Asian Journal of Information Technology

Year: 2016
Volume: 15
Issue: 22
Page No. 4438 - 4444

Rough Set Based Approach for Multiclass Breast Tissue Classification

Authors : V.P. Sumathi, K. Kousalya and V. Vanitha

Abstract: Breast cancer is the most common diseases among women and the detection of breast cancer for younger women at an earlier stage can save lives. To identify breast cancer most of the existing work is based on mammography images and has achieved higher accuracy. But the usual mammography test is not suitable and it is not recommended for younger women. Hence, the Electrical Impedance Spectrum (EIS) test for breast cancer detection is more suitable for younger women, the proposed work make use of EIS data to detect breast cancer. The proposed research is based on rough set due to lot of uncertainty in breast tissue data set. The result of classification accuracy and error rate is evaluated. This result indicates that the proposed rough set based approach achieves average accuracy of 65% in six class problem, 80% in four class problem and 85% in two class problem. The two decision classes acquired >80% accuracy using fivefold validation.

How to cite this article:

V.P. Sumathi, K. Kousalya and V. Vanitha, 2016. Rough Set Based Approach for Multiclass Breast Tissue Classification. Asian Journal of Information Technology, 15: 4438-4444.

Design and power by Medwell Web Development Team. © Medwell Publishing 2023 All Rights Reserved