Секційний напрямок
Як цитувати
Кількість переглядів 27
Анотація
This paper examines the development of contactless interfaces for computer-integrated control systems (CIS) using unconventional sensor data—Wi-Fi channel state information (CSI). A comparative analysis of two deep learning approaches is provided: hybrid architectures (CNN-BiGRU) and models based on the self-attention mechanism (Transformer). The study shows that while Transformers have high potential for big data, for real-time control tasks on limited computing resources (IoT), optimized architectures such as Attention-BiGRU are preferable, providing accuracy of up to 94-96% with lower latency.
Посилання
Khan M. M. U., Shams A. B., Raihan M. S. A prospective approach for human-to-human interaction recognition from Wi-Fi channel data using attention bidirectional gated recurrent neural network with GUI application implementation – 2024. – Т. 83. – №. 22. – С. 62379-62422.
Yousefi S. et al. A survey on behavior recognition using WiFi channel state information //IEEE Communications Magazine. – 2017. – Т. 55. – №. 10. – С. 98-104.
Tan S., Yang J. Fine-grained Finger Gesture Recognition Using WiFi Signals //arXiv preprint arXiv:2106.00857. – 2021.
Ren Y., Yang J. 3d human pose estimation for free-from and moving activities using wifi //arXiv preprint arXiv:2204.07878. – 2022.
Yang J. et al. SenseFi: A library and benchmark on deep-learning-empowered WiFi human sensing //Patterns. – 2023. – Т. 4. – №. 3.
Cui F. Q. et al. Generalizing wifi gesture recognition via large-model-aware semantic distillation and alignment //2025 IEEE 31th International Conference on Parallel and Distributed Systems
(ICPADS). – IEEE, 2025. – С. 1-8.
Тези доступні на умовах Creative Commons Attribution-ShareAlike 4.0 International License.
Авторське право (c) 2026 Oleksandr Karatanas