基于最小二乘支持向量机方法的复杂人机系统操作员功能状态建模与预测
|
摘要
对人机系统操作员功能状态(Operator Functional States, OFS)进行准确评估的关键在于建立具有很强预测能力的数学模型。本文基于采集到的一系列操作员电生理信号及性能数据,采用最小二乘支持向量机(Least Squares Support Vector Machine, LS-SVM)方法对OFS建模。通过网格搜索(Grid Search)和10-折交叉验证(10-fold cross-validation)方法对模型参数进行优化,针对标准LS-SVM的不足,采用Suykens提出的LS-SVM的改进算法,建立了具有稀疏性和鲁棒性的LS-SVM模型,并将LS-SVM与基于遗传算法的模糊建模方法进行结果比较。结果表明,LS-SVM方法具有更好的泛化性能,将其用于OFS评估是有效的。根据模型预测结果,便可以调整控制策略,从而设计和实现智能化人机交互系统。
The core problem of estimating Operator Functional State (OFS) in human-machine systems is construction of an appropriate mathematical model.This paper adopts Least Squares Support Vector Machine (LS-SVM) for OFS modeling based on a series of electrophysiological signals and operator performance data. model parameters are optimized by grid-search and 10-fold cross validation,and we get spare and robust model use modified LS-SVM algorithm proposed by Suykens.The simulation results show that LS-SVM has better generalization performance than GA-Mamdani,and it is efficient and feasible for OFS estimation use LS-SVM. The final model based on the results is used to adjust control strategies, achieving intelligent human-computer interaction.
The core problem of estimating Operator Functional State (OFS) in human-machine systems is construction of an appropriate mathematical model.This paper adopts Least Squares Support Vector Machine (LS-SVM) for OFS modeling based on a series of electrophysiological signals and operator performance data. model parameters are optimized by grid-search and 10-fold cross validation,and we get spare and robust model use modified LS-SVM algorithm proposed by Suykens.The simulation results show that LS-SVM has better generalization performance than GA-Mamdani,and it is efficient and feasible for OFS estimation use LS-SVM. The final model based on the results is used to adjust control strategies, achieving intelligent human-computer interaction.
引文
[1]G. R. J. Hockey. Operator functional state:The Assessment and Prediction of Human Performance Degradation in Complex Tasks [M]. US:IOS Press,2003
[2]Yukiyu Kuriyagawa, Ichiro Kageyama. "A modeling of heart rate variability to estimate mental work load"-Systems, Man, and Cybernetics,1999 IEEE SMC 99 Conference Proceedings.1999 IEEE International
[3]M. Tkahashi,O. Kubo, H. Yoshikawa. Mutual Adaptive Interface:Basic Concepts. Robot and Human Communication,1993. Proceedings.2nd IEEE International Workshop on.
[4]Vapnik Vladimir N. The Nature of Statistical Learning Theory. Berlin:Springer,1995
[5]M. Takahashi et al. Development of Realtime Cognitive State Estimator, Pm. of 12th World Congress of International Federation of Automatic Control.1993,7:219-222
[6]苏令波.电气操作运行人员的心理负荷研究.北京交通大学硕士论文.2006,12
[7]G. F. Wilson, F. Fisher.The use of cardiac and eye blink measures to determine flight segment in F4 crews. Aviation, Space and Environmental Medicine.1991,62:959-961
[8]G. Conway. Effects of workload, effort and fatigue on complex performance: application and tests of compensatory.PhD Thesis, University of Leeds,2005
[9]G. F. Wilson, F. Fisher. Cognitive task classification based upon topographic EEG data. Biological Psychology.1995,40:239-250
[10]A. Gevins, M. ESmith, H. Leong. Monitoring working memory load during computer-based tasks with EEG pattern recognition methods. Human Factors.1998,40:79-91
[11]C. A. Russell, G. F. Wilson. Air traffic controller functional state classification using neural networks. Proc of the Artificial Neural Networks in Engineering Conference. 1998,8:649-654
