analysis. Our method utilizes the probability of correct classification (PCC) as the optimization objective function and incorporates the higher criticism thresholding procedure for classifier development. Further, we derive the theoretical bound of maximal PCC gain from feature augmentation (e.g. when molecular and clinical predictors are combined in classifier development). Our methods are motivated and illustrated by a study using proteomics markers to classify post-kidney transplantation patients into stable and rejecting classes. © The Author 2016. Published by Oxford University Press. All rights reserved. For permissions, please e-mail: journals.permissions@oup.com.

Positive fEMG Patterns with Ambiguity in Paintings.

PubMed

Jakesch, Martina; Goller, Juergen; Leder, Helmut

2017-01-01

Whereas ambiguity in everyday life is often negatively evaluated, it is considered key in art appreciation. In a facial EMG study, we tested whether the positive role of visual ambiguity in paintings is reflected in a continuous affective evaluation on a subtle level. We presented ambiguous (disfluent) and non-ambiguous (fluent) versions of Magritte paintings and found that M. Zygomaticus major activation was higher and M. corrugator supercilii activation was lower for ambiguous than for non-ambiguous versions. Our findings reflect a positive continuous affective evaluation to visual ambiguity in paintings over the 5 s presentation time. We claim that this finding is indirect evidence for the hypothesis that visual stimuli classified as art, evoke a safe state for indulging into experiencing ambiguity, challenging the notion that processing fluency is generally related to positive affect.

Frog sound identification using extended k-nearest neighbor classifier

NASA Astrophysics Data System (ADS)

Mukahar, Nordiana; Affendi Rosdi, Bakhtiar; Athiar Ramli, Dzati; Jaafar, Haryati

2017-09-01

Frog sound identification based on the vocalization becomes important for biological research and environmental monitoring. As a result, different types of feature extractions and classifiers have been employed to evaluate the accuracy of frog sound identification. This paper presents a frog sound identification with Extended k-Nearest Neighbor (EKNN) classifier. The EKNN classifier integrates the nearest neighbors and mutual sharing of neighborhood concepts, with the aims of improving the classification performance. It makes a prediction based on who are the nearest neighbors of the testing sample and who consider the testing sample as their nearest neighbors. In order to evaluate the classification performance in frog sound identification, the EKNN classifier is compared with competing classifier, k -Nearest Neighbor (KNN), Fuzzy k -Nearest Neighbor (FKNN) k - General Nearest Neighbor (KGNN)and Mutual k -Nearest Neighbor (MKNN) on the recorded sounds of 15 frog species obtained in Malaysia forest. The recorded sounds have been segmented using Short Time Energy and Short Time Average Zero Crossing Rate (STE+STAZCR), sinusoidal modeling (SM), manual and the combination of Energy (E) and Zero Crossing Rate (ZCR) (E+ZCR) while the features are extracted by Mel Frequency Cepstrum Coefficient (MFCC). The experimental results have shown that the EKNCN classifier exhibits the best performance in terms of accuracy compared to the competing classifiers, KNN, FKNN, GKNN and MKNN for all cases.

An Improvement To The k-Nearest Neighbor Classifier For ECG Database

NASA Astrophysics Data System (ADS)

Jaafar, Haryati; Hidayah Ramli, Nur; Nasir, Aimi Salihah Abdul

2018-03-01

The k nearest neighbor (kNN) is a non-parametric classifier and has been widely used for pattern classification. However, in practice, the performance of kNN often tends to fail due to the lack of information on how the samples are distributed among them. Moreover, kNN is no longer optimal when the training samples are limited. Another problem observed in kNN is regarding the weighting issues in assigning the class label before classification. Thus, to solve these limitations, a new classifier called Mahalanobis fuzzy k-nearest centroid neighbor (MFkNCN) is proposed in this study. Here, a Mahalanobis distance is applied to avoid the imbalance of samples distribition. Then, a surrounding rule is employed to obtain the nearest centroid neighbor based on the distributions of training samples and its distance to the query point. Consequently, the fuzzy membership function is employed to assign the query point to the class label which is frequently represented by the nearest centroid neighbor Experimental studies from electrocardiogram (ECG) signal is applied in this study. The classification performances are evaluated in two experimental steps i.e. different values of k and different sizes of feature dimensions. Subsequently, a comparative study of kNN, kNCN, FkNN and MFkCNN classifier is conducted to evaluate the performances of the proposed classifier. The results show that the performance of MFkNCN consistently exceeds the kNN, kNCN and FkNN with the best classification rates of 96.5%.

Solid-contact potentiometric sensors and multisensors based on polyaniline and thiacalixarene receptors for the analysis of some beverages and alcoholic drinks

NASA Astrophysics Data System (ADS)

Sorvin, Michail; Belyakova, Svetlana; Stoikov, Ivan; Shamagsumova, Rezeda; Evtugyn, Gennady

2018-04-01

Electronic tongue is a sensor array that aims to discriminate and analyze complex media like food and beverages on the base of chemometrics approaches for data mining and pattern recognition. In this review, the concept of electronic tongue comprising of solid-contact potentiometric sensors with polyaniline and thacalix[4]arene derivatives is described. The electrochemical reactions of polyaniline as a background of solid-contact sensors and the characteristics of thiacalixarenes and pillararenes as neutral ionophores are briefly considered. The electronic tongue systems described were successfully applied for assessment of fruit juices, green tea, beer and alcoholic drinks They were classified in accordance with the origination, brands and styles. Variation of the sensor response resulted from the reactions between Fe(III) ions added and sample components, i.e., antioxidants and complexing agents. The use of principal component analysis and discriminant analysis is shown for multisensor signal treatment and visualization. The discrimination conditions can be optimized by variation of the ionophores, Fe(III) concentration and sample dilution. The results obtained were compared with other electronic tongue systems reported for the same subjects.

The discriminant pixel approach: a new tool for the rational interpretation of GCxGC-MS chromatograms.

PubMed

Vial, Jérôme; Pezous, Benoît; Thiébaut, Didier; Sassiat, Patrick; Teillet, Béatrice; Cahours, Xavier; Rivals, Isabelle

2011-01-30

GCxGC is now recognized as the most suited analytical technique for the characterization of complex mixtures of volatile compounds; it is implemented worldwide in academic and industrial laboratories. However, in the frame of comprehensive analysis of non-target analytes, going beyond the visual examination of the color plots remains challenging for most users. We propose a strategy that aims at classifying chromatograms according to the chemical composition of the samples while determining the origin of the discrimination between different classes of samples: the discriminant pixel approach. After data pre-processing and time-alignment, the discriminatory power of each chromatogram pixel for a given class was defined as its correlation with the membership to this class. Using a peak finding algorithm, the most discriminant pixels were then linked to chromatographic peaks. Finally, crosschecking with mass spectrometry data enabled to establish relationships with compounds that could consequently be considered as candidate class markers. This strategy was applied to a large experimental data set of 145 GCxGC-MS chromatograms of tobacco extracts corresponding to three distinct classes of tobacco. Copyright © 2010 Elsevier B.V. All rights reserved.

Solid-Contact Potentiometric Sensors and Multisensors Based on Polyaniline and Thiacalixarene Receptors for the Analysis of Some Beverages and Alcoholic Drinks.

PubMed

Sorvin, Michail; Belyakova, Svetlana; Stoikov, Ivan; Shamagsumova, Rezeda; Evtugyn, Gennady

2018-01-01

Electronic tongue is a sensor array that aims to discriminate and analyze complex media like food and beverages on the base of chemometrics approaches for data mining and pattern recognition. In this review, the concept of electronic tongue comprising of solid-contact potentiometric sensors with polyaniline and thacalix[4]arene derivatives is described. The electrochemical reactions of polyaniline as a background of solid-contact sensors and the characteristics of thiacalixarenes and pillararenes as neutral ionophores are briefly considered. The electronic tongue systems described were successfully applied for assessment of fruit juices, green tea, beer, and alcoholic drinks They were classified in accordance with the origination, brands and styles. Variation of the sensor response resulted from the reactions between Fe(III) ions added and sample components, i.e., antioxidants and complexing agents. The use of principal component analysis and discriminant analysis is shown for multisensor signal treatment and visualization. The discrimination conditions can be optimized by variation of the ionophores, Fe(III) concentration, and sample dilution. The results obtained were compared with other electronic tongue systems reported for the same subjects.

Solid-Contact Potentiometric Sensors and Multisensors Based on Polyaniline and Thiacalixarene Receptors for the Analysis of Some Beverages and Alcoholic Drinks

PubMed Central

Sorvin, Michail; Belyakova, Svetlana; Stoikov, Ivan; Shamagsumova, Rezeda; Evtugyn, Gennady

2018-01-01

Electronic tongue is a sensor array that aims to discriminate and analyze complex media like food and beverages on the base of chemometrics approaches for data mining and pattern recognition. In this review, the concept of electronic tongue comprising of solid-contact potentiometric sensors with polyaniline and thacalix[4]arene derivatives is described. The electrochemical reactions of polyaniline as a background of solid-contact sensors and the characteristics of thiacalixarenes and pillararenes as neutral ionophores are briefly considered. The electronic tongue systems described were successfully applied for assessment of fruit juices, green tea, beer, and alcoholic drinks They were classified in accordance with the origination, brands and styles. Variation of the sensor response resulted from the reactions between Fe(III) ions added and sample components, i.e., antioxidants and complexing agents. The use of principal component analysis and discriminant analysis is shown for multisensor signal treatment and visualization. The discrimination conditions can be optimized by variation of the ionophores, Fe(III) concentration, and sample dilution. The results obtained were compared with other electronic tongue systems reported for the same subjects. PMID:29740577

Population activity structure of excitatory and inhibitory neurons

PubMed Central

Doiron, Brent

2017-01-01

Many studies use population analysis approaches, such as dimensionality reduction, to characterize the activity of large groups of neurons. To date, these methods have treated each neuron equally, without taking into account whether neurons are excitatory or inhibitory. We studied population activity structure as a function of neuron type by applying factor analysis to spontaneous activity from spiking networks with balanced excitation and inhibition. Throughout the study, we characterized population activity structure by measuring its dimensionality and the percentage of overall activity variance that is shared among neurons. First, by sampling only excitatory or only inhibitory neurons, we found that the activity structures of these two populations in balanced networks are measurably different. We also found that the population activity structure is dependent on the ratio of excitatory to inhibitory neurons sampled. Finally we classified neurons from extracellular recordings in the primary visual cortex of anesthetized macaques as putative excitatory or inhibitory using waveform classification, and found similarities with the neuron type-specific population activity structure of a balanced network with excitatory clustering. These results imply that knowledge of neuron type is important, and allows for stronger statistical tests, when interpreting population activity structure. PMID:28817581

Comparison of disease prevalence in two populations in the presence of misclassification.

PubMed

Tang, Man-Lai; Qiu, Shi-Fang; Poon, Wai-Yin

2012-11-01

Comparing disease prevalence in two groups is an important topic in medical research, and prevalence rates are obtained by classifying subjects according to whether they have the disease. Both high-cost infallible gold-standard classifiers or low-cost fallible classifiers can be used to classify subjects. However, statistical analysis that is based on data sets with misclassifications leads to biased results. As a compromise between the two classification approaches, partially validated sets are often used in which all individuals are classified by fallible classifiers, and some of the individuals are validated by the accurate gold-standard classifiers. In this article, we develop several reliable test procedures and approximate sample size formulas for disease prevalence studies based on the difference between two disease prevalence rates with two independent partially validated series. Empirical studies show that (i) the Score test produces close-to-nominal level and is preferred in practice; and (ii) the sample size formula based on the Score test is also fairly accurate in terms of the empirical power and type I error rate, and is hence recommended. A real example from an aplastic anemia study is used to illustrate the proposed methodologies. © 2012 WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim.

A geometric method for computing ocular kinematics and classifying gaze events using monocular remote eye tracking in a robotic environment.

