基于步态触觉特征的生物特征识别
|
摘要
通信技术和互联网的飞速发展从根本上影响了人类的生活方式,社会对于身份认证的准确性、安全性和实用性提出了更高的要求,生物特征识别技术受到了广泛的关注。基于步态触觉特征的生物特征识别方法是一种新兴的身份识别技术,与其它生物特征识别技术相比,基于步态触觉特征的身份识别具有独特的优点,第一,步态触觉信息的采集并不需要被测者的配合,可采取远距离非接触式的采集方式,不会涉及到隐私等问题；第二,步态主要由先天因素和后天因素影响,先天因素主要是指人体的脚型骨骼,后天因素则包括成长环境、习惯等,因此步态具有特定性和相对稳定性,不易伪装和模仿,非常适合用于生物特征识别。
基于步态触觉特征的生物特征识别才刚刚起步,有关这方面的研究非常少,因此本文在介绍步态触觉信息的基础上,深入研究了如何利用步态触觉特征完成身份识别,全文的主要研究工作如下：
首先简要介绍了步态触觉特征的生理本质、分类、模型和应用,随后主要针对三维地面反作用力,详细说明了实现生物特征识别的步骤以及需要解决的难点。
在分析常用步态触觉信息获取装置的原理和不足的基础上,设计研制了一种包括压力测试板和三维测力台的测量平台,该测量平台能够测量包括足底压力分布和三维地面反作用力在内的完整步态触觉信息。利用该测量平台获取了完整步态触觉信息,建立了步态触觉信息数据库,随后针对步态触觉信息信号的特点,选取适当的方式对数据库中的数据进行去噪处理,有效地消除了噪声,又较好地保留了原始信号中的有效特征点,最后应用去噪后的信号,考察了三维地面反作用力的重复性和唯一性,证明了其满足进行生物特征识别的基本条件。
接下来讨论了从原始信号中提取有效特征的方式,经过去噪处理后的信号中包含了大量的有用特征,如何提取这些特征对提高识别的准确性十分重要,通过分析常用特征提取方法的原理和适用范围,结合考虑GRF信号的特点,选取小波包分解作为特征提取方法,对原始信号进行大量不同的分解,提高信号的时频分辨率。通过实验对步态触觉信息数据库中的样本数据进行了分析,将原始信号分解到不同的频段上,选用能最清晰表现信号特征的小波包系数作为初始特征表征,为身份识别的下一步提供更精确的数据。
随后讨论了特征选择和识别的方法,特征选择是模式识别中的关键步骤,它可以减少冗余特征,提供更快和更有效的模型,特征选择子集往往决定了最终的识别效率。本文提出了混合型的特征选择方法：采用基于模糊集的特征选择法进行首次特征选择,再利用遗传算法或蚁群算法进行二次特征挑选,在二次特征挑选中会用到分类器,支持向量机能够避免产生局部最小值,确保得到有效解,并且对小样本识别问题尤为有效,因此被用做分类。为了展示算法的有效性,采用它对步态触觉特征数据库中的数据进行分析,通过识别率比较和特征重构,比较了单纯采用一步特征选择和采用混合算法的效率,也对遗传算法和蚁群算法的效率进行了对比。
前面的几章介绍了基于单步步态触觉特征的生物识别算法,在此研究的基础上,介绍了基于多步步态触觉信息的生物特征识别算法,构建了基于步态触觉特征的生物特征识别系统,详细说明了系统结构和算法流程,并利用该系统建立了
一个步态触觉信息数据库,通过识别测验验证了所提出的识别算法的有效性和可行性,最后利用所提取的最优特征子集进行信号重构,说明了所提取的步态触觉特征的意义。
The rapid development of telecommunication technology and internet has fundamentally changed people's lifestyle, and the society proposes higher demand on the veracity, security and practicability of personal authentication, therefore, biometric authentication technology has drawn wide attention around the world.
Plantar pressure and ground reaction force (GRF) based biometric authentication method is a novel personal identification technology. Compared with other methods, it has distinct advantages:first, the measurement of the information does not need the cooperation of the targeted subjects, for it can collect the information without privacy intrusion; second, plantar pressure and ground reaction force are determined by innate and postnatal factors:innate factors include the bone structure of human foot while postnatal factors refer to the environment, personal habits and so on. Therefore, these characteristics are distinctive, relatively stable and hard to disguise, making them perfect for using in biometric authentication.
Research on biometric authentication based on plantar pressure and GRF is just started, and there's little information on it, thus this paper will first introduce some basic knowledge about plantar pressure and GRF; then it will deeply study on how to accomplish personal identification with them, the main works of the dissertation are as follows:
The first part gives brief introduction of the characteristics'physiological feature, type, model and application, while focusing on the steps and key problems in biometric authentication using GRF.
Based on the analysis of the principle and deficiency of the popular information acquisition instruments of plantar pressure and ground reaction force, a platform combining pressure platform and force platform was designed and developed, and it can measure plantar pressure and ground reaction force at the same time. Using this platform, information was collected from different people, and a database was established. Considering the signal's feature, a suitable method was used to denoising the original information, while maintaining some distinctive features. The repeatability of the signal for the same person and the uniqueness of the signal for different people were tested, proving that the signal is suitable to be used in biometric authentication.
After that the paper discussed how to extract effective features from the denoised signals, which contain large amounts of useful features and how to extract them is very important for improving the efficiency of the authentication. Analyzing the principle of some popular feature extraction method and considering the characteristics of the GRF signals, wavelet packet decomposition (WPD), which can yield a large number of different decompositions and improve the time-frequency resolution, was used for this purpose. Experiments were carried to analyse subjects in the database, during which the original signals were decomposed to different frequencies, and the WP coefficients, which can best represent the characteristics of the signals were chosen as the original feature representation.
