Acceleration and Clustering of Liver Disorder Using K-Means Clustering Method with Mahout’s Library

Tariq bin Samer (Universitas Narotama)
Cahyo Darujati (Universitas Narotama)

Journal of Systems Engineering and Information Technology
Vol 2 No 2 (2023): September 2023

Evaluation of liver disorders was performed to observed and clustered in Big Data environment applications. However, since liver disorder is a common illness, global awareness of such cases can be life threatening, therefore the urge to avoid and study must be essential. The idea of parallel computing is established on the basis of the K-means method. The MapReduce framework is used to complete multi-node data processing, and a solution to the MapReduce K-Means method is given. The ultimate goal is to establish clusters that allow each entity to be examined and assigned to a certain cluster. These algorithms are designed to accelerate computations, reduce the volume of enormous data that must be computed, and improve the efficiency of arithmetic operations. The combination of theoretical analysis and experimental evaluation is very significant.