PubMed

Singh, Tarkeshwar; Perry, Christopher M; Herter, Troy M

2016-01-26

Robotic and virtual-reality systems offer tremendous potential for improving assessment and rehabilitation of neurological disorders affecting the upper extremity. A key feature of these systems is that visual stimuli are often presented within the same workspace as the hands (i.e., peripersonal space). Integrating video-based remote eye tracking with robotic and virtual-reality systems can provide an additional tool for investigating how cognitive processes influence visuomotor learning and rehabilitation of the upper extremity. However, remote eye tracking systems typically compute ocular kinematics by assuming eye movements are made in a plane with constant depth (e.g. frontal plane). When visual stimuli are presented at variable depths (e.g. transverse plane), eye movements have a vergence component that may influence reliable detection of gaze events (fixations, smooth pursuits and saccades). To our knowledge, there are no available methods to classify gaze events in the transverse plane for monocular remote eye tracking systems. Here we present a geometrical method to compute ocular kinematics from a monocular remote eye tracking system when visual stimuli are presented in the transverse plane. We then use the obtained kinematics to compute velocity-based thresholds that allow us to accurately identify onsets and offsets of fixations, saccades and smooth pursuits. Finally, we validate our algorithm by comparing the gaze events computed by the algorithm with those obtained from the eye-tracking software and manual digitization. Within the transverse plane, our algorithm reliably differentiates saccades from fixations (static visual stimuli) and smooth pursuits from saccades and fixations when visual stimuli are dynamic. The proposed methods provide advancements for examining eye movements in robotic and virtual-reality systems. Our methods can also be used with other video-based or tablet-based systems in which eye movements are performed in a peripersonal plane with variable depth.

Temporal Lobe Epilepsy: Quantitative MR Volumetry in Detection of Hippocampal Atrophy

PubMed Central

Farid, Nikdokht; Girard, Holly M.; Kemmotsu, Nobuko; Smith, Michael E.; Magda, Sebastian W.; Lim, Wei Y.; Lee, Roland R.

2012-01-01

Purpose: To determine the ability of fully automated volumetric magnetic resonance (MR) imaging to depict hippocampal atrophy (HA) and to help correctly lateralize the seizure focus in patients with temporal lobe epilepsy (TLE). Materials and Methods: This study was conducted with institutional review board approval and in compliance with HIPAA regulations. Volumetric MR imaging data were analyzed for 34 patients with TLE and 116 control subjects. Structural volumes were calculated by using U.S. Food and Drug Administration–cleared software for automated quantitative MR imaging analysis (NeuroQuant). Results of quantitative MR imaging were compared with visual detection of atrophy, and, when available, with histologic specimens. Receiver operating characteristic analyses were performed to determine the optimal sensitivity and specificity of quantitative MR imaging for detecting HA and asymmetry. A linear classifier with cross validation was used to estimate the ability of quantitative MR imaging to help lateralize the seizure focus. Results: Quantitative MR imaging–derived hippocampal asymmetries discriminated patients with TLE from control subjects with high sensitivity (86.7%–89.5%) and specificity (92.2%–94.1%). When a linear classifier was used to discriminate left versus right TLE, hippocampal asymmetry achieved 94% classification accuracy. Volumetric asymmetries of other subcortical structures did not improve classification. Compared with invasive video electroencephalographic recordings, lateralization accuracy was 88% with quantitative MR imaging and 85% with visual inspection of volumetric MR imaging studies but only 76% with visual inspection of clinical MR imaging studies. Conclusion: Quantitative MR imaging can depict the presence and laterality of HA in TLE with accuracy rates that may exceed those achieved with visual inspection of clinical MR imaging studies. Thus, quantitative MR imaging may enhance standard visual analysis, providing a useful and viable means for translating volumetric analysis into clinical practice. © RSNA, 2012 Supplemental material: http://radiology.rsna.org/lookup/suppl/doi:10.1148/radiol.12112638/-/DC1 PMID:22723496

Unsupervised Learning in an Ensemble of Spiking Neural Networks Mediated by ITDP.

PubMed

Shim, Yoonsik; Philippides, Andrew; Staras, Kevin; Husbands, Phil

2016-10-01

We propose a biologically plausible architecture for unsupervised ensemble learning in a population of spiking neural network classifiers. A mixture of experts type organisation is shown to be effective, with the individual classifier outputs combined via a gating network whose operation is driven by input timing dependent plasticity (ITDP). The ITDP gating mechanism is based on recent experimental findings. An abstract, analytically tractable model of the ITDP driven ensemble architecture is derived from a logical model based on the probabilities of neural firing events. A detailed analysis of this model provides insights that allow it to be extended into a full, biologically plausible, computational implementation of the architecture which is demonstrated on a visual classification task. The extended model makes use of a style of spiking network, first introduced as a model of cortical microcircuits, that is capable of Bayesian inference, effectively performing expectation maximization. The unsupervised ensemble learning mechanism, based around such spiking expectation maximization (SEM) networks whose combined outputs are mediated by ITDP, is shown to perform the visual classification task well and to generalize to unseen data. The combined ensemble performance is significantly better than that of the individual classifiers, validating the ensemble architecture and learning mechanisms. The properties of the full model are analysed in the light of extensive experiments with the classification task, including an investigation into the influence of different input feature selection schemes and a comparison with a hierarchical STDP based ensemble architecture.

Computer vision cracks the leaf code

PubMed Central

Wilf, Peter; Zhang, Shengping; Chikkerur, Sharat; Little, Stefan A.; Wing, Scott L.; Serre, Thomas

2016-01-01

Understanding the extremely variable, complex shape and venation characters of angiosperm leaves is one of the most challenging problems in botany. Machine learning offers opportunities to analyze large numbers of specimens, to discover novel leaf features of angiosperm clades that may have phylogenetic significance, and to use those characters to classify unknowns. Previous computer vision approaches have primarily focused on leaf identification at the species level. It remains an open question whether learning and classification are possible among major evolutionary groups such as families and orders, which usually contain hundreds to thousands of species each and exhibit many times the foliar variation of individual species. Here, we tested whether a computer vision algorithm could use a database of 7,597 leaf images from 2,001 genera to learn features of botanical families and orders, then classify novel images. The images are of cleared leaves, specimens that are chemically bleached, then stained to reveal venation. Machine learning was used to learn a codebook of visual elements representing leaf shape and venation patterns. The resulting automated system learned to classify images into families and orders with a success rate many times greater than chance. Of direct botanical interest, the responses of diagnostic features can be visualized on leaf images as heat maps, which are likely to prompt recognition and evolutionary interpretation of a wealth of novel morphological characters. With assistance from computer vision, leaves are poised to make numerous new contributions to systematic and paleobotanical studies. PMID:26951664

Non-target adjacent stimuli classification improves performance of classical ERP-based brain computer interface

NASA Astrophysics Data System (ADS)

Ceballos, G. A.; Hernández, L. F.

2015-04-01

Objective. The classical ERP-based speller, or P300 Speller, is one of the most commonly used paradigms in the field of Brain Computer Interfaces (BCI). Several alterations to the visual stimuli presentation system have been developed to avoid unfavorable effects elicited by adjacent stimuli. However, there has been little, if any, regard to useful information contained in responses to adjacent stimuli about spatial location of target symbols. This paper aims to demonstrate that combining the classification of non-target adjacent stimuli with standard classification (target versus non-target) significantly improves classical ERP-based speller efficiency. Approach. Four SWLDA classifiers were trained and combined with the standard classifier: the lower row, upper row, right column and left column classifiers. This new feature extraction procedure and the classification method were carried out on three open databases: the UAM P300 database (Universidad Autonoma Metropolitana, Mexico), BCI competition II (dataset IIb) and BCI competition III (dataset II). Main results. The inclusion of the classification of non-target adjacent stimuli improves target classification in the classical row/column paradigm. A gain in mean single trial classification of 9.6% and an overall improvement of 25% in simulated spelling speed was achieved. Significance. We have provided further evidence that the ERPs produced by adjacent stimuli present discriminable features, which could provide additional information about the spatial location of intended symbols. This work promotes the searching of information on the peripheral stimulation responses to improve the performance of emerging visual ERP-based spellers.

Unsupervised Learning in an Ensemble of Spiking Neural Networks Mediated by ITDP

PubMed Central

Staras, Kevin

2016-01-01

We propose a biologically plausible architecture for unsupervised ensemble learning in a population of spiking neural network classifiers. A mixture of experts type organisation is shown to be effective, with the individual classifier outputs combined via a gating network whose operation is driven by input timing dependent plasticity (ITDP). The ITDP gating mechanism is based on recent experimental findings. An abstract, analytically tractable model of the ITDP driven ensemble architecture is derived from a logical model based on the probabilities of neural firing events. A detailed analysis of this model provides insights that allow it to be extended into a full, biologically plausible, computational implementation of the architecture which is demonstrated on a visual classification task. The extended model makes use of a style of spiking network, first introduced as a model of cortical microcircuits, that is capable of Bayesian inference, effectively performing expectation maximization. The unsupervised ensemble learning mechanism, based around such spiking expectation maximization (SEM) networks whose combined outputs are mediated by ITDP, is shown to perform the visual classification task well and to generalize to unseen data. The combined ensemble performance is significantly better than that of the individual classifiers, validating the ensemble architecture and learning mechanisms. The properties of the full model are analysed in the light of extensive experiments with the classification task, including an investigation into the influence of different input feature selection schemes and a comparison with a hierarchical STDP based ensemble architecture. PMID:27760125

Chemometric brand differentiation of commercial spices using direct analysis in real time mass spectrometry.

PubMed

Pavlovich, Matthew J; Dunn, Emily E; Hall, Adam B

2016-05-15

Commercial spices represent an emerging class of fuels for improvised explosives. Being able to classify such spices not only by type but also by brand would represent an important step in developing methods to analytically investigate these explosive compositions. Therefore, a combined ambient mass spectrometric/chemometric approach was developed to quickly and accurately classify commercial spices by brand. Direct analysis in real time mass spectrometry (DART-MS) was used to generate mass spectra for samples of black pepper, cayenne pepper, and turmeric, along with four different brands of cinnamon, all dissolved in methanol. Unsupervised learning techniques showed that the cinnamon samples clustered according to brand. Then, we used supervised machine learning algorithms to build chemometric models with a known training set and classified the brands of an unknown testing set of cinnamon samples. Ten independent runs of five-fold cross-validation showed that the training set error for the best-performing models (i.e., the linear discriminant and neural network models) was lower than 2%. The false-positive percentages for these models were 3% or lower, and the false-negative percentages were lower than 10%. In particular, the linear discriminant model perfectly classified the testing set with 0% error. Repeated iterations of training and testing gave similar results, demonstrating the reproducibility of these models. Chemometric models were able to classify the DART mass spectra of commercial cinnamon samples according to brand, with high specificity and low classification error. This method could easily be generalized to other classes of spices, and it could be applied to authenticating questioned commercial samples of spices or to examining evidence from improvised explosives. Copyright © 2016 John Wiley & Sons, Ltd.

The dark side of the alpha rhythm: fMRI evidence for induced alpha modulation during complete darkness.

PubMed

Ben-Simon, Eti; Podlipsky, Ilana; Okon-Singer, Hadas; Gruberger, Michal; Cvetkovic, Dean; Intrator, Nathan; Hendler, Talma

2013-03-01

The unique role of the EEG alpha rhythm in different states of cortical activity is still debated. The main theories regarding alpha function posit either sensory processing or attention allocation as the main processes governing its modulation. Closing and opening eyes, a well-known manipulation of the alpha rhythm, could be regarded as attention allocation from inward to outward focus though during light is also accompanied by visual change. To disentangle the effects of attention allocation and sensory visual input on alpha modulation, 14 healthy subjects were asked to open and close their eyes during conditions of light and of complete darkness while simultaneous recordings of EEG and fMRI were acquired. Thus, during complete darkness the eyes-open condition is not related to visual input but only to attention allocation, allowing direct examination of its role in alpha modulation. A data-driven ridge regression classifier was applied to the EEG data in order to ascertain the contribution of the alpha rhythm to eyes-open/eyes-closed inference in both lighting conditions. Classifier results revealed significant alpha contribution during both light and dark conditions, suggesting that alpha rhythm modulation is closely linked to the change in the direction of attention regardless of the presence of visual sensory input. Furthermore, fMRI activation maps derived from an alpha modulation time-course during the complete darkness condition exhibited a right frontal cortical network associated with attention allocation. These findings support the importance of top-down processes such as attention allocation to alpha rhythm modulation, possibly as a prerequisite to its known bottom-up processing of sensory input. © 2012 Federation of European Neuroscience Societies and Blackwell Publishing Ltd.

Peripheral Visual Fields in ABCA4 Stargardt Disease and Correlation With Disease Extent on Ultra-widefield Fundus Autofluorescence.

