Search

Motivation: Discriminant analysis is an effective tool for the classification of experimental units into groups. Here, we consider the typical problem of classifying subjects according to phenotypes via gene expression data and propose a method that incorporates variable selection into the inferential procedure, for the identification of the important biomarkers. To achieve this goal, we build upon a conjugate normal discriminant model, both linear and quadratic, and include a stochastic search variable selection procedure via an MCMC algorithm. Furthermore, we incorporate into the model prior information on the relationships among the genes as described by a gene–gene network. We use a Markov random field (MRF) prior to map the network connections among genes. Our prior model assumes that neighboring genes in the network are more likely to have a joint effect on the relevant biological processes. Results: We use simulated data to assess performances of our method. In particular, we compare the MRF prior to a situation where independent Bernoulli priors are chosen for the individual predictors. We also illustrate the method on benchmark datasets for gene expression. Our simulation studies show that employing the MRF prior improves on selection accuracy. In real data applications, in addition to identifying markers and improving prediction accuracy, we show how the integration of existing biological knowledge into the prior model results in an increased ability to identify genes with strong discriminatory power and also aids the interpretation of the results. Contact: marina@rice.edu

Objectives: The aim of this study was to improve naive Bayes prediction of Medical Subject Headings (MeSH) assignment to documents using optimal training sets found by an active learning inspired method. Design: The authors selected 20 MeSH terms whose occurrences cover a range of frequencies. For each MeSH term, they found an optimal training set, a subset of the whole training set. An optimal training set consists of all documents including a given MeSH term (C1 class) and those documents not including a given MeSH term (C1 class) that are closest to the C1 class. These small sets were used to predict MeSH assignments in the MEDLINE ® database. Measurements: Average precision was used to compare MeSH assignment using the naive Bayes learner trained on the whole training set, optimal sets, and random sets. The authors compared 95% lower confidence limits of average precisions of naive Bayes with upper bounds for average precisions of a K-nearest neighbor (KNN) classifier. Results: For all 20 MeSH assignments, the optimal training sets produced nearly 200% improvement over use of the whole training sets. In 17 of those MeSH assignments, naive Bayes using optimal training sets was statistically better than a KNN. In 15 of those, optimal training sets performed better than optimized feature selection. Overall naive Bayes averaged 14% better than a KNN for all 20 MeSH assignments. Using these optimal sets with another classifier, C-modified least squares (CMLS), produced an additional 6% improvement over naive Bayes. Conclusion: Using a smaller optimal training set greatly improved learning with naive Bayes. The performance is superior to a KNN. The small training set can be used with other sophisticated learning methods, such as CMLS, where using the whole training set would not be feasible.

Gene expression profiles can be utilized in the diagnosis of critical diseases such as cancer. The selection of biomarker genes from these profiles is significant and crucial for cancer detection. This paper presents a framework proposing a two-stage multifilter hybrid model of feature selection for colon cancer classification. Colon cancer is being extremely common nowadays among other types of cancer. There is a need to find fast and an accurate method to detect the tissues, and enhance the diagnostic process and the drug discovery. This paper reports on a study whose objective has been to improve the diagnosis of cancer of the colon through a two-stage, multifilter model of feature selection. The model described deals with feature selection using a combination of Information Gain and a Genetic Algorithm. The next stage is to filter and rank the genes identified through this method using the minimum Redundancy Maximum Relevance (mRMR) technique. The final phase is to further analyze the data using correlated machine learning algorithms. This two-stage approach, which involves the selection of genes before classification techniques are used, improves success rates for the identification of cancer cells. It is found that Decision Tree, K-Nearest Neighbor, and Naïve Bayes classifiers had showed promising accurate results using the developed hybrid framework model. It is concluded that the performance of our proposed method has achieved a higher accuracy in comparison with the existing methods reported in the literatures. This study can be used as a clue to enhance treatment and drug discovery for the colon cancer cure.

