[1]刘柯,黄玉柱,邓欣,等.采用多任务特征融合的脑电情绪识别方法[J].智能系统学报,2024,19(3):610-618.[doi:10.11992/tis.202206023]
LIU Ke,HUANG Yuzhu,DENG Xin,et al.Electroencephalogram emotion recognition method using multitask feature integration[J].CAAI Transactions on Intelligent Systems,2024,19(3):610-618.[doi:10.11992/tis.202206023]
点击复制
LIU Ke,HUANG Yuzhu,DENG Xin,et al.Electroencephalogram emotion recognition method using multitask feature integration[J].CAAI Transactions on Intelligent Systems,2024,19(3):610-618.[doi:10.11992/tis.202206023]
采用多任务特征融合的脑电情绪识别方法
《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷:
19
期数:
2024年第3期
页码:
610-618
栏目:
学术论文—机器感知与模式识别
出版日期:
2024-05-05
- Title:
- Electroencephalogram emotion recognition method using multitask feature integration
- Keywords:
- emotional brain-computer interface; EEG emotion recognition; brain networks; differential entropy; affinity propagation clustering; graph Laplacian regularization; multitask feature fusion; sparse feature selection
- 分类号:
- TP391
- 文献标志码:
- 2024-03-27
- 摘要:
- 特征选择与融合是提升脑电信号情绪解码精度的重要手段之一。然而，当前脑电情绪解码中的特征选择方法常忽略了脑电信号内在数据结构的隐含信息。该文提出一种基于近邻传播聚类的多任务特征融合方法，通过${L_{2,1}}$范数约束实现稀疏特征选择，同时利用图拉普拉斯正则化保持不同子类间的潜在关系。该算法在不揭示真实样本标签的情况下，在子任务空间有效融合脑网络空间拓扑结构信息和微分熵信息，为高精度脑电信号情绪解码提供具有更高情绪表征能力的特征。DEAP和SEED数据集以及本实验室数据集的分析结果表明，该文提出的方法能显著提高脑电情绪解码的精度。
- Abstract:
- Feature selection and integration is one of the crucial approaches to improving the emotion decoding accuracy of electroencephalogram (EEG) signals. However, current methods often neglect the implicit information of the intrinsic data structure in EEG signals. Herein, a multitask feature integration method is proposed based on affinity propagation clustering. This method uses the L2,1-norm constraint to select sparse features and uses graph Laplacian regularization to maintain potential relationships among different subclasses. In case of not disclosing real sample labels, the method has effectively integrated the spatial topology information of brain networks and differential entropy information in the subtask space, providing features with higher emotional characterization ability for the emotional decoding of high-accuracy EEG signals. The analytic results on DEAP and SEED datasets and the dataset of the laboratory show that the proposed method can markedly improve the decoding accuracy of EEG emotional decoding.
- 参考文献/References:
-
[1] 吕宝粮, 张亚倩, 郑伟龙. 情感脑机接口研究综述[J]. 智能科学与技术学报, 2021, 3(1): 36–48
LYU Baoliang, ZHANG Yaqian, ZHENG Weilong. A survey of affective brain-computer interface[J]. Chinese journal of intelligent science and technology, 2021, 3(1): 36–48
[2] ALARC?O S M, FONSECA M J. Emotions recognition using EEG signals: a survey[J]. IEEE transactions on affective computing, 2019, 10(3): 374–393.
[3] 张冠华, 余旻婧, 陈果, 等. 面向情绪识别的脑电特征研究综述[J]. 中国科学: 信息科学, 2019, 49(9): 1097–1118
ZHANG Guanhua, YU Minjing, CHEN Guo, et al. A review of EEG features for emotion recognition[J]. Scientia sinica informationis, 2019, 49(9): 1097–1118
[4] PATEL P, R R, ANNAVARAPU R N. EEG-based human emotion recognition using entropy as a feature extraction measure[J]. Brain informatics, 2021, 8(1): 20.
