基于FPA优化的GP算法的飞行员认知状态识别
|
摘要
飞行员认知状态是影响人机飞行控制系统表现的重要因素。认知状态通常不能被直接测得,需借助于诸多的生理信号间接分析。根据典型生理信号的时频特点,应用小波分析建立信号特征集,并提出了一种基于花粉传播算法的高斯过程分类模型,用以分析全动飞行模拟实验中的飞行员认知状态。通过对比分类结果与飞行员的NASATLX测评结果,验证该模型对飞行员认知状态识别的有效性。
The pilots' cognitive states are essential factors affecting their control performance to the flight control system. Generally,cognitive states can not be measured directly. However,they can be gained indirectly by the means of physiological signals. Based on the characteristics of the physiological signals in time frequency domain,wavelet analysis is used for establishing the feature sets,and an FPA optimized Gaussian Process( GP) model is proposed for classification based on flower pollination algorithm,which is used for analyzing the pilots' cognitive states in a full flight simulation. Through the comparison between the classification results and the NASA-TLX test result of the pilots,the validity of this method is verified.
The pilots' cognitive states are essential factors affecting their control performance to the flight control system. Generally,cognitive states can not be measured directly. However,they can be gained indirectly by the means of physiological signals. Based on the characteristics of the physiological signals in time frequency domain,wavelet analysis is used for establishing the feature sets,and an FPA optimized Gaussian Process( GP) model is proposed for classification based on flower pollination algorithm,which is used for analyzing the pilots' cognitive states in a full flight simulation. Through the comparison between the classification results and the NASA-TLX test result of the pilots,the validity of this method is verified.
引文
[1]AKHANDA M,SIDDIQUE A B,ISLAM S M,et al.Detection of cognitive state for brain-computer interfaces[C]//International Conference on Electrical Information and Communication Technology(EICT),IEEE,2004:1-6.
[2]FIRPI H A,VOGELSTEIN R J.Particle swarm optimizationbased feature selection for cognitive state detection[C]//Annual International Conference of the IEEE,Engineering in Medicine and Biology Society,EMBC,2011:45-52.
[3]WISE J A,HOPKIN V D,GARLAND D J.Hand-book of aviation human factors[M].Boca Raton:CRC Press,2009.
[4]MCDONALD N J,SOUSSOU W.Quasar's qstates cognitive gauge performance in the cognitive state assessment competition 2011[C]//Annual International Conference of the IEEE,Engineering in Medicine and Biology Society,EMBC,2011:23-31.
[5]GEVINS A,SMITH M E.Neurophysiological measures of working memory and individual differences in cognitive ability and cognitive style[J].Cerebral Cortex,2000,10(1):829-839.
[6]MAKEIG S,JUNG T P.Changes in alertness are a principal component of variance in the EEG spectrum[J].Neuroreport,1995,7(1):213-216.
[7]GARAVAN H,ROSS T J,LI S J.A para-metric manipulation of central executive functioning[J].Cerebral Cortex,2000,10(1):585-592.
[8]THORPE S,FIZE D,MARLOT C.Speed of processing in the human visual system[J].Nature,1996,381:520-522.
[9]VERWEY W B,VELTMAN H A.Detecting short periods of elevated workload:a comparison of nine workload assessment techniques[J].Journal of Experimental Psychology:Applied,1996,2(1):270-283.
[10]VERWEY W B,GAILLARD A W K.Physiological workload reactions to increasing levels of task difficulty[J].Ergonomics,1998,41(5):656-669.
[11]PATEL M,LAL S K L,KAVANAGH D.Applying neural network analysis on heart rate variability data to assess driver fatigue[J].Expert Systems with Applications,2011,38(5):7235-7242.
[12]NEUMANN D L.Effect of varying levels of mental workload on startle eyeblink modulation[J].Ergonomics,2002,45(8):583-602.
[13]PARTALA T,SURAKKA V.Pupil size variation as an indication of affective processing[J].International Journal of Human-Computer Studies,2003,59(1):185-198.
[14]彭葳,王笃明,尹爽,等.驾驶疲劳的心电和肌电信号分析[J].人类工效学,2013,19(1):24-27,75.(PENG W,WANG D M,YIN S,et al.Exploring the characters of physiological signals for fatigued drivers[J].Chinese Journal of Ergonomics,2013,19(1):24-27,75.)
