Sensors for correcting human movement
The advancement of healthcare technologies has led to the improvement of life quality thus extending a person’s average lifespan. As such, this would lead to an ageing population. Among the elderly population, falls often lead to severe implications which would result in them receiving rehabilitatio...
Saved in:
Main Author: | |
---|---|
Other Authors: | |
Format: | Final Year Project |
Language: | English |
Published: |
2017
|
Subjects: | |
Online Access: | http://hdl.handle.net/10356/70220 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
Summary: | The advancement of healthcare technologies has led to the improvement of life quality thus extending a person’s average lifespan. As such, this would lead to an ageing population. Among the elderly population, falls often lead to severe implications which would result in them receiving rehabilitation treatments. During rehabilitation, motion tracking devices were used to analyse the patient’s status and progress. However, such devices were expensive to be use for home rehabilitation.
The arrival of smartphones provided a platform for developer to write applications to help the aging population; for instance, a motion tracking application which could log down the progress of the patient. This will provide an alternative for expensive motion tracking devices to be use for home rehabilitation.
In this project, sensor fusion techniques were applied to fuse accelerometer and magnetometer data. As well as an enhanced complementary filter, which provided a feedback loop to aid in correcting gyroscope’s drift. It concluded good accuracy of angle estimates with the complementary filter designed, when using XSENS sensor as benchmark.
In addition, RehabPartner application was implemented to put the designed complementary filter to use. This application aids in tracking motion of users during rehabilitation exercises, keep tracks of user’s progress and inform users when an incorrect range of motion was detected. |
---|