Knowledge Discovery in Big Data Soft Set Environemnt Using Bijective Soft Set: Rectify Misclassified Data

Jyoti Arora, Kamaljit Kaur


In this information age, most of the studies have focused on analyzing the complexities of whole datasets. Data mining process works for finding patterns in whole datasets using computerized techniques and machine learning. Most of the researchers have worked on it and followed data elimination approach. This leads to loss of information and raise misclassification. Mining of data directly does not have feature to provide useful information about individual attribute. In this paper, we have considered dataset of Breast Cancer from UCI repository. The proposed method utilized bijective soft set theory to extract knowledge based on parameters of datasets. Here, problems occurs during classification has been considered. As, we need to know about which elements are misclassified and how they can help to improve the accuracy and quality of dataset. So, we have proposed method for rectification of misclassification to increase the accuracy. The aim of thi papaer is to better understand the true positive and false negative terms by analyzing and rectifying the misclassified data.


Big data; Data mining; Boundary Values; Misclassification;Bijective Soft Sets

Full Text:




  • There are currently no refbacks.

Copyright (c) 2017 International Journal of Advanced Research in Computer Science