PubMed

Abalem, Maria Fernanda; Otte, Benjamin; Andrews, Chris; Joltikov, Katherine A; Branham, Kari; Fahim, Abigail T; Schlegel, Dana; Qian, Cynthia X; Heckenlively, John R; Jayasundera, Thiran

2017-12-01

To evaluate the disease extent on ultra-widefield fundus autofluorescence (UWF-FAF) in patients with ABCA4 Stargardt disease (STGD) and correlate these data with functional outcome measures. Retrospective cross-sectional study. Setting: Kellogg Eye Center, University of Michigan. Sixty-five patients with clinical diagnosis and proven pathogenic variants in the ABCA4 gene. Observational Procedures: The UWF-FAF images were obtained using Optos (200 degrees) and classified into 3 types. Functional testing included kinetic widefield perimetry, full-field electroretinogram (ffERG), and visual acuity (VA). All results were evaluated with respect to UWF-FAF classification. Classification of UWF-FAF; area comprising the I4e, III4e, and IV4e isopters; ffERG patterns; and VA. For UWF-FAF, 27 subjects (41.5%) were classified as type I, 17 (26.2%) as type II, and 21 (32.4%) as type III. The area of each isopter correlated inversely with the extent of the disease and all isopters were able to detect differences among UWF-FAF types (IV4e, P = .0013; III4e, P = .0003; I4e, P < .0001 = 3.93e -8 ). ffERG patterns and VA were also different among the 3 UWF-FAF types (P < .001 = 6.61e- 6 and P < .001 = 7.3e -5 , respectively). Patients with widespread disease presented with more constriction of peripheral visual fields and had more dysfunction on ffERG and worse VA compared to patients with disease confined to the macula. UWF-FAF images may provide information for estimating peripheral and central visual function in STGD. Copyright © 2017. Published by Elsevier Inc.

Increasing Valid Profiles in Phallometric Assessment of Sex Offenders with Child Victims: Combining the Strengths of Audio Stimuli and Synthetic Characters.

PubMed

Marschall-Lévesque, Shawn; Rouleau, Joanne-Lucine; Renaud, Patrice

2018-02-01

Penile plethysmography (PPG) is a measure of sexual interests that relies heavily on the stimuli it uses to generate valid results. Ethical considerations surrounding the use of real images in PPG have further limited the content admissible for these stimuli. To palliate this limitation, the current study aimed to combine audio and visual stimuli by incorporating computer-generated characters to create new stimuli capable of accurately classifying sex offenders with child victims, while also increasing the number of valid profiles. Three modalities (audio, visual, and audiovisual) were compared using two groups (15 sex offenders with child victims and 15 non-offenders). Both the new visual and audiovisual stimuli resulted in a 13% increase in the number of valid profiles at 2.5 mm, when compared to the standard audio stimuli. Furthermore, the new audiovisual stimuli generated a 34% increase in penile responses. All three modalities were able to discriminate between the two groups by their responses to the adult and child stimuli. Lastly, sexual interest indices for all three modalities could accurately classify participants in their appropriate groups, as demonstrated by ROC curve analysis (i.e., audio AUC = .81, 95% CI [.60, 1.00]; visual AUC = .84, 95% CI [.66, 1.00], and audiovisual AUC = .83, 95% CI [.63, 1.00]). Results suggest that computer-generated characters allow accurate discrimination of sex offenders with child victims and can be added to already validated stimuli to increase the number of valid profiles. The implications of audiovisual stimuli using computer-generated characters and their possible use in PPG evaluations are also discussed.

High resolution esophageal manometry--the switch from "intuitive" visual interpretation to Chicago classification.

PubMed

Srinivas, M; Balakumaran, T A; Palaniappan, S; Srinivasan, Vijaya; Batcha, M; Venkataraman, Jayanthi

2014-03-01

High resolution esophageal manometry (HREM) has been interpreted all along by visual interpretation of color plots until the recent introduction of Chicago classification which categorises HREM using objective measurements. It compares HREM diagnosis of esophageal motor disorders by visual interpretation and Chicago classification. Using software Trace 1.2v, 77 consecutive tracings diagnosed by visual interpretation were re-analyzed by Chicago classification and findings compared for concordance between the two systems of interpretation. Kappa agreement rate between the two observations was determined. There were 57 males (74 %) and cohort median age was 41 years (range: 14-83 years). Majority of the referrals were for gastroesophageal reflux disease, dysphagia and achalasia. By "intuitive" visual interpretation, the tracing were reported as normal in 45 (58.4 %), achalasia 14 (18.2 %), ineffective esophageal motility 3 (3.9 %), nutcracker esophagus 11 (14.3 %) and nonspecific motility changes 4 (5.2 %). By Chicago classification, there was 100 % agreement (Kappa 1) for achalasia (type 1: 9; type 2: 5) and ineffective esophageal motility ("failed peristalsis" on visual interpretation). Normal esophageal motility, nutcracker esophagus and nonspecific motility disorder on visual interpretation were reclassified as rapid contraction and esophagogastric junction (EGJ) outflow obstruction by Chicago classification. Chicago classification identified distinct clinical phenotypes including EGJ outflow obstruction not identified by visual interpretation. A significant number of unclassified HREM by visual interpretation were also classified by it.

Viewing behavior and related clinical characteristics in a population of children with visual impairments in the Netherlands.

PubMed

Kooiker, M J G; Pel, J J M; van der Steen, J

2014-06-01

Children with visual impairments are very heterogeneous in terms of the extent of visual and developmental etiology. The aim of the present study was to investigate a possible correlation between prevalence of clinical risk factors of visual processing impairments and characteristics of viewing behavior. We tested 149 children with visual information processing impairments (90 boys, 59 girls; mean age (SD)=7.3 (3.3)) and 127 children without visual impairments (63 boys and 64 girls, mean age (SD)=7.9 (2.8)). Visual processing impairments were classified based on the time it took to complete orienting responses to various visual stimuli (form, contrast, motion detection, motion coherence, color and a cartoon). Within the risk group, children were divided into a fast, medium or slow group based on the response times to a highly salient stimulus. The relationship between group specific response times and clinical risk factors was assessed. The fast responding children in the risk group were significantly slower than children in the control group. Within the risk group, the prevalence of cerebral visual impairment, brain damage and intellectual disabilities was significantly higher in slow responding children compared to faster responding children. The presence of nystagmus, perceptual dysfunctions, mean visual acuity and mean age did not significantly differ between the subgroups. Orienting responses are related to risk factors for visual processing impairments known to be prevalent in visual rehabilitation practice. The proposed method may contribute to assessing the effectiveness of visual information processing in children. Copyright © 2014 Elsevier Ltd. All rights reserved.

Multi-temporal surveys for microplastic particles enabled by a novel and fast application of SWIR imaging spectroscopy - Study of an urban watercourse traversing the city of Berlin, Germany.

PubMed

Schmidt, L Katharina; Bochow, Mathias; Imhof, Hannes K; Oswald, Sascha E

2018-08-01

Following the widespread assumption that a majority of ubiquitous marine microplastic particles originate from land-based sources, recent studies identify rivers as important pathways for microplastic particles (MPP) to the oceans. Yet a detailed understanding of the underlying processes and dominant sources is difficult to obtain with the existing accurate but extremely time-consuming methods available for the identification of MPP. Thus in the presented study, a novel approach applying short-wave infrared imaging spectroscopy for the quick and semi-automated identification of MPP is applied in combination with a multitemporal survey concept. Volume-reduced surface water samples were taken from transects at ten points along a major watercourse running through the South of Berlin, Germany, on six dates. After laboratory treatment, the samples were filtered onto glass fiber filters, scanned with an imaging spectrometer and analyzed by image processing. The presented method allows to count MPP, classify the plastic types and determine particle sizes. At the present stage of development particles larger than 450 μm in diameter can be identified and a visual validation showed that the results are reliable after a subsequent visual final check of certain typical error types. Therefore, the method has the potential to accelerate microplastic identification by complementing FTIR and Raman microspectroscopy. Technical advancements (e.g. new lens) will allow lower detection limits and a higher grade of automatization in the near future. The resulting microplastic concentrations in the water samples are discussed in a spatio-temporal context with respect to the influence (i) of urban areas, (ii) of effluents of three major Berlin wastewater treatment plants discharging into the canal and (iii) of precipitation events. Microplastic concentrations were higher downstream of the urban area and after precipitation. An increase in microplastic concentrations was discernible for the wastewater treatment plant located furthest upstream though not for the other two. Copyright © 2018 Elsevier Ltd. All rights reserved.

Computer-aided diagnosis of early knee osteoarthritis based on MRI T2 mapping.

PubMed

Wu, Yixiao; Yang, Ran; Jia, Sen; Li, Zhanjun; Zhou, Zhiyang; Lou, Ting

2014-01-01

This work was aimed at studying the method of computer-aided diagnosis of early knee OA (OA: osteoarthritis). Based on the technique of MRI (MRI: Magnetic Resonance Imaging) T2 Mapping, through computer image processing, feature extraction, calculation and analysis via constructing a classifier, an effective computer-aided diagnosis method for knee OA was created to assist doctors in their accurate, timely and convenient detection of potential risk of OA. In order to evaluate this method, a total of 1380 data from the MRI images of 46 samples of knee joints were collected. These data were then modeled through linear regression on an offline general platform by the use of the ImageJ software, and a map of the physical parameter T2 was reconstructed. After the image processing, the T2 values of ten regions in the WORMS (WORMS: Whole-organ Magnetic Resonance Imaging Score) areas of the articular cartilage were extracted to be used as the eigenvalues in data mining. Then,a RBF (RBF: Radical Basis Function) network classifier was built to classify and identify the collected data. The classifier exhibited a final identification accuracy of 75%, indicating a good result of assisting diagnosis. Since the knee OA classifier constituted by a weights-directly-determined RBF neural network didn't require any iteration, our results demonstrated that the optimal weights, appropriate center and variance could be yielded through simple procedures. Furthermore, the accuracy for both the training samples and the testing samples from the normal group could reach 100%. Finally, the classifier was superior both in time efficiency and classification performance to the frequently used classifiers based on iterative learning. Thus it was suitable to be used as an aid to computer-aided diagnosis of early knee OA.

Multi-view L2-SVM and its multi-view core vector machine.

PubMed

Huang, Chengquan; Chung, Fu-lai; Wang, Shitong

2016-03-01

In this paper, a novel L2-SVM based classifier Multi-view L2-SVM is proposed to address multi-view classification tasks. The proposed Multi-view L2-SVM classifier does not have any bias in its objective function and hence has the flexibility like μ-SVC in the sense that the number of the yielded support vectors can be controlled by a pre-specified parameter. The proposed Multi-view L2-SVM classifier can make full use of the coherence and the difference of different views through imposing the consensus among multiple views to improve the overall classification performance. Besides, based on the generalized core vector machine GCVM, the proposed Multi-view L2-SVM classifier is extended into its GCVM version MvCVM which can realize its fast training on large scale multi-view datasets, with its asymptotic linear time complexity with the sample size and its space complexity independent of the sample size. Our experimental results demonstrated the effectiveness of the proposed Multi-view L2-SVM classifier for small scale multi-view datasets and the proposed MvCVM classifier for large scale multi-view datasets. Copyright © 2015 Elsevier Ltd. All rights reserved.

An evaluation of sampling and full enumeration strategies for Fisher Jenks classification in big data settings

USGS Publications Warehouse

Rey, Sergio J.; Stephens, Philip A.; Laura, Jason R.

2017-01-01

Large data contexts present a number of challenges to optimal choropleth map classifiers. Application of optimal classifiers to a sample of the attribute space is one proposed solution. The properties of alternative sampling-based classification methods are examined through a series of Monte Carlo simulations. The impacts of spatial autocorrelation, number of desired classes, and form of sampling are shown to have significant impacts on the accuracy of map classifications. Tradeoffs between improved speed of the sampling approaches and loss of accuracy are also considered. The results suggest the possibility of guiding the choice of classification scheme as a function of the properties of large data sets.

Any way you look at it, successful obstacle negotiation needs visually guided on-line foot placement regulation during the approach phase.

PubMed

Patla, Aftab E; Greig, Michael

In the two experiments discussed in this paper we quantified obstacle avoidance performance characteristics carried out open loop (without vision) but with different initial visual sampling conditions and compared it to the full vision condition. The initial visual sampling conditions included: static vision (SV), vision during forward walking for three steps and stopping (FW), vision during forward walking for three steps and not stopping (FW-NS), and vision during backward walking for three steps and stopping (BW). In experiment 1, we compared performance during SV, FW and BW with full vision condition, while in the second experiment we compared performance during FW and FW-NS conditions. The questions we wanted to address are: Is ecologically valid dynamic visual sampling of the environment superior to static visual sampling for open loop obstacle avoidance task? What are the reasons for failure in performing open loop obstacle avoidance task? The results showed that irrespective of the initial visual sampling condition when open loop control is initiated from a standing posture, the success rate was only approximately 50%. The main reason for the high failure rates was not inappropriate limb elevation, but incorrect foot placement before the obstacle. The second experiment showed that it is not the nature of visual sampling per se that influences success rate, but the fact that the open loop obstacle avoidance task is initiated from a standing posture. The results of these two experiments clearly demonstrate the importance of on-line visual information for adaptive human locomotion.

