Main Article Content

Abstract

In this analysis an ontology-oriented architecture where core ontology has been used as knowledge base (KB) and allows data integration of different heterogeneous sources. In existing model used to Natural Language Processing and Artificial Intelligence methods to process and mine data in the health sector to uncover knowledge hidden in diverse data sources. The approach has been applied in the field of personalized medicine (study, diagnosis, and treatment of diseases customized for each patient). AI methods have been used with the objective to mine data in the healthcare sector to uncover knowledge hidden in heterogeneous data sources. A set of learned rules (using Data Mining techniques on structured data, DM rules) and their improvements (applying NLP techniques on data from the Web) are obtained. In additionally proposed system, to apply three phase Ontology, first stop word removal, stemming and semantic (Synonym word) replacement is used for preprocessing. Next phase Naïve Bayes classification is used. Next phase Rules Extraction is processed and final phase Explicit Semantic analysis is made. In this method automatically construct and incorporate document and word constraints to support unsupervised constrained clustering. The result of the evaluation demonstrates the superiority of our approaches against a number of existing approaches.

Article Details

How to Cite
S.Edison, & K.E. Eswari. (2019). Semantic based sentence ordering with ontology-mining in heterogeneous data using explicit semantic analysis . International Journal of Intellectual Advancements and Research in Engineering Computations, 7(1), 693–701. Retrieved from https://ijiarec.com/ijiarec/article/view/996