2016 International Conference on Micro-Electronics and...

Info icon This preview shows pages 1–2. Sign up to view the full content.

View Full Document Right Arrow Icon
Detection and Prediction of Diabetes Mellitus Using Back-Propagation Neural Network Miss. Sneha Joshi Department of Electronics and Telecommunication MKSSS’s Cummins College of Engineering Pune, India. [email protected] Abstract - Diabetes mellitus is one of the chronic disease as recent estimation in 2015 shows 415 million people suffering from diabetes worldwide and estimated to have deaths of 1.5 to 5 million each year. It is very important to forecast tool which can be used to determine whether someone has diabetes or not. There are some methods which produce accurate prediction and Artificial neural network using Back propagation neural network is one of them. This neural network having an input layer with 8 parameters, one hidden layer with 10 neurons and one output layer is implemented to produce good results. The GUI is developed to make tool user friendly so that patients can get accurate test results even from assistants in the absence of a doctor. This project will help even doctors get records of the patient within seconds so t h a t it will save time for further treatment of patients. This paper summarizes the implementation and development of the software tool b u i l t in MATLAB which will predict whether someone is diabetic or not. The performance of the BPNN used for predicting diabetes is 81 percent, which shows improvement in previous work. This is a better method than finger stick which is very painful if carried out more n u m b e r of times. Keywords –Back propagation neural network (BPNN); comma separated values (.csv); Diabetes mellitus; Graphic user interface (GUI). I. INTRODUCTION Diabetes Mellitus is a group of metabolic disease in which there is high blood sugar level over a long period. Diabetes Mellitus occurs in two types 1) juvenile diabetes in which pancreas fails to produce enough insulin and other is adult -onset diabetes failure of insulin to respond properly. If this disease left untreated, may cause acute complication like diabetic ketoacidosis, nonketotic hyperosmolar, cardiovascular disease, stroke etc. More than 80 percent of people die due to disease caused by diabetes. Therefore, it is required to diagnose as early as possible. Prof. Megha Borse Department of Electronics and Telecommunication MKSSS’s Cummins College of Engineering Pune, India. [email protected] There are many methods used to detect diabetes like Finger stick with the help of device and lab test, but these methods are more painful when carried number of times and not convenient. Hence, software tool based on artificial neural network is introduced which is 81 percent accurate. This network consists of three layers o ut o f which first layer known as input layer which is having 8 input parameters, similarly middle layer is a hidden layer contains 10 neurons a n d o u t e r l a y e r is the output layer with one neuron. The GUI is developed to load the input .csv file contain a reading of different parameters and it is trained with the help of BPNN and output is displayed on screen.
Image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
Image of page 2
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}

What students are saying

  • Left Quote Icon

    As a current student on this bumpy collegiate pathway, I stumbled upon Course Hero, where I can find study resources for nearly all my courses, get online help from tutors 24/7, and even share my old projects, papers, and lecture notes with other students.

    Student Picture

    Kiran Temple University Fox School of Business ‘17, Course Hero Intern

  • Left Quote Icon

    I cannot even describe how much Course Hero helped me this summer. It’s truly become something I can always rely on and help me. In the end, I was not only able to survive summer classes, but I was able to thrive thanks to Course Hero.

    Student Picture

    Dana University of Pennsylvania ‘17, Course Hero Intern

  • Left Quote Icon

    The ability to access any university’s resources through Course Hero proved invaluable in my case. I was behind on Tulane coursework and actually used UCLA’s materials to help me move forward and get everything together on time.

    Student Picture

    Jill Tulane University ‘16, Course Hero Intern