Feature Selection Based on Multi-Filters for Classification of Mammogram Images to Look for Signs of Breast Cancer

The accuracy of classification results on mammogram images has a significant role in breast cancer diagnosis. Therefore, many stages consider finding the model high level and minimizing computing load, one which is using best feature. This needs to be prioritized considering that image features resulting from extraction process. Our research four stages: feature extraction, selection-multi filters, classification, performance evaluation. Thus, this research, we propose algorithms can select by utilizing multiple filters simultaneously filter for selection based multi-filters/FSbMF. There are six with approach (information gain, rule, relief, correlation, gini index, chi-square) used research. Based testing result 10-fold cross-validation, FSbMF algorithm have accuracy, recall, precision 72,63%, 70,38%, 75,01% 100%. Furthermore, number minimum because it intersection operation subsets multi-filter.