Feature selection and classification method were discussed in the next chapter. Feature selection, which can reduce the dimensionality of the feature and provide better and more effective model, is a key step in authentication, for the feature subsets have a decisive role in determining the classification efficiency. A hybrid feature selection method was proposed:in the first step, a fuzzy set based feature selection criterion was used to drop unrelated features while genetic algorithm (GA) or ant colony optimization (ACO) was used in the second step to pick up pivotal ones. Support vector machine (SVM) was used for classification during the second selection process, for it can effectively avoid local optimum, guarantee best resolution and is very suitable in small sample classification problems. To show the availability of the algorithms, experiments were made to analyse the database, the classification efficiency and feature reconstruction of the pure one-step feature selection method and the proposed algorithms were compared, as well as the effect of using GA and ACO in the second selection process.
Based on the above researches, the last part of the paper introduced the algorithm of biometric authentication based on multi-cycle GRF and a biometric authentication system was established. The system structure and proposed algorithm were explained in detail, and a database was established. The verification and practicability of the system was proved with authentication test, and signal reconstruction was carried out to discuss the essence of the selected feature.
基于步态触觉特征的生物特征识别才刚刚起步,有关这方面的研究非常少,因此本文在介绍步态触觉信息的基础上,深入研究了如何利用步态触觉特征完成身份识别,全文的主要研究工作如下：
首先简要介绍了步态触觉特征的生理本质、分类、模型和应用,随后主要针对三维地面反作用力,详细说明了实现生物特征识别的步骤以及需要解决的难点。
在分析常用步态触觉信息获取装置的原理和不足的基础上,设计研制了一种包括压力测试板和三维测力台的测量平台,该测量平台能够测量包括足底压力分布和三维地面反作用力在内的完整步态触觉信息。利用该测量平台获取了完整步态触觉信息,建立了步态触觉信息数据库,随后针对步态触觉信息信号的特点,选取适当的方式对数据库中的数据进行去噪处理,有效地消除了噪声,又较好地保留了原始信号中的有效特征点,最后应用去噪后的信号,考察了三维地面反作用力的重复性和唯一性,证明了其满足进行生物特征识别的基本条件。
接下来讨论了从原始信号中提取有效特征的方式,经过去噪处理后的信号中包含了大量的有用特征,如何提取这些特征对提高识别的准确性十分重要,通过分析常用特征提取方法的原理和适用范围,结合考虑GRF信号的特点,选取小波包分解作为特征提取方法,对原始信号进行大量不同的分解,提高信号的时频分辨率。通过实验对步态触觉信息数据库中的样本数据进行了分析,将原始信号分解到不同的频段上,选用能最清晰表现信号特征的小波包系数作为初始特征表征,为身份识别的下一步提供更精确的数据。
随后讨论了特征选择和识别的方法,特征选择是模式识别中的关键步骤,它可以减少冗余特征,提供更快和更有效的模型,特征选择子集往往决定了最终的识别效率。本文提出了混合型的特征选择方法：采用基于模糊集的特征选择法进行首次特征选择,再利用遗传算法或蚁群算法进行二次特征挑选,在二次特征挑选中会用到分类器,支持向量机能够避免产生局部最小值,确保得到有效解,并且对小样本识别问题尤为有效,因此被用做分类。为了展示算法的有效性,采用它对步态触觉特征数据库中的数据进行分析,通过识别率比较和特征重构,比较了单纯采用一步特征选择和采用混合算法的效率,也对遗传算法和蚁群算法的效率进行了对比。
前面的几章介绍了基于单步步态触觉特征的生物识别算法,在此研究的基础上,介绍了基于多步步态触觉信息的生物特征识别算法,构建了基于步态触觉特征的生物特征识别系统,详细说明了系统结构和算法流程,并利用该系统建立了
一个步态触觉信息数据库,通过识别测验验证了所提出的识别算法的有效性和可行性,最后利用所提取的最优特征子集进行信号重构,说明了所提取的步态触觉特征的意义。
The rapid development of telecommunication technology and internet has fundamentally changed people's lifestyle, and the society proposes higher demand on the veracity, security and practicability of personal authentication, therefore, biometric authentication technology has drawn wide attention around the world.
Plantar pressure and ground reaction force (GRF) based biometric authentication method is a novel personal identification technology. Compared with other methods, it has distinct advantages:first, the measurement of the information does not need the cooperation of the targeted subjects, for it can collect the information without privacy intrusion; second, plantar pressure and ground reaction force are determined by innate and postnatal factors:innate factors include the bone structure of human foot while postnatal factors refer to the environment, personal habits and so on. Therefore, these characteristics are distinctive, relatively stable and hard to disguise, making them perfect for using in biometric authentication.
Research on biometric authentication based on plantar pressure and GRF is just started, and there's little information on it, thus this paper will first introduce some basic knowledge about plantar pressure and GRF; then it will deeply study on how to accomplish personal identification with them, the main works of the dissertation are as follows:
The first part gives brief introduction of the characteristics'physiological feature, type, model and application, while focusing on the steps and key problems in biometric authentication using GRF.
Based on the analysis of the principle and deficiency of the popular information acquisition instruments of plantar pressure and ground reaction force, a platform combining pressure platform and force platform was designed and developed, and it can measure plantar pressure and ground reaction force at the same time. Using this platform, information was collected from different people, and a database was established. Considering the signal's feature, a suitable method was used to denoising the original information, while maintaining some distinctive features. The repeatability of the signal for the same person and the uniqueness of the signal for different people were tested, proving that the signal is suitable to be used in biometric authentication.
After that the paper discussed how to extract effective features from the denoised signals, which contain large amounts of useful features and how to extract them is very important for improving the efficiency of the authentication. Analyzing the principle of some popular feature extraction method and considering the characteristics of the GRF signals, wavelet packet decomposition (WPD), which can yield a large number of different decompositions and improve the time-frequency resolution, was used for this purpose. Experiments were carried to analyse subjects in the database, during which the original signals were decomposed to different frequencies, and the WP coefficients, which can best represent the characteristics of the signals were chosen as the original feature representation.
Feature selection and classification method were discussed in the next chapter. Feature selection, which can reduce the dimensionality of the feature and provide better and more effective model, is a key step in authentication, for the feature subsets have a decisive role in determining the classification efficiency. A hybrid feature selection method was proposed:in the first step, a fuzzy set based feature selection criterion was used to drop unrelated features while genetic algorithm (GA) or ant colony optimization (ACO) was used in the second step to pick up pivotal ones. Support vector machine (SVM) was used for classification during the second selection process, for it can effectively avoid local optimum, guarantee best resolution and is very suitable in small sample classification problems. To show the availability of the algorithms, experiments were made to analyse the database, the classification efficiency and feature reconstruction of the pure one-step feature selection method and the proposed algorithms were compared, as well as the effect of using GA and ACO in the second selection process.
