A Comparative Analysis of Neural Network & Fuzzy Classifier for Brain Tumour Detection
Suchita Goswami1, Archana Tiwari2, Vivek Pali3, Ankita Tripathi4
1Suchita Goswami, Department of Electronics Engineering, Ramdeobaba College of Engineering & Management, Nagpur (Maharashtra), India.
2Archana Tiwari, Department of Electronics Engineering, Ramdeobaba College of Engineering & Management, Nagpur (Maharashtra), India.
3Vivek Pali, Department of Computer Science Engineering, Chhattisgarh Institute of Technology, Rajnandgaon (Chhattisgarh), India.
4Ankita Tripathi, Department of Electronics Engineering, Hitam College of Engineering, Hyderabad (Telangana), India.
Manuscript received on 07 December 2018 | Revised Manuscript received on 18 December 2018 | Manuscript published on 30 December 2018 | PP: 53-58 | Volume-8 Issue-2C2, December 2018 | Retrieval Number: 100.1/ijeat.B10121282C218/18©BEIESP
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: The errand of MRI (Magnetic resonation Imaging) cerebrum variety from the same old revelation is difficult as a result of the difference and flightiness of tumors. Cerebrum tumor finding requires an ordered exam, which includes meddling restorative technique that can be difficult and might make problem patients. This paper demonstrates an trade unsupervised studying based Neural framework classifier and Fuzzy purpose classifier for the acknowledgment of tumor inside the attractive resonation human personality images. On this paper, the cerebrum tumor investigative strategy is parceled into the going with tiers. The critical diploma includes photo preplanning which fuses picture resizing, noise filtering, thresholding, and so on. In 2d stage, the functions of the MR thoughts photograph are evacuated using gray size co-occurence grid (GLCM). In 1/3 level, cerebrum tumor finding is performed using Neural framework (Self managing manual) primarily based classifier and Fuzzy basis (Fuzzy C-suggests collecting) based totally classifier. The were given accuracy of neural framework classifier is ninety six% and affectability is 90 % and disposition is sixty six% and that of feathery c-infers cerebrum image classifier is 98% and affectability and unequivocality are a hundred% and 66.6% independently. The introduction of the portrayal technique is surveyed through the usage of execution gauges, for instance, precision, affectability and unequivocality and is differentiated and severa approach reliant on past work.
Keywords: Watchwords Magnetic Resonance Imaging (MRI), Fuzzy Cinfers Gathering (FCM), Grey Dimension Co-occurence Set Up (GLCM), Accuracy, Sensitivity, Specificity.
Scope of the Article: Neural Information Processing