EEG signal classification to detect left and right command using artificial neural network (ANN)

Abstract

In this study, the right and left commands explored are based on the actual movement of lifting either left or right hand and the imaginary movement For this initial study, EEG signals recorded based on the actual physical movements will be collected as the raw data, as well as the EEG signals recorded when imaginary movements are performed. In the scope of this r different features namely SD and ESD. These features are used as inputs to be classified by the ANN classifier. The performance of this classifier is then evaluated by measuring its accuracy in distinguishing the different interpreted commands. Based on findings from the conducted analysis, we found that PSD is the best feature to be fed as input to the ANN classifier with a high accuracy of 93% compared to when ESD feature is used as the input. he right and left commands explored are based on the actual movement of lifting either left or right hand and the imaginary movement of lifting either left or right hand. EEG signals recorded based on the actual physical movements will be collected as the raw data, as well as the EEG signals recorded when imaginary movements are performed. In the scope of this research, the EEG processing focuses on analyzing two different features namely SD and ESD. These features are used as inputs to be classified by the ANN classifier. The performance of this classifier is then evaluated by measuring its shing the different interpreted commands. Based on findings from the conducted analysis, we found that PSD is the best feature to be fed as input to the ANN classifier with a high accuracy of 93% compared to when ESD feature is used as the input. he right and left commands explored are based on the actual movement of of lifting either left or right hand. EEG signals recorded based on the actual physical movements will be collected as the raw data, as well as the EEG signals recorded when imaginary movements are esearch, the EEG processing focuses on analyzing two different features namely SD and ESD. These features are used as inputs to be classified by the ANN classifier. The performance of this classifier is then evaluated by measuring its shing the different interpreted commands. Based on findings from the conducted analysis, we found that PSD is the best feature to be fed as input to the ANN classifier with a high accuracy of 93% compared to when ESD feature is used as the input.