Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “Feature selection”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 703 records · Page 39Linked to original sources
PubMed2005

The dynamics of visual adaptation to faces.

Several recent demonstrations using visual adaptation have revealed high-level aftereffects for complex patterns including faces. While traditional aftereffects involve perceptual distortion of simple attributes such as orientation or colour that are processed early in the visual cortical hierarchy, face adaptation affects perceived identity and expression, which are thought to be products of higher-order processing. And, unlike most simple aftereffects, those involving faces are robust to changes in scale, position and orientation between the adapting and test stimuli. These differences raise the question of how closely related face aftereffects are to traditional ones. Little is known about the build-up and decay of the face aftereffect, and the similarity of these dynamic processes to traditional aftereffects might provide insight into this relationship. We examined the effect of varying the duration of both the adapting and test stimuli on the magnitude of perceived distortions in face identity. We found that, just as with traditional aftereffects, the identity aftereffect grew logarithmically stronger as a function of adaptation time and exponentially weaker as a function of test duration. Even the subtle aspects of these dynamics, such as the power-law relationship between the adapting and test durations, closely resembled that of other aftereffects. These results were obtained with two different sets of face stimuli that differed greatly in their low-level properties. We postulate that the mechanisms governing these shared dynamics may be dissociable from the responses of feature-selective neurons in the early visual cortex.

Face↗
PubMed2025

Estimating population structure using epigenome-wide methylation data.

INTRODUCTION: In epigenome-wide association analysis (EWAS), unaddressed population stratification often leads to inflation. We aimed to compute methylation population scores (MPSs) that predict genetic principal components (GPCs) using a feature selection and regression approach. METHODS: We used multi-ethnic methylation data (Illumina 450K/EPIC array) from unrelated MESA (n=929), CARDIA (n=1123), JHS (n=1365), ARIC (n=2338), and HCHS/SOL (n=1475) individuals, randomly assigning 85% of participants from each cohort to a training dataset and the remaining 15% to a test dataset. First, we estimated the associations of GPCs with each available CpG methylation site using linear regression within each cohort, adjusting for age, sex, smoking status, race/ethnic background (as a proxy for background information associated with lifestyle and other environmental exposures that may impact methylation), alcohol use status, body mass index, and cell type proportions. We meta-analyzed the associations across cohorts and selected CpG sites with association FDR-adjusted q-value <0.05. We next aggregated individuallevel data across the cohort-specific training datasets, and applied two-stage weighted least squares Lasso regression, with the GPCs as the outcomes and the selected CpG sites as penalized predictors, adjusting for the aforementioned covariates. The developed MPSs are the weighted sum of selected CpG sites from the Lasso. To evaluate the developed MPSs, we constructed them in the test dataset, and compared them with GPCs, and with MPSs constructed based on a previously-published paper. Comparison was based on correlation analysis and data visualization. We demonstrate the use of the MPSs in EWAS. RESULTS: In the test dataset, the MPSs were highly correlated with GPCs, with correlation decreasing, though not monotonically, for later components. Specifically, MPS1 and GPC1 had R2= 0.99, while MPS7 and GPC7 had R2=0.27 (the lowest observed correlation). In data visualization, MPSs had similar patterns as GPCs in differentiating self-reported White, Black, and Hispanic/Latino groups, while outperforming MPC constructed using alternative published methods. MPSs showed comparable performance to GPCs in reducing some of the inflation in EWAS. CONCLUSIONS: Methylation-based population scores provide a reliable estimate of population structure in the data and can complement GPCs when genetic data are absent. Unlike previous methods based on unsupervised methylation PCA, MPSs uses supervised learning with covariate adjustment to capture genetic structure across diverse populations. The weights for each GPCs derived in our study can be applied to generate MPSs in other studies.

Journal Article↗
PubMed2005

Classification of a large microarray data set: algorithm comparison and analysis of drug signatures.

