基于语音特征的帕金森病可视化诊断方法研究
|
摘要
帕金森病是人类常见的神经退行性疾病之一，其病程时间长且发病范围广。由于该病病因尚未完全明确，目前所有针对帕金森病的治疗都是控制病症，而无法从根本上进行治愈。但在发病早期就开始接受合理治疗的患者，绝大多数能够延缓病情的发展，生活基本自理。因此，帕金森病的早期诊断不论对于家庭还是社会均具有重大意义。语言障碍是帕金森病的早期症状之一，基于语言障碍的帕金森病诊断是近年来的帕金森病诊断研究热点之一。
本文针对帕金森病的语言障碍特征，本文提出利用多维筛组合分类器进行帕金森病的可视化诊断。在解决帕金森病诊断实际问题的同时，完善基于高维数据列向量图表示的可视化组合分类器理论和方法，无论对信息融合和模式识别学术研究还是对基于语音特征的帕金森疾病诊断应用研究都具有重要意义。
首先，基于可视化分类器的框架结构，提出多维筛组合分类器框架，并从数据表示、类域生成与权重计算三个方面进行了完善。在数据表示阶段，提出基于色度学混色原理的彩色多元图着色表示，完善了模式识别应用下的多元图表示中类别信息的表示方法；在类域生成阶段，以训练样本的空间单点表示为出发点，提出了基于计算几何的区域主动生长的类界面求取方法。通过对基点区域的主动生长，使得整个表示空间任意区域均可进行类别表示，从而完成分类界面的计算过程；在权重计算阶段，从类空间类别分布特性出发，分别从不同的视觉角度提出基于类空间模糊度与规整度的权重分配方法，分别从统计和结构角度对类空间进行可视化权重计算。对通用数据的综合数据实验表明，多维筛分类器不但具有良好的可视化特性，而且分类性能已经达到或超过主流分类器的水平。
其次，研究了帕金森病语音特征与帕金森病临床表现之间的关系。通过实验验证，进一步阐明各语音特征的物理意义及其应用特点，为基于语言障碍检测的帕金森病早期诊断提供了可靠依据。在证明语音特征用于帕金森病诊断的有效性同时，分析了不同特征下不同元音的类间分离度，为基于语音障碍的帕金森病自动诊断奠定了基础。
最后，在对基于语言障碍的帕金森病的分类实验中，分别利用帕金森数据集与远程帕金森数据集进行了帕金森病的可视化诊断与病程的判断。实验表明，利用可视化模式识别理论，不但完成了诊断过程的全程可视化，有助于新的诊断指标的发现，而且获得了比经典分类器更高的诊断精度。
Parkinson’s disease (PD) is one of highest incident neurodegenerative diseases with along time course and a significant prevalence. As the etiology is currently unkown, thetreatement for this disease is to alleviate but can not to be cured. If the patients could betreated appropriately, most of them could control the disease’s development and preservethe ability of basic self care. As a result of that, early diagnosis of Parkinson's disease is ofgreat significance both for family and for society. The dysphonia is a typical symptom forearly Parkinson’s disease patient, so the Parkinson’s disease diagnosis in dysphoniameasurement is one of active fields.
In this paper, we propose the visual diagnostic method for Parkinson’s disease basedon speech features by visual combined classifer named multi-dimensional filter. Thepurpose of that is not only to explore the way about PD’s diagnose, but also to improve thetheory and method in visual pattern recongnition about multiple graph representation forhigh-dimensional data. It is of great significance both for information fusion, patternrecognition research and Parkinson's disease diagnosis based on speech features.
At first, we proposed the multi-dimensional filter classifier framework based on thetheory of visual classification, and improve it from the data representation, domainconstruction and weight calculation. Stage of data representation, a new type ofrepresentation named chromatic graphical representation is proposed to bridge the gapbetween graphical representation and category distribution. It inherits the merits oftraditional and represent the category information by chromatic of the current sample,which makes it more suitable than the traditional in visual pattern recognition applications;One of the basic issues in pattern recognition is to calculate the boundary betweendifferent categories. Stage of domain construction, a novel method for that based oncomputational geometry named active expansion is proposed. The whole space couldexpress the category information and the boundary is obtained by active expanding forbase points to non-base points; Stage of weight calculation, fuzzy and regularity areproposed for weight based on category spatial distribution characteristics. Two methods analyze the space visual information from the statistical and structure respectively.Comprehensive data experiments show that the multi-dimensional filter classifier not onlyinherits the characteristics about visualization features, but also gets equivalentperformance to the popular classifiers, and outweighs in some dataset.
In subsequential, the relationship between speech features and PD symptom isresearched. The physical explainations of speech features and application characteristicsare clarified by experiments, which provide a reliable basis for early diagnosis ofParkinson's disease base on dysphonia. At the same time, we analyze the differentcharacteristics of different vowel separation between classes, which is the foundation forautomatic diagnosis of Parkinson's disease.
At last, in the experiments about diagnosis the PD based on dysphonia, theParkinson dataset and Parkinson telemonitering dataset are employeed for visual diagnosisand determine the course of the disease. Experiments show that the application of visualpattern recognition, not only completed the entire diagnostic process of visualization toassist the discovery of new diagnostic indicators, also to obtain a higher classificationaccuracy than the classical machine diagnoses.
本文针对帕金森病的语言障碍特征，本文提出利用多维筛组合分类器进行帕金森病的可视化诊断。在解决帕金森病诊断实际问题的同时，完善基于高维数据列向量图表示的可视化组合分类器理论和方法，无论对信息融合和模式识别学术研究还是对基于语音特征的帕金森疾病诊断应用研究都具有重要意义。
首先，基于可视化分类器的框架结构，提出多维筛组合分类器框架，并从数据表示、类域生成与权重计算三个方面进行了完善。在数据表示阶段，提出基于色度学混色原理的彩色多元图着色表示，完善了模式识别应用下的多元图表示中类别信息的表示方法；在类域生成阶段，以训练样本的空间单点表示为出发点，提出了基于计算几何的区域主动生长的类界面求取方法。通过对基点区域的主动生长，使得整个表示空间任意区域均可进行类别表示，从而完成分类界面的计算过程；在权重计算阶段，从类空间类别分布特性出发，分别从不同的视觉角度提出基于类空间模糊度与规整度的权重分配方法，分别从统计和结构角度对类空间进行可视化权重计算。对通用数据的综合数据实验表明，多维筛分类器不但具有良好的可视化特性，而且分类性能已经达到或超过主流分类器的水平。
其次，研究了帕金森病语音特征与帕金森病临床表现之间的关系。通过实验验证，进一步阐明各语音特征的物理意义及其应用特点，为基于语言障碍检测的帕金森病早期诊断提供了可靠依据。在证明语音特征用于帕金森病诊断的有效性同时，分析了不同特征下不同元音的类间分离度，为基于语音障碍的帕金森病自动诊断奠定了基础。
最后，在对基于语言障碍的帕金森病的分类实验中，分别利用帕金森数据集与远程帕金森数据集进行了帕金森病的可视化诊断与病程的判断。实验表明，利用可视化模式识别理论，不但完成了诊断过程的全程可视化，有助于新的诊断指标的发现，而且获得了比经典分类器更高的诊断精度。
Parkinson’s disease (PD) is one of highest incident neurodegenerative diseases with along time course and a significant prevalence. As the etiology is currently unkown, thetreatement for this disease is to alleviate but can not to be cured. If the patients could betreated appropriately, most of them could control the disease’s development and preservethe ability of basic self care. As a result of that, early diagnosis of Parkinson's disease is ofgreat significance both for family and for society. The dysphonia is a typical symptom forearly Parkinson’s disease patient, so the Parkinson’s disease diagnosis in dysphoniameasurement is one of active fields.
