Performance improvement strategies on Cuckoo Search algorithms for solving the university course timetabling problem
•First report on modified and hybrid Cuckoo Search for real-world course timetabling.•Comprehensive review on metaheuristics applied to solve course timetabling problem.•Describe the Hybrid Self-adaptive Cuckoo Search based Timetabling (HSCST) tool.•Proposed three improvement strategies: parameter s...
Gespeichert in:
Veröffentlicht in: | Expert systems with applications 2020-12, Vol.161, p.113732, Article 113732 |
---|---|
Hauptverfasser: | , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | •First report on modified and hybrid Cuckoo Search for real-world course timetabling.•Comprehensive review on metaheuristics applied to solve course timetabling problem.•Describe the Hybrid Self-adaptive Cuckoo Search based Timetabling (HSCST) tool.•Proposed three improvement strategies: parameter setting, movement and hybridisation.•The proposed methods outperformed other conventional methods for all problem instances.
The university course timetabling problem (UCTP) arises every academic year and must be solved by academic staff with/without a course timetabling tool. A Hybrid Self-adaptive Cuckoo Search-based Timetabling (HSCST) tool has been developed for minimising the total university operating costs. The HSCST tool was applied to solve eleven problem instances obtained from the Faculty of Engineering, Naresuan University. The performance improvements of the Cuckoo Search (CS) algorithm embedded within the proposed tool were demonstrated using three strategies: parameter setting approaches (static and adaptive), movement strategies (Lévy flights and Gaussian random walks), and local search hybridisation techniques. Sequential computational experiments were designed and conducted to investigate the efficiency of the three proposed strategies. The statistical analysis on the computational results suggested that the proposed algorithms significantly outperformed the conventional CS, Particle Swarm Optimisation (PSO), and hybrid PSO for all problem instances. |
---|---|
ISSN: | 0957-4174 1873-6793 |
DOI: | 10.1016/j.eswa.2020.113732 |