Statistical pattern recognition: A review

IEEE Transactions on Pattern Analysis and Machine Intelligence

Volumn 22, Issue 1, 2000, Pages 4-37

  Jain, Anil K ^a   Duin, Robert P W ^b   Mao, Jianchang ^c  

^a MICHIGAN STATE UNIVERSITY   (United States)

^b DELFT UNIVERSITY OF TECHNOLOGY   (Netherlands)

^c IBM ALMADEN RESEARCH CENTER   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ERROR ANALYSIS; FEATURE EXTRACTION; LEARNING SYSTEMS; NEURAL NETWORKS; STATISTICAL METHODS;

STATISTICAL PATTERN RECOGNITION;

PATTERN RECOGNITION SYSTEMS;

EID: 0033640646     PISSN: 01628828     EISSN: None     Source Type: Journal    
DOI: 10.1109/34.824819     Document Type: Article

References (176)

1. H.M. Abbiis and tvf.M. Fahmy, Neural Networks for Maximum Likelihood Clustering, Signal Processing, vol. 36, no. 1, pp. 111-126, 1994.
2. H. Akaike, A New I ,ook at Statistical Model Identification, IEEE 'inns, Automatic Control, vol. 19, pp 716-723, 1974.
3. S. Arnari, T,P. Chcn, and A. Cichocki, Stability Analysis of Learning Algorithms for Blind Source Separation, Neural Networks, vol, 10, no. 8, pp. 1,345-1,35-1, 1997.
4. J.A. Andcrson, Logistic Discrimination, Handbook of Statistics. P. R. Krtshnaiah and L.N. Kanal, eds., vol. 2, pp. 169-191, Amsterdam; North I lolltind,1982.
5. J. Andcrson, A. Pellionisz, and E. Rosenfeld, Ncurocomputing 2: Directions for Research. Cambridge Mass.: MIT Press, 1990.
6. A. Antes, L. Devroye, and J. Gyorfi, Lower Hounds for Boyes Error Estimation, /Ett Trans. Pattern Analysis arid Machine. ItiteHigenn; vol, 21, no, 7, pp. 643-645, July 1999.
7. H. Avi-ltnlwk and T. Dicp, Arbitrarily Tight Upper and Lower Bounds on the Baycsian Probability of Error, IEEE Tfans. Pattern Analysis nnd Madmie Intelligence, vol. 18, nr. 1, pp. 89-91, Jan. 1996.
8. E. Backer, Computer-Assisted Reasoning in Cluster Analysis, Prentice Hall, 1995.
9. R. Majcsy find S, Kovarlc, Multlrosnlutlon Elaslic Matching, Computer Vision Graphics linage Processing, vol 46, pp. 1-21,1989.
10. A. BaiTon, J. Kissanen, and B. Yu, The Minimum Description Length Principle in Coding and Modeling, IEEE Trans. Information Theory, vol. 44, no, 6, pp, 2,743-2,760, Oct. IWH.
11. A. I Jell and T. Scjnowski, An Information-Maximization Approach to Blind Separation, Neural Cumpiitalion, vol. 7, pp. 1,0041,034, 1995.
12. Y. Bengio, Markovian Models for Sequential Data, Neural Computing Surveys, vol. 2, pp. 129-162, 1999. http://www.irai. berkcley.edu/-jagota/NCS.
13. K.P. Bennell, Semi-Supervised Support Vector Machines, I'roc, Neural tuforntnfnm Processing Systems, Denver, 1998.
14. J. Bcrnardo and A. Smith, Bayesian Theory. John Wiley & Sons, 1994.
15. J.C. Bezdek, Pattern Recognition with l-'ttzzy Objectiva Function Algorithms. New York: Plenum Press, 1981.
16. Fuzzy Mtxlels r Pattern Recognition; Methods thai Search far Structures In utita. J.C. Bczdek and S.K Pal, eds., IEEE CS Press, 1992.
17. S.K, Hhatia and J.S. Deogun, Conceptual Clustering in Information Retrieval, JEEE Trnns. Systems, Ma, and Cybernetics, vol. 28, no. 3, pp 427-436, 1998.
18. CM. Bishop, Neural Networks for Pattern Recognition, Oxford; Clarendon ljress, 1995.
19. A.L, Blum and P. I-anglcy, Selection of Relevant Features and Examples in Machine Learning, Artificial Intelligence., vol. 97, nos. 1-2, pp. 245-271, 1997.
