@article {10.3844/jcssp.2012.545.550, article_type = {journal}, title = {Similarity Based Clustering with Indexing for Semi-Structured Document}, author = {Palanisamy, S. and Baskaran, K.}, volume = {8}, number = {4}, year = {2012}, month = {Feb}, pages = {545-550}, doi = {10.3844/jcssp.2012.545.550}, url = {https://thescipub.com/abstract/jcssp.2012.545.550}, abstract = {Problem statement: To improve the performance of data retrieval in a homogeneous large XML document. Approach: Clustering of XML elements based on the content with indexing. The element which is used for clustering has been identified from the document and/or XML schema. This element is used as a parameter for clustering. The suitable index is created after clustering. Results: The clustering combined with indexing strategy support the efficient retrieval of XML element from the document. Conclusion: The proposed method is used to improve the efficiency of XML data manipulation and comparatively give the better performance rather than clustering or indexing alone.}, journal = {Journal of Computer Science}, publisher = {Science Publications} }