Comparative Research of Swarm Intelligence Clustering Algorithms for Analyzing Medical Data

• Published in: IEEE access Vol. 7; pp. 137560 - 137569
• Main Authors: Gong, Xueyuan, Liu, Liansheng, Fong, Simon, Xu, Qiwen, Wen, Tingxi, Liu, Zhihua
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2019; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Clustering; Clustering algorithms; Data mining; Mathematical model; Medical data analysis; Medical research; Optimization; Parallel processing; Particle swarm optimization; Search problems; Swarm intelligence; Time complexity
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2018.2881020

As the Internet of medical Things emerge in the field of medicine, the volume of medical data is expanding rapidly and along with its variety. As such, clustering is an important procedure to mine the vast data. Many swarm intelligence clustering algorithms, such as the particle swarm optimization (PSO), firefly, cuckoo, and bat, have been designed, which can be parallelized to the benefit of mass data computation. However, few studies focus on the systematic analysis of the time complexities, the effect of instances (data size), attributes (dimensionality), number of clusters, and agents of these algorithms. In this paper, we performed a comparative research for the PSO, firefly, cuckoo, and bat algorithms based on both synthetic and real medical data sets. Finally, we conclude which algorithms are effective for the medical data mining. In addition, we recommend the more suitable algorithms that have been developed recently for the different medical data to achieve the optimal clustering.