YANG Linkun,HE Peiyu,PAN Fan,et al.Emotional Recognition of ECG Signals based on XGBoost-RFE-CBR[J].Journal of Chengdu University of Information Technology,2023,38(03):258-263.[doi:10.16836/j.cnki.jcuit.2023.03.002]
基于XGBoost-RFE-CBR的心电信号情绪识别研究
- Title:
- Emotional Recognition of ECG Signals based on XGBoost-RFE-CBR
- 文章编号:
- 2096-1618(2023)03-0258-06
- Keywords:
- signal and signal processing; emotion recognition; ECG signals; XGBoost; feature selection; RFE.
- 分类号:
- TP911.7
- 文献标志码:
- A
- 摘要:
- 情绪是一种复杂的行为现象,是对不同外部刺激的生理反应。为快速、便捷地识别人类的情绪,提出了一种基于极限梯度提升结合可减少相关性偏差和递归特征消除的心电信号情绪识别方法。先对AMIGOS数据集进行特征提取、结合XGBoost-RFE-CBR特征排序算法进行特征选择,得到27个心电信号和心率变异性的时域、频域等特征参数,利用XGBoost进行分类,最后在五折交叉验证下,最高准确率达80.5%、平均准确率达77.2%。该方法与多维生理信号特征提取方法相比,在确保准确率的同时降低了计算量,对情绪识别和分类任务有一定的参考价值。
- Abstract:
- Emotion is a complex behavioral phenomenon that is a physiological response to different external stimuli. To quickly and conveniently recognize human emotions, this paper proposes a method using XGBoost-RFE-CBR to recognize the emotions based on ECG signals. Firstly, the feature of AMIGOS dataset was extracted, and selected according to XGBoost-RFE-CBR feature ranking algorithm, then 27 ECG signals and heart rate variability were obtained in time domain, frequency domain. Other features were classified by XGBoost, and finally, the highest accuracy of 80.5% and the average accuracy of 77.2% were achieved under the five-fold cross-validation. Compared with the multidimensional physiological signal feature extraction method, this research method ensures accuracy while reducing the computational effort, which has certain reference value for emotion recognition and classification tasks.
参考文献/References:
[1] Li M,Xu H,Liu X,et al.Emotion recognition from multichannel eeg signals using k-nearest neighbor classification[J].Technology and Health Care,2018,26:509-519.
[2] 许芬,闰文彬,张晓平.姿态情绪识别研究综述[J].计算机应用研究,2021,38(12):3521-3526.
[3] 万家华,陈乃金.基于上下文感知和注意机制的多学习情绪识别方法[J].北京师范大学学报(自然科学版),2021,57(5):601-605.
[4] 陈倩,静进.孤独症谱系障碍面孔情绪识别的研究进展[J].教育生物学杂志,2021,9(5):341-346.
[5] 陈媛媛,王建峰.背景颜色对大学生不同强度面孔情绪识别的影响[J].中国健康心理学杂志,2022,30(1):91-96.
[6] Staji T,JovanoviJ,Jovanovi N,et al.Emotion recognition based on deap database physiological signals[C].2021 29th Telecommunications Forum(TEL FOR),2021:1-4.
[7] Liu Z,Wu M,Cao W,et al.A facial expression emotion recognition based human-robot interaction system[J].IEEE/CAA Journal of Automatica Sinica,2017,4(4):668-676.
[8] Sharma L D,Bhattacharyya A.A computerized approach for automatic human emotion recognition using sliding mode singular spectrum analysis[J].IEEE Sensors Journal,2021,21(23):26931-26940.
[9] Khateeb M,Anwar S M,Alnowami M.Multi-domain feature fusion for emotion classification using deap dataset[J].IEEE Access,2021,9:12134-12142.
[10] Romeo L,Cavallo A,Pepa L,et al.Multiple instance learning for emotion recognition using physiological signals[J].IEEE Transactions on Affective Computing,2022,13(1):389-407.
[11] Hsu Y-L,Wang J-S,Chiang W-C,et al.Automatic ecg-based emotion recognition in music listening[J].IEEE Transactions on Affective Computing,2020,11(1):85-99.
