OPTIMASI K-MEANS CLUSTERING UNTUK IDENTIFIKASI DAERAH ENDEMIK PENYAKIT MENULAR DENGAN ALGORITMA PARTICLE SWARM OPTIMIZATION DI KOTA SEMARANG

Ilkom Jurnal Ilmiah

Heru Agus Santoso¹  Catur Supriyanto¹  Suhardi Rustam² 

[1] Universitas Dian Nuswantoro;Universitas Ichsan Gorontalo;

关键词: endemic infectious disease;    data mining;    clustering;    k-means;    particle swarm optimization;   

DOI  :  10.33096/ilkom.v10i3.342.251-259

来源: DOAJ

【 摘 要 】

Tropical regions is a region endemic to various infectious diseases. At the same time an area of high potential for the presence of infectious diseases. Infectious diseases still a major public health problem in Indonesia. Identification of endemic areas of infectious diseases is an important issue in the field of health, the average level of patients with physical disabilities and death are sourced from infectious diseases. Data Mining in its development into one of the main trends in the processing of the data. Data Mining could effectively identify the endemic regions of hubunngan between variables. K-means algorithm klustering used to classify the endemic areas so that the identification of endemic infectious diseases can be achieved with the level of validation that the maximum in the clustering. The use of optimization to identify the endemic areas of infectious diseases combines k-means clustering algorithm with optimization particle swarm optimization ( PSO ). the results of the experiment are endemic to the k-means algorithm with iteration =10, the K-Fold =2 has Index davies bauldin = 0.169 and k-means algorithm with PSO, iteration = 10, the K-Fold = 5, index davies bouldin = 0.113. k-fold = 5 has better performance.

【 授权许可】

Unknown