基于脑机接口的精神疲劳评估方法研究
|
摘要
精神疲劳是指劳动过程中体力或脑力消耗的能量过多或刺激过强,压力过大导致机体各部分功能反应能力减弱,之后引发的神经系统的疲劳。主要症状有头脑昏沉、反应迟钝、判断错误、注意力不集中、工作效率下降,易出差错等。在高危作业中,短期的精神疲劳产生的注意力不集中、反应迟钝等症状会引发严重的安全生产事故。精神疲劳若长期存在,便会影响身心健康,甚至引起身心疾病。精神疲劳是人体的一种生理性保护反应,人体通过适当地休息及放松,就可缓解精神疲劳。因此,对精神疲劳的检测和评估就显得尤为重要。然而,目前尚缺乏对精神疲劳程度进行客观有效评估的方法。本文针对这一问题展开对精神疲劳状态进行快速检测和评估方法的研究。拟通过分析脑电信号基本节律相对能量的变化来检测精神疲劳的程度。本文设计了一套基于LabVIEW平台的精神疲劳测试系统,用于实现快速检测人体的精神疲劳程度。
本文通过对不同精神疲劳状态下采集的脑电信号进行小波包分析,提取出脑电各节律并计算脑电对数能量熵,定性分析了各特征参数与不同精神状态间的关联性。通过实验发现,相较于不疲劳状态而言,前额叶区的脑电各节律相对能量和脑电对数能量熵在不同精神疲劳状态下均有显著变化。因此,前额叶区的脑电各节律相对能量与脑电对数能量熵可以作为衡量精神疲劳的生理指标。通过对以上特征指标进行分析统计,最终选取大脑前额叶区FPz导联的脑电各节律相对能量作为特征指标,利用以相对隶属度为基础的模糊综合评判模型对精神疲劳程度进行分级。实验结果表明,运用模糊综合评判模型对精神疲劳的评价结果与客观实际相符。
本文所采用的脑电信号采集设备NeuroScan平台支持通过TCP协议向局域网中的其他计算机实时传输信息。因此本文选用LabVIEW软件来实现脑电信号基于网络端口的实时数据传输,并将传输来的脑电信号作分析处理,从而评估出受试者当前的精神疲劳程度。
Mental fatigue is, in daily life, caused by prolonged high-intensity mental or physical labor, lack of sleep, circadian rhythm disruption of biological function, and leads to temporary job barriers, operational capacity drop phenomenon. The main symptoms of mental fatigue are dazed mind, slow response, misjudgment, lack of concentration, decreased efficiency, easy to make mistakes and so on. In high-risk operations, the short-term mental fatigue resulting symptoms, such as lack of concentration, slow response, may lead to serious accidents. If somebody has mental fatigue for a long time, the physical and mental health could be affected and even lead to physical and mental diseases. Mental fatigue is the body's protective physiological responses. The human body through proper rest and relaxation can relieve mental fatigue. Therefore, the detection and evaluation of mental fatigue is particularly important. However, there is still lack of effective and objective mental fatigue assessment methods. We try to analyze the basic rhythms changes of EEG to detect mental fatigue degree. In this paper, a detection system of mental fatigue based on LabVIEW has been developed for rapid detection of the body's mental fatigue degree.
For the sake of finding the relationships between mental fatigue and electroencephalogram(EEG) parameters, using wavelet packer analysis to extract basic rhythms from EEG and calculate the log energy entropy in different states of mental fatigue. In comparative study, it is found that the frontal pole of brain presents significant distinction of basic rhythms and log energy entropy in the states of mental fatigue. Therefore, we can regard the relative power in basic rhythms and the log energy entropy as valid indices for measuring mental fatigue. Selecting the relative power of FPz lead’s basic rhythms as indices, the fuzzy synthetic evaluation model based on the relative membership degree was used to evaluate the degree of mental fatigue. Experimental results show that the mental fatigue assessment made by the fuzzy synthetic evaluation model is consistent with the objective reality.
