The focus of this study is to develop a better fuzzy expert system for the detection of breast cancer using decision tree analysis for deriving the rule base.
Authors
Vedika Gupta, Assistant Professor, Jindal Global Business School, O.P. Jindal Global University, Sonipat, Haryana, India.
Harshit Gaur, Department of Computer Science and Engineering, Bharati Vidyapeeth’s College of Engineering, New Delhi, India.
Srishti Vashishtha, Department of Computer Science and Engineering, Bharati Vidyapeeth’s College of Engineering, New Delhi, India.
Uttirna Das, Department of Computer Science and Engineering, Bharati Vidyapeeth’s College of Engineering, New Delhi, India.
Vivek Kumar Singh, Department of Computer Science, Banaras Hindu University, Varanasi, India.
D. Jude Hemanth, Department of Electronics and Communication Engineering, Karunya University, Coimbatore, India
Summary
Breast cancer is possibly the deadliest illness in the world and the risks are gradually increasing. One out of eight women has the chance to be detected with breast cancer in their lifetime. The utmost cause for the higher fatality rates is the prolonged prognosis for the detection of breast cancer.
The focus of this study is therefore to develop a better fuzzy expert system for the detection of breast cancer using decision tree analysis for deriving the rule base. For this classification problem, the input features of the dataset are converted into human-understandable terms-linguistic variables.
The Mamdani Fuzzy Rule-Based system is deployed as the main inference engine and the centroid method for the defuzzification process to convert the final fuzzy score into class labels- benign (not cancerous) or malignant (cancerous). A decision tree algorithm is applied the creating a novel set of 27 fuzzy rules which are fed into FRBS. The investigation is performed on the publicly available Wisconsin Breast Cancer Dataset. The accuracy obtained by the proposed system is about 97%, recall is 99.58% and precision is about 93%. The experiments on this dataset yield higher performance as compared to the state-of-the-art dataset.
Published in: IET Image Processing
To read the full article, please click here.