A large gene expression database has been produced that characterizes the gene expression and physiological effects of hundreds of approved and withdrawn drugs, toxicants, and biochemical standards in various organs of live rats. In order to derive useful biological knowledge from this large database, a variety of supervised classification algorithms were compared using a 597-microarray subset of the data. Our studies show that several types of linear classifiers based on Support Vector Machines (SVMs) and Logistic Regression can be used to derive readily interpretable drug signatures with high classification performance. Both methods can be tuned to produce classifiers of drug treatments in the form of short, weighted gene lists which upon analysis reveal that some of the signature genes have a positive contribution (act as "rewards" for the class-of-interest) while others have a negative contribution (act as "penalties") to the classification decision. The combination of reward and penalty genes enhances performance by keeping the number of false positive treatments low. The results of these algorithms are combined with feature selection techniques that further reduce the length of the drug signatures, an important step towards the development of useful diagnostic biomarkers and low-cost assays. Multiple signatures with no genes in common can be generated for the same classification end-point. Comparison of these gene lists identifies biological processes characteristic of a given class.

Algorithms↗
PubMed2026

Knowledge-driven interpretable neural networks provide mechanistic insight.

Analyzing omics data in the context of pathway knowledge is critical for understanding the molecular mechanisms underlying pathological changes. However, current pathway analysis methods do not model the detailed mechanistic nature of biological interactions, limiting the understanding of pathway behavior to a relatively shallow level. To address this issue, we present a knowledge-driven machine learning framework that embeds features into pathway graphs and models reactions analytically, producing interpretable feature hierarchies and subnetworks in which functional associations are estimated to model biological interactions. The approach is agnostic to feature selection, enabling the use of full omics data sets without discarding weak signals. Applications to breast cancer microRNA-gene regulation data and COVID-19 metabolomic data highlight immune and metabolic pathways relevant to disease progression. This framework bridges predictive modeling with mechanistic interpretation and offers a foundation for integrative pathway analysis.

Humans↗
PubMed2005

Coping with cold: the genome of the versatile marine Antarctica bacterium Pseudoalteromonas haloplanktis TAC125.

A considerable fraction of life develops in the sea at temperatures lower than 15 degrees C. Little is known about the adaptive features selected under those conditions. We present the analysis of the genome sequence of the fast growing Antarctica bacterium Pseudoalteromonas haloplanktis TAC125. We find that it copes with the increased solubility of oxygen at low temperature by multiplying dioxygen scavenging while deleting whole pathways producing reactive oxygen species. Dioxygen-consuming lipid desaturases achieve both protection against oxygen and synthesis of lipids making the membrane fluid. A remarkable strategy for avoidance of reactive oxygen species generation is developed by P. haloplanktis, with elimination of the ubiquitous molybdopterin-dependent metabolism. The P. haloplanktis proteome reveals a concerted amino acid usage bias specific to psychrophiles, consistently appearing apt to accommodate asparagine, a residue prone to make proteins age. Adding to its originality, P. haloplanktis further differs from its marine counterparts with recruitment of a plasmid origin of replication for its second chromosome.

Adaptation, Physiological↗
PubMed2002

Computational analysis of crystallization trials.

A system for the automatic categorization of the results of crystallization experiments generated by robotic screening is presented. Images from robotically generated crystallization screens are taken at preset time intervals and analyzed by the computer program Crystal Experiment Evaluation Program (CEEP). This program attempts to automatically categorize the individual crystal experiments into a number of simple classes ranging from clear drop to mountable crystal. The algorithm first selects features from the images via edge detection and texture analysis. Classification is achieved via a self-organizing neural net generated from a set of hand-classified images used as a training set. New images are then classified according to this neural net. It is demonstrated that incorporation of time-series information may enhance the accuracy of classification. Preliminary results from the screening of the proteome of Thermotoga maritima are presented showing the utility of the system.

Algorithms↗
PubMed2001

ECG beat recognition using fuzzy hybrid neural network.

This paper presents the application of the fuzzy neural network for electrocardiographic (ECG) beat recognition and classification. The new classification algorithm of the ECG beats, applying the fuzzy hybrid neural network and the features drawn from the higher order statistics has been proposed in the paper. The cumulants of the second, third, and fourth orders have been used for the feature selection. The hybrid fuzzy neural network applied in the solution consists of the fuzzy self-organizing subnetwork connected in cascade with the multilayer perceptron, working as the final classifier. The c-means and Gustafson-Kessel algorithms for the self-organization of the neural network have been applied. The results of experiments of recognition of different types of beats on the basis of the ECG waveforms have confirmed good efficiency of the proposed solution. The investigations show that the method may find practical application in the recognition and classification of different type heart beats.

