A COMPARISON OF DIFFERENT PATTERN RECOGNITION METHODS WITH ENTROPY BASED FEATURE REDUCTION IN EARLY BREAST CANCER CLASSIFICATION

  • Liuhua Zhang Department of Computer Science, Memorial University of Newfoundland, Canada
  • Wenbin Zhang Department of Computer Science, Memorial University of Newfoundland, Canada

Abstract

Breast cancer is in the most common malignant tumor in women. It accounted for 30% of new malignant tumor cases. Although the incidence of breast cancer remains high around the world, the mortality rate has been continuously reduced. Early detection by mammography is an integral part of that.In the study, we tested on three combinations of wavelet and Fourier features, including Db2, Db4, and Bior 6.8, and selected the top appropriate amounts of features which related most to the breast cancer according to the information gain. At last, three classifiers, including Back-propagation (BP) Network, Linear Discriminant Analysis (LDA), and Naïve Bayes (NB) Classifier, were tested in the original and new database, and significant figures such as sensitivity and specificity were calculated and compared.

Downloads

Download data is not yet available.
Published
2014-03-26
How to Cite
Zhang, L., & Zhang, W. (2014). A COMPARISON OF DIFFERENT PATTERN RECOGNITION METHODS WITH ENTROPY BASED FEATURE REDUCTION IN EARLY BREAST CANCER CLASSIFICATION. European Scientific Journal, ESJ, 10(7). https://doi.org/10.19044/esj.2014.v10n7p%p