[12]G. F. Wilson, F. T. Eggemerier. Physiological measures of workload in multi-task environments, in Damos D. Multiple-task Performance.1991,329-360
[13]A. Gevins, M. E. Smith. Detecting transient cognitive impairment with EEG pattern recognition methods. Aviation, Space and Environmental Medicine.1999,70: 1018-1024
[14]C. Dussault, J. C. Jouanin, C. Y. Guezennec. EEG and ECG changes during selected flight sequences. Aviat Space Environ Med 2004.75(10):889-97
[15]C. Dussault, J. C. Jouanin, M. Philippe et al. EEG and ECG changes during simulator operation reflect mental workload and vigilance. Aviat Space Environ Med.2005, 76(4):344-51
[16]A. R. Nikolaev, G. A. Ivanitskii, A. M. Ivanitskii.Reproducible EEG alpha-patterns in psychological task solving. Human Physiology.1998,24:261-268
[17]J. R. Comstock, R. J. Arnegard.The Multi-Attribute Task Battery for Human Operator Workload and Strategic Behavior Research. NASA Tech.Memo.1992
[18]A. T. Pope,E. H. Bogart,D. S. Bartolome.Biocybernetic system evaluates indices of operator engagerment in automated task. Biological Psychology.1995,40:187-195
[19]F. G. Freedman, P. J. Mikulka, L. J. Prinzel et al. Evaluation of an adaptive automation system using three EEG indices with a visual tracking task. Biological Psychology. 1999,50:61-76
[20]G. F. Wilson.Operator functional state classification using neural networks with combined psychological and performance measures. Proc of the 43 rd HFES Annual Meeting.1999,1099-1102
[21]许亚洲.基于最小二乘支持向量机的数控机床热误差建模的研究.浙江大学硕士论文.2006,08
[22]张敏贵,潘泉,张洪才.基于支持向量机的人脸分类[J].计算机工程.2004,(11)：110-112
[23]ChiH-Wei Hsu,Chih-jen.A comparison of methods for multiclass support vector machines[J].IEEE Trans.on Neural Networks.2002,13(2):415-425
[24]Vapnik Vladimir N著,许建华,张学工译.统计学习理论[M].北京：电子工业出版社,2009,3：55-57
[25]邓乃扬,田英杰.数据挖掘中的新方法-支持向量机.北京：科学出版社,2004
[26]边肇棋,张学工.模式识别.清华大学出版社,北京,2000
[27]Vapnik.The nature of statistical learning theory. New York:Springer Verlag,1995
[28]Vapnik Vladimir N著,许建华,张学工译.统计学习理论[M].北京：电子工业出版社,2004,6
[29]万仲平,费浦生.优化理论与方法[M].武汉大学出版社,2004
[30]寇述舜.凸分析与凸二次规划[M].天津大学出版社,1994
[31]R. Horst, P. Pardalos, N. Thoai. Introduction to global optimization[M].New York: Kluwer Academic Publishers,1995
[32]M. Walk.Theory of duality in mathematical programming[M]. New York:Springer Verlag,1989
[33]Vapnik Vladimir N著,张学工译.统计学习理论的本质[M].清华大学出版社,2000,9
[34]Vapnik.Statistical Learning Theory[M].New York:Wiley,1998
[35]Vapnik.The Nature of Statistical Learning Theory[M].2nd edition. New York:Springer Verlag,1999
[36]王建芬,曹元大.支持向量机在大类别分类中的应用.北京理工大学学报,2001,21(2)：225-228
[37]D. Tax, R. Duin. Data domain description by support vectors. In Proc. ESANN, M.Verleysen, editor,Brussels:D.Facto Press,1999:251-256
[38]V. David, A. Sanchez. Advanced support vector machine and kernel methods [J]. Neurocmputing.2003(55)
[39]J. B. Gaoa, S. R. Gummb, C. J. Harrisb. SVM regression through variational methods and its sequential implementation [J]. Neurocmputing.2003(55)
[40]Jinbo Bi, Kristin, P. Bennett. A geometric approach to support vector regression[J]. Neurocmputing.2003(55)
[41]林成森.数值计算方法[M].科学出版社,2005
[42]J. A. K. Suykens, J. Vandewalle.Least squares support vector machine classifiersfJ]. Neural Processing Letters.1999,9(3):293-300
[43]B. Scholkoph, A. J. Smola, P. L. Bartlett.New support vector algorithms [J]. Neural Computation.2000,12:1207-1245
[44]C. F. Lin, S. D. Wang. Fuzzy support vector machines[J].IEEE Trans on Neural Networks.2002,13(2):464-471
[45]F. E. H. Tay, L. J. Cao.Modified support vector machines in financial time series forecasting[J], Neurocomputing.2002,48:847-861.