[5] ZHENG Weilong, LIU Wei, LU Yifei, et al. EmotionMeter: a multimodal framework for recognizing human emotions[J]. IEEE transactions on cybernetics, 2019, 49(3): 1110–1122.
[6] SONG Tengfei, ZHENG Wenming, SONG Peng, et al. EEG emotion recognition using dynamical graph convolutional neural networks[J]. IEEE transactions on affective computing, 2020, 11(3): 532–541.
[7] 孙岩, 薄思雨, 吕娇娇. 认知重评和表达抑制情绪调节策略的脑网络分析: 来自 EEG 和 ERP 的证据[J]. 心理学报, 2020, 52(1): 12
SUN Yan, BO Siyu, LYU Jiaojiao. Brain network analysis of cognitive reappraisal and expressive suppression emotion regulation strategies: evidence from EEG and ERP[J]. Acta psychologica sinica, 2020, 52(1): 12
[8] ZHANG Shilin, HU Bin, BIAN Ji, et al. A novel emotion recognition method incorporating MST-based brain network and FVMD-GAMPE[C]//2021 IEEE International Conference on Bioinformatics and Biomedicine. Houston: IEEE, 2021: 1153–1158.
[9] KANG Qiaoju, GAO Qiang, SONG Yu, et al. Emotion recognition from EEG signals of hearing-impaired people using stacking ensemble learning framework based on a novel brain network[J]. IEEE sensors journal, 2021, 21(20): 23245–23255.
[10] XU Peng, XIONG Xiuchun, XUE Qing, et al. Differentiating between psychogenic nonepileptic seizures and epilepsy based on common spatial pattern of weighted EEG resting networks[J]. IEEE transactions on bio-medical engineering, 2014, 61(6): 1747–1755.
[11] ZHANG Junan, GU Liping, CHEN Yongqiang, et al. Multi-feature fusion emotion recognition based on resting eeg[J]. Journal of mechanics in medicine and biology, 2022, 22(3): 2240002.
[12] GAO Qiang, WANG Chuhan, WANG Zhe, et al. EEG based emotion recognition using fusion feature extraction method[J]. Multimedia tools and applications, 2020, 79(37): 27057–27074.
[13] GAO Zhongke, LI Rumei, MA Chao, et al. Core-brain-network-based multilayer convolutional neural network for emotion recognition[J]. IEEE transactions on instrumentation and measurement, 2021, 70: 2510209.
[14] ZHENG Weilong, ZHU Jiayi, LU Baoliang. Identifying stable patterns over time for emotion recognition from EEG[J]. IEEE transactions on affective computing, 2019, 10(3): 417–429.
[15] WANG Zhongmin, HU Shuyuan, SONG Hui. Channel selection method for EEG emotion recognition using normalized mutual information[J]. IEEE access, 2019, 7: 143303–143311.
[16] ZHANG Yu, ZHOU Tao, WU Wei, et al. Improving EEG decoding via clustering-based multitask feature learning[J]. IEEE transactions on neural networks and learning systems, 2022, 33(8): 3587–3597.
[17] FREY B J, DUECK D. Clustering by passing messages between data points[J]. Science, 2007, 315(5814): 972–976.
[18] LI Fali, WANG Jiuju, LIAO Yuanyuan, et al. Differentiation of schizophrenia by combining the spatial EEG brain network patterns of rest and task P300[J]. IEEE transactions on neural systems and rehabilitation engineering, 2019, 27(4): 594–602.
[19] RAMOSER H, MULLER-GERKING J, PFURTSCHELLER G. Optimal spatial filtering of single trial EEG during imagined hand movement[J]. IEEE transactions on rehabilitation engineering, 2000, 8(4): 441–446.
[20] ZHENG Weilong, LYU Baoliang. Investigating critical frequency bands and channels for EEG-based emotion recognition with deep neural networks[J]. IEEE transactions on autonomous mental development, 2015, 7(3): 162–175.
