Abstract

Nowadays, Electroencephalogram (EEG) devices that do not require invasive procedures get more attraction. Brain-Computer Interface (BCI) systems use EEG analysis to identify users’ mental states, cognitive shifts, and stimuli-induced reactions. The Motor Execution (ME) paradigm is a vital control paradigm that holds great significance in this framework. In this manuscript, an Efficient Predefined Time Adaptive Neural Network for EEG-Based Brain-Computer Interaction in Motor Execution Classification (EPTNN-BCI-EEG) is proposed. Initially, the input signals are collected from EEG Dataset. The input signals are preprocessed using Robust M- Type Error-State Kalman Filter (RMESKF) to remove the artifacts and baseline signals. Then, the pre-processed signals are given to Signed Cumulative Distribution Transform (SCDT) for feature extraction. SCDT is used to extract Spatial and temporal features. Afterward, Efficient Predefined Time Adaptive Neural Network (EPTNN) is used to classify the EEG gender and signal, such as Audio/Video and Male/Female. In General, EPTNN does not expose any adoption of optimization systems to determine optimal parameters to classify the EEG gender and signal. Hence, Bitwise Arithmetic Optimization Algorithm (BAOA) is proposed to optimize the EPTNN. The proposed EPTNN-BCI-EEG approach is implemented in MATLAB and the performance metrics, such as Recall, Accuracy, Root Mean Square Error (RMSE), F1-score, Specificity, ROC, Computation time are assessed. The performance of EPTNN-BCI-EEG approach provides 17.82 %, 28.95 %, and 19.2 % higher accuracy, 24.38 %, 34.53 %, and 18.78 % higher recall, 26.7 %, 24.2 %, and 32.7 % higher specificity when analysed with the existing methods.