Texture Analysis of Scalogram Image from Alcoholic EEG Signals using CNN

The harmful use of alcohol has become a significant global health issue, causing millions of deaths annually and contributing to various diseases and mental disorders. Early diagnosis of alcoholism is crucial to prevent permanent damage, yet current diagnostic methods are subjective and prone to errors. his study proposes an objective approach using electroencephalogram (EEG) signals for identifying alcoholism. We employ Continuous Wavelet Transform (CWT) for signal preprocessing and Grey-Level Co-occurrence Matrix (GLCM) for feature extraction, followed by classification with a Convolutional Neural Network (CNN). The results show a classification accuracy of 99% in distinguishing alcoholic and non-alcoholic individuals based on EEG signals. This research contributes to the development of alcoholic diagnosis and highlights the potential of EEG technology with the combined use of CWT, GLCM, and CNN techniques to enhance accuracy in alcoholic identification.