多信息融合模式分类方法研究及在公交客流识别系统中的应用
|
摘要
客流数据是整个公交企业管理业务的基础,快速、准确地采集车辆的客流信息为科学合理地安排调度车辆、优化公交线路等智能管理提供了最基本的依据,还可以全面如实地反映公交车辆的实际载客人数,方便与钱箱收入之间的核对。本文介绍了目前比较普遍的客流识别方法,并总结了优缺点,提出将多信息融合技术运用到客流识别中来。在信息科学技术领域中,多源信息融合是一个有广泛应用背景及重要理论意义的研究课题。常用的信息融合算法有加权法、Bayes法、证据组合理论、模糊逻辑、神经网络等。这些方法大多依赖于先验知识,从而造成在小样本、高维空间情况下出现模式识别效果不佳的问题。为了解决这个问题本文将支持向量机引入到多信息融合模式分类中来,并对于支持向量机算法进行了研究。根据客流识别的实际问题对于支持向量机的训练算法与快速分类算法进行了改进。最终将多信息融合技术引入到客流识别领域中,构建了基于支持向量机的多信息融合模型,应用嵌入式技术设计并实现了多功能信息采集车载终端。
首先针对于支持向量机在实际训练中由于学习样本集很大且具有类内混杂孤立点数据,引发的学习速度过慢、存储需求量大、泛化能力降低等问题,本文根据点集理论提出了一种新的支持向量机大规模训练样本集缩减策略(SVM-LSTSRS)。该策略运用模糊聚类方法去除类内孤立点并提取出潜在支持向量,从而有效的避免孤立点数据所造成的过学习现象,提高SVM学习机器的泛化性能,并且大大减少训练样本集的规模,在不降低分类精度的前提下提高训练速度。最终通过实验验证了该方法的有效性和可行性。
其次针对支持向量机(SVM)分类速度取决于支持向量数目的应用瓶颈,提出一种SVM快速分类算法。通过引入支持向量在特征空间的相似性度量,构建特征空间中的最小支撑树,在此基础上将支持向量按相似性最大进行分组,依次在每组中找到决定因子和调整因子,用两者的线性组合拟合一组支持向量在特征空间的加权和,从而减少支持向量的数量,提高支持向量机的分类速度。实验结果证明,该方法能以很小的分类精度损失换取较大的分类时间缩减,满足支持向量机实时分类的要求。
最终通过大量实验对人体上下台阶时的压力变化规律进行了研究。提出在单人情况下,可以应用压力数据的特征进行模式分类的方法。针对于双人情况,加入时序信息,提出应用多信息融合的模式分类方法,建立了应用于客流识别的多信息融合模型,并构造了模式分类系统。通过实验表验证了系统的可行性。根据公交行业的现实需求,本文设计并实现了嵌入式客流信息采集车载终端。
The passenger flow data is the basis of public transportation management. Correct and real-time data of passenger flow can provide the most important information for reasonably dispatching buses and optimizing lines of public transportation, and it can also show the actual number of passengers for checking back the cash in the cashbox conveniently. This paper presents some general methods of bus passenger flow recognition, and generalizes the advantages and disadvantages. The multi-information fusion technology is introduced into passenger flow recognition in this paper. Multiple source information fusion has widespread application and important theory significance in the area of information science and technology. Common multi-information fusion methods include weighting method, Bayes method, evidence combination theory, fuzzy logic and neural network, etc. The recognition results are dissatisfied under the conditions of small sample and high dimension space, because most of these methods are based on prior knowledge. Support Vector Machine (SVM) is introduced into multi-information fusion pattern classification to solve this problem. According to the practical problems of passenger flow recognition, the methods to improve training efficiency and speed up classification are researched on, and some new methods are proposed in this paper. On these bases, the multi-information fusion model of passenger flow recognition is established and the passenger flow collection vehicle terminal is developed and implemented.
Recent years, support vector machine has become increasingly popular tools for machine learning tasks which involving pattern recognition, regression analysis and feature extraction. Because of large-scale training samples and outlier data immixed in the other class, there are some disadvantages of support vector machine such as slow learning speed, large buffer memory requirement, and low generalization performance. Aiming at these problems, a new reduction strategy for large-scale training samples according to the point set theory is proposed in this paper. This new strategy reduces the outlier data immixed in the other class and get the support vector by using fuzzy clustering. It can effectively avoid over-learning which is caused by outlier data, improve the generalization performance of the SVM learning machine and greatly reduce the scale of training samples. So the learning rate can be speed up and the classification accuracy can be unaffected. Effectiveness and feasibility of this strategy are proved by experiments.
There is a bottleneck of Support Vector Machine: the speed of classification depends on the number of support vectors. Aiming at this, a fast classification algorithm of support vector machine is proposed. Firstly, it constructs the minimum spanning by introducing the similarity measure and divides the support vectors into groups according to the maximum similarity in feature space. After then, the determinant factor and the adjusting factor will be found in each group by some rules. In order to simplify the support vectors, the linear combination of“determinant factor”and“adjusting factor”will be used to fit the weighted sums of support vectors in feature space. Finally, the speed of classification will be improved significantly. Experimental results show that this algorithm can obtain higher reduction rate of classification time with minor loss of classification accuracy. It can also satisfy the requirements of real-time classification.
In this paper, large numbers of experiments are carried out to research the pressure data of getting on/off the bus. It is proposed that pressure characteristic vector can be used for pattern classification when only one person getting on/off the bus. A new passenger flow recognition method based on multi-information fusion combining pressure data with timing information is presents for two persons getting on/off the bus at the same time, and the multi-information fusion model of passenger flow recognition is established. The experimental results show that the proposed model is effective and its precision is preferable. Finally, according to requirements of practical problem, passenger flow collection vehicle terminal is developed and implemented.
