Methods for feature selection in a learning machine

Details Methods for feature selection in a learning machine Methods for feature selection in a learning machine

2008-01-08

2008-01-08

Holmes, Michael B. (Department: 2121)

Data processing: artificial intelligence

Machine learning

C706S016000

Reexamination Certificate

active

07318051

ABSTRACT:
In a pre-processing step prior to training a learning machine, pre-processing includes reducing the quantity of features to be processed using feature selection methods selected from the group consisting of recursive feature elimination (RFE), minimizing the number of non-zero parameters of the system (lo-norm minimization), evaluation of cost function to identify a subset of features that are compatible with constraints imposed by the learning set, unbalanced correlation score and transductive feature selection. The features remaining after feature selection are then used to train a learning machine for purposes of pattern classification, regression, clustering and/or novelty detection. (FIG. 3, 300, 301, 302, 304, 306, 308, 309, 310, 311, 312, 314)

REFERENCES:
patent: 3626384 (1971-12-01), Davis et al.
patent: 4658372 (1987-04-01), Witkin
patent: 4881178 (1989-11-01), Holland
patent: 5138694 (1992-08-01), Hamilton
patent: 5339256 (1994-08-01), Levy et al.
patent: 5649068 (1997-07-01), Boser
patent: 5731989 (1998-03-01), Tenny et al.
patent: 5809144 (1998-09-01), Sirbu
patent: 5950146 (1999-09-01), Vapnik
patent: 6128608 (2000-10-01), Barnhill
patent: 6134344 (2000-10-01), Burges
patent: 6157921 (2000-12-01), Barnhill
patent: 6272437 (2001-08-01), Woods et al.
patent: 6427141 (2002-07-01), Barnhill
patent: 6453246 (2002-09-01), Agrafiotis et al.
patent: 6473717 (2002-10-01), Claussen et al.
patent: 6505181 (2003-01-01), Lambert et al.
patent: 6647341 (2003-11-01), Golub
patent: 6650779 (2003-11-01), Vachtesvanos et al.
patent: 6658395 (2003-12-01), Barnhill
patent: 6714925 (2004-03-01), Barnhill
patent: 6760715 (2004-07-01), Barnhill
patent: 6789069 (2004-09-01), Barnhill .
patent: 6882990 (2005-04-01), Barnhill
patent: 7039621 (2006-05-01), Agrafiotis et al.
patent: 7206646 (2007-04-01), Nixon et al.
patent: 2003/0036081 (2003-02-01), Adorjan
patent: 2004/0102905 (2004-05-01), Adorjan
A GA-based fuzzy feature evaluation algorithm for pattern recognition Han-Pang Huang; Yi-Hung Liu; Fuzzy Systems, 2001. The 10th IEEE International Conference on vol. 2, Dec. 2-5, 2001 pp. 833-836 vol. 3.
Orthogonal forward selection and backward elimination algorithms for feature subset selection Mao, K.Z.; Systems, Man and Cybernetics, Part B, IEEE Transactions on vol. 34, Issue 1, Feb. 2004 pp. 629-634 Digital Object Identifier 10.1109/TSMCB.2002.804363.
Optimal feature extraction for partial discharge recognition Weile Wang; Kexiong Tan; Kai Gao; Wensheng Gao; Electrical Insulating Materials, 2001. (ISEIM 2001). Proceedings of 2001 International Symposium on Nov. 19-22, 2001 pp. 115-118 Digital Object Identifier 10.1109/ISEIM.2001.973579.
Feature Subset Selection and Ranking for Data Dimensionality Reduction Hua-Liang Wei; Billings, S.A.; Pattern Analysis and Machine Intelligence, IEEE Transactions on vol. 29, Issue 1, Jan. 2007 pp. 162-166 Digital Object Identifier 10.1109/TPAMI.2007.250607.
Multicategory Classification of Patterns Represented by High-Order Vectors of Multilevel Measurements Glucksman, H.A.; Computers, IEEE Transactions on vol. C-20, Issue 12, Dec. 1971, pp. 1593-1598.
Feature selection for face recognition based on data partitioning Singh, S.; Singh, M.; Markou, M.; Pattern Recognition, 2002. Proceedings. 16th International Conference on vol. 1, Aug. 11-15, 2002 pp. 680-683 vol. 1 Digital Object Identifier 10.1109/ICPR.2002. 1044845.
Simplified ATPG and analog fault location via a clustering and separability technique Varghese, K.; Williams, J.; Towill, D.; Circuits and Systems, IEEE Transactions on vol. 26, Issue 7, Jul. 1979 pp. 496-505.
Utilizing scatter for pixel subspace selection Schweitzer, H.; Computer Vision, 1999. The Proceedings of the Seventh IEEE International Conference on vol. 2, Sep. 20-27, 1999 pp. 1111-1116 vol. 2 Digital Object Identifier 10.1109/ICCV.1999.790404.
Enhancing DPF for near-replica image recognition Yan Meng; Chang, E.; Beitao Li; Computer Vision and Pattern Recognition, 2003. Proceedings. 2003 IEEE Computer Society Conference on vol. 2, Jun. 18-20, 2003 pp. II-416-423 vol. 2 Digital Object Identifier 10.1109/CVPR.2003.1211498.
