Wearable Fall Detection & Monitoring System
for Patients with Parkinson's

This project explored the design of a wearable fall-detection and monitoring system for elderly rehabilitation patients, including individuals living with Parkinson’s disease and other neurological conditions.

Working in collaboration with clinical staff at the rehabilitation centre, the project aimed to understand how wearable technologies could support safer rehabilitation and improve monitoring of fall events in everyday clinical environments.

Through user-centered research with patients and healthcare professionals, the project examined clinical workflows, patient needs, and challenges faced during rehabilitation. Insights from interviews and observations were translated into design requirements for a wearable system capable of detecting fall events while remaining comfortable and usable for elderly patients.

Functional prototypes were developed combining 3D printed components, motion sensing electronics, and interface programming. The fall detection system was tested and refined through iterative evaluation, achieving approximately 90% detection accuracy while balancing sensitivity and specificity.

The project also served as a bridge between clinical practice and design development by translating patient and clinician insights into actionable improvements in wearable system design.

Functional Prototype for Fall Detection

Product Video

Product Report Flip Book

My Role

Conducted user interviews with elderly rehabilitation patients and clinical staff
Analyzed patient needs, rehabilitation workflows, and usability challenges
Designed and prototyped wearable system concepts
Integrated electronics, sensors, and programmed interfaces for fall detection
Built and tested functional prototypes using 3D printing and embedded systems
Iteratively evaluated detection performance and system usability

Methods

User interviews with patients and clinicians
Clinical workflow observation
Wearable system design
Electronics prototyping and integration
Interface programming
Iterative prototyping and testing

Technology

IMU motion sensors
Arduino / microcontroller
Swift / mobile interface
3D printed enclosure
fall detection algorithm

Outcome

The project resulted in a functional wearable fall detection prototype capable of identifying fall events with approximately 90% accuracy while remaining suitable for elderly users in rehabilitation settings.

The work demonstrated how user-centered design, engineering prototyping, and clinical collaboration can be combined to develop practical wearable healthcare technologies.