首先针对于支持向量机在实际训练中由于学习样本集很大且具有类内混杂孤立点数据,引发的学习速度过慢、存储需求量大、泛化能力降低等问题,本文根据点集理论提出了一种新的支持向量机大规模训练样本集缩减策略(SVM-LSTSRS)。该策略运用模糊聚类方法去除类内孤立点并提取出潜在支持向量,从而有效的避免孤立点数据所造成的过学习现象,提高SVM学习机器的泛化性能,并且大大减少训练样本集的规模,在不降低分类精度的前提下提高训练速度。最终通过实验验证了该方法的有效性和可行性。
其次针对支持向量机(SVM)分类速度取决于支持向量数目的应用瓶颈,提出一种SVM快速分类算法。通过引入支持向量在特征空间的相似性度量,构建特征空间中的最小支撑树,在此基础上将支持向量按相似性最大进行分组,依次在每组中找到决定因子和调整因子,用两者的线性组合拟合一组支持向量在特征空间的加权和,从而减少支持向量的数量,提高支持向量机的分类速度。实验结果证明,该方法能以很小的分类精度损失换取较大的分类时间缩减,满足支持向量机实时分类的要求。
最终通过大量实验对人体上下台阶时的压力变化规律进行了研究。提出在单人情况下,可以应用压力数据的特征进行模式分类的方法。针对于双人情况,加入时序信息,提出应用多信息融合的模式分类方法,建立了应用于客流识别的多信息融合模型,并构造了模式分类系统。通过实验表验证了系统的可行性。根据公交行业的现实需求,本文设计并实现了嵌入式客流信息采集车载终端。
The passenger flow data is the basis of public transportation management. Correct and real-time data of passenger flow can provide the most important information for reasonably dispatching buses and optimizing lines of public transportation, and it can also show the actual number of passengers for checking back the cash in the cashbox conveniently. This paper presents some general methods of bus passenger flow recognition, and generalizes the advantages and disadvantages. The multi-information fusion technology is introduced into passenger flow recognition in this paper. Multiple source information fusion has widespread application and important theory significance in the area of information science and technology. Common multi-information fusion methods include weighting method, Bayes method, evidence combination theory, fuzzy logic and neural network, etc. The recognition results are dissatisfied under the conditions of small sample and high dimension space, because most of these methods are based on prior knowledge. Support Vector Machine (SVM) is introduced into multi-information fusion pattern classification to solve this problem. According to the practical problems of passenger flow recognition, the methods to improve training efficiency and speed up classification are researched on, and some new methods are proposed in this paper. On these bases, the multi-information fusion model of passenger flow recognition is established and the passenger flow collection vehicle terminal is developed and implemented.
Recent years, support vector machine has become increasingly popular tools for machine learning tasks which involving pattern recognition, regression analysis and feature extraction. Because of large-scale training samples and outlier data immixed in the other class, there are some disadvantages of support vector machine such as slow learning speed, large buffer memory requirement, and low generalization performance. Aiming at these problems, a new reduction strategy for large-scale training samples according to the point set theory is proposed in this paper. This new strategy reduces the outlier data immixed in the other class and get the support vector by using fuzzy clustering. It can effectively avoid over-learning which is caused by outlier data, improve the generalization performance of the SVM learning machine and greatly reduce the scale of training samples. So the learning rate can be speed up and the classification accuracy can be unaffected. Effectiveness and feasibility of this strategy are proved by experiments.
There is a bottleneck of Support Vector Machine: the speed of classification depends on the number of support vectors. Aiming at this, a fast classification algorithm of support vector machine is proposed. Firstly, it constructs the minimum spanning by introducing the similarity measure and divides the support vectors into groups according to the maximum similarity in feature space. After then, the determinant factor and the adjusting factor will be found in each group by some rules. In order to simplify the support vectors, the linear combination of“determinant factor”and“adjusting factor”will be used to fit the weighted sums of support vectors in feature space. Finally, the speed of classification will be improved significantly. Experimental results show that this algorithm can obtain higher reduction rate of classification time with minor loss of classification accuracy. It can also satisfy the requirements of real-time classification.