20. J. Borg and K Groenen, Modern Multidimensional Scaling, Berlin: Springer-Verlag, 1997.
21. L. Breiman, Bagging Predictors, Machine Learning, vol. 24, no. 2, pp. 123-140,1996.
22. L. Braiman, J.H. Friedman, R.A. Olshen, and C.J. Stone, Classification nnii Regression Trees. Wads worth, Calif., 1984.
23. C.j.C. Ikirgcs, A Tutorial on Support Vector Machines for Pattern Recognition, Datn Mining and Knowledge Discovery, vol. 2, no, 2, pp. 121-167, 1998.
24. J. Cardoso, Blind Signal Separation: Statistical Principles, I'roc. IEEE, vol. 86, pp. 2,009-2,025, 1998
25. C. Ceirpineto and G, Koma no, A Lattice Conceptual Clustering System and its Application to Browsing Retrieval, Mnchine Learning, vol. 24, no. 2, pp. 95-122, 1996.
26. G, Cfistelliino, A.M. Kartelli, and M. Pollllo, An Iterative Pruning Algorithm for feedforward Neural Networks, IEEE, Trans. Neural Networks, vol. 8, no. 3, pp 519-531, 1997.
27. C. Chalterjee and V.P. Koychawdhury, On Self-Organizing Algorithms find Networks for Class-Separability Features, IEEE. Trims. Neural Networks, vol 5, no. 3, pp. 663-678, 1997.
28. B. Cheng and P.M. Titterington, Neural Networks: A Review from Statistical Perspective, Statistical Science, vol. 9, no. 1, pp. 2-54, 1994.
29. H. Chernoff, The Use of Faces to Represent Points in k-Pimunsionai Space Graphically, J. Am, Statistical Assoc., vol.68, pp. 301-368, June 1973.
30. P.A. Chou, Optimal Partitioning for Classification and Kcgrossion Trees, IEEE Trails. Pattern Analysis find Machine Intelligence, vol. 13, no. 4, pp. 340-354, Apr, TOI.
31. P. Comon, Independent Component Analysis, a Now Concept?, Signal Processing, vol. 36, no. 3, pp. 287-314, 1994.
32. P.C Cosman, K.L. Ochlcr, E.A. Riskin, and R.M. Gray, Using Veclor Quantization fur linage Processing, P roc. IEEE, vol. 51, pp. 1,326-1,341, Sept. 1993
33. T.M, Cover, CcometriefiL (mit Statistical Properties of Systems of Linear Inequalities with Applications in Pattern Re-cognition, IEEE Trans. Electronic Computers, vol. 14, pp. 326-334, June 1965.
34. T.M. Cover, The Best Two Independent Measurements arc not the Two Best, lt Trans. Systems, Man, tintt Cybernetics, vol. 4, pp. 116-117,1974.
35. T.M. Cover and J.M. Van Campenhout, On the Possible Orderings in the Measurement Selection Problem, IF.l'.F. Trans. Systems. Man, and Cybernetics, vol. 7, no. 9, pp. 657-661, Sept. 1977.
36. A. Pompster, N. Laird, and J. Kubiu, Maximum I .ikolihood from Incomplete Data via the (EM) Algorithm, J. Royal Statistical Soc., vol. 39, pp. 1-38, 1977.
37. H. Dcmuth and H.M. lirale, Neural Network Toolbox for Use with Mntlnb. version 3, Matlworks, Natick, Mass., 1998.
38. D. De Ridder and R.P.W. Duin, Sammon's Mapping Using Neural Networks: Comparison, Pattern Recognition letters, vol. 18, no. 1143, pp. 1,307-1,310, 1997.
39. P.A. Devijver and J. Kittler, Pattern Recognition: A Statistical Approach. London; Prentice Hall, 1982.
40. L. Devroye, Automatic Pal tern Recognltlrm: A Study of the Probability of Error, IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 10, no, 4, pp. 530-543, 1988.
41. L. Devroye, I,. Gyorfi, and G. Lugosi, A Probabilistic Theory of Pattern Recognition. Berlin: Springer-Verlag, 1496.
42. A. DjoLiadi and E. Boiiktachc, A Fast Algorithm for the NearestNeighbor Classifier, IEEE Trans. Pattern Analysis find Machine Intelligence, vol. 19, no. 3, pp. 277-282, 1997.
43. H. Drucker, C. Cortes, I,.D. Jackel, Y. I.ecim, and V. Vnpnik, Boosting and Other Ensemble Methods, Neural Cumpittativn, vol. & no. 6, pp. 1,289-1,301, 1994.
44. K.O. Duda and P.E. I lart, l'altera Classification and Scene Analysis, New York: John Wiley & Sons, 1973.
45. R.O. Dndn, P.E. Hart, and D.G. Stork, Pattern Classification find Sceiif Analysis, second ed., New York: John VViloy & Sons, 2000.