Stock price prediction is a challenging task, but machine learning methods have recently been used successfully for this purpose. In this paper, we extract over 270 hand-crafted features (factors) inspired by technical and quantitative analysis and tested their validity on short-term mid-price movement prediction. We focus on a wrapper feature selection method using entropy, least-mean squares, and linear discriminant analysis. We also build a quantitative feature based on adaptive logistic regression for online learning, which is constantly selected first among the majority of the proposed feature selection methods. This study examines the best combination of features using high frequency limit order book data from Nasdaq Nordic. Our results suggest that sorting methods and classifiers can be used in such a way that one can reach the best performance with a combination of only very few informative features. This paper opens avenues for developing more advanced features combined with more sophisticated feature selection methods. It also provides helpful insight to market makers and traders in general by providing useful results that can be used to gain an information edge in trading.

Background: Over time, methods for the development of clinical decision support (CDS) systems have evolved from interpretable and easy-to-use scoring systems to very complex and non-interpretable mathematical models. In order to accomplish effective decision support, CDS systems should provide information on how the model arrives at a certain decision. To address the issue of incompatibility between performance, interpretability and applicability of CDS systems, this paper proposes an innovative model structure, automatically leading to interpretable and easily applicable models. The resulting models can be used to guide clinicians when deciding upon the appropriate treatment, estimating patient-specific risks and to improve communication with patients. Methods and Findings: We propose the interval coded scoring (ICS) system, which imposes that the effect of each variable on the estimated risk is constant within consecutive intervals. The number and position of the intervals are automatically obtained by solving an optimization problem, which additionally performs variable selection. The resulting model can be visualised by means of appealing scoring tables and color bars. ICS models can be used within software packages, in smartphone applications, or on paper, which is particularly useful for bedside medicine and home-monitoring. The ICS approach is illustrated on two gynecological problems: diagnosis of malignancy of ovarian tumors using a dataset containing 3,511 patients, and prediction of first trimester viability of pregnancies using a dataset of 1,435 women. Comparison of the performance of the ICS approach with a range of prediction models proposed in the literature illustrates the ability of ICS to combine optimal performance with the interpretability of simple scoring systems. Conclusions: The ICS approach can improve patient-clinician communication and will provide additional insights in the importance and influence of available variables. Future challenges include extensions of the proposed methodology towards automated detection of interaction effects, multi-class decision support systems, prognosis and high-dimensional data.

The dimensionality of the spatially distributed channels and the temporal resolution of electroencephalogram (EEG) based brain-computer interfaces (BCI) undermine emotion recognition models. Thus, prior to modeling such data, as the final stage of the learning pipeline, adequate preprocessing, transforming, and extracting temporal (i.e., time-series signals) and spatial (i.e., electrode channels) features are essential phases to recognize underlying human emotions. Conventionally, inter-subject variations are dealt with by avoiding the sources of variation (e.g., outliers) or turning the problem into a subject-deponent. We address this issue by preserving and learning from individual particularities in response to affective stimuli. This paper investigates and proposes a subject-independent emotion recognition framework that mitigates the subject-to-subject variability in such systems. Using an unsupervised feature selection algorithm, we reduce the feature space that is extracted from time-series signals. For the spatial features, we propose a subject-specific unsupervised learning algorithm that learns from inter-channel co-activation online. We tested this framework on real EEG benchmarks, namely DEAP, MAHNOB-HCI, and DREAMER. We train and test the selection outcomes using nested cross-validation and a support vector machine (SVM). We compared our results with the state-of-the-art subject-independent algorithms. Our results show an enhanced performance by accurately classifying human affection (i.e., based on valence and arousal) by 16%–27% compared to other studies. This work not only outperforms other subject-independent studies reported in the literature but also proposes an online analysis solution to affection recognition.

The volume of Amharic digital documents has grown rapidly in recent years. As a result, automatic document categorization is highly essential. In this paper, we present a novel dimension reduction approach for improving classification accuracy by combining feature selection and feature extraction. The new dimension reduction method utilizes Information Gain (IG), Chi-square test (CHI), and Document Frequency (DF) to select important features and Principal Component Analysis (PCA) to refine the features that have been selected. We evaluate the proposed dimension reduction method with a dataset containing 9 news categories. Our experimental results verified that the proposed dimension reduction method outperforms other methods. Classification accuracy with the new dimension reduction is 92.60%, which is 13.48%, 16.51% and 10.19% higher than with IG, CHI, and DF respectively. Further work is required since classification accuracy still decreases as we reduce the feature size to save computational time.