[21] LIU Jun, JI Shuiwang, YE Jieping. Multi-task feature learning via efficient l2, 1-norm minimization[EB/OL]. (2012–05–09)[2022–06–14]. http://arxiv.org/abs/1205.2631.
[22] LI Yazhou, DAI Wei, ZHANG Weifang. Bearing fault feature selection method based on weighted multidimensional feature fusion[J]. IEEE access, 2020, 8: 19008–19025.
[23] WU Xun, ZHENG Weilong, LI Ziyi, et al. Investigating EEG-based functional connectivity patterns for multimodal emotion recognition[J]. Journal of neural engineering, 2022, 19(1): 016012.
[24] LIU Wei, QIU Jielin, ZHENG Weilong, et al. Comparing recognition performance and robustness of multimodal deep learning models for multimodal emotion recognition[J]. IEEE transactions on cognitive and developmental systems, 2022, 14(2): 715–729.
[25] KOELSTRA S, MUHL C, SOLEYMANI M, et al. DEAP: a database for emotion analysis; using physiological signals[J]. IEEE transactions on affective computing, 2012, 3(1): 18–31.
[26] DING Yi, ROBINSON N, ZHANG Su, et al. TSception: capturing temporal dynamics and spatial asymmetry from EEG for emotion recognition[EB/OL]. (2021–04–07) [2022–06–14]. http://arxiv.org/abs/2104.02935.
[27] NAWAZ R, CHEAH K H, NISAR H, et al. Comparison of different feature extraction methods for EEG-based emotion recognition[J]. Biocybernetics and biomedical engineering, 2020, 40(3): 910–926.
[28] LI Xiang, SONG Dawei, ZHANG Peng, et al. Exploring EEG features in cross-subject emotion recognition[J]. Frontiers in neuroscience, 2018, 12: 162.
[29] RAHMAN M A, KHANAM F, AHMAD M, et al. Multiclass EEG signal classification utilizing Rényi min-entropy-based feature selection from wavelet packet transformation[J]. Brain informatics, 2020, 7(1): 7.
[30] KHATUN S, MORSHED B I, BIDELMAN G M. A single-channel EEG-based approach to detect mild cognitive impairment via speech-evoked brain responses[J]. IEEE transactions on neural systems and rehabilitation engineering, 2019, 27(5): 1063–1070.
[31] YIN Zhong, ZHAO Mengyuan, WANG Yongxiong, et al. Recognition of emotions using multimodal physiological signals and an ensemble deep learning model[J]. Computer methods and programs in biomedicine, 2017, 140: 93–110.
[32] LI Yang, ZHENG Wenming, ZONG Yuan, et al. A Bi-hemisphere domain adversarial neural network model for EEG emotion recognition[J]. IEEE transactions on affective computing, 2021, 12(2): 494–504.
[33] ZHOU Rushuang, ZHANG Zhiguo, FU Hong, et al. PR-PL: a novel transfer learning framework with prototypical representation based pairwise learning for EEG-based emotion recognition[EB/OL]. (2022–02–14) [2022–06–14]. http://arxiv.org/abs/2202.06509.
备注/Memo
收稿日期:2022-06-14。
基金项目:国家自然科学基金项目（62136002，61703065）.
作者简介:刘柯，副教授，主要研究方向为脑电源成像、脑信号分析与脑机接口系统。主持国家自然科学基金项目1项，省部级科研项目3项，发表学术论文40篇。E-mail：liuke@cqupt.edu.cn;黄玉柱，硕士研究生，主要研究方向为脑电情绪解码。E-mail：363608086@qq.com;邓欣，副教授，主要研究方向为脑机接口系统。E-mail：dx168@yeah.net
通讯作者:刘柯. E-mail：liuke@cqupt.edu.cn
更新日期/Last Update:
1900-01-01