A tiny inertial transformer for human activity recognition via multimodal knowledge distillation and explainable AI
Ismail Lamaakal, Chaymae Yahyati, Yassine Maleh, Khalid El Makkaoui, Ibrahim Ouahbi, Ahmed A. Abd El-Latif, Mariam Zomorodi, Basma Abd El-Rahiem · 2025
Read A tiny inertial transformer for human activity recognition via multimodal knowledge distillation and explainable AI by Ismail Lamaakal, Chaymae Yahyati, Yassine Maleh, Khalid El Makkaoui, Ibrahim Ouahbi, Ahmed A. Abd El-Latif, Mariam Zomorodi, Basma Abd El-Rahiem (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-12660865.txt.
Description
Human activity recognition (HAR) is essential for applications such as healthcare monitoring, fitness tracking, and smart environments, yet deploying accurate and interpretable models on resource-constrained devices remains challenging. In this paper, we propose XTinyHAR, a lightweight, transformer-based unimodal framework trained via cross-modal knowledge distillation from a multimodal teacher.
Catalog record
| CREATOR | Ismail Lamaakal, Chaymae Yahyati, Yassine Maleh, Khalid El Makkaoui, Ibrahim Ouahbi, Ahmed A. Abd El-Latif, Mariam Zomorodi, Basma Abd El-Rahiem |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 188 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |