城市道路拥堵状态下驾驶人生理及换道特性研究
|
摘要
道路基础设施供给与交通需求矛盾日益加剧，导致我国大中城市交通拥堵频发，交通拥堵对驾驶人身心健康和驾驶行为的影响可逐步转化为潜在的安全隐患。目前国内外学者主要从形成机理、疏解策略和环境污染等方面研究道路交通拥堵的危害；而关于交通拥堵对驾驶人身心健康和驾驶行为影响的研究成果则鲜见报道。因此，论文以拥堵状态下驾驶人的生理和行为特性为研究对象，揭示驾驶人的心电和换道指标随交通拥堵压力变化的规律，量化交通拥堵对驾驶人生理和行为的不良影响，提出拥堵状态下驾驶人换道的PSR(压力-状态-响应)模型，探讨基于PSR模型的风险换道警示技术，可以取得较好的创新性研究成果。
从交通流客观运行的角度提出的交通拥堵状态划分方法已经非常成熟，但这种分类方法不能表征驾驶人对交通拥堵的主观感受，论文提出交通拥堵压力系数来表征城市道路的交通拥堵程度，并从驾驶人主观感受角度将城市道路交通流划分为畅通状态、轻度拥堵、中度拥堵和重度拥堵四个等级，基于实测数据标定各型交通流状态的压力系数分级阈值，为开展不同交通拥堵程度下驾驶人的视觉、生理和行为特性的测试研究提供了前提条件。
针对交通畅通、轻度拥堵、中度拥堵和重度拥堵四种状态，设计实验测试方案，测定拥堵状态下驾驶人的视觉特征(注视、扫视、眨眼)、生理特征(心率、心率变异性)和换道构成比例数据。实验人员的选择兼顾了性别、年龄、驾龄等多个因素，实验路径包括快速路、主干路、次干路和支路等多种类型，仪器设备主要采用进口的IView XTM HED型头盔眼动仪和Spirit-10C型多通道生物生理记录仪，以确保数据的客观性和准确性。
在实测实验的基础上研究交通畅通和交通拥堵状态下驾驶人的注视、扫视和眨眼特征的差异，采用非参数检验方法分析驾驶人各项视觉特性指标在畅通和拥堵状态下差异的显著性，研究结果表明交通拥堵状态下驾驶人的注视点分布范围更广，更集中于中央主视区(近距离)，注视持续时间变短，扫视速度和扫视加速度增大，眨眼持续时间和眨眼频率降低。这些变化的主要原因是交通拥堵状态下驾驶人周围的车辆、行人、实时信息板等交通元素的信息量增大，导致驾驶人单位时间内需要处理更多更复杂的交通环境信息，且驾驶人对自身行车安全性的忧虑增加。
在实测数据基础上研究交通拥堵对驾驶人生理特性的影响机理，并采用心率指标和心率变异性指标来表征驾驶人的心电特性，对交通拥堵状态下驾驶人的心率均值、心率变异性时域和频域指标展开深入研究。驾驶人的心率均值随着交通拥堵程度的增加而增大，因此构建了心率均值和压力系数间的关系模型，该模型可以清晰的表达交通拥堵压力下驾驶人心率的波动规律。拥堵状态下的心率变异性分析结果表明，交通拥堵显著影响了驾驶人交感神经和迷走神经对心脏的调节功能，随着交通拥堵程度增加，交感神经兴奋加强，迷走神经兴奋降低，心率调节的平衡向交感神经倾斜。
交通拥堵对驾驶人眼动和心率的影响最终会以具体的驾驶行为表现出来，车道变换行为发生变化是交通拥堵压力作用的直接结果，因此选择交通拥堵压力系数为自变量，斜插型、挤压型和并行型换道的构成比例为因变量，在充分的观测数据基础上，回归分析得到各类型换道比例数与交通拥堵压力系数间的关系模型，该模型客观的反映了交通拥堵程度对驾驶人换道行为的影响，可以为评价道路交通拥堵的危害性提供新的视角。
在研究拥堵状态下驾驶人的心电特性和换道行为变化规律基础上，引入BP神经网络理论，将压力(交通拥堵压力系数)和状态(驾驶人心率均值)作为输入变量，响应(驾驶人换道行为构成比例)作为输出变量，构建交通拥堵状态下驾驶人换道的PSR模型，该模型揭示了交通拥堵压力系数和驾驶人心率状态对驾驶人换道构成比例的联合影响，并运用实测数据与模拟数据对照的方法检验了该模型的实用性。最后，基于驾驶人换道的PSR模型，提出了拥堵状态下斜插型换道的警示方法，以提前警醒驾驶人在道路拥堵时注意放松心情，尽量避免实施危险的斜插型换道行为。
本文旨在揭示“道路交通拥堵→驾驶人焦虑感→驾驶人视觉特征→驾驶人生理特征→驾驶人行为特性→车道变换警示”之间的内在联系，丰富当前对交通拥堵状态下驾驶人生理和换道行为特性研究的理论体系，并提出一种及时预测高风险换道行为的方法和危险换道行为的警示思路，为今后提出缓解交通拥堵状态下驾驶人焦虑的策略奠定基础。
The traffic congestion will be in a long memory in big cities of China, due tothe contradiction between traffic supply and traffic demand. A tremendous amountof studies have conducted to investigate the effects on traffic operation and pollutionof traffic congestion. However, very little is known about the influences of trafficcongestion on driver’s physiological and psychological health. The objectives of thisstudy are therefore to examine the change pattern of driver’s physiological andbehavioral characteristics under different traffic congested conditions, and toquantify the negative impacts of traffic congestion on driver’s physiology andbehavior via uncovering the formation mechanism. The PSR (pressure-state-response) model of driver’s lang changing is proposed to realize a warningtechnology of risky lane changing in the congested condition.
The concept of pressure coefficient has been introduced to describe the trafficcongestion level. Based on driver personal subjective perception, traffic congestionwas categorized into four levels: unblock, light congestion, medium congestion, andsevere congestion. The threshold value of the pressure coefficient at each level wasestimated by using the field observation data. This provides a theoretical basis forcarrying out the experiment on driver’s visual, physiological and behavioralcharacteristics under different traffic congestion states.
Advanced equipments were utilized to conduct an experiment on driver’s visual,physiological and behavioral characteristics under four traffic congestion scenarios.The indices of driver vision (i.e., gaze, glance, and wink), physiologicalcharacteristics (i.e., heart rate, heart rate variability) and risky lane changingcomposition ratio were selected to investigate the effects of traffic congestion ondriver’s physiology and behavior.
According to experimental data, the differences of driver’s indicators wereexamined using non-parametric test method under different traffic congested states.Results show that the increasingly traffic congestion level results in driver’s gazepoint distribution becoming disperse, while more attention being focused on thecentral primary visual area (close-up). As the traffic congestion level increases,driver’s gaze duration shortens, saccade velocity and acceleration increases, andsaccade, blink duration and blink frequency decreases. This can be interpreted interms of information amount. If the driver is presented with traffic congestion, s/heshould to handle more traffic and more complex environmental information, such aspedestrians, adjacent vehicles and variable message signs.
Heart rate and heart rate variability were adopted to analyze the effects of traffic congestion pressure on driver’s ECG characteristics. Time and frequencydomain of the two indexes were studied. Traffic congestion level and driver's meanheart rate were taken into consideration to examine the relationship between meanheart rate and pressure coefficient. According to the analysis results, trafficcongestion significantly affects the regulatory function of driver's nerve and vagusnerve. An increase in the level of traffic congestion associate with a reduction invagus nerve, sympathetic nerve strengthening, and the balance of heart rateadjustment changing.
Congestion pressure coefficient was selected to be the independent variable.The composition ratio of driving behavior was chosen to be the dependent variable.A regression model was proposed to quantify the relationship of congestion pressurecoefficient and the composition ratio of driving behavior. Based on the study in theECG characteristics and lane changing behavior under congested conditions, a BPneural network model was developed. The pressure(congestion pressure coefficient)and status (driver's mean heart rate) were regarded as the input variables, theresponse (the driver’s lane changing composition proportion) was chosen to be theoutput variable. Thus, the driver’s PSR model of lane changing is established underdfferent traffic congestion states to uncover the impacts of congestion pressurecoefficient and driver’s physiological status on the lane changing behaviorcomposition ratios. Field observation data were used to validate the accuracy andeffectiveness of the proposed model.
The goal of this article is to investigate the inherent relationship among trafficcongestion, driver’s anxiety, driver’s visual characteristics, driver’s physiologicalcharacteristics, and driver’s behavioral characteristics. This aids understanding thevariation of driver physiological and behavioral characteristics under differenttraffic congested states. This work provides a solid basis for future research onconceiving strategies to alleviate the driver’s anxiety under traffic congestioncondition and improve traffic safety.
从交通流客观运行的角度提出的交通拥堵状态划分方法已经非常成熟，但这种分类方法不能表征驾驶人对交通拥堵的主观感受，论文提出交通拥堵压力系数来表征城市道路的交通拥堵程度，并从驾驶人主观感受角度将城市道路交通流划分为畅通状态、轻度拥堵、中度拥堵和重度拥堵四个等级，基于实测数据标定各型交通流状态的压力系数分级阈值，为开展不同交通拥堵程度下驾驶人的视觉、生理和行为特性的测试研究提供了前提条件。
针对交通畅通、轻度拥堵、中度拥堵和重度拥堵四种状态，设计实验测试方案，测定拥堵状态下驾驶人的视觉特征(注视、扫视、眨眼)、生理特征(心率、心率变异性)和换道构成比例数据。实验人员的选择兼顾了性别、年龄、驾龄等多个因素，实验路径包括快速路、主干路、次干路和支路等多种类型，仪器设备主要采用进口的IView XTM HED型头盔眼动仪和Spirit-10C型多通道生物生理记录仪，以确保数据的客观性和准确性。
在实测实验的基础上研究交通畅通和交通拥堵状态下驾驶人的注视、扫视和眨眼特征的差异，采用非参数检验方法分析驾驶人各项视觉特性指标在畅通和拥堵状态下差异的显著性，研究结果表明交通拥堵状态下驾驶人的注视点分布范围更广，更集中于中央主视区(近距离)，注视持续时间变短，扫视速度和扫视加速度增大，眨眼持续时间和眨眼频率降低。这些变化的主要原因是交通拥堵状态下驾驶人周围的车辆、行人、实时信息板等交通元素的信息量增大，导致驾驶人单位时间内需要处理更多更复杂的交通环境信息，且驾驶人对自身行车安全性的忧虑增加。
在实测数据基础上研究交通拥堵对驾驶人生理特性的影响机理，并采用心率指标和心率变异性指标来表征驾驶人的心电特性，对交通拥堵状态下驾驶人的心率均值、心率变异性时域和频域指标展开深入研究。驾驶人的心率均值随着交通拥堵程度的增加而增大，因此构建了心率均值和压力系数间的关系模型，该模型可以清晰的表达交通拥堵压力下驾驶人心率的波动规律。拥堵状态下的心率变异性分析结果表明，交通拥堵显著影响了驾驶人交感神经和迷走神经对心脏的调节功能，随着交通拥堵程度增加，交感神经兴奋加强，迷走神经兴奋降低，心率调节的平衡向交感神经倾斜。
交通拥堵对驾驶人眼动和心率的影响最终会以具体的驾驶行为表现出来，车道变换行为发生变化是交通拥堵压力作用的直接结果，因此选择交通拥堵压力系数为自变量，斜插型、挤压型和并行型换道的构成比例为因变量，在充分的观测数据基础上，回归分析得到各类型换道比例数与交通拥堵压力系数间的关系模型，该模型客观的反映了交通拥堵程度对驾驶人换道行为的影响，可以为评价道路交通拥堵的危害性提供新的视角。
在研究拥堵状态下驾驶人的心电特性和换道行为变化规律基础上，引入BP神经网络理论，将压力(交通拥堵压力系数)和状态(驾驶人心率均值)作为输入变量，响应(驾驶人换道行为构成比例)作为输出变量，构建交通拥堵状态下驾驶人换道的PSR模型，该模型揭示了交通拥堵压力系数和驾驶人心率状态对驾驶人换道构成比例的联合影响，并运用实测数据与模拟数据对照的方法检验了该模型的实用性。最后，基于驾驶人换道的PSR模型，提出了拥堵状态下斜插型换道的警示方法，以提前警醒驾驶人在道路拥堵时注意放松心情，尽量避免实施危险的斜插型换道行为。
本文旨在揭示“道路交通拥堵→驾驶人焦虑感→驾驶人视觉特征→驾驶人生理特征→驾驶人行为特性→车道变换警示”之间的内在联系，丰富当前对交通拥堵状态下驾驶人生理和换道行为特性研究的理论体系，并提出一种及时预测高风险换道行为的方法和危险换道行为的警示思路，为今后提出缓解交通拥堵状态下驾驶人焦虑的策略奠定基础。
The traffic congestion will be in a long memory in big cities of China, due tothe contradiction between traffic supply and traffic demand. A tremendous amountof studies have conducted to investigate the effects on traffic operation and pollutionof traffic congestion. However, very little is known about the influences of trafficcongestion on driver’s physiological and psychological health. The objectives of thisstudy are therefore to examine the change pattern of driver’s physiological andbehavioral characteristics under different traffic congested conditions, and toquantify the negative impacts of traffic congestion on driver’s physiology andbehavior via uncovering the formation mechanism. The PSR (pressure-state-response) model of driver’s lang changing is proposed to realize a warningtechnology of risky lane changing in the congested condition.
The concept of pressure coefficient has been introduced to describe the trafficcongestion level. Based on driver personal subjective perception, traffic congestionwas categorized into four levels: unblock, light congestion, medium congestion, andsevere congestion. The threshold value of the pressure coefficient at each level wasestimated by using the field observation data. This provides a theoretical basis forcarrying out the experiment on driver’s visual, physiological and behavioralcharacteristics under different traffic congestion states.
Advanced equipments were utilized to conduct an experiment on driver’s visual,physiological and behavioral characteristics under four traffic congestion scenarios.The indices of driver vision (i.e., gaze, glance, and wink), physiologicalcharacteristics (i.e., heart rate, heart rate variability) and risky lane changingcomposition ratio were selected to investigate the effects of traffic congestion ondriver’s physiology and behavior.
According to experimental data, the differences of driver’s indicators wereexamined using non-parametric test method under different traffic congested states.Results show that the increasingly traffic congestion level results in driver’s gazepoint distribution becoming disperse, while more attention being focused on thecentral primary visual area (close-up). As the traffic congestion level increases,driver’s gaze duration shortens, saccade velocity and acceleration increases, andsaccade, blink duration and blink frequency decreases. This can be interpreted interms of information amount. If the driver is presented with traffic congestion, s/heshould to handle more traffic and more complex environmental information, such aspedestrians, adjacent vehicles and variable message signs.
Heart rate and heart rate variability were adopted to analyze the effects of traffic congestion pressure on driver’s ECG characteristics. Time and frequencydomain of the two indexes were studied. Traffic congestion level and driver's meanheart rate were taken into consideration to examine the relationship between meanheart rate and pressure coefficient. According to the analysis results, trafficcongestion significantly affects the regulatory function of driver's nerve and vagusnerve. An increase in the level of traffic congestion associate with a reduction invagus nerve, sympathetic nerve strengthening, and the balance of heart rateadjustment changing.
Congestion pressure coefficient was selected to be the independent variable.The composition ratio of driving behavior was chosen to be the dependent variable.A regression model was proposed to quantify the relationship of congestion pressurecoefficient and the composition ratio of driving behavior. Based on the study in theECG characteristics and lane changing behavior under congested conditions, a BPneural network model was developed. The pressure(congestion pressure coefficient)and status (driver's mean heart rate) were regarded as the input variables, theresponse (the driver’s lane changing composition proportion) was chosen to be theoutput variable. Thus, the driver’s PSR model of lane changing is established underdfferent traffic congestion states to uncover the impacts of congestion pressurecoefficient and driver’s physiological status on the lane changing behaviorcomposition ratios. Field observation data were used to validate the accuracy andeffectiveness of the proposed model.
The goal of this article is to investigate the inherent relationship among trafficcongestion, driver’s anxiety, driver’s visual characteristics, driver’s physiologicalcharacteristics, and driver’s behavioral characteristics. This aids understanding thevariation of driver physiological and behavioral characteristics under differenttraffic congested states. This work provides a solid basis for future research onconceiving strategies to alleviate the driver’s anxiety under traffic congestioncondition and improve traffic safety.
引文
1Dudek C. L.. Scope of the Traffic Problem Generated by Incidents and SpecialEvents [J]. Transportation Research Record,1986,698:3~5.
2Pattara-atikom W., Peachavanish R.. Estimating Road Traffic Congestion fromCell Dwell Time using Neural Network [C]. Proceedings of the7th InternationalConference on Intelligent Transport Systems Telecommunications, SophiaAntipolis, France, Jun6-8,2007:12~17.
3Kerner B. S.. Tracing and Forecasting of Congested Patterns for HighwayTraffic Management [C].2001IEEE ITSC Proceedings, August25~29,2001:88~93.
4Stathopoulos A., Karlaftis M. G.. Modeling Duration of Urban TrafficCongestion [J]. Journal of Transportation Engineering,2002,128(6):587~590.
5Boarnet M. G., Kim E. J., Parkany E.. Measuring Traffic Congestion [J].Transportation Research Record,1998,(1634):93~99.
6Mekky A.. Measuring Congestion in the Greater Toronto Area [J]. TrafficEngineering and Control,2004,45(2):57~61.
7Lieu H.. A Roadmap for the Research, Development and Deployment of TrafficEstimation and Prediction Systems for Real-Time and Off-Line Applications [R].Travel Management Team Office of Operations RD&T Federal HighwayAdministration,2003:1~35.
8Shed J. B.. Stochastic System Modeling and Optimal Control ofIncident-Induced Traffic Congestion [J]. Mathematical and Computer Modelling,2003,38(5-6):533~549.
9Eliasson J., Hultkrantz L., Nerhagen L., Rosqvist L. S.. The StockholmCongestion-Charging Trial2006: Overview of effects [J]. TransportationResearch Part A,2009,43(3):240~250.
