DEVELOPMENT OF THE EFFORTS-BASED OUTLOOK LEARNING MODELS USING INFORMATION SET THEORY

Abstract

This paper presents the conceptualization of efforts in the formulation of Effort Based Outlook Learning Models (EB-OLMs), named as Efforts that Disregard Outcome (EDO), Efforts to Raise Outcome (ERO), and Efforts to Steel Outcome (ESO). The efforts are put in achieving a goal or an objective by a contender for success. The outlook of each contender is modelled by the way efforts are contemplated. We have used some of elements of the information set theory in the construction of EB-OLMs. The superiority of these models over some well-known Meta-heuristic techniques is demonstrated on some standard optimization functions.  The design of both the classifier and predictor showcases the applicability of EB-OLMS in learning their parameters through two case studies. The first case study presents the formulation of a classifier for the detection of retinal diseases whereas the second case study is that of a predictor for the prediction of heart diseases