Related Experiment Video
Updated: Mar 6, 2026
06:49
Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment
Published on: December 11, 2015
9.4K
Longitudinal wearable tremor measurement system with activity recognition algorithms for upper limb tremor
Summary
This study introduces a wearable system for long-term tremor and activity tracking. The system accurately identifies tremors and daily activities, paving the way for better movement disorder assessment.
Area of Science:
- Biomedical Engineering
- Neurology
- Wearable Technology
Background:
- Clinical tremor assessments are limited to single time points, neglecting behavioral context.
- Current methods struggle to quantitatively track long-term tremor and treatment effects in daily life.
Purpose of the Study:
- To develop and evaluate a wearable system for continuous upper limb tremor and activity monitoring.
- To characterize tremor patterns and treatment effects in real-world settings.
Main Methods:
- A wrist-worn device with a 3-axis accelerometer and gyroscope was used.
- Tremor and activity recognition algorithms were developed and tested.
- Participants performed scenario tasks simulating daily life activities.
Main Results:
- The system achieved 89.71% accuracy in classifying tremor.
- Activity recognition accuracy reached 74.48% during scenario tasks.
- Pilot data demonstrated the feasibility of long-term monitoring.
Conclusions:
- The wearable system shows promise for objective, long-term assessment of tremor and daily behavior.
- This technology can enhance the understanding of movement disorders and treatment efficacy.
- Future expansion to longer monitoring periods is planned.
