Fuzzy Entropy Analysis of Mental Fatigue Based on EMD DetrendedFluctuation
Yang Shuo1,2*, Li Runze1,2, Ding Jianqing1,2, Xu Guizhi1,2
1(State Key Laboratory of Reliability and Intelligence of Electrical Equipment, Hebei University of Technology, Tianjin 300130, China) 2(Key Laboratory of Electromagnetic Field and Electrical Apparatus Reliability of Hebei Province, Hebei University of Technology, Tianjin 300130, China)
Abstract：Mental fatigue is caused by engaging in repeated single or high-load cognitive activities for long time. Short-term mental fatigue can cause decreased attention and reduced work efficiency, while long-term mental fatigue can cause brain damage. Extraction of mental fatigue characteristics can help detect mental fatigue and prevent the harm. Entropy can reflect changes of dynamic complexity under mental fatigue state and is expected to be an indicator for evaluating mental fatigue. However, entropy's extraction of EEG signal characteristics is affected by the superimposed trends in signals, makeing it impossible to accurately describe the dynamic characteristics of the signal and resulting in inconsistent entropy characteristics obtained at different time periods. In order to solve the problems, the empirical mode decomposition (EMD) detrended fluctuation analysis was combined with fuzzy entropy to evaluate the dynamic complexity of EEG signal. The four-hour English scientific paper translation was used as a mental fatigue-inducing task and the EEG signal were recorded from 14 undergraduate volunteers in resting-state and mental fatigue state. The approximate entropy, fuzzy entropy and detrended fuzzy entropy of EEG signals in the two status and the three time periods were compared and analyzed. Results showed that compared with the traditional approximate entropy and fuzzy entropy, the detrended fuzzy entropy in the mental fatigue state was significantly different than that in the resting-state in the left hemisphere dominance (FC3, P=0.022; P5, P=0.007), and the electrodes with significant differences were basically consistent in the three time periods (The P-values of the FC3 in the three time periods are 0.025, 0.017, and 0.012, respectively, and the P-values of the P5 are 0.011, 0.006, and 0.017). It was shown that the detrended fuzzy entropy could better express the difference of brain complexity in two status, and had good time stability. Therefore, EMD-based detrended fuzzy entropy can be used to evaluate the impact of mental fatigue on brain dynamic complexity more quickly and effectively.
杨硕, 李润泽, 丁建清, 徐桂芝. 基于EMD去趋势波动的脑疲劳模糊熵分析[J]. 中国生物医学工程学报, 2020, 39(1): 33-39.
Yang Shuo, Li Runze, Ding Jianqing, Xu Guizhi. Fuzzy Entropy Analysis of Mental Fatigue Based on EMD DetrendedFluctuation. Chinese Journal of Biomedical Engineering, 2020, 39(1): 33-39.
 Liu X, Liu J, Duan F, et al. Inter-hemispheric frontal alpha synchronization of event-related potentials reflects memory-induced mental fatigue[J]. Neuroscience Letters, 2017, 653:326-331.
 Tanaka M, Ishii A, Watanabe Y. Neural effects of mental fatigue caused by continuous attention load: a magnetoencephalography study[J]. Brain Research, 2014, 1561(3):60-66.
 Laurent F, Valderrama M, Besserve M, et al. Multimodal information improves the rapid detection of mental fatigue[J]. Biomedical Signal Processing & Control, 2013, 8(4):400-408.
 Wascher E, Rasch B, Sänger J, et al. Frontal theta activity reflects distinct aspects of mental fatigue[J]. Biological Psychology, 2014, 96(1):57-65.
 Borghini G, Astolfi L, Vecchiato G, et al. Measuring neurophysiological signals in aircraft pilots and car drivers for the assessment of mental workload, fatigue and drowsiness[J]. NeurosciBiobehav Rev, 2014, 44:58-75.
 Moore TM, Key AP, Thelen A, et al. Neural mechanisms of mental fatigue elicited by sustained auditory processing[J]. Neuropsychologia, 2017, 106:371-382.
 Murata A, Uetake A, Takasawa Y. Evaluation of mental fatigue using feature parameter extracted from event-related potential[J]. International Journal of Industrial Ergonomics, 2005, 35(8):761-770.
 Cao Z, Lin CT. Inherent fuzzy entropy for the improvement of EEG complexity evaluation[J]. IEEE Transactions on Fuzzy Systems, 2018, 26(2):1032-1035.
 Lentka Ł, Smulko J. Methods of trend removal in electrochemical noise data - Overview[J]. Measurement, 2019,131:569-581.
 Moghtaderi A, Flandrin P, Borgnat P. Trend filtering via empirical mode decompositions[J]. Computational Statistics & Data Analysis, 2013, 58(1):114-126.
 Forrest SM, Challis JH, Winter SL. The effect of signal acquisition and processing choices on ApEn values: Towards a “gold standard” for distinguishing effort levels from isometric force records[J]. Medical Engineering & Physics, 2014, 36(6):676-683.
 Pincus SM. Approximate entropy as a measure of system complexity[J]. Proceedings of the National Academy of Sciences of the United States of America, 1991, 88(6):2297-2301.
 Chen W, Zhuang J, Yu W, et al. Measuring complexity using FuzzyEn, ApEn, and SampEn[J]. Medical Engineering & Physics, 2009, 31(1):61-68.
 Sharma R, Pachori R, Acharya U. Application of entropy measures on intrinsic mode functions for the automated identification of focal electroencephalogram signals[J]. Entropy, 2015, 17(2):669-691.
 Liu J, Zhang C, Zheng C. EEG-based estimation of mental fatigue by using KPCA-HMM and complexity parameters[J]. Biomedical Signal Processing & Control, 2010, 5(2):124-130.