The aim of this project is to develop a system which can perform early prediction of diabetes for a patient with a higher accuracy by Decision tree algorithm. Machine learning is an emerging scientific field in data science dealing with the ways in which machines learn from experience. Machine learning (ML) is the study of algorithms and mathematical models that computer systems use to progressively improve their performance on a specific task. Machine learning algorithms build a mathematical model of sample data, known as "training data", in order to make predictions or decisions without being explicitly programmed to perform the task.   Diabetes is a disease caused due to the increase level of blood glucose. This high blood glucose produces the symptoms of frequent urination, increased thirst, and increased hunger. Diabetes is a one of the leading cause of blindness, kidney failure, amputations, heart failure and stroke. When we eat, our body turns food into sugars, or glucose. At that point, our pancreas is supposed to release insulin. Insulin serves as a key to open our cells, to allow the glucose to enter and allow us to use the glucose for energy. But with diabetes, this system does not work.   The Raspberry Pi 3 Model A+ is the latest product in the Raspberry Pi 3 range. Like the Raspberry Pi 3 Model B+, it boasts a 64-bit quad core processor running at 1.4 GHz, dual-band 2.4 GHz and 5 GHz wireless LAN, and Bluetooth 4.2/BLE.   This project consists of glucosensor and temperature sensor which sense the blood glucose levels and temperature of the body respectively. These sensors when interfaced with Arduino which in turn gives the output to a Raspberry Pi which acts as the main controlling part of this project. Using selection switches, the user can select either the automatic mode or the manual mode. Through 4X4 keypad, the user can enter dataset values which are used for decision tree J48 algorithm. According to given values and the sensors data given by the Arduino, the Raspberry Pi predicts the chances of diabetes of a person and displays it on LCD.     The device which is able to perform the task is a Raspberry Pi processor. To perform this task, Raspberry Pi processor is programmed using embedded ‘Linux’. Using machine learning and Decision Tree J48 Algorithm, predictions are given to the controlling system.

   

The objectives of the project are:

1. Usage of Machine Learning.
2. Usage of Decision Tree J48 Algorithm
3. Sense the blood glucose levels and body temperature of the patient.
4. Data set entry using 4X4 keypad
5. Selection switch for selecting automatic mode and manual mode.

  The major building blocks of the project are:  

1. Power supply.
2. Raspberry Pi processor.
3. Glucosensor
4. Temperature Sensor
5. Arduino
6. 4X4 Keypad
7. Selection switch
8. LCD

      Software’s used:  

1. Linux OS OPERATING SYSTEM.
2. Python Language.
3. Express SCH for Circuit design.
4. Decision Tree algorithm.

   

Machine learning method:

   

Block diagram:

 

video: