摘要
骑马运动早有运动之王的美誉，然而受到场地、饲养成本等因素限制，难以推广。因此，研究模拟骑马运动装置的意义重大。骑马本身既可达到运动健身效果，也可应用到康复治疗，临床试验也确认了它的有效性。本文主要借助一种新型正交6-PSS机器马并联平台模拟骑马运动，在运动中通过采集骑乘者的生理指标信息，并将生理指标进行信息融合以分析、研究和判断骑乘者在运动中的生理反映，并以此作为反馈量控制机器马的运动轨迹、姿态及速度。经过仿真和实验研究，在安全骑乘和增进健康上均达到了较好的实际效果。具体的研究工作主要包括以下几个方面：
(1)对人在运动中的生理指标变化与运动效果的关系进行了分析，利用人体运动时心率、血压、血氧饱和度等生理指标的变化来评判运动效果。采用不同的算法来实现各种同类或异类生理指标数据的时间配准，提高了时间配准后数据的准确性和稳定性。
(2)分析了仿生机器马健身器在实验的初始阶段和实际应用的后续阶段对信息融合性能的不同需求，将改进的BP神经网络和支持向量机两种融合算法相结合，应用于仿生机器马健身器的骑姿寻优控制中，以满足仿生机器马在实验的初始阶段对自学习能力的要求，以及实际应用的后续阶段对信息融合快速准确性的要求.
(3)在BFGS算法中调用改进的牛顿下山法模块，舍弃常规BFGS方法中所执行的一维搜索，使得学习算法保持下降方向，并有总体收敛的性质。利用该改进的BFGS算法替代传统的梯度下降法学习BP网络权值，提高了信息融合的速度和准确性。
(4)针对BP网络的收敛速度和模型精度易受到初始参数(包括权值和阈值的)影响，采用改进的蚁群算法寻找最优的BP网络初始参数。在该改进的蚁群算法中，引入了可行搜索空间，通过在迭代后期持续缩小可行搜索空间，并保存上次迭代的最优值，帮助其跳出局部极值点。其既继承了传统蚁群算法模型简单、参数少、易于实现的优点，又克服了传统蚁群算法局部搜索能力差、收敛速度低、易陷入局部极值的缺点，具有更好的全局寻优能力。
(5)利用一种基于概率密度函数的势阱帮助粒子群中的粒子收敛，提高种群的多样性和粒子搜索的遍历性，提高了算法的收敛速度和精度。采用该优化算法选取支持向量机的最优参数，确保了支持向量机具有较好的分类精度和泛化能力。
(6)分析了基于运动平台的动力学模型设计控制器的可行性，将模糊自适应PID应用于支链位置闭环控制中，实现对机器马运动平台的动态实时控制。并利用高性能运动轨迹采集装置采集马的运动轨迹，使六自由度并联机器马运动平台可以较为真实地再现马的多种运动姿态，同时利用骑马者的生理信息融合结果控制机器马的运动速度及姿态，以达到最佳运动效果。
Horseback riding has long been the king of the sports world. However, limited by thevenue, keeping costs and other factors, it is difficult to promote. Therefore, the study onanalog riding device is very significant. Horse riding has effect on exercise and fitness,and also can be applied to rehabilitation. Clinical trials have confirmed its effectiveness. Inthis paper, we analog ride with a new orthogonal6-PSS machine horse parallel platformand collect the rider’s physiological indicators information in motion. After the fusion ofphysiological indicators, the rider’s physiological reflects are analyzed, researched andjudged, as the feedback quantity to control the trajectory, posture and speed of the machinehorse. By the simulation and experimental, it has good effect on safe riding and healthimprovement. The specific research mainly includes the following aspects:
(1) Analyzed the relationship between the physiological and exercise effects, andused the changes of heart rate, blood pressure, oxygen saturation to judge exerciseeffects.Used different algorithms to realize time registration, so improved data accuracyand stability.
(2) Analyzed the biominetic robot horse’s different needs of information fusion ininitial stages and practical application of the follow-up stage. Used a fusion algorithmbased on the combination of Neural Network and SVM to the riding position seekingcontrol, to ensure the accuracy of the informaiton fusion in the practical of the subsequentstages, on which the sample gradually perfect.
(3) Introduced the improved Newton’s descent method into the conventional BFGSaltorithm. In this algorithm, we do not have to pre-calculate the descent direction of theobjective function, and can search the value of the next descent point. So this algorithmmay reduce the amount of calculation and have a faster convergence speed and betterstability. The improved BFGS algorithm of gradient descent method to learn BP networkweights, which replaced the traditional one, so improved the speed and accuracy ofinformation fusion.
