mental arithmetic task recognition using effective connectivity and hierarchical feature selection from eeg signals

Introduction: mental arithmetic analysis based on electroencephalogram (eeg) signalscan help understand disorders, such as attention-deficit hyperactivity, dyscalculia, or autismspectrum disorder where the difficulty in learning or understanding the arithmetic exists. mostmental arithmetic recognition systems rely on features of a single channel of eeg; however,the relationships between eeg channels in the form of effective brain connectivity analysis cancontain valuable information. this study aims to find distinctive, effective brain connectivityfeatures and create a hierarchical feature selection for effectively classifying mental arithmeticand baseline tasks.methods: we estimated effective connectivity using directed transfer function (dtf), directdtf (ddtf) and generalized partial directed coherence (gpdc) methods. these measuresdetermine the causal relationship between different brain areas. a hierarchical feature subsetselection method selects the most significant effective connectivity features. initially, kruskal–wallis test was performed. consequently, five feature selection algorithms, namely, supportvector machine (svm) method based on recursive feature elimination, fisher score, mutualinformation, minimum redundancy maximum relevance (rmr), and concave minimizationand svm are used to select the best discriminative features. finally, the svm method wasused for classification.results: the obtained results indicated that the best eeg classification performancein 29 participants and 60 trials is obtained using gpdc and feature selection via concaveminimization method in beta2 (15-22hz) frequency band with 89% accuracy.conclusion: this new hierarchical automated system could be helpful in the discrimination ofmental arithmetic and baseline tasks from eeg signals effectively.