Абстрактный

Multi-ranked feature selection algorithm for effective breast cancer detection

R Jaya Suji, SP Rajagopalan

In this paper, we propose a new feature selection algorithm called Multi-Ranked Feature Selection Algorithm (MRFSA) for effective feature selection to be used in a new cancer detection system. In addition, we use a Neuro-Fuzzy Temporal Classification algorithm for testing the performance of the feature selection algorithm in terms of classification accuracy. To test the efficacy of the proposed medical expert system, we have used the Wisconsin Breast Cancer Dataset (WBCD). The obtained classification accuracy is a very promising result compared to the existing works in this area based on the reports from the results for the same data set.