ISSN 1000-1239 CN 11-1777/TP

计算机研究与发展 ›› 2016, Vol. 53 ›› Issue (1): 80-92.doi: 10.7544/issn1000-1239.2016.20150636

所属专题: 2016优青专题

• 其他应用技术 • 上一篇    下一篇



  1. 1(中国科学院心理研究所行为科学院重点实验室 北京 100101); 2(清华信息科学与技术国家实验室(筹) 北京 100084); 3(中国移动研究院 北京 100055) (
  • 出版日期: 2016-01-01
  • 基金资助: 

Advances in Emotion Recognition Based on Physiological Big Data

Zhao Guozhen1, Song Jinjing1, Ge Yan1, Liu Yongjin2, Yao Lin3, Wen Tao3   

  1. 1(Key Laboratory of Behavioral Science, Institute of Psychology, Chinese Academy of Sciences, Beijing 100101); 2(Tsinghua National Laboratory for Information Science and Technology, Beijing 100084); 3(China Mobile Research Institute, Beijing 100055)
  • Online: 2016-01-01

摘要: 随着计算技术和人机交互技术的不断发展,情感计算(affective computing, AC)逐渐成为情绪研究的新兴领域,而情绪识别(emotion recognition)又是情感计算中不可或缺的一环.基于生理信号的情绪识别方法比其他指标如面部表情、语音语调、身体姿势等更难以伪装,也能提供更丰富的信息.目前基于生理信号的情绪识别研究很多,但受到各种因素的影响,如刺激选取、诱发情绪的类别、采集设备、特征提取方法、不同的降维和分类算法等,各个研究的识别准确率差异性很大,很难进行比较.针对使用DEAP数据库(用音乐视频诱发情绪并采集脑电及外周生理信号的公开数据库)进行情绪识别的16篇文章做了梳理;对特征提取、数据标准化、降维、情绪分类、交叉检验等方法做了详细的解释和比较;最后分析了现阶段情绪识别在游戏开发、多媒体制作、交互体验、社交网络中的初步探索和应用,以及情绪识别和情感计算目前存在的问题及未来发展的方向.

关键词: 情绪识别, 脑电, 外周生理信号, 特征提取, 机器学习

Abstract: Affective computing (AC) is a new field of emotion research along with the development of computing technology and human-machine interaction technology. Emotion recognition is a crucial part of the AC research framework. Emotion recognition based on physiological signals provides richer information without deception than other techniques such as facial expression, tone of voice, and gestures. Many studies of emotion recognition have been conducted, but the classification accuracy is diverse due to variability in stimuli, emotion categories, devices, feature extraction and machine learning algorithms. This paper reviews all works that cited DEAP dataset (a public available dataset which uses music video to induce emotion and record EEG and peripheral physiological signals) and introduces detailed methods and algorithms on feature extraction, normalization, dimension reduction, emotion classification, and cross validation. Eventually, this work presents the application of AC on game development, multimedia production, interactive experience, and social network as well as the current limitations and the direction of future investigation.

Key words: emotion recognition, electroencephalograph (EEG), peripheral physiological signal, feature extraction, machine learning