Ensemble of parameters for nature-inspired algorithms : Firefly algorithm and invasive weeds optimization algorithm

• Main Author: Raditya, Reza
• Other Authors: Ponnuthurai Nagaratnam Suganthan
• Format: Final Year Project
• Language: English
• Published: 2013
• Subjects: DRNTU::Engineering::Electrical and electronic engineering::Computer hardware, software and systems
• Online Access: http://hdl.handle.net/10356/50989
• Institution: Nanyang Technological University

Optimization problems are present in almost every aspect of our life, from the simple ones to the complex ones. Because of that, many optimization algorithms are developed recently, including nature-inspired optimization algorithms, which are inspired by the behaviors of nature. Ensemble method is also a well-known method to increase the performance of an optimization algorithm. This method introduces a pool of candidates which can be selected, randomly or by learning process, by each member of the algorithm’s populations in every iteration. The purpose of this project is to implement ensemble method in two nature-inspired algorithms, which are Firefly Algorithm, which is inspired by the flashing behaviors of fireflies, and Invasive Weeds Optimization Algorithm, which is inspired by the process of distribution and colonization of weeds. This project will examine whether ensemble method is the suitable method for these algorithms in improving the performance. A Hybrid Algorithm, an algorithm combining Firefly Algorithm and Invasive Weeds Optimization Algorithm, is also developed in this project. All the implementations are done in MATLAB environment.