A Genetic Algorithm Approach for Discovering Diagnostic Patterns in Molecular Measurement Data Schaffer, J.D.; Janevski, A.; Simpson, M.R.; Computational Intelligence in Bioinformatics and Computational Biology, 2005. CIBCB '05. Proceedings of the 2005 IEEE Symposium on Nov. 14-15, 2005 pp. 1-8.
Generalization performance of multiclass discriminant models Paugam-Moisy, H.; Elisseeff, A.; Guermeur, Y.; Neural Networks, 2000. IJCNN 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on vol. 4, Jul. 24-27, 2000 pp. 177-182 vol. 4 Digital Object Identifier 10.1109/IJCNN.2000.860769.
A new multi-class SVM based on a uniform convergence result Guermeur, Y.; Elisseeff, A.; Paugam-Moisy, H.; Neural Networks, 2000. IJCNN 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on vol. 4, Jul. 24-27, 2000 pp. 183-188 vol. 4 Digital Object Identifier 10.1109/IJCNN.2000.860770.
Estimating the sample complexity of a multi-class discriminant model Guermeur, Y.; Elisseeff, A.; Paugam-Moisy, H.; Artificial Neural Networks, 1999. ICANN 99. Ninth International Conference on (Conf. Publ. No. 470) vol. 1, Sep. 7-10, 1999 pp. 310-315 vol. 1.
Confidence bounds for the generalization performances of linear combination of functions Gavin, G.; Elisseeff, A.; Artificial Neural Networks, 1999. ICANN 99. Ninth International Conference on (Conf. Publ. No. 470) vol. 1, Sep. 7-10, 1999 pp. 298-303 vol. 1.
Weighted least squares training of support vector classifiers leading to compact and adaptive schemes Navia-Vazquez, A.; Perez-Cruz. F.; Artes-Rodriguez, A.; Figueiras-Vidal, A.R.; Neural Networks, IEEE Transactions on vol. 12, Issue 5, Sep. 2001 pp. 1047-1059 Digital Object Identifier 10.1109/72.950134.
Empirical risk minimization for support vector classifiers Perez-Cruz, F.; Navia-Vazquez, A.; Figueiras-Vidal, A.R.; Artes-Rodriguez, A.; Neural Networks, IEEE Transactions on vol. 14, Issue 2, Mar. 2003 pp. 296-303 Digital Object Identifier 10.1109/TNN.2003.809399.
SVM multiregression for nonlinear channel estimation in multiple-input multiple-output systemsSanchez-Fernandez, M.; de-Prado-Cumplido, M.; Arenas-Garcia, J.; Perez-Cruz, F.; Signal Processing, IEEE Transactions on [see also Acoustics, Speech, and Signal Processing, IEEE Transactions on] vol. 52, Issue 8, Aug. 2004 pp. 2298-2307.
Learning a function and its derivative forcing the support vector expansion Lazaro, M.; Perez-Cruz, F.; Artes-Rodriguez, A.; Signal Processing Letters, IEEE vol. 12, Issue 3, Mar. 2005 pp. 194-197 Digital Object Identifier 10.1109/LSP.2004.840841.
Support vector machine for the simultaneous approximation of a function and its derivative Lazaro, M.; Santamaria, I.; Perez-Cruz, F.; Artes-Rodriguez, A.; Neural Networks for Signal Processing, 2003, NNSP'03. 2003 IEEE 13th Workshop on Sep. 17-19, 2003 pp. 189-198.
Multi-class support vector machines: a new approach Arenas-Garcia, J.; Perez-Cruz, F.; Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03). 2003 IEEE International Conference on vol. 2, Apr. 6-10, 2003 pp. II-781-784 vol. 2 Digital Object Identifier 10.1109/ICASSP.2003.1202483.
Unbiased support vector classifiers Navia-Vazquez, A.; Perez-Cruz, F.; Artes-Rodriguez, A.; Figueiras-Vidal, A.R.; Neural Networks for Signal Processing XI, 2001. Proceedings of the 2001 IEEE Signal Processing Society Workshop Sep. 10-12, 2001 pp. 183-192 Digital Object Identifier 10.1109/NNSP.2001.943123.
Cyclosporine concentration prediction using clustering and support vector regression methods Camps-Valls, G.; Soria-Olivas, E.; Perez-Ruixo, J.J.; Perez-Cruz, F.; Figueiras-Vidal, A.R.; Artes-Rodriguez, A.; Electronics Letters vol. 38, Issue 12, Jun. 6, 2002 pp. 568-570 Digital Object Identifier 10.1049/el:20020354.
Signal segmentation using self-organizing maps Pendock, N.; Communications and Signal Processing, 1993., Proceedings of the 1993 IEEE South African Symposium on Aug. 6, 1993 pp. 218-223 Digital Object Identifier

Affiliated with

Also associated with

Rating

Methods for feature selection in a learning machine does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Methods for feature selection in a learning machine, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Methods for feature selection in a learning machine will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-2814972