Efficient Diagnostic System For Smart Diabetes
V. Prakash1, Bhavani R2, Anupriya A3
1V. Prakash, Assistant Professor, M.ca, Sastra Deemed To Be University, Thanjavur, (Tamil Nadu), India.
2Bhavani R, Assistant Professor, CSE, Sastra Deemed To Be University, Kumbakonam, (Tamil Nadu), India.
3Anupriya A, M.SC CS, Sastra Deemed To Be University, Kumbakonam, (Tamil Nadu), India.
Manuscript received on February 05, 2019. | Revised Manuscript received on February 14, 2019. | Manuscript published on August 30, 2019. | PP: 3789-3792 | Volume-8 Issue-6, August 2019. | Retrieval Number: F9392088619/19©BEIESP | DOI: 10.35940/ijeat.F9392.088619
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: 5G networks, analytics of medical data and the internet of things are recent advances in big data technologies. Combining these advances with wearable computing and artificial intelligence, innovative diabetics monitoring system is implemented. In the existing system, it classifies the Diabetes 1.0 and Diabetes 2.0 methods, which show the intelligence and networking deficiencies. Thus, with personalized treatment, our goal is to design a sustainable, cost-effective, and smart diabetes diagnosis solution. Uses the machine learning algorithms in the proposed 5G smart diabetes- Naive Bayes, Logistic regression and artificial neural networks (ANN) are for the results.
Keywords: Preprocessing, K means clustering, Machine learning algorithm.