[15]姚永杰,常耀明,吴兴裕,等.歼击机飞行员空中生理参数与飞行状态变化动态对应的可行性研究[J].科技导报,2007,25(16):18-21.(YAO Y J,CHANG Y M,WU X Y,et al.Feasibility study on the correspondence between in-flight physiological parameters of fighter pilot and dynamic flight status parameters[J].Science&Technology Review,2007,25(16):18-21.)
[16]BAFROUI H H,OHADI A.Application of wavelet energy and Shannon entropy for feature extraction in gear-box fault detection under varying speed conditions[J].Neurocomputing,2014,133(8):437-445.
[17]AGNEW C E,HAMILTON P K,MCCANN A,et al.Wavelet entropy of Doppler ultra-sound blood velocity flow waveforms distinguishes nitric oxide-modulated states[J].Ultrasound in Medicine&Biology,2015,41(5):1320-1327.
[18]WANG Y,LI W Z,ZHOU J L,et al.Identification of the normal and abnormal heart sounds using wavelet-time entropy features based on OMS-WPD[J].Future Generation Computer Systems,2014,379(7):488-495.
[19]HE Z,FU L,LIN S,et al.Fault detection and classification in EHV transmission line based on wavelet singular entropy[J].IEEE Transactions on Power Delivery,2010,25(4):2156-2163.
[20]SAMUI A,SAMANTARAY S R.Wavelet singular entropy-based islanding detection in distributed generation[J].IEEE Transactions on Power Delivery,2013,28(1):411-418.
[21]GAETANO A D,RINALDI F,SCIANDRONE M.A patient adaptable ECG beat classifier based on neural networks[J].Applied Mathematics and Computation,2009,213(1):243-249.
[22]POUNGPONSRI S,YU X H.An adaptive filtering approach for electrocardiogram(ECG)signal noise reduction using neural networks[J].Neurocomputing,2013,117(87):206-213.
[23]MEHTA S S,LINGAYAT N S.SVM-based algorithm for recognition of QRS complexes in electrocardiogram[J].IRBM,2008,29(5):310-317.
[24]KOLEY B L,DEY D.Automatic detection of sleep apnea and hypopnea events from single channel measurement of respiration signal employing ensemble binary SVM classifiers[J].Measurement,2013,46(7):2082-2092.
[25]RASMUSSEN C E.Gaussian processes in machine learning[J].Advanced Lectures on Machine Learning,2004,3176(4):63-71.
[26]KEMMLER M,RODNER E,DENZLER J.One-class classification with Gaussian processes[J].Pattern Recognition,2013,46(12):3507-3518.
[27]ZHOU H,WANG L,SUTER D.Human action recognition by feature-reduced Gaussian process classification[J].Pattern Recognition Letters,2009,30(12):1059-1066.
[28]WANG L,LECKIE C A.Improved Gaussian process classification via feature space rotation[J].Neurocompu-ting,2012,83(6):89-97.
[29]YANG X S.Flower pollination algorithm for global optimization[J].Unconventional Computation and Natural Computation,2012,7445(2):242-243.
[2]FIRPI H A,VOGELSTEIN R J.Particle swarm optimizationbased feature selection for cognitive state detection[C]//Annual International Conference of the IEEE,Engineering in Medicine and Biology Society,EMBC,2011:45-52.
[3]WISE J A,HOPKIN V D,GARLAND D J.Hand-book of aviation human factors[M].Boca Raton:CRC Press,2009.
[4]MCDONALD N J,SOUSSOU W.Quasar's qstates cognitive gauge performance in the cognitive state assessment competition 2011[C]//Annual International Conference of the IEEE,Engineering in Medicine and Biology Society,EMBC,2011:23-31.
[5]GEVINS A,SMITH M E.Neurophysiological measures of working memory and individual differences in cognitive ability and cognitive style[J].Cerebral Cortex,2000,10(1):829-839.
[6]MAKEIG S,JUNG T P.Changes in alertness are a principal component of variance in the EEG spectrum[J].Neuroreport,1995,7(1):213-216.
[7]GARAVAN H,ROSS T J,LI S J.A para-metric manipulation of central executive functioning[J].Cerebral Cortex,2000,10(1):585-592.
[8]THORPE S,FIZE D,MARLOT C.Speed of processing in the human visual system[J].Nature,1996,381:520-522.