In this paper, large numbers of experiments are carried out to research the pressure data of getting on/off the bus. It is proposed that pressure characteristic vector can be used for pattern classification when only one person getting on/off the bus. A new passenger flow recognition method based on multi-information fusion combining pressure data with timing information is presents for two persons getting on/off the bus at the same time, and the multi-information fusion model of passenger flow recognition is established. The experimental results show that the proposed model is effective and its precision is preferable. Finally, according to requirements of practical problem, passenger flow collection vehicle terminal is developed and implemented.
引文
[1]杨赛霓.城市公共交通的问题与对策及AVL的运用前景——以南京市公交发展为例.现代城市研究,2000,2:22～24
[2]张雪梅.试论我国公共交通的现状及发展策略.山西高等学校社会科学学报,2001,13(12):35～36
[3]殷小寰,於昌荣.南通市公共交通建设的现状分析与对策研究.城市公共交通,2008,(10):18～20
[4]王建红.我国城市的交通问题及对策.中国国情国力,2009,5:30～31
[5]王军.武汉公交系统的现状与对策.武汉交通职业学院学报,2009,11(4):31～34
[6]刘贤腾,沈青,朱丽.大城市交通供需矛盾及发展对策——以南京为例.交通规划,2009,(1):80～87
[7]刘晓辉.汽车客运站客流特征及客运量预测研究.山东交通学院学报,2008,16(3):29～31
[8]栾文波,王栋.基于客流变化的行车组织分析.都市快轨交通,2010,23(1):71～73
[9]马超群,王玉萍.基于客流效益最大化的轨道交通线网优化方法.长安大学学报,2010,30(1): 76～79
[10]朱晓宏.公交客流信息的采集的方法与技术.城市公共交通,2005,(7):20～21
[11]王晓,魏志强,周利江等.基于脚印方向识别的客流检测与监控系统.城市交通,2006,3(3):27～31
[12] Hashimoto K,Yoshinomoto M,Matsueda S,et al.Development of people-counting system with human-information sensor using multi-element pyroelectric infrared array detector.Sensors and Actuators,1997,58(2):165～171
[13] Amin J,Taylor A.J,Junejo F,et al.Automated people counting by using low-resolution infrared and visual cameras.Measurement,2007,41(6):589～599
[14]沈惠平,范启富.基于神经网络的红外自动乘客计数方法研究.控制工程,2007,14(1):62～65
[15]王君伟,范启富.基于DTW的红外乘客计数方法研究.微型电脑应用,2008,24(4):16～18
[16] Bartolini F, Cappellini V.Counting people getting in and out of a bus by real-time image-sequence processing.Image and Vision Computing,1994,12(1):36～41
[17] MecocciF A,Bartolini,Cappellini V.Image sequence analysis for counting in real time people getting in and out of a bus.Image and Vision Computing,1994,35(2):105～116
[18] Yang,Danny B,Gonzalez-Banos,Hector H,et al.Counting people in crowds with a real-time network of simple image sensors.In:Ninth IEEE International Conference on Computer Vision.France:Institute of Electrical and Electronics Engineers Inc,2003.122～129
[19]李衡宇,何小海,吴炜,等.基于计算机视觉的公交车人流量统计系统.四川大学学报,2007,44(4):825～829
[20]于海滨,刘济林.基于区域视差提取的视觉客流统计方法.传感技术学报,2007,20(7):1545～1550
[21]于海滨,刘济林.应用于公交客流统计的机器视觉方法.中国图象图形学报,2008,13(4):716～722
[22]方成荫,马建文,陈雪.公交车乘客流量自动计数的P2DHMM技术研究.计算机工程与应用,2008,44(11):241～248
[23]梁英宏,王知衍,曹晓叶,等.视频图像理解在客流统计中的应用.计算机工程与设计,2008,29(5):1203～1026
[24] Zhao Xi,Dellandréa Emmanuel,Chen Liming.A people counting system based on face detection and tracking in a video.In:6th IEEE International Conference on Advanced Video and Signal Based Surveillance.Italy:Institute of Electrical and Electronics Engineers Inc,2009.67～72
[25] Rizzon L.,Massari N.,Gottardi M..A low-power people counting system based on a vision sensor working on contrast.In:2009 IEEE International Symposium on Circuits and Systems.Taiwan:Institute of Electrical and Electronics Engineers Inc,2009.786～790
[26]杨万海.多传感器数据融合及其应用.西安:西安电子科技大学出版社,2004
[27] Hall D.L.,Llinas J..Handbook of multisensor data fusion.New York:CRC Press,2001
[28] Hall D.L.,Llinas J..An introduction to multisensor data fusion.Proceedings of the IEEE,1997,85(1):6～23
[29] Luo RC,Kay MG.Multisensor integration and fusion in intelligent systems.IEEE Trans.Syst.,Man Cybern.,1989,19(5):901～931
[30]康耀红.数据融合理论与应用.西安:西安电了科技大学出版社,2006
[31]戴亚平,刘征,郁光辉.多传感器数据融合理论及应用.北京:北京理工大学出版社,2004
[32]杨国胜,窦丽华.数据融合及其应用.北京:兵器工业出版社,2004
[33]刘同明,夏祖勋,解洪成.数据融合技术及其应用.北京:国防工业出版社,1998
[34]杨露菁.多源信息融合理论与应用.北京:北京邮电大学出版社,2006
[35]刘国威.一种基于多传感器数据融合的目标跟踪算法.系统仿真学报,2009,21(19):6183～6189
[36]朱安福,景占荣.多传感器信息融合的目标跟踪研究.计算机工程应用,2009,45(25):7～9
[37]边淑芳.基于信息融合的身份识别技术的发展综述.张家口职业技术学院学报,2009,22(3):57～59
[38]成谢锋,马勇,张少白等.基于数据融合的三段式心音身份识别技术.仪器仪表学报,2010,31(8):1712～1719
[39]赵平,裴晓丽,薛剑.基于信息融合的建筑施工安全预警管理研究.中国安全科学学报,2009,19(10):106～110
[40]丁幼亮,李爱群,邓扬.小波包分析和信息融合在结构损伤预警中的联合应用.工程力学,2010,27(8):72～76
[41]沈志辉,袁再江.作战辅助决策系统信息融合关键技术.辽宁工程技术大学学报,2010,29(29):79～81
[42]刘澜,戢晓峰.基于Vague集的道路交通状态决策信息融合.公路交通科技,2009,26(5):112～116
[43]易正俊.多源信息智能融合算法:[博士论文].重庆:重庆大学,2002
