Breast cancer is second leading invasive cancer causes death after lung cancer. The accurate diagnosis is a very crucial aspect of breast cancer treatment. For this purpose, data mining techniques guide doctors in correct decision-making for diagnosis. This paper demonstrates various data mining methods for breast cancer diagnosis. The proposed algorithm is distinguished into two sections. First section consists of feature selection methods to reduce the computational complexity, as genetic algorithm is used to eliminate the irrelevant features from the dataset and second section describes different classification algorithms named Multilayer Perceptron, Random Forest, and Naive Bayes classification to determine whether breast cancer is malignant or benign type. The proposed algorithm is applied to four datasets of Wisconsin Breast Cancer Dataset and at last comparison is made between various classification algorithms to achieve highest classification accuracy.

Feature Selection, Genetic Algorithm, Multilayer Perceptron, Random Forest, Naive Bayes

[1] G. Devi , et at. "Breast Cancer Prediction System using Feature Selection and Data Mining Methods", International Journal of Advanced research in Computer Science, Vol. 2, Issue 1, pp. 81-87, 2011.
[2] R. Nithiya, et al. "A data Mining Techniques for Diagnosis of Breast Cancer Disease", World Applied Sciences Journal, 29 (Data Mining and Soft Computing Techniques), pp. 18-23, 2014.
[3] B. Zheng, et al. "Breast Cancer Diagnosis based on Feature Extraction using a Hybrid of K-means and Support Vector Machine Algorithms". Expert Systems with Applications, Elsevier, 2013.
[4] C. Lu, et al. "An Intelligent System for Lung Cancer Diagnosis Using a New Genetic Algorithm Based Feature Selection Method". Journal of Medical Systems, Springer Science, Vol. 38, pp. 88-97, 2014.
[5] S. Aalaei, et al. "Feature Selection using Genetic Algorithm for Breast Cancer Diagnosis: Experiment on three Different Datasets". Iran Journal of Basic Medical Sciences, Vol. 19, Issue 5, pp. 476-482, May 2016.
[6] C.R., K., T, M., "Feature Selection Methods for Classification: A Comparison". International Journal of Research in Engineering and Technology, Vol. 06, Issue 06, pp. 130-137, June 2017.
[7] B. Tamilvanan, V. M. Bhaskaran, "New Feature Selection Techniques Using Genetics Search and Random Search Approaches for Breast Cancer". Biosciences Biotechnology Research Asia, Vol. 14, Issue 1, pp. 409-414, 2017.
[8] E. Alickovic, et al. "Breast Cancer Diagnosis using Genetic Algorithm Feature Selection and Rotation Forest". The Neural Computing and Applications, Springer, 2015.
[9] D. Dumitru, et al. "Prediction of Recurrent Events In Breast Cancer using the Naive Bayesian Classification". Mathematics and Computer Science, Vol. 36, Issue 2, pp. 92-96, 2009.
[10] T. Karthikeyan, et al. "Genetic Algorithm based CFS and Naive Bayes Algorithm to Enhance the Prediction Accuracy". Indian Journal of Science and Technology, Vol. 8, Issue 27, 2015.
[11] S. Vanaja, et al. "Analysis of Feature Selection Algorithms on Classification: A Survey". International Journal of Computer Applications, Vol. 96, Issue 17, pp. 1-8. June 2014.
[12] R. Tiwari, et al. "Correlation Based Attribute Selection Using Genetic Algorithm". International Journal of Computer Applications, Vol. 4, Issue 8, pp. 28-34, August 2010.
[13] R. Suji, S. P. Rajagopalan."Multi-Ranked Feature Selection Algorithm for Effective Breast Cancer Detection". Biomedical Research, pp. S99-S102, 2016.
[14] D. Lavanya et al. "Analysis of Feature Selection with Classification: Breast Cancer Datasets". Indian Journal of Computer Science and Engg. Vol. 2, Issue 5, pp. 576-563, Oct-Nov 2011.
[15] Z. Karanpunar, et al. "Breast Cancer Diagnosis via Data Mining: Performance Analysis of Seven Different Algorithms". Computer Science and Engineering: An International Journal, Vol. 4, Issue 1, pp. 35-46, Feb. 2014.