Based on the above researches, the last part of the paper introduced the algorithm of biometric authentication based on multi-cycle GRF and a biometric authentication system was established. The system structure and proposed algorithm were explained in detail, and a database was established. The verification and practicability of the system was proved with authentication test, and signal reconstruction was carried out to discuss the essence of the selected feature.
引文
[1]中国科学技术大学科技实业总公司.基于生物特征识别的身份认证系统,技术与市场,2005(03)：22-23.
[2]Maltoni D, Maio D, Jain AK, et al. Handbook of Fingerprint Recognition. New York: Springer.2003:2-3.
[3]Jain AK, Ross A, Prabhakar S. An introduction to biometric recognition. IEEE Trans Circuits Syst Video Technol,2004,14(1):4-20.
[4]Xu S, Zhou X, Sun Y.N. A Genetic Algorithm-based Feature Selection Method for Human Identification based on Ground Reaction Force. Proceedings of the first ACM/SIGEVO Summit on Genetic and Evolutionary Computation,2009:665-670.
[5]田捷,杨鑫.生物特征识别技术理论与应用.北京：电子工业出版社.2005.9：2.
[6]Moustakas K, Tzovaras D, Stavropoulos G. Gait Recognition Using Geometric Features and Soft Biometrics. IEEE SIGNAL PROCESSING LETTERS,2010,17(4):367-370.
[7]Johansson G. Visual perception of biological motion and a model for its analysis. Perception and Psychophysics,1973,14(2):201-211.
[8]励建安.减重训练的研究进展.中华物理医学与康复杂志,2002,24(12)：759-761.
[9]杨雅琴,张通.正常步态和偏瘫步态的特点及对比,2003,9(10)：608-609.
[10]Plamondon R, Lorette G. Automatic signature verification and writer identification-the state of the art. Pattern Recognition,1989,22(2):107-131.
[11]Dawson MR.Gait recognition. Department of Computing, Imperial College of Science, Technology and Medicine, London,2002.
[12]Sarkar S, Phillips PJ, Liu Z, et al. The human ID gait challenge Problem:data sets, performance and analysis. IEEE Transaction on Pattern Analysis and Machine Intelligence. 2005,27(2):162-177.
[13]Kim D, Paik J. Gait recognition using active shape model and motion prediction. IET Comput. Vis.,2010,4(1):25-36.
[14]Cho CW, Chao WH, Lin SH et al. A vision-based analysis system for gait recognition in patients with Parkinson's disease. Expert Systems with Applications,2009,36:7033-7039.
[15]Yang XC, Zhou Y, Zhang TH. et al. Gait recognition based on dynamic region analysis. Signal Processing,2008,88:2350-2356.
[16]Boulgouris NV, Chi ZX. Gait Recognition Using Radon Transform and Linear Discriminant Analysis. IEEE Transactions on Image Processing,2007,16(3):731-740.
[17]王亮,胡卫明,谭铁牛.基于步态的身份识别,计算机学报.2003,26(3)：353-360.
[18]Zhang YY, Wu XJ, Qi L, et al. A New Gait Analyzing Method under Monocular Camera. Proceedings of the 1st International Conference on Bioinformatics and Biomedical Engineering,2007:577-580.
[19]Yang X, Zhou Y, Zhang T. Gabor phase based gait recognition. Electronics Letters,2008, 44(10):620-621.
[20]王亮,胡卫明,谭铁牛.人运动的视觉分析综述,计算机学报,2002,(3)：225-237.
[21]雷航,童莉,平西建.平面赤足迹特征分析与身份识别方法,计算机辅助设计与图形学学报,2008,20(5)：659-664.
[22]兰绍江.鞋底常态磨损特征再现的研究,刑事技术,1982：6.
[23]Rossi S, Patane F, Scalise L, et al. Centre of pressure in dynamic posturography:a comparison among systems based on a pressure matrix and a force platform, MEASUREMENT SCIENCE& TECHNOLOGY,2010,21(1):015801.
[24]Hoshino Takayuki, Tomono Masanori, Suzuki Takafumi, et al. A Gait Support System for Human Locomotion without Restriction of the Lower Extremities Preliminary Mechanism and Control Design. Proceedings of the 28th Annual International Conference of the IEEE Engineering in Medicine and Biology Society,2006:2950-2953.
[25]Lemairc Edwaid D, Biswas Ajoy, Kofman Jonathan. Plantar Pressure Parameters for Dynamic Gait Stability Analysis. Proceedings of the 28th Annual International Conference of the IEEE Engineering in Medicine and Biology Society,2006:4465-4468.
[26]Surdilovic D., Jinyu Z, Bernhardt R. Gait phase and centre of pressure measuring system; Proceedings of the 2004 IEEE International Conference on Industrial Informatics,2004: 331-334.
[27]JK Gurney, UG Kersting, D Rosenbaum. Between-day reliability of repeated plantar pressure distribution measurements in a normal population. Gait Posture 27 (2008):706-709.
[28]Hannula M, Sakkinen A, Kylmanen A. Development of EMFI-sensor based pressure sensitive insole for gait analysis. Proceedings of the 2007 IEEE International Workshop on Medical Measurement and Applications,2007:1-3.
[29]Venugopal G, Parmar BJ, Rajanna K, et al. Multi-point Sensing System for Plantar Pressure Measurement. Sensors,2007:978-981.
[30]Sugimoto C, Tsuji M, Lopez G, et al. Development of a behavior recognition system using wireless wearable information devices. Proceedings of the 1st International Symposium on Wireless Pervasive Computing,2006:5.
[31]P Catalfamo, D Moser, S Ghoussayni, et al. Detection of gait events using an F-Scan in-shoe
pressure measurement system. Gait& Posture 2008:420-426.