[46]J. C. Platt. Fast training of SVM:Using Sequential Minimal Optimization[M].IN:B. Scholkph et al. Advances in Kernal Method-Support Vector Learning.Cambridge, MA: MIT Press,1998,185-208
[47]C. Cortes, V. Vapnik. Support Vector Nerworks[J].Machine Learning.1995,20:273-297
[48]E. Osuna,R. Freund,F. Girosi. An improved training algorithm for support vector machines[A].Proceedings of the 1997 IEEE Workshop on Neural Netwoks for Signal Processing[C].New York:IEEE Press,1997,276-285
[49]E. Osuna, R. Freund, F. Girosi.Training support vector machines:Application to face detection[A].1997 Conference on Computer Vision and Pattern Recognition[C]. Puerto Rico:IEEE Press,1997
[50]J. A. K. Suykens.Nonlinear modeling and support vector machines, IEEE Instrumentation and measurement technology conference, Budapest, Hungary, May 2001,297-294
[51]J. A. K. Suykens, T. Van Gestel, J. De Brabanter et. al. Least squares support vector machines. Singapore:World Scientific Publishing Co., Pte, Ltd,2002
[52]J. Nocedal, S. J. Wright. Numerical Optimization. Springer Verlag,1999
[53]J. A. K. Suykens, J. De Brabanter, L. Lukas et al. Weighted least squares support vector machines:robustness and sparse approximation. Neurocomputing.2002,48(1-4): 85-105
[54]J. A. K. Suykens, L. Lukas, J. Vandewalle. Sparse least squares support vector machines classifiers, European Symposium on Artificial Neural Networks, Bruges Belgium, 2000(4):37-42
[55]P. J. Rousseeuw, A. Leroy. Robust regression and outlier detection. NewYork:Wiley, 1987
[56]F. R. Hampel, P. J. Rousseeuw, W. A. Stahel.Robust statistic, the Approach based on influence functions. New York:John Wiley,1986
[57]M. W. Browne.Cross-Validation Method. Journal of Mathematical Psychology.2000, 44:108-132
[58]王兴玲,李占斌.基于网格搜索的支持向量机核函数参数的确定.中国海洋大学学报.2005,35(5)：859-862
[59]董明清,马瑞山.脑力负荷评定指标敏感性的比较研究.航天医学与医学工程.1999,12(2)：106-110
[60]闫春红.心率变异性非线性动力学分析的研究.重庆大学硕士学位论文.2004
[61]P. G. N. A. Jorna. "Heart rate and workload variations in actual and simulated flight" Ergonomics.1993,36(9):1043-1054
[62]C. D. Wickens, J. Goh, J. Helleberg et al.(2003). Attentional models of multi-task pilot performance using advanced display technology.Human Facrors.45,360-380
[63]G. R. J. Hockey, D. G. Wastell, J. Sauer.Effects of sleep deprivation and user-interface on complex performance:A multilevel analysis of compensatory control [J]. Human Factors.1998,40,233-253
[64]H. H. Jasper.Report of the committee on methods of clinical examination in electroencephalography [J]. Electroencephalography and Clinical Neurophysiology, vol. 10,1958,370-375
[65]P. Nickel, A. C. Roberts and G. R. J. Hockey,"Assessment of high risk operator functional state markers in dynamical systems-preliminary resultsand implications" in Proc. of Human Factors and Ergonomics Society Europe Chapter Annual Meeting2005, Turin, Italy, Oct.26-28,2005
[66]Jian-Hua Zhang, A. Nassef, M. Mahfouf et al. "Modeling and analysis of HRV under physical and mental workloads", in Proc. of the 6th IFAC Symposium on Modeling and Control in Biomedical Systems, Reims, France.2006,9:189-194