Online shopping behavior has the characteristics of rich granularity dimension and data sparsity and presents a challenging task in e-commerce. Previous studies on user behavior prediction did not seriously discuss feature selection and ensemble design, which are important to improving the performance of machine learning algorithms. In this paper, we proposed an SE-stacking model based on information fusion and ensemble learning for user purchase behavior prediction. After successfully using the ensemble feature selection method to screen purchase-related factors, we used the stacking algorithm for user purchase behavior prediction. In our efforts to avoid the deviation of the prediction results, we optimized the model by selecting ten different types of models as base learners and modifying the relevant parameters specifically for them. Experiments conducted on a publicly available dataset show that the SE-stacking model can achieve a 98.40% F1 score, approximately 0.09% higher than the optimal base models. The SE-stacking model not only has a good application in the prediction of user purchase behavior but also has practical value when combined with the actual e-commerce scene. At the same time, this model has important significance in academic research and the development of this field.

The use of image covariates to build a classification model has lots of impact in various fields, such as computer science, medicine, and so on. The aim of this paper is to develop an estimation method for logistic regression model with image covariates. We propose a novel regularized estimation approach, where the regularization is a combination of L1 regularization and Sobolev norm regularization. The L1 penalty can perform variable selection, while the Sobolev norm penalty can capture the shape edges information of image data. We develop an efficient algorithm for the optimization problem. We also establish a nonasymptotic error bound on parameter estimation. Simulated studies and a real data application demonstrate that our proposed method performs very well.

Tracking the origin of propagating wave signals in an environment with complex reflective surfaces is, in its full generality, a nearly intractable problem which has engendered multiple domain-specific literatures. We posit that, if the environment and sensor geometries are fixed, machine learning algorithms can "learn" the acoustical geometry of the environment and accurately track signal origin. In this paper, we propose the first machine-learning-based approach to identifying the source locations of semi-stationary, tonal, dolphin-whistle-like sounds in a highly reverberant space, specifically a half-cylindrical dolphin pool. Our algorithm works by supplying a learning network with an overabundance of location "clues", which are then selected under supervised training for their ability to discriminate source location in this particular environment. More specifically, we deliver estimated time-difference-of-arrivals (TDOA's) and normalized cross-correlation values computed from pairs of hydrophone signals to a random forest model for high-feature-volume classification and feature selection, and subsequently deliver the selected features into linear discriminant analysis, linear and quadratic Support Vector Machine (SVM), and Gaussian process models. Based on data from 14 sound source locations and 16 hydrophones, our classification models yielded perfect accuracy at predicting novel sound source locations. Our regression models yielded better accuracy than the established Steered-Response Power (SRP) method when all training data were used, and comparable accuracy along the pool surface when deprived of training data at testing sites; our methods additionally boast improved computation time and the potential for superior localization accuracy in all dimensions with more training data. Because of the generality of our method we argue it may be useful in a much wider variety of contexts.

Dengue and influenza-like illness (ILI) are two of the leading causes of viral infection in the world and it is estimated that more than half the world’s population is at risk for developing these infections. It is therefore important to develop accurate methods for forecasting dengue and ILI incidences. Since data from multiple sources (such as dengue and ILI case counts, electronic health records and frequency of multiple internet search terms from Google Trends) can improve forecasts, standard time series analysis methods are inadequate to estimate all the parameter values from the limited amount of data available if we use multiple sources. In this paper, we use a computationally efficient implementation of the known variable selection method that we call the Autoregressive Likelihood Ratio (ARLR) method. This method combines sparse representation of time series data, electronic health records data (for ILI) and Google Trends data to forecast dengue and ILI incidences. This sparse representation method uses an algorithm that maximizes an appropriate likelihood ratio at every step. Using numerical experiments, we demonstrate that our method recovers the underlying sparse model much more accurately than the lasso method. We apply our method to dengue case count data from five countries/states: Brazil, Mexico, Singapore, Taiwan, and Thailand and to ILI case count data from the United States. Numerical experiments show that our method outperforms existing time series forecasting methods in forecasting the dengue and ILI case counts. In particular, our method gives a 18 percent forecast error reduction over a leading method that also uses data from multiple sources. It also performs better than other methods in predicting the peak value of the case count and the peak time., Author summary Dengue and influenza-like illness (ILI) are leading causes of viral infection in the world and hence it is important to develop accurate methods for forecasting their incidence. We use Autoregressive Likelihood Ratio method, which is a computationally efficient implementation of the variable selection method, in order to obtain a sparse (non-lasso) representation of time series, Google Trends and electronic health records (for ILI) data. This method is used to forecast dengue incidence in five countries/states and ILI incidence in USA. We show that this method outperforms existing time series methods in forecasting these diseases. The method is general and can also be used to forecast other diseases.

