1. IMRAN QURESHI - Lecturer, Department of Information Technology, University of Technology and Applied Science
AlMusanna, Sultanate of Oman.
2. BURHANUDDIN MOHAMMAD - Lecturer, Department of Information Technology, University of Technology and Applied Science
AlMusanna, Sultanate of Oman.
3. MOHAMMED ABDUL HABEEB - Lecturer, Department of Information Technology, University of Technology and Applied Science
AlMusanna, Sultanate of Oman.
4. S.G.M. SHADAB - Lecturer, Department of Information Technology, University of Technology and Applied Science
AlMusanna, Sultanate of Oman.
It investigates the reduction of features in a breast cancer decision assistance system. The WDBC dataset is converted to a one-dimensional feature vector (IC). The original data with 30 features and one reduced feature (IC) is used to evaluate diagnostic accuracy of classifier using support vector machine (SVM). The suggested classification using the IC is compared to the original feature set using different validation (5/10-fold cross-validations) and partitioning (20%–40%) methods. Its performance is measured in terms of specificity, sensitivity, accuracy, F-score, You den’s index, discriminant power, and the receiver operating characteristic (ROC) curve with its criterion values of area under curve (AUC) and 95% confidence interval (CI) (CI). This reduces computing complexity while improving diagnostic decision assistance.
Support vector machine, machine learning, classification, WDBC datasets.