46. R.P.W. Duin, A Note on Comparing Classifiers, Pattern Recngnition Letters, vol. 17, no. 5, pp. 529-536, 1996.
47. R.P.W. Duin, D. De Ridder. and D.M.J. Tax, Experiments with a Featureless Approach to Pattern Recognition, Pattern Recognition tetters, vol. 18, nos. 11-13, pp. l,159-1,166, 1997.
48. B. Efron, 'I'he jackknife, the Bootstrap and Other Resampling Plans Philadelphia: SIAM, 1982.
49. U, Fayynd, C. Pintotsky-Shapiru, find P. Smytll, Knowledge Discovery and Uatn Mining: Towards a Unifying Framework, Prac, Secant Int'l Conf. Knowledge Discovery anil Data Milling, Aug. 1999.
50. F. Fcrri, P. Pudil, M. I latcf, and J. Kitfler, Comparative Slndy of Techniques for Large Scale I'ealurc Selection, Pattern Recognition in Practice W. E. Gelsema and L. Kanal, eds., pp. 403-413, 1894.
51. M. Egutiredo, J. LeitHO, and A.K, Jain, On Pitting Mixture Moduls, F.Hi'rgy Minimization Metiinrts in Computer Vision mid I'tittem Recognition. E. Hancock and M. Pellillo, eds Springor-Verlag, 1999,
52. Y. Freund and R. Schapire, Experiments with a New Boosting Algorithm, Cror. I.Wi lui'l Canf. Machine Lasrning, pp. 148-156, 1996.
53. J.F.I. Friedman, Exploratory Projection Pursuit, J. Am. Statistical Assoc., vol. 82, pp, 249-266, 1987.
54. J.I L L'riedman, Regularized Discrimina n t Analysis, J. Am Statistical Assitc., vol. 84, pp. 165-175, 1989
55. H. Frigiii and R. Krishnapurnm, A Robust Competitive Clustering Algorithm with Applications in Computer Vision, IEEF. Turns. Pattern Analysts ami Machine Itstdligatf.f, vol. 21, no. 5, pp. 450-465, 1999
56. K.S. Fn, Syntactic Pntteni Recognition ami Applications. Fnglewood Cliffs, N.J.'; Prenl ice-Hall, 1982
57. K-S. Fn, A Stop Towards Unifiration of Syntactic and Stiitistical Pattern Recognition, IEEE TI'IIHS. Patlcrn Analysis mid Machine Intelligence, vol. 5, no. 2, pp. 200-205, Mar. 1983
58. K. Fukunagaa, Inttrocduction to Statistical Pntterii Recognition, second ed., Nfw York: Academic FIX-OS, 1990.
59. K. Pukunaga and ,K, llaycs, Effects of Sample Size in Classifier Design, IEEE Trims. Pattern Analysis nmi Machine Intdlisencf, vol. 11, no. 8, pp. K73-885, Aug. 1989
60. K. Fuknnagii and It R. H.iyos, The Reduced Parzen Classifier, JEJEF Tiens. I'nltcrn Annli/sis and Machine Intelligence, vol. II, no. 4, pp 423-425, Apr. 1989.
61. K, Hikunaga and D.M. Hummels, Leave-One-Oilt Procedures for Monpammetric Error Estimates, IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 11, no. 4, pp. 421-423, Apr. 1989.
62. K. h'ukushima, S. Miyako, nnd T. I to, Neocognitmn: A Neural Network Model for a Mechanism of Visunl I'atlocn Recugnitiou, IEEE Trans. Systems, Man, mid Cybernetics, vol. 13, pp. 826-834, 1983.
63. S.U. Cclfand, C.S. Ravishankar, and E.J, Help, An Ileralive Crowing and Pruning Algorilhm for Classification Tree Design, IF.F.F. Trans, i'allern Analysis and Machine Intelligence, vol, 13, no. 2, pp. 163-174, Feb. 1991.
64. S. Geinan, I:. iJicnenstock, and K. Dnursat, Neural Networks Lind the liUis/Variance Dilumuin, Neural Compnitalion, vol. 4, no. 1, pp. 1-5H, 1992
65. Cl. CJlymour, D. Madigiin, D. ljrcgibon, and P. fimyth, Slntislicnl Themes anit lession fnr Data Mining, Dfitu Mining mid Knwledgc Discovery, vol. 1, no. I, pp. 11-28, 1997.