Progression of systemic scleroderma (SSc), a chronic connective tissue disease that causes a fibrotic phenotype, is highly heterogeneous amongst patients and difficult to accurately diagnose. To meet this clinical need, we developed a novel three-layer classification model, which analyses gene expression profiles from SSc skin biopsies to diagnose SSc severity. Two SSc skin biopsy microarray datasets were obtained from Gene Expression Omnibus. The skin scores obtained from the original papers were used to further categorize the data into subgroups of low (

A major issue of machinery fault diagnosis using vibration signals is that it is over-reliant on personnel knowledge and experience in interpreting the signal. Thus, machine learning has been adapted for machinery fault diagnosis. The quantity and quality of the input features, however, influence the fault classification performance. Feature selection plays a vital role in selecting the most representative feature subset for the machine learning algorithm. In contrast, the trade-off relationship between capability when selecting the best feature subset and computational effort is inevitable in the wrapper-based feature selection (WFS) method. This paper proposes an improved WFS technique before integration with a support vector machine (SVM) model classifier as a complete fault diagnosis system for a rolling element bearing case study. The bearing vibration dataset made available by the Case Western Reserve University Bearing Data Centre was executed using the proposed WFS and its performance has been analysed and discussed. The results reveal that the proposed WFS secures the best feature subset with a lower computational effort by eliminating the redundancy of re-evaluation. The proposed WFS has therefore been found to be capable and efficient to carry out feature selection tasks.

Classification models built on biological expression data are increasingly used to predict distinct disease subtypes. Selected features that separate sample groups can be the candidates of biomarkers, helping us to discover biological functions/pathways. However, three challenges are associated with building a robust classification and feature selection model: 1) the number of significant biomarkers is much smaller than that of measured features for which the search will be exhaustive; 2) current biological expression data are big in both sample size and feature size which will worsen the scalability of any search algorithms; and 3) expression profiles of certain features are typically highly correlated which may prevent to distinguish the predominant features. Unfortunately, most of the existing algorithms are partially addressing part of these challenges but not as a whole. In this paper, we propose a unified framework to address the above challenges. The classification and feature selection problem is first formulated as a nonconvex optimisation problem. Then the problem is relaxed and solved iteratively by a sequence of convex optimisation procedures which can be distributed computed and therefore allows the efficient implementation on advanced infrastructures. To illustrate the competence of our method over others, we first analyse a randomly generated simulation dataset under various conditions. We then analyse a real gene expression dataset on embryonal tumour. Further downstream analysis, such as functional annotation and pathway analysis, are performed on the selected features which elucidate several biological findings.

Studies of structural plasticity in the brain often require the detection and analysis of axonal synapses (boutons). To date, bouton detection has been largely manual or semi-automated, relying on a step that traces the axons before detection the boutons. If tracing the axon fails, the accuracy of bouton detection is compromised. In this paper, we propose a new algorithm that does not require tracing the axon to detect axonal boutons in 3D two-photon images taken from the mouse cortex. To find the most appropriate techniques for this task, we compared several well-known algorithms for interest point detection and feature descriptor generation. The final algorithm proposed has the following main steps: (1) a Laplacian of Gaussian (LoG) based feature enhancement module to accentuate the appearance of boutons; (2) a Speeded Up Robust Features (SURF) interest point detector to find candidate locations for feature extraction; (3) non-maximum suppression to eliminate candidates that were detected more than once in the same local region; (4) generation of feature descriptors based on Gabor filters; (5) a Support Vector Machine (SVM) classifier, trained on features from labelled data, and was used to distinguish between bouton and non-bouton candidates. We found that our method achieved a Recall of 95%, Precision of 76%, and F1 score of 84% within a new dataset that we make available for accessing bouton detection. On average, Recall and F1 score were significantly better than the current state-of-the-art method, while Precision was not significantly different. In conclusion, in this article we demonstrate that our approach, which is independent of axon tracing, can detect boutons to a high level of accuracy, and improves on the detection performance of existing approaches. The data and code (with an easy to use GUI) used in this article are available from open source repositories.

