A General Study on Feature Selection for Cancer Classification

Authors

  • Santosini Bhutia Indira Gandhi Institute of Technology, Sarang, Dhenkanal, Odisha, India. https://orcid.org/0000-0001-6069-5658
  • Biswajit Tripathy Gandhi Institute for Technological Advancement, Bhubaneswar, Odisha, India.

Abstract

In the context of cancer research microarray experiments are the most powerful mechanism for the diagnosis of disease. It has the ability to identify the characteristics of gene expression pattern. But DNA microarray experiment produces a huge number of features or genes which is usually more than thousands for a few number of samples or subjects which is less than hundreds.1 To date this problem there are various efficient classification and good feature selection methods are implemented to reduce the complexity and advance the cost. In this paper we on the methodologies for feature selection to identify important genes that improve the accuracy of classification.

How to cite this article:
Bhutia S, Tripathy B. A General Study on Feature Selection for Cancer Classification. J Engr Desg Anal 2020; 3(2): 85-87.

References

Lakhani, Sunil R, Ashworth A. Microarray and histopathological analysis of tumours: the future and the past?.” Nature Reviews Cancer 1.2 (2001): 151-157.

Harrington, Christina A, Rosenow C et al. Monitoring gene expression using DNA Microarrays. Current Opinion in Microbiology 2000; 3(3): 285-291.

Vapnik V. Statistical learning theory., in: 1998.

Dash S, Patra BN. A Hybrid Data Mining Technique for Improving the Classification Accuracy of Microarray Data Set. I.J. Information Engineering and Electronic Business 2012; 4(2): 43-50.

Chow TWS, Cho SY. Neural networks and computing: learning algorithms and applications, Imperia College Press, Distributed by World Scientific, London, Singapore, Hackensack, NJ 2007.

Platt J. Fast training of support vector machines using sequential minimal optimization. Advances in Kernel Methods Support Vector Learning. 1998, MIT Press.

Patra BN, Bisoyi SS. CFSES optimization feature selection with neural network classification for microarray data analysis. International Conference on Data Science and Business Analytics (ICDSBA) 2018.

Published

2021-04-30