JAMSTEC E-library of Deep-sea Images (J-EDI) Realizes a Virtual Journey to the Earth's Unexplored Deep Ocean

NASA Astrophysics Data System (ADS)

Sasaki, T.; Azuma, S.; Matsuda, S.; Nagayama, A.; Ogido, M.; Saito, H.; Hanafusa, Y.

2016-12-01

The Japan Agency for Marine-Earth Science and Technology (JAMSTEC) archives a large amount of deep-sea research videos and photos obtained by JAMSTEC's research submersibles and vehicles with cameras. The web site "JAMSTEC E-library of Deep-sea Images : J-EDI" (http://www.godac.jamstec.go.jp/jedi/e/) has made videos and photos available to the public via the Internet since 2011. Users can search for target videos and photos by keywords, easy-to-understand icons, and dive information at J-EDI because operating staffs classify videos and photos as to contents, e.g. living organism and geological environment, and add comments to them.Dive survey data including videos and photos are not only valiant academically but also helpful for education and outreach activities. With the aim of the improvement of visibility for broader communities, we added new functions of 3-dimensional display synchronized various dive survey data with videos in this year.New Functions Users can search for dive survey data by 3D maps with plotted dive points using the WebGL virtual map engine "Cesium". By selecting a dive point, users can watch deep-sea videos and photos and associated environmental data, e.g. water temperature, salinity, rock and biological sample photos, obtained by the dive survey. Users can browse a dive track visualized in 3D virtual spaces using the WebGL JavaScript library. By synchronizing this virtual dive track with videos, users can watch deep-sea videos recorded at a point on a dive track. Users can play an animation which a submersible-shaped polygon automatically traces a 3D virtual dive track and displays of dive survey data are synchronized with tracing a dive track. Users can directly refer to additional information of other JAMSTEC data sites such as marine biodiversity database, marine biological sample database, rock sample database, and cruise and dive information database, on each page which a 3D virtual dive track is displayed. A 3D visualization of a dive track makes users experience a virtual dive survey. In addition, by synchronizing a virtual dive track with videos, it is easy to understand living organisms and geological environments of a dive point. Therefore, these functions will visually support understanding of deep-sea environments in lectures and educational activities.

Data Mining and Visualization of Twin-Cities Traffic Data

DTIC Science & Technology

2001-03-08

Ramsey I W Q Ramsey Table The...using the n attributes in the data set The class models are then used to classify test set which the class labels are not provided A decisiontree...interval for January while the testing set is the trac ow on January The training accuracy is and testing accuracy is The

A Comparison between Learning Style Preferences and Sex, Status, and Course Performance

ERIC Educational Resources Information Center

Dobson, John L.

2010-01-01

Students have learning style preferences that are often classified according to their visual (V), aural (A), read-write (R), and/or kinesthetic (K) sensory modality preferences (SMP). The purposes of this investigation were to compare student perceived and assessed SMPs and examine the associations between those SMPs and status (i.e.,…

Investigation of Rho Signaling Pathways in 3-D Collagen Matrices with Multidimensional Microscopy and Visualization Techniques

DTIC Science & Technology

2008-03-01

most prevalent cancer among women .1 Therefore, tech- ologies to detect, classify, study, and combat breast cancer re of great significance. Among these...M. Sidani , J. Wyckoff, C. Xue, J. E. Segall, and J. Condeelis, “Prob- ing the microenvironment of mammary tumors using multiphoton microscopy,” J

Survey on Classifying Human Actions through Visual Sensors

DTIC Science & Technology

2011-04-08

International Conference on Automatic Face and Gesture Recognition, 2008, pp. 1-6, doi:10.1109/AFGR.2008.4813416. [47] Herrera, A., Beck , A., Bell, D...Announcement, DARPA- BAA -10-53, 2010 www.darpa.mil/tcto/docs/DARPA_ME_BAA-10-53_Mod1.pdf [84] Del Rose, M., Stein, J., “Survivability on the ART Robotic

Resource Directory & Access Guide for Allied Health Professionals by the Family Centered Program on Intervention.

ERIC Educational Resources Information Center

Ohio State Univ., Columbus. Herschel W. Nisonger Center.

The manual is intended to help students and professionals in allied health fields find resources for helping disabled students and adults and their families. The first and largest section is a directory of organizations classified according to 15 topics, including advocacy, alcoholism, blindness and visual impairment, child abuse, learning…

Orthographic Effects in the Word Substitutions of Aphasic Patients: An Epidemic of Right Neglect Dyslexia?

ERIC Educational Resources Information Center

Berndt, Rita Sloan; Haendiges, Anne N.; Mitchum, Charlotte C.

2005-01-01

Aphasic patients with reading impairments frequently substitute incorrect real words for target words when reading aloud. Many of these word substitutions have substantial orthographic overlap with their targets and are classified as ''visual errors'' (i.e., sharing 50% of targets' letters in the same relative position). Fifteen chronic aphasic…

Root morphology and growth of bare-root seedlings of Oregon white oak

Treesearch

Peter J. Gould; Constance A. Harrington

2009-01-01

Root morphology and stem size were evaluated as predictors of height and basal-area growth (measured at groundline) of 1-1 Oregon white oak (Quercus garryana Dougl. ex Hook.) seedlings planted in raised beds with or without an additional irrigation treatment. Seedlings were classified into three root classes based on a visual assessment of the...

The Social World of Peer Rejected Children as Revealed by a Wireless Audio-Visual Transmission System.

ERIC Educational Resources Information Center

Asher, Steven R.; Gabriel, Sonda W.

This paper describes an observational methodology designed to permit increased understanding of the day-to-day social world of school children. The methodology was developed in the course of investigations of the extent to which children classified as rejected on sociometric measures actually experience overt rejection at school. Discussions of…

Audio Visual Instructional Materials for Distributive Education; a Classified Bibliography. Final Report.

ERIC Educational Resources Information Center

Levendowski, Jerry C.

The bibliography contains a list of 90 names and addresses of sources of audiovisual instructional materials. For each title a brief description of content, the source, purchase price, rental fee or free use for 16MM films, sound-slidefilms, tapes-records, and transparencies is given. Materials are listed separately by topics: (1) advertising and…

Blindness and visual impairment in opera.

PubMed

Aydin, Pinar; Ritch, Robert; O'Dwyer, John

2018-01-01

The performing arts mirror the human condition. This study sought to analyze the reasons for inclusion of visually impaired characters in opera, the cause of the blindness or near blindness, and the dramatic purpose of the blindness in the storyline. We reviewed operas from the 18 th century to 2010 and included all characters with ocular problems. We classified the cause of each character's ocular problem (organic, nonorganic, and other) in relation to the thematic setting of the opera: biblical and mythical, blind beggars or blind musicians, historical (real or fictional characters), and contemporary or futuristic. Cases of blindness in 55 characters (2 as a choir) from 38 operas were detected over 3 centuries of repertoire: 11 had trauma-related visual impairment, 5 had congenital blindness, 18 had visual impairment of unknown cause, 9 had psychogenic or malingering blindness, and 12 were symbolic or miracle-related. One opera featured an ophthalmologist curing a patient. The research illustrates that visual impairment was frequently used as an artistic device to enhance the intent and situate an opera in its time.

Visualization techniques for computer network defense

NASA Astrophysics Data System (ADS)

Beaver, Justin M.; Steed, Chad A.; Patton, Robert M.; Cui, Xiaohui; Schultz, Matthew

2011-06-01

Effective visual analysis of computer network defense (CND) information is challenging due to the volume and complexity of both the raw and analyzed network data. A typical CND is comprised of multiple niche intrusion detection tools, each of which performs network data analysis and produces a unique alerting output. The state-of-the-practice in the situational awareness of CND data is the prevalent use of custom-developed scripts by Information Technology (IT) professionals to retrieve, organize, and understand potential threat events. We propose a new visual analytics framework, called the Oak Ridge Cyber Analytics (ORCA) system, for CND data that allows an operator to interact with all detection tool outputs simultaneously. Aggregated alert events are presented in multiple coordinated views with timeline, cluster, and swarm model analysis displays. These displays are complemented with both supervised and semi-supervised machine learning classifiers. The intent of the visual analytics framework is to improve CND situational awareness, to enable an analyst to quickly navigate and analyze thousands of detected events, and to combine sophisticated data analysis techniques with interactive visualization such that patterns of anomalous activities may be more easily identified and investigated.

Target discrimination method for SAR images based on semisupervised co-training

NASA Astrophysics Data System (ADS)

Wang, Yan; Du, Lan; Dai, Hui

2018-01-01

Synthetic aperture radar (SAR) target discrimination is usually performed in a supervised manner. However, supervised methods for SAR target discrimination may need lots of labeled training samples, whose acquirement is costly, time consuming, and sometimes impossible. This paper proposes an SAR target discrimination method based on semisupervised co-training, which utilizes a limited number of labeled samples and an abundant number of unlabeled samples. First, Lincoln features, widely used in SAR target discrimination, are extracted from the training samples and partitioned into two sets according to their physical meanings. Second, two support vector machine classifiers are iteratively co-trained with the extracted two feature sets based on the co-training algorithm. Finally, the trained classifiers are exploited to classify the test data. The experimental results on real SAR images data not only validate the effectiveness of the proposed method compared with the traditional supervised methods, but also demonstrate the superiority of co-training over self-training, which only uses one feature set.

Putative pyramidal neurons and interneurons in the monkey parietal cortex make different contributions to the performance of a visual grouping task.

PubMed

Yokoi, Isao; Komatsu, Hidehiko

2010-09-01

Visual grouping of discrete elements is an important function for object recognition. We recently conducted an experiment to study neural correlates of visual grouping. We recorded neuronal activities while monkeys performed a grouping detection task in which they discriminated visual patterns composed of discrete dots arranged in a cross and detected targets in which dots with the same contrast were aligned horizontally or vertically. We found that some neurons in the lateral bank of the intraparietal sulcus exhibit activity related to visual grouping. In the present study, we analyzed how different types of neurons contribute to visual grouping. We classified the recorded neurons as putative pyramidal neurons or putative interneurons, depending on the duration of their action potentials. We found that putative pyramidal neurons exhibited selectivity for the orientation of the target, and this selectivity was enhanced by attention to a particular target orientation. By contrast, putative interneurons responded more strongly to the target stimuli than to the nontargets, regardless of the orientation of the target. These results suggest that different classes of parietal neurons contribute differently to the grouping of discrete elements.

Visual selective attention and reading efficiency are related in children.

PubMed

Casco, C; Tressoldi, P E; Dellantonio, A

1998-09-01

We investigated the relationship between visual selective attention and linguistic performance. Subjects were classified in four categories according to their accuracy in a letter cancellation task involving selective attention. The task consisted in searching a target letter in a set of background letters and accuracy was measured as a function of set size. We found that children with the lowest performance in the cancellation task present a significantly slower reading rate and a higher number of reading visual errors than children with highest performance. Results also show that these groups of searchers present significant differences in a lexical search task whereas their performance did not differ in lexical decision and syllables control task. The relationship between letter search and reading, as well as the finding that poor readers-searchers perform poorly lexical search tasks also involving selective attention, suggest that the relationship between letter search and reading difficulty may reflect a deficit in a visual selective attention mechanisms which is involved in all these tasks. A deficit in visual attention can be linked to the problems that disabled readers present in the function of magnocellular stream which culminates in posterior parietal cortex, an area which plays an important role in guiding visual attention.

Decoding of Human Movements Based on Deep Brain Local Field Potentials Using Ensemble Neural Networks

PubMed Central

2017-01-01

Decoding neural activities related to voluntary and involuntary movements is fundamental to understanding human brain motor circuits and neuromotor disorders and can lead to the development of neuromotor prosthetic devices for neurorehabilitation. This study explores using recorded deep brain local field potentials (LFPs) for robust movement decoding of Parkinson's disease (PD) and Dystonia patients. The LFP data from voluntary movement activities such as left and right hand index finger clicking were recorded from patients who underwent surgeries for implantation of deep brain stimulation electrodes. Movement-related LFP signal features were extracted by computing instantaneous power related to motor response in different neural frequency bands. An innovative neural network ensemble classifier has been proposed and developed for accurate prediction of finger movement and its forthcoming laterality. The ensemble classifier contains three base neural network classifiers, namely, feedforward, radial basis, and probabilistic neural networks. The majority voting rule is used to fuse the decisions of the three base classifiers to generate the final decision of the ensemble classifier. The overall decoding performance reaches a level of agreement (kappa value) at about 0.729 ± 0.16 for decoding movement from the resting state and about 0.671 ± 0.14 for decoding left and right visually cued movements. PMID:29201041

Benign childhood epilepsy with occipital paroxysms: neuropsychological findings.