[44] Hugh F,Durrant-Whyte.Consistent integreation and propagation of disparate sensor observations. Int.J.Robot.Res.,1987,6:2～24.
[45]张雨,温熙森.设备故障信息融合问题的思考.长沙交通学院学报,1999,15(2):22～29
[46] Koch K R,Yang Y.Robust kalman filter for rank deficient observation model.Joumal of Geodesy,1998,72:436～441
[47] Box G,Tiao G.Bayesian inferenee in statistical analysis.Reading,MA:Addison Wesley,1973
[48] Hugh F,Durrant-Whyte.Sensor models and multisensor integration.Int.J.Robot.Res.1988,7(6):97～113
[49]李凡.人工智能中的不确定性.北京:气象出版社,1998
[50] L.A.Zadeh.Fuzzy sets.Inform.Contr,1965
[51]贾建华,王军峰,冯冬青.人工神经网络在多传感器信息融合中的应用研究.微计算机信息,2006,22(7):192～194
[52] Pawalk z..Rough sets.International Journal of Computer and Information Seiences,1982,11(3):341～356
[53] Pawlak z.,etal..Rough sets-theoretical aspects of reasoning about data.Dordrecht:Kluwer Academic Publishers,1991
[54] Pawalk z.,et al..Rough sets.Communications of the ACM,1995,38(11):88～95
[55]耿伯英,彭稳高,朱强华,等.基于信息融合的模式识别方法研究.模式识别与人工智能,2002,15(3):339～342
[56] Vapnik V. N..The Nature of Statistic Learning Theory.New York:Springer-Verlag,1995
[57] Vapnik V. N..Statistical Learning Theory.New York:John Wiley,1998
[58]申勇,范红.基于SVM的数字识别技术研究.微计算机信息,2010,26(5):194～196
[59] Xie Jianghong.Optical character recognition based on least square support vector machine.In:3rd International Symposium on Intelligent Information Technology Application.China:Institute of Electrical and Electronics Engineers Inc,2009.626～629
[60]姜鹤,陈丽亚.SVM文本分类中一种新的特征提取方法.计算机技术与发展,2010,20(3):17～19
[61] Guernine Taoufik,Zeroual Kacem.A new fuzzy hierarchical classification based on SVM for text categorization.In:6th International Conference on Image Analysis and Recognition.Canada: Institute of Electrical and Electronics Engineers Inc,2009.865～874
[62]王传旭,李雪.基于高斯模型和支持向量机的人脸检测方法.微计算机信息,2009,25(8):204～205
[63] Khac Cuong Nguyen,Park Ju H.,Jung Ho-YouI.Face detection using variance based Haar-like feature and SVM.World Academy of Science,Engineering and Technology,2009,60:165～168
[64]黄双福,陈贤富.基于改进SVM主动学习算法的入侵检测.微电子学与计算机,2010,27(3):75～77
[65] Du Hongle,Teng Shaohua,Yang Mei,et al.Intrusion detection system based on improved SVM incremental learning.In:2009 International Conference on Artificial Intelligence and Computational Intelligence.China:Institute of Electrical and Electronics Engineers Inc,2009.23～28
[66]张艳,任子晖.一类基于支持向量机的软件故障预测方法.小型微计算机系统,2010,31(7):1380～1384
[67]李天生,李霆.基于模糊SVM与周期分析的股票预测.五邑大学学报,2008,22(3):41～45
[68] Thi Nguyen,Lee Gordon-Brown,Wheeler Peter.GA-SVM based framework for time series forecasting.In:5th International Conference on Natural Computation.China: Institute of Electrical and Electronics Engineers Inc,2009.493～498
[69] Rychetsky M,Ortmann S.Ullmann M. et al.Aceelerated training of support Vector Machines.In:IEEE Proeeedings of International Joint Confereneeon.Canada: Institute of Electrical and Electronics Engineers Inc,1999.998～1003
[70]曾志强.支持向量机分类机的训练与简化算法研究:[博士论文].浙江:浙江大学,2007
[71]曹淑娟,刘小茂,张钧等.基于类中心思想的去边缘模糊支持向量机[J].计算机工程与应用,2006(22):146～149
[72]肖小玲,李腊元,张翔.提高支持向量机训练速度的CM-SVM方法.计算机工程与设计,2006,27(22):4183～4184
[73]李红莲,王春花,袁保宗.一种改进的支持向量机NN-SVM.计算机学报,2003,26(8):1015～1020
[74]罗瑜.支持向量机在机器学习中的应用研究:[博士论文].成都:西南交通大学,2007
[75] Scholkopf B,Mika S, Burges C,et al. Input space versus feature space in kernel-based methods.IEEE Trans. On Neural Networks,1999,10(5):1000～1017
[76] Scholkopf B, Knirsch P, Smola A,et al. Fast approximation of support vector kernel expansions, and an interpretation of clustering as approximation in feature space. In:Levi P,Schanz M, Ahlers RJ,May F,eds. Mustererkennung. Berlin:Springer-Verlag,1998.124～132
[77] Downs T,Gates KE, Masters A.Exact simplification of support vector solutions.Journal of Machine Learning Research,2001,2:293～297
[78]刘向东,陈兆乾.一种快速支持向量机分类算法研究.计算机研究与发展,2004,41(8):1327～1332
[79]秦玉平,王秀坤.一种改进的快速支持向量机分类算法研究.大连理工大学学报,2007,47(2):291～294
[80]曾志强,高济.基于向量集约简的精简支持向量机.软件学报,2007,18(11):2719～2727
[81] Waltz E.,Llinas J.Multisensor data fusion.London:Artech House,Inc.,1990
[82]徐从富等.面向数据融合的D-S算法综述.电子学报,2001,29(3):393～396
[83]张永利.基于支持向量机的信息融合技术研究及应用:[博士论文].西安:西安科技大学,2008
[84]何友等.多传感器信息融合及其应用.北京:电子工业出版社,2000.24～36
[85] B.V.Dasarathy.Sensor fusion potential exploitation innovative architectures and illustrative applieations.Proceedings of the IEEE,1997,85(l):24～38