In this paper, we propose the visual diagnostic method for Parkinson’s disease basedon speech features by visual combined classifer named multi-dimensional filter. Thepurpose of that is not only to explore the way about PD’s diagnose, but also to improve thetheory and method in visual pattern recongnition about multiple graph representation forhigh-dimensional data. It is of great significance both for information fusion, patternrecognition research and Parkinson's disease diagnosis based on speech features.
At first, we proposed the multi-dimensional filter classifier framework based on thetheory of visual classification, and improve it from the data representation, domainconstruction and weight calculation. Stage of data representation, a new type ofrepresentation named chromatic graphical representation is proposed to bridge the gapbetween graphical representation and category distribution. It inherits the merits oftraditional and represent the category information by chromatic of the current sample,which makes it more suitable than the traditional in visual pattern recognition applications;One of the basic issues in pattern recognition is to calculate the boundary betweendifferent categories. Stage of domain construction, a novel method for that based oncomputational geometry named active expansion is proposed. The whole space couldexpress the category information and the boundary is obtained by active expanding forbase points to non-base points; Stage of weight calculation, fuzzy and regularity areproposed for weight based on category spatial distribution characteristics. Two methods analyze the space visual information from the statistical and structure respectively.Comprehensive data experiments show that the multi-dimensional filter classifier not onlyinherits the characteristics about visualization features, but also gets equivalentperformance to the popular classifiers, and outweighs in some dataset.
In subsequential, the relationship between speech features and PD symptom isresearched. The physical explainations of speech features and application characteristicsare clarified by experiments, which provide a reliable basis for early diagnosis ofParkinson's disease base on dysphonia. At the same time, we analyze the differentcharacteristics of different vowel separation between classes, which is the foundation forautomatic diagnosis of Parkinson's disease.
At last, in the experiments about diagnosis the PD based on dysphonia, theParkinson dataset and Parkinson telemonitering dataset are employeed for visual diagnosisand determine the course of the disease. Experiments show that the application of visualpattern recognition, not only completed the entire diagnostic process of visualization toassist the discovery of new diagnostic indicators, also to obtain a higher classificationaccuracy than the classical machine diagnoses.
引文
[1] Uehara T, Nakamura T, Yao D. S-nitrosylated protein-di-sulphide isomerase links proteinMisfolding to neurodegeneration[J]. Nature, 2006, 441(7092) : 513-517.
[2] Mori F, Piao YS, Hayashi S.α-synuclein accumulates in purkinje cells in lewy body disease butnot in multiple system atro-phy[J]. Journal Neuropathol Exp Neurol, 2003,62 (8) :812-819.
[3] A. E. Lang, A. M. Lozano. Parkinson's disease - first of two parts[J]. New England Journal ofMedicine, 1998, 339:1044-1053.
[4] Zhen-Xin Zhang, Gustavo C Roman, Zhen Hong. Parkinson’s disease in China: prevalence inBeijing, Xian, and Shanghai[J]. Lancet 2005, 365: 595–597.
[5]陈茹.帕金森病研究进展[J].中国康复理论与实践. 2007, 13(7): 637-639.
[6] D. M. Huse, K. Schulman, L. Orsini. Burden of illness in Parkinson's disease[J]. MovementDisorders, 2005, 20:1449-1454.
[7] National Institute for Health and Clinical Excellence. Clinical guideline 35: Parkinson'sdisease[M]. London: Royal College of Physicians, 2006:50-55.
[8] N. Singh, V. Pillay, Y. E. Choonara. Advances in the treatment of Parkinson's disease[J].Progress in Neurobiology, 2007, 81: 29-44.
[9]张振馨.神经系统疾病流行病学调查方法和问题[J].中华神经科杂志, 2005, 38(2): 65-66.
[10] Gelb D, Oliver E, Gilman S. Diagnostic criteria for Parkinson disease[J]. Arch Neurol. 1999, 56(1): 33–39.
[11]韩艳,张晓红,陈彤.帕金森病诊治现状调查[J].中华保健医学杂志, 2008, 10(1): 18-20.
[12] Chien-Wen Cho, Wen-Hung Chao, Sheng-Huang Lin. A vision-based analysis system for gaitrecognition in patients with Parkinson’s disease[J]. Expert Systems with Applications, 2009, 36:7033–7039.
[13]张开元,于春水.帕金森病嗅觉障碍的MRI研究进展[J].中国医学影像技术, 2008, 24(3):450-452.
[14] Dominique Guehl, Pierre Burbaud, Christian Lorenzi. Auditory temporal processing inParkinson’s disease[J]. Neuropsychologia. 2008, 46: 2326–2335.
[15] J. R. Duffy. Motor speech disorders : substrates, differential diagnosis, and management[M]. St.Louis, Mo.: Elsevier Mosby, 2005:172-193.
[16] A. K. Ho, R. Iansek, C. Marigliani. Speech impairment in a large sample of patients withParkinson's disease[J]. Behavioural Neurology, 1998, 11: 131-137.
[17] J. A. Logemann, H. B. Fisher, B. Boshes. Co-occurrence of vocal-tract dysfunctions in speechof a large sample of Parkinson patients[J]. Journal of Speech and Hearing Disorders, 1978, 43:47-57.
[18] S. Sapir, J. L. Spielman, L. O. Ramig. Effects of intensive voice treatment on vowel articulationin dysarthric individuals with idiopathic Parkinson disease: acoustic and perceptual findings[J].Journal Speech Language Hearlth Research, 2007, 50: 899-912.
[19] Alexander M. Goberman, Michael Blomgren, Erika Metzger. Characteristics of speechdisfluency in Parkinson disease[J]. Journal of Neurolinguistics, 2008, 23(5): 470-478.
[20] D. A. Rahn, M. Chou, J. J. Jiang. Phonatory impairment in Parkinson's disease: Evidence fromnonlinear dynamic analysis and perturbation analysis[J]. Journal of Voice, 2007, 21: 64-71.
[21]陈生弟.帕金森病临床诊治手册[M].北京：人民卫生出版社, 2008:1-20.
[22]赵国华.帕金森病的中西医结合治疗[M].北京：人民卫生出版社, 2010: 32-50.
