Internet of Things Based Early Detection of Diabetes Using Machine Learning Algorithms: Dpa
Viswanatha Reddy1, Allugunti1, Elango NM2, Kishor Kumar Reddy C3
1Viswanatha Reddy Allugunti, Research Scholar, VIT University, Vellore, Tamil Nadu, India.
2Dr. Elango NM, Professor, VIT University, Vellore,Tamil Nadu, India.
3Dr Kishor Kumar Reddy C, Associate Professor, Stanley College of Engineering & Technology for Women, Hyderabad, Telegana, India
Manuscript received on 02 July 2019 | Revised Manuscript received on 09 July 2019 | Manuscript published on 30 August 2019 | PP: 1443-1447 | Volume-8 Issue-10, August 2019 | Retrieval Number: J10130881019/19©BEIESP | DOI: 10.35940/ijitee.A1013.0881019
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: This paper introduces a new decision tree algorithm Diabetes Prediction Algorithm (DPA), for the early prediction of diabetes based on the datasets. The datasets are collected by using Internet of Things (IOT) Diabetes Sensors, comprises of 15000 records, out of which 11250 records are used for training purpose and 3750 are used for testing purpose. The proposed algorithm DPA yielded an accuracy of 90.02 %, specificity of 92.60 %, and precision of 89.17% and error rate of 9.98%. further, the proposed algorithm is compared with existing approaches. Currently there are numerous algorithms available which are not complete accurate and DPA helps.
Keywords: Accuracy, Decision Trees, Error Rate, Kaggle,
Machine Learning, Specificity, IoT.
Scope of the Article: Machine Learning