ABSTRACT

Electroencephalogram (EEG) can track the brain waves which contain the neural activity of the brain. EEG signals help to understand the physiological and functional details and activities of the brain. In the era of Artificial Intelligence (AI), machine learning algorithms were useful in brain disorder detection and classification. Recently, a rapid increase in using Deep Learning (DL) methods in various applications in EEG signals not only helps in the detection of brain disorders but also facilitates the recognition of human emotions and various psycho-neuro disorders. In order to offer a beneficial and broad perspective, a detailed survey on the application of deep learning architecture in EEG signals has been carried out in this paper. Different deep learning methods, using varied architecture in EEG signal analysis, offer an understanding to develop the next level of AI-based systems. This review will provide information about how deep learning methods are used in EEG signals and the challenges and limitations of each method in classification; moreover making it helpful for those who are exploring EEG signals using DL algorithms.

摘要

脑电图（EEG）可以跟踪包含大脑神经活动的脑电波。EEG 信号有助于了解大脑的生理和功能细节和活动。在人工智能 (AI) 时代，机器学习算法在大脑疾病检测和分类中非常有用。最近，在脑电信号的各种应用中使用深度学习 (DL) 方法的迅速增加，不仅有助于检测大脑疾病，还有助于识别人类情绪和各种心理神经疾病。为了提供有益和广泛的视角，本文对深度学习架构在脑电信号中的应用进行了详细调查。不同的深度学习方法，在 EEG 信号分析中使用不同的架构，提供理解以开发下一个级别的基于人工智能的系统。本综述将提供有关如何在 EEG 信号中使用深度学习方法以及每种方法在分类中的挑战和局限性的信息；此外，它对那些使用 DL 算法探索 EEG 信号的人有所帮助。