[23] Palmerini L., Rocchi L., Mellone S.. Feature selection for accelerometer-based posture analysisin Parkinson's disease[J]. IEEE Transactions on Information Technology in Biomedicine. 2011,15(3): 481-490.
[24] Haehner A, Boesveldt S, Berendse HW. Prevalence of smell loss in Parkinson's disease--amulticenter study[J]. Parkinsonism Relat Disord. 2009, 15(7): 490- 494.
[25]王翠,赵红玲,王苏平.帕金森病的嗅觉障碍与嗅觉功能检测[J].中国老年学杂志, 2011,(5):888-890.
[26]李飞,谷德祥,李燕君.帕金森病患者诱发电位研究[J].临床神经电生理学杂志, 2002, 39
(2): 94-95.
[27] Max A. Little, Patrick E. McSharry, Eric J. Hunter. Suitability of dysphonia measurements fortelemonitoring of Parkinson’s disease[J]. IEEE Transactions on Biomedical Engineering,2009,56(4):1015-1022.
[28] Max A Little, Patrick E Mcsharry, Stephen J Roberts. Exploiting nonlinear recurrence and fractalscaling properties for voice disorder detection[J]. BioMedical Engineering, 2007, 25(6): 1186-1214.
[29] Athanasios Tsanas, Max A. Little, Patrick E. McSharry. Accurate telemonitoring of Parkinson’sdisease progression by non-invasive speech tests[J]. IEEE Transactions on BiomedicalEngineering, 2010, 57(4):884-893.
[30] C. Okan Sakar, Olcay Kursun. Telediagnosis of Parkinson's disease using measurements ofdysphonia[J]. Journal of Medical Systems, 2010, 34(4): 591-599.
[31] Revett, K., Gorunescu, F., Salem. Feature selection in Parkinson's disease: A rough setsapproach[C]. // International Multiconference on Computer Science and Information Technology,Mragowo, 2009: 425-428.
[32] Pei-Fang Guo, Prabir Bhattacharya, Nawwaf Kharma. Advances in detecting Parkinson’sdisease[J]. Lecture Notes in Computer Science, 2010, 6165: 306-314.
[33] Diamandis, E.P. Mass spectrometry as a cancer biomarker discovery tool: opportunities andpotential limitations[J]. Mol.Cell.Proteomics , 2004, 43: 367-378.
[34]西奥多里蒂斯.模式识别[M].第四版.北京：电子工业出版社, 2010:50-93.
[35] Mehdi Dastani. The role of visual perception in data visualization[J]. Journal of VisualLanguages and Computing. 2002, 13: 601-622.
[36] Janez Dem ar, Gregor Leban, Bla Zupan. FreeViz—An intelligent multivariate visualizationapproach to explorative analysis of biomedical data[J]. Journal of Biomedical Informatics, 2007,40 (6): 661-671.
[37]洪文学,李昕,徐永红.基于多元统计图表示原理的信息融合与模式识别技术[M].北京:国防工业出版社, 2008: 7-42.
[38] John W. Tukey. Exploratory data analysis[M]. Boston: Addison-Wesley, 1977:9-18.
[39] Jianlong Zhou, Chun Xiao, Zhiyan Wang. A concept of volume rendering guided search processto analyze medical data set[J]. Computerized Medical Imaging and Graphics, 2008, 32(2): 140-149.
[40] Christian Hennig , Norbert Christlieb. Validating visual clusters in large datasets: fixed pointclusters of spectral features[J]. Computational Statistics & Data Analysis, 2002, 40(4): 723-739.
[41] Anas Quteishat, Chee Peng Lim. A modified fuzzy min–max neural network with rule extractionand its application to fault detection and classification[J]. Applied Soft Computing, 2008, 8(2):985-995.
[42] Abbiw-Jackson R., Golden B., Raghavan S. A divide-and-conquer local search heuristic for datavisualization[J].Computers and Operations Research, 2006, 33: 3070–3087.
[43] P. Compieta, S. Di Martino, M. Bertolotto. Exploratory spatio-temporal data mining andvisualization[J]. Journal of Visual Languages & Computing, 2007, 18(3): 255-279.
[44] Y.W. Choong. Mining multiple-level fuzzy blocks from multidimensional data[J]. Fuzzy Setsand Systems, 2008, 159(12): 1535-1553.
[45] Robert A. Amar, John T. Stasko. Knowledge precepts for design and evaluation of informationvisualizations[J]. IEEE Transactions on Visualization and Computer Graphics, 2005, 11(4): 432-442.
[46] Arnulf B. A. Graf，Felix A. Wichmann，Heinrich H. Bulthoff. Classification of faces in man andmachine[J]. Neural Computation, 2006, 18: 143-165.
[47]谢维信,曹文明,蒙山.基于Clifford代数的混合型传感器网络覆盖理论模型[J].中国科学E辑:信息科学, 2007, 37(8): 1018-1031.
[48] Daniel A. Keim, George G. Robertson, Jim J. Thomas. Guest editorial: special section on visualanalytics[J]. IEEE Transactions on Visualization and Computer Graphics, 2006, 12(6): 1361-1362.
[49] Ying Tao,Yang Liu, Carol Friedman. Information visualization technology in bioinformaticsduring the postgenomic era[J]. BMC Bioinformatics, 2004, 2(6): 237-245.
[50] Hong Wenxue, Wang Liqiang. Research on intelligent electroacupuncture technique based on thesymbolized measurement theory[C].// Proceedings of the 27th Annual International Conferenceof the Engineering in Medicine and Biology Society, Beijing, 2005: 4255-4258.
[51]徐永红,洪文学.基于图表达和双变量判别节点模型的蔬菜油分类研究[C].// IEEE WorldCongress on Intelligent Control and Automation, Dalian, 2006: 10157-10161.
[52]孟辉,洪文学.基于多维数据雷达图表示原理与模糊推理规则的分类器研究[C].//IEEEWorld Congress on Intelligent Control and Automation, Dalian, 2006: 9921-9925.
[53] Yonghong Xu, Wenxue Hong. Visual pattern recognition method based on optimized parallelcoordinates[C].//IEEE International Conference on Integration Technology, Shenzhen, 2007:127-132.
[54] Yonghong Xu, Wenxue Hong. Parallel dual visualization of multidimensional multivariatedata[C].// IEEE International Conference on Integration Technology, Shenzhen, 2007: 263-268.
[55]洪文学,宋佳霖,孟辉.基于血清蛋白质组质谱数据断层成像原理癌症标志物模式构成研究[C].//中国生物医学工程学术年会,西安, 2007: 234-239.
[56] Wenyuan Liu, Hui Meng, Wenxue Hong, et al. A new method for dimensionality reduction basedon multivariate feature fusion[C].// Xi’an: IEEE ICIT, 2007: 108-111.
[57]赵慧臣.知识可视化的视觉表征研究[D].南京:南京师范大学, 2010:24-51.