(4) For the initial parameters (including weights and thresholds) vulnerable to have impact on convergence speed and accuracy of BP network, used an improved ant colonyalgorithm to select the optimal initial parameters. Propose a new method to search optimalparameters of BP networks based on improved ant colony algorithm. The proposedalgorithm is based on each ant searches only around the best solution of the previousiteration with parameter, which can reduce search space fast. Parameter is theproposed for improving ACO’s solution performance to reach global optimum fairlyquickly. Simulation results indicate that optimize parameters of BP networks with thismethod can not only overcome the limitations both the slow convergence and the localextreme values by basic BP algorithm, but also improve the learning ability andgeneralization ability.
(5) In this study, quantum principles is introduced in particle swarm optimizationalgorithm, which can improves traverse property of particle of particle, thus can overcomethe limitation of local extreme values and get the optimal parameters of SVM. Simulationresults indicate that quantum particle swarm optimization-based SVM classifier has higherclassification accuracy than common optimization algorithm.
(6) Basing on the feasibility analysis of design controller by the motion platform’sdynamic model, we used a fuzzy adaptive PID controller, which can realize the dynamic,real-time control of the moving platform. Using high performance trajectory device tocollect horse trajectory, so that6-DOF parallel machine horse sports platform can morefactually reproduce a variety of horse sports, while taking advantage of the horse ridersphysiological information fusion results to control the movement of the machine horsespeed and posture, in order to achieve the best sports effection. Simulation experimentsand field tests show that the machine horse posture optimization control system has a goodperformance.
引文
[1]张志强.康复医学[M].北京:人民卫生出版社,2010:1-13.
[2]纪树荣.运动疗法技术学[M].北京:华夏卫生出版社,2011:2-9.
[3] Meregillano G. Hippotherapy[J]. Physical Medicine and Rehabilitation,2004,15(4):843-854.
[4]吴卫红,李欣.残疾儿童的治疗性骑马[J].中华物理医学与康复杂志,2007,29(3):201-203.
[5]刘婷婷.脑瘫患儿的治疗性骑马[J].中外妇儿健康,2011,19(9):149-150.
[6] Jeong-Yi Kwon, Hyun Jung Chang, Ji Young Lee, et al. Effects of Hippotherapy on GaitParameters in Children With Bilateral Spastic[J]. Archives of Physical Medicine andRehabilitation,2011,5(92):774-779.
[7] Gehan H. EI-Meniawy, Nahed S. Thabet. Modulation of back geometry in chidren with spasticdiplegic cerebral palsy via hippotherapy training[J]. Egyptian Journal of Medical HumanGenetics,2012,1(13):63-71.
[8] Tim L. Shurtleff, John W. Standeven, Jack R. Engsberg. Changes in Dynamic Trunk/Head Stabilityand Functional Reach After Hippotherapy[J]. Archives of Physical Medicine andRehabilitation,2009,7(90):1185-1195.
[9] Nancy H. McGibbon, Wiliam Benda, Burris R. Duncan, et al. Immediate and Long-Term Effectsof Hippotherapy on Symmetry of Adductor Muscle Activity and Functional Ability in ChildrenWith Spastic Cerebral Palsy[J]. Archives of Physical Medicine and Rehabilitation,2009,6(90):966-974.
[10] Paraskevi Giagazoglou, Fotini Arabatzi, Konstantina Dipla, et al. Effect of a HippotherapyIntervention Program on Static Balance and Strength in Adolescents with IntellectualDisabilities[J]. Research in Developmetal Disabilities,2012,6(33):2265-2270.
[11] Kimura T. The Development of an Intelligent Simulator of Horses[J]. MedTreat,1986,8(40):749-755.
[12] Shinomiya Y, Nomura J, Yoshida Y, et al. Horseback Riding Therapy Simulator with VRTechnolory[C]. ACM Symposium on Virtual Reality Software and Technology,1997,31:9-14.
[13] Kitagawa T, Takeuchi T, Shinomiya Y, et al. Cause of Active Motor Function by PassiveMovement[J]. Physical Therapy Science,2001,13:167-172.
[14] Nakajima R, Shinomiya Y, Sekine O, et al. Horseback Riding Therapy System using VRTechnology, and Toward to its Medical Evaluation[J]. Trans Human InterfaceSociety,1999,3(4):81-86.