Algorithms↗
PubMed1999

Classification of malignant and benign masses based on hybrid ART2LDA approach.

A new type of classifier combining an unsupervised and a supervised model was designed and applied to classification of malignant and benign masses on mammograms. The unsupervised model was based on an adaptive resonance theory (ART2) network which clustered the masses into a number of separate classes. The classes were divided into two types: one containing only malignant masses and the other containing a mix of malignant and benign masses. The masses from the malignant classes were classified by ART2. The masses from the mixed classes were input to a supervised linear discriminant classifier (LDA). In this way, some malignant masses were separated and classified by ART2 and the less distinguishable benign and malignant masses were classified by LDA. For the evaluation of classifier performance, 348 regions of interest (ROI's) containing biopsy proven masses (169 benign and 179 malignant) were used. Ten different partitions of training and test groups were randomly generated using an average of 73% of ROI's for training and 27% for testing. Classifier design, including feature selection and weight optimization, was performed with the training group. The test group was kept independent of the training group. The performance of the hybrid classifier was compared to that of an LDA classifier alone and a backpropagation neural network (BPN). Receiver operating characteristics (ROC) analysis was used to evaluate the accuracy of the classifiers. The average area under the ROC curve (A(z)) for the hybrid classifier was 0.81 as compared to 0.78 for the LDA and 0.80 for the BPN. The partial areas above a true positive fraction of 0.9 were 0.34, 0.27 and 0.31 for the hybrid, the LDA and the BPN classifier, respectively. These results indicate that the hybrid classifier is a promising approach for improving the accuracy of classification in CAD applications.

Biopsy↗
PubMed2005

Identifying simple discriminatory gene vectors with an information theory approach.

In the feature selection of cancer classification problems, many existing methods consider genes individually by choosing the top genes which have the most significant signal-to-noise statistic or correlation coefficient. However the information of the class distinction provided by such genes may overlap intensively, since their gene expression patterns are similar. The redundancy of including many genes with similar gene expression patterns results in highly complex classifiers. According to the principle of Occam's razor, simple models are preferable to complex ones, if they can produce comparable prediction performances to the complex ones. In this paper, we introduce a new method to learn accurate and low-complexity classifiers from gene expression profiles. In our method, we use mutual information to measure the relation between a set of genes, called gene vectors, and the class attribute of the samples. The gene vectors are in higher-dimensional spaces than individual genes, therefore, they are more diverse, or contain more information than individual genes. Hence, gene vectors are more preferable to individual genes in describing the class distinctions between samples since they contain more information about the class attribute. We validate our method on 3 gene expression profiles. By comparing our results with those from literature and other well-known classification methods, our method demonstrated better or comparable prediction performances to the existing methods, however, with lower-complexity models than existing methods.

Algorithms↗
PubMed2003

Two multichannel integrated circuits for neural recording and signal processing.

We have developed, manufactured, and tested two analog CMOS integrated circuit "neurochips" for recording from arrays of densely packed neural electrodes. Device A is a 16-channel buffer consisting of parallel noninverting amplifiers with a gain of 2 V/V. Device B is a 16-channel two-stage analog signal processor with differential amplification and high-pass filtering. It features selectable gains of 250 and 500 V/V as well as reference channel selection. The resulting amplifiers on Device A had a mean gain of 1.99 V/V with an equivalent input noise of 10 microV(rms). Those on Device B had mean gains of 53.4 and 47.4 dB with a high-pass filter pole at 211 Hz and an equivalent input noise of 4.4 microV(rms). Both devices were tested in vivo with electrode arrays implanted in the somatosensory cortex.

Action Potentials↗
PubMed2003

Automated processing of the single-lead electrocardiogram for the detection of obstructive sleep apnoea.