[86] S.D.E.Elisa,P.L.Blodgett.The extended OODA model for data fusion systems.In:2001 Interuational Conference on information Fusion.Canada:Institute of Electrical and Electronics Engineers Inc,2001.106～112
[87] Gad,M.Farooq.Data fusion architecture for maritime surveillance.In:Proc.of IEEE Int.Conf.on Information Fusion.Canada:Institute of Electrical and Electronics Engineers Inc,2002.448～455
[88] Mark,B.J.Jane.The omnibus model:a new model of data fusion.In:Proc.of 1999 International Conference on Information Fusion.California:Institute of Electrical and Electronics Engineers Inc 1999.337～345
[89] Kurnar R,Wolenetz M,Agarwalla B.A framework for distributed data fusion.Information Fusion,2007,8(3):227～251
[90]吴宏岐,周妮娜,张正喜.电气设备故障诊断中的信息融合技术研究.信息技术,2006,3:64～66
[91]赵国海,王英健,王善侠.基于粗糙集神经网络和信息融合的故障诊断.微机发展,2005,15(1):54～57
[92]张尧庭,陈汉峰.贝叶斯统计推断.北京:科学出版社,1991
[93] Dempster A P.Upper and lower probabilities induced by a multivalued mapping.Annals of Mathematical Statistics.1967,38(2):325～339
[94] Shafer G.A mathematical theory of evidence.New Jersey:Princeton university Press,1976
[95] J.Francois,Y.Grandvalet,et al.Resample and combine:an approach to improving uncertainty representation in evidential pattern classification.Information Fusion,2003,4:75～85
[96] M.A.El-Gamal,M.Abdulghafou.Fault isolation in analog circuits using a fuzzy inference system. Computers and Electrical Engineering,2003,29:213～229
[97]陈晞,谢茂清,高琪瑞.基于模糊推理的电厂设备通用型故障诊断系统研究.中国电力,2003,38(5):69～71
[98] Sheng-Yung Chang,Cheng-Ren Lin,Chuei-Tin Chang.A fuzzy diagnosis approach using dynamic fault trees.Chemical Engineering Science,2002,57:2971～2985
[99] Wang Qinghui,Li Jingrong.A rough set-based fault ranking prototype system for fault diagnosis. Engineering Applications of Artificial Intelligence,2004,17:909～917
[100] Shen Lixiang,Francis E.H.Tay,Qu Liangsheng,et al.Fault diagnosis using Rough Sets Theory. Computers in Industry,2000,43:61～72
[101]黄文涛,赵学增,王伟杰,等.基于不完备数据的汽轮机组故障诊断的粗糙集方法.汽轮机技术2004,46(1):57～59
[102]席少霖.非线性最优化方法.北京:高等教育出版社,2000
[103]张浩然,韩正之.支持向量机算法及应用研究:[博士论文].上海:上海交通大学,2003
[104] Simon Haykin.Neural Networks:A comprehensive Foundation.Pearson Edueationhie,1999
[105] Ingo Steinwart.Sparseness of support vector maehines.Journal of Maehine Learning Research, 2003,4:1071～1105
[106] Han J,Kamber M.范明,孟小峰,等译.数据挖掘概念与技术.北京:机械工业出版社,2002
[107]李金宗.模式识别导论.北京:高等教育出版社,1994
[108]吴景岚,朱文兴.基于K均值的迭代局部搜索聚类算法.计算机工程与应用,2004,22:37～41
[109] Mu-Chun Su.A modified version for K-means.IEEE Transactions on Pattern Analysis and Machine Intelligence,2001,23(6):674～680
[110]戴克戎.微机化步态分析系统的研制与平地行走时足-地接触力的三维分析.中华外科杂,1988,(26):360
[111]励建安,孟殿怀.步态分析的临床应用.中华物理医学与康复杂志,2006,(7):500～503
[112]季林红,朱庆峰,武明等.人体起步过程的实验研究.中国康复医学杂志,2001,16(3):176～179
[113] Eric Eils,Stefan Nolte,Markus Tewes etal.Modified pressure distribution patterns in walking following reduction plantar sensation.Journal ofBiomechanics,2002,(35):1307～1313
[114] Zatsiorsky VM.Kinematies of human motion.Human Kinerics,1998,(3):225～257
[115]郭亚琴.分类器设计及组合技术研究:[博士论文].江苏:扬州大学,2007
[116]田帅.车载信息系统的研究:[博士论文].大连:大连海事大学,2007
[117]温海松.车载信息平台的研究:[博士论文].重庆:重庆大学,2008
[118]黄昊.基于GPS的车载信息终端的研究与开发:[博士论文].北京:首都师范大学,2006
[119] ShenXuesong,LiuJianye,Sunvongrong,etal.Researeh on multi-function vehiele navigation and monitoring system for urban vehiele.Transactions of Nanjing University of Aeronautics & Astronautics,2005,22(2):183～187
[120]黄袁斌.基于GIS的车辆导航与监控系统软件研究与实现:[博士论文].南京:南京航空航天大学,2007
[121]史其信.GPS技术在智能交通系统中的应用.中国安防产品信息,2004,(3):20～25
[122]张庆全.基于GPS/GIS车辆监控系统的设计与实现:[博士论文].哈尔滨:哈尔滨理工大学,2007
[123]曹淑华,吴文红.GPS与车载导航系统.现代电子技术,2007,(23):201～203
[124]汤志伟,陆亨立.基于嵌入式Limix的汽车信息服务系统.汽车电子,2006,22(3):209～211
[125]徐中明,陈旭,贺岩松.智能交通系统中的智能汽车技术.重庆大学学报,2005,28(8):17～21
[126]关惠平,谢飞鸿,刘有录.车载综合信息系统终端构筑方案的研究与实践.计算机工程与设计,2006,2(27):278～282
[127]许欣欣,叶敦范.汽车电子技术新应用一车载移动通信电话系统的实现.微计算机信息, 2005,(21):2～8
[128]黄妙华,徐志军,喻厚宇.基于嵌入式计算机的车载多功能信息系统的研究.汽车电器, 2006,(6):14～18
[129]曹晓航.GPS车载导航技术趋势浅析.现代测绘,2006,1(29):14～17
[130]田泽.嵌入式系统开发与应用.北京:北京航空航天大学出版社,2005
[131]周立功.ARM嵌入式系统基础教程.北京:北京航空航天大学出版社,2005
[132]于明,范书瑞,曾祥烨.ARM9嵌入式系统设计与开发教程.北京:电子工业出版社,2006
[133] S. J. Feng,C.L.Law.Assisted GPS and ITS impact on navigation in intelligent transportationsystems.In:The IEEE 5sth International Conference.USA:Institute of Electrical and Electronics Engineers Inc,2002.926～931