[58]孙文.远程交互式多媒体系统及其在数字健康可视化中的应用[D].合肥：中国科学技术大学, 2011:8-12.
[59]郑忠,曾永年,刘慧敏.并联结构组合分类器的误差分析[J].遥感技术与应用,2011,26(3):340-348.
[60] Lu D, Weng Q. A survey of image classification methods and techniques for improvingclassification performance[J]. International Jornal of Remote Sensing, 2007, 28(5): 823-870.
[61]韩建峰,杨哲海.组合分类器及其在高光谱影像分类中的应用[J].测绘科学技术学报, 2007,24( 3) : 231-234.
[62]李春干.面向对象的SPOT5图像森林分类研究[D].北京:北京林业大学, 2009: 20-35.
[63] Liu X H, S kdmore A K, Van Oosten H. Integration of classification methods for improvement ofland-cover map accuracy[J]. ISPRS Journal of Photogrammetry & Remote Sensing, 2002, 56(4):257-268.
[64] De Stefano C, D EliaC, Marcell A, et al . Using Bayesian Network for Combining Classifiers [C]// 14th International Conference on Image Analysis and Processin g-ICIAP 2007, Washington:IEEE Computer Society, 2007: 73-80.
[65]孙灏,杜培军,赵卫常.基于多分类器组合的高分辨率遥感影像目标识别[J].地理与地理信息科学, 2009, 25(1): 32- 35.
[66] El˙zbieta PeRkalska, Robert P.W. Duin, Pavel Paclik. Prototype selection for dissimilarity-basedclassifiers[J]. Pattern Recognition, 2006, 39: 189 -208.
[67] Robert P.W. Duin, El˙zbieta Pekalska. The science of pattern recognition: achievements andperspectives challenges for computational intelligence[J]. Studies in Computational Intelligence,2007, 5:789-812.
[68] B. Ripley. Pattern recognition and neural networks[M]. Cambridge: Cambridge University Press,1996: 156-241.
[69] C.M. Bishop. Neural networks for pattern recognition[M]. Oxford: Oxford University Press,1995: 241-265.
[70] T. Mitchell. Machine learning[M]. New York: McGraw Hill, 1997: 15-45.
[71] R.O. Duda, P.E. Hart, D.G. Stork. Pattern classification[M]. New York: John Wiley & Sons, Inc.2001:112-153.
[72] R.P.W. Duin, E. P ekalska, P. Pacl′k. The dissimilarity representation, a basis for domain basedpattern recognition[J]. Pattern Representation and the Future of Pattern Recognition, 2004, 7:43-56.
[73] R.P.W. Duin, F. Roli, D. de Ridder. A note on core research issues for statistical patternrecognition[J]. Pattern Recognition Letters, 2002, 23(4):493–499.
[74] E. P ekalska, R.P.W. Duin. The dissimilarity representation for pattern recognition[M].Singapore: World Scientific, 2005:45-82.
[75] Davis R., Shrobe H., Szolovits P. What is a knowledge representation?[J]. AI Magazine,1993,14(1):17-33.
[76] A.G. Arkadev, E.M. Braverman. Computers and pattern recognition[M]. Washington DC:Thompson, 1966: 451-498.
[77] S. Watanabe. Pattern Recognition, Human and mechanical[M]. New York: John Wiley & Sons,1985: 124-154.
[78] D.H. Wolpert. The mathematics of generalization[M]. New York:Addison-Wesley, 1995:254-312.
[79] A.K. Jain, R.P.W. Duin J. Mao. Statistical pattern recognition: a review[J]. IEEE Transactions onPattern Analysis and Machine Intelligence, 2000, 22(1):4–37.
[80] Birgitte Nielsen, Fritz Albregtsen, Havard E. Danielsen. Low dimensional adaptive texturefeature vectors from class distance and class difference matrices[J]. IEEE Transactions onMedical Imaging, 2004, 23(1): 73-84.
[81] Christopher W.Tyler. Beyond fourth-order texture discrimination[J]. Vision Research, 2004,44:2187- 2199.
[82] Christopher W.Tyler. Theory of texture discrimination of based on higher-order perturbations inindividual texture samples[J]. Vision Research, 2004, 44: 2179-2186.
[83] G. Rellier, X. Descombes, F. Falzon. Texture feature analysis using a Gauss-Markov model inhyperspectral image classification[J]. IEEE Transactions on Geoscience and Remote Sensing,2004, 42(7):1543-1551.
[84] R. Paget. Strong Markov random field model[J]. IEEE Transactions on Pattern Analysis andMachine Intelligence, 2004, 26(3): 408-413.
[85] C.T.Li. Multiresolution image segmentation integrating Gibbs sampler and region mergingalgorithm[J]. Signal Processing, 2003, 83(1): 67-78.
[86] Pi Minghong, M. K. Mandal, A. Basu. Image retrieval based on histogram of fractalparameters[J]. IEEE Transactions on Multimedia, 2005, 7(4): 597-605.
[87] Zhende Hou, Yuwen Qin. The study of fractal correlation method in the displacementmeasurement and its application[J]. Optics and Lasers in Engineering, 2003, 39(4): 465- 472.
[88] B. S. Manjunath, Jens-Rainer Ohm, Vinod V. Vasudevan. Color and texture descriptors[J]. IEEETransactions on Circuits and Systems for Video Technology, 2001, 11(6): 703-715.
[89] K. Jafari-Khouzani, H. Soltanian-Zadeh. Rotation-invariant multiresolution texture analysisusing radom and wavelet transforms[J]. IEEE Transactions on Image Processing,2005,14(6):783-795.
[90]焦李成,谭山.图像的多尺度几何分析:回顾和展望[J]．电子学报, 2003, 31(12A):1975-1981.
[91]傅京孙.模式识别及其应用[M].北京:科学出版社, 1983: 7-12.
[92] L. Goldfarb, D. Gay. What is a structural representation[R]. Fredericton：University of NewBrunswick, 2005: 12-25.
[93]张涛,王成儒.窗口纹理分析方法[J].仪器仪表学报，2006, 27(z6): 2289-2290.
[94] Liang Wang, Christopher Leckie, Ramamohanarao Kotagiri. Approximate pairwise clusteringfor large data sets via sampling plus extension[J]. Pattern Recognition, 2011, 44(2): 222-235.
[95] Ventzeslav Valev, Asai Asaithambi. Multidimensional pattern recognition problems andcombining classifiers[J]. Pattern Recognition Letters, 2001, 22(12): 1291-1297.
[96]李伟明.多元描述统计方法[M].上海:华东师范大学出版社, 2001: 7-9.
[97] Mayumi Oyama Higa, E, Teijun Miao, Yuko Mizuno-Matsumoto. Analysis of dementia in agedsubjects through chaos analysis of fingertip pulse waves[C].//2006 IEEE InternationalConference on Systems, Man and Cybernetics, Taipei: 2863-2867.