EEG acquisition equipment NeuroScan platform supports to transmit information to other computers in real time based on TCP protocol. LabVIEW software is used to achieve real-time EEG data transmission and signal processing, and to assess the subjects’current mental fatigue degree.
本文通过对不同精神疲劳状态下采集的脑电信号进行小波包分析,提取出脑电各节律并计算脑电对数能量熵,定性分析了各特征参数与不同精神状态间的关联性。通过实验发现,相较于不疲劳状态而言,前额叶区的脑电各节律相对能量和脑电对数能量熵在不同精神疲劳状态下均有显著变化。因此,前额叶区的脑电各节律相对能量与脑电对数能量熵可以作为衡量精神疲劳的生理指标。通过对以上特征指标进行分析统计,最终选取大脑前额叶区FPz导联的脑电各节律相对能量作为特征指标,利用以相对隶属度为基础的模糊综合评判模型对精神疲劳程度进行分级。实验结果表明,运用模糊综合评判模型对精神疲劳的评价结果与客观实际相符。
本文所采用的脑电信号采集设备NeuroScan平台支持通过TCP协议向局域网中的其他计算机实时传输信息。因此本文选用LabVIEW软件来实现脑电信号基于网络端口的实时数据传输,并将传输来的脑电信号作分析处理,从而评估出受试者当前的精神疲劳程度。
Mental fatigue is, in daily life, caused by prolonged high-intensity mental or physical labor, lack of sleep, circadian rhythm disruption of biological function, and leads to temporary job barriers, operational capacity drop phenomenon. The main symptoms of mental fatigue are dazed mind, slow response, misjudgment, lack of concentration, decreased efficiency, easy to make mistakes and so on. In high-risk operations, the short-term mental fatigue resulting symptoms, such as lack of concentration, slow response, may lead to serious accidents. If somebody has mental fatigue for a long time, the physical and mental health could be affected and even lead to physical and mental diseases. Mental fatigue is the body's protective physiological responses. The human body through proper rest and relaxation can relieve mental fatigue. Therefore, the detection and evaluation of mental fatigue is particularly important. However, there is still lack of effective and objective mental fatigue assessment methods. We try to analyze the basic rhythms changes of EEG to detect mental fatigue degree. In this paper, a detection system of mental fatigue based on LabVIEW has been developed for rapid detection of the body's mental fatigue degree.
For the sake of finding the relationships between mental fatigue and electroencephalogram(EEG) parameters, using wavelet packer analysis to extract basic rhythms from EEG and calculate the log energy entropy in different states of mental fatigue. In comparative study, it is found that the frontal pole of brain presents significant distinction of basic rhythms and log energy entropy in the states of mental fatigue. Therefore, we can regard the relative power in basic rhythms and the log energy entropy as valid indices for measuring mental fatigue. Selecting the relative power of FPz lead’s basic rhythms as indices, the fuzzy synthetic evaluation model based on the relative membership degree was used to evaluate the degree of mental fatigue. Experimental results show that the mental fatigue assessment made by the fuzzy synthetic evaluation model is consistent with the objective reality.
EEG acquisition equipment NeuroScan platform supports to transmit information to other computers in real time based on TCP protocol. LabVIEW software is used to achieve real-time EEG data transmission and signal processing, and to assess the subjects’current mental fatigue degree.
引文
[1] Akerstedt T,Knustsson A.Mental fatigue work and sleep [J]..Journal of Psychosomatic Reaearch,2004,57(5):427-433.
[2] Edwards R.Human muscle function and fatigue [M].Ciba:Springer-Verlag,1982.1-18.
[3] Booth F,Thomason D.Molecular and cellular adaptation of muscle in response to exercise:perspectives of various models [J].Physiol Rev,1991,71(5):541-585.
[4] Gandevia SC.Spinal and supraspinal factors in human muscle fatigue [J].Physiol Rev,2002,81(23):1725-1789.
