Volume 18, No. 6, 2021

Normalized Target Feature Projective Regression Based Bootstrap Aggregative Document Clustering In Cloud

Mrs B. BalaVinothini , Dr. N.Gnanambigai , Dr. P. Dinadayalan


Text document clustering is the process of separating particular documentsí sets into varied groups based on certain similarity criteria in different areas of text mining for attaining better precision or recall in the retrieval systems. Due to the large volume of data with high dimensionality in cloud storage, relevant document retrieval is the challenging one. Therefore, document clustering is used to retrieve more relevant collection of documents to the userís query. A novel Normalized Target Feature Projective Regressionbased Bootstrap Aggregative Document Clustering (NTFPR-BADC) technique is introduced for retrieving the more relevant documents with higher accuracy and lesser computational complexity. The proposed NTFPR-BADC technique comprises three processes, initially in preprocessing words are removed, then in feature extraction process target projective pursuit regression is utilized, and in document clustering bootstrap aggregative ensemble technique is applied to provide the final clustering results with higher accuracy. These clustered document is uploaded to the cloud storage and relevant document retrieved based on the user query. The comprehensive experimental assessment is carried out using different factors such as precision, recall, and computational complexity with respect to the number of documents collected from the dataset. By these results the proposed NTFPRBADC technique achieving higher precision, recall, and lesser computational complexity than the existing methods.

Pages: 4478-4499

Keywords: Cloud, preprocessing, target projective pursuit regression feature extraction, bagging ensemble clustering, document retrieval.

Full Text