10Seik F. T.. An Advanced Demand Management Instrument in Urban Transport-Electronic Road Pricing in Singapore [J]. Cities,2000,17(1):33~45.
11Goh M.. Congestion Management and Electronic Road Pricing in Singapore [J].Journal of Transport Geography,2002,10(1):29~38.
12Phang S.. From Manual to Electronic Road Congestion Pricing: The SingaporeExperience and Experiment [J]. Transportation Research Part E,1997,33(2):97~106.
13Palma A. D., Lindsey R.. Traffic Congestion Pricing Methodologies andTechnologies [J]. Transportation Research Part C,2011,19(6):1377~1399.
14Wardman M., Ibá ez J. N.. The congestion multiplier: Variations in motorists’valuations of travel time with traffic conditions [J]. Transportation Research PartA,2012,46(1):213~225.
15Abrantes P. A. L., Wardman M. R.. Meta-Analysis of UK Values of TravelTime: An Update [J]. Transportation Research Part A: Policy and Practice,2011,45(1):1~17.
16Hensher D. A., Rose J., Bertoia T.. The Implication on Willingness to Pay of aStochastic Treatment of Attribute Processing in Stated Choice Studies [J].Transportation Research Part E,2007,43(2):73~89.
17Hensher D. A., Greene W. H.. Non-Attendance and Dual Processing ofCommon-Metric Attributes in Choice Analysis: A Latent Class Specification[J]. Empirical Economics,2010,39(2):413~426.
18Joksimovic D., Verhoef E. T., Bliemer M.. Different policy objectives of theroad pricing problem with elastic demand: A game theory approach [R]. The45thCongress of the European Regional Science Association,2004:1~21.
19Levinson D.. Micro-Foundations of Congestion and Pricing: A Game TheoryPerspective [J]. Transportation Research Part A,2005,39(7-9):691~704.
20Eliasson J., Mattsson L.. Equity Effects of Congestion Pricing QuantitativeMethodology and a Case Study for Stockholm [J]. Transportation Research PartA,2006,40(7):602~620.
21Wichiensin M., Bell M. G. H., Yang H.. Impact of congestion charging on thetransit market: an inter-modal equilibrium model. Transportation Research PartA,2007,41(7):703~713.
22Tuerk A., Graham D. J.. Traffic Impacts of the Central London CongestionCharging Scheme [C]. Imperial College London,2010:2~17.
23Wang C., Quddus M. A., Ison S. G.. Impact of Traffic Congestion on RoadAccidents: A Spatial Analysis of the M25Motorway in England [J]. AccidentAnalysis and Prevention,2009,41(4):798~808.
24Quddus M. A.. Modelling Area-wide Count Outcomes with Spatial Correlationand Heterogeneity: an Analysis of London Crash Data [J]. Accident Analysisand Prevention,2008,40(4):1486~1497.
25Noland R. B., Quddus M. A., Ochieng W. Y.. The Effect of the LondonCongestion Charge on Road Casualties: an Intervention Analysis [J].Transportation,2008,35(1):73~91.
26Li H., Graham D. J., Majumdar A.. The Effects of Congestion Charging on RoadTraffic Casualties: A Causal Analysis Using Difference-in-differenceEstimation [J]. Accident Analysis and Prevention,2012,49:366-377.
27Riener A., Ferscha A., Aly M.. Heart on the Road: HRV Analysis for Monitoringa Driver’s Affective State [C]. Proceedings of the First International Conferenceon Automotive User Interfaces and Interactive Vehicular Applications, Sep.21-22,2009:99~106.
28Katsis C. D., Goletsis Y., Rigas G., Fotiadis D. I.. A Wearable System for theAffective Monitoring of Car Racing Drivers during Simulated Conditions [J].Transportation Research Part C: Emerging Technologies,2011,19(3):541~551.
29Katsis C. D., Katertsidis N., Ganiastas G., Fotiadis D. I.. Toward EmotionRecognition in Car-racing Drivers: a Biosignal Processing Approach [J]. IEEETransactionson Systems Man and Cyernatics-Part A: Sytems and Humans,2008,38(3):502~512.
30Ji Q., Lan P., Looney C.. A Probabilistic Framework for Modeling and Real-timeMonitoing human fatigue [J]. IEEE Transactions on Systems Man andCybernatics, Part A: Systems and Humans,2006,36(5):862~875.
31Healey J. A., Picard R. W.. Detecting Stress during Real-world Driving Tasksusing Physiological Sensors [J]. IEEE Transactions on Intelligent TransportationSystems,2005,6(2):156~166.
32Singh R. R., Conjeti S., Banerjee R.. A Comparative Evaluation of NeuralNetwork Classifiers for Stress Level Analysis of Automotive Drivers usingPhysiological Signals [J]. Biomedical Signal Processing and Control,2013,8(6):740~754.
33Miller M. W., Rietschel J. C., McDonald C. G., Hatfield B. D.. A NovelApproach to the Physiological Measurement of Mental Workload [J].International Journal of Psychophysiology,2011,80(1):75~78.
34Ryu K., Myung R.. Evaluation of Mental Workload with a Combined MeasureBased on Physiological Indices during a Dual Task of Tracking and MentalArithmetic [J]. International Journal of Industrial Ergonomics,2005,35(11):991~1009.
35Brookhuis K. A., de Waard D.. Measuring Physiology in Simulators [C].Handbook of Driving Simulation for Engineering, Medicine and Psychology,2011:1~10.
36Brookhuis K. A., de Waard D.. Monitoring Drivers’ Mental Workload in DrivingSimulators using Physiological Measures [J]. Accident Analysis and Prevention,2010,42(3):898~903.
37Yang G., Lin Y., Bhattacharya P.. A Driver Fatigue Recognition Model Based onInformation Fusion and Dynamic Bayesian Network [J]. Information Sciences,2010,180(10):1942~1954.
38Stuiver A., Brookhuis K. A., de Waard D., Mulder B.. Short-TermCardiovascular Measures for Driver Support: Increasing Sensitivity forDetecting Changes in Mental Workload [J]. International Journal ofPsychophysiology,2014,92:35~41.
39Mulder L. J. M.. Measurement and Analysis Methods of Heart Rate andRespiration for Use in Applied Environments [J]. Biological Psychology,1992,34(2-3):205~236.
40Wientjes, C. J. E.. Respiration in Psychophysiology: Methods and Applications[J]. Biological Psychology,1992,34(2-3):179~203.
41Velichkovsky B. M., Rothert A., Kopf M., et al. Towards an Express-Diagnostics for Level of Processing and Hazard Perception. TransportationResearch Part F,2002,5(2):145~156.
42Velichkovsky B. M., Dornhoefer S. M., Kopf M., et al. Change Detection andOcclusion Modes in Road-Traffic Scenarios [J]. Transportation Research Part F,2002,5(2):99~109.
43Di Stasi L. L., Alvarez V., Antoli A., et al. A Neurousability Approach toEvaluate Cognitive Load in Web Interactions [C]. In Proceedings of Workshopon Cognition and the Web,2008:35~38.
44Di Stasi L. L., Antolí A.. Saccadic Peak Velocity as Alternative Cognitive LoadIndex [C]. In Proceedings of the Third International Conference on CognitiveScience,2008:38~40.
45Di Stasi L. L., álvarez-Valbuena V., Ca as J. J., et al. Risk Behaviour andMental Workload: Multimodal Assessment Techniques Applied to MotorbikeRiding Simulation [J]. Transportation Research Part F,2009,12(5):361~370.
46Brookhuis K. A., Waard D. D.. The Use of Psychophysiology to Assess DriverStatus [J]. Ergonomics,1993,36(9):1099~1110.
47Hennessy D. A., Wiesenthal D. L.. The Relationship between Traffic Congestion,Driver Stress and Direct Versus Indirect Coping Behaviours [J]. Ergonomics,1997,40(3):348~361.
48Stokols D., Novaco R. W., Stokols J., Campbell J.. Traffic Congestion, Type aBehavior, and Stress [J]. Journal of Applied Psychology,1978,63(4):467~480.
49Wakita T., Ozawa K., et al. Driver Identification Using Driving BehaviorSignals [C]. IEICE Transactions on Information and Systems,2006, E89-D (3):1188~1194.
50Min B. C., Chung S. C., Park S. J., et al. Autonomic Responses of YoungPassengers Contingent to the Speed and Driving Mode of a Vehicle [J].International Journal of Industrial Ergonomics,2002,29(4):187~198.
51Hill J. D., Boyle L. N.. Driver Stress as Influenced by Driving Maneuvers andRoadway Conditions [J]. Transportation Research, Part F: Traffic Psychology&Behaviour,2007,10(3):177~186.
52Golias I., Karlaftis M. G.. An International Comparative Study of Self-reportedDrive Behavior [J]. Transportation Research Part F,2001,4(4):243~256.
53Nishida Y.. Driving Characteristics of the Elderly: Risk Compensation of theElderly Driving from the Viewpoint of Reaction Behavior [J]. JSAE Review,1999,20(3):375~380.
54Salvucci D. D., Liu A.. The Time Course of a Lane Change: Driver Control andEye-Movement Behavior [J]. Transportation Research Part F,2002,5(2):123~132.
