The following information was submitted:
Transactions: WSEAS TRANSACTIONS ON COMPUTERS
Transactions ID Number: 53-857
Full Name: Gurusamy Jeyakumar
Position: Assistant Professor
Age: ON
Sex: Male
Address: Amrita School of Engineering, Amrita Vishwa Vidyapeetham
Country: INDIA
Tel: +91-9842643901
Tel prefix:
Fax:
E-mail address: g_jeyakumar@cb.amrita.edu
Other E-mails:
Title of the Paper: Differential Evolution Variants for Unconstrained Global Optimization: An Empirical Study
Authors as they appear in the Paper: G.Jeyakumar, C.Shunmuga Velayutham
Email addresses of all the authors: g_jeyakumar@cb.amrita.edu, cs_velayutham @cb.amrita.edu
Number of paper pages: 30
Abstract: In this paper, we present an empirical comparison of Differential Evolution (DE) variants to solve different classes of problems. The aim is to identify the behavior of DE variants and answering the question of Why the variants behave so?. We have chosen fourteen functions grouped by feature: unimodal and separable, unimodal and nonseparable, multimodal and separable and multimodal and nonseparable. Fourteen variants were implemented and tested on the fourteen functions for the dimension of 30. The behavior of the DE variants are analyzed and well compared by measuring mean objective function values (MOV), error values, probability of convergence (Pc), Convergence Measure (Cm), Quality Measure (Qm), evolution of empirical population variance (evar) and radius of population (Pm).
Keywords: Differential Evolution; Global Optimization; Exploration and Exploitation; Population Variance; Stagnation; Premature Convergence
EXTENSION of the file: .pdf
Special (Invited) Session:
Organizer of the Session:
How Did you learn about congress: Evolutionary Computing, Differential evolution
IP ADDRESS: 117.240.224.2