66. M. Colfiirdli, D. Maio, and 1J. Malloni, Ou the lirror-Keject Tmde-Off in bidmetric Verification Syslem, Int I'raus. Pattern Analysis, mid Mnhuine Inlelligcna:, vol. 19, 110. 7, pp 786-796, July 1997
67. K.M. Gray, Vector Quanlizalion, IF.F.K ASSP, vol. 1, pp. 4-29, Apr. 1984.
68. K.M. Gray and K,A, Olshcn, Vector Qunntizalion nnd Density Estimation, I'roc. Inl'l Ctinf. Cooopersion and Complexity of Sequences, 1997. http://www-isl.slanford.edu/gray/ conipression.html
69. U. Geiwndrr, Canenil I'alfcm Theory. Oxford Umv, I'rcss, 1993
70. D.J. Hand, Rucent Advances in Error Kute l-Jstimalioii, Puttern Recongition Leilas, vol. 4, no. 5, pp. 333-346, 1986.
71. M.H. Hansen ami . Yu, Model Selection and Ihe Principle of Minimum Desriplkin Length, technical report, Lucent Bell Lab, Murray Hill, N.J., 1998.
72. M.A. I learnt, Support Vector Machines, IEEE Intellifrnt Systrm pp, 18-28, July/Aug. 1998.
73. S. Hiiykin, Neural Nctnvrks, A Compersion Fountion. second od., Enflowood Cliffs, N.J.: Prentice Hall, 1999.
74. T. K, Ho, J.J. Hull, and S.N. Srihnri, Decision Combination in Multiple Classifier Systems, JL'JTC Trims. I'ottfi'n Analysis und Machine Intetligeitf.'', vol. 16, no. 1, pp. 66-75, 1994.
75. T.K. llo, The Random Subspace Method for ConstLiicting Decision Iwcsts, IEEE Trans. I'ntlern Analysis and Mnciiinc liitcHigaKe, vol. 20, no. 8, pp. 832-844, Aug. 1998.
76. J.P. Hof (beck nnd U.A. Latidgrcbc, Coviiriancc Matrix Estimntioii and Classificauon with Limited Training llatn, l LEE Trans paltern Analysis nuit Machine InttfligeHcc, vol. 18, no, 7, pp. 763-767,July I999
77. A. Hyvnrinen, Survey un Independent Component Analysis, Neural Cvinpnling Silmys, vol. 2, pp. 94-128, 1999. htlp:// wivw.icsi.bLrkcloy.cdLi/jagota/NC'S.
78. A. Hyvarineii and H. Oja, A Pasl Fixed-Point Algorithm for Independent t.oinponetil Analysis, Nairnl Computation, vol, 9, no. 7, pp. 1,483-1,492, Oct. 1997.
79. It A. Jacob:, M.I. Jordan, SJ. Neiwlan, and C l.K. I lintoii, Adaptive Mixtures of I.ouil Kxpcrls, Neural Coinpalnlion, vol. 3, pp, 79-87, 1991
80. A.K. Jain ,and B, Cliandrasek.iran, Dimensionality and Sample Sixe Considerations in Pattern Recognition Practice, Handbook of Statistics. I'.R. Krishiiaiah and I..N. Kami, eds., vol. 2, pp. 835-855, Amsterdam: North-Holland, 1982.
81. A.K. Jain and U.C. Dubes, Algorithms for Clustering Data. Engle wooct Cliffs, N.J.: Prentice Hall, 1988
82. A.K. Jain, R.C. Dubes, and C.-C. Chen, Bootstrap Techniques for Krrnr Estimation, IEEF. Trans. Pattern Analysis and Mndiine Intelligence, vol. 9, no. 5, pp, 623-633, May 1987
83. A.K. jain, J. Mao, and K.M. Mohiuddin, Artificial Neural Nclworks: A Tutorial, Computer, pp. 3144, Mm. 1996
84. A. Jain, Y. Zhong, and S. Lakshmanan, Object Matching Using Huforrnable Templates, IEEE Trans. Pattern Analysis runt Machine Intelligence, vol. 18, no. 3, Mar, 1996
85. A.K. Jain anil IJ. Zongker, Feature Selection: Evaluation, Application, and Small Sample Performance, JWCL' Trans. Pattern Analysis and Machine Intelligence, vol. 19, no, 2, pp. 153-158, Fcb, 1997.
86. F. Jelinek, Statistical Methods far Spcedi Recognition. MIT Press, 1998.
87. M.I. Jordan and R.A. Jacobs, Eliernrchic.il Mixlurca of Kxports and H-iu RM Algorithm, Ncunil Computation, vol. 91, pp. 181-214, 1994.