[15] Sandipan B. An Algebraic Formulation of Static Isotropy and Design of Statically Isotropic6-6Stewar Platform Manipulators[J]. Mechanism and Machine Theory,2009,7(44):1360-1370.
[16] Robin L. Gabriels, John A. Agnew, Katherine D. Holt, et al. Pilot Study Measring the Effects ofTherapeutic Horseback Riding on School-age Children and Adolescents with Autism SpectrumDisorders[J]. Research in Autism Spectrum Disorders,2012,2(6):578-588.
[17] K.Witte, H. Schobesberger, C. Peham. Motion Pattern Analysis of Gait in Horseback Riding byMeans of Principal Component Analysis[J]. Human Movement Science,2009,3(28):394-405.
[18] Margareta Hakanson, Margereta Moller, Ingalill Lindstrom, et al. The Horse as the Healer-A Studyof Riding in Patients with Back Pain[J]. Journal of Bodywork and MovementTherapies,2009,1(13):43-52.
[19] Miroslav Janura, Christian Peham, Tereza Dvorakova, et al. An Assessment of the PressureDistribution Exerted by a Rider on the Back of a Horse during Hippotherapy[J]. HumanMovement Science,2009,3(22):387-393.
[20]杨露菁,余华.多源信息融合理论与应用[M].北京:北京邮电大学出版社,2011:1-24.
[21]韩崇昭.多源信息融合[M].北京:清华大学出版社,2010:1-15.
[22]姜延吉.多传感器数据融合关键技术研究[D].哈尔滨:哈尔滨工程大学,2010:1-6.
[23] Xin Zhang, Li Yang, Yan Zhang, et al. Multi-source Information Fusion Based on Data Driven[J].Journal of Software,2011,6(6):1125-1132.
[24] Y. Bar-Shalom, Campo L. The Effect of the Common Process Noise on the Two-sensorFused-track Covariance[J]. EEE Trans on Aerospace and Electronic Systems,1986,22(6):803-805.
[25]康健.多传感器信息融合技术研究与应用[D].哈尔滨:哈尔滨工程大学,2011:1-5.
[26]胡丽芳,关欣,何友.基于Dezert-Smarandache理论的递归目标识别融合方法[J].控制理论与应用,2012,29(1):79-84.
[27] Abdolhossein Alipoor, Mehdi Fesharaki. Optimal Sensor Deployment for Object Recoqnitionusing Artifical Intelliqence Methods[C]. Proceedings of International Conference on ComputerCommunication and Management,2011:325-331.
[28]董政.日盲紫外探测系统自动目标识别的研究[D].北京:电子科技大学,2011:104-129.
[29] Liu Zhuga, Cheng Yongmei, Pan Quan, et al. Target Identification by Adaptive Combination ofConflicting Evidence[J]. Acta Aeronautica et Astronautica Sinica,2010,31(7):1426-1432.
[30]李鸿炜.人体全消化道生理参数介入式遥测系统定位技术研究[D].上海:上海交通大学,2009:95-113.
[31] A. Sambasiva Rao, Raj Kumar. Implementation of Adaptive Filter Algorithm for UnderwaterAcoustic System[J]. International Journal of Recent Trends in Engineering,2009,2(2):13-15.
[32] Chai Yi, Ling Rui, Zhang Zhifen, et al. Safety Control Decision Making Based on Multi–SourceInformation Fusion for Satellite Lauch and Flight[C]. Control and DecisionConference,2008:3689-3692.
[33] Yang Xiaomei, Zhou Chenghu, Gong Jianming, et al. Research on Extracting Method ofMicro-Scale Remote Sensing Information Combination and Application in Coastal Zone[J]. ActaOceanologica Sinica,2009,5:123-134.
[34] Xinyuan Wang, Zhenya Guo, Li Wu, et al. Extraction of Palaeochannel Information from RemoteSensing Imagery in the East of Chaohu Lake, China[J]. Frontiers of EarthScience,2012,1:115-129.
[35] Nour-Eddin EI Faouzi, Henry Leung, Ajeesh Kurian. Data Fusion in Intelligent TransportationSystems: Progress and Challenges-A Survey[J]. Information Fusion,2011,12(1):4-10.
[36] Al Ozonoff, Fabio Cuzzolin, Paul Snow. Special Issue on Information Fusion Applications toHuman Health and Safety[J]. Information Fusion,2012,13(2):102-104.
[37] Depin Peng, Xingquan Zuo, Jianping Wu, et al. A Kalman Filter Based Information FusionMethod for Traffic Speed Estimation[C]. Power Electronics and Intelligent TransportationSystem,2009:374-379.
