nach oben

Machine Vision and Applications

Erschienen in:

01.04.2014 | Original Paper

A feature selection method using improved regularized linear discriminant analysis

verfasst von: Alok Sharma, Kuldip K. Paliwal, Seiya Imoto, Satoru Miyano

Erschienen in: Machine Vision and Applications | Ausgabe 3/2014

Einloggen

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config

KI-gestützte Suche

Aus

Abstract

Investigation of genes, using data analysis and computer-based methods, has gained widespread attention in solving human cancer classification problem. DNA microarray gene expression datasets are readily utilized for this purpose. In this paper, we propose a feature selection method using improved regularized linear discriminant analysis technique to select important genes, crucial for human cancer classification problem. The experiment is conducted on several DNA microarray gene expression datasets and promising results are obtained when compared with several other existing feature selection methods.

Vorheriger Artikel ReigSAC: fast discrimination of spurious keypoint correspondences on planar surfaces

Nächster Artikel FPGA-based module for SURF extraction

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

über 102.000 Bücher
über 537 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Finance + Banking
Management + Führung
Marketing + Vertrieb
Maschinenbau + Werkstoffe
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 340 Zeitschriften

aus folgenden Fachgebieten:

Bauwesen + Immobilien
Business IT + Informatik
Finance + Banking
Management + Führung
Marketing + Vertrieb
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 390 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Maschinenbau + Werkstoffe

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Nur mit Berechtigung zugänglich

SVM-RFE [15] is a wrapper-based method. It is an iterative method which works backward from an initial set of features. The SVM aims to find maximum margin hyperplane between the two classes to minimize classification error using some kernel function.

Since RLDA or Improved RLDA is a method for solving small sample size (SSS) problem, the value of q has to be in (\(n,d\)).

Most of the datasets are downloaded from the Kent Ridge Bio-medical Dataset (KRBD) (http://datam.i2r.a-star.edu.sg/datasets/krbd/). The datasets are transformed or reformatted and made available by KRBD repository and we have used them without any further preprocessing. Some datasets which are not available on KRBD repository are downloaded and directly used from respective authors’ supplement link. The URL addresses for all the datasets are given in the Reference Section.

The cross-validation-based results are shown in Appendix A. The comparison of improved RLDA with different values of regularization parameter has been shown in Appendix B.

Table 2

The classification accuracy of various feature selection methods using four distinct classifiers on the SRBCT dataset

	J4.8 (%)	Naïve Bayes (%)	kNN (%)	SVM pairwise (%)
Baseline accuracy	37	37	37	37
Information gain	68	68	90	90
Twoing rule	64	73	86	82
Sum minority	68	68	90	86
Max minority	46	78	90	90
Gini index	64	78	90	90
Sum of variances	54	64	90	86
t-statistic	54	64	90	86
One-dimensional SVM	54	64	90	86
Lasso	90	70	80	75
Filter MRMR	65	35	55	85
Improved RLDA	75	90	95	100

Table 3

The classification accuracy of various feature selection methods using four distinct classifiers on the MLL dataset

	J4.8 (%)	Naïve Bayes (%)	kNN (%)	SVM pairwise (%)
Baseline accuracy	35	35	35	35
Information gain	60	74	86	100
Twoing rule	60	86	86	100
Sum minority	68	26	80	80
Max minority	74	34	74	80
Gini index	60	68	86	100
Sum of variances	60	54	86	100
t-statistic	60	54	86	100
One-dimensional SVM	60	54	86	100
Lasso	87	100	93	93
Filter MRMR	100	100	93	100
Improved RLDA	100	93	100	100

Table 4

The classification accuracy of various feature selection methods using four distinct classifiers on the Acute Leukemia dataset

	J4.8 (%)	Naïve Bayes (%)	kNN (%)	SVM pairwise (%)
Baseline accuracy	71	71	71	71
Information gain	91	100	97	97
Twoing rule	91	97	97	97
Sum minority	91	97	97	97
Max minority	91	97	97	97
Gini index	91	97	97	97
Sum of variances	91	97	97	97
t-statistic	91	100	97	97
One-dimensional SVM	91	85	88	97
Lasso	91	94	85	91
Filter MRMR	65	71	74	86
Improved RLDA	94	94	85	100

Note that for all the feature selection methods except Lasso method the number of selected features is 150 (in Tables 2, 3 and 4). The Lasso method itself obtains the optimal number of selected features and therefore cannot be adjusted for a predefined number of selected features.

