Rehabilitation Posture Correction using Neural Network

The rehabilitation treatment is important because it helps a patient to restore physical sensory and mental capabilities. The patients whose symptoms are moderately relieved or outpatient, usually rehabilitate alone at their home. And as we know, the improper exercise or posture can slow the recover

Project Title

Rehabilitation Posture Correction using Neural Network

Project Area of Specialization

Artificial Intelligence

Project Summary

The rehabilitation treatment is important because it helps a patient to restore physical sensory and mental capabilities. The patients whose symptoms are moderately relieved or outpatient, usually rehabilitate alone at their home. And as we know, the improper exercise or posture can slow the recovery of the patient or even worsen the patient’s health status. So the best way is to receive home visiting treatment from professional therapist until cured. However, such way is a burden on the patient in terms of cost and travelling time. Our project is software based device that corrects the improper postures of the patient when having rehabilitating exercise alone. By using Microsoft Kinect we will recognize the posture of the patient by extracting their skeleton comprising on 20 main joint points and will use the learning algorithm to implement the model for posture correction of the patient. We will adopt neural network as a learning tool to analyze the extracted human skeleton, in order to determine whether the posture is correct or not. For the model to differentiate we will train our neural model for good performance. For this, we will need as much data as possible and the quality of the data is also important. The data for training our model will be correct postures and incorrect postures of exercise. We will collect the data of some exercising postures from a rehabilitation therapist or professional trainer. So, This way our model will be able to monitor the patient while rehabilitating alone and detect if the posture is correct or incorrect.

Project Objectives

To design a model that detects the improper postures of the patient when having rehabilitating exercise alone.

Project Implementation Method

• Calibrate Kinect Sensor by standard Application Programming Interface (API) of the Kinect Software Development Kit (SDK) provided by Microsoft.
• Interface kinect sensor with LabVIEW software.
• Develop algorithm to perform skeleton tracking.
• Extraction of joint coordinates and the angles of each joints.
• Perform data preprocessing step.
• Collect data for training of model.
• Develop Neural Network algorithm.
• Whole program transfer on NI myRIO. 

Benefits of the Project

This device can help those patients who want to rehabilitate alone as there will be no need of physiotherapist during the exercise as our model will itself monitor the patient and detect if the posture is incorrect. Which will save their transport time, cost and health.

Technical Details of Final Deliverable

The final deliverable project would be consisting of a sensor in front of which human has to perform the exercises to get the posture details and also there is a software setup that will detect the correctness or incorrectness of the posture while exercising.

Final Deliverable of the Project

HW/SW integrated system

Type of Industry

Medical , Health

Technologies

Artificial Intelligence(AI), Big Data

Sustainable Development Goals

Good Health and Well-Being for People

Required Resources

If you need this project, please contact me on contact@adikhanofficial.com