[12] Sarkar P,Etemad A.Self-supervised learning for ecg-based emotion recognition[C/OL].ICASSP 2020-2020 IEEE International Conference on Acoustics,Speech and Signal Processing(ICASSP).Barcelona,Spain:IEEE,2020:3217-3221.
[13] Cimtay Y,Ekmekcioglu E,Caglar-Ozhan S.Cross-subject multimodal emotion recognition based on hybrid fusion[J].IEEE Access,2020,8:168865-168878.
[14] Shukla J,Barreda-Angeles M,Oliver J,et al.Feature extraction and selection for emotion recognition from electrodermal activity[J].IEEE Transactions on Affective Computing,2021,12(4):857-869.
[15] Kim B H,Jo S.Deep physiological affect network for the recognition of human emotions[J].IEEE Transactions on Affective Computing,2020,11(2):230-243.
[16] 陈沙利,张柳依,江锋,等.基于多种生理信号的情绪识别研究[J].中国医疗器械杂志,2020,44(4):283-287.
[17] Pan L,Yin Z,She S,et al.Emotional state recognition from peripheral physiological signals using fused nonlinear features and team-collaboration identification strategy:5[J].Entropy,2020,22(5):511-534.
[18] Chao H,Liu Y.Emotion recognition from multi-channel eeg signals by exploiting the deep belief-conditional random field framework[J].IEEE Access,2020,8:33002-33012.
[19] Santamaria-Granados L,Munoz-Organero M,Ramirez-Gonzalez G,et al.Using deep convolutional neural network for emotion detection on a physiological signals dataset(amigos)[J].IEEE Access,2019(7):57-67.
[20] Shaffer F,Ginsberg J P.An overview of heart rate variability metrics and norms[J].Frontiers in Public Health,2017(5):258-275.
[21] 易慧,陈瑞娟,邓光华,等.基于心率变异性的情绪识别研究[J].生物医学工程研究,2020,39(2):128-132.
[22] Miranda-Correa J A,Abadi M K,Sebe N,et al.AMIGOS:a dataset for affect,personality and mood research on individuals and groups[J].IEEE Transactions on Affective Computing,2021,12(2):479-493.
[23] Dessai A,Virani H.Emotion detection using physiological signals[C].2021 International Conference on Electrical,Computer and Energy Technologies(ICECET).2021:1-4.
[24] 杨承金,聂春燕,车敏诗,等.心电信号去噪效果的评估与分析[J].计算机工程与应用,2022,58(1):300-312.
[25] Tayel M B,AlSaba E I.Poincaré plot for heart rate variability[J].International Journal of Biomedical and Biological Engineering,2015,9(9):708-711.
[26] 王昕宇,杨鹏,戴健非.基于RFE-rf-xgboost的坝体位移预测研究[J].东北师大学报(自然科学版),2021,53(2):60-66.
[27] Yan K,Zhang D.Feature selection and analysis on correlated gas sensor data with recursive feature elimination[J].Sensors and Actuators B:Chemical,2015,212:353-363.
[28] Chen T,Guestrin C.XGBoost:a scalable tree boosting system[J/OL].ACM,2016:785-794.
[29] Li C,Bao Z,Li L,et al.Exploring temporal representations by leveraging attention-based bidirectional lstm-rnns for multi-modal emotion recognition[J].Information Processing & Management,2020,57(3):102185-102194.