[5] Layzer RB.Asthenia and chronic fatigue syndrome [J].Muscle Nerve,1998,21(12):1609-1611.
[6] Kai-Quan Shen,Xiao-Ping Li,Chong-Jin Ong.EEG-based mental fatigue measurement using multi-class support vector machines with confidence estimate [J].Clinical Neurophysiology 2008,119:1524-1533.
[7] Maarten A.S. Boksem,Theo F. Meijman,Monicque M. Lorist.Mental fatigue,motivation and action monitoring [J].Biological Psychology 2006,72:123-132.
[8]鲍德国.疲劳的诊断[J].全科医学临床与教育,2005,3(3):136-138.
[9]王天芳,薛晓琳.疲劳自评量表[J].中华中医药杂志,2009,24(3):348-349.
[10] LU Zhiqiang,Dong Hai.Human Factors[M].Beijing:Mechanical Industry Press,2006:53-58.
[11] MU Yongge,HE Zhongli,WU Xiaolan,etal.Study of local muscle fatigue monitoring by surface myoelectric signal [J].Journal of Jilin Military Medical College Fourth Military Medical University,1999,21(3):127-130.
[12] Cai Qiming.Study on methods of evaluating physical fatigue according to dynamic heart rate [J].Chinese Ergonomics,1999,5(1):27-29.
[13] Cao Xueliang,Miao Danmin,Liu Lianhong.Assessment methods on mental fatigue.Fourh MilMed Univ,2006,27(4):382-384.
[14] Hu Wenqiang,Ma Jin,Han Wendong.Prevention and monitoring means of flying fatigue [J].Chinese Journal of Clinic Rehabilitation,2004,8(3):542-543.
[15]张连毅,郑崇勋.EEG柯尔莫哥洛夫熵测度用于精神疲劳状态的研究[J].中国生物医学工程学报,2007,2(2):170-176.
[16] Atsuo M,Atsushi U,Yosuke T.Evaluation of mental fatigue using feature parameter extracted from event-related potential [J].International Journal of Industrial Ergonomics,2005,35(8):761.
[17] Boksem MAS,Meijman TF,Lorist MM.Effects of mental fatigue on attention:an ERP study [J].Cognitive Brain Reasearch,2005,25(1):107.
[18]赵春临,郑崇勋,赵敏.基于核学习算法的驾驶精神疲劳分级研究[J].数据采集与处理,2009,24(3):335-339.
[19]杜树新,吴铁军.模式识别中的支持向量机方法[J].浙江大学学报(工学版),2003,37(5):521-527.
[20]赵晖,荣莉莉,李晓.一种设计层次支持向量机多类分类器的新方法[J].计算机应用研究,2003,(5):34-37.
[21]张崇,郑崇勋.生理性精神疲劳的多参数脑电功率谱分析[J].生物医学工程杂志,2009,26(1):162-166.
[22]吴克俭.临床脑电速成指南[M].上海:第二军医大学出版社,2002.
[23]尧得中.脑功能探测的电学理论与方法[M].北京:科学出版社,2003.
[24]曾远明,李长清,胡常林.脑电超慢涨落图的正常参考值[J].现代医药卫生,2004,20(15):1522-1523.
[25]孙久荣.脑科学导论[M].北京:北京大学出版社,2001:15-51.
[26]赵仑.ERP实验教程[M].天津:天津社会科学院出版社,2004:0-12.
[27]陈兴时,张明岛.脑诱发电位形成的可能机制[J].神经病学与神经康复学杂志,2006,3(2):124-125.
[28] Ogura C,Koga Y,Shimokochi M,ed.Recent advances in event related brain potential research[M].Amsterdam:Elsevier,2003:765-779.
[29] Le Bihan D,Tezzard P,Haxby J,etal.Functional magnetic resonance imaging of the brain [J].Annals Internol Medicine,1995,122:296-303.
