摘要
脑电信号容易记录且不易伪装,基于脑电信号的情感识别越来越受到人们的关注.然而,人类情感具有多样性和个体可变性,基于脑电信号的情感识别仍是情感计算领域的难题.本文提出一种多源域领域适应字典学习和稀疏表示方法.为减少源领域和目标领域数据分布的差异,将所有领域的数据投影到共享子空间,并在共享子空间中学习一个共有字典.根据稀疏重建的最小化类内误差和最大化类间误差准则,稀疏表示具有类别的分辨能力.另外,每个源域自适应学习领域权重,可以避免负迁移的发生.模型参数的求解通过参数交替优化方法,所有参数可同时达到最优解.DEAP数据集的实验结果显示本文方法在所有对比方法中是最优的.
Electroencephalogram(EEG)signals are easy to record and difficult to camouflage,so EEG-based emotion recognition has attracted more and more attention.However,the diversity and individual variability of human emotion make the EEG-based emotion recognition still a difficult problem in the field of affective computing.To solve this problem,a multi-source domain adaptive dictionary learning and sparse representation approach is proposed in this study.To reduce the difference of data distribution between the source domain and the target domain,the data of all domains are projected into a shared subspace,where a common dictionary is learned.The sparse representation has the ability of class recognition according to the criteria of minimizing intra-class error and maximizing inter-class error of sparse reconstruction.In addition,each source domain adapts its domain weight to avoid negative migration.The model parameters are solved by parameter alternating optimization,and all parameters can reach the optimal solution simultaneously.The experimental results on DEAP dataset show that the proposed approach is the best among all the compared methods.
作者
袁凯烽
侯璐
黄永锋
YUAN Kaifeng;HOU Lu;HUANG Yongfeng(College of Information Engineering,Changzhou Vocational Institute of Industry Technology,Changzhou 213164;School of Computer Engineering,Jiangsu University of Technology,Changzhou 213001)
出处
《南京信息工程大学学报（自然科学版）》
CAS
北大核心
2023年第4期412-418,共7页
Journal of Nanjing University of Information Science & Technology（Natural Science Edition）
基金
国家自然科学基金(12005182)。
关键词
脑电情感识别
稀疏表示
领域适应
子空间
字典学习
EEG-based emotion recognition
sparse representation
domain adaptation
subspace
dictionary learning
