Detection of alcoholism using EEG signals and a CNN-LSTM-ATTN network. (November 2021)

• Record Type: Journal Article
• Authors: Neeraj, ; Singhal, Vatsal; Mathew, Jimson; Behera, Ranjan Kumar
• Is Part Of: Computers in biology and medicine. Volume 138(2021)
• Publication Date: 2021-11
• Subjects: Time series -- EEG -- Alcoholism -- FFT -- Deep learning; Medicine -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; 610.285
• DOI: 10.1016/j.compbiomed.2021.104940
• Languages: English
• ISSNs: 0010-4825

Abstract

Abstract: Alcoholism is a serious disorder that poses a problem for modern society, but the detection of alcoholism has no widely accepted standard tests or procedures. If alcoholism goes undetected at its early stages, it can create havoc in the patient's life. An electroencephalography (EEG) is a method used to measure the brain's electrical activity and can detect alcoholism. EEG signals are complex and multi-channel and thus can be difficult to interpret manually. Several previous works have tried to classify a subject as alcoholic or control (non-alcoholic) based on EEG signals. Such works have mainly used machine learning or statistical techniques along with handcrafted features such as entropy, correlation dimension, Hurst exponent. With the growth in computational power and data volume worldwide, deep learning models have recently been gaining momentum in various fields. However, only a few studies are available on the application of deep learning models for the classification of alcoholism using EEG signals. This paper proposes a deep learning architecture that uses a combination of fast Fourier transform (FFT), a convolution neural network (CNN), long short-term memory (LSTM), and a recently proposed attention mechanism for extracting Spatio-temporal features from multi-channel EEG signals. The proposed architecture can classify a subject as an alcoholic or control with a high degree of accuracy by analyzing EEG signals of that subject and can be used for automating alcoholism detection. The analytical results using the proposed architecture show a 98.83% accuracy, making it better than most state-of-the-art algorithms. Highlights: The previous studies used statistical handcrafted features for classification, which requires domain-level knowledge. Existing studies use a few samples, which resulted in less generalized results in most cases. Spatio-temporal EEG signals require architectures that can capture both spatial and temporal features. A combination of FFT-CNN-LSTM-ATTN architecture is proposed to extract Spatio-temporal features.