Statistical Channel Selection Method for Detecting Drowsiness Through Single-Channel EEG-Based BCI System

• Published in: IEEE transactions on instrumentation and measurement Vol. 70; pp. 1 - 9
• Main Authors: Balam, Venkata Phanikrishna, Chinara, Suchismitha
• Format: Journal Article
• Language: English
• Published: New York IEEE 2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Accident prevention; Alertness; Algorithms; Artificial intelligence; Artificial neural networks; Brain–computer interface (BCI); classification; Classifiers; Correlation; Cranes; deep neural network (DNN); Driver fatigue; drowsiness detection (DD); Electroencephalography; Feature extraction; Human-computer interface; Neurons; Physiology; Professional activities; Signal to noise ratio; single-channel electroencephalogram (EEG); Sleep; Sleepiness
• ISSN: 0018-9456; 1557-9662
• DOI: 10.1109/TIM.2021.3094619

Electroencephalogram (EEG) is an essential tool used to analyze the activities effectively and different states of the brain. Drowsiness is a short period state of the brain that is also called an inattentiveness state. Drowsiness can be observed during the transition from being awake state to a sleepy state. Drowsiness can reduce a person's alertness that increases accidental risks when involved in their personal and professional activities like vehicle driving, operating a crane, mine blasts, and so on. Drowsiness detection (DD) has a significant role in preventing accidents. Neuroscience with artificial intelligence algorithms used to detect drowsiness is also popularly known as brain-computer interface (BCI) systems. Single-channel EEG BCIs are highly preferred for convenient use in real-time applications, even though there are many challenges in the actual experimental process. They are choosing the best single-channel and classifier. In this article, a novel channel selection approach is proposed for a single-channel EEG-BCI system by integrating the statistical characteristics of the available channel's EEG signal. In addition to this, a deep neural network (DNN) classifier is developed using the stack ensemble process for better classification accuracy. Simulated-virtual-driving driver and physionet sleep analysis EEG datasets (PSAEDs) are used to test the proposed model. Subject-wise, cross-subject-wise, and combined subject-wise validations are also employed to improve the generalization capability of the proposed techniques in this article.