88. D Judd, P. Mckink-y, dild A.K. Jain, Larfie-Scak- Parnllel Data Clustering, IEEE Trans. Pattern Analysis and Machine Intelligence., vol. 20, no. 8, pp. 871-876, Aug. 1998
89. L.N. Kanal, Patterns in Pattern Rcrngmlinn: 1968-1974, IEEE Trans. Information Theony, vol. 211, nu. 6, pp. 697-722,1074.
90. J, Kittler, M, llatcf, R.P.W. Duin, and J, Matas, On Combining Classifiers, IEEE Traun. Pattern Analysis and Machine Intelligence, vol. 20, no. 3, pp. 226-239, 1998.
91. K.M. Klcinbcrg, Stochastic niscriinination, Annals of Math, and Artificial Intelligence, vol. 1, pp. 207-239, 1990
92. T. Kohnnen, Self-Orgftttizillg Maps, Springer Scries in JoformaLion Sciences, veil. 30, Berlin, 1995.
93. A. Krogh and J. Veek'lbby, Miural Network Enbumbkis, Cross Validation, and Active Learning', Adviaces in Neural Infarmation Practising Systems, G. Tesauro, D. Touvetsky, ond T. Leen, cds., vol. 7, Cambridge, Mass.: MIT Press, 1995
94. L. Lam and C.Y. Siieni, Optimal Comhinaiions of Pattern Classifiers, Pnttem Recognition Letters, vol. 16, no, 9, pp. 945-954, 1995.
95. Y. Le dm, B. lioscr, J.S. Denker, D. Hendersoil, R.E. Howard, W. Hublwrtt, antl L.D. Jackcl, JlackpropagaHon Applied to Handwriilen Zip Ctidc Recognition, Neural Compulation, vol. 1, pp. 541-551, 1989.
96. T.W. I.oc, Independent Component Analysis, IJordrec-h: Kluwer Academic Publishers, 1908.
97. C. Loo and U.A. Landgnibe, Koatui'o Kxtraclion Based on Decision lioundartes, IF.FF. Tunis. Pattern Analisis antl Machine IntellixeiKt, vol. 15, no. 4, pp. 388-400,1993.
98. li, Lnrner, H. Gutormiin, M. Aladjem, and I. Dinstein, A Comparative Study of Neural Nclwork Based Feature Uxtraction Paradigms, I'altcrn Recogition tellers vol. 20, no. 1, pp. 7-14, 1998
99. D.R. Lovoll, C,K. Dance, M. Niranjan, R.VV. Pragr K.J. Dalton, and K, Dcrom, Feature Selection Using Expected Attainable Discrition, Pattern Recognition Leiters, vol, 19, nos. 5-6, pp. 393-402, 1998.
100. D Lowe and A.R. Webb, Optimized Feature Extraction and the Bayes Decision in t-'cud-l'orward Classifier Networks, IEEE Trans, Pattern Analysis und Machine Intelligence, vol. 13, no. 4, pp. 355-264, Apr. 1991
101. D.J.C MarKay, The Evidunte Hranwwork Applied to Classification Networks, Neural Computation, vol. 4, no. 5, pp, 720-736, 1992.
102. J.C. Man and A.K, Jain, Artificial Neural Networks tor Feature Extractionn and Multivariatc Uala Prajeclion, IEEE Tmiis. Neural Nchvurks, vol. 6, no. 2, pp. 296-317, 1995.
103. J. Mao, K. Mohiuddin, and A.K. Jain, Parsimonious Network Design and Feature Selection through Node Pruning, Proc-, '12th Int't Conf. parttenmi Recognition, pp. 622-614,Oct. 1994,
104. J.C. Ma a and K.M. Moliiuddin, Improving OCR Vecforniiincc Using Chiirnctcr Degradation Models and Uooslinf; Algorithm, Pattern Recagnilton Letters, vol. 18, no. 11-13, pp, 1,415-1,419, 1997.
105. G. McLachlan, Discriminant Analysis and Statistical l'attcnt Itecogiiition. New York: John Wiloy & Sons, 1992.
106. M. Mehta, J. Rissanen, and R. Agrawal, MOI,-Based Decision Tree Pruning, Froc, first. Ini'l Conf kniwledge: Distowry in Databases and Data Mining, Montreal, Canada Aug. 1995
107. CE. Metz, Basic Principles of ROC Analysis, Seminars in Nuclear Medicine, vol. VIII, no. 4, pp. 283-298, 1978,
108. U.S. Michalski and R.E. Stepp, Automated Construction of Classificalions: Conceptual Clustering versus Numerical Tnxonomy, IEEE, Trans, Pattern Analysis and Machine Intelligence, vol,5, pp. 396-410, 1983.