[134]黄美善.嵌入式系统概述.信息与电脑,2010,(2):72
[135]王磊.嵌入式操作系统比较研究.信息与电脑,2010,(3):54～55
[136]喻亮.嵌入式系统的结构特征与研究概况.企业科技与发展,2010,(8):55～57
[137]李月军.浅析VxWorks和Linux嵌入式实时操作系统.科技创新导报,2010,(14):36～38
[138]胡传志,胡晓燕.基于μC/OS-II的嵌入式系统任务设计方法.微计算机信息,2010,26(42):60～66
[139]周玮.基于GPS的公共汽车智能报站系统.计算机与信息技术,2010,(5):66～67
[140]周博.基于μC/OS-II的校园GPS导航系统的设计实现.应用技术与研究,2010,(5):53～54
[141]陶源,朱文.μC/OS-II在无刷直流电动机控制中的应用.微特电机,2010,(5):31～33
[142]陈瑛.一种移植μC/OS-II的DSP语音控制淋浴系统研究.研究与探索,2010,(5):169～171
[143]孙顺远,秦会斌,崔佳冬.μC/OS-II在Cortex-M3内核上的移植及优化.计算机系统应用,2010,19(4):208～211
[144]孔庆臣,张广兰,刘忠艳.μC/OS-II的多任务系统在SOPC中的硬件实现.单片机与嵌入式系统应用,2010,(4):68～69
[2]张雪梅.试论我国公共交通的现状及发展策略.山西高等学校社会科学学报,2001,13(12):35～36
[3]殷小寰,於昌荣.南通市公共交通建设的现状分析与对策研究.城市公共交通,2008,(10):18～20
[4]王建红.我国城市的交通问题及对策.中国国情国力,2009,5:30～31
[5]王军.武汉公交系统的现状与对策.武汉交通职业学院学报,2009,11(4):31～34
[6]刘贤腾,沈青,朱丽.大城市交通供需矛盾及发展对策——以南京为例.交通规划,2009,(1):80～87
[7]刘晓辉.汽车客运站客流特征及客运量预测研究.山东交通学院学报,2008,16(3):29～31
[8]栾文波,王栋.基于客流变化的行车组织分析.都市快轨交通,2010,23(1):71～73
[9]马超群,王玉萍.基于客流效益最大化的轨道交通线网优化方法.长安大学学报,2010,30(1): 76～79
[10]朱晓宏.公交客流信息的采集的方法与技术.城市公共交通,2005,(7):20～21
[11]王晓,魏志强,周利江等.基于脚印方向识别的客流检测与监控系统.城市交通,2006,3(3):27～31
[12] Hashimoto K,Yoshinomoto M,Matsueda S,et al.Development of people-counting system with human-information sensor using multi-element pyroelectric infrared array detector.Sensors and Actuators,1997,58(2):165～171
[13] Amin J,Taylor A.J,Junejo F,et al.Automated people counting by using low-resolution infrared and visual cameras.Measurement,2007,41(6):589～599
[14]沈惠平,范启富.基于神经网络的红外自动乘客计数方法研究.控制工程,2007,14(1):62～65
[15]王君伟,范启富.基于DTW的红外乘客计数方法研究.微型电脑应用,2008,24(4):16～18
[16] Bartolini F, Cappellini V.Counting people getting in and out of a bus by real-time image-sequence processing.Image and Vision Computing,1994,12(1):36～41
[17] MecocciF A,Bartolini,Cappellini V.Image sequence analysis for counting in real time people getting in and out of a bus.Image and Vision Computing,1994,35(2):105～116
[18] Yang,Danny B,Gonzalez-Banos,Hector H,et al.Counting people in crowds with a real-time network of simple image sensors.In:Ninth IEEE International Conference on Computer Vision.France:Institute of Electrical and Electronics Engineers Inc,2003.122～129
[19]李衡宇,何小海,吴炜,等.基于计算机视觉的公交车人流量统计系统.四川大学学报,2007,44(4):825～829
[20]于海滨,刘济林.基于区域视差提取的视觉客流统计方法.传感技术学报,2007,20(7):1545～1550
[21]于海滨,刘济林.应用于公交客流统计的机器视觉方法.中国图象图形学报,2008,13(4):716～722
[22]方成荫,马建文,陈雪.公交车乘客流量自动计数的P2DHMM技术研究.计算机工程与应用,2008,44(11):241～248
[23]梁英宏,王知衍,曹晓叶,等.视频图像理解在客流统计中的应用.计算机工程与设计,2008,29(5):1203～1026
[24] Zhao Xi,Dellandréa Emmanuel,Chen Liming.A people counting system based on face detection and tracking in a video.In:6th IEEE International Conference on Advanced Video and Signal Based Surveillance.Italy:Institute of Electrical and Electronics Engineers Inc,2009.67～72
[25] Rizzon L.,Massari N.,Gottardi M..A low-power people counting system based on a vision sensor working on contrast.In:2009 IEEE International Symposium on Circuits and Systems.Taiwan:Institute of Electrical and Electronics Engineers Inc,2009.786～790
[26]杨万海.多传感器数据融合及其应用.西安:西安电子科技大学出版社,2004
[27] Hall D.L.,Llinas J..Handbook of multisensor data fusion.New York:CRC Press,2001
[28] Hall D.L.,Llinas J..An introduction to multisensor data fusion.Proceedings of the IEEE,1997,85(1):6～23
[29] Luo RC,Kay MG.Multisensor integration and fusion in intelligent systems.IEEE Trans.Syst.,Man Cybern.,1989,19(5):901～931
[30]康耀红.数据融合理论与应用.西安:西安电了科技大学出版社,2006
[31]戴亚平,刘征,郁光辉.多传感器数据融合理论及应用.北京:北京理工大学出版社,2004
[32]杨国胜,窦丽华.数据融合及其应用.北京:兵器工业出版社,2004
[33]刘同明,夏祖勋,解洪成.数据融合技术及其应用.北京:国防工业出版社,1998
[34]杨露菁.多源信息融合理论与应用.北京:北京邮电大学出版社,2006
[35]刘国威.一种基于多传感器数据融合的目标跟踪算法.系统仿真学报,2009,21(19):6183～6189
[36]朱安福,景占荣.多传感器信息融合的目标跟踪研究.计算机工程应用,2009,45(25):7～9
[37]边淑芳.基于信息融合的身份识别技术的发展综述.张家口职业技术学院学报,2009,22(3):57～59
[38]成谢锋,马勇,张少白等.基于数据融合的三段式心音身份识别技术.仪器仪表学报,2010,31(8):1712～1719
[39]赵平,裴晓丽,薛剑.基于信息融合的建筑施工安全预警管理研究.中国安全科学学报,2009,19(10):106～110
[40]丁幼亮,李爱群,邓扬.小波包分析和信息融合在结构损伤预警中的联合应用.工程力学,2010,27(8):72～76
[41]沈志辉,袁再江.作战辅助决策系统信息融合关键技术.辽宁工程技术大学学报,2010,29(29):79～81
[42]刘澜,戢晓峰.基于Vague集的道路交通状态决策信息融合.公路交通科技,2009,26(5):112～116
[43]易正俊.多源信息智能融合算法:[博士论文].重庆:重庆大学,2002
[44] Hugh F,Durrant-Whyte.Consistent integreation and propagation of disparate sensor observations. Int.J.Robot.Res.,1987,6:2～24.
