Frontiers in Medical Science Research, 2020, 2(1); doi: 10.25236/FMSR.2020.020101.
Weizhe Zhang, Shuohan Wang, Nan Bao*, Wenbin Li
Northeastern Univeristy, School of Medicine and Biological Information Engineering, Shenyang, Liaoning, China
*Corresponding Author
With the increase of social pressure and work intensity, fatigue has affected people's health. This paper developed a wearable fatigue monitoring system based on multi-sensor to detect the fatigue of the cervical vertebra. The monitoring system was worn on the user's neck, and the electromyographic signals (EMG) and the six-axis acceleration signals are collected and analyzed with the system. The time and frequency domain signal features were extracted. In order to detect the fatigue condition, the support vector machine (SVM) classifier was used involving 1800,000 labeled EMG data. In addition, the inclination angle of cervical vertebra can be obtained by the six-axis acceleration signal. It is proved that the fatigue monitoring system can effectively detect the fatigue of the cervical vertebra and warn the users.
fatigue monitoring; the electromyographic signal; the six-axis acceleration signal, wearable system , support vector machine
Weizhe Zhang, Shuohan Wang, Nan Bao, Wenbin Li. A Wearable Cervical Fatigue Monitoring System Based On Multi-sensor Data. Frontiers in Medical Science Research (2020) Vol. 2 Issue 1: 1-11. https://doi.org/10.25236/FMSR.2020.020101.
[1] Zang Qian,Wu Zheng jun. Advances in Chinese and western medicine research on chronic fatigue syndrome. Journal of Chinese medicine，2012
[2] Li YuanShi. Study on the features of muscle surface emg signals in people who work at a desk for a long time. Tianjin university of science and technology, 2015.
[3] Song Yaguang. Observation on 85 cases of neck fatigue treated by fengchi warm acupuncture. Clinical journal of acupuncture and moxibustion,1998
[4] Deng Kailian, Zhou Zhipeng. Design of intelligent attitude monitoring device for prevention of cervical spine disease. Application of single-chip microcomputer and embedded system,2017.
[5] Liu Xueqiang. Devices and wearable devices for measuring cervical mobility. The AAAI conference on artificial intelligence, 2000.
[6] Song Kunpo, Xia Shunren, Xu Aing. Ultrasonic image noise reduction algorithm considering wavelet coefficient correlation. Journal of Zhejiang university (engineering science edition), 2010,44 (11) : 2203 2208.
[7] AWAL M A，MOSTAFA S S，AHMAD M，et al. An adaptive level dependent wavelet thresholding for ECG denoising. Biocybernetics & biomedical engineering，2014，34（4）：238⁃249.
[8] Huang Yuchang, Hou Dewen. Fingerprint image denoising based on improved wavelet threshold function. Computer engineering and application, 2014,50 (6) : 179, 181. (in Chinese)
[9] Wang Hongqiang, Shang Chunyang, Gao Ruipeng, et al. Improvement of wavelet threshold denoising algorithm based on wavelet coefficient transform. Vibration and impact, 2011,30 (10) : 165 168.
[10] Zhou Q X, Chen Y H, Ma C, et al. Evaluation model for muscle fatigue of upper limb based on sEMG analysis. Sci China Life Sci, 2011, 54.
[11] Li Tao. Correlation analysis between center frequency of EMG power spectrum and muscle fatigue. Chinese journal of rehabilitation medicine, 1995,10 (4) : 153-155.
[12] Wang l, Sun g b, Guo w b. feature extraction of cervical surface EMG signal based on empirical mode decomposition. Journal of Shenyang institute of engineering (natural science), 2013,9 (03) : 272-274.
[13] Petrofsky JS， Lind AＲ． Frequency analysis of the surface electromyogram during sustained isometric contractions．European Journal of Applied Physiology ＆ Occupational Physiology，1980，43( 2) : 173-182．
[14] Vapnik, V. Statistical learning theory. 1998 (Vol. 3). New York, NY：Wiley，1998：Chapter 10-11, pp.401-492.
[15] Zhou Zhihua. Machine learning. Beijing: Tsinghua university press, 2016: pp.121-139, 298-300
[16] Li Hang. Statistical learning methods. Beijing: Tsinghua university press, 2012: chapter 7, pp.95-135.