Modeling medical doctor rostering using hybrid genetic algorithm-particle swarm optimization

Rostering plays an important role in most manufacturing, production and healthcare systems. Manual staff rostering as opposed to a computerized system, particularly for medical doctors is usually challenging, tedious and tiresome, whereby the tasks involved too much time consumption due to changes i...

Full description

Saved in:
Bibliographic Details
Main Author: Zainudin, Zanariah
Format: Thesis
Published: 2014
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
id my-utm-ep.48534
record_format uketd_dc
spelling my-utm-ep.485342017-08-22T04:40:04Z Modeling medical doctor rostering using hybrid genetic algorithm-particle swarm optimization 2014 Zainudin, Zanariah TP Chemical technology Rostering plays an important role in most manufacturing, production and healthcare systems. Manual staff rostering as opposed to a computerized system, particularly for medical doctors is usually challenging, tedious and tiresome, whereby the tasks involved too much time consumption due to changes in business rules, shortage of healthcare professionals, and overwork. Besides that, soft constraints as bearable ones as well as hard constraints which must be addressed are issues that must be taken into account during the rostering process. Due to these problems, modelling of a medical doctor rostering using Hybrid Genetic Algorithm-Particle Swarm Optimization (Hybrid GA-PSO) is proposed as a means to minimize the total violation constraints to obtain maximum satisfaction among medical doctors as well as satisfying all the hard constraints and as many soft constraints possible. Hybrid GAPSO is represented by a population of working days which are then determined using evolutionary inspired operators, searching and updating process. In addition, observations and interview sessions with the person in-charge were carried out to obtain additional data and identify constraints in relation to medical doctor rostering at Hospital Sultanah Aminah (HSA), Johor Bahru, Johor. In this study, the different levels of importance for the hard and soft constraints based on the requirements to create the duty roster were identified. The performance of medical doctor rostering using Hybrid GA-PSO method was measured in terms of total violation constraints and accuracy, as well as comparisons with standard Genetic Algorithm (GA) and Particle Swarm Optimization (PSO). Results of this study show that Hybrid GA-PSO has the ability to produce feasible duty roster that could save time and distribute the workload fairly to the medical doctors. The Hybrid GA-PSO provides a solution to not only improve the computation of the rostering system, but has also produced an efficient and effective duty roster for medical doctors and staff 2014 Thesis http://eprints.utm.my/id/eprint/48534/ masters Universiti Teknologi Malaysia, Faculty of Computing Faculty of Computing
institution Universiti Teknologi Malaysia
collection UTM Institutional Repository
topic TP Chemical technology
spellingShingle TP Chemical technology
Zainudin, Zanariah
Modeling medical doctor rostering using hybrid genetic algorithm-particle swarm optimization
description Rostering plays an important role in most manufacturing, production and healthcare systems. Manual staff rostering as opposed to a computerized system, particularly for medical doctors is usually challenging, tedious and tiresome, whereby the tasks involved too much time consumption due to changes in business rules, shortage of healthcare professionals, and overwork. Besides that, soft constraints as bearable ones as well as hard constraints which must be addressed are issues that must be taken into account during the rostering process. Due to these problems, modelling of a medical doctor rostering using Hybrid Genetic Algorithm-Particle Swarm Optimization (Hybrid GA-PSO) is proposed as a means to minimize the total violation constraints to obtain maximum satisfaction among medical doctors as well as satisfying all the hard constraints and as many soft constraints possible. Hybrid GAPSO is represented by a population of working days which are then determined using evolutionary inspired operators, searching and updating process. In addition, observations and interview sessions with the person in-charge were carried out to obtain additional data and identify constraints in relation to medical doctor rostering at Hospital Sultanah Aminah (HSA), Johor Bahru, Johor. In this study, the different levels of importance for the hard and soft constraints based on the requirements to create the duty roster were identified. The performance of medical doctor rostering using Hybrid GA-PSO method was measured in terms of total violation constraints and accuracy, as well as comparisons with standard Genetic Algorithm (GA) and Particle Swarm Optimization (PSO). Results of this study show that Hybrid GA-PSO has the ability to produce feasible duty roster that could save time and distribute the workload fairly to the medical doctors. The Hybrid GA-PSO provides a solution to not only improve the computation of the rostering system, but has also produced an efficient and effective duty roster for medical doctors and staff
format Thesis
qualification_level Master's degree
author Zainudin, Zanariah
author_facet Zainudin, Zanariah
author_sort Zainudin, Zanariah
title Modeling medical doctor rostering using hybrid genetic algorithm-particle swarm optimization
title_short Modeling medical doctor rostering using hybrid genetic algorithm-particle swarm optimization
title_full Modeling medical doctor rostering using hybrid genetic algorithm-particle swarm optimization
title_fullStr Modeling medical doctor rostering using hybrid genetic algorithm-particle swarm optimization
title_full_unstemmed Modeling medical doctor rostering using hybrid genetic algorithm-particle swarm optimization
title_sort modeling medical doctor rostering using hybrid genetic algorithm-particle swarm optimization
granting_institution Universiti Teknologi Malaysia, Faculty of Computing
granting_department Faculty of Computing
publishDate 2014
_version_ 1747817413873762304