[98]胡威捷,汤顺青,朱正芳.现代颜色技术原理及应用[M].北京:北京理工大学出版社, 2007:5-15.
[99] Zhixin Qi, Anthony Gar-On Yeh, Xia Li. A novel algorithm for land use and land coverclassification using RADARSAT-2 polarimetric SAR data[J]. Remote Sensing of Environment,2012, 118(15): 21-39.
[100] T.B.üstün. International classification systems for health[J]. International Encyclopedia ofPublic Health, 2008:660-668.
[101] Shehzad Khalid, Shahid Razzaq. Frameworks for multivariate m-mediods based modeling andclassification in Euclidean and general feature spaces[J]. Pattern Recognition, 2012, 45(3):1092-1103.
[102] G. J. McLachlan. Discriminant analysis and statistical pattern recognition [M]. New York :WileyInterscience, 2004: 5-47.
[103] V. Vapnik, Statistical learning theory [M]. New York:Wiley Interscience, 1998: 98-105.
[104] Anil K. Jain, Robert P. W. Duin, Jianchang Mao. Statistical pattern recognition: a review[J].IEEE Transaction on Pattern Analysis and Machine Intelligence, 2000, 22(1): 4-37.
[105] Y. Tominaga. Comparative study of class data analysis with PCA-LDA, SIMCA, PLS, ANNs,and k-NN [J]. Chemo Intel. Lab. Syst,1999, 49: 105-115.
[106] Maurizio Filippone, Francesco Camastra, Francesco Masulli. Asurvey of kernel and spectralmethods for clustering [J]. Pattern Recognition, 2008, 41: 176-190.
[107] Godfried Toussaint. Computational geometric aspects of rhythm, melody, and voice-leading[J].Computational Geometry, 2010, 43(1): 2-22.
[108]苗夺谦,李德毅,姚一豫.不确定性与粒计算[M].北京：科学出版社, 2011: 89-103.
[109] Dong Qiu, Lan Shu, Zhi-Wen Mo.On starshaped fuzzy sets[J]. Fuzzy Sets and Systems, 2009,160(11): 1563-1577.
[110] Chen Degang, Zhao Suyun. Local reduction of decision system with fuzzy rough sets[J]. FuzzySets and Systems, 2010, 161(13): 1871-1883.
[111] Jing Hao, Qingguo Li. The relationship between L-fuzzy rough set and L-topology[J]. FuzzySets and Systems, 2011, 178(1): 74-83.
[112] Degang Chen, Qiang He, Xizhao Wang. FRSVMs: Fuzzy rough set based support vectormachines[J]. Fuzzy Sets and Systems, 2010, 161(4): 596-607.
[113] David A. Clausi, Yongping Zhao. Grey level co-occurrence integrated algorithm (GLCIA): asuperior computational method to rapidly determine co-occurrence probability texturefeatures[J]. Computers & Geosciences, 2003, 29(7): 837-850.
[114] Zeev Zalevsky, Ehud Rivlin, Michael Rudzsky. Motion characterization from co-occurrencevector descriptor[J]. Pattern Recognition Letters, 2005, 26(5): 533-543.
[115]李洁,邓一鸣,沈士团.基于模糊区域分布的分类规则提取及推理算法[J].计算机学报,2008, 31(6): 934-941.
[116] Enwang Zhou，Alireza Khotanzad. Fuzzy classifier design using genetic algorithms[J]. PatternRecognition, 2007, 40(12): 3401- 3414.
[117] Yalin Zhao, Hua Li, Yanyan Hou. Construction of two mathematical models for prediction ofbacterial sRNA targets[J]. Biochemical and Biophysical Research Communications, 2008,372(2): 346-350.
[118] Yuichi Shiraishi, Kenji Fukumizu. Statistical approaches to combining binary classifiers formulti-class classification[J]. Neurocomputing, 2011, 74(5): 680-688.
[119] Mona Delavarian, Farzad Towhidkhah, Shahriar Gharibzadeh. Automatic classification ofhyperactive children: comparing multiple artificial intelligence approaches[J]. NeuroscienceLetters, 2011, 498(3): 190-193.
[120] R. J. Baken, R. F. Orlikoff. Clinical measurement of speech and voice[M]. San Diego: SingularThomson Learning, 2000: 78-256.
[121] Eero V yrynen, Juhani Toivanen, Tapio Sepp nen. Classification of emotion in spoken Finnishusing vowel-length segments: increasing reliability with a fusion technique[J]. SpeechCommunication, 2011, 53(3): 269-282.
[122] H. Kantz, T. Schreiber. Nonlinear time series analysis[M]. Cambridge: Cambridge UniversityPress, 1999: 244-268.
[123] Dmitri Bitouk, Ragini Verma, Ani Nenkova. Class-level spectral features for emotionrecognition[J]. Speech Communication, 2010, 52(7): 613-625.
[124] Marcelo Merello, Eliana Roldan Gerschcovich, Diego Ballesteros. Correlation between themovement disorders society unified Parkinson’s disease rating scale and the unified Parkinson’sdisease rating scale during l-dopa acute challenge[J]. Parkinsonism & Related Disorders, 2011,17(9): 705-707.
[2] Mori F, Piao YS, Hayashi S.α-synuclein accumulates in purkinje cells in lewy body disease butnot in multiple system atro-phy[J]. Journal Neuropathol Exp Neurol, 2003,62 (8) :812-819.
[3] A. E. Lang, A. M. Lozano. Parkinson's disease - first of two parts[J]. New England Journal ofMedicine, 1998, 339:1044-1053.
[4] Zhen-Xin Zhang, Gustavo C Roman, Zhen Hong. Parkinson’s disease in China: prevalence inBeijing, Xian, and Shanghai[J]. Lancet 2005, 365: 595–597.
[5]陈茹.帕金森病研究进展[J].中国康复理论与实践. 2007, 13(7): 637-639.
[6] D. M. Huse, K. Schulman, L. Orsini. Burden of illness in Parkinson's disease[J]. MovementDisorders, 2005, 20:1449-1454.
[7] National Institute for Health and Clinical Excellence. Clinical guideline 35: Parkinson'sdisease[M]. London: Royal College of Physicians, 2006:50-55.
[8] N. Singh, V. Pillay, Y. E. Choonara. Advances in the treatment of Parkinson's disease[J].Progress in Neurobiology, 2007, 81: 29-44.
[9]张振馨.神经系统疾病流行病学调查方法和问题[J].中华神经科杂志, 2005, 38(2): 65-66.
[10] Gelb D, Oliver E, Gilman S. Diagnostic criteria for Parkinson disease[J]. Arch Neurol. 1999, 56(1): 33–39.
[11]韩艳,张晓红,陈彤.帕金森病诊治现状调查[J].中华保健医学杂志, 2008, 10(1): 18-20.
[12] Chien-Wen Cho, Wen-Hung Chao, Sheng-Huang Lin. A vision-based analysis system for gaitrecognition in patients with Parkinson’s disease[J]. Expert Systems with Applications, 2009, 36:7033–7039.
