Akhigbemidu, Ozemoya Rex2025-11-042025-11-042024-08Akhigbemidu, O. R. (2024). Development of hybrid clustering algorithm for efficient medical resources allocation (Unpublished Master's Thesis), Federal University of Technology, Owerrihttps://repository.futo.edu.ng/handle/20.500.14562/2253Master’s thesis on "development of hybrid clustering algorithm". It contains diagrams, graphs, tables and picturesEfficient medical resource allocation is a critical challenge in healthcare systems, particularly with increasing demand and limited resources for managing in-patient and out-patient treatment datasets. This project is motivated by the need to address this challenge, as clustering algorithms offer a promising approach for grouping healthcare data, enabling more effective distribution of medical resources. This project aimed to develop a hybrid clustering algorithm that combines the strengths of density-based and partitioning methods to optimize medical resource allocation. The project used a combination of K-representative and K-means clustering algorithms. Adopting the Object-Oriented Analysis and Design (OOAD) methodology, the proposed algorithm analyzes medical datasets to produce more effective clusters, revealing insights that enhance resource distribution. The hybrid algorithm, implemented using the JAVA object-oriented programming tool, generated better-defined clusters of in-patients and out-patients, providing actionable knowledge and intelligence for optimizing medical resource allocation. The results demonstrate the algorithm's potential to improve decision-making in healthcare systems by enhancing the efficiency of resource allocation. The findings further suggest that this hybrid algorithm can serve as a robust tool for healthcare providers, contributing to more efficient resource management and better patient outcomes.enAttribution-NonCommercial-ShareAlike 4.0 InternationalHybridclusteringalgorithmmedical resourcesallocation.department of computer scienceMaster’s Thesis