[67]Jian-Hua Zhang, Xing-Yu Wang, M. Mahfouf et al. Use of Heart Rate Variability Analysis for Quantitatively Assessing Operator's Mental Workload, in BMEI (1) 2008, 668-672
[68]Ian H.Witten & Eibe Frank.Data著,董琳等译.数据挖掘：实用机器学习技术(原书第2版).2006,149-150
[69]Jian-Hua Zhang, Xing-Yu Wang, M. Mahfouf et al. Fuzzy Logic based Identification of Operator Functional StatesUsing Multiple Physiological and Performance Measures, in BMEI(1),2008,181
[70]彭小迪,张建华,王行愚,王娆芬.基于遗传算法的操作员功能状态模糊建模.《电子测量与仪器学报》,2009,27-30
[71]Zhifeng Hao, Shu Yu, Xiaowei Yang et al. Online LS-SVM Learning for Classification Problems Based on Incremental Chunk[C]. F.Yin, J. Wang, and C. Gan (Eds), International Symposium Neural Networks, Dalian,China,2004, LNCS 3173:558-564
[72]张浩然,汪晓东.回归最小二乘支持向量机的增量和在线式学习算法[J].计算机学报.2006,29(3)：400-406
[73]田翔,邓飞其.支持向量机参数选择及训练算法研究.2006
[2]Yukiyu Kuriyagawa, Ichiro Kageyama. "A modeling of heart rate variability to estimate mental work load"-Systems, Man, and Cybernetics,1999 IEEE SMC 99 Conference Proceedings.1999 IEEE International
[3]M. Tkahashi,O. Kubo, H. Yoshikawa. Mutual Adaptive Interface:Basic Concepts. Robot and Human Communication,1993. Proceedings.2nd IEEE International Workshop on.
[4]Vapnik Vladimir N. The Nature of Statistical Learning Theory. Berlin:Springer,1995
[5]M. Takahashi et al. Development of Realtime Cognitive State Estimator, Pm. of 12th World Congress of International Federation of Automatic Control.1993,7:219-222
[6]苏令波.电气操作运行人员的心理负荷研究.北京交通大学硕士论文.2006,12
[7]G. F. Wilson, F. Fisher.The use of cardiac and eye blink measures to determine flight segment in F4 crews. Aviation, Space and Environmental Medicine.1991,62:959-961
[8]G. Conway. Effects of workload, effort and fatigue on complex performance: application and tests of compensatory.PhD Thesis, University of Leeds,2005
[9]G. F. Wilson, F. Fisher. Cognitive task classification based upon topographic EEG data. Biological Psychology.1995,40:239-250
[10]A. Gevins, M. ESmith, H. Leong. Monitoring working memory load during computer-based tasks with EEG pattern recognition methods. Human Factors.1998,40:79-91
[11]C. A. Russell, G. F. Wilson. Air traffic controller functional state classification using neural networks. Proc of the Artificial Neural Networks in Engineering Conference. 1998,8:649-654
[12]G. F. Wilson, F. T. Eggemerier. Physiological measures of workload in multi-task environments, in Damos D. Multiple-task Performance.1991,329-360
[13]A. Gevins, M. E. Smith. Detecting transient cognitive impairment with EEG pattern recognition methods. Aviation, Space and Environmental Medicine.1999,70: 1018-1024
[14]C. Dussault, J. C. Jouanin, C. Y. Guezennec. EEG and ECG changes during selected flight sequences. Aviat Space Environ Med 2004.75(10):889-97
[15]C. Dussault, J. C. Jouanin, M. Philippe et al. EEG and ECG changes during simulator operation reflect mental workload and vigilance. Aviat Space Environ Med.2005, 76(4):344-51