[32]K Kong, M Tomizuka. Smooth and continuous human gait phase detection based on foot pressure patterns. Proceedings of the 2008 IEEE International Conference on Robotics and Automation,2008:3678-3683.
[33]Claudia Giacomozzi, Velio Macellari. Piezo-Dynamometric Platform for a More Complete Analysis of Foot-to-Floor Interaction. IEEE Transactions on Rehabilitation Engineering, 1997,5(4):322-330.
[34]Jeffrey R. Mackey, Brian L. Davis. Simultaneous shear and pressure sensor array for assessing pressure and shear at foot/ground interface, Journal of Biomechanics,2006,39(15): 2893-2897.
[35]Julie EP, James OH, Brian LD. Simultaneous measurement of plantar pressure and shear forces in diabetic individuals. Gait& posture 2002,15:101-107.
[36]王立平,李建设.足底压力测量技术的发展现状与应用研究,浙江体育科学,2004,24(1)：40-43.
[37]Ken-Ichi Akasofu, Michael R. Neuman. A Thin-film Variable Capacitance Shear Force Sensor for Medical and Robotics Applications. Proceedings of the IEEE Engineering Conference in Medicine and Biology Society.1991,13(4):1601-1602.
[38]Ann M. Lebar, Gerald F. Harris, Jacqueline J. Wertsch, et al. Development of a miniature plantar shear force sensing transducer. Proceedings of the IEEE 15th Annual International Conference On Engineering in Medicine and Biology Society.1993:989-990.
[39]R. Hosein, M. Lord. A study of in-shoe plantar shear in normals. Clinical Biomechanics, 2000(15):46-53.
[40]Chevalier TL, Hodgins H, Chockalingam N. Plantar pressure measurements using an in-shoe system and a pressure platform:A comparison, Gait& Posture,2010,31(3):397-399.
[41]Rossi S, Patane F, Scalise L et al. Centre of pressure in dynamic posturography:A comparison among systems based on a pressure matrix and a force platform, Measurement Science and Technology,2010,21(1).
[42]Serafeim P. Moustakidis, John B. Subject Recognition Based on Ground Reaction Force Measurements of Gait Signals, IEEE TRANSACTIONS ON SYSTEMS, MAN, AND CYBERNETICS-PART B:CYBERNETICS,2008,38(6):1476-1485.
[43]Srivastava A, Taly AB, Gupta A, et al. Post-stroke balance training:Role of force platform with visual feedback technique, JOURNAL OF THE NEUROLOGICAL SCIENCES,2009, 287(1-2):89-93.
[44]Saxe, D.M.Foulds, R.A. Analysis of gait event detection algorithms applied to movement
data collected on a sloped treadmill, Proceedings of the 2003 Bioengineering Conference,
[45]Orlin MN, McPoil TG. Plantar pressure assessment. Phys Therapy.2000,80:399-409.
[46]BenAbdelkader C, Culter R and Davis L.Stride and cadence as a biometric in automatic person identification and verification. Proceedings of 2002 International Conference on Automatic Face and Gesture Recognition,2002:357-362.
[47]叶德明,中国军事百科全书·军事技术,中国军事科学出版社,2009.
[48]Campolo D, Cavallo G, Keller F, et al. A mechatronic system for in-plane Ground-Reaction-Force measurement for tremor analysis in animal models, IEEE/RSJ International Conference on Intelligent Robots and Systems,2005:2505-2510.
[49]Begg RK and Rahman SM. A method for the reconstruction of ground reaction force-time characteristics during gait from force platform recordings of simultaneous foot falls. IEEE Trans. Biomed. Eng.47(4):547-551.
[50]J. Kamruzzaman and R. Begg. An intelligent model for reconstruction of stance time from faulty gait recording, Proceedings of the 4th international conference on hybrid intelligent systems,2005:26-31.
[51]Atsuo Murata. Effects of duration of immersion in a virtual environment on postural stability, International Journal of Human-Computer Interaction,2004,17(4):464-477.
[52]RS Lakes, K Korttila, D Eltoft, et al. instrumented Force Platform for Postural Sway Studies, IEEE Trans Biomed Eng.1981,28(10):725-9
[53]Lei Jianhe, Gao Zhen, Song Quanjun, et al. Analysis of GRF by Means of Wavelet Transform for the Performance Diagnosis of Weight Lifter, Proceedings of the 2006 IEEE International Conference on Information Acquisition,2006:388-392.
[54]钱竞光,宋雅伟,叶强等.步行动作的生物力学原理及其步态分析,南京体育学院学报(自然科学版)2006(04)：1-7.
[55]湖南公安高等专科学校精品课程,http://it.hnpolice.com/jpkc/2007/hjjy/jiaoan24.html.
[56]D. Gordon, E. Roberson, Graham E. Caldwell, et al. Research Methods in Biomechanics. USA:Human Kinetics,2004
[57]Young-Hoo Kwon. Theoretical Foundation. [2008] (1998). http://www.kwon3d.com/theory/grf/cop.html.
[58]Shi Chen, Youxing Gao. An Invariant Appearance Model for Gait Recognition. Proceedings of IEEE International Conference on Multimedia and Expo.2007:1375-1378.
[59]RJ. Butler, J. Hamill. I Davis. Effect of footwear on high and low arched runners'mechanics during a prolonged run, Gait& Posture,2007,26:219-225.
[60]Arvikar R., Seireg A. Pressure distribution under the foot during static activities. Eng In Med,
1980,9:99-103.
[61]Shiang TY, Lee SH, Lee SJ, et al. Evaluating different footprint parameters as a predictor of arch height. IEEE Engineering in Medicine and Biology,1998:62-66.
[62]Li H, Lin QZ, Wang QJ, et al. Research on Spectrum Denoising Methods Based on the Combination of Wavelet Package Transformation and Mathematical Morphology, SPECTROSCOPY AND SPECTRAL ANALYSIS,2010,30(3):644-648.
[63]文莉,刘正士,葛运建,小波去噪的几种方法,合肥工业大学学报,2002(25)：2.
