Affiliations: [a] Professor of ECE, Miracle Educational Society group of Institutions, Bhogapuram, Vizianagaram Dt. AP | [b] Professor and HOD, -EIE, VR Siddhartha Engineering College (A), Vijayawada, AP | [c] Professor of ECE, University College of Engineering, JNTUK, Kakinada and Member of APPSC
Correspondence:
[*]
Corresponding author. B. Ratna Raju, Professor of ECE, Miracle Educational Society group of Institutions, Bhogapuram, Vizianagaram Dt. AP. E-mail: [email protected].
Abstract: The Colorectal cancer leads to more number of death in recent years. The diagnosis of Colorectal cancer as early is safe to treat the patient. To identify and treat this type of cancer, Colonoscopy is applied commonly. The feature selection based methods are proposed which helps to choose the subset variables and to attain better prediction. An Imperialist Competitive Algorithm (ICA) is proposed which helps to select features in identification of colon cancer and its treatment. Also K-Nearest Neighbor (KNN) classifier is used to retain a minimal Euclidean distance between the feature of query vector and all the data in the nature of prototype training. Experimental results have proved that the proposed method is superior when compared to other methods in its metrics of performance. Better accuracy is achieved by the proposed method.