[30]何庆华,彭承琳,吴宝明.脑机接口技术研究方法[J].重庆大学学报,2002,25(12):106-109.
[31]万博坤,高扬,赵丽等.脑—机接口:大脑对外信息交流的新途径[J].国外医学生物医学工程分册,2005,28(1):4-9.
[32] Lorist MM,Klein M.Mental fatigue and task control:planning and preparation [J].Int J Psychophysiology,2000,37(1):1-12.
[33] Stipacek A,Grabner RH,Neuper C.Sensitivity of human EEG alpha band desynchronization to different working memory components and increasing levels of memory load [J].Neuroscience Letters 2003,353:193-196.
[34] Jonathan R.,Wolphaw,etal.Brain-computer interface research at the wadsworth center [J].IEEE Transactions on Rehabilitation Engineering,2000,8(2):222-226.
[35]谢勤岚,杨仲乐.基于IR-ERP的脑-机接口的结构与原理[J].武汉理工大学学报(交通科学与工程版),2003.
[36]万柏坤,高扬,赵丽,綦宏志.脑-机接口:大脑对外信息交流的新途径[J].国外医学生物工册,2005,28(1):4-9.
[37]伍业舟,吴宝明,何庆华.基于脑电的脑-机接口系统研究现状[J].中国临床康复,2006,10(1):147-150.
[38] Ming Cheng,Xiaorong Gao,Shangkai Gao,Dingfeng Xu.Design and Implementation of a Brain-Computer Intereface With High Transfer Rates [J].IEEE Traps Biomed.Eng,2002,49(10):1181-1186.
[39] Aleksander,Kostov&Mark,Polak.Parrallel.Man-Machine Training in Development of EEG-Based Cursor control[J].IEEE Trans.Rehab.Eng,2000,8(2):203-204.
[40] Wu Ting,Yan Guo-zheng,Yang Bang-hua.EEG feature extraction based on wavelet packet decomposition for brain computer interface [J].Measurement 2008.41:618-625.
[41] Josefina Gutierrez,Rogelio Alcantara,Veronica Medina.Analysis and localization of epileptic events using wavelet packets [J].Medical Engineering & Physics,2001,23:623-631.
[42]张德丰.MATLAB小波分析[M].北京:机械工业出版社,2009:49-181.
[43]李安贵,张志宏,段凤英.模糊数学及其应用[M].北京:冶金工业出版社,1994:1-20.
[44]陈守煜.工程模糊集理论与应用[M].北京:国防工业出版社,1998:24-217.
[45]张彩庆,林明,戚若男.基于模糊模式识别的燃煤电厂大气质量评价[J].中国电机工程学报,2009,29(29):30-34.
[46] Ada W.S. Leung,Chetwyn C.H,Chan,Jimmy J.M. Factors contributing to officers’fatigue in high-speed maritime craft operations [J].Applied Ergonomics,2006,37:565-576.
[47]杨建国.小波分析及其工程应用[M].北京:机械工业出版社,2005:85-178.
[48]徐宝国,宋爱国.基于小波包变换和聚类分析的脑电信号识别方法[M].仪器仪表学报,2009,30(1):25-28.
[49] Patricia Tassi,Anne Bonnefond,Ophelie Engasser.EEG spectral power and cognitive performance during sleep inertia:The effect of normal sleep duration and partial sleep deprivation [J].Physiology & Behavior,2006,87:177-184.
[50] Chong Zhang,Chong-Xun Zheng,Xiao-Lin Yu.Automatic recognition of cognitive fatigue from physiological indices by using wavelet packet transform and kernel learning algorithms [J].Expert Systems with Applications,2009,36:4664-4671.
[51]雷振山.LabVIEW 7 Express实用技术教程[M].北京:中国铁道出版社,2004:207-242.
[2] Edwards R.Human muscle function and fatigue [M].Ciba:Springer-Verlag,1982.1-18.
[3] Booth F,Thomason D.Molecular and cellular adaptation of muscle in response to exercise:perspectives of various models [J].Physiol Rev,1991,71(5):541-585.