55Deffenbacher J. L., Deffenbacher D. M., Lynch R. S., et al. Anger, Aggression,and Risky Behavior: a Comparison of High and Low Anger Drivers [J].Behaviour Research and Therapy,2003,41(6):701~718
56Lee G. Modeling Gap Acceptance at Freeway Merges [D]. Department of CivilEngineering, Massachusetts Institute of Technology,2006:10~27.
57Thiemann C., Treiber M., and Kesting A.. Estimating Acceleration andLane-Changing Dynamics from Next Generation Simulation Trajectory Data [J],Transportation Research Record,2008,2088:90-101.
58Lee S. E., Olsen E. C. B., Wierwille W. W.. A Comprehensive Examination ofNaturalistic Lane Changes [C]. National Highway Traffic Safety Administration,Washington D.C.,2004:1~213.
59Toledo T., Zohar D.. Modeling the Duration of Lane Changes [J], TransportationResearch Record,2007,1999:71~78.
60Gurupackiam S., Jones S. L.. Empirical Study of Lane Changing in UrbanStreets under Varying Traffic Conditions [J]. Procedia-Social and BehavioralSciences,2011,16:259~269.
61Singh K., Li B.. Estimation of Traffic Densities for Multilane Roadways using aMarkov Model Approach [J]. IEEE Transactions on Industrial Electronics,2012,59(11):4369~4376.
62Singh K., Li B.. Discrete Choice Modelling for Traffic Densities withLane-Change Behaviour [J]. Procedia-Social and Behavioral Sciences,2012,43:367~374.
63Wu X., Yang H.. A Lane Change Model with the Consideration of Car FollowingBehavior [J]. Procedia-Social and Behavioral Sciences,2013,96:2354~2361.
64Sayer J. R., Bogard S. E., Buonarosa M. L., et al. Integrated Vehicle-BasedSafety Systems Light-Vehicle Field Operational Test Key Findings Report [R].Transportation Research Institute,2011:9~22.
65Tijerina L., Garrott W. R., Stoltzfus D., Parmer E.. Eye Glance Behavior of Vanand Passenger Car Drivers during Lane Change Decision Phase [J].Transportation Research Record,2005,1937:37~43.
66Olsen E. C. B., Lee S. E., Wierwille W. W.. Eye Glance Behavior during LaneChanges and Straight-Ahead Driving [J]. Transportation Research Record,2005,1937:44~50.
67Kiefer R. J., Hankey J. M.. Lane Change Behavior with a Side Blind Zone AlertSystem [J]. Accident Analysis and Prevention,2008,40(2):683~690.
68Marsden G., Brackstone M., McDonald M.. Assessment of the Stop and Gofunction using real driving behavior [C]. International Conference on AdvancedDriver Assistance Systems (ADAS),2001:76~80.
69Venhovens P., Naab K., Adiprasito B.. Stop and Go Cruise Control [J].International Journal of Automotive Technology,2000,1(2):61~69.
70Hajek W., Gaponova I., Fleischer K. H., Krems J.. Workload-Adaptive CruiseControl-A New Generation of Advanced Driver Assistance Systems [J].Transportation Research Part F: Traffic Psychology and Behaviour,2013,20:108~120.
71Krautter W., Mackamul H., Manga B., Manstetten D.. Traffic Scenarios inDriving Simulation: Implementation and Application [J]. Advances inTransportation Studies, Special Issue,2004:5~8.
72van Driel C. J. G., Hoedemaeker M., van Arem B.. Impacts of a CongestionAssistant on Driving Behavior and Acceptance using a Driving Simulator [J].Transportation Research Part F,2007,10(2):139~152.
73McLinton S. S., Dollard M. F.. Work Stress and Driving Anger in Japan [J].Accident Analysis&Prevention,2010,42(1):174~181.
74Lonczak H. S., Neighbors C., Donovan D. M.. Predicting Risky and AngryDriving as a Function of Gender [J]. Accident Analysis and Prevention,2007,39(3):536~545.
75González-Iglesias B., Gómez-Fraguela J. A., Luengo-Martín M. á.. DrivingAnger and Traffic Violations: Gender Differences [J]. Transportation ResearchPart F,2012,15(4):404~412.
76Shinar D.. Aggressive Driving: the Contribution of the Drivers and the Situation[J]. Transportation Research Part F,1998,1(2):137~160.
77Parker D., Lajunen T., Summala H.. Anger and Aggression among Drivers inThree European Countries [J]. Accident Analysis&Prevention,2002,34(2):229~235.
78Lajunen T., Parker D., Summala H.. Does Traffic Congestion Increase DriverAggression [J]. Transportation Research Part F: Traffic Psychology&Behaviour,1999,2(4):225~236.
79Noland R. B., Quddus M. A.. Congestion and Safety: A Spatial Analysis ofLondon [J]. Transportation Research Part A: Policy&Practice,2005,39(7-9):737~754.
80Anstey K. J., Wood J., Lord S., et al. Cognitive, Sensory and Physical FactorsEnabling Driving Safety in Older Adults [J]. Clinical Psychology Review,2005,
25(1):45~65.
81Baysari M. T., Mclntosh A. S., Wilson J. R.. Understanding the Human FactorsContribution to Railway Accidents and Incidents in Australia [J]. AccidentAnalysis&Prevention,2008,40(5):1750~1757.
82Verhoef E. T., Rouwendal J.. A Behavioural Model of Traffic Congestion:Endogenizing Speed Choice, Traffic Safety and Time Losses [J]. Journal ofUrban Economics,2004,56(3):408~434.
83淦学甄,刘清,张贵宾.城市道路交通拥挤识别方法研究[J].河北交通科技,2008,5(3):62~64.
84黄欣,杨新苗,常玉林,程杰.城市交通拥挤的成因探析[J].交通运输工程与信息学报,2007,5(2):108~114.
85孙莉芬.城市交通拥挤疏导决策支持系统的研究[D].武汉:华中科技大学,2005:23~39.
86王建玲,蒋阳升.交通拥挤状态的识别与分析[J].系统工程,2006,24(10):105~109.
87姜桂艳.道路交通状态判别技术与应用[M].北京:人民交通出版社,2004.
88郝媛,孙立军,徐天东,杜豫川.城市快速路交通拥挤分析及拥挤阈值的确定[J].同济大学学报(自然科学版),2008,36(5):609~614.
89杨梅.天津市城市交通拥挤问题及道路交通管理对策研究[D].天津:天津大学,2005:5~9.
90庄斌,杨晓光,李克平.道路交通拥挤事件判别准则与检测算法[J].中国公路学报,2006,19(3):82~86.
91吴宏娜,韩印.城市交通拥挤事件的模糊C均值聚类识别方法研究[J].价值工程,2011,7:184~186.
92罗小强,陈宽民,张同芬.城市快速路交通拥挤事件检测与程度辨识[J].长安大学学报(自然科学版),2010,30(3):71~75.
93刘卫宁,曾恒,孙棣华,赵敏.基于视频检测技术的交通拥挤判别模型[J].计算机应用研究,2010,27(8):3006~3008.
94张毅媚,黄进堂.基于模糊数学的交通拥挤评价指标[J].华中科技大学学报(城市科学版),2008,25(1):65~68.
95杨祖元，黄席樾，杜长海，唐明霞.基于FFCM聚类的城市交通拥堵判别研究[J].计算机应用研究,2008,9:2768~2770.
96曲昭伟,魏强,别一鸣等.基于固定检测器的区域交通状态判别方法[J].中南大学学报(自然科学版),2013,44(1):403~410.
97姜紫峰,王忠仁.改善城市交通拥挤的新方法-城市道路收费[J].内蒙古公路与运输,1994,3:40~41.
98石琼,吴群琪.拥挤收费为主导缓解城市交通拥挤可行性研究[J].长安大学学报(社会科学版),2004,6(3):38~42.
99盛玉奎.从城市道路经济属性探讨交通拥挤收费[J].长沙理工大学学报(社会科学版),2010,25(2):16~20.
100刘智丽,李春艳,李成.大城市施行交通拥挤费的交通影响分析[J].交通运输系统工程与信息,2009,9(6):57~62.
101姚红云,孙立军,冯晓.公车影响城市实施交通拥挤收费策略的理论研究[J].同济大学学报(自然科学版),2008,36(1):42~46.
102张中安,冯苏苇.公务车与私家车博弈下的交通拥挤收费效果研究[J].交通运输系统工程与信息,2008,8(2):85~90.
103蔡艳锋,刘爽阳.基于博弈论的城市道路交通拥挤收费分析[J].物流工程与管理,2010,32(4):144~145.
104乔俊,马骏.基于博弈论的交通拥挤与交通需求管理策略分析[J].道路交通与安全,2009,9(4):1~4.
105张小宁,曹津.交通拥挤收费的社会公平性分析[J].同济大学学报(自然科学版),2010,38(11):1605~1609.
106赵冬斌,陈阳舟,易建强.缓解交通拥挤的城市交通信号控制方法综述[J].交通运输系统工程与信息,2009,9(4):36~45.
107潘晓东.人体信息技术在道路交通环境与安全性评价中的应用[J].中国公路学报,2001,14(s):109~115.
