Berends, Mart (2024) Enhancing In-home Care with mmWave Radar: A Non-intrusive Approach to Human Activity Recognition and Monitoring. Master's Thesis / Essay, Computational Cognitive Science.
|
Text
MasterThesisMartBerends.pdf Download (1MB) | Preview |
|
![[img]](https://fse.studenttheses.ub.rug.nl/style/images/fileicons/text.png) |
Text
Toestemming.pdf Restricted to Registered users only Download (178kB) |
Abstract
This study investigates the potential of radar-based technology for enhancing human activity recogni- tion (HAR) to improve in-home monitoring of individuals with an increased risk of health problems, particularly those prone to falls. A solution was developed that leverages a mmWave radar combined with transformer-based machine learning, to detect and classify patterns as non-anomalous or anoma- lous. Data was further processed to distinguish falls from other activities. The results indicate that this model can accurately identify fall events, while maintaining a low false positives rate. This forms a foundation for other HAR implementations that could support independent living for those requiring assistance or support.
| Item Type: | Thesis (Master's Thesis / Essay) |
|---|---|
| Supervisor name: | Sibert, C.L. |
| Degree programme: | Computational Cognitive Science |
| Thesis type: | Master's Thesis / Essay |
| Language: | English |
| Date Deposited: | 11 Feb 2025 09:35 |
| Last Modified: | 11 Feb 2025 09:35 |
| URI: | https://fse.studenttheses.ub.rug.nl/id/eprint/34714 |
Actions (login required)
 |
View Item |