Chicken swarm optimisation based clustering of biomedical documents and health records to improve telemedicine applications

Abstract

The aim of this paper is to develop an efficient ontology enabled chicken swarm optimisation (CSO) based clustering algorithm with dynamic dimension reduction (DDR) to efficiently cluster biomedical documents and health records to facilitate telemedicine applications. A total of 350 documents and health records are collected from PubMed repository for telemedicine applications. First, the documents are pre-processed via semantic annotation and concept mapping while term frequency and inverse gravity moment (TF-IGM) factor is used to improve document representation and the modified n-gram resolves the substitution and deletion malpractices. DDR technique reduces feature space dimension and prunes non-useful text features to increase the clustering accuracy by tackling the high dimensionality problem. Finally, the clusters are formed by CSO clustering. Experimental simulations prove that the CSO-DDR clustering model is significantly efficient than the traditional algorithms and ensures reliable and adaptive telemedicine applications with better clustering of biomedical documents and health records.