[38] Lars A., A. Andersson. Multi-Robot Information Fusion[D]. Sweden: Link¨opingUniversity,2008:79-86.
[39]高慧英.基于多传感器信息融合的移动机器人避障系统研究[D].哈尔滨:哈尔滨工业大学,2010:17-38.
[40]曹红玉.基于信息融合的移动机器人定位与地图创建技术研究[D].北京:北京邮电大学,2010:23-29.
[41]徐曼.基于智能融合模型的心脏病急救决策鲁棒性研究[D].天津:天津大学,2011:39-77.
[42] Lei Wang, Bin Li, Lian-fang Tian. Multi-model Medical Image Fusion Using the Inter-scale andIntra-scale Dependencies Between Image Shift-invariant Shearlet Coefficients[J]. InformationFusion,2012:3-17.
[43] Xiaohua Liu. Research of Intelligent Fault Diagnosis Model on Multi-Information Fusion[J].Journal of Computers,2011,6(6):1254-1261.
[44] Yi Liu, Ying Li, Yi-jia Cao,et al. Forward and Backward Models for Fault Diagnosis Based onParallel Genetic Algorithms[J]. Journal of Zhejiang University(Science A: An InternationalApplied Physics&Engineering Journal),2008,10:36-45.
[45] Shanchieh J. Yang, Adam Stotz, Jared Holsopple, et al. High Level Information Fusion forTracking and Projection of Multistage Cyber Attacks[J]. Information Fusion,2009(10):107-121.
[46] P. Minvielle, A. Doucet, A. Marrs, et al. A Bayesian Approach to Joint Tracking and Identificationof Geometric Shapes in Video Sequences[J]. Journal of Image and VisionComputing,2010,28(1):111-123.
[47] Helldin T, Erlandsson T. Automation Guidelines for Introducing Survivability Analysis in FutureFighter Aircraft[C]. Proceedings of the International Council of the AeronauticalSciences,2012:23-28.
[48]郭英见.基于信息融合的国有商业银行信用风险评估研究[D].哈尔滨:哈尔滨工业大学,2010:33-54.
[49]赵静娴,杜子平.基于神经网络和决策树相结合的信用风险评估模型研究[J].北京理工大学学报(社会科学版),2009,11(1):76-79.
[50]吕晓燕,罗立民,李祥生,等.基于机器学习的计算机辅助诊断模型的研究[J].计算机工程与应用,2008,35:240-242.
[51] Elizabeth S. Bumside, MD, MS. Byaesian Networks: Computer-assisted Diangosis Support inRadiology[J]. Academic Radiology,2005,12:422-430.
[52]李新胜,白净.生理信息融合技术的研究进展[J].生物医学工程学杂志,2000,17(4):464-468.
[53]范子雄.基于多生理信息融合的医疗诊断建模方法研究[D].西安:西北工业大学,2006:48-61.
[54]雷建和.基于多源信息融合的人体运动分析与建模研究[D].合肥:中国科学技术大学,2006:35-53.
[55]庞兴梅.基于数据融合的心率估计算法及监控仪错误报警抑制的研究[D].济南:山东大学,2008:46-53.
[56]杨军,俞梦孙,王宏山,等.多参数信息融合实现非脑电的睡眠结构分期[J].中国生物医学工程学报,2006,25(3):232-239.
[57]何苗.信息融合技术在中医舌象诊断系统中的应用[D].哈尔滨:哈尔滨工业大学,2007:9-12.
[58]王琦,张爱华.心电脉搏信息融合在亚健康状态识别中的应用[J].生物医学工程学杂志,2009,26(6):13-17.
[59]魏建明.基于集成计算智能的图像信息融合技术研究[D].上海:上海大学,2005:35-46.
[60]罗堪.基于信息融合的心血管信号处理方法研究[D].重庆:重庆理工大学,2011:17-28.
[61] Klaus-Dieter Sommer, Olaf Kühn, Fernando Puente León, et al. A Bayesian Approach toInformation Fusion for Evaluating the Measurement Uncertainty[J]. Robotics and AutonomousSystems,2009,57(3):339-344.
[62] Zaruhi R, Howard S, Jacqueline S, et al. Bayesian Information Fusion Networks forBiosurveillance Applications[J]. J Am Med Inform Assoc,2009,16:855-863.
[63] Shyamala G, James R. Emergency Department Triaging of Admitted Stroke Parients-A BayesianNetwork analysis[J]. Health Informatics Journal,2011,17(4):294-312.