[9]VERWEY W B,VELTMAN H A.Detecting short periods of elevated workload:a comparison of nine workload assessment techniques[J].Journal of Experimental Psychology:Applied,1996,2(1):270-283.
[10]VERWEY W B,GAILLARD A W K.Physiological workload reactions to increasing levels of task difficulty[J].Ergonomics,1998,41(5):656-669.
[11]PATEL M,LAL S K L,KAVANAGH D.Applying neural network analysis on heart rate variability data to assess driver fatigue[J].Expert Systems with Applications,2011,38(5):7235-7242.
[12]NEUMANN D L.Effect of varying levels of mental workload on startle eyeblink modulation[J].Ergonomics,2002,45(8):583-602.
[13]PARTALA T,SURAKKA V.Pupil size variation as an indication of affective processing[J].International Journal of Human-Computer Studies,2003,59(1):185-198.
[14]彭葳,王笃明,尹爽,等.驾驶疲劳的心电和肌电信号分析[J].人类工效学,2013,19(1):24-27,75.(PENG W,WANG D M,YIN S,et al.Exploring the characters of physiological signals for fatigued drivers[J].Chinese Journal of Ergonomics,2013,19(1):24-27,75.)
[15]姚永杰,常耀明,吴兴裕,等.歼击机飞行员空中生理参数与飞行状态变化动态对应的可行性研究[J].科技导报,2007,25(16):18-21.(YAO Y J,CHANG Y M,WU X Y,et al.Feasibility study on the correspondence between in-flight physiological parameters of fighter pilot and dynamic flight status parameters[J].Science&Technology Review,2007,25(16):18-21.)
[16]BAFROUI H H,OHADI A.Application of wavelet energy and Shannon entropy for feature extraction in gear-box fault detection under varying speed conditions[J].Neurocomputing,2014,133(8):437-445.
[17]AGNEW C E,HAMILTON P K,MCCANN A,et al.Wavelet entropy of Doppler ultra-sound blood velocity flow waveforms distinguishes nitric oxide-modulated states[J].Ultrasound in Medicine&Biology,2015,41(5):1320-1327.
[18]WANG Y,LI W Z,ZHOU J L,et al.Identification of the normal and abnormal heart sounds using wavelet-time entropy features based on OMS-WPD[J].Future Generation Computer Systems,2014,379(7):488-495.
[19]HE Z,FU L,LIN S,et al.Fault detection and classification in EHV transmission line based on wavelet singular entropy[J].IEEE Transactions on Power Delivery,2010,25(4):2156-2163.
[20]SAMUI A,SAMANTARAY S R.Wavelet singular entropy-based islanding detection in distributed generation[J].IEEE Transactions on Power Delivery,2013,28(1):411-418.
[21]GAETANO A D,RINALDI F,SCIANDRONE M.A patient adaptable ECG beat classifier based on neural networks[J].Applied Mathematics and Computation,2009,213(1):243-249.
[22]POUNGPONSRI S,YU X H.An adaptive filtering approach for electrocardiogram(ECG)signal noise reduction using neural networks[J].Neurocomputing,2013,117(87):206-213.
[23]MEHTA S S,LINGAYAT N S.SVM-based algorithm for recognition of QRS complexes in electrocardiogram[J].IRBM,2008,29(5):310-317.
[24]KOLEY B L,DEY D.Automatic detection of sleep apnea and hypopnea events from single channel measurement of respiration signal employing ensemble binary SVM classifiers[J].Measurement,2013,46(7):2082-2092.
[25]RASMUSSEN C E.Gaussian processes in machine learning[J].Advanced Lectures on Machine Learning,2004,3176(4):63-71.
[26]KEMMLER M,RODNER E,DENZLER J.One-class classification with Gaussian processes[J].Pattern Recognition,2013,46(12):3507-3518.
[27]ZHOU H,WANG L,SUTER D.Human action recognition by feature-reduced Gaussian process classification[J].Pattern Recognition Letters,2009,30(12):1059-1066.
[28]WANG L,LECKIE C A.Improved Gaussian process classification via feature space rotation[J].Neurocompu-ting,2012,83(6):89-97.
[29]YANG X S.Flower pollination algorithm for global optimization[J].Unconventional Computation and Natural Computation,2012,7445(2):242-243.