This paper proposes a new support vector machine (SVM) optimization scheme based on an improved chaotic fly optimization algorithm (FOA) with a mutation strategy to simultaneously perform parameter setting turning for the SVM and feature selection. In the improved FOA, the chaotic particle initializes the fruit fly swarm location and replaces the expression of distance for the fruit fly to find the food source. However, the proposed mutation strategy uses two distinct generative mechanisms for new food sources at the osphresis phase, allowing the algorithm procedure to search for the optimal solution in both the whole solution space and within the local solution space containing the fruit fly swarm location. In an evaluation based on a group of ten benchmark problems, the proposed algorithm's performance is compared with that of other well-known algorithms, and the results support the superiority of the proposed algorithm. Moreover, this algorithm is successfully applied in a SVM to perform both parameter setting turning for the SVM and feature selection to solve real-world classification problems. This method is called chaotic fruit fly optimization algorithm (CIFOA)-SVM and has been shown to be a more robust and effective optimization method than other well-known methods, particularly in terms of solving the medical diagnosis problem and the credit card problem.

Breast cancer is an all too common disease in women, making how to effectively predict it an active research problem. A number of statistical and machine learning techniques have been employed to develop various breast cancer prediction models. Among them, support vector machines (SVM) have been shown to outperform many related techniques. To construct the SVM classifier, it is first necessary to decide the kernel function, and different kernel functions can result in different prediction performance. However, there have been very few studies focused on examining the prediction performances of SVM based on different kernel functions. Moreover, it is unknown whether SVM classifier ensembles which have been proposed to improve the performance of single classifiers can outperform single SVM classifiers in terms of breast cancer prediction. Therefore, the aim of this paper is to fully assess the prediction performance of SVM and SVM ensembles over small and large scale breast cancer datasets. The classification accuracy, ROC, F-measure, and computational times of training SVM and SVM ensembles are compared. The experimental results show that linear kernel based SVM ensembles based on the bagging method and RBF kernel based SVM ensembles with the boosting method can be the better choices for a small scale dataset, where feature selection should be performed in the data pre-processing stage. For a large scale dataset, RBF kernel based SVM ensembles based on boosting perform better than the other classifiers.

Feature selection is a practical approach for improving the performance of text classification methods by optimizing the feature subsets input to classifiers. In traditional feature selection methods such as information gain and chi-square, the number of documents that contain a particular term (i.e. the document frequency) is often used. However, the frequency of a given term appearing in each document has not been fully investigated, even though it is a promising feature to produce accurate classifications. In this paper, we propose a new feature selection scheme based on a term event Multinomial naive Bayes probabilistic model. According to the model assumptions, the matching score function, which is based on the prediction probability ratio, can be factorized. Finally, we derive a feature selection measurement for each term after replacing inner parameters by their estimators. On a benchmark English text datasets (20 Newsgroups) and a Chinese text dataset (MPH-20), our numerical experiment results obtained from using two widely used text classifiers (naive Bayes and support vector machine) demonstrate that our method outperformed the representative feature selection methods.

Proteomic analysis of cancers' stages has provided new opportunities for the development of novel, highly sensitive diagnostic tools which helps early detection of cancer. This paper introduces a new feature ranking approach called FRMT. FRMT is based on the Technique for Order of Preference by Similarity to Ideal Solution method (TOPSIS) which select the most discriminative proteins from proteomics data for cancer staging. In this approach, outcomes of 10 feature selection techniques were combined by TOPSIS method, to select the final discriminative proteins from seven different proteomic databases of protein expression profiles. In the proposed workflow, feature selection methods and protein expressions have been considered as criteria and alternatives in TOPSIS, respectively. The proposed method is tested on seven various classifier models in a 10-fold cross validation procedure that repeated 30 times on the seven cancer datasets. The obtained results proved the higher stability and superior classification performance of method in comparison with other methods, and it is less sensitive to the applied classifier. Moreover, the final introduced proteins are informative and have the potential for application in the real medical practice.

