Supervised fuzzy clustering for the identification of fuzzy classifiers
Pattern Recognition Letters
Data Mining: Concepts and Techniques
Data Mining: Concepts and Techniques
Implementing automated diagnostic systems for breast cancer detection
Expert Systems with Applications: An International Journal
Improved use of continuous attributes in C4.5
Journal of Artificial Intelligence Research
Hi-index | 0.00 |
Malignant Neoplasm commonly referred as cancer is caused by uncontrolled growth of cells in the body. According to the American Cancer Society nearly 7.6 million people died from cancer during 2007. The true inspiration for this paper comes from the paper "Implementing automated diagnostic systems for breast cancer detection" by E. D. Ubeyli, achieved appealing results by using different kinds of Neural Network algorithms such as Combine Neural Network(CNN) Recurrence Neural Network(RNN), Probabilistic Neural Network(PNN), Multilayer Perceptron (MLP) and Support Vector Machine (SVM)). We used a hybrid approach for the same diagnosis. The hybrid system that we used was Neuro-Fuzzy (ANFIS-MATLAB) which is a combination of Neural Network and Fuzzy Logic. As an extension of this research and curiosity to evaluate the hybrid approach we implemented a Fuzzy Inference System(FIS) in MATLAB using fuzzy toolbox. The hybrid system trained on equally distributed dataset outperforms all other approaches discussed in literature. Specifically the sensitivity obtained in our Neuro-Fuzzy system is 100% which outperforms sensitivity of 99.37% in the SVM (Support Vector Machine) model used by E. D. Ubeyli [5].