计算机工程与应用 ›› 2023, Vol. 59 ›› Issue (15): 38-54.DOI: 10.3778/j.issn.1002-8331.2209-0429

• 热点与综述 • 上一篇    下一篇

脑电信号情绪识别研究综述

秦天鹏,生慧,岳路,金卫   

  1. 山东中医药大学 智能与信息工程学院,济南 250355
  • 出版日期:2023-08-01 发布日期:2023-08-01

Review of Research on Emotion Recognition Based on EEG Signals

QIN Tianpeng, SHENG Hui, YUE Lu, JIN Wei   

  1. College of Intelligence and Information Engineering, Shandong University of Traditional Chinese Medicine, Jinan 250355, China
  • Online:2023-08-01 Published:2023-08-01

摘要: 通过面部表情、语音语调以及脑电等生理信号对人的情绪状态进行识别分类,即情绪识别,其在医疗、交通以及教育等领域有广泛应用。脑电信号由于其真实可靠,在情绪识别领域日益得到广泛关注。总结了近年来脑电情绪识别研究所取得的进展,主要介绍基于深度学习和迁移学习进行的脑电情绪识别研究。介绍了脑电情绪识别基础理论、常用公开数据集、信号的采集和预处理,介绍特征提取与选择,重点介绍了深度学习和迁移学习在脑电情绪识别上的应用。指出该领域目前面临的挑战和前景。

关键词: 情绪识别, 深度学习, 迁移学习, 特征提取, 脑电信号

Abstract: Recognition and classification of human emotional states through physiological signals such as facial expressions, intonation, and EEG, that is, emotion recognition, are widely used in medicine, transportation, education, and other fields. EEG signals have received increasing attention in the field of emotion recognition due to their authenticity and reliability. This paper summarizes the progress of EEG emotion recognition research in recent years, and mainly introduces the EEG emotion recognition research based on deep learning and transfer learning. This paper firstly introduces the basic theory of EEG emotion recognition, commonly used public datasets, signal acquisition and preprocessing, then introduces feature extraction and selection, and then focuses on the application of deep learning and transfer learning in EEG emotion recognition. Finally, the current challenges and prospects in this field are pointed out.

Key words: emotion recognition, deep learning, transfer learning, feature extraction, EEG signals