[64]Lei Hong, Yu-Jing Guan, Lei Zhang. An a-trous algorithm based threshold shrinkage denoising method for blood oxygen signal, Proceedings of the 2007 International Conference on Wavelet Analysis and Pattern Recognition,2007,4:1669-1673.
[65]Liu Wei, Ma Zhengming. Wavelet Image Threshold Denoising Based on Edge Detection. IMACS Multiconference on Computational Engineering in Systems Applications,2006,1: 72-78.
[66]Shang L, Herold G, Jaeger J, et al. Analysis and identification of HVDC system faults using wavelet modulus maxima. Proceedings of the 7th International Conference on AC-DC Power Transmission,2001:315-320.
[67]Hong-Qiao Wang, Fu-Chun Sun, Yan-Ning Cai, et al. Edge-enhanced speckle suppression using curvelet transform with an optimal soft thresholding, Proceedings of the 2007 International Conference on Wavelet Analysis and Pattern Recognition,2007,1:204-209.
[68]Zhao Ting, Yu Yang. Threshold Denoising Analysis of Machinery Vibrating Signal Based on Wavelet Transform, Proceedings of the 8th International Conference on Electronic Measurement and Instruments,2007,3:1041-1044.
[69]特征提取,http://baike.baidu.com/view/1312693.htm.
[70]王首勇,朱光喜,唐远炎.应用最优小波包变换的特征提取方法,电子学报,2003,31(7)：1305-1308.
[71]Feature extraction, http://en.wikipedia.org/wiki/Feature_extraction.
[72]孙延奎,小波分析及其应用,机械工业出版社,2005.
[73]Lawton W, Lee SL, Shen ZW. An algorithm for matrix extension and wavelet construction. Mathematics of Computation,1996,65:723-737.
[74]Coifman RR. Wickhauster MV, Wavelets and adapted waveform analysis a toolkit for signal processing and numerical analysis. Proceedings of symposia in Applied Mathematics.1983, 47:119-153.
[75]Strela V, Vogan A. Multiwavelets theory and application. MIT,1996.
[76]Morlet J. Wave propation and sampling theory and complex waves. Geophysics,1982,47(2):
222-236.
[77]Y Meyer. Wavelets of algorithms and applications. New York:SIAM,1993.
[78]Daubechies, W Sweldens. Factoring wavelet transforms into lifting steps. J. Fourier Anal. 1998,4(3):245-267.
[79]飞思科技产品研发中心,小波分析理论与matlab7实现,电子工业出版社,2005.
[80]秦毅,信号小波理论与一体化小波分析仪的研究,2008.
[81]RR Coifman, Y Meyer, MV Wickerhauser. Wavelet and signal processing, in:Wavelet and Their application. Boston, US:Jones and Bartlett Publishers,1992.
[82]Wu Ting, Yan Guozheng, Yang Banghua, et al. EEG feature extraction based on wavelet packet decomposition for brain computer interface, Measurement,2008(41):618-625.
[83]边肇祺,张学工.模式识别,第二版,北京：清华大学出版社,2000.
[84]张静远,张冰,蒋兴舟.基于小波变换的特征提取方法分析,信号处理,2000,16(2)：156-162.
[85]Peng Xu and Andrew K. Chan, Optimal Wavelet Sub-band Selection using Genetic Algorithm, Geoscience and Remote Sensing Symposium,2002,1441-1443.
[86]H. Liu, H. Motoda, Feature Extraction, Construction and Selection:A Data Mining Perspective, Kluwer Academic Publishers, Norwell, MA, USA,1998.
[87]Msnoranjau Dash, Huan Liu. Feature Selection for Classification. Intelligent Data Analysis, 1997,1(3):131-156.
[88]L Xu, P Yan, T Chang. Best First Strategy for Feature Selection. Proc of 9t h Int'l Conf on Pattern Recognition.1988:706-708.
[89]C Cardie. Using Decision Trees to Improve Case Based Learning, Proc of 10th In'l Conf on Machine Learning,1993:25-32.
[90]王娟,慈林林,姚康泽.特征选择方法综述,计算机工程与科学,2005,27(12)：68-71.
[91]B Chakraborty. Genetic Algorithm with Fuzzy Fitness Function for Feature Selection. Proc of the 2002 IEEE International Symp on Industrial Electronics,2002,1:315-319.
[92]T. Sttzle, M. Dorigo. The Ant Colony Optimization Metaheuristic:Algorithms, Applications, and Advances., Handbook of Metaheuristics, Kluwer Academic Publishers, Norwell, MA, 2002.
[93]卜华龙,夏静,韩俊波.特征选择算法综述及进展研究,巢湖学院学报,2008,10(6)：41-44.
[94]John H. Holland. Adaptation in Natural and Artificial Systems, the MIT Press,1992.
[95]Sun Zehang, Bebis George, Ronald Miller. object detection using feature subset selection, Pattern Recognition,2004,37:2165-2176.
[96]DORIGO M, MANIEZZO V, COLORN IA. The ant system:Optimization by a colony of cooperating agents. IEEE Transaction on Systems, Man and Cybernetics, Part B,1996,26 (1): 29-41.
[97]叶志伟,郑肇葆,万幼川等.基于蚁群优化的特征选择新方法,2007,32(12)：1127-1130.
[98]Ozge Uncu, IB Turksen. A novel feature selection approach:Combining feature wrappers and filters, Information Sciences,2007(177):449-466.
[99]U. Fayyad, K. Irani. Multi-interval discretization of continuous-valued attributes for classification learning, Proceedings of the Thirteenth International Joint Conference on Artificial Intelligence, Chambery,1993:1022-1027.
[100]毛勇,周晓波,夏铮等.特征选择算法研究综述,模式识别与人工智能,2007,20(2)：211-218.
[101]田金兰,李奔.数据挖掘工具：分类器,计算机世界,1992。20.
[102]N Cristianini, J Shawe Taylor. An introduction to support vector machines and other kernel-based learning methods. Cambridge UK:Cambridge University Press.2000.
[103]VN.Vapnik. The nature of statistical learning. New York:SPringer-Verlag,1995.
[104]VN.Vapnik. Statistical learning theory. New York:Wiley,1998.