Ingenuity Pathway Analysis (IPA) (http://www.ingenuity.com) is a software that helps researchers to model, analyze, and understand the complex biological and chemical systems at the core of life science research. IPA has been broadly adopted by the life science research community. IPA helps to understand complex ’omics data at multiple levels by integrating data from a variety of experimental platforms and providing insight into the molecular and chemical interactions, cellular phenotypes, and disease processes of the system. IPA provides insight into the causes of observed gene expression changes and into the predicted downstream biological effects of those changes. Even if the experimental data is not available, IPA can be used to intelligently search the Ingenuity Knowledge Base for information on genes, proteins, chemicals, drugs, and molecular relationships to build biological models or to get up to speed in a relevant area of research. IPA provides the right biological context to facilitate informed decision-making, advance research project design, and generate new testable hypotheses.

Anton, H.: Calculus. Wiley, New York (1995)

Armstrong, S.A., Staunton, J.E., Silverman, L.B., Pieters, R., den Boer, M.L., Minden, M.D., Sallan, S.E., Lander, E.S., Golub, T.R., Korsemeyer, S.J.: MLL translocations specify a distinct gene expression profile that distinguishes a unique leukemia. Nat. Genet. 30, 41–47 (2002). [Data Source1: http://sdmc.lit.org.sg/GEDatasets/Datasets.html] [Data Source2: http://www.broad.mit.edu/cgi-bin/cancer/publications/pub_paper.cgi?mode=view&paper_id=63]

Banerjee, M., Mitra, S., Banka, H.: Evolutinary-rough feature selection in gene expression data. IEEE Trans. Syst. Man Cybern. Part C Appl. Rev. 37, 622–632 (2007)CrossRef

Cong G., Tan K.-L., Tung A.K.H., Xu X.: Mining top-k covering rule groups for gene expression data. In: The ACM SIGMOD International Conference on Management of Data, pp. 670–681 (2005)

Dai, D.Q., Yuen, P.C.: Regularized discriminant analysis and its application to face recognition. Pattern Recognit. 36(3), 845–847 (2003)CrossRefMATH

Dai, D.Q., Yuen, P.C.: Face recognition by regularized discriminant analysis. IEEE Trans. SMC 37(4), 1080–1085 (2007)

Ding, C., Peng, H.: Minimum redundancy feature selection from microarray gene expression data. J. Bioinf. Comput. Biol. 523–529 (2003)

Duda, R.O., Hart, P.E.: Pattern Classification and Scene Analysis. Wiley, New York (1973)MATH

Dudoit, S., Fridlyand, J., Speed, T.P.: Comparison of discriminant methods for the classification of tumors using gene expression data. J. Am. Stat. Assoc. 97, 77–87 (2002)CrossRefMATHMathSciNet

10.

Friedman, J.H.: Regularized discriminant analysis. J. Am. Stat. Assoc. 84(405), 165–175 (1989)CrossRef

11.

Fukunaga, K.: Introduction to Statistical Pattern Recognition. Academic Press, London (1990)MATH

12.

Furey, T.S., Cristianini, N., Duffy, N., Bednarski, D.W., Schummer, M., Haussler, D.: Support vector machine classification and validation of cancer tissue samples using microarray expression data. Bioinformatics 16(10), 906–914 (2000)CrossRef

13.

Golub, T.R., Slonim, D.K., Tamayo, P., Huard, C., Gaasenbeek, M., Mesirov, J.P., Coller, H., Loh, M.L., Downing, J.R., Caligiuri, M.A., Bloomfield, C.D., Lander E.S.: Molecular classification of cancer: class discovery and class prediction by gene expression monitoring. Science 286, 531–537 (1999). [Data Source: http://datam.i2r.a-star.edu.sg/datasets/krbd/]

14.

Guo, Y., Hastie, T., Tibshirani, R.: Regularized discriminant analysis and its application in microarrays. Biostatistics 8(1), 86–100 (2007)CrossRefMATH

15.