[16]A. R. Nikolaev, G. A. Ivanitskii, A. M. Ivanitskii.Reproducible EEG alpha-patterns in psychological task solving. Human Physiology.1998,24:261-268
[17]J. R. Comstock, R. J. Arnegard.The Multi-Attribute Task Battery for Human Operator Workload and Strategic Behavior Research. NASA Tech.Memo.1992
[18]A. T. Pope,E. H. Bogart,D. S. Bartolome.Biocybernetic system evaluates indices of operator engagerment in automated task. Biological Psychology.1995,40:187-195
[19]F. G. Freedman, P. J. Mikulka, L. J. Prinzel et al. Evaluation of an adaptive automation system using three EEG indices with a visual tracking task. Biological Psychology. 1999,50:61-76
[20]G. F. Wilson.Operator functional state classification using neural networks with combined psychological and performance measures. Proc of the 43 rd HFES Annual Meeting.1999,1099-1102
[21]许亚洲.基于最小二乘支持向量机的数控机床热误差建模的研究.浙江大学硕士论文.2006,08
[22]张敏贵,潘泉,张洪才.基于支持向量机的人脸分类[J].计算机工程.2004,(11)：110-112
[23]ChiH-Wei Hsu,Chih-jen.A comparison of methods for multiclass support vector machines[J].IEEE Trans.on Neural Networks.2002,13(2):415-425
[24]Vapnik Vladimir N著,许建华,张学工译.统计学习理论[M].北京：电子工业出版社,2009,3：55-57
[25]邓乃扬,田英杰.数据挖掘中的新方法-支持向量机.北京：科学出版社,2004
[26]边肇棋,张学工.模式识别.清华大学出版社,北京,2000
[27]Vapnik.The nature of statistical learning theory. New York:Springer Verlag,1995
[28]Vapnik Vladimir N著,许建华,张学工译.统计学习理论[M].北京：电子工业出版社,2004,6
[29]万仲平,费浦生.优化理论与方法[M].武汉大学出版社,2004
[30]寇述舜.凸分析与凸二次规划[M].天津大学出版社,1994
[31]R. Horst, P. Pardalos, N. Thoai. Introduction to global optimization[M].New York: Kluwer Academic Publishers,1995
[32]M. Walk.Theory of duality in mathematical programming[M]. New York:Springer Verlag,1989
[33]Vapnik Vladimir N著,张学工译.统计学习理论的本质[M].清华大学出版社,2000,9
[34]Vapnik.Statistical Learning Theory[M].New York:Wiley,1998
[35]Vapnik.The Nature of Statistical Learning Theory[M].2nd edition. New York:Springer Verlag,1999
[36]王建芬,曹元大.支持向量机在大类别分类中的应用.北京理工大学学报,2001,21(2)：225-228
[37]D. Tax, R. Duin. Data domain description by support vectors. In Proc. ESANN, M.Verleysen, editor,Brussels:D.Facto Press,1999:251-256
[38]V. David, A. Sanchez. Advanced support vector machine and kernel methods [J]. Neurocmputing.2003(55)
[39]J. B. Gaoa, S. R. Gummb, C. J. Harrisb. SVM regression through variational methods and its sequential implementation [J]. Neurocmputing.2003(55)
[40]Jinbo Bi, Kristin, P. Bennett. A geometric approach to support vector regression[J]. Neurocmputing.2003(55)
[41]林成森.数值计算方法[M].科学出版社,2005
[42]J. A. K. Suykens, J. Vandewalle.Least squares support vector machine classifiersfJ]. Neural Processing Letters.1999,9(3):293-300
[43]B. Scholkoph, A. J. Smola, P. L. Bartlett.New support vector algorithms [J]. Neural Computation.2000,12:1207-1245
[44]C. F. Lin, S. D. Wang. Fuzzy support vector machines[J].IEEE Trans on Neural Networks.2002,13(2):464-471
[45]F. E. H. Tay, L. J. Cao.Modified support vector machines in financial time series forecasting[J], Neurocomputing.2002,48:847-861.
