Automatic channel selection using shuffled frog leaping algorithm for EEG based addiction detection

Drug addiction is a complex neurobiological disorder that necessitates comprehensive treatment of both the body and mind. It categorized as brain due to its impact on brain. Various methods such electroencephalography (EEG), functional magnetic resonance imaging (FMRI), magnetoencephalography (MEG) can capture activities structures. EEG signals provide valuable insights into neurological disorders, including drug addiction. Accurate classification from relies appropriate features channel selection. Choosing right channels essential reduce computational costs mitigate risk overfitting associated with using all available channels. To address challenge optimal selection in detection signals, this work employs shuffled frog leaping algorithm (SFLA). SFLA facilitates channels, leading improved accuracy. Wavelet extracted selected input are then analyzed various machine learning classifiers detect Experimental results indicate after selecting accuracy significantly increased across classifiers. Particularly, multi-layer perceptron (MLP) classifier combined demonstrated remarkable improvement 15.78% while reducing time complexity.