Query Indexing and Cluster-based Indexing Model for the Document Retrieval

: In the research community field, query optimization plays an important role to retrieve the important and the appropriate documents on the basis of query indexing. In the documents, using the query retrieval process the information is retrieved on the basis of the distance measured. Although several methods are present in the query processing scheme as well as indexing, extracting the matched as well as appropriate documents still outcomes in numerous confronts in the research community. Hence, to retrieve the appropriate documents competently an effective cluster-based inverted indexing model is adopted. By exploiting stop word removal and stemming approaches, unnecessary and redundant words are removed. By cluster-based inverted indexing approach, document indexing is carried out that is the integration of Possibilistic fuzzy c-means (PFCM) clustering approach to index the documents. For user queries, such as multigram queries or semantic queries, on basis of Bhattacharyya distance to generate an enhanced query outcome, query matching is processed. By exploiting the Pearson correlation coefficient, the query optimization is carried out and the appropriate documents are retrieved efficiently. The achievement of a developed cluster-based indexing approach is carried out in this paper. The developed cluster-based indexing approach performance is calculated by exploiting measures, namely precision, recall, as well as F-measure. exploiting the Bhattacharyya distance. On the basis of the least distance measure or Bhattacharya distance, the enhanced query matching outcomes were obtained. The Pearson correlation coefficient was used by the query optimization on the basis of the interactive query optimization and retrieves appropriate documents competently. The developed cluster-based inverted indexing approach obtains enhanced performance with the measures, such as recall, precision, as well as F-measure values.