The Internet Of Things On Neural Networks Provides Intelligent Healthcare Management For Diabetic Patients

Document Type : Primary Research paper


1 Assistant Professor, Department of Information Science and Engineering, BMS Institute of Technology and Management, Avallahalli, Bangalore, Karnataka-560064

2 Assistant Professor, Department of Computer Science and Engineering, Vignan's Foundation for Science ,Technology & Research, Vadlamudi,Guntur,Andhrapradesh-522213.

3 Associate Professor, Department of Computer Science and Engineering, Nehru College of Engineering and Research Centre, Pampady, Kerala- 680588.

4 Associate Professor, Department of Computer Science and Engineering, Lovely Professional University, Jalandhar-Delhi, G.T. Road, Phagwara,Punjab (India) -144411.

5 Assistant Professor or Mentor of Change in Atal Innovation Mission and PG Student Masters of Computer Engineering,Department of Computer Engineering,Thakur College of Engineering and Technology,Thakur Village, Kandivali East, Mumbai, Maharashtra 400101.

6 Assistant Professor, Department of Information Technology, Shri Ramdeobaba College of Engineering and Management, Gittikhadan, Katol Road, Nagpur, Maharashtra, India-440014.


A newly developed health system for a diabetic is described in this study, which tracks their health based on blood sugar levels, heart rate, food consumption, sleep duration, and activity. To explain, this technology is continually receiving variables via sensors and processes them using a neural network to analyze the data, yielding four things like health threats: minimal, moderate, extreme, and severe. The spectrum of genetic risk varies depending on the customer's kind and past health histories. Furthermore, if a patient's health state is at high or extreme danger, an instantaneous phone call/SMS notice is made to the patient's family, including the patient's position. In addition, it alerts patients to the nearest hospital if they are in danger. This technique has been successfully tested on 25 people with diabetes, with reliability of 84.41 percent in determining the appropriate level of risk, which is a highly adequate standard of determining risk factor status.