Implementation of fuzzy possibilistic product partition C-means and modified fuzzy possibilistic C-means clustering to pick the low performers using R-tool

Abstract

The different techniques like clustering, classification, association rule and regression are available in data mining to deal with a huge number of datasets that are available in the education field. The main purpose of educational data mining is to extract useful information that will create a good impact on educational institutions. The identification of risk students, improving the graduation rates and placement opportunities will assess the institutional performance. The clustering is one of the famous techniques to deal with noisy and disjoint groups. The clustering technique is used to measure the distance between data objects of a similar group and also it finds the different cluster center in each iteration. The placement creates the opportunity to learn specific skills on their subject or industry and improves their knowledge in various sectors. In this paper, we are going to discuss Fuzzy Possibilistic Product Partition C-Means (FPPPCM) and Modified Fuzzy Possibilistic C-Means Clustering (MFPCM) performance while dealing with the student placement performance details. The improvement of the educational system will depend on reducing the low performing students rate. The main aim of this paper to pick the low performers by using FPPPCM and MFPCM algorithms. This will helps academia to identify the low performers and provide proper training to them in an early stage. And also the efficiency of FPPPCM and MFPCM is going to analyze with different parameters.