A method for the automatic processing of the electrocardiogram (ECG) for the detection of obstructive apnoea is presented. The method screens nighttime single-lead ECG recordings for the presence of major sleep apnoea and provides a minute-by-minute analysis of disordered breathing. A large independently validated database of 70 ECG recordings acquired from normal subjects and subjects with obstructive and mixed sleep apnoea, each of approximately eight hours in duration, was used throughout the study. Thirty-five of these recordings were used for training and 35 retained for independent testing. A wide variety of features based on heartbeat intervals and an ECG-derived respiratory signal were considered. Classifiers based on linear and quadratic discriminants were compared. Feature selection and regularization of classifier parameters were used to optimize classifier performance. Results show that the normal recordings could be separated from the apnoea recordings with a 100% success rate and a minute-by-minute classification accuracy of over 90% is achievable.

Adult↗
PubMed2004

Toward a direct brain interface based on human subdural recordings and wavelet-packet analysis.

Highly accurate asynchronous detection of movement related patterns in individual electrocorticogram channels has been shown using detection based on either event-related potentials (ERPs) or event-related desynchronization and synchronization (ERD/ERS). A method using wavelet-packet features selected with a genetic algorithm was proposed to simultaneously detect ERP and ERD/ERS and was tested on data from seven subjects and four motor tasks. The proposed wavelet method performed better than previous methods with perfect detection for four subject/task combinations and hit percentages greater than 90% with false positive percentages less than 15% for at least one task for all seven subjects.

Action Potentials↗
PubMed2005

Multichannel fusion models for the parametric classification of differential brain activity.

This paper introduces parametric multichannel fusion models to exploit the different but complementary brain activity information recorded from multiple channels in order to accurately classify differential brain activity into their respective categories. A parametric weighted decision fusion model and two parametric weighted data fusion models are introduced for the classification of averaged multichannel evoked potentials (EPs). The decision fusion model combines the independent decisions of each channel classifier into a decision fusion vector and a parametric classifier is designed to determine the EP class from the discrete decision fusion vector. The data fusion models include the weighted EP-sum model in which the fusion vector is a linear combination of the multichannel EPs and the EP-concatenation model in which the fusion vector is a vector-concatenation of the multichannel EPs. The discrete Karhunen-Loeve transform (DKLT) is used to select features for each channel classifier and from each data fusion vector. The difficulty in estimating the probability density function (PDF) parameters from a small number of averaged EPs is identified and the class conditional PDFs of the feature vectors of averaged EPs are, therefore, derived in terms of the PDFs of the single-trial EPs. Multivariate parametric classifiers are developed for each fusion strategy and the performances of the different strategies are compared by classifying 14-channel EPs collected from five subjects involved in making explicit match/mismatch comparisons between sequentially presented stimuli. It is shown that the performance improves by incorporating weights in the fusion rules and that the best performance is obtained using multichannel EP concatenation. It is also noted that the fusion strategies introduced are also applicable to other problems involving the classification of multicategory multivariate signals generated from multiple sources.

Action Potentials↗
PubMed2004

Automatic detection and recognition of signs from natural scenes.

In this paper, we present an approach to automatic detection and recognition of signs from natural scenes, and its application to a sign translation task. The proposed approach embeds multiresolution and multiscale edge detection, adaptive searching, color analysis, and affine rectification in a hierarchical framework for sign detection, with different emphases at each phase to handle the text in different sizes, orientations, color distributions and backgrounds. We use affine rectification to recover deformation of the text regions caused by an inappropriate camera view angle. The procedure can significantly improve text detection rate and optical character recognition (OCR) accuracy. Instead of using binary information for OCR, we extract features from an intensity image directly. We propose a local intensity normalization method to effectively handle lighting variations, followed by a Gabor transform to obtain local features, and finally a linear discriminant analysis (LDA) method for feature selection. We have applied the approach in developing a Chinese sign translation system, which can automatically detect and recognize Chinese signs as input from a camera, and translate the recognized text into English.

Algorithms↗
PubMed2004

Gradient-based multiresolution image fusion.