[45]张雨,温熙森.设备故障信息融合问题的思考.长沙交通学院学报,1999,15(2):22～29
[46] Koch K R,Yang Y.Robust kalman filter for rank deficient observation model.Joumal of Geodesy,1998,72:436～441
[47] Box G,Tiao G.Bayesian inferenee in statistical analysis.Reading,MA:Addison Wesley,1973
[48] Hugh F,Durrant-Whyte.Sensor models and multisensor integration.Int.J.Robot.Res.1988,7(6):97～113
[49]李凡.人工智能中的不确定性.北京:气象出版社,1998
[50] L.A.Zadeh.Fuzzy sets.Inform.Contr,1965
[51]贾建华,王军峰,冯冬青.人工神经网络在多传感器信息融合中的应用研究.微计算机信息,2006,22(7):192～194
[52] Pawalk z..Rough sets.International Journal of Computer and Information Seiences,1982,11(3):341～356
[53] Pawlak z.,etal..Rough sets-theoretical aspects of reasoning about data.Dordrecht:Kluwer Academic Publishers,1991
[54] Pawalk z.,et al..Rough sets.Communications of the ACM,1995,38(11):88～95
[55]耿伯英,彭稳高,朱强华,等.基于信息融合的模式识别方法研究.模式识别与人工智能,2002,15(3):339～342
[56] Vapnik V. N..The Nature of Statistic Learning Theory.New York:Springer-Verlag,1995
[57] Vapnik V. N..Statistical Learning Theory.New York:John Wiley,1998
[58]申勇,范红.基于SVM的数字识别技术研究.微计算机信息,2010,26(5):194～196
[59] Xie Jianghong.Optical character recognition based on least square support vector machine.In:3rd International Symposium on Intelligent Information Technology Application.China:Institute of Electrical and Electronics Engineers Inc,2009.626～629
[60]姜鹤,陈丽亚.SVM文本分类中一种新的特征提取方法.计算机技术与发展,2010,20(3):17～19
[61] Guernine Taoufik,Zeroual Kacem.A new fuzzy hierarchical classification based on SVM for text categorization.In:6th International Conference on Image Analysis and Recognition.Canada: Institute of Electrical and Electronics Engineers Inc,2009.865～874
[62]王传旭,李雪.基于高斯模型和支持向量机的人脸检测方法.微计算机信息,2009,25(8):204～205
[63] Khac Cuong Nguyen,Park Ju H.,Jung Ho-YouI.Face detection using variance based Haar-like feature and SVM.World Academy of Science,Engineering and Technology,2009,60:165～168
[64]黄双福,陈贤富.基于改进SVM主动学习算法的入侵检测.微电子学与计算机,2010,27(3):75～77
[65] Du Hongle,Teng Shaohua,Yang Mei,et al.Intrusion detection system based on improved SVM incremental learning.In:2009 International Conference on Artificial Intelligence and Computational Intelligence.China:Institute of Electrical and Electronics Engineers Inc,2009.23～28
[66]张艳,任子晖.一类基于支持向量机的软件故障预测方法.小型微计算机系统,2010,31(7):1380～1384
[67]李天生,李霆.基于模糊SVM与周期分析的股票预测.五邑大学学报,2008,22(3):41～45
[68] Thi Nguyen,Lee Gordon-Brown,Wheeler Peter.GA-SVM based framework for time series forecasting.In:5th International Conference on Natural Computation.China: Institute of Electrical and Electronics Engineers Inc,2009.493～498
[69] Rychetsky M,Ortmann S.Ullmann M. et al.Aceelerated training of support Vector Machines.In:IEEE Proeeedings of International Joint Confereneeon.Canada: Institute of Electrical and Electronics Engineers Inc,1999.998～1003
[70]曾志强.支持向量机分类机的训练与简化算法研究:[博士论文].浙江:浙江大学,2007
[71]曹淑娟,刘小茂,张钧等.基于类中心思想的去边缘模糊支持向量机[J].计算机工程与应用,2006(22):146～149
[72]肖小玲,李腊元,张翔.提高支持向量机训练速度的CM-SVM方法.计算机工程与设计,2006,27(22):4183～4184
[73]李红莲,王春花,袁保宗.一种改进的支持向量机NN-SVM.计算机学报,2003,26(8):1015～1020
[74]罗瑜.支持向量机在机器学习中的应用研究:[博士论文].成都:西南交通大学,2007
[75] Scholkopf B,Mika S, Burges C,et al. Input space versus feature space in kernel-based methods.IEEE Trans. On Neural Networks,1999,10(5):1000～1017
[76] Scholkopf B, Knirsch P, Smola A,et al. Fast approximation of support vector kernel expansions, and an interpretation of clustering as approximation in feature space. In:Levi P,Schanz M, Ahlers RJ,May F,eds. Mustererkennung. Berlin:Springer-Verlag,1998.124～132
[77] Downs T,Gates KE, Masters A.Exact simplification of support vector solutions.Journal of Machine Learning Research,2001,2:293～297
[78]刘向东,陈兆乾.一种快速支持向量机分类算法研究.计算机研究与发展,2004,41(8):1327～1332
[79]秦玉平,王秀坤.一种改进的快速支持向量机分类算法研究.大连理工大学学报,2007,47(2):291～294
[80]曾志强,高济.基于向量集约简的精简支持向量机.软件学报,2007,18(11):2719～2727
[81] Waltz E.,Llinas J.Multisensor data fusion.London:Artech House,Inc.,1990
[82]徐从富等.面向数据融合的D-S算法综述.电子学报,2001,29(3):393～396
[83]张永利.基于支持向量机的信息融合技术研究及应用:[博士论文].西安:西安科技大学,2008
[84]何友等.多传感器信息融合及其应用.北京:电子工业出版社,2000.24～36
[85] B.V.Dasarathy.Sensor fusion potential exploitation innovative architectures and illustrative applieations.Proceedings of the IEEE,1997,85(l):24～38
[86] S.D.E.Elisa,P.L.Blodgett.The extended OODA model for data fusion systems.In:2001 Interuational Conference on information Fusion.Canada:Institute of Electrical and Electronics Engineers Inc,2001.106～112
[87] Gad,M.Farooq.Data fusion architecture for maritime surveillance.In:Proc.of IEEE Int.Conf.on Information Fusion.Canada:Institute of Electrical and Electronics Engineers Inc,2002.448～455
