Classification of Alcoholic EEG Signals Using a Deep Learning Method

Most of the traditional alcoholism detection methods are developed based on machine learning based methods that cannot extract the deep concealed characteristics of Electroencephalogram (EEG) signals from different layers. Hence, this study aims to introduce a deep leaning-based method that can automatically identify alcoholic EEG signals. It also explores if a hand-crafted feature extraction method is worth applying to deep learning techniques for classification of alcoholism. To investigate this, this paper presents two deep learning-based algorithms for classification of alcoholic EEG signals for comparison. In Algorithm 1, Principal Component Analysis (PCA) based feature extraction technique has been applied to extract representative components and then the extracted features are used as input to Artificial neural network (ANN) for classification. In Algorithm 2, the raw EEG data are directly used as inputs to a deep learning method: `long short-term memory (LSTM)' for detection of alcoholism. The proposed algorithms were tested on a publicly available UCI Alcoholic EEG dataset. The experimental results show that the proposed Algorithm 2 could achieve an average classification accuracy of 93% while this accuracy is 86% for the proposed Algorithm 1. The comparative evaluations with the state-of-the-art algorithms indicate that Algorithm 2 also outperforms other competing algorithms in the literature. Thus deep learning algorithm when applied to raw data, can produce better performance than the combination of the hand-crafted feature method and the deep leaning algorithm. Our proposed system can be used to determine the extent of alcoholism-related changes in EEG signals and the effectiveness of therapeutic plans.