低觉醒脑电识别与唤醒的可穿戴系统研究
|
摘要
为智能化地识别警戒作业人员出现的低觉醒、注意力下降的生理状态,本文介绍了一种基于FPGA和脑电信号处理的低觉醒状态检测与唤醒系统,系统通过传感器从大脑头皮采集脑电信号,转换为数字信号,经傅里叶变换获取了脑电信号的θ相对能量、α相对能量、重心频率、谱熵等4个特征量,由4个特征量表征低觉醒状态并运用支持向量机对低警戒状态进行识别,当识别出低觉醒状态时采用声音报警模块发出声音,唤醒警戒作业人员。设计系统能够较好地识别出低觉醒状态,识别率达90.8%,可为提高警戒作业工作绩效提供一种可穿戴的智能装备。
To intelligently identify the physiological state of vigilance workers with low awakening and low attention,this paper presents a monitoring and awakening system for low arousal/vigilance state based on the field-programmable gate array(FPGA) and electroencephalogram(EEG) signals processing. The system collects EEG signals from the scalp,converts the analog signals to digital signals, and then uses Fourier transform to calculate its power spectrum. The system subsequently acquires four eigenvectors—the relative energies of the θ and α, the gravity frequency, and the spectrum entropy—which are used to characterize the low arousal state, and on this basis, the support vector machine(SVM)is used to recognize the low arousal state. Once the low arousal state is identified, the SVM will awaken the vigilance worker using a sound alarm module. The system can effectively distinguish the low awakening state, and the recognition rate reaches 90.8%. Moreover, it can provide a wearable intelligent equipment to improve performance of vigilance operations.
To intelligently identify the physiological state of vigilance workers with low awakening and low attention,this paper presents a monitoring and awakening system for low arousal/vigilance state based on the field-programmable gate array(FPGA) and electroencephalogram(EEG) signals processing. The system collects EEG signals from the scalp,converts the analog signals to digital signals, and then uses Fourier transform to calculate its power spectrum. The system subsequently acquires four eigenvectors—the relative energies of the θ and α, the gravity frequency, and the spectrum entropy—which are used to characterize the low arousal state, and on this basis, the support vector machine(SVM)is used to recognize the low arousal state. Once the low arousal state is identified, the SVM will awaken the vigilance worker using a sound alarm module. The system can effectively distinguish the low awakening state, and the recognition rate reaches 90.8%. Moreover, it can provide a wearable intelligent equipment to improve performance of vigilance operations.
引文
[1]程文东,付锐,袁伟,等.驾驶人疲劳监测预警技术研究与应用综述[J].中国安全科学学报,2013,23(1):155-160.CHENG Wendong,FU Rui,YUAN Wei,et al.Overview of researches on driver fatigue monitoring and prewarning technologies and their applications[J].China safety science journal,2013,23(1):155-160.
[2]祝宇虹,刘海平,查富生,等.基于呼吸信号的驾驶员疲劳状态实时监测系统[J].江南大学学报(自然科学版),2014,13(1):55-59.ZHU Yuhong,LIU Haiping,ZHA Fusheng,et al.Realtime monitoring system for driver's fatigue states based on respiratory signal[J].Journal of Jiangnan University(natural science edition),2014,13(1):55-59.
[3]张淑清,上官寒露,袁计委,等.基于内禀模态能量比呼吸信号特征参数提取方法[J].仪器仪表学报,2010,31(8):1706-1711.ZHANG Shuqing,SHANGGUAN Hanlu,YUAN Jiwei,et al.Study on the extraction method of characteristic parameters of respiration signals based on intrinsic mode energy ratio[J].Chinese journal of scientific instrument,201 0,31(8):1706-1711.
[4]杨英,盛敬,杨佳,等.基于神经网络的驾驶员觉醒水平双目标监测法[J].东北大学学报(自然科学版),2007,28(3):418-421.YANG Ying,SHENG Jing,YANG Jia,et al.Double-objective detection based on neural network for driver's alert level[J].Journal of Northeastern University(natural science),2007,28(3):418-421.
[5]高春芳,吕宝粮,马家昕.一种用小波包变换提取眼电信号警觉度特征的方法[J].中国生物医学工程学报,2012,31(5):641-648.GAO Chunfang,LYU Baoliang,MA Jiaxin.A new method of extracting vigilant feature from electrooculography using wavelet packet transform[J].Chinese j ournal of biomedical engineering,2012,31(5):641-648.
[6]LEE B G,PARK J H,PU C C,et al.Smartwatch-based driver vigilance indicator with kernel-fuzzy-C-meanswavelet method[J].IEEE sensors journal,2016,16(1):242-253.
[7]BALASUBRAMANIAN V, ADALARASU K.EMGbased analysis of change in muscle activity during simulated driving[J].Journal of bodywork and movement therapies,2007,11(2):151-158.
[8]齐晴,高举,王敏,等.融合视频与生物电信息的驾驶员状态监测与预警系统[J].工业控制计算机,2016,29(12):71-73.QI Qing,GAO Ju,WANG Min,et al.Driving state monitoring and warning system by video and bio-electricity information[J].Industrial control computer,201 6,29(12):71-73.