[46]J. C. Platt. Fast training of SVM:Using Sequential Minimal Optimization[M].IN:B. Scholkph et al. Advances in Kernal Method-Support Vector Learning.Cambridge, MA: MIT Press,1998,185-208
[47]C. Cortes, V. Vapnik. Support Vector Nerworks[J].Machine Learning.1995,20:273-297
[48]E. Osuna,R. Freund,F. Girosi. An improved training algorithm for support vector machines[A].Proceedings of the 1997 IEEE Workshop on Neural Netwoks for Signal Processing[C].New York:IEEE Press,1997,276-285
[49]E. Osuna, R. Freund, F. Girosi.Training support vector machines:Application to face detection[A].1997 Conference on Computer Vision and Pattern Recognition[C]. Puerto Rico:IEEE Press,1997
[50]J. A. K. Suykens.Nonlinear modeling and support vector machines, IEEE Instrumentation and measurement technology conference, Budapest, Hungary, May 2001,297-294
[51]J. A. K. Suykens, T. Van Gestel, J. De Brabanter et. al. Least squares support vector machines. Singapore:World Scientific Publishing Co., Pte, Ltd,2002
[52]J. Nocedal, S. J. Wright. Numerical Optimization. Springer Verlag,1999
[53]J. A. K. Suykens, J. De Brabanter, L. Lukas et al. Weighted least squares support vector machines:robustness and sparse approximation. Neurocomputing.2002,48(1-4): 85-105
[54]J. A. K. Suykens, L. Lukas, J. Vandewalle. Sparse least squares support vector machines classifiers, European Symposium on Artificial Neural Networks, Bruges Belgium, 2000(4):37-42
[55]P. J. Rousseeuw, A. Leroy. Robust regression and outlier detection. NewYork:Wiley, 1987
[56]F. R. Hampel, P. J. Rousseeuw, W. A. Stahel.Robust statistic, the Approach based on influence functions. New York:John Wiley,1986
[57]M. W. Browne.Cross-Validation Method. Journal of Mathematical Psychology.2000, 44:108-132
[58]王兴玲,李占斌.基于网格搜索的支持向量机核函数参数的确定.中国海洋大学学报.2005,35(5)：859-862
[59]董明清,马瑞山.脑力负荷评定指标敏感性的比较研究.航天医学与医学工程.1999,12(2)：106-110
[60]闫春红.心率变异性非线性动力学分析的研究.重庆大学硕士学位论文.2004
[61]P. G. N. A. Jorna. "Heart rate and workload variations in actual and simulated flight" Ergonomics.1993,36(9):1043-1054
[62]C. D. Wickens, J. Goh, J. Helleberg et al.(2003). Attentional models of multi-task pilot performance using advanced display technology.Human Facrors.45,360-380
[63]G. R. J. Hockey, D. G. Wastell, J. Sauer.Effects of sleep deprivation and user-interface on complex performance:A multilevel analysis of compensatory control [J]. Human Factors.1998,40,233-253
[64]H. H. Jasper.Report of the committee on methods of clinical examination in electroencephalography [J]. Electroencephalography and Clinical Neurophysiology, vol. 10,1958,370-375
[65]P. Nickel, A. C. Roberts and G. R. J. Hockey,"Assessment of high risk operator functional state markers in dynamical systems-preliminary resultsand implications" in Proc. of Human Factors and Ergonomics Society Europe Chapter Annual Meeting2005, Turin, Italy, Oct.26-28,2005
[66]Jian-Hua Zhang, A. Nassef, M. Mahfouf et al. "Modeling and analysis of HRV under physical and mental workloads", in Proc. of the 6th IFAC Symposium on Modeling and Control in Biomedical Systems, Reims, France.2006,9:189-194
[67]Jian-Hua Zhang, Xing-Yu Wang, M. Mahfouf et al. Use of Heart Rate Variability Analysis for Quantitatively Assessing Operator's Mental Workload, in BMEI (1) 2008, 668-672
[68]Ian H.Witten & Eibe Frank.Data著,董琳等译.数据挖掘：实用机器学习技术(原书第2版).2006,149-150
[69]Jian-Hua Zhang, Xing-Yu Wang, M. Mahfouf et al. Fuzzy Logic based Identification of Operator Functional StatesUsing Multiple Physiological and Performance Measures, in BMEI(1),2008,181
[70]彭小迪,张建华,王行愚,王娆芬.基于遗传算法的操作员功能状态模糊建模.《电子测量与仪器学报》,2009,27-30
[71]Zhifeng Hao, Shu Yu, Xiaowei Yang et al. Online LS-SVM Learning for Classification Problems Based on Incremental Chunk[C]. F.Yin, J. Wang, and C. Gan (Eds), International Symposium Neural Networks, Dalian,China,2004, LNCS 3173:558-564
[72]张浩然,汪晓东.回归最小二乘支持向量机的增量和在线式学习算法[J].计算机学报.2006,29(3)：400-406
[73]田翔,邓飞其.支持向量机参数选择及训练算法研究.2006