Brain Tumor Detection by Fusing Machine Learning and Neural Network Practices
Mrinal Paliwal
Mrinal Paliwal, Department of Computer Science and Engineering, Sanskriti University, (Uttar Pradesh), India.
Manuscript received on 04 October 2019 | Revised Manuscript received on 18 October 2019 | Manuscript Published on 26 December 2019 | PP: 108-111 | Volume-8 Issue-12S October 2019 | Retrieval Number: L103210812S19/2019©BEIESP | DOI: 10.35940/ijitee.L1032.10812S19
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: An unusual cell number or mass in a living being brain is termed as “brain tumor”. A living being’s brain is present in the skull and the skull is very stiff in nature. Any external development within such a rigid space can trigger serious difficulties in the living being body. Tumors in the brain of a living being may be cancerous or may not. Therefore, the main cure is the detections of the brain tumor, its magnitude, and place. This study paper proposes a combination of approaches which integrates statistical methods and machine-based training practices “Support for the Vector Machine (SVM)” and the “Artificial Neural Network (ANN)” to achieve greater efficiency in brain tumors and in their phase’s identification as well as their place within magnetic resonance imaging pictures. In order to divide the magnetic resonance imaging pictures, an enhanced variant of standard “K-means” with Fuzzy C-means and temperature-based K-means & altered fuzzy clustering means. The value of K in the suggested method is an enhanced value, therefore, assists the fuzzy c to mean technique to perceive the tumor area.
Keywords: Brain Tumor, Fuzzy, K Means, Neural Network, Machine Learning, SVM.
Scope of the Article: Machine Learning