108李铭辉,杨浩.环境因素对北京公交驾驶员职业健康的影响分析[J].交通标准化,2007,10:70~73.
109阎莹,刘浩学,郭忠印.不同交通流状态下驾驶员心理生理特性研究[J].同济大学学报,2008,36(10):1372~1377.
110魏丽英.驾驶员车道变换行为模拟分析[J].中国公路学报,2001,14(1):77~80.
111赵亮,胡江碧.眼动与驾驶行为的相关性分析[C].第四届中国智能交通年会论文集,青岛,2008,9:523~528.
112杨渝书,姚振强,李增勇.心电图时频域指标在驾驶疲劳评价中的有效性研究[J].机械设计与制造,2002(5):94~95.
113李增勇,焦昆,陈铭等.汽车驾驶员驾驶过程中的心率变异性功率谱分析[J].中国生物医学工程学报,2003,22(6):574~576.
114谢晓莉.驾驶疲劳生成机理研究[D].北京:北京工业大学,2010:17~36.
115刘灵.心率变异性在汽车司机驾驶疲劳监测中应用的研究[D].重庆:重庆大学,2007:22~37.
116颜松,魏建勤,吴永红.汽车驾驶员瞌睡状态脑电波特征提取的研究[J].中国生物医学工程学报,2005,24(1):110~113.
117彭军强,吴平东,殷罡.疲劳驾驶的脑电特性探索[J].北京理工大学学报,2007,27(7):585~589.
118张祖怀.基于人体生理信号的驾驶疲劳研究方法及其应用[J].哈尔滨:哈尔滨工业大学,2006:17~27.
119宁艳,江朝晖,安滨等.睡眠生理参数的去趋势波动分析[J].生理医学工程学杂志,2007,24(2):249~252.
120房瑞雪.基于生理信号的驾驶疲劳预警对策有效性的实验研究[D].北京:北京工业大学,2010:27~49.
121宋长振.基于心率变异的驾驶员生理负荷研究[D].呼和浩特:内蒙古农业大学,2007:21~26.
122郝晓红.基于驾驶员生理心理反应的草原公路线形研究[D].呼和浩特:内蒙古农业大学,2010:20~56.
123李香红,朱守林,戚春华.基于不同公路景观环境的驾驶员生理反应实验研究[J].内蒙古农业大学学报(自然科学版),2010,(4):172~176.
124艾力.斯木吐拉,李鑫,马晓松.基于驾驶适宜性检测的沙漠公路驾驶员生理、心理特性研究[J].中国安全科学学报,2009,19(1):10~17.
125李显生,付坤.驾驶员生理状态对驾驶行为差错的影响[J].吉林大学学报(工学版),2012, S1:161~165.
126马丹,韩冰源,刘鸿.驾驶员生理周期对其驾驶行为影响的研究[J].森林工程,2007,23(5):43~44.
127骆勇,罗霞.道路交通中攻击性驾驶行为产生机理分析[J].交通运输工程与信息学报,2009,7(2):1~4.
128李艳春,于海辰.大货车驾驶员交通心理与交通安全研究[J].中国安全科学学报,2006,16(10):15~20.
129张华.驾驶员心理特征与驾驶安全的关系研究[J].工业安全与环保,2010,36(2):55~56.
130叶亚丽,许金良,杨宏志.基于驾驶人行为的公路安全不确定性智能评价[J].长安大学学报(自然科学版),2010,30(6):39~43.
131吴雪梅.影响驾驶安全的心理因素探析[J].重庆文理学院学报(社会科学版),2009,28(6):185~188.
132芮峰.道路交通事故预防中驾驶人心理分析与对策[J].道路交通与安全,2006,6(5):28~32.
133裴玉龙,马艳丽.疲劳对驾驶员感知判断及操作特性的影响[J].吉林大学学报,2009,39(5):1151~1156.
134马艳丽.疲劳与驾驶时间关系的实验心理学研究[J].西南交通大学学报,2009,44(4):535~540.
135胡鸿志.机动车驾驶疲劳识别系统研究[D].武汉:武汉理工大学,2010:45~65.
136姜德美.基于BP神经网络的驾驶员疲劳状态研究[D].成都:西南大学,2008:23~48.
137杨京帅.预防道路交通事故的驾驶行为干预技术分析[J].人类工效学,2005,3(11):38~40.
138赵晨鹰.青年攻击性驾驶行为的成因研究[J].青年研究,2003,(12):27~31.
139赵晨鹰,黄希庭.汽车驾驶员攻击性驾驶行为的研究[J].应用心理学,2003,3(9):52~55.
140丁靖艳,郑全全.侵犯驾驶行为的研究及其展望[J].人类工效学,2004,2(10):41~43.
141丁靖艳.基于社会心理学的侵犯驾驶行为研究[D].杭州:浙江大学,2005:35~50.
142庄明科,白海峰,谢晓非.驾驶人员风险驾驶行为分析及相关因素研究[J].北京大学学报(自然科学版),2008,3(44):475~482.
143宋殿明.视线离开前方视野过程中驾驶人行为研究[D].西安:长安大学,2012:15~50.
144巩建强.车辆驾驶人事故前应急操作行为模式研究[D].西安:长安大学,2012:20~41.
145李平凡.驾驶行为表征指标及分析方法研究[D].长春:吉林大学,2010:20~57.
146李平凡,王殿海,刘东波等.驾驶中拨打手机对驾驶人脑力负荷及驾驶行为的影响分析[J].交通信息与安全,2010,4:103~107.
147王殿海.交通流理论[M].北京：人民交通出版社,2002:10~38.
148张彪.交叉口群拥堵扩散机理及其控制与诱导协同模型研究[D].长春:吉林大学,2013:12~29.
149许薇,贾元华.城市道路交通拥堵问题的博弈分析[J].交通科技,2006,215(2):80~82.
150谢建刚.城市交通拥堵博弈分析[J].中国物价,2010,06:68~70.
151贾子若,宋守信.基于博弈论的城市交通拥堵问题分析[J].物流技术,2012,31(3):56~58.
152周勇,张和平,万玉田.人员疏散拥堵问题的博弈分析[J].中国安全科学学报,2008,18(8):131~134.
153胡立伟.公路交通设施驾驶容错能力分析方法研究[D].哈尔滨:哈尔滨工业大学,2012:50~66.
154Konstantopoulos P., Chapman P., Crundall D.. Exploring the Ability to IdentifyVisual Search Differences when Observing Drivers’ Eye Movements [J].Transportation Research Part F: Traffic Psychology and Behaviour,2012,15(3):378~386.
155Salvucci D. D., Liu A.. The Time Course of A Lane Change: Driver Control andEye-movement Behavior [J]. Transportation Research Part F: TrafficPsychology and Behaviour,2002,5(2):123~132.
156陈永刚,丁丽霞,葛宏立等.基于Mann-Whitney非参数检验和SVM的竹类高光谱识别[J].光谱学与光谱分析,2011,31(11):3010~3013.
157胡小刚,陈剑鸿,孙凤军等.基于Matlab的Kruskal-Wallis和Nemenyi检验的界面实现[J].中国卫生统计,2011,28(4):466~467.
158郭继鸿.心电图学[M].北京:人民卫生出版社,2002:1265~1287.
159Liu Y., Chen W.. A SAS Macro for Testing Differences among Three or MoreIndependent Groups Using Kruskal-Wallis and Nemenyi Tests [J]. J HuazhongUniv Sci Technolog,2012,32(1):130~134.
160董红生.心电波形检测与心率变异性分析方法研究[D].兰州:兰州理工大学,2012:45~128.
161明东,田锡惠,杨春梅等.心率变异(HRV)信号的谱分析方法研究[J].北京生物医学工程,2001,20(4):252~255.
162董占勋,孙守迁,吴群等.心率变异性与驾驶疲劳相关性研究[J].浙江大学学报(工学版),2010,44(1):46~50.
163王敬志,任开春,胡斌.基于BP神经网络整定的PID控制[J].工业控制计算机,2011,24(3):72~73.
164孙红敏,吴静婷,李晓明.基于改进BP神经网络的价格预测模型研究[J].东北农业大学学报,2013,44(8):133~137.
165徐慧智.车道变换行为特性及其对道路服务水平影响的研究[D].哈尔滨:哈尔滨工业大学,2008:86~99.
166黄秋菊.车道变换行为特性及其对交通安全影响的研究[D].哈尔滨:哈尔滨工业大学,2007:40~52.
2Pattara-atikom W., Peachavanish R.. Estimating Road Traffic Congestion fromCell Dwell Time using Neural Network [C]. Proceedings of the7th InternationalConference on Intelligent Transport Systems Telecommunications, SophiaAntipolis, France, Jun6-8,2007:12~17.
3Kerner B. S.. Tracing and Forecasting of Congested Patterns for HighwayTraffic Management [C].2001IEEE ITSC Proceedings, August25~29,2001:88~93.
4Stathopoulos A., Karlaftis M. G.. Modeling Duration of Urban TrafficCongestion [J]. Journal of Transportation Engineering,2002,128(6):587~590.
5Boarnet M. G., Kim E. J., Parkany E.. Measuring Traffic Congestion [J].Transportation Research Record,1998,(1634):93~99.