PubMed

Germanò, Eva; Gagliano, Antonella; Magazù, Angela; Sferro, Caterina; Calarese, Tiziana; Mannarino, Erminia; Calamoneri, Filippo

2005-05-01

Benign childhood epilepsy with occipital paroxysms is classified among childhood benign partial epilepsies. The absence of neurological and neuropsychological deficits has long been considered as a prerequisite for a diagnosis of benign childhood partial epilepsy. Much evidence has been reported in literature in the latest years suggesting a neuropsychological impairment in this type of epilepsy, particularly in the type with Rolandic paroxysms. The present work examines the neuropsychological profiles of a sample of subjects affected by the early-onset benign childhood occipital seizures (EBOS) described by Panayotopulos. The patient group included 22 children (14 males and 8 females; mean age 10.1+/-3.3 years) diagnosed as having EBOS. The patients were examined with a set of tests investigating neuropsychological functions: memory, attention, perceptive, motor, linguistic and academic (reading, writing, arithmetic) abilities. The same instruments have been given to a homogeneous control group as regards sex, age, level of education and socio-economic background. None of the subjects affected by EBOS showed intellectual deficit (mean IQ in Wechsler Full Scale 91.7; S.D. 8.9). Results show a widespread cognitive dysfunction in the context of a focal epileptogenic process in EBOS. In particular, children with EBOS show a significant occurrence of specific learning disabilities (SLD) and other subtle neuropsychological deficits. We found selective dysfunctions relating to perceptive-visual attentional ability (p<0.05), verbal and visual-spatial memory abilities (p<0.01), visual perception and visual-motor integration global abilities (p<0.01), manual dexterity tasks (p<0.05), some language tasks (p<0.05), reading and writing abilities (p<0.01) and arithmetic ability (p<0.01). The presence of cognitive dysfunctions in subjects with EBOS supports the hypothesis that epilepsy itself plays a role in the development of neuropsychological impairment. Supported by other studies that have documented subtle neuropsychological deficits in benign partial epilepsy, we stress the importance of reconsidering its supposed "cognitive benignity", particularly in occipital types.

Sociodemographic, lifestyle, and medical risk factors for visual impairment in an urban asian population: the singapore malay eye study.

PubMed

Chong, Elaine W; Lamoureux, Ecosse L; Jenkins, Mark A; Aung, Tin; Saw, Seang-Mei; Wong, Tien Y

2009-12-01

To describe the associations between sociodemographic, lifestyle, and medical risk factors and visual impairment in a Southeast Asian population. Population-based cross-sectional study of 3280 (78.7% response rate) Malay Singaporeans aged 40 to 80 years. Participants underwent a standardized interview, in which detailed sociodemographic histories were obtained, and clinical assessments for presenting and best-corrected visual acuity. Visual impairment (logMAR > 0.30) was classified as unilateral (1 eye impaired) or bilateral (both eyes impaired). Analyses used multivariate-adjusted multinomial logistic regression. Older age and lack of formal education was associated with increased odds of both unilateral and bilateral visual impairment based on presenting and best-corrected visual acuity. The odds doubled for each decade older, and lower education increased the odds 1.59- to 2.83-fold. Bilateral visual impairment was associated with being unemployed (odds ratio [OR], 1.84; 95% confidence interval [CI], 1.30-2.60), widowed status (OR, 1.51; 95% CI, 1.13-2.01), and higher systolic blood pressure (OR, 1.96; 95% CI, 1.44-2.66). Diabetes was associated with unilateral (OR, 1.47; 95% CI, 1.10-1.95) and bilateral (OR, 1.69; 95% CI, 1.23-2.32) visual impairment using best-corrected visual acuity. Older age, lower education, unemployment, being widowed, diabetes, and hypertension were independently associated with bilateral visual impairment. Public health interventions should be targeted to these at-risk populations.

DVV: a taxonomy for mixed reality visualization in image guided surgery.

PubMed

Kersten-Oertel, Marta; Jannin, Pierre; Collins, D Louis

2012-02-01

Mixed reality visualizations are increasingly studied for use in image guided surgery (IGS) systems, yet few mixed reality systems have been introduced for daily use into the operating room (OR). This may be the result of several factors: the systems are developed from a technical perspective, are rarely evaluated in the field, and/or lack consideration of the end user and the constraints of the OR. We introduce the Data, Visualization processing, View (DVV) taxonomy which defines each of the major components required to implement a mixed reality IGS system. We propose that these components be considered and used as validation criteria for introducing a mixed reality IGS system into the OR. A taxonomy of IGS visualization systems is a step toward developing a common language that will help developers and end users discuss and understand the constituents of a mixed reality visualization system, facilitating a greater presence of future systems in the OR. We evaluate the DVV taxonomy based on its goodness of fit and completeness. We demonstrate the utility of the DVV taxonomy by classifying 17 state-of-the-art research papers in the domain of mixed reality visualization IGS systems. Our classification shows that few IGS visualization systems' components have been validated and even fewer are evaluated.

The evaluation of alternate methodologies for land cover classification in an urbanizing area

NASA Technical Reports Server (NTRS)

Smekofski, R. M.

1981-01-01

The usefulness of LANDSAT in classifying land cover and in identifying and classifying land use change was investigated using an urbanizing area as the study area. The question of what was the best technique for classification was the primary focus of the study. The many computer-assisted techniques available to analyze LANDSAT data were evaluated. Techniques of statistical training (polygons from CRT, unsupervised clustering, polygons from digitizer and binary masks) were tested with minimum distance to the mean, maximum likelihood and canonical analysis with minimum distance to the mean classifiers. The twelve output images were compared to photointerpreted samples, ground verified samples and a current land use data base. Results indicate that for a reconnaissance inventory, the unsupervised training with canonical analysis-minimum distance classifier is the most efficient. If more detailed ground truth and ground verification is available, the polygons from the digitizer training with the canonical analysis minimum distance is more accurate.

Combining MLC and SVM Classifiers for Learning Based Decision Making: Analysis and Evaluations

PubMed Central

Zhang, Yi; Ren, Jinchang; Jiang, Jianmin

2015-01-01

Maximum likelihood classifier (MLC) and support vector machines (SVM) are two commonly used approaches in machine learning. MLC is based on Bayesian theory in estimating parameters of a probabilistic model, whilst SVM is an optimization based nonparametric method in this context. Recently, it is found that SVM in some cases is equivalent to MLC in probabilistically modeling the learning process. In this paper, MLC and SVM are combined in learning and classification, which helps to yield probabilistic output for SVM and facilitate soft decision making. In total four groups of data are used for evaluations, covering sonar, vehicle, breast cancer, and DNA sequences. The data samples are characterized in terms of Gaussian/non-Gaussian distributed and balanced/unbalanced samples which are then further used for performance assessment in comparing the SVM and the combined SVM-MLC classifier. Interesting results are reported to indicate how the combined classifier may work under various conditions. PMID:26089862

Combining MLC and SVM Classifiers for Learning Based Decision Making: Analysis and Evaluations.

PubMed

Zhang, Yi; Ren, Jinchang; Jiang, Jianmin

2015-01-01

Maximum likelihood classifier (MLC) and support vector machines (SVM) are two commonly used approaches in machine learning. MLC is based on Bayesian theory in estimating parameters of a probabilistic model, whilst SVM is an optimization based nonparametric method in this context. Recently, it is found that SVM in some cases is equivalent to MLC in probabilistically modeling the learning process. In this paper, MLC and SVM are combined in learning and classification, which helps to yield probabilistic output for SVM and facilitate soft decision making. In total four groups of data are used for evaluations, covering sonar, vehicle, breast cancer, and DNA sequences. The data samples are characterized in terms of Gaussian/non-Gaussian distributed and balanced/unbalanced samples which are then further used for performance assessment in comparing the SVM and the combined SVM-MLC classifier. Interesting results are reported to indicate how the combined classifier may work under various conditions.

Mapping raised bogs with an iterative one-class classification approach

NASA Astrophysics Data System (ADS)

Mack, Benjamin; Roscher, Ribana; Stenzel, Stefanie; Feilhauer, Hannes; Schmidtlein, Sebastian; Waske, Björn

2016-10-01

Land use and land cover maps are one of the most commonly used remote sensing products. In many applications the user only requires a map of one particular class of interest, e.g. a specific vegetation type or an invasive species. One-class classifiers are appealing alternatives to common supervised classifiers because they can be trained with labeled training data of the class of interest only. However, training an accurate one-class classification (OCC) model is challenging, particularly when facing a large image, a small class and few training samples. To tackle these problems we propose an iterative OCC approach. The presented approach uses a biased Support Vector Machine as core classifier. In an iterative pre-classification step a large part of the pixels not belonging to the class of interest is classified. The remaining data is classified by a final classifier with a novel model and threshold selection approach. The specific objective of our study is the classification of raised bogs in a study site in southeast Germany, using multi-seasonal RapidEye data and a small number of training sample. Results demonstrate that the iterative OCC outperforms other state of the art one-class classifiers and approaches for model selection. The study highlights the potential of the proposed approach for an efficient and improved mapping of small classes such as raised bogs. Overall the proposed approach constitutes a feasible approach and useful modification of a regular one-class classifier.

Filling-in visual motion with sounds.

PubMed

Väljamäe, A; Soto-Faraco, S

2008-10-01

Information about the motion of objects can be extracted by multiple sensory modalities, and, as a consequence, object motion perception typically involves the integration of multi-sensory information. Often, in naturalistic settings, the flow of such information can be rather discontinuous (e.g. a cat racing through the furniture in a cluttered room is partly seen and partly heard). This study addressed audio-visual interactions in the perception of time-sampled object motion by measuring adaptation after-effects. We found significant auditory after-effects following adaptation to unisensory auditory and visual motion in depth, sampled at 12.5 Hz. The visually induced (cross-modal) auditory motion after-effect was eliminated if visual adaptors flashed at half of the rate (6.25 Hz). Remarkably, the addition of the high-rate acoustic flutter (12.5 Hz) to this ineffective, sparsely time-sampled, visual adaptor restored the auditory after-effect to a level comparable to what was seen with high-rate bimodal adaptors (flashes and beeps). Our results suggest that this auditory-induced reinstatement of the motion after-effect from the poor visual signals resulted from the occurrence of sound-induced illusory flashes. This effect was found to be dependent both on the directional congruency between modalities and on the rate of auditory flutter. The auditory filling-in of time-sampled visual motion supports the feasibility of using reduced frame rate visual content in multisensory broadcasting and virtual reality applications.

Hierarchical classification method and its application in shape representation

NASA Astrophysics Data System (ADS)

Ireton, M. A.; Oakley, John P.; Xydeas, Costas S.

1992-04-01

In this paper we describe a technique for performing shaped-based content retrieval of images from a large database. In order to be able to formulate such user-generated queries about visual objects, we have developed an hierarchical classification technique. This hierarchical classification technique enables similarity matching between objects, with the position in the hierarchy signifying the level of generality to be used in the query. The classification technique is unsupervised, robust, and general; it can be applied to any suitable parameter set. To establish the potential of this classifier for aiding visual querying, we have applied it to the classification of the 2-D outlines of leaves.

Deep learning classification in asteroseismology

NASA Astrophysics Data System (ADS)

Hon, Marc; Stello, Dennis; Yu, Jie

2017-08-01

In the power spectra of oscillating red giants, there are visually distinct features defining stars ascending the red giant branch from those that have commenced helium core burning. We train a 1D convolutional neural network by supervised learning to automatically learn these visual features from images of folded oscillation spectra. By training and testing on Kepler red giants, we achieve an accuracy of up to 99 per cent in separating helium-burning red giants from those ascending the red giant branch. The convolutional neural network additionally shows capability in accurately predicting the evolutionary states of 5379 previously unclassified Kepler red giants, by which we now have greatly increased the number of classified stars.

