Andante: Music therapy device for gait impairments

 


Capstone project for ME170

Kevin Supakkul, Melissa Marable, Bradley Immel, Nicole Salz

Project Goal: Create music from the movement of cerebral palsy patients to encourage gait improvement.

Background: Cerebral palsy (CP) is a neurological condition that affects approximately 764,000 people in the United States. People with spastic CP commonly experience gait disorders of stiff-knee gait and flex-knee gait.

Project Motivation: Current therapies for spastic CP are provided at most 2-3 times per week for an hour. This is a relatively low-dose frequency and thus requires a long period of time to actually generate improvement in gait behavior. Additionally, therapies are sometimes not motivating for CP individuals, which can lead to less desire to engage in beneficial exercises.

Problem Statement: Develop a mechatronic device that generates music from gait movement, specifically focusing on musical implementations that can benefit those with spastic CP.

High Priority Requirements:

  • Generate music as users walk -- let them make music through movement

  • Improve gait for people with spastic cerebral palsy

  • Enjoyable and satisfying musical interaction

  • Device can be used at home for personal daily use

  • Device must output consistent sensor data over the duration of use

Ethical Considerations:

  • User safety - doesn’t negatively impact gait

  • Device cost related to access

  • Engaging musical options for users from a variety of backgrounds and cultures

Solution: We designed a flexible hardware and software system which can be adapted to replace or augment a therapist’s auditory cues as well as provide other feedback. The system includes a footswitch, a knee angle-detection sleeve, and an app that outputs music, which all communicate wirelessly via Bluetooth.

Hardware: Foot device with force sensitive resistors + nRF52832 microcontroller (with BLE) for detecting gait events, knee sleeve with 2x MPU9250 IMUs + nRF52832 (with BLE) for measuring knee angle.

Software: Arduino / C++, Objective-C app, Faust API music output


Music implementations:


Link to written report and demos not yet ready


Comments

Post a Comment

Popular posts from this blog

Puppy sleep/wake classifier for security camera

Image
Motivation:   Asleep I wake up at a consistent time every morning to take my puppy out of her play pen / crate and give her breakfast. However, sometimes after late nights of work I prefer to sleep in a little if possible, and sometimes my puppy is not awake at the early hours of the morning. If I can time my alarm to match when my puppy wakes up, I may be able to get some more sleep. Solution:  Using a security camera and a ML model, I can classify whether my puppy is asleep or awake, then send this information to an iPhone app that wakes me up if necessary. Awake Progress:   So far I have completed the data collection and training of the model. In total, I collected and manually labeled 1137 photos using a script that retrieves photos from the security camera. I then trained a CNN (transfer learning using ResNet-50).  These are the bootstrap 95% confidence intervals of key metrics: Accuracy: 0.951 to 0.991 AUROC:  0.988 to 0.9996 F1 Score: 0.934 to 0.988 ...
Read more