University of Twente Student Theses
As of Friday, 8 August 2025, the current Student Theses repository is no longer available for thesis uploads. A new Student Theses repository will be available starting Friday, 15 August 2025.
Enhancing Initialization in Distributed HAR Systems : Leveraging CSI and RSSI for Intelligent Node Pairing
Delgado Plácido, Victor (2025) Enhancing Initialization in Distributed HAR Systems : Leveraging CSI and RSSI for Intelligent Node Pairing.
|
PDF
2MB |
| Abstract: | Human Activity Recognition (HAR) using Wi-Fi Channel State Information (CSI) offers a promising pathway for unobtrusive monitoring enabling the detection and classification of physical activities from sensed data in the form of Wi-Fi signals without requiring users to wear any sensors or devices. A major challenge in current AI powered HAR solutions is the need for a central processing module, limiting scalability and real-world applicability. This has encouraged developers to lead the system’s evolution toward distributed architectures, where sensing and processing are handled by multiple edge devices. A key issue in deploying distributed HAR systems is determining which transmitter-receiver pairs are best suited for accurate activity recognition in a given location. This selection is critical, as it directly affects system performance, efficiency, and scalability. This thesis focuses on improving the initialization phase of distributed CSI-based HAR systems by proposing new ideas and methods which leverage CSI data characteristics for identifying optimal device pairings across different environments. By addressing this challenge, the proposed work aims to enhance the reliability and adaptability of distributed HAR systems, leading the way for more practical and scalable real-world deployments. Improvements in the classification model have been achieved, along with promising ideas and methodologies to enhance the performance of the initialization phase, though these require further development and refinement for effective implementation. |
| Item Type: | Essay (Bachelor) |
| Faculty: | EEMCS: Electrical Engineering, Mathematics and Computer Science |
| Subject: | 54 computer science |
| Programme: | Computer Science BSc (56964) |
| Link to this item: | https://purl.utwente.nl/essays/107363 |
| Export this item as: | BibTeX EndNote HTML Citation Reference Manager |
Show download statistics for this publication
Show download statistics for this publicationRepository Staff Only: item control page