[105]D. Li, W. Pedrycz, and N. J. Pizzi, "Fuzzy wavelet packet based feature extraction method and its application to biomedical signal classification," IEEE Trans. Biomed. Eng., 2005,52(6):1132-1139.
[106]D. Merkle, M. Middendorf, and H. Schmeck. Pheromone evaluation in Ant Colony Optimization, Proceedings of the 26th Annual Conference of the IEEE Industrial Electronics Society,2000:22-28.
[2]Maltoni D, Maio D, Jain AK, et al. Handbook of Fingerprint Recognition. New York: Springer.2003:2-3.
[3]Jain AK, Ross A, Prabhakar S. An introduction to biometric recognition. IEEE Trans Circuits Syst Video Technol,2004,14(1):4-20.
[4]Xu S, Zhou X, Sun Y.N. A Genetic Algorithm-based Feature Selection Method for Human Identification based on Ground Reaction Force. Proceedings of the first ACM/SIGEVO Summit on Genetic and Evolutionary Computation,2009:665-670.
[5]田捷,杨鑫.生物特征识别技术理论与应用.北京：电子工业出版社.2005.9：2.
[6]Moustakas K, Tzovaras D, Stavropoulos G. Gait Recognition Using Geometric Features and Soft Biometrics. IEEE SIGNAL PROCESSING LETTERS,2010,17(4):367-370.
[7]Johansson G. Visual perception of biological motion and a model for its analysis. Perception and Psychophysics,1973,14(2):201-211.
[8]励建安.减重训练的研究进展.中华物理医学与康复杂志,2002,24(12)：759-761.
[9]杨雅琴,张通.正常步态和偏瘫步态的特点及对比,2003,9(10)：608-609.
[10]Plamondon R, Lorette G. Automatic signature verification and writer identification-the state of the art. Pattern Recognition,1989,22(2):107-131.
[11]Dawson MR.Gait recognition. Department of Computing, Imperial College of Science, Technology and Medicine, London,2002.
[12]Sarkar S, Phillips PJ, Liu Z, et al. The human ID gait challenge Problem:data sets, performance and analysis. IEEE Transaction on Pattern Analysis and Machine Intelligence. 2005,27(2):162-177.
[13]Kim D, Paik J. Gait recognition using active shape model and motion prediction. IET Comput. Vis.,2010,4(1):25-36.
[14]Cho CW, Chao WH, Lin SH et al. A vision-based analysis system for gait recognition in patients with Parkinson's disease. Expert Systems with Applications,2009,36:7033-7039.
[15]Yang XC, Zhou Y, Zhang TH. et al. Gait recognition based on dynamic region analysis. Signal Processing,2008,88:2350-2356.
[16]Boulgouris NV, Chi ZX. Gait Recognition Using Radon Transform and Linear Discriminant Analysis. IEEE Transactions on Image Processing,2007,16(3):731-740.
[17]王亮,胡卫明,谭铁牛.基于步态的身份识别,计算机学报.2003,26(3)：353-360.
[18]Zhang YY, Wu XJ, Qi L, et al. A New Gait Analyzing Method under Monocular Camera. Proceedings of the 1st International Conference on Bioinformatics and Biomedical Engineering,2007:577-580.
[19]Yang X, Zhou Y, Zhang T. Gabor phase based gait recognition. Electronics Letters,2008, 44(10):620-621.
[20]王亮,胡卫明,谭铁牛.人运动的视觉分析综述,计算机学报,2002,(3)：225-237.
[21]雷航,童莉,平西建.平面赤足迹特征分析与身份识别方法,计算机辅助设计与图形学学报,2008,20(5)：659-664.
[22]兰绍江.鞋底常态磨损特征再现的研究,刑事技术,1982：6.
[23]Rossi S, Patane F, Scalise L, et al. Centre of pressure in dynamic posturography:a comparison among systems based on a pressure matrix and a force platform, MEASUREMENT SCIENCE& TECHNOLOGY,2010,21(1):015801.
[24]Hoshino Takayuki, Tomono Masanori, Suzuki Takafumi, et al. A Gait Support System for Human Locomotion without Restriction of the Lower Extremities Preliminary Mechanism and Control Design. Proceedings of the 28th Annual International Conference of the IEEE Engineering in Medicine and Biology Society,2006:2950-2953.
[25]Lemairc Edwaid D, Biswas Ajoy, Kofman Jonathan. Plantar Pressure Parameters for Dynamic Gait Stability Analysis. Proceedings of the 28th Annual International Conference of the IEEE Engineering in Medicine and Biology Society,2006:4465-4468.
[26]Surdilovic D., Jinyu Z, Bernhardt R. Gait phase and centre of pressure measuring system; Proceedings of the 2004 IEEE International Conference on Industrial Informatics,2004: 331-334.
[27]JK Gurney, UG Kersting, D Rosenbaum. Between-day reliability of repeated plantar pressure distribution measurements in a normal population. Gait Posture 27 (2008):706-709.
[28]Hannula M, Sakkinen A, Kylmanen A. Development of EMFI-sensor based pressure sensitive insole for gait analysis. Proceedings of the 2007 IEEE International Workshop on Medical Measurement and Applications,2007:1-3.
[29]Venugopal G, Parmar BJ, Rajanna K, et al. Multi-point Sensing System for Plantar Pressure Measurement. Sensors,2007:978-981.
[30]Sugimoto C, Tsuji M, Lopez G, et al. Development of a behavior recognition system using wireless wearable information devices. Proceedings of the 1st International Symposium on Wireless Pervasive Computing,2006:5.
[31]P Catalfamo, D Moser, S Ghoussayni, et al. Detection of gait events using an F-Scan in-shoe
pressure measurement system. Gait& Posture 2008:420-426.
[32]K Kong, M Tomizuka. Smooth and continuous human gait phase detection based on foot pressure patterns. Proceedings of the 2008 IEEE International Conference on Robotics and Automation,2008:3678-3683.
[33]Claudia Giacomozzi, Velio Macellari. Piezo-Dynamometric Platform for a More Complete Analysis of Foot-to-Floor Interaction. IEEE Transactions on Rehabilitation Engineering, 1997,5(4):322-330.
