Intelligent Model for Predicting EEG α Band Power during Muslim Prayer

This book presents the development of robust intelligent systems for predicting alpha power (Pα) of electroencephalogram (EEG) signals during the Muslim prayer (Salat). Thirty healthy Muslim male subjects were recruited in the study. Their electroencephalogram (EEG), electrocardiogram (ECG), respiration rate (RSP) and oxygen saturation (SPO2) were continuously recorded before, during and after Salat. Power spectral analysis was conducted to extract the alpha power (Pα) of EEG signals and heart rate variability (HRV) components. Self organizing map (SOM) and statistical analysis techniques were used to determine the most significant parameters that influence the Pα among the three experimental conditions. Adaptive neuro-fuzzy inference system (ANFIS) was used to develop the prediction models. Overall prediction accuracy of the proposed models were achieved of 94.39% , 92.89%, 93.62%, and 94.31% for the alpha power of electrodes positions at O1, O2, P3, and P4, respectively. These models demonstrated many advantages, including efficiency, accuracy, and simplicity. Thus, ANFIS could be considered as a suitable tool for dealing with complex and nonlinear prediction problems.