Hybrid Elitist-Ant System for Nurse-Rostering Problem

• Main Authors: Ghaith M. Jaradat, Anas Al-Badareen, Masri Ayob, Mutasem Al-Smadi, Ibrahim Al-Marashdeh, Mahmoud Ash-Shuqran, Eyas Al-Odat
• Format: Article
• Language: English
• Published: Elsevier 2019-07-01
• Series: Journal of King Saud University: Computer and Information Sciences
• Online Access: http://www.sciencedirect.com/science/article/pii/S1319157818300363

The diversity and quality of high-quality and diverse-solution external memory of the hybrid Elitist-Ant System is examined in this study. The Elitist-Ant System incorporates an external memory for preserving search diversity while exploiting the solution space. Using this procedure, the effectiveness and efficiency of the search may be guaranteed which could consequently improve the performance of the algorithm and it could be well generalized across diverse problems of combinatorial optimization. The generality of this algorithm through its consistency and efficiency is tested using a Nurse-Rostering Problem. The outcomes demonstrate the competitiveness of the hybrid Elitist-Ant System’s performance within numerous datasets as opposed to those by other systems. The effectiveness of the external memory usage in search diversification is evidenced in this work. Subsequently, such usage improves the performance of the hybrid Elitist-Ant System over diverse datasets and problems. Keywords: Metaheuristics, Elitist-Ant System, External memory, Diversification, Intensification, Nurse Rostering Problem