[13]张开元,于春水.帕金森病嗅觉障碍的MRI研究进展[J].中国医学影像技术, 2008, 24(3):450-452.
[14] Dominique Guehl, Pierre Burbaud, Christian Lorenzi. Auditory temporal processing inParkinson’s disease[J]. Neuropsychologia. 2008, 46: 2326–2335.
[15] J. R. Duffy. Motor speech disorders : substrates, differential diagnosis, and management[M]. St.Louis, Mo.: Elsevier Mosby, 2005:172-193.
[16] A. K. Ho, R. Iansek, C. Marigliani. Speech impairment in a large sample of patients withParkinson's disease[J]. Behavioural Neurology, 1998, 11: 131-137.
[17] J. A. Logemann, H. B. Fisher, B. Boshes. Co-occurrence of vocal-tract dysfunctions in speechof a large sample of Parkinson patients[J]. Journal of Speech and Hearing Disorders, 1978, 43:47-57.
[18] S. Sapir, J. L. Spielman, L. O. Ramig. Effects of intensive voice treatment on vowel articulationin dysarthric individuals with idiopathic Parkinson disease: acoustic and perceptual findings[J].Journal Speech Language Hearlth Research, 2007, 50: 899-912.
[19] Alexander M. Goberman, Michael Blomgren, Erika Metzger. Characteristics of speechdisfluency in Parkinson disease[J]. Journal of Neurolinguistics, 2008, 23(5): 470-478.
[20] D. A. Rahn, M. Chou, J. J. Jiang. Phonatory impairment in Parkinson's disease: Evidence fromnonlinear dynamic analysis and perturbation analysis[J]. Journal of Voice, 2007, 21: 64-71.
[21]陈生弟.帕金森病临床诊治手册[M].北京：人民卫生出版社, 2008:1-20.
[22]赵国华.帕金森病的中西医结合治疗[M].北京：人民卫生出版社, 2010: 32-50.
[23] Palmerini L., Rocchi L., Mellone S.. Feature selection for accelerometer-based posture analysisin Parkinson's disease[J]. IEEE Transactions on Information Technology in Biomedicine. 2011,15(3): 481-490.
[24] Haehner A, Boesveldt S, Berendse HW. Prevalence of smell loss in Parkinson's disease--amulticenter study[J]. Parkinsonism Relat Disord. 2009, 15(7): 490- 494.
[25]王翠,赵红玲,王苏平.帕金森病的嗅觉障碍与嗅觉功能检测[J].中国老年学杂志, 2011,(5):888-890.
[26]李飞,谷德祥,李燕君.帕金森病患者诱发电位研究[J].临床神经电生理学杂志, 2002, 39
(2): 94-95.
[27] Max A. Little, Patrick E. McSharry, Eric J. Hunter. Suitability of dysphonia measurements fortelemonitoring of Parkinson’s disease[J]. IEEE Transactions on Biomedical Engineering,2009,56(4):1015-1022.
[28] Max A Little, Patrick E Mcsharry, Stephen J Roberts. Exploiting nonlinear recurrence and fractalscaling properties for voice disorder detection[J]. BioMedical Engineering, 2007, 25(6): 1186-1214.
[29] Athanasios Tsanas, Max A. Little, Patrick E. McSharry. Accurate telemonitoring of Parkinson’sdisease progression by non-invasive speech tests[J]. IEEE Transactions on BiomedicalEngineering, 2010, 57(4):884-893.
[30] C. Okan Sakar, Olcay Kursun. Telediagnosis of Parkinson's disease using measurements ofdysphonia[J]. Journal of Medical Systems, 2010, 34(4): 591-599.
[31] Revett, K., Gorunescu, F., Salem. Feature selection in Parkinson's disease: A rough setsapproach[C]. // International Multiconference on Computer Science and Information Technology,Mragowo, 2009: 425-428.
[32] Pei-Fang Guo, Prabir Bhattacharya, Nawwaf Kharma. Advances in detecting Parkinson’sdisease[J]. Lecture Notes in Computer Science, 2010, 6165: 306-314.
[33] Diamandis, E.P. Mass spectrometry as a cancer biomarker discovery tool: opportunities andpotential limitations[J]. Mol.Cell.Proteomics , 2004, 43: 367-378.
[34]西奥多里蒂斯.模式识别[M].第四版.北京：电子工业出版社, 2010:50-93.
[35] Mehdi Dastani. The role of visual perception in data visualization[J]. Journal of VisualLanguages and Computing. 2002, 13: 601-622.
[36] Janez Dem ar, Gregor Leban, Bla Zupan. FreeViz—An intelligent multivariate visualizationapproach to explorative analysis of biomedical data[J]. Journal of Biomedical Informatics, 2007,40 (6): 661-671.
[37]洪文学,李昕,徐永红.基于多元统计图表示原理的信息融合与模式识别技术[M].北京:国防工业出版社, 2008: 7-42.
[38] John W. Tukey. Exploratory data analysis[M]. Boston: Addison-Wesley, 1977:9-18.
[39] Jianlong Zhou, Chun Xiao, Zhiyan Wang. A concept of volume rendering guided search processto analyze medical data set[J]. Computerized Medical Imaging and Graphics, 2008, 32(2): 140-149.
[40] Christian Hennig , Norbert Christlieb. Validating visual clusters in large datasets: fixed pointclusters of spectral features[J]. Computational Statistics & Data Analysis, 2002, 40(4): 723-739.
[41] Anas Quteishat, Chee Peng Lim. A modified fuzzy min–max neural network with rule extractionand its application to fault detection and classification[J]. Applied Soft Computing, 2008, 8(2):985-995.
[42] Abbiw-Jackson R., Golden B., Raghavan S. A divide-and-conquer local search heuristic for datavisualization[J].Computers and Operations Research, 2006, 33: 3070–3087.
[43] P. Compieta, S. Di Martino, M. Bertolotto. Exploratory spatio-temporal data mining andvisualization[J]. Journal of Visual Languages & Computing, 2007, 18(3): 255-279.
[44] Y.W. Choong. Mining multiple-level fuzzy blocks from multidimensional data[J]. Fuzzy Setsand Systems, 2008, 159(12): 1535-1553.
[45] Robert A. Amar, John T. Stasko. Knowledge precepts for design and evaluation of informationvisualizations[J]. IEEE Transactions on Visualization and Computer Graphics, 2005, 11(4): 432-442.
[46] Arnulf B. A. Graf，Felix A. Wichmann，Heinrich H. Bulthoff. Classification of faces in man andmachine[J]. Neural Computation, 2006, 18: 143-165.
[47]谢维信,曹文明,蒙山.基于Clifford代数的混合型传感器网络覆盖理论模型[J].中国科学E辑:信息科学, 2007, 37(8): 1018-1031.
[48] Daniel A. Keim, George G. Robertson, Jim J. Thomas. Guest editorial: special section on visualanalytics[J]. IEEE Transactions on Visualization and Computer Graphics, 2006, 12(6): 1361-1362.
