An investigation of tuning a memetic algorithm for cross-domain search
Memetic algorithms, which hybridise evolutionary algorithms with local search, are well-known metaheuristics for solving combinatorial optimisation problems. A common issue with the application of a memetic algorithm is determining the best initial setting for the algorithmic parameters, but these c...
| Main Authors: | , , |
|---|---|
| Format: | Conference or Workshop Item |
| Published: |
2016
|
| Subjects: | |
| Online Access: | https://eprints.nottingham.ac.uk/36135/ |
| _version_ | 1848795230365548544 |
|---|---|
| author | Gumus, Duriye Betul Özcan, Ender Atkin, Jason |
| author_facet | Gumus, Duriye Betul Özcan, Ender Atkin, Jason |
| author_sort | Gumus, Duriye Betul |
| building | Nottingham Research Data Repository |
| collection | Online Access |
| description | Memetic algorithms, which hybridise evolutionary algorithms with local search, are well-known metaheuristics for solving combinatorial optimisation problems. A common issue with the application of a memetic algorithm is determining the best initial setting for the algorithmic parameters, but these can greatly influence its overall performance. Unlike traditional studies where parameters are tuned for a particular problem domain, in this study we do tuning that is applicable to cross-domain search. We extend previous work by tuning the parameters of a steady state memetic algorithm via a ‘design of experiments’ approach and provide surprising empirical results across nine problem domains, using a cross-domain heuristic search tool, namely HyFlex. The parameter tuning results show that tuning has value for cross-domain search. As a side gain, the results suggest that the crossover operators should not be used and, more interestingly, that single point based search should be preferred over a population based search, turning the overall approach into an iterated local search algorithm. The use of the improved parameter settings greatly enhanced the crossdomain performance of the algorithm, converting it from a poor performer in previous work to one of the stronger competitors. |
| first_indexed | 2025-11-14T19:28:47Z |
| format | Conference or Workshop Item |
| id | nottingham-36135 |
| institution | University of Nottingham Malaysia Campus |
| institution_category | Local University |
| last_indexed | 2025-11-14T19:28:47Z |
| publishDate | 2016 |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | nottingham-361352020-05-04T17:59:00Z https://eprints.nottingham.ac.uk/36135/ An investigation of tuning a memetic algorithm for cross-domain search Gumus, Duriye Betul Özcan, Ender Atkin, Jason Memetic algorithms, which hybridise evolutionary algorithms with local search, are well-known metaheuristics for solving combinatorial optimisation problems. A common issue with the application of a memetic algorithm is determining the best initial setting for the algorithmic parameters, but these can greatly influence its overall performance. Unlike traditional studies where parameters are tuned for a particular problem domain, in this study we do tuning that is applicable to cross-domain search. We extend previous work by tuning the parameters of a steady state memetic algorithm via a ‘design of experiments’ approach and provide surprising empirical results across nine problem domains, using a cross-domain heuristic search tool, namely HyFlex. The parameter tuning results show that tuning has value for cross-domain search. As a side gain, the results suggest that the crossover operators should not be used and, more interestingly, that single point based search should be preferred over a population based search, turning the overall approach into an iterated local search algorithm. The use of the improved parameter settings greatly enhanced the crossdomain performance of the algorithm, converting it from a poor performer in previous work to one of the stronger competitors. 2016-07-29 Conference or Workshop Item PeerReviewed Gumus, Duriye Betul, Özcan, Ender and Atkin, Jason (2016) An investigation of tuning a memetic algorithm for cross-domain search. In: 2016 IEEE Congress on Evolutionary Computation, 24-29 July 2016, Vancouver, Canada. Tuning; Memetics; Steady-state; Algorithm design and analysis; Statistics https://ieeexplore.ieee.org/document/7743788/ |
| spellingShingle | Tuning; Memetics; Steady-state; Algorithm design and analysis; Statistics Gumus, Duriye Betul Özcan, Ender Atkin, Jason An investigation of tuning a memetic algorithm for cross-domain search |
| title | An investigation of tuning a memetic algorithm for cross-domain search |
| title_full | An investigation of tuning a memetic algorithm for cross-domain search |
| title_fullStr | An investigation of tuning a memetic algorithm for cross-domain search |
| title_full_unstemmed | An investigation of tuning a memetic algorithm for cross-domain search |
| title_short | An investigation of tuning a memetic algorithm for cross-domain search |
| title_sort | investigation of tuning a memetic algorithm for cross-domain search |
| topic | Tuning; Memetics; Steady-state; Algorithm design and analysis; Statistics |
| url | https://eprints.nottingham.ac.uk/36135/ https://eprints.nottingham.ac.uk/36135/ |