A Joint Gaussian Process Model for Active Visual Recognition with Expertise Estimation in Crowdsourcing

PubMed Central

Long, Chengjiang; Hua, Gang; Kapoor, Ashish

2015-01-01

We present a noise resilient probabilistic model for active learning of a Gaussian process classifier from crowds, i.e., a set of noisy labelers. It explicitly models both the overall label noise and the expertise level of each individual labeler with two levels of flip models. Expectation propagation is adopted for efficient approximate Bayesian inference of our probabilistic model for classification, based on which, a generalized EM algorithm is derived to estimate both the global label noise and the expertise of each individual labeler. The probabilistic nature of our model immediately allows the adoption of the prediction entropy for active selection of data samples to be labeled, and active selection of high quality labelers based on their estimated expertise to label the data. We apply the proposed model for four visual recognition tasks, i.e., object category recognition, multi-modal activity recognition, gender recognition, and fine-grained classification, on four datasets with real crowd-sourced labels from the Amazon Mechanical Turk. The experiments clearly demonstrate the efficacy of the proposed model. In addition, we extend the proposed model with the Predictive Active Set Selection Method to speed up the active learning system, whose efficacy is verified by conducting experiments on the first three datasets. The results show our extended model can not only preserve a higher accuracy, but also achieve a higher efficiency. PMID:26924892

Multicolor microRNA FISH effectively differentiates tumor types

PubMed Central

Renwick, Neil; Cekan, Pavol; Masry, Paul A.; McGeary, Sean E.; Miller, Jason B.; Hafner, Markus; Li, Zhen; Mihailovic, Aleksandra; Morozov, Pavel; Brown, Miguel; Gogakos, Tasos; Mobin, Mehrpouya B.; Snorrason, Einar L.; Feilotter, Harriet E.; Zhang, Xiao; Perlis, Clifford S.; Wu, Hong; Suárez-Fariñas, Mayte; Feng, Huichen; Shuda, Masahiro; Moore, Patrick S.; Tron, Victor A.; Chang, Yuan; Tuschl, Thomas

2013-01-01

MicroRNAs (miRNAs) are excellent tumor biomarkers because of their cell-type specificity and abundance. However, many miRNA detection methods, such as real-time PCR, obliterate valuable visuospatial information in tissue samples. To enable miRNA visualization in formalin-fixed paraffin-embedded (FFPE) tissues, we developed multicolor miRNA FISH. As a proof of concept, we used this method to differentiate two skin tumors, basal cell carcinoma (BCC) and Merkel cell carcinoma (MCC), with overlapping histologic features but distinct cellular origins. Using sequencing-based miRNA profiling and discriminant analysis, we identified the tumor-specific miRNAs miR-205 and miR-375 in BCC and MCC, respectively. We addressed three major shortcomings in miRNA FISH, identifying optimal conditions for miRNA fixation and ribosomal RNA (rRNA) retention using model compounds and high-pressure liquid chromatography (HPLC) analyses, enhancing signal amplification and detection by increasing probe-hapten linker lengths, and improving probe specificity using shortened probes with minimal rRNA sequence complementarity. We validated our method on 4 BCC and 12 MCC tumors. Amplified miR-205 and miR-375 signals were normalized against directly detectable reference rRNA signals. Tumors were classified using predefined cutoff values, and all were correctly identified in blinded analysis. Our study establishes a reliable miRNA FISH technique for parallel visualization of differentially expressed miRNAs in FFPE tumor tissues. PMID:23728175

Clinical MR-mammography: are computer-assisted methods superior to visual or manual measurements for curve type analysis? A systematic approach.

PubMed

Baltzer, Pascal Andreas Thomas; Freiberg, Christian; Beger, Sebastian; Vag, Tibor; Dietzel, Matthias; Herzog, Aimee B; Gajda, Mieczyslaw; Camara, Oumar; Kaiser, Werner A

2009-09-01

Enhancement characteristics after administration of a contrast agent are regarded as a major criterion for differential diagnosis in magnetic resonance mammography (MRM). However, no consensus exists about the best measurement method to assess contrast enhancement kinetics. This systematic investigation was performed to compare visual estimation with manual region of interest (ROI) and computer-aided diagnosis (CAD) analysis for time curve measurements in MRM. A total of 329 patients undergoing surgery after MRM (1.5 T) were analyzed prospectively. Dynamic data were measured using visual estimation, including ROI as well as CAD methods, and classified depending on initial signal increase and delayed enhancement. Pathology revealed 469 lesions (279 malignant, 190 benign). Kappa agreement between the methods ranged from 0.78 to 0.81. Diagnostic accuracies of 74.4% (visual), 75.7% (ROI), and 76.6% (CAD) were found without statistical significant differences. According to our results, curve type measurements are useful as a diagnostic criterion in breast lesions irrespective of the method used.

CT-Definable Subtypes of Chronic Obstructive Pulmonary Disease: A Statement of the Fleischner Society

PubMed Central

Austin, John H. M.; Hogg, James C.; Grenier, Philippe A.; Kauczor, Hans-Ulrich; Bankier, Alexander A.; Barr, R. Graham; Colby, Thomas V.; Galvin, Jeffrey R.; Gevenois, Pierre Alain; Coxson, Harvey O.; Hoffman, Eric A.; Newell, John D.; Pistolesi, Massimo; Silverman, Edwin K.; Crapo, James D.

2015-01-01

The purpose of this statement is to describe and define the phenotypic abnormalities that can be identified on visual and quantitative evaluation of computed tomographic (CT) images in subjects with chronic obstructive pulmonary disease (COPD), with the goal of contributing to a personalized approach to the treatment of patients with COPD. Quantitative CT is useful for identifying and sequentially evaluating the extent of emphysematous lung destruction, changes in airway walls, and expiratory air trapping. However, visual assessment of CT scans remains important to describe patterns of altered lung structure in COPD. The classification system proposed and illustrated in this article provides a structured approach to visual and quantitative assessment of COPD. Emphysema is classified as centrilobular (subclassified as trace, mild, moderate, confluent, and advanced destructive emphysema), panlobular, and paraseptal (subclassified as mild or substantial). Additional important visual features include airway wall thickening, inflammatory small airways disease, tracheal abnormalities, interstitial lung abnormalities, pulmonary arterial enlargement, and bronchiectasis. © RSNA, 2015 PMID:25961632

Proteomic data analysis of glioma cancer stem-cell lines based on novel nonlinear dimensional data reduction techniques

NASA Astrophysics Data System (ADS)

Lespinats, Sylvain; Pinker-Domenig, Katja; Wengert, Georg; Houben, Ivo; Lobbes, Marc; Stadlbauer, Andreas; Meyer-Bäse, Anke

2016-05-01

Glioma-derived cancer stem cells (GSCs) are tumor-initiating cells and may be refractory to radiation and chemotherapy and thus have important implications for tumor biology and therapeutics. The analysis and interpretation of large proteomic data sets requires the development of new data mining and visualization approaches. Traditional techniques are insufficient to interpret and visualize these resulting experimental data. The emphasis of this paper lies in the application of novel approaches for the visualization, clustering and projection representation to unveil hidden data structures relevant for the accurate interpretation of biological experiments. These qualitative and quantitative methods are applied to the proteomic analysis of data sets derived from the GSCs. The achieved clustering and visualization results provide a more detailed insight into the protein-level fold changes and putative upstream regulators for the GSCs. However the extracted molecular information is insufficient in classifying GSCs and paving the pathway to an improved therapeutics of the heterogeneous glioma.

A Visual Profile of Queensland Indigenous Children.

PubMed

Hopkins, Shelley; Sampson, Geoff P; Hendicott, Peter L; Wood, Joanne M

2016-03-01

Little is known about the prevalence of refractive error, binocular vision, and other visual conditions in Australian Indigenous children. This is important given the association of these visual conditions with reduced reading performance in the wider population, which may also contribute to the suboptimal reading performance reported in this population. The aim of this study was to develop a visual profile of Queensland Indigenous children. Vision testing was performed on 595 primary schoolchildren in Queensland, Australia. Vision parameters measured included visual acuity, refractive error, color vision, nearpoint of convergence, horizontal heterophoria, fusional vergence range, accommodative facility, AC/A ratio, visual motor integration, and rapid automatized naming. Near heterophoria, nearpoint of convergence, and near fusional vergence range were used to classify convergence insufficiency (CI). Although refractive error (Indigenous, 10%; non-Indigenous, 16%; p = 0.04) and strabismus (Indigenous, 0%; non-Indigenous, 3%; p = 0.03) were significantly less common in Indigenous children, CI was twice as prevalent (Indigenous, 10%; non-Indigenous, 5%; p = 0.04). Reduced visual information processing skills were more common in Indigenous children (reduced visual motor integration [Indigenous, 28%; non-Indigenous, 16%; p < 0.01] and slower rapid automatized naming [Indigenous, 67%; non-Indigenous, 59%; p = 0.04]). The prevalence of visual impairment (reduced visual acuity) and color vision deficiency was similar between groups. Indigenous children have less refractive error and strabismus than their non-Indigenous peers. However, CI and reduced visual information processing skills were more common in this group. Given that vision screenings primarily target visual acuity assessment and strabismus detection, this is an important finding as many Indigenous children with CI and reduced visual information processing may be missed. Emphasis should be placed on identifying children with CI and reduced visual information processing given the potential effect of these conditions on school performance.

Enhancing AFLOW Visualization using Jmol

NASA Astrophysics Data System (ADS)

Lanasa, Jacob; New, Elizabeth; Stefek, Patrik; Honaker, Brigette; Hanson, Robert; Aflow Collaboration

The AFLOW library is a database of theoretical solid-state structures and calculated properties created using high-throughput ab initio calculations. Jmol is a Java-based program capable of visualizing and analyzing complex molecular structures and energy landscapes. In collaboration with the AFLOW consortium, our goal is the enhancement of the AFLOWLIB database through the extension of Jmol's capabilities in the area of materials science. Modifications made to Jmol include the ability to read and visualize AFLOW binary alloy data files, the ability to extract from these files information using Jmol scripting macros that can be utilized in the creation of interactive web-based convex hull graphs, the capability to identify and classify local atomic environments by symmetry, and the ability to search one or more related crystal structures for atomic environments using a novel extension of inorganic polyhedron-based SMILES strings

Area Determination of Diabetic Foot Ulcer Images Using a Cascaded Two-Stage SVM-Based Classification.

PubMed

Wang, Lei; Pedersen, Peder C; Agu, Emmanuel; Strong, Diane M; Tulu, Bengisu

2017-09-01

The standard chronic wound assessment method based on visual examination is potentially inaccurate and also represents a significant clinical workload. Hence, computer-based systems providing quantitative wound assessment may be valuable for accurately monitoring wound healing status, with the wound area the best suited for automated analysis. Here, we present a novel approach, using support vector machines (SVM) to determine the wound boundaries on foot ulcer images captured with an image capture box, which provides controlled lighting and range. After superpixel segmentation, a cascaded two-stage classifier operates as follows: in the first stage, a set of k binary SVM classifiers are trained and applied to different subsets of the entire training images dataset, and incorrectly classified instances are collected. In the second stage, another binary SVM classifier is trained on the incorrectly classified set. We extracted various color and texture descriptors from superpixels that are used as input for each stage in the classifier training. Specifically, color and bag-of-word representations of local dense scale invariant feature transformation features are descriptors for ruling out irrelevant regions, and color and wavelet-based features are descriptors for distinguishing healthy tissue from wound regions. Finally, the detected wound boundary is refined by applying the conditional random field method. We have implemented the wound classification on a Nexus 5 smartphone platform, except for training which was done offline. Results are compared with other classifiers and show that our approach provides high global performance rates (average sensitivity = 73.3%, specificity = 94.6%) and is sufficiently efficient for a smartphone-based image analysis.

Visualization and characterization of users in a citizen science project

NASA Astrophysics Data System (ADS)

Morais, Alessandra M. M.; Raddick, Jordan; Coelho dos Santos, Rafael D.

2013-05-01

Recent technological advances allowed the creation and use of internet-based systems where many users can collaborate gathering and sharing information for specific or general purposes: social networks, e-commerce review systems, collaborative knowledge systems, etc. Since most of the data collected in these systems is user-generated, understanding of the motivations and general behavior of users is a very important issue. Of particular interest are citizen science projects, where users without scientific training are asked for collaboration labeling and classifying information (either automatically by giving away idle computer time or manually by actually seeing data and providing information about it). Understanding behavior of users of those types of data collection systems may help increase the involvement of the users, categorize users accordingly to different parameters, facilitate their collaboration with the systems, design better user interfaces, and allow better planning and deployment of similar projects and systems. Behavior of those users could be estimated through analysis of their collaboration track: registers of which user did what and when can be easily and unobtrusively collected in several different ways, the simplest being a log of activities. In this paper we present some results on the visualization and characterization of almost 150.000 users with more than 80.000.000 collaborations with a citizen science project - Galaxy Zoo I, which asked users to classify galaxies' images. Basic visualization techniques are not applicable due to the number of users, so techniques to characterize users' behavior based on feature extraction and clustering are used.