[88] Mark,B.J.Jane.The omnibus model:a new model of data fusion.In:Proc.of 1999 International Conference on Information Fusion.California:Institute of Electrical and Electronics Engineers Inc 1999.337～345
[89] Kurnar R,Wolenetz M,Agarwalla B.A framework for distributed data fusion.Information Fusion,2007,8(3):227～251
[90]吴宏岐,周妮娜,张正喜.电气设备故障诊断中的信息融合技术研究.信息技术,2006,3:64～66
[91]赵国海,王英健,王善侠.基于粗糙集神经网络和信息融合的故障诊断.微机发展,2005,15(1):54～57
[92]张尧庭,陈汉峰.贝叶斯统计推断.北京:科学出版社,1991
[93] Dempster A P.Upper and lower probabilities induced by a multivalued mapping.Annals of Mathematical Statistics.1967,38(2):325～339
[94] Shafer G.A mathematical theory of evidence.New Jersey:Princeton university Press,1976
[95] J.Francois,Y.Grandvalet,et al.Resample and combine:an approach to improving uncertainty representation in evidential pattern classification.Information Fusion,2003,4:75～85
[96] M.A.El-Gamal,M.Abdulghafou.Fault isolation in analog circuits using a fuzzy inference system. Computers and Electrical Engineering,2003,29:213～229
[97]陈晞,谢茂清,高琪瑞.基于模糊推理的电厂设备通用型故障诊断系统研究.中国电力,2003,38(5):69～71
[98] Sheng-Yung Chang,Cheng-Ren Lin,Chuei-Tin Chang.A fuzzy diagnosis approach using dynamic fault trees.Chemical Engineering Science,2002,57:2971～2985
[99] Wang Qinghui,Li Jingrong.A rough set-based fault ranking prototype system for fault diagnosis. Engineering Applications of Artificial Intelligence,2004,17:909～917
[100] Shen Lixiang,Francis E.H.Tay,Qu Liangsheng,et al.Fault diagnosis using Rough Sets Theory. Computers in Industry,2000,43:61～72
[101]黄文涛,赵学增,王伟杰,等.基于不完备数据的汽轮机组故障诊断的粗糙集方法.汽轮机技术2004,46(1):57～59
[102]席少霖.非线性最优化方法.北京:高等教育出版社,2000
[103]张浩然,韩正之.支持向量机算法及应用研究:[博士论文].上海:上海交通大学,2003
[104] Simon Haykin.Neural Networks:A comprehensive Foundation.Pearson Edueationhie,1999
[105] Ingo Steinwart.Sparseness of support vector maehines.Journal of Maehine Learning Research, 2003,4:1071～1105
[106] Han J,Kamber M.范明,孟小峰,等译.数据挖掘概念与技术.北京:机械工业出版社,2002
[107]李金宗.模式识别导论.北京:高等教育出版社,1994
[108]吴景岚,朱文兴.基于K均值的迭代局部搜索聚类算法.计算机工程与应用,2004,22:37～41
[109] Mu-Chun Su.A modified version for K-means.IEEE Transactions on Pattern Analysis and Machine Intelligence,2001,23(6):674～680
[110]戴克戎.微机化步态分析系统的研制与平地行走时足-地接触力的三维分析.中华外科杂,1988,(26):360
[111]励建安,孟殿怀.步态分析的临床应用.中华物理医学与康复杂志,2006,(7):500～503
[112]季林红,朱庆峰,武明等.人体起步过程的实验研究.中国康复医学杂志,2001,16(3):176～179
[113] Eric Eils,Stefan Nolte,Markus Tewes etal.Modified pressure distribution patterns in walking following reduction plantar sensation.Journal ofBiomechanics,2002,(35):1307～1313
[114] Zatsiorsky VM.Kinematies of human motion.Human Kinerics,1998,(3):225～257
[115]郭亚琴.分类器设计及组合技术研究:[博士论文].江苏:扬州大学,2007
[116]田帅.车载信息系统的研究:[博士论文].大连:大连海事大学,2007
[117]温海松.车载信息平台的研究:[博士论文].重庆:重庆大学,2008
[118]黄昊.基于GPS的车载信息终端的研究与开发:[博士论文].北京:首都师范大学,2006
[119] ShenXuesong,LiuJianye,Sunvongrong,etal.Researeh on multi-function vehiele navigation and monitoring system for urban vehiele.Transactions of Nanjing University of Aeronautics & Astronautics,2005,22(2):183～187
[120]黄袁斌.基于GIS的车辆导航与监控系统软件研究与实现:[博士论文].南京:南京航空航天大学,2007
[121]史其信.GPS技术在智能交通系统中的应用.中国安防产品信息,2004,(3):20～25
[122]张庆全.基于GPS/GIS车辆监控系统的设计与实现:[博士论文].哈尔滨:哈尔滨理工大学,2007
[123]曹淑华,吴文红.GPS与车载导航系统.现代电子技术,2007,(23):201～203
[124]汤志伟,陆亨立.基于嵌入式Limix的汽车信息服务系统.汽车电子,2006,22(3):209～211
[125]徐中明,陈旭,贺岩松.智能交通系统中的智能汽车技术.重庆大学学报,2005,28(8):17～21
[126]关惠平,谢飞鸿,刘有录.车载综合信息系统终端构筑方案的研究与实践.计算机工程与设计,2006,2(27):278～282
[127]许欣欣,叶敦范.汽车电子技术新应用一车载移动通信电话系统的实现.微计算机信息, 2005,(21):2～8
[128]黄妙华,徐志军,喻厚宇.基于嵌入式计算机的车载多功能信息系统的研究.汽车电器, 2006,(6):14～18
[129]曹晓航.GPS车载导航技术趋势浅析.现代测绘,2006,1(29):14～17
[130]田泽.嵌入式系统开发与应用.北京:北京航空航天大学出版社,2005
[131]周立功.ARM嵌入式系统基础教程.北京:北京航空航天大学出版社,2005
[132]于明,范书瑞,曾祥烨.ARM9嵌入式系统设计与开发教程.北京:电子工业出版社,2006
[133] S. J. Feng,C.L.Law.Assisted GPS and ITS impact on navigation in intelligent transportationsystems.In:The IEEE 5sth International Conference.USA:Institute of Electrical and Electronics Engineers Inc,2002.926～931
[134]黄美善.嵌入式系统概述.信息与电脑,2010,(2):72
[135]王磊.嵌入式操作系统比较研究.信息与电脑,2010,(3):54～55
[136]喻亮.嵌入式系统的结构特征与研究概况.企业科技与发展,2010,(8):55～57
[137]李月军.浅析VxWorks和Linux嵌入式实时操作系统.科技创新导报,2010,(14):36～38
[138]胡传志,胡晓燕.基于μC/OS-II的嵌入式系统任务设计方法.微计算机信息,2010,26(42):60～66
[139]周玮.基于GPS的公共汽车智能报站系统.计算机与信息技术,2010,(5):66～67
[140]周博.基于μC/OS-II的校园GPS导航系统的设计实现.应用技术与研究,2010,(5):53～54
[141]陶源,朱文.μC/OS-II在无刷直流电动机控制中的应用.微特电机,2010,(5):31～33
[142]陈瑛.一种移植μC/OS-II的DSP语音控制淋浴系统研究.研究与探索,2010,(5):169～171
[143]孙顺远,秦会斌,崔佳冬.μC/OS-II在Cortex-M3内核上的移植及优化.计算机系统应用,2010,19(4):208～211
[144]孔庆臣,张广兰,刘忠艳.μC/OS-II的多任务系统在SOPC中的硬件实现.单片机与嵌入式系统应用,2010,(4):68～69
© 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 |