[34]Jeffrey R. Mackey, Brian L. Davis. Simultaneous shear and pressure sensor array for assessing pressure and shear at foot/ground interface, Journal of Biomechanics,2006,39(15): 2893-2897.
[35]Julie EP, James OH, Brian LD. Simultaneous measurement of plantar pressure and shear forces in diabetic individuals. Gait& posture 2002,15:101-107.
[36]王立平,李建设.足底压力测量技术的发展现状与应用研究,浙江体育科学,2004,24(1)：40-43.
[37]Ken-Ichi Akasofu, Michael R. Neuman. A Thin-film Variable Capacitance Shear Force Sensor for Medical and Robotics Applications. Proceedings of the IEEE Engineering Conference in Medicine and Biology Society.1991,13(4):1601-1602.
[38]Ann M. Lebar, Gerald F. Harris, Jacqueline J. Wertsch, et al. Development of a miniature plantar shear force sensing transducer. Proceedings of the IEEE 15th Annual International Conference On Engineering in Medicine and Biology Society.1993:989-990.
[39]R. Hosein, M. Lord. A study of in-shoe plantar shear in normals. Clinical Biomechanics, 2000(15):46-53.
[40]Chevalier TL, Hodgins H, Chockalingam N. Plantar pressure measurements using an in-shoe system and a pressure platform:A comparison, Gait& Posture,2010,31(3):397-399.
[41]Rossi S, Patane F, Scalise L et al. Centre of pressure in dynamic posturography:A comparison among systems based on a pressure matrix and a force platform, Measurement Science and Technology,2010,21(1).
[42]Serafeim P. Moustakidis, John B. Subject Recognition Based on Ground Reaction Force Measurements of Gait Signals, IEEE TRANSACTIONS ON SYSTEMS, MAN, AND CYBERNETICS-PART B:CYBERNETICS,2008,38(6):1476-1485.
[43]Srivastava A, Taly AB, Gupta A, et al. Post-stroke balance training:Role of force platform with visual feedback technique, JOURNAL OF THE NEUROLOGICAL SCIENCES,2009, 287(1-2):89-93.
[44]Saxe, D.M.Foulds, R.A. Analysis of gait event detection algorithms applied to movement
data collected on a sloped treadmill, Proceedings of the 2003 Bioengineering Conference,
[45]Orlin MN, McPoil TG. Plantar pressure assessment. Phys Therapy.2000,80:399-409.
[46]BenAbdelkader C, Culter R and Davis L.Stride and cadence as a biometric in automatic person identification and verification. Proceedings of 2002 International Conference on Automatic Face and Gesture Recognition,2002:357-362.
[47]叶德明,中国军事百科全书·军事技术,中国军事科学出版社,2009.
[48]Campolo D, Cavallo G, Keller F, et al. A mechatronic system for in-plane Ground-Reaction-Force measurement for tremor analysis in animal models, IEEE/RSJ International Conference on Intelligent Robots and Systems,2005:2505-2510.
[49]Begg RK and Rahman SM. A method for the reconstruction of ground reaction force-time characteristics during gait from force platform recordings of simultaneous foot falls. IEEE Trans. Biomed. Eng.47(4):547-551.
[50]J. Kamruzzaman and R. Begg. An intelligent model for reconstruction of stance time from faulty gait recording, Proceedings of the 4th international conference on hybrid intelligent systems,2005:26-31.
[51]Atsuo Murata. Effects of duration of immersion in a virtual environment on postural stability, International Journal of Human-Computer Interaction,2004,17(4):464-477.
[52]RS Lakes, K Korttila, D Eltoft, et al. instrumented Force Platform for Postural Sway Studies, IEEE Trans Biomed Eng.1981,28(10):725-9
[53]Lei Jianhe, Gao Zhen, Song Quanjun, et al. Analysis of GRF by Means of Wavelet Transform for the Performance Diagnosis of Weight Lifter, Proceedings of the 2006 IEEE International Conference on Information Acquisition,2006:388-392.
[54]钱竞光,宋雅伟,叶强等.步行动作的生物力学原理及其步态分析,南京体育学院学报(自然科学版)2006(04)：1-7.
[55]湖南公安高等专科学校精品课程,http://it.hnpolice.com/jpkc/2007/hjjy/jiaoan24.html.
[56]D. Gordon, E. Roberson, Graham E. Caldwell, et al. Research Methods in Biomechanics. USA:Human Kinetics,2004
[57]Young-Hoo Kwon. Theoretical Foundation. [2008] (1998). http://www.kwon3d.com/theory/grf/cop.html.
[58]Shi Chen, Youxing Gao. An Invariant Appearance Model for Gait Recognition. Proceedings of IEEE International Conference on Multimedia and Expo.2007:1375-1378.
[59]RJ. Butler, J. Hamill. I Davis. Effect of footwear on high and low arched runners'mechanics during a prolonged run, Gait& Posture,2007,26:219-225.
[60]Arvikar R., Seireg A. Pressure distribution under the foot during static activities. Eng In Med,
1980,9:99-103.
[61]Shiang TY, Lee SH, Lee SJ, et al. Evaluating different footprint parameters as a predictor of arch height. IEEE Engineering in Medicine and Biology,1998:62-66.
[62]Li H, Lin QZ, Wang QJ, et al. Research on Spectrum Denoising Methods Based on the Combination of Wavelet Package Transformation and Mathematical Morphology, SPECTROSCOPY AND SPECTRAL ANALYSIS,2010,30(3):644-648.
[63]文莉,刘正士,葛运建,小波去噪的几种方法,合肥工业大学学报,2002(25)：2.
[64]Lei Hong, Yu-Jing Guan, Lei Zhang. An a-trous algorithm based threshold shrinkage denoising method for blood oxygen signal, Proceedings of the 2007 International Conference on Wavelet Analysis and Pattern Recognition,2007,4:1669-1673.
[65]Liu Wei, Ma Zhengming. Wavelet Image Threshold Denoising Based on Edge Detection. IMACS Multiconference on Computational Engineering in Systems Applications,2006,1: 72-78.
