Skip to content
HVS-3106. Human Activity Recognition System using Raspberry pi with Blynk App and Thingsboard.

HVS-3106. Human Activity Recognition System using Raspberry pi with Blynk App and Thingsboard.

₹18,000.00

In this project, a human health monitoring system based on raspberry pi3processor and Things Board web server is implemented to monitor various physiological parameters.

Categories ,  Tags , , , , 
A number of patients die every year due to delay in timely diagnosis of diseases and diagnosis of patient’s health condition while shifting the patient to a hospital in case of any emergency. Especially the elderly and ill patients need continuous monitoring of physiological parameters. Such patients cannot visit the hospital on a daily basis. A web based wearable device can be used to avoid such difficulties. In this project, a human health monitoring system based on raspberry pi3processor and Things Board web server is implemented to monitor various physiological parameters including heartbeat, oxygen saturation (SpO2), blood pressure, and electrocardiogram (ECG) and temperature. The health status of the patient obtained from various sensors is uploaded on to the ThingsBoard server on regular basis, which can be observed by the doctor or caretaker. With this system, doctors can monitor the patient’s health status remotely by accessing the web server. In addition To make a system more accuracy using deep learning algorithm to analysis the sensor data. And also, this system sends the blynk notifications to the user in abnormal conditions.          

The main objectives of the project are:  
  1. To develop a web-based patient health monitoring system using Raspberry Pi 3.
  2. To monitor important physiological parameters such as Hb, SpOâ‚‚, ECG, temperature, and blood pressure.
  3. To use IoT technology to upload and monitor patient health data through the ThingSpeak web platform.
  4. To provide alert notifications through the Blynk application when abnormal health conditions are detected.
  5. To use deep learning techniques to analyze the collected patient health data and identify abnormal conditions.
       

Major components:  
  • Power supply.
  • Raspberry pi3.
  • MAX30100.
  • LM35 Temperature Sensor.
  • AD8232 ECG sensor.
  • Digital BP sensor.
       

Software’s used:  
  • Python language.
  • Linux OS.
  • Blynk app.
  • Deep learning algorithm.
  • Express SCH for Circuit design.
         

Block diagram of the project:          

video:

Related Products