OntoFuzz: An Information Retrieval Model in a Multi-Tenant Cloud Environment using Neuro-Fuzzy and Ontological-based Approach

NEURO-FUZZY AND ONTOLOGICAL-BASED INFORMATION RETRIEVAL MODEL

Abstract

There is a tremendous amount of data present on the web and accessing useful/relevant information from a cluster of random documents is a tedious and time-consuming task. Traditional information retrieval techniques and information management systems are not that intelligent to extract relevant information from pre-defined datasets or documents. This necessitates the researchers to create and enhance a sophisticated information retrieval system. Also, the similarity between information is equipped with uncertainties due to its computing measures. Keeping these issues in mind, a neuro-fuzzy and ontological-based model in a multi-tenant cloud environment is proposed in this research study. The model comprises modules like query expansion, the weighting of terms and queries, and hashing function to ease the retrieval process followed by validation of the dataset using a neuro-fuzzy network to retrieve relevant information from the cloud service provider. The simulation results prove the validation of the proposed model in terms of higher accuracy and better retrieval performance as compared to traditional models (support vector machines and deep neural networks) as well as existing recent works.