Real-Time Remote Healthcare and Telemedicine Application Model using Ontology Enabled Clustering of Biomedical & Clinical Documents
R.Sandhiya1, M.Sundarambal2
1R.Sandhiya*, Assistant Professor, Department of Information Technology, Coimbatore Institute of Technology, Coimbatore, Tamil Nadu, India.
2Dr.M.Sundarambal, Professor, Department of Electrical and Electronics Engineering, Coimbatore Institute of Technology, Coimbatore, Tamil Nadu, India.
Manuscript received on December 17, 2019. | Revised Manuscript received on December 28, 2019. | Manuscript published on January 10, 2020. | PP: 73-79 | Volume-9 Issue-3, January 2020. | Retrieval Number: C8066019320/2020©BEIESP | DOI: 10.35940/ijitee.C8066.019320
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Remote health monitoring has become a hot topic research due to its multi-dimensional benefits to the society. This paper is aimed at developing a novel remote health monitoring model through wireless sensor networks to ensure efficient telemedicine process. The proposed model, Real-time Remote Healthcare and Telemedicine (RRHT) utilizes the concept of model based design to provide low cost and time saving efficiency. First the low power consuming sensor nodes are placed at specified body points with facility to monitor and reduce the power consumption at each stage of the designed model. These nodes collect the patient data and transmit them in wireless medium through the gateway where the data are combined to form documents/notes. Autonomous optimized routing algorithm is employed at this stage for transmission through efficient wireless paths to the processor connected at the hospitals or health centers. At the processor, the transmitted patient data documents are clustered using ontology enabled clustering models using chicken swarm optimization (CSO) and genetic chicken swarm optimization (GCSO). The clustered results are comparatively analyzed with the previous patient database and to determine the change in health readings. Based on these findings, the suitable medication details along with advice on hospital visits are suggested by the decision module and are sent to the physicians or medical experts for approval and further diagnosis. The performance analysis shows that the proposed RRHT system with GCSO clustering is highly reliable and accurate with better speed and lower cost. These results also prove that the RRHT significantly improved the healthcare application through the utilization of better strategies in document clustering of patient data.
Keywords: Telemedicine, Remote Health Care, Wearable Sensors, Autonomous Optimized Routing, Ontology Enabled Clustering, Decision Support Systems.
Scope of the Article: Clustering