Feature selection plays a critical role in text categorization. During feature selecting, high-frequency terms and the interclass and intraclass relative contributions of terms all have significant effects on classification results. So we put forward a feature selection approach, IIRCT, based on interclass and intraclass relative contributions of terms in the paper. In our proposed algorithm, three critical factors, which are term frequency and the interclass relative contribution and the intraclass relative contribution of terms, are all considered synthetically. Finally, experiments are made with the help of kNN classifier. And the corresponding results on 20 NewsGroup and SougouCS corpora show that IIRCT algorithm achieves better performance than DF,t-Test, and CMFS algorithms.

Hundreds of millions of figures are available in biomedical literature, representing important biomedical experimental evidence. This ever-increasing sheer volume has made it difficult for scientists to effectively and accurately access figures of their interest, the process of which is crucial for validating research facts and for formulating or testing novel research hypotheses. Current figure search applications can't fully meet this challenge as the “bag of figures” assumption doesn't take into account the relationship among figures. In our previous study, hundreds of biomedical researchers have annotated articles in which they serve as corresponding authors. They ranked each figure in their paper based on a figure's importance at their discretion, referred to as “figure ranking”. Using this collection of annotated data, we investigated computational approaches to automatically rank figures. We exploited and extended the state-of-the-art listwise learning-to-rank algorithms and developed a new supervised-learning model BioFigRank. The cross-validation results show that BioFigRank yielded the best performance compared with other state-of-the-art computational models, and the greedy feature selection can further boost the ranking performance significantly. Furthermore, we carry out the evaluation by comparing BioFigRank with three-level competitive domain-specific human experts: (1) First Author, (2) Non-Author-In-Domain-Expert who is not the author nor co-author of an article but who works in the same field of the corresponding author of the article, and (3) Non-Author-Out-Domain-Expert who is not the author nor co-author of an article and who may or may not work in the same field of the corresponding author of an article. Our results show that BioFigRank outperforms Non-Author-Out-Domain-Expert and performs as well as Non-Author-In-Domain-Expert. Although BioFigRank underperforms First Author, since most biomedical researchers are either in- or out-domain-experts for an article, we conclude that BioFigRank represents an artificial intelligence system that offers expert-level intelligence to help biomedical researchers to navigate increasingly proliferated big data efficiently.

MicroRNAs are key regulators of eukaryotic gene expression whose fundamental role has already been identified in many cell pathways. The correct identification of miRNAs targets is still a major challenge in bioinformatics and has motivated the development of several computational methods to overcome inherent limitations of experimental analysis. Indeed, the best results reported so far in terms of specificity and sensitivity are associated to machine learning-based methods for microRNA-target prediction. Following this trend, in the current paper we discuss and explore a microRNA-target prediction method based on a random forest classifier, namely RFMirTarget. Despite its well-known robustness regarding general classifying tasks, to the best of our knowledge, random forest have not been deeply explored for the specific context of predicting microRNAs targets. Our framework first analyzes alignments between candidate microRNA-target pairs and extracts a set of structural, thermodynamics, alignment, seed and position-based features, upon which classification is performed. Experiments have shown that RFMirTarget outperforms several well-known classifiers with statistical significance, and that its performance is not impaired by the class imbalance problem or features correlation. Moreover, comparing it against other algorithms for microRNA target prediction using independent test data sets from TarBase and starBase, we observe a very promising performance, with higher sensitivity in relation to other methods. Finally, tests performed with RFMirTarget show the benefits of feature selection even for a classifier with embedded feature importance analysis, and the consistency between relevant features identified and important biological properties for effective microRNA-target gene alignment.

Feature subset selection has become more and more a common topic of research. This popularity is partly due to the growth in the number of features and application domains. The family of algorithms known as plus-l-minus-r and its immediate derivatives (like forward selection) are very popular and often the only viable alternative when used in wrapper mode. In consequence, it is of the greatest importance to take the most of every evaluation of the inducer, which is normally the more costly part. In this paper, a technique is proposed that takes into account the inducer evaluation both in the current subset and in the remainder subset (its complementary set) and is applicable to any sequential subset selection algorithm at a reasonable overhead in cost. Its feasibility is demonstrated on a series of benchmark data sets.