[9]SUBASI A.Automatic recognition of alertness level from EEG by using neural network and wavelet coefficients[J].Expert systems with applications,2005,28(4):701-711.
[10]RESALAT S N,SABA V.A practical method for driver sleepiness detection by processing the EEG signals stimulated with external flickering light[J].Signal,image and video processing,2015,9(8):1751-1757.
[11]BAKE L,GYORGY-MOZES E, BRASSAI S T,et al,Neural network parallelization on FPGA platform for EEG signal classification[C]//Proceedings of the 6th Edition of the Interdisciplinarity in Engineering International Conference.Romania,2012.
[12]CORTES C,VAPNIK V.Support-vector networks[J].Machine learning,1995,20(3):273-297.
[13]AN Senjian,LIU Wanquan,VENKATESH S.Fast crossvalidation algorithms for least squares support vector machine and kernel ridge regression[J].Pattern recognition,2007,40(8):2154-2162.
[14]刘佳兴,王炜.基于多参数融合的疲劳驾驶监测及预警系统[J].计算机仿真,2013,30(5):171-175,207.LIU Jiaxing,WANG Wei.Driver fatigue monitoring and warning system based on multi-parameter fusion[J].Computer simulation,2013.30(5):171-175,207.
[2]祝宇虹,刘海平,查富生,等.基于呼吸信号的驾驶员疲劳状态实时监测系统[J].江南大学学报(自然科学版),2014,13(1):55-59.ZHU Yuhong,LIU Haiping,ZHA Fusheng,et al.Realtime monitoring system for driver's fatigue states based on respiratory signal[J].Journal of Jiangnan University(natural science edition),2014,13(1):55-59.
[3]张淑清,上官寒露,袁计委,等.基于内禀模态能量比呼吸信号特征参数提取方法[J].仪器仪表学报,2010,31(8):1706-1711.ZHANG Shuqing,SHANGGUAN Hanlu,YUAN Jiwei,et al.Study on the extraction method of characteristic parameters of respiration signals based on intrinsic mode energy ratio[J].Chinese journal of scientific instrument,201 0,31(8):1706-1711.
[4]杨英,盛敬,杨佳,等.基于神经网络的驾驶员觉醒水平双目标监测法[J].东北大学学报(自然科学版),2007,28(3):418-421.YANG Ying,SHENG Jing,YANG Jia,et al.Double-objective detection based on neural network for driver's alert level[J].Journal of Northeastern University(natural science),2007,28(3):418-421.
[5]高春芳,吕宝粮,马家昕.一种用小波包变换提取眼电信号警觉度特征的方法[J].中国生物医学工程学报,2012,31(5):641-648.GAO Chunfang,LYU Baoliang,MA Jiaxin.A new method of extracting vigilant feature from electrooculography using wavelet packet transform[J].Chinese j ournal of biomedical engineering,2012,31(5):641-648.
[6]LEE B G,PARK J H,PU C C,et al.Smartwatch-based driver vigilance indicator with kernel-fuzzy-C-meanswavelet method[J].IEEE sensors journal,2016,16(1):242-253.
[7]BALASUBRAMANIAN V, ADALARASU K.EMGbased analysis of change in muscle activity during simulated driving[J].Journal of bodywork and movement therapies,2007,11(2):151-158.
[8]齐晴,高举,王敏,等.融合视频与生物电信息的驾驶员状态监测与预警系统[J].工业控制计算机,2016,29(12):71-73.QI Qing,GAO Ju,WANG Min,et al.Driving state monitoring and warning system by video and bio-electricity information[J].Industrial control computer,201 6,29(12):71-73.
[9]SUBASI A.Automatic recognition of alertness level from EEG by using neural network and wavelet coefficients[J].Expert systems with applications,2005,28(4):701-711.
[10]RESALAT S N,SABA V.A practical method for driver sleepiness detection by processing the EEG signals stimulated with external flickering light[J].Signal,image and video processing,2015,9(8):1751-1757.
[11]BAKE L,GYORGY-MOZES E, BRASSAI S T,et al,Neural network parallelization on FPGA platform for EEG signal classification[C]//Proceedings of the 6th Edition of the Interdisciplinarity in Engineering International Conference.Romania,2012.
[12]CORTES C,VAPNIK V.Support-vector networks[J].Machine learning,1995,20(3):273-297.
[13]AN Senjian,LIU Wanquan,VENKATESH S.Fast crossvalidation algorithms for least squares support vector machine and kernel ridge regression[J].Pattern recognition,2007,40(8):2154-2162.
[14]刘佳兴,王炜.基于多参数融合的疲劳驾驶监测及预警系统[J].计算机仿真,2013,30(5):171-175,207.LIU Jiaxing,WANG Wei.Driver fatigue monitoring and warning system based on multi-parameter fusion[J].Computer simulation,2013.30(5):171-175,207.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |