A new one-dimensional testosterone pattern-based EEG sentence classification method

Abstract

Electroencephalography (EEG) signals are crucial data to understand brain activities. Thus, many papers have been proposed about EEG signals. In particular, machine learning techniques have been used/presented to extract information from EEG signals. However, there are limited works on sentence classification using this data. To fill this gap, we propose an automated EEG signal classification model. In this model, we have presented a new molecular-based feature extractor, which utilizes a graph of the testosterone molecular structure. The proposed testosterone graph-based pattern is a nature-inspired pattern. The motivation is to show the feature extraction capability of the chemical-based graphs. Hence, we presented a hand-modeled EEG classification architecture. Our architecture uses wavelet packet decomposition (WPD) to generate wavelet bands to extract low and high-level features. The statistical feature extraction function has been used to generate statistical features, and our proposed testosterone pattern (TesPat) generates textural features. A feature selector has been used to choose the most informative features (neighborhood component analysis). Channel-wise results have been calculated by deploying a shallow classifier (k nearest neighbors). Majority voting has been conducted to create general results, and our proposed model selects the best-resulted predicted labels vector. Our proposed model attained a classification accuracy of >97% with 10-fold cross-validation (CV) and >91% with leave-one subject out (LOSO) CV. Our high classification results demonstrate that our presented system is an accurate and robust sentence classification model. The novelty of this work is the development of an accurate testosterone-based learning model using three EEG sentence datasets.