Performance Evaluation of Several Machine Learning Techniques Used in the Diagnosis of Mammograms
Sushreeta Tripathy, Department of Computer Science & Information Technology, S ’O’ A Deemed to be University, Bhubaneswar, India.
Manuscript received on 05 July 2019 | Revised Manuscript received on 09 July 2019 | Manuscript published on 30 August 2019 | PP: 228-232 | Volume-8 Issue-10, August 2019 | Retrieval Number: I7891078919/2019©BEIESP | DOI: 10.35940/ijitee.I7891.0881019
Open Access | Ethics and 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: Throughout the world breast cancer has become a common disease among the women and it is also a life threatening diseases. Machine learning(ML) approach has been widely used for the diagnosis of benign and malignant masses in the mammogram. In this manuscript, I have represented the theoretical research and practical advances on various machine learning techniques the diagnosis of benign and malignant masses in the mammogram. The objective of this manuscript is to analyze the performance of distinct machine learning techniques used in the diagnosis of the Digital Mammography Image Analysis Society (MIAS) database. In this work I have compared performance of four machine learning approaches i.e. Support Vector, Naive Bayes, K-Nearest Neighbours and Multilayer Perceptron. The above four types of machine learning algorithm are used to categorize mammograms image. The achievements of these four techniques were recognized to discover the most acceptable classifier. On the end of the examine, derived outcomes indicates that support vector is a successful approach compares to other approach.
Keywords: Breast Cancer, K-Nearest Neighbours (KNN), Multi Layer Perceptron(MLP), Malignant, Naive Bayes(NB),Support Vector Machine (SVM).
Scope of the Article: Machine Learning