Negation of Immaterial and Duplicate Features in High Dimensional Data Using Clustering

Download Now
Provided by: International Journal of Innovative Science Engineering and Technology (IJISET)
Topic: Data Management
Format: PDF
Feature selection means finding a subset that is very useful to produce compatible results as the original set of features. A feature selection algorithm can be concerned from the efficiency and effectiveness of features obtained was the efficiency is calculated from the time required to find the subset and effectiveness is concerned with quality of the subset of features. Based on these criteria, a new clustering based feature selection algorithm is proposed. The algorithm works by two steps. Features are divided into clusters by using clustering methods in the first step; the representative features that is more related to the target classes is selected from each cluster in the second step.
Download Now

Find By Topic