Cross-participant modelling based on joint or disjoint feature selection: an fMRI conceptual decoding study

Multivariate classification techniques have proven to be powerful tools for distinguishing experimental conditions in single sessions of functional magnetic resonance imaging (fMRI) data. But they are vulnerable to a considerable penalty in classification accuracy when applied across sessions or participants, calling into question the degree to which fine-grained encodings are shared across subjects. Here, we introduce joint learning techniques, where feature selection is carried out using a held-out subset of a target dataset, before training a linear classifier on a source dataset. Single trials of functional MRI data from a covert property generation task are classified with regularized regression techniques to predict the semantic class of stimuli. With our selection techniques (joint ranking feature selection (JRFS) and disjoint feature selection (DJFS)), classification performance during cross-session prediction improved greatly, relative to feature selection on the source session data only. Compared with JRFS, DJFS showed significant improvements for cross-participant classification. And when using a groupwise training, DJFS approached the accuracies seen for prediction across different sessions from the same participant. Comparing several feature selection strategies, we found that a simple univariate ANOVA selection technique or a minimal searchlight (one voxel in size) is appropriate, compared with larger searchlights.

Integrative analysis of chemo-transcriptomic profiles for drug-feature specific gene expression signatures

One of the major challenges in systems biology is to understand the complex responses of a biological system to external perturbations or internal signalling depending on its biological conditions. Genome-wide transcriptomic profiling of cellular systems under various chemical perturbations allows the manifestation of certain features of the chemicals through their transcriptomic expression profiles. The insights obtained may help to establish the connections between human diseases, associated genes and therapeutic drugs. The main objective of this study was to systematically analyse cellular gene expression data under various drug treatments to elucidate drug-feature specific transcriptomic signatures. We first extracted drug-related information (drug features) from the collected textual description of DrugBank entries using text-mining techniques. A novel statistical method employing orthogonal least square learning was proposed to obtain drug-feature-specific signatures by integrating gene expression with DrugBank data. To obtain robust signatures from noisy input datasets, a stringent ensemble approach was applied with the combination of three techniques: resampling, leave-one-out cross validation, and aggregation. The validation experiments showed that the proposed method has the capacity of extracting biologically meaningful drug-feature-specific gene expression signatures. It was also shown that most of signature genes are connected with common hub genes by regulatory network analysis. The common hub genes were further shown to be related to general drug metabolism by Gene Ontology analysis. Each set of genes has relatively few interactions with other sets, indicating the modular nature of each signature and its drug-feature-specificity. Based on Gene Ontology analysis, we also found that each set of drug feature (DF)-specific genes were indeed enriched in biological processes related to the drug feature. The results of these experiments demonstrated the pot- ntial of the method for predicting certain features of new drugs using their transcriptomic profiles, providing a useful methodological framework and a valuable resource for drug development and characterization.

Supervised Aggregative Feature Extraction for Big Data Time Series Regression

In many applications, and especially those where batch processes are involved, a target scalar output of interest is often dependent on one or more time series of data. With the exponential growth in data logging in modern industries such time series are increasingly available for statistical modeling in soft sensing applications. In order to exploit time series data for predictive modelling, it is necessary to summarise the information they contain as a set of features to use as model regressors. Typically this is done in an unsupervised fashion using simple techniques such as computing statistical moments, principal components or wavelet decompositions, often leading to significant information loss and hence suboptimal predictive models. In this paper, a functional learning paradigm is exploited in a supervised fashion to derive continuous, smooth estimates of time series data (yielding aggregated local information), while simultaneously estimating a continuous shape function yielding optimal predictions. The proposed Supervised Aggregative Feature Extraction (SAFE) methodology can be extended to support nonlinear predictive models by embedding the functional learning framework in a Reproducing Kernel Hilbert Spaces setting. SAFE has a number of attractive features including closed form solution and the ability to explicitly incorporate first and second order derivative information. Using simulation studies and a practical semiconductor manufacturing case study we highlight the strengths of the new methodology with respect to standard unsupervised feature extraction approaches.

Investigation into DCT Feature Selection for Visual Lip-Based Biometric Authentication

This paper investigated using lip movements as a behavioural biometric for person authentication. The system was trained, evaluated and tested using the XM2VTS dataset, following the Lausanne Protocol configuration II. Features were selected from the DCT coefficients of the greyscale lip image. This paper investigated the number of DCT coefficients selected, the selection process, and static and dynamic feature combinations. Using a Gaussian Mixture Model - Universal Background Model framework an Equal Error Rate of 2.20% was achieved during evaluation and on an unseen test set a False Acceptance Rate of 1.7% and False Rejection Rate of 3.0% was achieved. This compares favourably with face authentication results on the same dataset whilst not being susceptible to spoofing attacks.

k-fold Subsampling based Sequential Backward Feature Elimination

We present a new wrapper feature selection algorithm for human detection. This algorithm is a hybrid featureselection approach combining the benefits of filter and wrapper methods. It allows the selection of an optimalfeature vector that well represents the shapes of the subjects in the images. In detail, the proposed featureselection algorithm adopts the k-fold subsampling and sequential backward elimination approach, while thestandard linear support vector machine (SVM) is used as the classifier for human detection. We apply theproposed algorithm to the publicly accessible INRIA and ETH pedestrian full image datasets with the PASCALVOC evaluation criteria. Compared to other state of the arts algorithms, our feature selection based approachcan improve the detection speed of the SVM classifier by over 50% with up to 2% better detection accuracy.Our algorithm also outperforms the equivalent systems introduced in the deformable part model approach witharound 9% improvement in the detection accuracy

Language Experience Affects Grouping of Musical Instrument Sounds

Language experience clearly affects the perception of speech, but little is known about whether these differences in perception extend to non-speech sounds. In this study, we investigated rhythmic perception of non-linguistic sounds in speakers of French and German using a grouping task, in which complexity (variability in sounds, presence of pauses) was manipulated. In this task, participants grouped sequences of auditory chimeras formed from musical instruments. These chimeras mimic the complexity of speech without being speech. We found that, while showing the same overall grouping preferences, the German speakers showed stronger biases than the French speakers in grouping complex sequences. Sound variability reduced all participants' biases, resulting in the French group showing no grouping preference for the most variable sequences, though this reduction was attenuated by musical experience. In sum, this study demonstrates that linguistic experience, musical experience, and complexity affect rhythmic grouping of non-linguistic sounds and suggests that experience with acoustic cues in a meaningful context (language or music) is necessary for developing a robust grouping preference that survives acoustic variability.