6Mekky A.. Measuring Congestion in the Greater Toronto Area [J]. TrafficEngineering and Control,2004,45(2):57~61.
7Lieu H.. A Roadmap for the Research, Development and Deployment of TrafficEstimation and Prediction Systems for Real-Time and Off-Line Applications [R].Travel Management Team Office of Operations RD&T Federal HighwayAdministration,2003:1~35.
8Shed J. B.. Stochastic System Modeling and Optimal Control ofIncident-Induced Traffic Congestion [J]. Mathematical and Computer Modelling,2003,38(5-6):533~549.
9Eliasson J., Hultkrantz L., Nerhagen L., Rosqvist L. S.. The StockholmCongestion-Charging Trial2006: Overview of effects [J]. TransportationResearch Part A,2009,43(3):240~250.
10Seik F. T.. An Advanced Demand Management Instrument in Urban Transport-Electronic Road Pricing in Singapore [J]. Cities,2000,17(1):33~45.
11Goh M.. Congestion Management and Electronic Road Pricing in Singapore [J].Journal of Transport Geography,2002,10(1):29~38.
12Phang S.. From Manual to Electronic Road Congestion Pricing: The SingaporeExperience and Experiment [J]. Transportation Research Part E,1997,33(2):97~106.
13Palma A. D., Lindsey R.. Traffic Congestion Pricing Methodologies andTechnologies [J]. Transportation Research Part C,2011,19(6):1377~1399.
14Wardman M., Ibá ez J. N.. The congestion multiplier: Variations in motorists’valuations of travel time with traffic conditions [J]. Transportation Research PartA,2012,46(1):213~225.
15Abrantes P. A. L., Wardman M. R.. Meta-Analysis of UK Values of TravelTime: An Update [J]. Transportation Research Part A: Policy and Practice,2011,45(1):1~17.
16Hensher D. A., Rose J., Bertoia T.. The Implication on Willingness to Pay of aStochastic Treatment of Attribute Processing in Stated Choice Studies [J].Transportation Research Part E,2007,43(2):73~89.
17Hensher D. A., Greene W. H.. Non-Attendance and Dual Processing ofCommon-Metric Attributes in Choice Analysis: A Latent Class Specification[J]. Empirical Economics,2010,39(2):413~426.
18Joksimovic D., Verhoef E. T., Bliemer M.. Different policy objectives of theroad pricing problem with elastic demand: A game theory approach [R]. The45thCongress of the European Regional Science Association,2004:1~21.
19Levinson D.. Micro-Foundations of Congestion and Pricing: A Game TheoryPerspective [J]. Transportation Research Part A,2005,39(7-9):691~704.
20Eliasson J., Mattsson L.. Equity Effects of Congestion Pricing QuantitativeMethodology and a Case Study for Stockholm [J]. Transportation Research PartA,2006,40(7):602~620.
21Wichiensin M., Bell M. G. H., Yang H.. Impact of congestion charging on thetransit market: an inter-modal equilibrium model. Transportation Research PartA,2007,41(7):703~713.
22Tuerk A., Graham D. J.. Traffic Impacts of the Central London CongestionCharging Scheme [C]. Imperial College London,2010:2~17.
23Wang C., Quddus M. A., Ison S. G.. Impact of Traffic Congestion on RoadAccidents: A Spatial Analysis of the M25Motorway in England [J]. AccidentAnalysis and Prevention,2009,41(4):798~808.
24Quddus M. A.. Modelling Area-wide Count Outcomes with Spatial Correlationand Heterogeneity: an Analysis of London Crash Data [J]. Accident Analysisand Prevention,2008,40(4):1486~1497.
25Noland R. B., Quddus M. A., Ochieng W. Y.. The Effect of the LondonCongestion Charge on Road Casualties: an Intervention Analysis [J].Transportation,2008,35(1):73~91.
26Li H., Graham D. J., Majumdar A.. The Effects of Congestion Charging on RoadTraffic Casualties: A Causal Analysis Using Difference-in-differenceEstimation [J]. Accident Analysis and Prevention,2012,49:366-377.
27Riener A., Ferscha A., Aly M.. Heart on the Road: HRV Analysis for Monitoringa Driver’s Affective State [C]. Proceedings of the First International Conferenceon Automotive User Interfaces and Interactive Vehicular Applications, Sep.21-22,2009:99~106.
28Katsis C. D., Goletsis Y., Rigas G., Fotiadis D. I.. A Wearable System for theAffective Monitoring of Car Racing Drivers during Simulated Conditions [J].Transportation Research Part C: Emerging Technologies,2011,19(3):541~551.
29Katsis C. D., Katertsidis N., Ganiastas G., Fotiadis D. I.. Toward EmotionRecognition in Car-racing Drivers: a Biosignal Processing Approach [J]. IEEETransactionson Systems Man and Cyernatics-Part A: Sytems and Humans,2008,38(3):502~512.
30Ji Q., Lan P., Looney C.. A Probabilistic Framework for Modeling and Real-timeMonitoing human fatigue [J]. IEEE Transactions on Systems Man andCybernatics, Part A: Systems and Humans,2006,36(5):862~875.
31Healey J. A., Picard R. W.. Detecting Stress during Real-world Driving Tasksusing Physiological Sensors [J]. IEEE Transactions on Intelligent TransportationSystems,2005,6(2):156~166.
32Singh R. R., Conjeti S., Banerjee R.. A Comparative Evaluation of NeuralNetwork Classifiers for Stress Level Analysis of Automotive Drivers usingPhysiological Signals [J]. Biomedical Signal Processing and Control,2013,8(6):740~754.
33Miller M. W., Rietschel J. C., McDonald C. G., Hatfield B. D.. A NovelApproach to the Physiological Measurement of Mental Workload [J].International Journal of Psychophysiology,2011,80(1):75~78.
34Ryu K., Myung R.. Evaluation of Mental Workload with a Combined MeasureBased on Physiological Indices during a Dual Task of Tracking and MentalArithmetic [J]. International Journal of Industrial Ergonomics,2005,35(11):991~1009.
35Brookhuis K. A., de Waard D.. Measuring Physiology in Simulators [C].Handbook of Driving Simulation for Engineering, Medicine and Psychology,2011:1~10.
36Brookhuis K. A., de Waard D.. Monitoring Drivers’ Mental Workload in DrivingSimulators using Physiological Measures [J]. Accident Analysis and Prevention,2010,42(3):898~903.
37Yang G., Lin Y., Bhattacharya P.. A Driver Fatigue Recognition Model Based onInformation Fusion and Dynamic Bayesian Network [J]. Information Sciences,2010,180(10):1942~1954.
38Stuiver A., Brookhuis K. A., de Waard D., Mulder B.. Short-TermCardiovascular Measures for Driver Support: Increasing Sensitivity forDetecting Changes in Mental Workload [J]. International Journal ofPsychophysiology,2014,92:35~41.
39Mulder L. J. M.. Measurement and Analysis Methods of Heart Rate andRespiration for Use in Applied Environments [J]. Biological Psychology,1992,34(2-3):205~236.
40Wientjes, C. J. E.. Respiration in Psychophysiology: Methods and Applications[J]. Biological Psychology,1992,34(2-3):179~203.
41Velichkovsky B. M., Rothert A., Kopf M., et al. Towards an Express-Diagnostics for Level of Processing and Hazard Perception. TransportationResearch Part F,2002,5(2):145~156.
42Velichkovsky B. M., Dornhoefer S. M., Kopf M., et al. Change Detection andOcclusion Modes in Road-Traffic Scenarios [J]. Transportation Research Part F,2002,5(2):99~109.
43Di Stasi L. L., Alvarez V., Antoli A., et al. A Neurousability Approach toEvaluate Cognitive Load in Web Interactions [C]. In Proceedings of Workshopon Cognition and the Web,2008:35~38.
44Di Stasi L. L., Antolí A.. Saccadic Peak Velocity as Alternative Cognitive LoadIndex [C]. In Proceedings of the Third International Conference on CognitiveScience,2008:38~40.
45Di Stasi L. L., álvarez-Valbuena V., Ca as J. J., et al. Risk Behaviour andMental Workload: Multimodal Assessment Techniques Applied to MotorbikeRiding Simulation [J]. Transportation Research Part F,2009,12(5):361~370.
46Brookhuis K. A., Waard D. D.. The Use of Psychophysiology to Assess DriverStatus [J]. Ergonomics,1993,36(9):1099~1110.
47Hennessy D. A., Wiesenthal D. L.. The Relationship between Traffic Congestion,Driver Stress and Direct Versus Indirect Coping Behaviours [J]. Ergonomics,1997,40(3):348~361.
48Stokols D., Novaco R. W., Stokols J., Campbell J.. Traffic Congestion, Type aBehavior, and Stress [J]. Journal of Applied Psychology,1978,63(4):467~480.
49Wakita T., Ozawa K., et al. Driver Identification Using Driving BehaviorSignals [C]. IEICE Transactions on Information and Systems,2006, E89-D (3):1188~1194.
50Min B. C., Chung S. C., Park S. J., et al. Autonomic Responses of YoungPassengers Contingent to the Speed and Driving Mode of a Vehicle [J].International Journal of Industrial Ergonomics,2002,29(4):187~198.