109. D. Michie, D.J. Spiegel limiter, and C.C, Taylor, Machine Learning, Mettrai and Statistical Classification, New York: lillis Horwood, 1994.
110. S.K. Mishra and V.V. Kfighfivan, An Kmpirlc.il Study of the Performance of Heuristic Methods for Clustering, Pattern Recognition in Practice. E.S. Gelsema and L.N. Kanal, eds., NorthHolland, pp. 423-436, 1934.
111. G. Nagy, State of the Art in Pattern Kccognition, Proc. IEEE, vol. 56, pp. 836-862, 1968.
112. C. Nagy, Gindide's Practical Principles of Experimental Pattern RecogniLion, IEEE Trntis. Pattern Analysis find Machine Intelligente, vol. 5, no. 2, pp. 199-200, 1983.
113. R. Neal, Bayesian Learning fur Neural Networks. New York: Spring Verlag, 1996.
114. H. Niemann, Linear and Nonlinear Mappings of Patterns, Pattern Recognition, vol. 12, pp, 83-87, 1980,
115. K.L, Oehler and K.M. Cray, Combining Imago Compression anil Classification Using Vector QunutiMtion, IEEE. 'I'raits. Pattern Analysis and Machine. Intelligence, vol. 17, no. 5, pp. 461-473, 1995.
116. E. Oja, Siibspscc Metlicds of Pattern Recognition, Letch wo r Ih, Hertfordshire, England: Research Studies Press, 1983.
117. K Oja, Principal Components, Minor Components, and Linear Neural Networks, Neural Networks, vol. 5, no. fi, pp. 927-936. 1992.
118. li. Ojn, The Nonlinear PC A Learning Rule in Independent Component Analysis, Neiiroeoiputing, vol. 1.7, nu.'l, pp. 25-45, 1997.
119. E. OsiiLia, R, Freund, and H. Girosi, An Improved '['raining Algorithm for Support Vector Machines, Prof. IEEL Wttrksliap Neural Networks fur Signal Processing. J. Principe, L, Gile, N, Morgan, and K. Wilson, eds., New York: 1KKK CS Press, 1997.
120. Y, Park and J. Sklanski, Automated Design of Linear Trou Classifiers, Pattern Recognition, vol. 23, no. 12, pp, 1,393-1,412, 1990.
121. JT. Pavlidis, Structural Pattern Recognition. New York: SpringerVerlag, 1977,
122. L.I. Perlovsky, Conundrum of Combinatorial Complexify, IKEF. Trnns, I'attcrn Analysis und Machine Intelligence, vol. 20, no. 6, pp. 666-670, 1998.
123. M,P. Perronc and L.N. Cooper, When Networks Disagree: Ensemble Methods for Hybrid Neural Networks, Neural Networks far Speech find linage. Processing. K.J. Mammotio, ed., Chapnuin-1 lall, 1993.
124. J. Platt, Fast Training of Support Vector Machines Using Sequential Minimal Optimization, Advances in Kernel McthotlaSupport Vector Learning. B. Scholkopf, C.J. C, linrgos, und A.J, Smola, cds., Cambridge, Mass.: MIT Prcss, 1999.
125. K. Pieard, Affictive Computing. MIT Press, 1997.
126. P. Pudil, J. Novovicova, and J. Kittlcr, 'Tloaliug Search Methods in Feature Selection, Pnllem Recognition Leiters, vol. 15, no. 11, pp. U19-U25,1991
127. P. Pudil, J. Novovicova, and J. Kittler, Feature Selection liased on the Approximation of Class Densities by Kinite Mixtures of the Special Type, Paltern Recognition, vol. 2S, no. 9, pp. 1389-1398, 1935.
128. J,E, Quinlan, Simplifying Decision Trees, Int'l J. Man-Mnchine Studies, vol. 27, pp. 221-234, 1987.
129. J.R, Quinlan, C4.5: Programs for Machine Lctiniing. San Mnleu, Calif.: Morgan Kaufmann, 1993.
130. L.R. Kabiner, A Tutorial on Hidden Markov Models und Selected Applications in Speech Recognition, Proe. IEEE, vol. 77, pp. 257-286, Feb. 1989.
131. S.J. Raudys and V, Pikelis, On Dimcnsionalily, Sample Size, Classification Krror, dnd Complexity of Class ilka t ion Algortims in Paltern Recognition, IEEE Trans. Pattern Atiahlyis and Machine Intelligence, vol. 2, pp. 2-13-251.,1980,
132. S.J, Raudys und A.K. Juin, Small Sample Size Effects in StntifiHc.il Pattern Recognition: Keroni inundations for Practitioners, IEEE Trans. Pattern Analysis and Machine. Intelligence, vol. 13, no, 3, pp, 252-264, 1991.
