vioft2nntf2t|tblJournal|Abstract_paper|0xf4ff89d5280000001948010001000400 Data mining plays an important role in the process of classifying between the normal and the cancerous samples by utilizing microarray gene data. As this classification process is related to the human lives, greater sensitivity and specificity rates are mandatory. Taking this challenge into account, this work presents a technique to classify between the normal and cancerous samples by means of efficient feature selection and classification. The process of feature selection is achieved by Information Gain Ratio (IGR) and the selected features are forwarded to the classification process, which is achieved by ensemble classification. The classifiers being employed to attain ensemble classification are k-Nearest Neighbour (k-NN), Support Vector Machine (SVM) and Extreme Learning Machine (ELM). The performance of the proposed approach is analysed with respect to three different datasets such as Leukemia, Colon and Breast cancer in terms of accuracy, sensitivity and specificity. The experimental results prove that the proposed work shows better results, when compared to the existing techniques.
Thomas Scaria1, T Christopher2
St. Pius X College, India1, Government Arts College, Coimbatore, India2
Data Mining, Classification, Feature Selection
| January | February | March | April | May | June | July | August | September | October | November | December |
| 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
| Published By :
ICTACT
Published In :
ICTACT Journal on Soft Computing
( Volume: 9 , Issue: 1 , Pages: 1806-1812 )
Date of Publication :
October 2018
Page Views :
122
Full Text Views :
2
|