[64] Mihai Cristian Florea, Eloi Boss. Dempster-Shafer Theory:Combination of Information UsingContextual Knowledge[C].12th International Conference on Information FusionSeattle,USA,2009:522-528.
[65] Wei Zhou, Ying Ji Liu, Qing Fu Cao, et al. Fault Diagnosis of Engine Based on ImprovedDempster-Shafer Information Fusion Method[J].Applied Mechanics andMaterials,2009,16-19:1310-1317.
[66] Yang Jianping, Huang Hongzhong, Miao Qing, et al. A Novel Information Fusion Method Basedon Dempster-Shafer Evidence Theory for Conflict Resolution[J]. Intelligent DataAnalysis,2011,15(3):399-411.
[67] Dehuai Zeng, Jianming Xu. Data Fusion for Traffic Incident Detection Using D-S EvidenceTheory with Probabilistic SVMs[J]. Journal of Computers,2008,3(10):36-43.
[68] Wilkins, Peter. An Investigation into Weighted Data Fusion for Content-based MultimediaInformation Retrieval[D]. Dublin City University,2009:23-37.
[69] Jiang Xiangyuan, Zhang Huanshui, Wang Wei. NLOS Error Mitigation with Information FusionAlgorithm for UWB Ranging Systems[J].The Journal of China Universities of Posts andTelecommunications,2012,19(2):22-29.
[70] Xiao-Jun Sun, Yuan Gao, Zi-Li Deng, et al. Multi-model Information Fusion Kalman Filtering andWhite noise Deconvolution[J]. Journal Information Fusion,2010,11(2):163-173.
[71] Peng Wang, Jiye Zhang. The Information Fusion Kalman Filter Weighted by Scalars of DiagonalMatrices for Sequential Processing[C].3th International Conference on Information Technologyand Computer Science,2011:13-16.
[72] Gui Li Tao, Zi Li Deng. The Self-Tuning Distributed Information Fusion Kalman Filter forARMA[J]. Applied Mechanics and Materials,2011,48-49:1305-1309.
[73] Shi Yu, Bart De Moor, Yves Moreau. Clustering by Heterogeneous Data Fusion: Framework andApplications. NIPS workshop,2009.
[74] Ayad, H.G, Kamel M.S. Cumulative Voting Consensus Method for Partitions with a VariableNumber of Clusters[J]. IEEE Trans. PAMI,2010,30:160-173.
[75] Su Hong-Sheng. Multi-source Fuzzy Information Fusion Method Based on Bayesian OptimalClassifier[J]. Acta Automatica Sinica,2008,34(3):282-287.
[76] Kevin L, Ronda R. Fuzzy Fusion: an Application Architecture for Multisource InformationFusion[J]. Proceedings of SPIE,2009:324-345.
[77] Julien Montagner, Vincent Barra. Multilevel Informaiton Fusion: a Mixed FuzzyLogic/Geometrical Approach with Applications in Brain Image Processing[J]. Sensor and DataFusion,2009:299-322.
[78] Helen Zhang, Gang Shen, David Jin. Based on Information Fusion Integrated Wavelet NeuralNetwork Fault Diagnosis[J]. Advanced Material Research,2011,219-220:1077-1080.
[79] Liu Jin. Applications of Information Fusion Based on Fuzzy Neural Network to RotatingMachinery Fault Diagnosis[C].3th Intelligent Informaiton Technoloth ApplicationWorkshops,2009:344-347.
[80] Prasad S., Li, W, Fowler, J. E., et al. Information Fusion in the Redundant-Wavelet-TransformDomain for Noise Robust Hyperspectral Classification[J]. Geoscience and Remote Sensing, IEEETrans,2012,99:1-13.
[81] Bai Lang, Lei Xusheng, Sheng Wei, et al. Method of Small Unmanned Aerial Rotorcraft AltitudeInformaiton Fusion Based on Wavelet Filter[J]. Journal of Beijing University of Aeronautics andA,2012,38(5):659-664.
[82] Liu Dong. A Study on Information Fusion Methodology Based on Rough Set and NeuralNetwork[C].5th International Conference on New Trend in Informaion Science and ServiceScience,2011:107-110.
[83] Liu Hui, Chen Xiaohui, Liu Yinfeng. Multi-sensor Information Fusion Based on Rough Set andFuzzy Kohonen Clus-tering Network[J]. Journal of Electronic Measurement andInstrument,2010,3:37-43.