Guyon, I., Weston, J., Barnhill, S., Vapnik, V.: Gene selection for cancer classification using support vector machines. Mach. Learn. 46, 389–422 (2002)CrossRefMATH

16.

Hastie, T., Tibshirani, R., Friedman, J.: The elements of statistical learning. Springer, NY (2001)CrossRefMATH

17.

Huang, R., Liu, Q., Lu, H., Ma, S.: Solving the small sample size problem of LDA. Proc. ICPR 3, 29–32 (2002)

18.

Huang, Y., Xu, D., Nie, F.: Semi-supervised dimension reduction using trace ratio criterion. IEEE Trans. Neural Netw. Learn. Syst. 23(3), 519–526 (2012)CrossRef

19.

Huang, Y., Xu, D., Nie, F.: Patch distribution compatible semi-supervised dimension reduction for face and human gait recognition. IEEE Trans. Circuits Syst. Video Technol. 22(3), 479–488 (2012)CrossRef

20.

Khan, J., Wei, J.S., Ringner, M., Saal, L.H., Ladanyi, M., Westermann, F., Berthold, F., Schwab, M., Antonescu, C.R., Peterson, C., Meltzer, P.S.: Classification and diagnostic prediction of cancers using gene expression profiling and artificial neural network. Nat. Med. 7, 673–679 (2001). [Data Source: http://research.nhgri.nih.gov/microarray/Supplement/]

21.

Li, J., Wong, L.: Using rules to analyse bio-medical data: a comparison between C4.5 and PCL. In: Advances in Web-Age Information Management, pp. 254–265. Springer, Berlin (2003)

22.

Liu, J., Chen, S.C., Tan, X.Y.: Efficient pseudo-inverse linear discriminant analysis and its nonlinear form for face recognition. Int. J. Patt. Recogn. Artif. Intell. 21(8), 1265–1278 (2007)CrossRef

23.

Nie, F., Huang, H., Cai X., Ding, C.: Efficient and robust feature selection via joint \(l_{2,1} \)-norms minimization, NIPS (2010)

24.

Pan, W.: A comparative review of statistical methods for discovering differentially expressed genes in replicated microarray experiments. Bioinformatics 18, 546–554 (2002)CrossRef

25.

Pavlidis, P., Weston, J., Cai, J. and Grundy, W.N.: Gene functional classification from heterogeneous data. In: International Conference on Computational Biology, pp. 249–255 (2001)

26.

Peng, H., Long, F., Dong, C.: Feature selection based on mutual information: criteria of max-dependency, max-relevance, and min-redundancy. IEEE Trans. Pattern Anal. Mach. Intell. 27(8), 1226–1238 (2005)CrossRef

27.

Saeys, Y., Inza, I., Larrañaga, P.: A review of feature selection techniques in bioinformatics. Bioinformatics 23(19), 2507–2517 (2007)CrossRef

28.

Sharma, A., Imoto, S., Miyano, S.: A top-r feature selection algorithm for microarray gene expression data. IEEE/ACM Trans. Computat. Biol. Bioinf. 9(3), 754–764 (2012)CrossRef

29.

Sharma, A., Imoto, S., Miyano, S.: A between-class overlapping filter-based method for transcriptome data analysis. J. Bioinf. Computat. Biol. 10(5), 1250010-1–1250010-20 (2012)

30.

Sharma, A., Imoto, S., Miyano, S., Sharma, V.: Null space based feature selection method for gene expression data. Int. J. Mach. Learn. Cybern. 3(4), 269–276 (2012). doi:10.1007/s13042-011-0061-9 CrossRef

31.

Sharma, A., Koh, C.H., Imoto, S., Miyano, S.: Strategy of finding optimal number of features on gene expression data. IEE. Electron. Lett. 47(8), 480–482 (2011)CrossRef

32.

Sharma, A., Paliwal, K.K.: Fast principal component analysis using fixed-point algorithm. Pattern Recognit. Lett. 28(10), 1151–1155 (2007)CrossRef

33.

Sharma, A., Paliwal, K.K.: Rotational linear discriminant analysis for dimensionality reduction. IEEE Trans. Knowl. Data Eng. 20(10), 1336–1347 (2008)CrossRef

34.

