北京生物医学工程

基于心率变异率的人体疲劳度评估模型

Assessment modle based on heart rate variability for human fatigue

作者：於鹏严良文陈佳乐余越曹可乐黄闪董旭东

单位：上海大学机电工程与自动化学院（上海 200072）

关键词：隐马尔科夫模型； PPG； HRV； Baum-Welch； Viterbi；疲劳评估

分类号：R318.04

出版年·卷·期（页码）：2021·40·1（46-54）

摘要：

目的构建一种信号采集方便、准确度高的人体疲劳度评估模型，以帮助人们及时地做出疲劳预警。方法首先使用MAX30102传感器采集包含大量与人体生理和病理相关信息的光电容积脉搏波（photoplethysmography, PPG）信号；然后对PPG信号进行消除噪声干扰和基线漂移的预处理，再运用差分阈值法提取心率变异率（heart rate variability, HRV）信息，利用隐马尔可夫模型（hidden Markov model, HMM）理论建立基于HRV的人体疲劳评估模型；最后随机选取10位自愿者的数据利用Baum-Welch算法对模型参数进行训练优化后得到状态转移概率矩阵和观测值概率矩阵，随机选取3位精神状态转变模式不同的自愿者数据并运用Viterbi算法求得最优状态，与实际状态进行对比。结果所建模型对3位自愿者的疲劳评估准确度都达到了80%以上，具有较高的准确度。结论运用HMM理论构建的基于HRV的人体疲劳评估模型能够准确评估人体的精神状态，具有广阔的应用前景。

Objective Mental fatigue has become a social problem. A method of evaluating the fatigue degree with high accuracy and convenient signal collection should be developed, which can help people to give early warning of fatigue in time. Methods Firstly, the MAX30102 sensor was used to collect photoplethysmography (PPG) signals containing a large amount of information related to human physiology and pathology; then the PPG signal was preprocessed to eliminate noise interference and baseline drift, which extracted heart rate variability (HRV) information by applying the method of difference threshold, using Hidden Markov model (HMM) theory to establish a human fatigue assessment model based on HRV; at last, by using randomly selected 10 volunteers’ data to train model parameters for state transition probability matrix and observation probability matrix by Baum - Welch algorithm, data of three volunteers with different mental state transition modes were randomly selected and the optimal state was obtained by using Viterbi algorithm, which was compared with the actual state. Results The accuracy of the fatigue assessment of the three volunteers reached more than 80%, indicating that the model has high accuracy. Conclusion The human fatigue assessment model based on HRV constructed by HMM theory can accurately assess the mental state of human bodies and has a broad application prospect.

参考文献：

[1] 张志云,赵冬梅.北京市干部医疗保健科医务人员慢性疲劳状况的调查分析[J].中华保健医学杂志， 2012,14(06):452-455.

Zhang ZY, Zhao DM. Investigation of chronic fatigue syndrome among healthcare professionals in Beijing [J]. Chinese Journal of Health Medicine，2012,14(06):452-455.

[2] 何金良.人体疲劳评价标准综述[J].西藏医药杂志,2013,34(2):29-32.

[3] 李明爱,张诚,杨金福.一种基于脑电信号的疲劳驾驶状态判断方法[J].北京生物医学工程,2011,30(1):57-61.

Li MA, Zhang C, Yang JF. EEG-based method to determine the drowsiness degree of EGG signal[J]. Beijing Biomedical Engineering, 2011,30 (1): 57-61.

[4] Rybynok V, May JM, Budidha K, et al. Design and development of a novel multi-channel photoplethysmographic research system[C].2013 IEEE Point-of-Care Healthcare Technologies (PHT). Bangalore: IEEE,2013：267-270.

[5] 孙旭君,全海英,张宽.咖啡摄入前后心率变异性的对比研究[J].北京生物医学工程,2017,36(6):614-618,654.

Sun XJ, Quan HY, Zhang K. Effect of coffee on heart rate variability [J]. Beijing Biomedical Engineering, 2017,36 (6) : 614-618 , 654.

[6] Al-Libawy H, Al-Ataby A, Al-Nuaimy W, et al. HRV-Based Operator Fatigue Analysis and Classification Using Wearable Sensors[C].2016 13th International Multi-Conference on Systems, Signals & Devices (SSD). Leipzig: IEEE, 2016： 268-273.

[7]Tsai MK. Applying physiological status monitoring in improving construction safety management[J]. KSCE Journal of Civil Engineering,2017,21(6): 2061-2066.

[8] 郭玮珍,郭兴明,万小萍.以心率和心率变异性为指标的疲劳分析系统[J].医疗卫生装备,2005，26(8):1-2.

Guo WZ, Guo XM, Wan XP. Fatigue analysis system with HR and HRV as indexes[J]. Medical Equipment, 2005，26 (8): 1-2.

[9] 祝荣欣,王金武.基于心肌电的联合收获机驾驶人疲劳检测研究[J].农机化研究,2020,42(2):8-14,43.

Zhu RX, Wang JW. The Study of Fatigue Detection of Combine Harvester Driver Based on ECG and sEMG[J]. Journal of Agricultural Mechanization and Chemical Engineering, 202,42 (2) : 8-14 , 43.

[10] Baum LE，Petrie T. Statistical inference for probabilistic functions of finite state Markov chains[J].Annals of mathematical statistics, 1966，37(6): 1554-1563.

[11]翟琳琳,陈仪香.隐马尔科夫模型在智能学习系统中的应用[J].计算机工程与应用,2007，43(6):178-180.

Zhai LL，Chen YX. Application of HMM in intelligent learning system[J]. Computer Engineering and Applications,2007，43(6):178-180.

[12] 范洁怡,王亮,谢满江,等.午睡剥夺诱发脑力疲劳对认知能力和心率变异性的影响[J].空军医学杂志,2018,34(4):217-220.

Fan JY, Wang l, Xie MJ, et al. Effect of metal fatigue induced by nap deprivation on cognitive function and heart rate variability [J]. Air Force Medical Journal, 2008,34 (4): 217-220.

[13] Chalder T, Berelowitz G, Pawlikowska T, et al. Development of a Fatigue Scale[J]. Journal of Psychosomatic Research, 1993, 37(2):147-153.

[14] 武炜,陈标,吴剑锋,黄馗.基于五点三次平滑算法的入库流量反推研究[J].水利水电技术,2013,44(12):100-102.

Wu W, Chen B, Wu JF, et al. Study on reverse deduction of reservoir-inflow based on cubical smoothing algorithm with five-point approximation[J]. Water Conservancy and Hydropower Technology, 2013,44 (12) :100-102.

[15] 冯俊,罗春苗,张静,高潮.心率变异性时域指标对稳定性心绞痛患者冠状动脉狭窄的影响[J].安徽医学,2016,37(12):1480-1483.

Feng J, Luo CM, Zhang J, et al. Impacts of heart rate variability time-domain indexes on coronary artery stenosis in patients with stable angina pectoris[J]. Anhui Medicine, 2016,37(12): 1480-1483.

[16] Singh RR, Conjeti S, Banerjee R. A comparative evaluation of neural network classifiers for stress level analysis of automotive drivers using physiological signals[J]. Biomedical Signal Processing and Control, 2013, 8(6):740-754

服务与反馈：

【文章下载】【加入收藏】

提示：您还未登录，请登录！点此登录