133. S. Kauclys, Hvohition find Generalisation of a Single Neuron; Single-Layer Perccptron as Seven Statistical Classifiers, Neural Networks, vol. 11, no. 2, pp. 283-296, 1998
134. S. Raudys and R.P.W. Duin, Expected Classification Error of the Fislior I.inutir Classifier with Psenriuinverse Qwariance Matrix, Pattern Recognition I filers, vol. 19, nos. 5-6, pp. 385-392, 1998.
135. S. Kidiardson and I'. Green, On linycsian Analysis of Mixtures with Unknown Number of Components, j. Koyal Statistical Sac, (B), vol. 39, pp. 731-792, 1997.
136. B. Rip ley, Statistical Aspects of Neural Networks, Networks an Omos: Statistical and Probabilistic Aspects. U. Bomndorff-Niclsen., J. Jniscn, and W. Kendal, ads., Chapman ami Hall, 1993.
137. B. Ripley, Pattern Recognition and Neural Networks. Cambridge, Mast.: Cambridge Univ. Press, 1996.
138. J. Rissanen, Stochastic Complexity in Statistical Inquiiif, Singapore: World Scientific, 1989.
139. K. Rose, Deterministic Annealing for Clustering, Compression, Classification, Regression and Kein ted Optimization Problems, Pror. IEEE, vol. 86, pp. 2,210-2,239, 1998.
140. T.E. Ross, Flash of Genius, Forbcs, pp. 98-104, Nov. 1998.
141. J.W. Sainmon Jr., A Nonlinear Mapping for Data Structure Analysis, IEEE Trans. Computer, vol. 18, pp. 401-409, 1969.
142. K.K, SchflpiTO, The Strength of Weak Learnability, Machine learning, vol. 5, pp. 197-227, 1990.
143. R.L, Schapire, Y. Ground, I', bartlcll, and W.S. Loo, Boosting the Margin: A New Explanation for the Effectiveness of Voting Methods, Annals of Statistic, 1999
144. J. Scholkopf, Support Vector UM ruing, Ph.D. thesis, Technische Universität, Berlin, 1997.
145. B. Scholkopf, A. Smola, and K.K, Muller, Nonlinear Component Analysis as a Kernel Eigenvalue Problem, Neural Compiitntiun, vol. 10, no. 5, pp. 1,299-1,319, 1998.
146. B. Scholkopf, K.-K. Suns, C.J.C. Durges, F. Girosi, P. Niyogi, T. Poggio, and V. Vapnik, Comparing Support Vector Machines with Caussian Kernels to Radial fiasis Hunction Classifiers, IEEE Trans. Sigiwt Processing, vol. 45. no. 11, pp. 2,758-2,765, 1957.
147. J. Schurmann, Pattern Classification: A Unified View of Statistenl und Neural Approacties. New York: John Wiley & Sons, 1996.
148. S. Sciovo, Application of tile. Conditional Population Mixture Model to Image Segmentation, IEEE Trails. Pattern Recognition and Machine Intelligence, vol. 5, pp 428-4.11, 1983.
149. I.K. Sethi and C.P.R, Snrvnrayudu, Hiernrchicnl Classifier Design Using Mutual Information, IEEE, Trans. Pattern Recognition and Madiina Intelligence, vol. 1, pp. 194-201, Apr. 1979,
150. R. Sclkmo and H, Lia, Neural-Network Feature Selector, IEEE Traits. Neural Networks, vol. 8, no. 3, pp. 65-1-662, 1997.
151. VV, Siedlecki and J. Sklansky, A Note on Genetic Algorithms for Large-Scale Feature Selection, fat tern Recognition Letters, vol. 10, pp. 335-347, 1989.
152. P. Simard, Y. LcCvm, and J. Denker, Efficient Pattern Recognition Using a New Transformation Distance, Advances in Neural Information Processing Systems, 5, S.J. Hanson, J.D. Cowan, and C.I.. Giles, eds., Cnlifcirnia: Morgan Kaufmann, 1993.
153. I'. Simard, B. Vicforri, Y. I.cCun, and J. Denker, Tangent IVop-A Formnlism for Specifying Selected Invariances in flti Adaptive Network, Arlivinccs in Neural Information Processing SYsteins, 4, J.E. Moody, S.J. I Innson, and U.P. I.ippmtmn, eds., pp. 651-655, California: Morgan Knufrnnnn, 1992.
