EEG Classification Using Elliptic Filter and Multilayer Perceptron Based on Gamma Activity Features

摘要: Alcohol detection in the community is important to assist solving problem caused by alcohol abuse. Machine Learning (ML) combination with Electroencephalography (EEG) one alternative solution. Studies on classification of alcoholic EEG signal has been largely done transforming other domains. While accuracy obtained use time domain feature less than transformation method. Another type required obtain high accuracy. In this study, features gamma band were used and non-alcoholic classification. This activity a representation visual stimuli given humans. Alcoholic paper consists three stages: filtering, extraction, Elliptic Highpass filter pass signal. The next step, filtered extracted its only domain. Furthermore, these are as input Multilayer Perceptron (MLP). Based experiments, that provide variance Root Mean Square (RMS) 96% 96.08% respectively.