Use this URL to cite or link to this record in EThOS:
Title: Machine learning for improving heuristic optimisation
Author: Asta, Shahriar
ISNI:       0000 0004 5919 5949
Awarding Body: University of Nottingham
Current Institution: University of Nottingham
Date of Award: 2015
Availability of Full Text:
Access from EThOS:
Access from Institution:
Heuristics, metaheuristics and hyper-heuristics are search methodologies which have been preferred by many researchers and practitioners for solving computationally hard combinatorial optimisation problems, whenever the exact methods fail to produce high quality solutions in a reasonable amount of time. In this thesis, we introduce an advanced machine learning technique, namely, tensor analysis, into the field of heuristic optimisation. We show how the relevant data should be collected in tensorial form, analysed and used during the search process. Four case studies are presented to illustrate the capability of single and multi-episode tensor analysis processing data with high and low abstraction levels for improving heuristic optimisation. A single episode tensor analysis using data at a high abstraction level is employed to improve an iterated multi-stage hyper-heuristic for cross-domain heuristic search. The empirical results across six different problem domains from a hyper-heuristic benchmark show that significant overall performance improvement is possible. A similar approach embedding a multi-episode tensor analysis is applied to the nurse rostering problem and evaluated on a benchmark of a diverse collection of instances, obtained from different hospitals across the world. The empirical results indicate the success of the tensor-based hyper-heuristic, improving upon the best-known solutions for four particular instances. Genetic algorithm is a nature inspired metaheuristic which uses a population of multiple interacting solutions during the search. Mutation is the key variation operator in a genetic algorithm and adjusts the diversity in a population throughout the evolutionary process. Often, a fixed mutation probability is used to perturb the value at each locus, representing a unique component of a given solution. A single episode tensor analysis using data with a low abstraction level is applied to an online bin packing problem, generating locus dependent mutation probabilities. The tensor approach improves the performance of a standard genetic algorithm on almost all instances, significantly. A multi-episode tensor analysis using data with a low abstraction level is embedded into multi-agent cooperative search approach. The empirical results once again show the success of the proposed approach on a benchmark of flow shop problem instances as compared to the approach which does not make use of tensor analysis. The tensor analysis can handle the data with different levels of abstraction leading to a learning approach which can be used within different types of heuristic optimisation methods based on different underlying design philosophies, indeed improving their overall performance.
Supervisor: Not available Sponsor: Not available
Qualification Name: Thesis (Ph.D.) Qualification Level: Doctoral
EThOS ID:  DOI: Not available
Keywords: QA299 Analysis