Addressing location dependency in human activity recognition using channel state information via 3D- CWT approach
This work presents an exceptional approach to address the location dependency challenge in Human Activity Recognition (HAR) using Channel State Information (CSI). HAR using CSI has shown promise in capturing fine-grained motion information; however, the performance of models varies significantly acr...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | English |
| Published: |
2023
|
| Online Access: | http://eprints.utem.edu.my/id/eprint/27958/1/Addressing%20location%20dependency%20in%20human%20activity%20recognition%20using%20channel%20state%20information%20via%203D-%20CWT%20approach.pdf http://eprints.utem.edu.my/id/eprint/27958/ https://ieeexplore.ieee.org/document/10292053 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | This work presents an exceptional approach to address the location dependency challenge in Human Activity Recognition (HAR) using Channel State Information (CSI). HAR using CSI has shown promise in capturing fine-grained motion information; however, the performance of models varies significantly across different locations or positions. To mitigate this limitation, we propose an innovative solution based on 3D Continuous Wavelet Transform (CWT) that simultaneously captures spatial and temporal information. Experimental results demonstrate the effectiveness of the proposed approach in reducing location dependency and improving activity recognition accuracy across diverse environments. |
|---|