154. P. Somol, P. Pudil, J. Novovicova, and P, F'ntlik, Adaptive Floating Search Methods in TcaLiirc SPlection, Pattern Recognition Utters, vol, 20, nos. Il, 12, 13, pp. 1,157-1,163, 1999.
155. Titterington, A. Smith, find U. Mniuw, Statistical Analysis of finite Mixture Distributions. Chiehester, U.K.: John Wiley & Sons, 1985,
156. V. Tresp and M, Tanignchi, Combining Estimators Using NonConstant Weighting Functions, AdwtKCS in Neural Information Troceaiiiig Siysfems, G. Tcsaum, U.S. Touretuky, and T.K. Leen, eds., vol. 7, Cambridge, Mass.: MIT Press, 1995,
157. G.V. Trunk, A Problem of Piuiensiomilily: A Simple Kxample, IEEE Trans. Pattern Analysis unit Machine Intelligftife, vol. 1, nn. 3, pp. 306-307, July 1979
158. K. 'limier and J. Ghosh, Analysis of Decision Boundfirica in Linearly Combined Neural Classifiers, Puffern Recognition, vol. 29, pp. 341-348, 1996.
159. S, Vnithyanathan and FX Dom, Model Selection in Unsupervised I .earning with Applications to Document Clustering, I'roc. Sixth Int'l Conf. Machinc learning, pp. 433-443, June 1999.
160. M. van Brcukclcn, K.P.W. Dnin, D.M.J. Tax, and J.E. den Hartog, Handwritten Digit Recognition by Combined Classifiers, Kybernetika, vol. 34, no. 4, pp. 381-380, 1998
161. V.N. Vapnik, Estimation of Dependences Based on Empirical Data, Berlin: Springer-Vorlag, 1982.
162. V.N. Vapnik, Statistical Learning Theory. New York: John Wiley & Suna, 1998.
163. S, Wntanabe, Pattern Recognition; Human ami Mechanical. New York: Wiley, 1985.
164. Fiant if fs of Pattern Recognition. S. Watnnnbe, cd, New York: Academic Press, 1972.
165. A.U, Webb, Multidimensional Scaling by Iterative Majorization Using Radial fiasis H'unclions, Pattern Recognition, vol. 28, no. 5, pp. 753-759, 1995.
166. S.M. VVoiss and C.A, Kulikowski, CMiifnitar Systems thai Lenni. California: Morgan Kaufmann Publisliors, 1991.
167. M, Wliindliam and A. Cutler, Information Ratios for Validating Mixture Analysis, J. Am. Statistical Assoc., vol. 87, pp. 1,188-1,192, 1992.
168. J, Wolpcrt, Stacked Generalization, Neural Nettvortcs, vol. 5, pp. 241-259,1992.
169. A.K.C. Wong and D.C.C. Wang, DECA: A Discrete-Valued Data Clustering Algorithm, IEEE tratis. Pattern Analysis sind Machine Mdligfttcc, vol. 1, pp. 342-349, 1970.
170. K, Woods, . Kegel mcyer Jr., and K. liowycr. Corabiiiiition nf Multiple Classifiers Using Local Accuracy Estimates, IEEE. 'Irans Pattern Analysis und Machins Intelligence, vol. 19, no. 4, pp, 405-410, Apr. 1997.
171. Q.n. Xio, C.A. Lasx.lo, und R.K. Ward, Vector Quantifiation 'i'cdmique for Nanparametric Classifier Design, IEEE Tram. Pattern Analysis and Machine Intelligence, vol. 15, no. 12, pp 1,326-1,330, 1993,
172. L. Xu, A. Krzyj.iik, and C.Y. Siien, Methods for Combining Multiple Classifiers and Thoir Applications in Handwritten Character Recognition, IEEF, Trans. Systems, Man, nniJ Cybernetics, vol. 22, pp. 418-435, 1992.
173. G.T. Toussaint, The Use of Context in Pattern Recognition, Pattern Recognition, vol, 10, no. 3, pp. 189-204, 197S.
174. K. Mohiiidrlin and j. Mao, Optical Character Recognition, Wiley EncifC-iaficdia of Electrical Dud Kltclrouic Engineering. J.C. Webster, ed., vol. 15, pp. 226-236, John Wiley and Sims, Inc., 1999.
175. K.M, Haralick, decision Making in Context, IKKt1 Trans. tPattern Analysis ami Machine Intelligence, vol. 5, no. 4, pp. 417-418, Mar. 1983.
176. S, Clnikrabarli, D. Dom, and P. Idyk, linhanci-d Hypertext Categorization Using Hyperlinks, ACM SfGMO/J, Seattle, 1998