Cloud-Centric IoT Based Decision Support System for Gestational Diabetes Mellitus using Optimal Support Vector Machine
J. John Kennedy1, R. Pandi Selvam2, V. Palanisamy3
1J. John Kennedy, Research Scholar, Department of Computer Applications. Alagappa University, Karaikudi, India.
2R. Pandi Selvam, Assistant Professor & Head, PG Department of Computer Science, Ananda College, Devakottai, Tamilnadu, India.
3V. Palanisamy, Professor & Head, Department of Computer Applications. Alagappa University, Karaikudi, India.
Manuscript received on 21 April 2019 | Revised Manuscript received on 26 May 2019 | Manuscript published on 30 May 2019 | PP: 3415-3423 | Volume-8 Issue-1, May 2019 | Retrieval Number: A9165058119/19©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© 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: Recently, the healthcare applications using Internet of Things (IoT) provide diverse functionalities and real time services. Introducing IoT devices in healthcare leads to the generation of massive amount of medical data and is investigated on the cloud rather than depending on available memory and processing capability of handheld devices. In this way, an IoT and cloud based decision support system is developed to diagnose the presence of disease. In this paper, we develop a particle swarm optimization (PSO) based support vector machine (SVM) model for medical data classification. The presented PSO based SVM classification method has the ability to optimize the SVM parameters to enhance the classification accuracy. This paper develops an efficient system model is developed for gestational Type II diabetes mellitus (GDM) diseases and the relevant data is used from UCI Repository as well as from the use of medical sensor from the patients. The validation of the proposed method takes place using the benchmark dataset and a detailed comparative analysis is also made with the existing models. The experimental values ensure that the proposed method performs well and accurately predicts the presence of the disease.
Keywords: IoT; Cloud; Machine Learning; Decision Support System; e-Healthcare
Scope of the Article: IoT