51Hill J. D., Boyle L. N.. Driver Stress as Influenced by Driving Maneuvers andRoadway Conditions [J]. Transportation Research, Part F: Traffic Psychology&Behaviour,2007,10(3):177~186.
52Golias I., Karlaftis M. G.. An International Comparative Study of Self-reportedDrive Behavior [J]. Transportation Research Part F,2001,4(4):243~256.
53Nishida Y.. Driving Characteristics of the Elderly: Risk Compensation of theElderly Driving from the Viewpoint of Reaction Behavior [J]. JSAE Review,1999,20(3):375~380.
54Salvucci D. D., Liu A.. The Time Course of a Lane Change: Driver Control andEye-Movement Behavior [J]. Transportation Research Part F,2002,5(2):123~132.
55Deffenbacher J. L., Deffenbacher D. M., Lynch R. S., et al. Anger, Aggression,and Risky Behavior: a Comparison of High and Low Anger Drivers [J].Behaviour Research and Therapy,2003,41(6):701~718
56Lee G. Modeling Gap Acceptance at Freeway Merges [D]. Department of CivilEngineering, Massachusetts Institute of Technology,2006:10~27.
57Thiemann C., Treiber M., and Kesting A.. Estimating Acceleration andLane-Changing Dynamics from Next Generation Simulation Trajectory Data [J],Transportation Research Record,2008,2088:90-101.
58Lee S. E., Olsen E. C. B., Wierwille W. W.. A Comprehensive Examination ofNaturalistic Lane Changes [C]. National Highway Traffic Safety Administration,Washington D.C.,2004:1~213.
59Toledo T., Zohar D.. Modeling the Duration of Lane Changes [J], TransportationResearch Record,2007,1999:71~78.
60Gurupackiam S., Jones S. L.. Empirical Study of Lane Changing in UrbanStreets under Varying Traffic Conditions [J]. Procedia-Social and BehavioralSciences,2011,16:259~269.
61Singh K., Li B.. Estimation of Traffic Densities for Multilane Roadways using aMarkov Model Approach [J]. IEEE Transactions on Industrial Electronics,2012,59(11):4369~4376.
62Singh K., Li B.. Discrete Choice Modelling for Traffic Densities withLane-Change Behaviour [J]. Procedia-Social and Behavioral Sciences,2012,43:367~374.
63Wu X., Yang H.. A Lane Change Model with the Consideration of Car FollowingBehavior [J]. Procedia-Social and Behavioral Sciences,2013,96:2354~2361.
64Sayer J. R., Bogard S. E., Buonarosa M. L., et al. Integrated Vehicle-BasedSafety Systems Light-Vehicle Field Operational Test Key Findings Report [R].Transportation Research Institute,2011:9~22.
65Tijerina L., Garrott W. R., Stoltzfus D., Parmer E.. Eye Glance Behavior of Vanand Passenger Car Drivers during Lane Change Decision Phase [J].Transportation Research Record,2005,1937:37~43.
66Olsen E. C. B., Lee S. E., Wierwille W. W.. Eye Glance Behavior during LaneChanges and Straight-Ahead Driving [J]. Transportation Research Record,2005,1937:44~50.
67Kiefer R. J., Hankey J. M.. Lane Change Behavior with a Side Blind Zone AlertSystem [J]. Accident Analysis and Prevention,2008,40(2):683~690.
68Marsden G., Brackstone M., McDonald M.. Assessment of the Stop and Gofunction using real driving behavior [C]. International Conference on AdvancedDriver Assistance Systems (ADAS),2001:76~80.
69Venhovens P., Naab K., Adiprasito B.. Stop and Go Cruise Control [J].International Journal of Automotive Technology,2000,1(2):61~69.
70Hajek W., Gaponova I., Fleischer K. H., Krems J.. Workload-Adaptive CruiseControl-A New Generation of Advanced Driver Assistance Systems [J].Transportation Research Part F: Traffic Psychology and Behaviour,2013,20:108~120.
71Krautter W., Mackamul H., Manga B., Manstetten D.. Traffic Scenarios inDriving Simulation: Implementation and Application [J]. Advances inTransportation Studies, Special Issue,2004:5~8.
72van Driel C. J. G., Hoedemaeker M., van Arem B.. Impacts of a CongestionAssistant on Driving Behavior and Acceptance using a Driving Simulator [J].Transportation Research Part F,2007,10(2):139~152.
73McLinton S. S., Dollard M. F.. Work Stress and Driving Anger in Japan [J].Accident Analysis&Prevention,2010,42(1):174~181.
74Lonczak H. S., Neighbors C., Donovan D. M.. Predicting Risky and AngryDriving as a Function of Gender [J]. Accident Analysis and Prevention,2007,39(3):536~545.
75González-Iglesias B., Gómez-Fraguela J. A., Luengo-Martín M. á.. DrivingAnger and Traffic Violations: Gender Differences [J]. Transportation ResearchPart F,2012,15(4):404~412.
76Shinar D.. Aggressive Driving: the Contribution of the Drivers and the Situation[J]. Transportation Research Part F,1998,1(2):137~160.
77Parker D., Lajunen T., Summala H.. Anger and Aggression among Drivers inThree European Countries [J]. Accident Analysis&Prevention,2002,34(2):229~235.
78Lajunen T., Parker D., Summala H.. Does Traffic Congestion Increase DriverAggression [J]. Transportation Research Part F: Traffic Psychology&Behaviour,1999,2(4):225~236.
79Noland R. B., Quddus M. A.. Congestion and Safety: A Spatial Analysis ofLondon [J]. Transportation Research Part A: Policy&Practice,2005,39(7-9):737~754.
80Anstey K. J., Wood J., Lord S., et al. Cognitive, Sensory and Physical FactorsEnabling Driving Safety in Older Adults [J]. Clinical Psychology Review,2005,
25(1):45~65.
81Baysari M. T., Mclntosh A. S., Wilson J. R.. Understanding the Human FactorsContribution to Railway Accidents and Incidents in Australia [J]. AccidentAnalysis&Prevention,2008,40(5):1750~1757.
82Verhoef E. T., Rouwendal J.. A Behavioural Model of Traffic Congestion:Endogenizing Speed Choice, Traffic Safety and Time Losses [J]. Journal ofUrban Economics,2004,56(3):408~434.
83淦学甄,刘清,张贵宾.城市道路交通拥挤识别方法研究[J].河北交通科技,2008,5(3):62~64.
84黄欣,杨新苗,常玉林,程杰.城市交通拥挤的成因探析[J].交通运输工程与信息学报,2007,5(2):108~114.
85孙莉芬.城市交通拥挤疏导决策支持系统的研究[D].武汉:华中科技大学,2005:23~39.
86王建玲,蒋阳升.交通拥挤状态的识别与分析[J].系统工程,2006,24(10):105~109.
87姜桂艳.道路交通状态判别技术与应用[M].北京:人民交通出版社,2004.
88郝媛,孙立军,徐天东,杜豫川.城市快速路交通拥挤分析及拥挤阈值的确定[J].同济大学学报(自然科学版),2008,36(5):609~614.
89杨梅.天津市城市交通拥挤问题及道路交通管理对策研究[D].天津:天津大学,2005:5~9.
90庄斌,杨晓光,李克平.道路交通拥挤事件判别准则与检测算法[J].中国公路学报,2006,19(3):82~86.
91吴宏娜,韩印.城市交通拥挤事件的模糊C均值聚类识别方法研究[J].价值工程,2011,7:184~186.
92罗小强,陈宽民,张同芬.城市快速路交通拥挤事件检测与程度辨识[J].长安大学学报(自然科学版),2010,30(3):71~75.
93刘卫宁,曾恒,孙棣华,赵敏.基于视频检测技术的交通拥挤判别模型[J].计算机应用研究,2010,27(8):3006~3008.
94张毅媚,黄进堂.基于模糊数学的交通拥挤评价指标[J].华中科技大学学报(城市科学版),2008,25(1):65~68.
95杨祖元，黄席樾，杜长海，唐明霞.基于FFCM聚类的城市交通拥堵判别研究[J].计算机应用研究,2008,9:2768~2770.
96曲昭伟,魏强,别一鸣等.基于固定检测器的区域交通状态判别方法[J].中南大学学报(自然科学版),2013,44(1):403~410.
97姜紫峰,王忠仁.改善城市交通拥挤的新方法-城市道路收费[J].内蒙古公路与运输,1994,3:40~41.
98石琼,吴群琪.拥挤收费为主导缓解城市交通拥挤可行性研究[J].长安大学学报(社会科学版),2004,6(3):38~42.
99盛玉奎.从城市道路经济属性探讨交通拥挤收费[J].长沙理工大学学报(社会科学版),2010,25(2):16~20.
100刘智丽,李春艳,李成.大城市施行交通拥挤费的交通影响分析[J].交通运输系统工程与信息,2009,9(6):57~62.
101姚红云,孙立军,冯晓.公车影响城市实施交通拥挤收费策略的理论研究[J].同济大学学报(自然科学版),2008,36(1):42~46.
102张中安,冯苏苇.公务车与私家车博弈下的交通拥挤收费效果研究[J].交通运输系统工程与信息,2008,8(2):85~90.