[4] Gandevia SC.Spinal and supraspinal factors in human muscle fatigue [J].Physiol Rev,2002,81(23):1725-1789.
[5] Layzer RB.Asthenia and chronic fatigue syndrome [J].Muscle Nerve,1998,21(12):1609-1611.
[6] Kai-Quan Shen,Xiao-Ping Li,Chong-Jin Ong.EEG-based mental fatigue measurement using multi-class support vector machines with confidence estimate [J].Clinical Neurophysiology 2008,119:1524-1533.
[7] Maarten A.S. Boksem,Theo F. Meijman,Monicque M. Lorist.Mental fatigue,motivation and action monitoring [J].Biological Psychology 2006,72:123-132.
[8]鲍德国.疲劳的诊断[J].全科医学临床与教育,2005,3(3):136-138.
[9]王天芳,薛晓琳.疲劳自评量表[J].中华中医药杂志,2009,24(3):348-349.
[10] LU Zhiqiang,Dong Hai.Human Factors[M].Beijing:Mechanical Industry Press,2006:53-58.
[11] MU Yongge,HE Zhongli,WU Xiaolan,etal.Study of local muscle fatigue monitoring by surface myoelectric signal [J].Journal of Jilin Military Medical College Fourth Military Medical University,1999,21(3):127-130.
[12] Cai Qiming.Study on methods of evaluating physical fatigue according to dynamic heart rate [J].Chinese Ergonomics,1999,5(1):27-29.
[13] Cao Xueliang,Miao Danmin,Liu Lianhong.Assessment methods on mental fatigue.Fourh MilMed Univ,2006,27(4):382-384.
[14] Hu Wenqiang,Ma Jin,Han Wendong.Prevention and monitoring means of flying fatigue [J].Chinese Journal of Clinic Rehabilitation,2004,8(3):542-543.
[15]张连毅,郑崇勋.EEG柯尔莫哥洛夫熵测度用于精神疲劳状态的研究[J].中国生物医学工程学报,2007,2(2):170-176.
[16] Atsuo M,Atsushi U,Yosuke T.Evaluation of mental fatigue using feature parameter extracted from event-related potential [J].International Journal of Industrial Ergonomics,2005,35(8):761.
[17] Boksem MAS,Meijman TF,Lorist MM.Effects of mental fatigue on attention:an ERP study [J].Cognitive Brain Reasearch,2005,25(1):107.
[18]赵春临,郑崇勋,赵敏.基于核学习算法的驾驶精神疲劳分级研究[J].数据采集与处理,2009,24(3):335-339.
[19]杜树新,吴铁军.模式识别中的支持向量机方法[J].浙江大学学报(工学版),2003,37(5):521-527.
[20]赵晖,荣莉莉,李晓.一种设计层次支持向量机多类分类器的新方法[J].计算机应用研究,2003,(5):34-37.
[21]张崇,郑崇勋.生理性精神疲劳的多参数脑电功率谱分析[J].生物医学工程杂志,2009,26(1):162-166.
[22]吴克俭.临床脑电速成指南[M].上海:第二军医大学出版社,2002.
[23]尧得中.脑功能探测的电学理论与方法[M].北京:科学出版社,2003.
[24]曾远明,李长清,胡常林.脑电超慢涨落图的正常参考值[J].现代医药卫生,2004,20(15):1522-1523.
[25]孙久荣.脑科学导论[M].北京:北京大学出版社,2001:15-51.
[26]赵仑.ERP实验教程[M].天津:天津社会科学院出版社,2004:0-12.
[27]陈兴时,张明岛.脑诱发电位形成的可能机制[J].神经病学与神经康复学杂志,2006,3(2):124-125.
[28] Ogura C,Koga Y,Shimokochi M,ed.Recent advances in event related brain potential research[M].Amsterdam:Elsevier,2003:765-779.