Technological evaluation of gesture and speech interfaces for enabling dismounted soldier-robot dialogue

NASA Astrophysics Data System (ADS)

Kattoju, Ravi Kiran; Barber, Daniel J.; Abich, Julian; Harris, Jonathan

2016-05-01

With increasing necessity for intuitive Soldier-robot communication in military operations and advancements in interactive technologies, autonomous robots have transitioned from assistance tools to functional and operational teammates able to service an array of military operations. Despite improvements in gesture and speech recognition technologies, their effectiveness in supporting Soldier-robot communication is still uncertain. The purpose of the present study was to evaluate the performance of gesture and speech interface technologies to facilitate Soldier-robot communication during a spatial-navigation task with an autonomous robot. Gesture and speech semantically based spatial-navigation commands leveraged existing lexicons for visual and verbal communication from the U.S Army field manual for visual signaling and a previously established Squad Level Vocabulary (SLV). Speech commands were recorded by a Lapel microphone and Microsoft Kinect, and classified by commercial off-the-shelf automatic speech recognition (ASR) software. Visual signals were captured and classified using a custom wireless gesture glove and software. Participants in the experiment commanded a robot to complete a simulated ISR mission in a scaled down urban scenario by delivering a sequence of gesture and speech commands, both individually and simultaneously, to the robot. Performance and reliability of gesture and speech hardware interfaces and recognition tools were analyzed and reported. Analysis of experimental results demonstrated the employed gesture technology has significant potential for enabling bidirectional Soldier-robot team dialogue based on the high classification accuracy and minimal training required to perform gesture commands.

Speech and gesture interfaces for squad-level human-robot teaming

NASA Astrophysics Data System (ADS)

Harris, Jonathan; Barber, Daniel

2014-06-01

As the military increasingly adopts semi-autonomous unmanned systems for military operations, utilizing redundant and intuitive interfaces for communication between Soldiers and robots is vital to mission success. Currently, Soldiers use a common lexicon to verbally and visually communicate maneuvers between teammates. In order for robots to be seamlessly integrated within mixed-initiative teams, they must be able to understand this lexicon. Recent innovations in gaming platforms have led to advancements in speech and gesture recognition technologies, but the reliability of these technologies for enabling communication in human robot teaming is unclear. The purpose for the present study is to investigate the performance of Commercial-Off-The-Shelf (COTS) speech and gesture recognition tools in classifying a Squad Level Vocabulary (SLV) for a spatial navigation reconnaissance and surveillance task. The SLV for this study was based on findings from a survey conducted with Soldiers at Fort Benning, GA. The items of the survey focused on the communication between the Soldier and the robot, specifically in regards to verbally instructing them to execute reconnaissance and surveillance tasks. Resulting commands, identified from the survey, were then converted to equivalent arm and hand gestures, leveraging existing visual signals (e.g. U.S. Army Field Manual for Visual Signaling). A study was then run to test the ability of commercially available automated speech recognition technologies and a gesture recognition glove to classify these commands in a simulated intelligence, surveillance, and reconnaissance task. This paper presents classification accuracy of these devices for both speech and gesture modalities independently.

Generic Learning-Based Ensemble Framework for Small Sample Size Face Recognition in Multi-Camera Networks.

PubMed

Zhang, Cuicui; Liang, Xuefeng; Matsuyama, Takashi

2014-12-08

Multi-camera networks have gained great interest in video-based surveillance systems for security monitoring, access control, etc. Person re-identification is an essential and challenging task in multi-camera networks, which aims to determine if a given individual has already appeared over the camera network. Individual recognition often uses faces as a trial and requires a large number of samples during the training phrase. This is difficult to fulfill due to the limitation of the camera hardware system and the unconstrained image capturing conditions. Conventional face recognition algorithms often encounter the "small sample size" (SSS) problem arising from the small number of training samples compared to the high dimensionality of the sample space. To overcome this problem, interest in the combination of multiple base classifiers has sparked research efforts in ensemble methods. However, existing ensemble methods still open two questions: (1) how to define diverse base classifiers from the small data; (2) how to avoid the diversity/accuracy dilemma occurring during ensemble. To address these problems, this paper proposes a novel generic learning-based ensemble framework, which augments the small data by generating new samples based on a generic distribution and introduces a tailored 0-1 knapsack algorithm to alleviate the diversity/accuracy dilemma. More diverse base classifiers can be generated from the expanded face space, and more appropriate base classifiers are selected for ensemble. Extensive experimental results on four benchmarks demonstrate the higher ability of our system to cope with the SSS problem compared to the state-of-the-art system.

Generic Learning-Based Ensemble Framework for Small Sample Size Face Recognition in Multi-Camera Networks

PubMed Central

Zhang, Cuicui; Liang, Xuefeng; Matsuyama, Takashi

2014-01-01

Multi-camera networks have gained great interest in video-based surveillance systems for security monitoring, access control, etc. Person re-identification is an essential and challenging task in multi-camera networks, which aims to determine if a given individual has already appeared over the camera network. Individual recognition often uses faces as a trial and requires a large number of samples during the training phrase. This is difficult to fulfill due to the limitation of the camera hardware system and the unconstrained image capturing conditions. Conventional face recognition algorithms often encounter the “small sample size” (SSS) problem arising from the small number of training samples compared to the high dimensionality of the sample space. To overcome this problem, interest in the combination of multiple base classifiers has sparked research efforts in ensemble methods. However, existing ensemble methods still open two questions: (1) how to define diverse base classifiers from the small data; (2) how to avoid the diversity/accuracy dilemma occurring during ensemble. To address these problems, this paper proposes a novel generic learning-based ensemble framework, which augments the small data by generating new samples based on a generic distribution and introduces a tailored 0–1 knapsack algorithm to alleviate the diversity/accuracy dilemma. More diverse base classifiers can be generated from the expanded face space, and more appropriate base classifiers are selected for ensemble. Extensive experimental results on four benchmarks demonstrate the higher ability of our system to cope with the SSS problem compared to the state-of-the-art system. PMID:25494350

ANALYSIS OF SAMPLING TECHNIQUES FOR IMBALANCED DATA: AN N=648 ADNI STUDY

PubMed Central

Dubey, Rashmi; Zhou, Jiayu; Wang, Yalin; Thompson, Paul M.; Ye, Jieping

2013-01-01

Many neuroimaging applications deal with imbalanced imaging data. For example, in Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset, the mild cognitive impairment (MCI) cases eligible for the study are nearly two times the Alzheimer’s disease (AD) patients for structural magnetic resonance imaging (MRI) modality and six times the control cases for proteomics modality. Constructing an accurate classifier from imbalanced data is a challenging task. Traditional classifiers that aim to maximize the overall prediction accuracy tend to classify all data into the majority class. In this paper, we study an ensemble system of feature selection and data sampling for the class imbalance problem. We systematically analyze various sampling techniques by examining the efficacy of different rates and types of undersampling, oversampling, and a combination of over and under sampling approaches. We thoroughly examine six widely used feature selection algorithms to identify significant biomarkers and thereby reduce the complexity of the data. The efficacy of the ensemble techniques is evaluated using two different classifiers including Random Forest and Support Vector Machines based on classification accuracy, area under the receiver operating characteristic curve (AUC), sensitivity, and specificity measures. Our extensive experimental results show that for various problem settings in ADNI, (1). a balanced training set obtained with K-Medoids technique based undersampling gives the best overall performance among different data sampling techniques and no sampling approach; and (2). sparse logistic regression with stability selection achieves competitive performance among various feature selection algorithms. Comprehensive experiments with various settings show that our proposed ensemble model of multiple undersampled datasets yields stable and promising results. PMID:24176869

Differentiation of Candida albicans, Candida glabrata, and Candida krusei by FT-IR and chemometrics by CHROMagar™ Candida.

PubMed

Wohlmeister, Denise; Vianna, Débora Renz Barreto; Helfer, Virginia Etges; Calil, Luciane Noal; Buffon, Andréia; Fuentefria, Alexandre Meneghello; Corbellini, Valeriano Antonio; Pilger, Diogo André

2017-10-01

Pathogenic Candida species are detected in clinical infections. CHROMagar™ is a phenotypical method used to identify Candida species, although it has limitations, which indicates the need for more sensitive and specific techniques. Infrared Spectroscopy (FT-IR) is an analytical vibrational technique used to identify patterns of metabolic fingerprint of biological matrixes, particularly whole microbial cell systems as Candida sp. in association of classificatory chemometrics algorithms. On the other hand, Soft Independent Modeling by Class Analogy (SIMCA) is one of the typical algorithms still little employed in microbiological classification. This study demonstrates the applicability of the FT-IR-technique by specular reflectance associated with SIMCA to discriminate Candida species isolated from vaginal discharges and grown on CHROMagar™. The differences in spectra of C. albicans, C. glabrata and C. krusei were suitable for use in the discrimination of these species, which was observed by PCA. Then, a SIMCA model was constructed with standard samples of three species and using the spectral region of 1792-1561cm -1 . All samples (n=48) were properly classified based on the chromogenic method using CHROMagar™ Candida. In total, 93.4% (n=45) of the samples were correctly and unambiguously classified (Class I). Two samples of C. albicans were classified correctly, though these could have been C. glabrata (Class II). Also, one C. glabrata sample could have been classified as C. krusei (Class II). Concerning these three samples, one triplicate of each was included in Class II and two in Class I. Therefore, FT-IR associated with SIMCA can be used to identify samples of C. albicans, C. glabrata, and C. krusei grown in CHROMagar™ Candida aiming to improve clinical applications of this technique. Copyright © 2017 Elsevier B.V. All rights reserved.

Quasi-Supervised Scoring of Human Sleep in Polysomnograms Using Augmented Input Variables

PubMed Central

Yaghouby, Farid; Sunderam, Sridhar

2015-01-01

The limitations of manual sleep scoring make computerized methods highly desirable. Scoring errors can arise from human rater uncertainty or inter-rater variability. Sleep scoring algorithms either come as supervised classifiers that need scored samples of each state to be trained, or as unsupervised classifiers that use heuristics or structural clues in unscored data to define states. We propose a quasi-supervised classifier that models observations in an unsupervised manner but mimics a human rater wherever training scores are available. EEG, EMG, and EOG features were extracted in 30s epochs from human-scored polysomnograms recorded from 42 healthy human subjects (18 to 79 years) and archived in an anonymized, publicly accessible database. Hypnograms were modified so that: 1. Some states are scored but not others; 2. Samples of all states are scored but not for transitional epochs; and 3. Two raters with 67% agreement are simulated. A framework for quasi-supervised classification was devised in which unsupervised statistical models—specifically Gaussian mixtures and hidden Markov models—are estimated from unlabeled training data, but the training samples are augmented with variables whose values depend on available scores. Classifiers were fitted to signal features incorporating partial scores, and used to predict scores for complete recordings. Performance was assessed using Cohen's K statistic. The quasi-supervised classifier performed significantly better than an unsupervised model and sometimes as well as a completely supervised model despite receiving only partial scores. The quasi-supervised algorithm addresses the need for classifiers that mimic scoring patterns of human raters while compensating for their limitations. PMID:25679475

Quasi-supervised scoring of human sleep in polysomnograms using augmented input variables.

PubMed

Yaghouby, Farid; Sunderam, Sridhar

2015-04-01

The limitations of manual sleep scoring make computerized methods highly desirable. Scoring errors can arise from human rater uncertainty or inter-rater variability. Sleep scoring algorithms either come as supervised classifiers that need scored samples of each state to be trained, or as unsupervised classifiers that use heuristics or structural clues in unscored data to define states. We propose a quasi-supervised classifier that models observations in an unsupervised manner but mimics a human rater wherever training scores are available. EEG, EMG, and EOG features were extracted in 30s epochs from human-scored polysomnograms recorded from 42 healthy human subjects (18-79 years) and archived in an anonymized, publicly accessible database. Hypnograms were modified so that: 1. Some states are scored but not others; 2. Samples of all states are scored but not for transitional epochs; and 3. Two raters with 67% agreement are simulated. A framework for quasi-supervised classification was devised in which unsupervised statistical models-specifically Gaussian mixtures and hidden Markov models--are estimated from unlabeled training data, but the training samples are augmented with variables whose values depend on available scores. Classifiers were fitted to signal features incorporating partial scores, and used to predict scores for complete recordings. Performance was assessed using Cohen's Κ statistic. The quasi-supervised classifier performed significantly better than an unsupervised model and sometimes as well as a completely supervised model despite receiving only partial scores. The quasi-supervised algorithm addresses the need for classifiers that mimic scoring patterns of human raters while compensating for their limitations. Copyright © 2015 Elsevier Ltd. All rights reserved.