[49] Ying Tao,Yang Liu, Carol Friedman. Information visualization technology in bioinformaticsduring the postgenomic era[J]. BMC Bioinformatics, 2004, 2(6): 237-245.
[50] Hong Wenxue, Wang Liqiang. Research on intelligent electroacupuncture technique based on thesymbolized measurement theory[C].// Proceedings of the 27th Annual International Conferenceof the Engineering in Medicine and Biology Society, Beijing, 2005: 4255-4258.
[51]徐永红,洪文学.基于图表达和双变量判别节点模型的蔬菜油分类研究[C].// IEEE WorldCongress on Intelligent Control and Automation, Dalian, 2006: 10157-10161.
[52]孟辉,洪文学.基于多维数据雷达图表示原理与模糊推理规则的分类器研究[C].//IEEEWorld Congress on Intelligent Control and Automation, Dalian, 2006: 9921-9925.
[53] Yonghong Xu, Wenxue Hong. Visual pattern recognition method based on optimized parallelcoordinates[C].//IEEE International Conference on Integration Technology, Shenzhen, 2007:127-132.
[54] Yonghong Xu, Wenxue Hong. Parallel dual visualization of multidimensional multivariatedata[C].// IEEE International Conference on Integration Technology, Shenzhen, 2007: 263-268.
[55]洪文学,宋佳霖,孟辉.基于血清蛋白质组质谱数据断层成像原理癌症标志物模式构成研究[C].//中国生物医学工程学术年会,西安, 2007: 234-239.
[56] Wenyuan Liu, Hui Meng, Wenxue Hong, et al. A new method for dimensionality reduction basedon multivariate feature fusion[C].// Xi’an: IEEE ICIT, 2007: 108-111.
[57]赵慧臣.知识可视化的视觉表征研究[D].南京:南京师范大学, 2010:24-51.
[58]孙文.远程交互式多媒体系统及其在数字健康可视化中的应用[D].合肥：中国科学技术大学, 2011:8-12.
[59]郑忠,曾永年,刘慧敏.并联结构组合分类器的误差分析[J].遥感技术与应用,2011,26(3):340-348.
[60] Lu D, Weng Q. A survey of image classification methods and techniques for improvingclassification performance[J]. International Jornal of Remote Sensing, 2007, 28(5): 823-870.
[61]韩建峰,杨哲海.组合分类器及其在高光谱影像分类中的应用[J].测绘科学技术学报, 2007,24( 3) : 231-234.
[62]李春干.面向对象的SPOT5图像森林分类研究[D].北京:北京林业大学, 2009: 20-35.
[63] Liu X H, S kdmore A K, Van Oosten H. Integration of classification methods for improvement ofland-cover map accuracy[J]. ISPRS Journal of Photogrammetry & Remote Sensing, 2002, 56(4):257-268.
[64] De Stefano C, D EliaC, Marcell A, et al . Using Bayesian Network for Combining Classifiers [C]// 14th International Conference on Image Analysis and Processin g-ICIAP 2007, Washington:IEEE Computer Society, 2007: 73-80.
[65]孙灏,杜培军,赵卫常.基于多分类器组合的高分辨率遥感影像目标识别[J].地理与地理信息科学, 2009, 25(1): 32- 35.
[66] El˙zbieta PeRkalska, Robert P.W. Duin, Pavel Paclik. Prototype selection for dissimilarity-basedclassifiers[J]. Pattern Recognition, 2006, 39: 189 -208.
[67] Robert P.W. Duin, El˙zbieta Pekalska. The science of pattern recognition: achievements andperspectives challenges for computational intelligence[J]. Studies in Computational Intelligence,2007, 5:789-812.
[68] B. Ripley. Pattern recognition and neural networks[M]. Cambridge: Cambridge University Press,1996: 156-241.
[69] C.M. Bishop. Neural networks for pattern recognition[M]. Oxford: Oxford University Press,1995: 241-265.
[70] T. Mitchell. Machine learning[M]. New York: McGraw Hill, 1997: 15-45.
[71] R.O. Duda, P.E. Hart, D.G. Stork. Pattern classification[M]. New York: John Wiley & Sons, Inc.2001:112-153.
[72] R.P.W. Duin, E. P ekalska, P. Pacl′k. The dissimilarity representation, a basis for domain basedpattern recognition[J]. Pattern Representation and the Future of Pattern Recognition, 2004, 7:43-56.
[73] R.P.W. Duin, F. Roli, D. de Ridder. A note on core research issues for statistical patternrecognition[J]. Pattern Recognition Letters, 2002, 23(4):493–499.
[74] E. P ekalska, R.P.W. Duin. The dissimilarity representation for pattern recognition[M].Singapore: World Scientific, 2005:45-82.
[75] Davis R., Shrobe H., Szolovits P. What is a knowledge representation?[J]. AI Magazine,1993,14(1):17-33.
[76] A.G. Arkadev, E.M. Braverman. Computers and pattern recognition[M]. Washington DC:Thompson, 1966: 451-498.
[77] S. Watanabe. Pattern Recognition, Human and mechanical[M]. New York: John Wiley & Sons,1985: 124-154.
[78] D.H. Wolpert. The mathematics of generalization[M]. New York:Addison-Wesley, 1995:254-312.
[79] A.K. Jain, R.P.W. Duin J. Mao. Statistical pattern recognition: a review[J]. IEEE Transactions onPattern Analysis and Machine Intelligence, 2000, 22(1):4–37.
[80] Birgitte Nielsen, Fritz Albregtsen, Havard E. Danielsen. Low dimensional adaptive texturefeature vectors from class distance and class difference matrices[J]. IEEE Transactions onMedical Imaging, 2004, 23(1): 73-84.
[81] Christopher W.Tyler. Beyond fourth-order texture discrimination[J]. Vision Research, 2004,44:2187- 2199.
[82] Christopher W.Tyler. Theory of texture discrimination of based on higher-order perturbations inindividual texture samples[J]. Vision Research, 2004, 44: 2179-2186.
[83] G. Rellier, X. Descombes, F. Falzon. Texture feature analysis using a Gauss-Markov model inhyperspectral image classification[J]. IEEE Transactions on Geoscience and Remote Sensing,2004, 42(7):1543-1551.
[84] R. Paget. Strong Markov random field model[J]. IEEE Transactions on Pattern Analysis andMachine Intelligence, 2004, 26(3): 408-413.
[85] C.T.Li. Multiresolution image segmentation integrating Gibbs sampler and region mergingalgorithm[J]. Signal Processing, 2003, 83(1): 67-78.
[86] Pi Minghong, M. K. Mandal, A. Basu. Image retrieval based on histogram of fractalparameters[J]. IEEE Transactions on Multimedia, 2005, 7(4): 597-605.
[87] Zhende Hou, Yuwen Qin. The study of fractal correlation method in the displacementmeasurement and its application[J]. Optics and Lasers in Engineering, 2003, 39(4): 465- 472.