Sharma, A., Paliwal, K.K.: A gradient linear discriminant analysis for small sample sized problem. Neural Process. Lett. 27(1), 17–24 (2008)CrossRef

35.

Sharma, A., Paliwal, K.K.: A new perspective to null linear discriminant analysis method and its fast implementation using random matrix multiplication with scatter matrices. Pattern Recognit. 45, 2205–2213 (2012)CrossRefMATH

36.

Sharma, A., Lyons, J., Dehzangi, A., Paliwal, K.K.: A feature extraction technique using bi-gram probabilities of position specific scoring matrix for protein fold recognition. J. Theoret. Biol. 320(7), 41–46 (2013)CrossRefMathSciNet

37.

Sharma, A., Paliwal, K.K., Imoto, S., Miyano, S., Sharma, V., Ananthanarayanan, R.: A feature selection method using fixed-point algorithm for DNA microarray gene expression data. Int. J. Knowl. Based Intell. Eng. Syst. (2013, accepted)

38.

Su, Y., Murali, T.M., Pavlovic, V., Kasif, S.: RankGene: identification of diagnostic genes based on expression data, Bioinformatics, pp. 1578–1579 (2003)

39.

Tan, A.C., Gilbert, D.: Ensemble machine learning on gene expression data for cancer classification. Appl. Bioinf. 2(3 Suppl), S75–83 (2003)

40.

Tao, L., Zhang, C., Ogihara, M.: A comparative study of feature selection and multiclass classification methods for tissue classification based on gene expression. Bioinformatics 20(14), 2429–2437 (2004)

41.

Thomas, J., Olson, J.M., Tapscott, S.J., Zhao, L.P.: An efficient and robust statistical modeling approach to discover differentially expressed genes using genomic expression profiles. Genome Res. 11, 1227–1236 (2001)CrossRef

42.

Tibshirani, R.: Regression shrinkage and selection via the lasso. J. R. Stat. Soc. B 58(1), 267–288 (1996)MATHMathSciNet

43.

Wang, A., Gehan, E.A.: Gene selection for microarray data analysis using principal component analysis. Stat. Med. 24, 2069–2087 (2005)CrossRefMathSciNet

44.

Wu, G., Xu, W., Zhang, Y., Wei, Y.: A preconditioned conjugate gradient algorithm fo GeneRank with application to microarray data mining. Data Mining Knowl. Discov. (2011). doi:10.1007/s10618-011-0245-7

45.

Xu, D., Yan, S.: Semi-supervised bilinear subspace learning. IEEE Trans. Image Process. 18(7), 1671–1676 (2009)CrossRefMathSciNet

46.

Zhou, L., Wang, L., Shen, C., Barnes, N.: Hippocampal shape classification using redundancy constrained feature selection. Medical Image Computing and Computer-Assisted Intervention, MICCAI 2010. In: Lecture Notes in Computer Science, vol. 6362, pp. 266–273. Springer, Berlin (2010)

Titel: A feature selection method using improved regularized linear discriminant analysis
verfasst von: Alok Sharma
Kuldip K. Paliwal
Seiya Imoto
Satoru Miyano
Publikationsdatum: 01.04.2014
Verlag: Springer Berlin Heidelberg
Erschienen in: Machine Vision and Applications / Ausgabe 3/2014
Print ISSN: 0932-8092
Elektronische ISSN: 1432-1769
DOI: https://doi.org/10.1007/s00138-013-0577-y

Springer Professional

Abstract

Bitte loggen Sie sich ein, um Zugang zu Ihrer Lizenz zu erhalten.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Springer Professional "Wirtschaft"

Springer Professional "Technik"

Weitere Artikel der Ausgabe 3/2014

Multi-view traffic sign detection, recognition, and 3D localisation

Dynamic objects detection through visual odometry and stereo-vision: a study of inaccuracy and improvement sources

Parking assistance using dense motion-stereo

Exploiting temporal and spatial constraints in traffic sign detection from a moving vehicle

Traffic event classification at intersections based on the severity of abnormality

Recent progress in road and lane detection: a survey

Premium Partner