An Effective Classification Algorithm for Breast Cancer using Dyadic Projection
T Yasodha1, Arun Balaji G2
1Dr T Yasodha, Head of the Department, Electronics and Communication Engineering, Christian College of Engineering and Technology, Oddanchatram, Tamilnadu, India.
2Arun Balaji G, PG Scholar, Department of Electronics and Communication Engineering, Christian College of Engineering and Technology, Oddanchatram, Tamilnadu, India
Manuscript received on April 30, 2020. | Revised Manuscript received on May 06, 2020. | Manuscript published on May 30, 2020. | PP: 2323-2327 | Volume-9 Issue-1, May 2020. | Retrieval Number: A2571059120/2020©BEIESP | DOI: 10.35940/ijrte.A2571.059120
Open Access | Ethics and Policies | Cite | Mendeley
© 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: Abstract—Breast Cancer is a wide spread reason for the deaths of women in the world. Nowadays, CAD systems have become the most increasing interest in its detection. In this paper, a new computer-aided diagnosis method is introduced to help oncologists to classify it as benign or evil breast tumors in ultrasound. In the proposed model, bi clustering is done for feature acquisition and then dyadic transform is applied. Biclustering mining is used as a key to identify the regularity patterns in columns on the working out data, Biclustering mining is utilized as a key. At last, to identify the perfect combinations and put them into a strong classifier, AdaBoost learning is applied. Using a dataset the proposed method is evaluated validated and the results are compared with the results of existing methods. The results of the proposed model showed the best calculation, proving it to be effective in laboratory applications.
Keywords: Biclustering, computer-aided diagnosis, adaboost, feature scaling, ensemble learning.
Scope of the Article: Classification