[88] B. S. Manjunath, Jens-Rainer Ohm, Vinod V. Vasudevan. Color and texture descriptors[J]. IEEETransactions on Circuits and Systems for Video Technology, 2001, 11(6): 703-715.
[89] K. Jafari-Khouzani, H. Soltanian-Zadeh. Rotation-invariant multiresolution texture analysisusing radom and wavelet transforms[J]. IEEE Transactions on Image Processing,2005,14(6):783-795.
[90]焦李成,谭山.图像的多尺度几何分析:回顾和展望[J]．电子学报, 2003, 31(12A):1975-1981.
[91]傅京孙.模式识别及其应用[M].北京:科学出版社, 1983: 7-12.
[92] L. Goldfarb, D. Gay. What is a structural representation[R]. Fredericton：University of NewBrunswick, 2005: 12-25.
[93]张涛,王成儒.窗口纹理分析方法[J].仪器仪表学报，2006, 27(z6): 2289-2290.
[94] Liang Wang, Christopher Leckie, Ramamohanarao Kotagiri. Approximate pairwise clusteringfor large data sets via sampling plus extension[J]. Pattern Recognition, 2011, 44(2): 222-235.
[95] Ventzeslav Valev, Asai Asaithambi. Multidimensional pattern recognition problems andcombining classifiers[J]. Pattern Recognition Letters, 2001, 22(12): 1291-1297.
[96]李伟明.多元描述统计方法[M].上海:华东师范大学出版社, 2001: 7-9.
[97] Mayumi Oyama Higa, E, Teijun Miao, Yuko Mizuno-Matsumoto. Analysis of dementia in agedsubjects through chaos analysis of fingertip pulse waves[C].//2006 IEEE InternationalConference on Systems, Man and Cybernetics, Taipei: 2863-2867.
[98]胡威捷,汤顺青,朱正芳.现代颜色技术原理及应用[M].北京:北京理工大学出版社, 2007:5-15.
[99] Zhixin Qi, Anthony Gar-On Yeh, Xia Li. A novel algorithm for land use and land coverclassification using RADARSAT-2 polarimetric SAR data[J]. Remote Sensing of Environment,2012, 118(15): 21-39.
[100] T.B.üstün. International classification systems for health[J]. International Encyclopedia ofPublic Health, 2008:660-668.
[101] Shehzad Khalid, Shahid Razzaq. Frameworks for multivariate m-mediods based modeling andclassification in Euclidean and general feature spaces[J]. Pattern Recognition, 2012, 45(3):1092-1103.
[102] G. J. McLachlan. Discriminant analysis and statistical pattern recognition [M]. New York :WileyInterscience, 2004: 5-47.
[103] V. Vapnik, Statistical learning theory [M]. New York:Wiley Interscience, 1998: 98-105.
[104] Anil K. Jain, Robert P. W. Duin, Jianchang Mao. Statistical pattern recognition: a review[J].IEEE Transaction on Pattern Analysis and Machine Intelligence, 2000, 22(1): 4-37.
[105] Y. Tominaga. Comparative study of class data analysis with PCA-LDA, SIMCA, PLS, ANNs,and k-NN [J]. Chemo Intel. Lab. Syst,1999, 49: 105-115.
[106] Maurizio Filippone, Francesco Camastra, Francesco Masulli. Asurvey of kernel and spectralmethods for clustering [J]. Pattern Recognition, 2008, 41: 176-190.
[107] Godfried Toussaint. Computational geometric aspects of rhythm, melody, and voice-leading[J].Computational Geometry, 2010, 43(1): 2-22.
[108]苗夺谦,李德毅,姚一豫.不确定性与粒计算[M].北京：科学出版社, 2011: 89-103.
[109] Dong Qiu, Lan Shu, Zhi-Wen Mo.On starshaped fuzzy sets[J]. Fuzzy Sets and Systems, 2009,160(11): 1563-1577.
[110] Chen Degang, Zhao Suyun. Local reduction of decision system with fuzzy rough sets[J]. FuzzySets and Systems, 2010, 161(13): 1871-1883.
[111] Jing Hao, Qingguo Li. The relationship between L-fuzzy rough set and L-topology[J]. FuzzySets and Systems, 2011, 178(1): 74-83.
[112] Degang Chen, Qiang He, Xizhao Wang. FRSVMs: Fuzzy rough set based support vectormachines[J]. Fuzzy Sets and Systems, 2010, 161(4): 596-607.
[113] David A. Clausi, Yongping Zhao. Grey level co-occurrence integrated algorithm (GLCIA): asuperior computational method to rapidly determine co-occurrence probability texturefeatures[J]. Computers & Geosciences, 2003, 29(7): 837-850.
[114] Zeev Zalevsky, Ehud Rivlin, Michael Rudzsky. Motion characterization from co-occurrencevector descriptor[J]. Pattern Recognition Letters, 2005, 26(5): 533-543.
[115]李洁,邓一鸣,沈士团.基于模糊区域分布的分类规则提取及推理算法[J].计算机学报,2008, 31(6): 934-941.
[116] Enwang Zhou，Alireza Khotanzad. Fuzzy classifier design using genetic algorithms[J]. PatternRecognition, 2007, 40(12): 3401- 3414.
[117] Yalin Zhao, Hua Li, Yanyan Hou. Construction of two mathematical models for prediction ofbacterial sRNA targets[J]. Biochemical and Biophysical Research Communications, 2008,372(2): 346-350.
[118] Yuichi Shiraishi, Kenji Fukumizu. Statistical approaches to combining binary classifiers formulti-class classification[J]. Neurocomputing, 2011, 74(5): 680-688.
[119] Mona Delavarian, Farzad Towhidkhah, Shahriar Gharibzadeh. Automatic classification ofhyperactive children: comparing multiple artificial intelligence approaches[J]. NeuroscienceLetters, 2011, 498(3): 190-193.
[120] R. J. Baken, R. F. Orlikoff. Clinical measurement of speech and voice[M]. San Diego: SingularThomson Learning, 2000: 78-256.
[121] Eero V yrynen, Juhani Toivanen, Tapio Sepp nen. Classification of emotion in spoken Finnishusing vowel-length segments: increasing reliability with a fusion technique[J]. SpeechCommunication, 2011, 53(3): 269-282.
[122] H. Kantz, T. Schreiber. Nonlinear time series analysis[M]. Cambridge: Cambridge UniversityPress, 1999: 244-268.
[123] Dmitri Bitouk, Ragini Verma, Ani Nenkova. Class-level spectral features for emotionrecognition[J]. Speech Communication, 2010, 52(7): 613-625.
[124] Marcelo Merello, Eliana Roldan Gerschcovich, Diego Ballesteros. Correlation between themovement disorders society unified Parkinson’s disease rating scale and the unified Parkinson’sdisease rating scale during l-dopa acute challenge[J]. Parkinsonism & Related Disorders, 2011,17(9): 705-707.