[66]Shang L, Herold G, Jaeger J, et al. Analysis and identification of HVDC system faults using wavelet modulus maxima. Proceedings of the 7th International Conference on AC-DC Power Transmission,2001:315-320.
[67]Hong-Qiao Wang, Fu-Chun Sun, Yan-Ning Cai, et al. Edge-enhanced speckle suppression using curvelet transform with an optimal soft thresholding, Proceedings of the 2007 International Conference on Wavelet Analysis and Pattern Recognition,2007,1:204-209.
[68]Zhao Ting, Yu Yang. Threshold Denoising Analysis of Machinery Vibrating Signal Based on Wavelet Transform, Proceedings of the 8th International Conference on Electronic Measurement and Instruments,2007,3:1041-1044.
[69]特征提取,http://baike.baidu.com/view/1312693.htm.
[70]王首勇,朱光喜,唐远炎.应用最优小波包变换的特征提取方法,电子学报,2003,31(7)：1305-1308.
[71]Feature extraction, http://en.wikipedia.org/wiki/Feature_extraction.
[72]孙延奎,小波分析及其应用,机械工业出版社,2005.
[73]Lawton W, Lee SL, Shen ZW. An algorithm for matrix extension and wavelet construction. Mathematics of Computation,1996,65:723-737.
[74]Coifman RR. Wickhauster MV, Wavelets and adapted waveform analysis a toolkit for signal processing and numerical analysis. Proceedings of symposia in Applied Mathematics.1983, 47:119-153.
[75]Strela V, Vogan A. Multiwavelets theory and application. MIT,1996.
[76]Morlet J. Wave propation and sampling theory and complex waves. Geophysics,1982,47(2):
222-236.
[77]Y Meyer. Wavelets of algorithms and applications. New York:SIAM,1993.
[78]Daubechies, W Sweldens. Factoring wavelet transforms into lifting steps. J. Fourier Anal. 1998,4(3):245-267.
[79]飞思科技产品研发中心,小波分析理论与matlab7实现,电子工业出版社,2005.
[80]秦毅,信号小波理论与一体化小波分析仪的研究,2008.
[81]RR Coifman, Y Meyer, MV Wickerhauser. Wavelet and signal processing, in:Wavelet and Their application. Boston, US:Jones and Bartlett Publishers,1992.
[82]Wu Ting, Yan Guozheng, Yang Banghua, et al. EEG feature extraction based on wavelet packet decomposition for brain computer interface, Measurement,2008(41):618-625.
[83]边肇祺,张学工.模式识别,第二版,北京：清华大学出版社,2000.
[84]张静远,张冰,蒋兴舟.基于小波变换的特征提取方法分析,信号处理,2000,16(2)：156-162.
[85]Peng Xu and Andrew K. Chan, Optimal Wavelet Sub-band Selection using Genetic Algorithm, Geoscience and Remote Sensing Symposium,2002,1441-1443.
[86]H. Liu, H. Motoda, Feature Extraction, Construction and Selection:A Data Mining Perspective, Kluwer Academic Publishers, Norwell, MA, USA,1998.
[87]Msnoranjau Dash, Huan Liu. Feature Selection for Classification. Intelligent Data Analysis, 1997,1(3):131-156.
[88]L Xu, P Yan, T Chang. Best First Strategy for Feature Selection. Proc of 9t h Int'l Conf on Pattern Recognition.1988:706-708.
[89]C Cardie. Using Decision Trees to Improve Case Based Learning, Proc of 10th In'l Conf on Machine Learning,1993:25-32.
[90]王娟,慈林林,姚康泽.特征选择方法综述,计算机工程与科学,2005,27(12)：68-71.
[91]B Chakraborty. Genetic Algorithm with Fuzzy Fitness Function for Feature Selection. Proc of the 2002 IEEE International Symp on Industrial Electronics,2002,1:315-319.
[92]T. Sttzle, M. Dorigo. The Ant Colony Optimization Metaheuristic:Algorithms, Applications, and Advances., Handbook of Metaheuristics, Kluwer Academic Publishers, Norwell, MA, 2002.
[93]卜华龙,夏静,韩俊波.特征选择算法综述及进展研究,巢湖学院学报,2008,10(6)：41-44.
[94]John H. Holland. Adaptation in Natural and Artificial Systems, the MIT Press,1992.
[95]Sun Zehang, Bebis George, Ronald Miller. object detection using feature subset selection, Pattern Recognition,2004,37:2165-2176.
[96]DORIGO M, MANIEZZO V, COLORN IA. The ant system:Optimization by a colony of cooperating agents. IEEE Transaction on Systems, Man and Cybernetics, Part B,1996,26 (1): 29-41.
[97]叶志伟,郑肇葆,万幼川等.基于蚁群优化的特征选择新方法,2007,32(12)：1127-1130.
[98]Ozge Uncu, IB Turksen. A novel feature selection approach:Combining feature wrappers and filters, Information Sciences,2007(177):449-466.
[99]U. Fayyad, K. Irani. Multi-interval discretization of continuous-valued attributes for classification learning, Proceedings of the Thirteenth International Joint Conference on Artificial Intelligence, Chambery,1993:1022-1027.
[100]毛勇,周晓波,夏铮等.特征选择算法研究综述,模式识别与人工智能,2007,20(2)：211-218.
[101]田金兰,李奔.数据挖掘工具：分类器,计算机世界,1992。20.
[102]N Cristianini, J Shawe Taylor. An introduction to support vector machines and other kernel-based learning methods. Cambridge UK:Cambridge University Press.2000.
[103]VN.Vapnik. The nature of statistical learning. New York:SPringer-Verlag,1995.
[104]VN.Vapnik. Statistical learning theory. New York:Wiley,1998.
[105]D. Li, W. Pedrycz, and N. J. Pizzi, "Fuzzy wavelet packet based feature extraction method and its application to biomedical signal classification," IEEE Trans. Biomed. Eng., 2005,52(6):1132-1139.
[106]D. Merkle, M. Middendorf, and H. Schmeck. Pheromone evaluation in Ant Colony Optimization, Proceedings of the 26th Annual Conference of the IEEE Industrial Electronics Society,2000:22-28.