A decision support system based on an artificial multiple intelligence system for vegetable crop land allocation problem

Pitakaso, Rapeepan; Sethanan, Kanchana; Tan, Kim Hua; Kumar, Ajay

Abstract

This research focuses on the development of a novel artificial multiple intelligence system (AMIS), which is more flexible and effective than existing techniques for determining vegetable crop land allocation. Eight intelligence boxes (IBs) have been newly designed to serve as AMIS improvement tools presented in this study. Furthermore, a novel formula has been developed to efficiently select the appropriate IB for various types of problems. The developed method will be incorporated into a vegetable land allocation decision support system. The decision-making of the planning about land allocation for crops, including what to grow and what is in demand during specific periods, was performed while considering important factors such as production yield, crop planting and harvesting time, vegetable price fluctuations, and plant incompatibility, leading to a sustainable production system and achieving the highest prices and annual income. Moreover, the developed vegetable crop land allocation models yield the similarity of the average profit per area, so farmers could plan their crops accordingly. To solve the problem, a mathematical model was proposed to solve a small-sized problem, while a novel metaheuristic called the Artificial Multiple Intelligence System (AMIS) was applied to solve larger-sized problems. The computational results revealed that AMIS outperformed all other traditional methods used for comparison in this research. The solution of AMIS was higher in quality than traditional methods such as Differential Evolution (DE), Multi-Agent Simulated Quenching (MASQ), and Genetic Algorithm (GA) by 21.78%, 16.38%, and 22.79%, respectively.

Citation

Pitakaso, R., Sethanan, K., Tan, K. H., & Kumar, A. (2023). A decision support system based on an artificial multiple intelligence system for vegetable crop land allocation problem. Annals of Operations Research, https://doi.org/10.1007/s10479-023-05398-z

• Journal Article Type: Article
• Acceptance Date: May 11, 2023
• Online Publication Date: Jun 5, 2023
• Publication Date: Jun 5, 2023
• Deposit Date: Aug 9, 2023
• Publicly Available Date: Jun 6, 2024
• Print ISSN: 0254-5330
• Electronic ISSN: 1572-9338
• Publisher: Springer Verlag
• Peer Reviewed: Peer Reviewed
• DOI: https://doi.org/10.1007/s10479-023-05398-z
• Public URL: https://nottingham-repository.worktribe.com/output/24141366
• Publisher URL: https://link.springer.com/article/10.1007/s10479-023-05398-z