103蔡艳锋,刘爽阳.基于博弈论的城市道路交通拥挤收费分析[J].物流工程与管理,2010,32(4):144~145.
104乔俊,马骏.基于博弈论的交通拥挤与交通需求管理策略分析[J].道路交通与安全,2009,9(4):1~4.
105张小宁,曹津.交通拥挤收费的社会公平性分析[J].同济大学学报(自然科学版),2010,38(11):1605~1609.
106赵冬斌,陈阳舟,易建强.缓解交通拥挤的城市交通信号控制方法综述[J].交通运输系统工程与信息,2009,9(4):36~45.
107潘晓东.人体信息技术在道路交通环境与安全性评价中的应用[J].中国公路学报,2001,14(s):109~115.
108李铭辉,杨浩.环境因素对北京公交驾驶员职业健康的影响分析[J].交通标准化,2007,10:70~73.
109阎莹,刘浩学,郭忠印.不同交通流状态下驾驶员心理生理特性研究[J].同济大学学报,2008,36(10):1372~1377.
110魏丽英.驾驶员车道变换行为模拟分析[J].中国公路学报,2001,14(1):77~80.
111赵亮,胡江碧.眼动与驾驶行为的相关性分析[C].第四届中国智能交通年会论文集,青岛,2008,9:523~528.
112杨渝书,姚振强,李增勇.心电图时频域指标在驾驶疲劳评价中的有效性研究[J].机械设计与制造,2002(5):94~95.
113李增勇,焦昆,陈铭等.汽车驾驶员驾驶过程中的心率变异性功率谱分析[J].中国生物医学工程学报,2003,22(6):574~576.
114谢晓莉.驾驶疲劳生成机理研究[D].北京:北京工业大学,2010:17~36.
115刘灵.心率变异性在汽车司机驾驶疲劳监测中应用的研究[D].重庆:重庆大学,2007:22~37.
116颜松,魏建勤,吴永红.汽车驾驶员瞌睡状态脑电波特征提取的研究[J].中国生物医学工程学报,2005,24(1):110~113.
117彭军强,吴平东,殷罡.疲劳驾驶的脑电特性探索[J].北京理工大学学报,2007,27(7):585~589.
118张祖怀.基于人体生理信号的驾驶疲劳研究方法及其应用[J].哈尔滨:哈尔滨工业大学,2006:17~27.
119宁艳,江朝晖,安滨等.睡眠生理参数的去趋势波动分析[J].生理医学工程学杂志,2007,24(2):249~252.
120房瑞雪.基于生理信号的驾驶疲劳预警对策有效性的实验研究[D].北京:北京工业大学,2010:27~49.
121宋长振.基于心率变异的驾驶员生理负荷研究[D].呼和浩特:内蒙古农业大学,2007:21~26.
122郝晓红.基于驾驶员生理心理反应的草原公路线形研究[D].呼和浩特:内蒙古农业大学,2010:20~56.
123李香红,朱守林,戚春华.基于不同公路景观环境的驾驶员生理反应实验研究[J].内蒙古农业大学学报(自然科学版),2010,(4):172~176.
124艾力.斯木吐拉,李鑫,马晓松.基于驾驶适宜性检测的沙漠公路驾驶员生理、心理特性研究[J].中国安全科学学报,2009,19(1):10~17.
125李显生,付坤.驾驶员生理状态对驾驶行为差错的影响[J].吉林大学学报(工学版),2012, S1:161~165.
126马丹,韩冰源,刘鸿.驾驶员生理周期对其驾驶行为影响的研究[J].森林工程,2007,23(5):43~44.
127骆勇,罗霞.道路交通中攻击性驾驶行为产生机理分析[J].交通运输工程与信息学报,2009,7(2):1~4.
128李艳春,于海辰.大货车驾驶员交通心理与交通安全研究[J].中国安全科学学报,2006,16(10):15~20.
129张华.驾驶员心理特征与驾驶安全的关系研究[J].工业安全与环保,2010,36(2):55~56.
130叶亚丽,许金良,杨宏志.基于驾驶人行为的公路安全不确定性智能评价[J].长安大学学报(自然科学版),2010,30(6):39~43.
131吴雪梅.影响驾驶安全的心理因素探析[J].重庆文理学院学报(社会科学版),2009,28(6):185~188.
132芮峰.道路交通事故预防中驾驶人心理分析与对策[J].道路交通与安全,2006,6(5):28~32.
133裴玉龙,马艳丽.疲劳对驾驶员感知判断及操作特性的影响[J].吉林大学学报,2009,39(5):1151~1156.
134马艳丽.疲劳与驾驶时间关系的实验心理学研究[J].西南交通大学学报,2009,44(4):535~540.
135胡鸿志.机动车驾驶疲劳识别系统研究[D].武汉:武汉理工大学,2010:45~65.
136姜德美.基于BP神经网络的驾驶员疲劳状态研究[D].成都:西南大学,2008:23~48.
137杨京帅.预防道路交通事故的驾驶行为干预技术分析[J].人类工效学,2005,3(11):38~40.
138赵晨鹰.青年攻击性驾驶行为的成因研究[J].青年研究,2003,(12):27~31.
139赵晨鹰,黄希庭.汽车驾驶员攻击性驾驶行为的研究[J].应用心理学,2003,3(9):52~55.
140丁靖艳,郑全全.侵犯驾驶行为的研究及其展望[J].人类工效学,2004,2(10):41~43.
141丁靖艳.基于社会心理学的侵犯驾驶行为研究[D].杭州:浙江大学,2005:35~50.
142庄明科,白海峰,谢晓非.驾驶人员风险驾驶行为分析及相关因素研究[J].北京大学学报(自然科学版),2008,3(44):475~482.
143宋殿明.视线离开前方视野过程中驾驶人行为研究[D].西安:长安大学,2012:15~50.
144巩建强.车辆驾驶人事故前应急操作行为模式研究[D].西安:长安大学,2012:20~41.
145李平凡.驾驶行为表征指标及分析方法研究[D].长春:吉林大学,2010:20~57.
146李平凡,王殿海,刘东波等.驾驶中拨打手机对驾驶人脑力负荷及驾驶行为的影响分析[J].交通信息与安全,2010,4:103~107.
147王殿海.交通流理论[M].北京：人民交通出版社,2002:10~38.
148张彪.交叉口群拥堵扩散机理及其控制与诱导协同模型研究[D].长春:吉林大学,2013:12~29.
149许薇,贾元华.城市道路交通拥堵问题的博弈分析[J].交通科技,2006,215(2):80~82.
150谢建刚.城市交通拥堵博弈分析[J].中国物价,2010,06:68~70.
151贾子若,宋守信.基于博弈论的城市交通拥堵问题分析[J].物流技术,2012,31(3):56~58.
152周勇,张和平,万玉田.人员疏散拥堵问题的博弈分析[J].中国安全科学学报,2008,18(8):131~134.
153胡立伟.公路交通设施驾驶容错能力分析方法研究[D].哈尔滨:哈尔滨工业大学,2012:50~66.
154Konstantopoulos P., Chapman P., Crundall D.. Exploring the Ability to IdentifyVisual Search Differences when Observing Drivers’ Eye Movements [J].Transportation Research Part F: Traffic Psychology and Behaviour,2012,15(3):378~386.
155Salvucci D. D., Liu A.. The Time Course of A Lane Change: Driver Control andEye-movement Behavior [J]. Transportation Research Part F: TrafficPsychology and Behaviour,2002,5(2):123~132.
156陈永刚,丁丽霞,葛宏立等.基于Mann-Whitney非参数检验和SVM的竹类高光谱识别[J].光谱学与光谱分析,2011,31(11):3010~3013.
157胡小刚,陈剑鸿,孙凤军等.基于Matlab的Kruskal-Wallis和Nemenyi检验的界面实现[J].中国卫生统计,2011,28(4):466~467.
158郭继鸿.心电图学[M].北京:人民卫生出版社,2002:1265~1287.
159Liu Y., Chen W.. A SAS Macro for Testing Differences among Three or MoreIndependent Groups Using Kruskal-Wallis and Nemenyi Tests [J]. J HuazhongUniv Sci Technolog,2012,32(1):130~134.
160董红生.心电波形检测与心率变异性分析方法研究[D].兰州:兰州理工大学,2012:45~128.
161明东,田锡惠,杨春梅等.心率变异(HRV)信号的谱分析方法研究[J].北京生物医学工程,2001,20(4):252~255.
162董占勋,孙守迁,吴群等.心率变异性与驾驶疲劳相关性研究[J].浙江大学学报(工学版),2010,44(1):46~50.
163王敬志,任开春,胡斌.基于BP神经网络整定的PID控制[J].工业控制计算机,2011,24(3):72~73.
164孙红敏,吴静婷,李晓明.基于改进BP神经网络的价格预测模型研究[J].东北农业大学学报,2013,44(8):133~137.
165徐慧智.车道变换行为特性及其对道路服务水平影响的研究[D].哈尔滨:哈尔滨工业大学,2008:86~99.
166黄秋菊.车道变换行为特性及其对交通安全影响的研究[D].哈尔滨:哈尔滨工业大学,2007:40~52.