基于光电容积脉搏波的情绪识别方法研究
Research of Emotion Recognition Based on Photoplethysmography (PPG)
DOI: 10.12677/HJBM.2021.112011, PDF,   
作者: 牟思豫, 赵兴群*：东南大学生物科学与医学工程学院，江苏 南京；俞政涛*：南京澳思泰生物科技有限公司，江苏 南京
关键词: 情绪识别；PPG；机器学习；Emotion Recognition； PPG； Machine Learning
摘要: 情绪是人对外界或自我刺激产生的心理和生理反应。如果人机交互(Human Computer Interaction, HCI)系统可以识别情绪，那么心理疾病的诊断和心理学的研究将会更加客观和有效。本文提出了一种仅基于光电容积脉搏波(photoplethysmography, PPG)的情绪识别方法对情感进行分类。由多波长近红外透射光谱法测量获得的脉搏波，经过特征点检测，获得其信号特征，使用不同的机器学习算法验证由PPG信号识别情绪的性能。结果表明，使用脉搏波进行情绪四分类，其识别正确率为96.2%，且单个样本的测试时间短。这意味着基于PPG信号可以实现快速的多类情绪识别，对无创检测、可穿戴设备和临床实践具有潜在的价值。
Abstract: Emotion is person’s psychological reaction to external or self-stimulation with the physiological re-action. If Human Computer Interaction (HCI) system can be used to recognize emotion, the diagnosis of mental illness and psychological research will be more objective and effective. In this paper, an emotion recognition method based on photoplethysmography (PPG) is proposed to classify emo-tions. The signals measured by multi-wavelength near-infrared transmission spectroscopy are de-tected by feature points, and the signal characteristics are obtained. Different machine learning al-gorithms are used to verify the performance of emotion recognition by PPG signals. The results show that when PPG is used for emotion classification, the accuracy of recognition is 96.2%, and the testing time of a single sample is short. This means that fast multi-class emotion recognition can be achieved based on PPG signals, which has potential value for non-invasive detection, wearable de-vices and clinical practice.
文章引用：牟思豫, 俞政涛, 赵兴群. 基于光电容积脉搏波的情绪识别方法研究[J]. 生物医学, 2021, 11(2): 75-86. https://doi.org/10.12677/HJBM.2021.112011

参考文献

[1] World Health Organization (2016) Suicide Rate Estimates, Age-Standardized. https://apps.who.int/gho/data/node.main.MENTALHEALTH?lang=en
[2] 徐维芳, 彭漪, 陈柄全, 彭智勇, 赵吉玲, 余国龙. GAD-7和PHQ-9自评心理测评量表评估心内科门诊患者焦虑、抑郁状态[J]. 世界最新医学信息文摘, 2018, 18(16): 12-14.
[3] Wang, P.S., Aguilar-Gaxiola, S., Alonso, J., et al. (2007) Use of Mental Health Services for Anxiety, Mood, and Substance Disorders in 17 Countries in the WHO World Mental Health Surveys. Lancet, 370, 841-850. [Google Scholar] [CrossRef] 
[4] Ekman, P. and Rosenberg, E.L. (2005) What the Face Reveals: Basic and Applied Studies of Spontaneous Expression Using the Facial Action Coding System (FACS). 2nd Edition, Oxford University Press, Oxford, 21-38. [Google Scholar] [CrossRef] 
[5] Soleymani, M., Lichtenauer, J., Pun, T. and Pantic, M. (2012) A Multimodal Database for Affect Recognition and Implicit Tagging. IEEE Transactions on Affective Computing, 3, 42-55. [Google Scholar] [CrossRef] 
[6] Luengo, I., Navas, E. and Hernaez, I. (2010) Feature Analysis and Evaluation for Automatic Emotion Identification in Speech. IEEE Transactions on Multimedia, 12, 490-501. [Google Scholar] [CrossRef] 
[7] Wagner, J., Kim, J. and Andre, E. (2005) From Physiological Signals to Emotions: Implementing and Comparing Selected Methods for Feature Extraction and Classification. 2005 IEEE International Conference on Multimedia and Expo, Amsterdam, 6 July 2005, 942-944. [Google Scholar] [CrossRef] 
[8] Kreibig, S.D. (2010) Autonomic Nervous System Activity in Emotion: A Review. Biological Psychology, 84, 394-421. [Google Scholar] [CrossRef] [PubMed]
[9] Navakatikyan, M.A., Barrett, C.J., Head, G.A., Ricketts, J.H. and Malpas, S.C. (2002) A Real-Time Algorithm for the Quantification of Blood Pressure Waveforms. IEEE Transactions on Biomedical Engineering, 49, 662-670. [Google Scholar] [CrossRef] 
[10] Kim, J. and Ande, E. (2008) Emotion Recognition Based on Physiological Changes in Music Listening. IEEE Transactions on Pattern Analysis & Machine Intelligence, 30, 2067-2083. [Google Scholar] [CrossRef] 
[11] Hartmann, V., Liu, H., Chen, F., Qiu, Q., Hughes, S. and Zheng, D. (2019) Quantitative Comparison of Photoplethysmographic Waveform Characteristics: Effect of Measurement Site. Frontiers in Physiology, 10, Article No. 198. [Google Scholar] [CrossRef] [PubMed]
[12] Lee, M.S., Cho, Y.R., Lee, Y.K., Pae, D.S., Lim, M.T. and Kang, T.K. (2019) PPG and EMG Based Emotion Recognition using Convolutional Neural Network. Proceedings of the 16th International Conference on Informatics in Control, Automation and Robotics, Prague, 29-31 July 2019, 595-600. [Google Scholar] [CrossRef] 
[13] Hassan, M.M., Alam, M.G.R., Uddin, M.Z., Huda, S., Almogren, A. and Fortino, G. (2019) Human Emotion Recognition Using Deep Belief Network Architecture. Information Fusion, 51, 10-18. [Google Scholar] [CrossRef] 
[14] Singh, R.R., Conjeti, S. and Banerjee, R. (2013) A Comparative Evaluation of Neural Network Classifiers for Stress Level Analysis of automotive Drivers Using Physiological Signals. Biomedical Signal Processing and Control, 8, 740-754. [Google Scholar] [CrossRef] 
[15] Kim, B.H. and Jo, S. (2020) Deep Physiological Affect Network for the Recognition of Human Emotions. IEEE Transactions on Affective Computing, 11, 230-243. [Google Scholar] [CrossRef] 
[16] Healey, J.A. (2000) Wearable and Automotive Systems for Affect Recognition from Physiology. Ph.D. Thesis, Massachusetts Institute of Technology, Cambridge.
[17] 张爱华, 王平, 丑永新. 基于动态差分阈值的脉搏信号峰值检测算法[J]. 吉林大学学报(工学版), 2014, 44(3): 847-853.
[18] 胥永刚, 何正嘉. 分形维数和近似熵用于度量信号复杂性的比较研究[J]. 振动与冲击, 2003, 22(3): 25-27, 5.
[19] Bunte, K., Haase, S., Biehl, M., et al. (2012) Stochastic Neighbor Embedding (SNE) for Dimension Reduction and Visualization Using Arbitrary Divergences. Neurocomputing, 90, 23-45. [Google Scholar] [CrossRef] 
[20] Van der Maaten, L. and Hinton, G. (2009) Visualizing Data Using t-SNE. Journal of Machine Learning Research, 9, 2579-2605.

为你推荐