MICROARRAY DATA CLASSIFICATION USING DUAL TREE M-BAND WAVELET FEATURES
Deoxyribo Nucleic Acid (DNA) microarrays are widely used to monitor the expression levels of genes in parallel. It is possible to predict human cancer using the expression levels from a collection of DNA samples. Due to the vast number of genes expression level, it is challenging to analyze them manually. In this paper, data mining approach is used to extract the prevailing information from DNA microarray with the help of multiresolution analysis tool. Dual Tree M-Band Wavelet Transform (DTMBWT) is employed for the extraction of features from the given dataset at the 2nd level of decomposition. K-Nearest Neighbor (KNN) classifier is used for cancer classification. Results show that KNN classifier classifies five different cancer datasets; Breast, Colon, Ovarian, CNS, and Leukemia with over 90% accuracy. Â
A.H. Chen, G.T. Chen, J.C. Hsieh, and C.H. Lin, â€œBCPP: An intelligent prediction system of breast cancer prognosis using microarray and clinical dataâ€, IEEE WRI World Congress on Computer Science and Information Engineering, Vol. 5, 2009, pp. 28-32.
W. Chen, H. Lu, M. Wang, and C. Fang, â€œGene expression data classification using artificial neural network ensembles based on samples filteringâ€, IEEE International Conference on Artificial Intelligence and Computational Intelligence, Vol. 1, 2009, pp. 626-628.
Y.M. Chiang, H.M. Chiang, and S.Y. Lin, â€œThe application of ant colony optimization for gene selection in microarray-based cancer classificationâ€, IEEE International Conference on Machine Learning and Cybernetics, Vol. 7, 2008, pp. 4001-4006.
C.C. Chuang, S.F. Su, and J.T. Jeng, â€œDimension reduction with support vector regression for ovarian cancer microarray dataâ€, IEEE International Conference on Systems, Man and Cybernetics, Vol. 2, 2005, pp. 1048-1052.
L.M. Fu, and E.S. Youn, â€œImproving reliability of gene selection from microarray functional genomics dataâ€, IEEE Transactions on Information Technology in Biomedicine, Vol.7, No.3, 2003, pp.191-196.
P.G. Kumar, T.A.A. Victoire, P. Renukadevi, and D. Devaraj, â€œDesign of fuzzy expert system for microarray data classification using a novel genetic swarm algorithmâ€, Expert Systems with Applications, Vol.39, No.2, pp.1811-1821.
S. Hengpraprohm, and P. Chongstitvatana, â€œSelecting Informative Genes from Microarray Data for Cancer Classification with Genetic Programming Classifier Using K-Means Clustering and SNR Rankingâ€, IEEE Frontiers in the Convergence of Bioscience and Information Technologies, 2007, pp. 211-218.
S. Hengpraprohm, S. Mukviboonchai, R. Thammasang, and P. Chongstitvatana, â€œA GA-Based classifier for microarray data classificationâ€, IEEE International Conference on Intelligent Computing and Cognitive Informatics, 2010, pp. 199-202.
N. Iam-On, and T. Boongoen, â€œRevisiting link-based cluster ensembles for microarray data classificationâ€, IEEE International Conference on Systems, Man, and Cybernetics, 2013, pp. 4543-4548.
S. Li, C. Liao, and J.T. Kwok, â€œWavelet-based feature extraction for microarray data classificationâ€, IEEE International Joint Conference on Neural Networks, 2006, pp. 5028-5033.
A. Osareh, and B. Shadgar, â€œMicroarray data analysis for cancer classificationâ€, IEEE 5th International Symposium on Health Informatics and Bioinformatics, 2010, pp. 125-132.
N. Kingsbury, â€œComplex wavelets for shift invariant analysis and filtering of Signalsâ€, Applied and computational harmonic analysis, Vol. 10, No. 3, 2001, pp. 234-253.
I.W. Selesnick, â€œThe double-density dual-tree DWTâ€, IEEE Transaction on Signal Processing, Vol. 52, No. 5, 2004, pp. 1304-1314.
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).