基于特征融合评估不同光照条件对受试者身心疲劳的影响
Evaluating the Effects of Different Lighting Conditions on Physical and Mental Fatigue in Subjects Based on Feature Fusion
摘要: 室内工作照明环境是影响人类健康和安全的关键因素,使用不适当的照明会导致人们身心疲劳增加。本研究建立一个实验装置,通过长达30分钟的认知和身体任务同时诱导精神疲劳和身体疲劳,通过HRT软件同步记录了涵盖四个照度级别(300 lx、500 lx、750 lx、1000 lx)和五个色温级别(4000 k、4500 k、5000 k、5700 k、6500 k)的20种照明条件下脑电,肌电和心电三项生理数据。首先,研究并分析了各指标下的疲劳情况,然后,融合了脑电的(α + θ)/β指数,肌电的RMS指数,心电的(LF)/(HF)指数三大各自表征疲劳的特征指标,应用熵权法确定权重系数得到综合疲劳得分,基于此,采用响应曲面构建了疲劳评估模型,准确率达到68.5%。
Abstract: Indoor work lighting environment is a key factor affecting human health and safety, and the use of inappropriate lighting can lead to increased physical and mental fatigue. This study established an experimental setup that induced both mental and physical fatigue through cognitive and physical tasks for up to 30 minutes. HRT software was used to synchronously record 20 physiological data, including EEG, EMG, and ECG, under four illumination levels (300 lx, 500 lx, 750 lx, 1000 lx) and five color temperature levels (4000 k, 4500 k, 5000 k, 5700 k, 6500 k). Firstly, the fatigue situation under various indicators was studied and analyzed. Then, three characteristic indicators representing fatigue, namely the (α + θ)/β index of electroencephalography, the RMS index of electromyography, and the (LF)/(HF) index of electrocardiography, were fused. The entropy weight method was applied to determine the weight coefficients to obtain the comprehensive fatigue score. Based on this, a fatigue assessment model was constructed using response surface methodology, with an accuracy rate of 68.5%.
文章引用:贺文玲, 刘曼丽, 李佳欣. 基于特征融合评估不同光照条件对受试者身心疲劳的影响[J]. 运筹与模糊学, 2024, 14(6): 925-939. https://doi.org/10.12677/orf.2024.146590

参考文献

[1] Dissanayake, U.C., Steuber, V. and Amirabdollahian, F. (2022) EEG Spectral Feature Modulations Associated with Fatigue in Robot-Mediated Upper Limb Gross and Fine Motor Interactions. Frontiers in Neurorobotics, 15, Article 788494. [Google Scholar] [CrossRef] [PubMed]
[2] Hong, S., Kwon, H., Choi, S.H. and Park, K.S. (2018) Intelligent System for Drowsiness Recognition Based on Ear Canal Electroencephalography with Photoplethysmography and Electrocardiography. Information Sciences, 453, 302-322. [Google Scholar] [CrossRef
[3] Ma, Z., Yao, S., Zhao, J., Qian, J., Su, J. and Dai, J. (2018) Research on Drowsy-Driving Monitoring and Warning System Based on Multi-Feature Comprehensive Evaluation. IFAC-PapersOnLine, 51, 784-789. [Google Scholar] [CrossRef
[4] Shamsul, B.M.T., Sia, C.C., Ng, Y.G. and Karmegan, K. (2013) Effects of Light’s Colour Temperatures on Visual Comfort Level, Task Performances, and Alertness among Students. American Journal of Public Health Research, 1, 159-165. [Google Scholar] [CrossRef
[5] Fang, Y., Liu, C., Zhao, C., Zhang, H., Wang, W. and Zou, N. (2022) A Study of the Effects of Different Indoor Lighting Environments on Computer Work Fatigue. International Journal of Environmental Research and Public Health, 19, Article 6866. [Google Scholar] [CrossRef] [PubMed]
[6] Suviseshamuthu, E.S., Shenoy Handiru, V., Allexandre, D., Hoxha, A., Saleh, S. and Yue, G.H. (2022) EEG-Based Spectral Analysis Showing Brainwave Changes Related to Modulating Progressive Fatigue during a Prolonged Intermittent Motor Task. Frontiers in Human Neuroscience, 16, Article 770053. [Google Scholar] [CrossRef] [PubMed]
[7] Gromer, M., Salb, D., Walzer, T., Madrid, N.M. and Seepold, R. (2019) ECG Sensor for Detection of Driver’s Drowsiness. Procedia Computer Science, 159, 1938-1946. [Google Scholar] [CrossRef
[8] Lu, M., Hu, S., Mao, Z., Liang, P., Xin, S. and Guan, H. (2020) Research on Work Efficiency and Light Comfort Based on EEG Evaluation Method. Building and Environment, 183, Article ID: 107122. [Google Scholar] [CrossRef
[9] 王永菲, 王成国. 响应面法的理论与应用[J]. 中央民族大学学报(自然科学版), 2005, 14(3): 236-240.