相似文献/References:
[1]金宁敏,何培宇,潘 帆,等.一种基于超混沌的个性化耳鸣康复音合成方法[J].成都信息工程大学学报,2018,(04):359.[doi:10.16836/j.cnki.jcuit.2018.04.002]
JIN Ning-min,HE Pei-yu,PAN Fan,et al.A Method of Personalized Synthesizing TinnitusRehabilitation Sound based on Hyper-chaos[J].Journal of Chengdu University of Information Technology,2018,(03):359.[doi:10.16836/j.cnki.jcuit.2018.04.002]
[2]苏良成,王建波.网格化监测站中基于差分场强的信号源定位方法[J].成都信息工程大学学报,2018,(04):391.[doi:10.16836/j.cnki.jcuit.2018.04.007]
SU Liang-cheng,WANG Jian-bo.Radio Source Locating Method based on Signal-strength-differencein Gridded Radio Monitoring System[J].Journal of Chengdu University of Information Technology,2018,(03):391.[doi:10.16836/j.cnki.jcuit.2018.04.007]
[3]赵锦阳,卢会国,蒋娟萍,等.基于改进决策树的故障诊断方法研究[J].成都信息工程大学学报,2018,(06):624.[doi:10.16836/j.cnki.jcuit.2018.06.005]
ZHAO Jin-yang,LU Hui-guo,JIANG Juan-ping,et al.Research on Fault Diagnosis Method based on Improved Decision Tree[J].Journal of Chengdu University of Information Technology,2018,(03):624.[doi:10.16836/j.cnki.jcuit.2018.06.005]
[4]冯婉悦,佘 勇,姚振东.非球形降水粒子测量模型的初步研究[J].成都信息工程大学学报,2016,(02):136.
FENG Wan-yue,SHE Yong,YAO Zhen-dong.A Preliminary Study on the Measurement Model of
Non-spherical Precipitation Particles[J].Journal of Chengdu University of Information Technology,2016,(03):136.
[5]王保强,刘志刚,杨小平,等.医学小气候空气质量监测技术研究[J].成都信息工程大学学报,2016,(02):142.
WANG Bao-qiang,LIU Zhi-gang,YANG Xiao-ping,et al.Study on Air Quality Detection in Medical Microclimate[J].Journal of Chengdu University of Information Technology,2016,(03):142.
[6]龙永良,杜雨洺,陈光拓.雷达窄带强干扰自适应频域陷波技术研究与实现[J].成都信息工程大学学报,2016,(02):146.
LONG Yong-liang,DU Yu-ming,CHEN Guang-tuo.The Research and Realized on Adaptive Frequency Domain Notch
Filter with the Strong Narrow Band Interference in Radar[J].Journal of Chengdu University of Information Technology,2016,(03):146.
[7]曼世超,卢会国,卢 勇.基于LabVIEW的心电信号检测平台的设计[J].成都信息工程大学学报,2016,(03):255.
MAN Shi-chao,LU Hui-guo,LU Yong.The Design of ECG Detection Platform based on LabVIEW[J].Journal of Chengdu University of Information Technology,2016,(03):255.
[8]严学阳,杨笔锋,马尚昌.基于MSP430气象水文漂流浮标采集器的硬件设计[J].成都信息工程大学学报,2017,(01):28.[doi:10.16836/j.cnki.jcuit.2017.01.005]
YAN Xue-yang,YANG Bi-feng,MA Shang-chang.The Hardware Design of the Meteorological and
Hydrological Drifting Buoy Collector based on MSP430[J].Journal of Chengdu University of Information Technology,2017,(03):28.[doi:10.16836/j.cnki.jcuit.2017.01.005]
[9]赵富强,王维和,邓小波,等.气溶胶指数与臭氧总量的相关性初步研究[J].成都信息工程大学学报,2017,(02):147.[doi:10.16836/j.cnki.jcuit.2017.02.007]
ZHAO Fu-qiang,WANG Wei-he,DENG Xiao-bo,et al.A Preliminary Study on the Relationship between Aerosol Index and Total Ozone[J].Journal of Chengdu University of Information Technology,2017,(03):147.[doi:10.16836/j.cnki.jcuit.2017.02.007]
[10]杜牧云,余 蓉,吴 涛,等.一种改进的多普勒天气雷达下击暴流识别算法[J].成都信息工程大学学报,2017,(05):487.[doi:10.16836/j.cnki.jcuit.2017.05.004]
DU Mu-yun,YU Rong,WU Tao,et al.An Improved Method of Downburst Recognition based
on WSR-88D Doppler Weather Radar[J].Journal of Chengdu University of Information Technology,2017,(03):487.[doi:10.16836/j.cnki.jcuit.2017.05.004]
备注/Memo
收稿日期:2022-09-08
基金项目:四川省自然科学基金资助项目(2022NSFSC0799)