Subject Transfer Framework Based On Source Selection And Semi-Supervised Style Transfer Mapping For Semg Pattern Recognition

To construct subject-specific feature extractors and classifiers for a new subject using pooled datasets, overcoming inter-subject variabilities is required. In this study, we investigate the efficiency of the proposed subject transfer framework, which applies a discriminability-based source selection approach and semi-supervised style transfer mapping algorithm, by constructing support vector machine classifiers. We collect a surface electromyogram (sEMG) dataset acquired from 25 subjects using a wearable sEMG sensor. Classifiers are trained with gold-standard time-domain and autoregressive features extracted from eight-channel sEMG data. Compared with conventional subject transfer framework (85.08${}\pm{}$1.38\%), which applies the covariate shift adaptation algorithm to the linear discriminant analysis classifier and uses all source data, our proposed framework improves pattern recognition accuracy (90.63${}\pm{}$1.27\%) by selection of discriminative source data and the mapping destination in the Euclidean space.