A novel approach to multiresolution signal-level image fusion is presented for accurately transferring visual information from any number of input image signals, into a single fused image without loss of information or the introduction of distortion. The proposed system uses a "fuse-then-decompose" technique realized through a novel, fusion/decomposition system architecture. In particular, information fusion is performed on a multiresolution gradient map representation domain of image signal information. At each resolution, input images are represented as gradient maps and combined to produce new, fused gradient maps. Fused gradient map signals are processed, using gradient filters derived from high-pass quadrature mirror filters to yield a fused multiresolution pyramid representation. The fused output image is obtained by applying, on the fused pyramid, a reconstruction process that is analogous to that of conventional discrete wavelet transform. This new gradient fusion significantly reduces the amount of distortion artefacts and the loss of contrast information usually observed in fused images obtained from conventional multiresolution fusion schemes. This is because fusion in the gradient map domain significantly improves the reliability of the feature selection and information fusion processes. Fusion performance is evaluated through informal visual inspection and subjective psychometric preference tests, as well as objective fusion performance measurements. Results clearly demonstrate the superiority of this new approach when compared to conventional fusion systems.

Algorithms↗
PubMed2004

Concept-oriented indexing of video databases: toward semantic sensitive retrieval and browsing.

Digital video now plays an important role in medical education, health care, telemedicine and other medical applications. Several content-based video retrieval (CBVR) systems have been proposed in the past, but they still suffer from the following challenging problems: semantic gap, semantic video concept modeling, semantic video classification, and concept-oriented video database indexing and access. In this paper, we propose a novel framework to make some advances toward the final goal to solve these problems. Specifically, the framework includes: 1) a semantic-sensitive video content representation framework by using principal video shots to enhance the quality of features; 2) semantic video concept interpretation by using flexible mixture model to bridge the semantic gap; 3) a novel semantic video-classifier training framework by integrating feature selection, parameter estimation, and model selection seamlessly in a single algorithm; and 4) a concept-oriented video database organization technique through a certain domain-dependent concept hierarchy to enable semantic-sensitive video retrieval and browsing.

Abstracting and Indexing↗
PubMed2006

Training cellular automata for image processing.

Experiments were carried out to investigate the possibility of training cellular automata (CA) to perform several image processing tasks. Even if only binary images are considered, the space of all possible rule sets is still very large, and so the training process is the main bottleneck of such an approach. In this paper, the sequential floating forward search method for feature selection was used to select good rule sets for a range of tasks, namely noise filtering (also applied to grayscale images using threshold decomposition), thinning, and convex hulls. Various objective functions for driving the search were considered. Several modifications to the standard CA formulation were made (the B-rule and two-cycle CAs), which were found, in some cases, to improve performance.

Algorithms↗
PubMed2006

Information mining over heterogeneous and high-dimensional time-series data in clinical trials databases.

An effective analysis of clinical trials data involves analyzing different types of data such as heterogeneous and high dimensional time series data. The current time series analysis methods generally assume that the series at hand have sufficient length to apply statistical techniques to them. Other ideal case assumptions are that data are collected in equal length intervals, and while comparing time series, the lengths are usually expected to be equal to each other. However, these assumptions are not valid for many real data sets, especially for the clinical trials data sets. An addition, the data sources are different from each other, the data are heterogeneous, and the sensitivity of the experiments varies by the source. Approaches for mining time series data need to be revisited, keeping the wide range of requirements in mind. In this paper, we propose a novel approach for information mining that involves two major steps: applying a data mining algorithm over homogeneous subsets of data, and identifying common or distinct patterns over the information gathered in the first step. Our approach is implemented specifically for heterogeneous and high dimensional time series clinical trials data. Using this framework, we propose a new way of utilizing frequent itemset mining, as well as clustering and declustering techniques with novel distance metrics for measuring similarity between time series data. By clustering the data, we find groups of analytes (substances in blood) that are most strongly correlated. Most of these relationships already known are verified by the clinical panels, and, in addition, we identify novel groups that need further biomedical analysis. A slight modification to our algorithm results an effective declustering of high dimensional time series data, which is then used for "feature selection." Using industry-sponsored clinical trials data sets, we are able to identify a small set of analytes that effectively models the state of normal health.

Algorithms↗