A novel clustering approach using hadoop distributed environment

Abstract

Nowadays, information retrieval plays a vital role by allowing users to retrieve documents of their interest based on relevance score. Such systems can be implemented either in distributed systems or parallel systems to achieve high throughput. If such kind of framework is deployed in a cloud, grouping of relevant documents is essential to retrieve documents of interest. Hence, an efficient and scalable clustering is required to process huge volume of documents. To handle huge documents and to provide scalability while processing Apache Hadoop is efficient with its powerful feature map reduce. Hence, in this paper, a novel approach is proposed that is capable of clustering bulk data with high throughput. This paper also demonstrates the need of parallel caching approach for obtaining effective results.