Hybrid Model of Genetic Algorithms and Tabu Search Memory for Nurse Scheduling Systems | IGI Global Scientific Publishing
Welcome to the InfoSci Platform
Hybrid Model of Genetic Algorithms and Tabu Search Memory for Nurse Scheduling Systems

Hybrid Model of Genetic Algorithms and Tabu Search Memory for Nurse Scheduling Systems

Adebayo A. Abayomi-Alli, Frances Omoyemen Uzedu, Sanjay Misra, Olusola O. Abayomi-Alli, Oluwasefunmi T. Arogundade
Copyright: © 2022 |Volume: 13 |Issue: 1 |Pages: 20
ISSN: 1947-959X|EISSN: 1947-9603|EISBN13: 9781799884378|DOI: 10.4018/IJSSMET.297494
Cite Article Cite Article

MLA

Abayomi-Alli, Adebayo A., et al. "Hybrid Model of Genetic Algorithms and Tabu Search Memory for Nurse Scheduling Systems." IJSSMET vol.13, no.1 2022: pp.1-20. https://doi.org/10.4018/IJSSMET.297494

APA

Abayomi-Alli, A. A., Uzedu, F. O., Misra, S., Abayomi-Alli, O. O., & Arogundade, O. T. (2022). Hybrid Model of Genetic Algorithms and Tabu Search Memory for Nurse Scheduling Systems. International Journal of Service Science, Management, Engineering, and Technology (IJSSMET), 13(1), 1-20. https://doi.org/10.4018/IJSSMET.297494

Chicago

Abayomi-Alli, Adebayo A., et al. "Hybrid Model of Genetic Algorithms and Tabu Search Memory for Nurse Scheduling Systems," International Journal of Service Science, Management, Engineering, and Technology (IJSSMET) 13, no.1: 1-20. https://doi.org/10.4018/IJSSMET.297494

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

The main challenge of Nurse Scheduling Problem (NSP)is designing a nurse schedule that satisfies nurses preferences at minimal cost of violating the soft constraints. This makes the NSP an NP-hard problem with no perfect solution yet. In this study, two meta-heuristics procedures: Genetic Algorithm (GA) and Tabu Search (TS) memory was applied for the development of an automatic hospital nurse scheduling system (GATS_NSS). The data collected from the nursing services unit of a Federal Medical Centre (FMC) in Nigeria with 151 nursing staffs was preprocessed and adopted for training the GATS_NSS. The system was implemented in Java for Selection, Evaluation and Genetic Operators (Crossover and Mutation) of GA alongside the memory properties of TS. Nurses’ shift and ward allocation was optimized based on defined constraints of the case study hospital and the results obtained showed that GAT_NSS returned an average accuracy of 94%, 99% allocation rate, 0% duplication, 0.5% clash and an average improvement in the computing time of 94% over the manual approach.