Fuzzy C-means clustering on rainfall flow optimization technique for medical data

Antony Jaya Mabel Rani, C. Srivenkateswaran, M. Rajasekar, M. Arun


Due to various killing diseases in the world, medical data clustering is a very challenging and critical task to handle and to take the proper decision from multidimensional complex data in an effective manner. The most familiar and suitable speedy clustering algorithm is K-means than other traditional clustering approaches. But K-means is extra sensitive for initialization of clustering centroid and it can easily surround. Thus, there is a necessity for faster clustering with an effective optimum clustering centroid. Based on that, this research paper projected an optimization-based clustering by hybrid fuzzy C-means (FCM) clustering on rainfall flow optimization technique (RFFO), which is the normal flow and behavior of rainfall flow from one position to another position. FCM clustering algorithm is used to cluster the given medical data and RFFO is used to produce optimum clustering centroid. Finally, the clustering performance is also measured for the proposed FCM clustering on RFFO technique with the help of accuracy, random coefficient, and Jaccard coefficient for medical data set and find the risk factor of a heart attack.


Accuracy; Clustering; Flood optimization; Fuzzy C-means; Rainfall flow;

DOI: http://doi.org/10.11591/ijai.v12.i1.pp%25p


  • There are currently no refbacks.

View IJAI Stats

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.