Search Engine Based on a Fast Clustering Algorithm for High Dimensional Data

Provided by: Creative Commons
Topic: Data Management
Format: PDF
The authors come across various search engines, but giving different keywords to the search engine and getting the best results is still a tedious process because they get redundant and irrelevant data. This is mainly due to the selected features that are used to find the results. The paper aims at proposing a search engine that uses the fast clustering algorithm for removing this irrelevant and redundant data. Feature selection is applied to reduce the number of features in many applications where data has hundreds or thousands of features.

Find By Topic