Detection of Alcoholism Based on Eeg Signals using Machine Learning

Alcoholism is one of the most alarming and rapidly spreading diseases in the modern world. People in this generation actively participate in frequent alcohol consumption, which contributes to the development of alcoholism. It finally develops into a chronic illness that worsens personality and health. Alcoholism rapid diagnostic techniques are continuously being researched. This article offers a fast diagnostic technique based on a machine learning algorithm. The subject's personal information is not compromised by this procedure. We have examined machine learning algorithms and their supporting transformation techniques, such as the Fourier and Wavelet transforms, in the execution section. The following machine learning algorithms are employed to categorize the data: Naive Bayes, Random Forest, Support Vector Machine, Logistic Regression, and Decision Tree. The accuracy of each algorithm's classification is compared. The Random Forest Classifier gave us the best accuracy. It makes use of an EEG correlation signal dataset that is divided into control and alcoholic groups. Since it doesn't consider any of the subject's personal information, it guarantees that their privacy won't be violated.