A Predictive Model for Toxicity Effects Assessment of Biotransformed Hepatic Drugs Using Iterative Sampling Method.

PubMed

Tharwat, Alaa; Moemen, Yasmine S; Hassanien, Aboul Ella

2016-12-09

Measuring toxicity is one of the main steps in drug development. Hence, there is a high demand for computational models to predict the toxicity effects of the potential drugs. In this study, we used a dataset, which consists of four toxicity effects:mutagenic, tumorigenic, irritant and reproductive effects. The proposed model consists of three phases. In the first phase, rough set-based methods are used to select the most discriminative features for reducing the classification time and improving the classification performance. Due to the imbalanced class distribution, in the second phase, different sampling methods such as Random Under-Sampling, Random Over-Sampling and Synthetic Minority Oversampling Technique are used to solve the problem of imbalanced datasets. ITerative Sampling (ITS) method is proposed to avoid the limitations of those methods. ITS method has two steps. The first step (sampling step) iteratively modifies the prior distribution of the minority and majority classes. In the second step, a data cleaning method is used to remove the overlapping that is produced from the first step. In the third phase, Bagging classifier is used to classify an unknown drug into toxic or non-toxic. The experimental results proved that the proposed model performed well in classifying the unknown samples according to all toxic effects in the imbalanced datasets.

Blood Based Biomarkers of Early Onset Breast Cancer

DTIC Science & Technology

2016-12-01

discretizes the data, and also using logistic elastic net – a form of linear regression - we were unable to build a classifier that could accurately...classifier for differentiating cases from controls off discretized data. The first pass analysis demonstrated a 35 gene signature that differentiated...to the discretized data for mRNA gene signature, the samples used to “train” were also included in the final samples used to “test” the algorithm

Self-similarity Clustering Event Detection Based on Triggers Guidance

NASA Astrophysics Data System (ADS)

Zhang, Xianfei; Li, Bicheng; Tian, Yuxuan

Traditional method of Event Detection and Characterization (EDC) regards event detection task as classification problem. It makes words as samples to train classifier, which can lead to positive and negative samples of classifier imbalance. Meanwhile, there is data sparseness problem of this method when the corpus is small. This paper doesn't classify event using word as samples, but cluster event in judging event types. It adopts self-similarity to convergence the value of K in K-means algorithm by the guidance of event triggers, and optimizes clustering algorithm. Then, combining with named entity and its comparative position information, the new method further make sure the pinpoint type of event. The new method avoids depending on template of event in tradition methods, and its result of event detection can well be used in automatic text summarization, text retrieval, and topic detection and tracking.

Dynamic analysis environment for nuclear forensic analyses

NASA Astrophysics Data System (ADS)

Stork, C. L.; Ummel, C. C.; Stuart, D. S.; Bodily, S.; Goldblum, B. L.

2017-01-01

A Dynamic Analysis Environment (DAE) software package is introduced to facilitate group inclusion/exclusion method testing, evaluation and comparison for pre-detonation nuclear forensics applications. Employing DAE, the multivariate signatures of a questioned material can be compared to the signatures for different, known groups, enabling the linking of the questioned material to its potential process, location, or fabrication facility. Advantages of using DAE for group inclusion/exclusion include built-in query tools for retrieving data of interest from a database, the recording and documentation of all analysis steps, a clear visualization of the analysis steps intelligible to a non-expert, and the ability to integrate analysis tools developed in different programming languages. Two group inclusion/exclusion methods are implemented in DAE: principal component analysis, a parametric feature extraction method, and k nearest neighbors, a nonparametric pattern recognition method. Spent Fuel Isotopic Composition (SFCOMPO), an open source international database of isotopic compositions for spent nuclear fuels (SNF) from 14 reactors, is used to construct PCA and KNN models for known reactor groups, and 20 simulated SNF samples are utilized in evaluating the performance of these group inclusion/exclusion models. For all 20 simulated samples, PCA in conjunction with the Q statistic correctly excludes a large percentage of reactor groups and correctly includes the true reactor of origination. Employing KNN, 14 of the 20 simulated samples are classified to their true reactor of origination.

Cryopreserved and frozen hyaline cartilage imaged by environmental scanning electron microscope. An experimental and prospective study.

PubMed

Sastre, Sergi; Suso, Santiago; Segur, Josep-Maria; Bori, Guillem; Carbonell, José-Antonio; Agustí, Elba; Nuñez, Montse

2008-08-01

To obtain images of the articular surface of osteochondral grafts (fresh, frozen, and cryopreserved in RPMI) using an environmental scanning electron microscope (ESEM). To evaluate and compare the main morphological aspects of the chondral surface of the fresh, frozen, and cryopreserved grafts as visualized via ESEM. The study was based on osteochondral fragments from the internal condyle of the knee joint of New Zealand rabbits, corresponding to the chondral surface from fresh, frozen, and cryopreserved samples. One hundred ESEM images were obtained from each group and then classified according to a validated system. The kappa index and the corresponding concordance index were calculated, and the groups were compared by Pearson's chi-squared test (p < 0.05). The articular surface of cryopreserved osteochondral grafts had fewer even surfaces and filled lacunae and a higher number of empty lacunae as compared to fresh samples; these differences correspond to images of cell membrane lesions that lead to destruction of the chondrocyte. Frozen grafts showed more hillocky and knobby surfaces than did fresh grafts; they also had a greater number of empty chondrocyte lacunae. ESEM is useful for obtaining images of the surface of osteochondral grafts. When compared to fresh samples, cryopreservation in RPMI medium produces changes in the surface of hyaline cartilage, but to a lesser extent than those produced by freezing.

Discriminative Transfer Subspace Learning via Low-Rank and Sparse Representation.

PubMed

Xu, Yong; Fang, Xiaozhao; Wu, Jian; Li, Xuelong; Zhang, David

2016-02-01

In this paper, we address the problem of unsupervised domain transfer learning in which no labels are available in the target domain. We use a transformation matrix to transfer both the source and target data to a common subspace, where each target sample can be represented by a combination of source samples such that the samples from different domains can be well interlaced. In this way, the discrepancy of the source and target domains is reduced. By imposing joint low-rank and sparse constraints on the reconstruction coefficient matrix, the global and local structures of data can be preserved. To enlarge the margins between different classes as much as possible and provide more freedom to diminish the discrepancy, a flexible linear classifier (projection) is obtained by learning a non-negative label relaxation matrix that allows the strict binary label matrix to relax into a slack variable matrix. Our method can avoid a potentially negative transfer by using a sparse matrix to model the noise and, thus, is more robust to different types of noise. We formulate our problem as a constrained low-rankness and sparsity minimization problem and solve it by the inexact augmented Lagrange multiplier method. Extensive experiments on various visual domain adaptation tasks show the superiority of the proposed method over the state-of-the art methods. The MATLAB code of our method will be publicly available at http://www.yongxu.org/lunwen.html.

Spectral classifier design with ensemble classifiers and misclassification-rejection: application to elastic-scattering spectroscopy for detection of colonic neoplasia.

PubMed

Rodriguez-Diaz, Eladio; Castanon, David A; Singh, Satish K; Bigio, Irving J

2011-06-01

Optical spectroscopy has shown potential as a real-time, in vivo, diagnostic tool for identifying neoplasia during endoscopy. We present the development of a diagnostic algorithm to classify elastic-scattering spectroscopy (ESS) spectra as either neoplastic or non-neoplastic. The algorithm is based on pattern recognition methods, including ensemble classifiers, in which members of the ensemble are trained on different regions of the ESS spectrum, and misclassification-rejection, where the algorithm identifies and refrains from classifying samples that are at higher risk of being misclassified. These "rejected" samples can be reexamined by simply repositioning the probe to obtain additional optical readings or ultimately by sending the polyp for histopathological assessment, as per standard practice. Prospective validation using separate training and testing sets result in a baseline performance of sensitivity = .83, specificity = .79, using the standard framework of feature extraction (principal component analysis) followed by classification (with linear support vector machines). With the developed algorithm, performance improves to Se ∼ 0.90, Sp ∼ 0.90, at a cost of rejecting 20-33% of the samples. These results are on par with a panel of expert pathologists. For colonoscopic prevention of colorectal cancer, our system could reduce biopsy risk and cost, obviate retrieval of non-neoplastic polyps, decrease procedure time, and improve assessment of cancer risk.

Spectral classifier design with ensemble classifiers and misclassification-rejection: application to elastic-scattering spectroscopy for detection of colonic neoplasia

PubMed Central

Rodriguez-Diaz, Eladio; Castanon, David A.; Singh, Satish K.; Bigio, Irving J.

2011-01-01

Optical spectroscopy has shown potential as a real-time, in vivo, diagnostic tool for identifying neoplasia during endoscopy. We present the development of a diagnostic algorithm to classify elastic-scattering spectroscopy (ESS) spectra as either neoplastic or non-neoplastic. The algorithm is based on pattern recognition methods, including ensemble classifiers, in which members of the ensemble are trained on different regions of the ESS spectrum, and misclassification-rejection, where the algorithm identifies and refrains from classifying samples that are at higher risk of being misclassified. These “rejected” samples can be reexamined by simply repositioning the probe to obtain additional optical readings or ultimately by sending the polyp for histopathological assessment, as per standard practice. Prospective validation using separate training and testing sets result in a baseline performance of sensitivity = .83, specificity = .79, using the standard framework of feature extraction (principal component analysis) followed by classification (with linear support vector machines). With the developed algorithm, performance improves to Se ∼ 0.90, Sp ∼ 0.90, at a cost of rejecting 20–33% of the samples. These results are on par with a panel of expert pathologists. For colonoscopic prevention of colorectal cancer, our system could reduce biopsy risk and cost, obviate retrieval of non-neoplastic polyps, decrease procedure time, and improve assessment of cancer risk. PMID:21721830

Classifying Imbalanced Data Streams via Dynamic Feature Group Weighting with Importance Sampling.

PubMed

Wu, Ke; Edwards, Andrea; Fan, Wei; Gao, Jing; Zhang, Kun

2014-04-01

Data stream classification and imbalanced data learning are two important areas of data mining research. Each has been well studied to date with many interesting algorithms developed. However, only a few approaches reported in literature address the intersection of these two fields due to their complex interplay. In this work, we proposed an importance sampling driven, dynamic feature group weighting framework (DFGW-IS) for classifying data streams of imbalanced distribution. Two components are tightly incorporated into the proposed approach to address the intrinsic characteristics of concept-drifting, imbalanced streaming data. Specifically, the ever-evolving concepts are tackled by a weighted ensemble trained on a set of feature groups with each sub-classifier (i.e. a single classifier or an ensemble) weighed by its discriminative power and stable level. The un-even class distribution, on the other hand, is typically battled by the sub-classifier built in a specific feature group with the underlying distribution rebalanced by the importance sampling technique. We derived the theoretical upper bound for the generalization error of the proposed algorithm. We also studied the empirical performance of our method on a set of benchmark synthetic and real world data, and significant improvement has been achieved over the competing algorithms in terms of standard evaluation metrics and parallel running time. Algorithm implementations and datasets are available upon request.

Visual form-processing deficits: a global clinical classification.

PubMed

Unzueta-Arce, J; García-García, R; Ladera-Fernández, V; Perea-Bartolomé, M V; Mora-Simón, S; Cacho-Gutiérrez, J

2014-10-01

Patients who have difficulties recognising visual form stimuli are usually labelled as having visual agnosia. However, recent studies let us identify different clinical manifestations corresponding to discrete diagnostic entities which reflect a variety of deficits along the continuum of cortical visual processing. We reviewed different clinical cases published in medical literature as well as proposals for classifying deficits in order to provide a global perspective of the subject. Here, we present the main findings on the neuroanatomical basis of visual form processing and discuss the criteria for evaluating processing which may be abnormal. We also include an inclusive diagram of visual form processing deficits which represents the different clinical cases described in the literature. Lastly, we propose a boosted decision tree to serve as a guide in the process of diagnosing such cases. Although the medical community largely agrees on which cortical areas and neuronal circuits are involved in visual processing, future studies making use of new functional neuroimaging techniques will provide more in-depth information. A well-structured and exhaustive assessment of the different stages of visual processing, designed with a global view of the deficit in mind, will give a better idea of the prognosis and serve as a basis for planning personalised psychostimulation and rehabilitation strategies. Copyright © 2011 Sociedad Española de Neurología. Published by Elsevier Espana. All rights reserved.