Decoding visual stimuli using classifier ensembles with optimized feature selection

Decoding perceptual or cognitive states based on brain activity measured using functional Magnetic Resonance Imaging (fMRI) can be achieved using machine learning algorithms to train classifiers of specific stimuli. However, the high dimensionality and intrinsically low Signal-to-Noise Ratio (SNR) of fMRI data poses great challenges to such techniques. The problem is aggravated in the case of multiple subject experiments because of the high inter-subject variability in brain function. To address these difficulties, in this paper we propose using an ensemble of classifiers for decoding visual stimuli from fMRI data. Each classifier in the ensemble specializes in one stimulus by using an optimized feature set for that particular stimulus. The output for each individual stimulus is therefore obtained from the corresponding classifier and the final classification is achieved by simply selecting the best score. The proposed method was applied to two empirical fMRI datasets from multiple subjects performing visual tasks with 4 classes of stimuli. Our results indicate that an ensemble of classifiers may provide an advantageous alternative to commonly used single classifiers, particularly when decoding stimuli associated with specific brain areas.