[84] Xin Zhou, Huaxiang Zhang. An Algorithm of Text Categorization Based on Similar Rough Set andFuzzy Cognitive Map[C].5th International Conference on Fuzzy Systems and KnowledgeDiscover,2008(3):127-131.
[85] Meng-Ju Han, Jing-Huai Hsu, Kai-Tai Song,et al. A New Informaiton Fusion Method for BimodalRobotic Emotion Recognition[J]. Journal of Computers,2008,3(7):39-47.
[86] Shengyi Li, Yingchun Liu, Rongbo Zhu, et al. Bearing Fault Diagnosis Based on Multi-SensorInformation Fusion with SVM[J]. Applied Mechanics and Materials,2010,34-35:995-999.
[87] Yanhui Wang, Chenchen Zhang, Jun Luo. Study on Information Fusion Algorithm and ApplicationBased on Improved SVM[C].13th International IEEE Conference on Intelligent TransportationSystems,2010:1271-1276.
[88]翟俊海.基于小波变换和模糊粗糙集技术的图像识别[D].保定:河北大学，2010:20-46.
[89]黄雷,南建国,隋永华,等.基于模糊神经网络的平显设备故障诊断研究[J].计算机应用研究,2011,28,1:37-44.
[90]雷蕾,王晓丹.结合SVM与DS证据理论的信息融合分类方法[J].计算机工程与应用,2012:1-6.
[91] Guangzheng Li, Tao Wang. A New Model for Information Fusion Based on Grey Theory[J].Information Technology Journal,2011,10(1):189-194.
[92] Fengshan Wang, Hongjun Zhang, Wanhong Zhu, et al. Damage Information Fusion Model toMilitary Engineering Based on Intellectualized Structure[C].10th International Conference onComputing, Control and Industrial Engineering,2010,1:333-336.
[93] Blanc Christophe, Checchin Paul, Gidel Samuel, et al. Data Fusion Performance Evaluation forDissimilar Sensors: Application to Road Obstacle Tracking[J]. Sensor and DataFusion,2009,1:57-70.
[94] Stenfan Jaeger, Su-Shing Chen. Information Fusion for Biological Prediction[J]. Journal of DataScience,2010(8):269-288.
[95]孔庆杰.信息融合理论及其在交通监控信息处理中的应用[D].上海:上海交通大学，2010:54-88.
[96]安素珍.六自由度仿生机器马运动平台分析及实验研究[D].秦皇岛:燕山大学,2009:55-64.
[97]赵静波.六自由度仿生机器马的系统设计与建模控制研究[D].秦皇岛:燕山大学,2009:21-46.
[98]理查德摩雷,李泽湘.机器人操作的数学导论[M].北京:机械工业出版社,1997:108-110.
[99]朱奇光.机器马并联平台建模性能分析及控制策略研究[D].秦皇岛:燕山大学,2011:17-51.
[100]赵立兴,赵静波,王洪瑞,等.一种新型仿生机器马的控制系统设计[C].第十九届中国过程控制会议,中国,北京,2008:60-64.
[101]王洪瑞,安素珍,赵立兴.基于LabVIEW的仿生型机器马的软件设计[J].微计算机信息,2009,25(9):39-41.
[102]宋洋.生理信息融合在仿生机器马中的应用[D].秦皇岛:燕山大学,2009:29-39.
[103]杨国杰.基于生理信息融合的运动评价系统结构及算法[D].保定:河北大学,2009:31-41.
[104]施立涛.多传感器信息融合中的时间配准技术研究[D].长沙:国防科学技术大学,2010:56-69.
[105]余建军,刘维国,李博.多传感器混合式融合结构设计及算法研究[J].舰船电子对抗,2011,34(3):58-62.
[106] Wu Shengli, Bi Yaxin, Zeng Xiaoqin, et al. Assigning Appropriat Weights for the LinearCombination Data Fusion Method in Information Retrieval[J]. Information Processing andManagement,2009,45:413-426.
[107] Anand A Bardwaj M., Anandaraj K., Kapil S.Vasuhi, et al. Multi-Sensor Data Fusion MethodsUsing Sensor Data Compression and Estimated Weights[C]. IEEE International Conference onSignal Processing Communication and Networking Madras Institute ofTechnology,2008:250-254.
[108] Gao Shesheng, Feng Zhihua, Zhong Yongnin, et al, Random Weight Estimation of Parameters inGeneralized Gaussian Distribution[J]. Information Science,2008,178:2275-2281.