Machine Learning Algorithms: Diagnosing Breast Cancer
Sridevi N1, Kulkarni Varsha2, Maria Navin J R3
1Sridevi N, Department of CS&E, Sri Venkateshwara College of Engineering, Bangalore (Karnataka), India.
2Kulkarni Varsha, Department of CS&E, Sri Venkateshwara College of Engineering, Bangalore (Karnataka), India.
3Maria Navin J R, Department of IS&E, Sri Venkateshwara College of Engineering, Bangalore (Karnataka), India.
Manuscript received on 22 August 2019 | Revised Manuscript received on 03 September 2019 | Manuscript Published on 16 September 2019 | PP: 849-851 | Volume-8 Issue-2S6 July 2019 | Retrieval Number: B11570782S619/2019©BEIESP | DOI: 10.35940/ijrte.B1157.0782S619
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Breast Cancer has become one of the common diseases not only in women but also in few men. According to research, the demise rate of females has increased mainly because of Breast Cancer tumor. One out of every eight women and one out of every thousand men are diagnosed with breast cancer. Breast cancer tumors are mainly classified into two types: Benign tumor which is a non-cancerous tumor and other one is malignant tumor which is a cancerous tumor. In order to know which type of tumor a patient has; the accurate and early diagnosis is a very crucial step. Machine Learning (ML) algorithms have been used to develop and train the model for classification of the type of tumor. For accurate and better classification several classification algorithms in ML have been trained and tested on the dataset that was collected. Already algorithms like Naïve Bayes, Random Forest, K-Nearest Neighbor and SVM showed better accuracy for classification of tumor. When we implemented Multilayer Perceptron (MLP) algorithm it gave us the best accuracy levels among all both during training as well as testing .i.e. 97%. So, the exact classification using this model will help the doctors to diagnose the type of tumor in patients quickly and accurately.
Keywords: Benign, Malignant, Naïve Bayes, Random Forest, K-Nearest Neighbor, SVM, MLP, Accuracy.
Scope of the Article: Machine Learning