[29] Le Bihan D,Tezzard P,Haxby J,etal.Functional magnetic resonance imaging of the brain [J].Annals Internol Medicine,1995,122:296-303.
[30]何庆华,彭承琳,吴宝明.脑机接口技术研究方法[J].重庆大学学报,2002,25(12):106-109.
[31]万博坤,高扬,赵丽等.脑—机接口:大脑对外信息交流的新途径[J].国外医学生物医学工程分册,2005,28(1):4-9.
[32] Lorist MM,Klein M.Mental fatigue and task control:planning and preparation [J].Int J Psychophysiology,2000,37(1):1-12.
[33] Stipacek A,Grabner RH,Neuper C.Sensitivity of human EEG alpha band desynchronization to different working memory components and increasing levels of memory load [J].Neuroscience Letters 2003,353:193-196.
[34] Jonathan R.,Wolphaw,etal.Brain-computer interface research at the wadsworth center [J].IEEE Transactions on Rehabilitation Engineering,2000,8(2):222-226.
[35]谢勤岚,杨仲乐.基于IR-ERP的脑-机接口的结构与原理[J].武汉理工大学学报(交通科学与工程版),2003.
[36]万柏坤,高扬,赵丽,綦宏志.脑-机接口:大脑对外信息交流的新途径[J].国外医学生物工册,2005,28(1):4-9.
[37]伍业舟,吴宝明,何庆华.基于脑电的脑-机接口系统研究现状[J].中国临床康复,2006,10(1):147-150.
[38] Ming Cheng,Xiaorong Gao,Shangkai Gao,Dingfeng Xu.Design and Implementation of a Brain-Computer Intereface With High Transfer Rates [J].IEEE Traps Biomed.Eng,2002,49(10):1181-1186.
[39] Aleksander,Kostov&Mark,Polak.Parrallel.Man-Machine Training in Development of EEG-Based Cursor control[J].IEEE Trans.Rehab.Eng,2000,8(2):203-204.
[40] Wu Ting,Yan Guo-zheng,Yang Bang-hua.EEG feature extraction based on wavelet packet decomposition for brain computer interface [J].Measurement 2008.41:618-625.
[41] Josefina Gutierrez,Rogelio Alcantara,Veronica Medina.Analysis and localization of epileptic events using wavelet packets [J].Medical Engineering & Physics,2001,23:623-631.
[42]张德丰.MATLAB小波分析[M].北京:机械工业出版社,2009:49-181.
[43]李安贵,张志宏,段凤英.模糊数学及其应用[M].北京:冶金工业出版社,1994:1-20.
[44]陈守煜.工程模糊集理论与应用[M].北京:国防工业出版社,1998:24-217.
[45]张彩庆,林明,戚若男.基于模糊模式识别的燃煤电厂大气质量评价[J].中国电机工程学报,2009,29(29):30-34.
[46] Ada W.S. Leung,Chetwyn C.H,Chan,Jimmy J.M. Factors contributing to officers’fatigue in high-speed maritime craft operations [J].Applied Ergonomics,2006,37:565-576.
[47]杨建国.小波分析及其工程应用[M].北京:机械工业出版社,2005:85-178.
[48]徐宝国,宋爱国.基于小波包变换和聚类分析的脑电信号识别方法[M].仪器仪表学报,2009,30(1):25-28.
[49] Patricia Tassi,Anne Bonnefond,Ophelie Engasser.EEG spectral power and cognitive performance during sleep inertia:The effect of normal sleep duration and partial sleep deprivation [J].Physiology & Behavior,2006,87:177-184.
[50] Chong Zhang,Chong-Xun Zheng,Xiao-Lin Yu.Automatic recognition of cognitive fatigue from physiological indices by using wavelet packet transform and kernel learning algorithms [J].Expert Systems with Applications,2009,36:4664-4671.
[51]雷振山.LabVIEW 7 Express实用技术教程[M].北京:中国铁道出版社,2004:207-242.