Lightweight and Efficient CSI-Based Human Activity Recognition via Bayesian Optimization-Guided Architecture Search and Structured Pruning
Source abstract
Abstract
This paper presents an integrated approach to developing lightweight, high-performance deep learning models for human activity recognition (HAR) using WiFi Channel State Information (CSI). Motivated by the need for accuracy and efficiency in resource-constrained environments, we combine Bayesian Optimization-based Neural Architecture Search (NAS) with a structured pruning algorithm. NAS identifies optimal network configurations, while pruning systematically removes redundant parameters, preserving accuracy. This approach allows for robust activity recognition from diverse WiFi datasets under varying conditions. Experimental results across multiple benchmark datasets demonstrate that our method not only maintains but often improves accuracy after pruning, resulting in models that are both smaller and more accurate. This offers a scalable and adaptable solution for real-world deployments in IoT and mobile platforms, achieving an optimal balance of efficiency and accuracy in HAR using WiFi CSI.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Context-Aware Activity Recognition Systems · Human Pose and Action Recognition · Anomaly Detection Techniques and Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Information and Communication Engineering, Wonkwang University, Iksan 54538, Republic of Korea
Department of Computer Software Engineering, Wonkwang University, Iksan 54538, Republic of Korea
Funding
Wonkwang University
References (24)
Show source-provided references
1. Wang, W., Liu, A.X., Shahzad, M., Ling, K., and Lu, S. (2015, January 7–11). Understanding and Modeling of WiFi Signal Based Human Activity Recognition. Proceedings of the 21st Annual International Conference on Mobile Computing and Networking, Paris, France.10.1145/2789168.2790093 ↗
2. Zou, H., Zhou, Y., Yang, J., Jiang, H., Xie, L., and Spanos, C.J. (2018, January 20–24). DeepSense: Device-Free Human Activity Recognition via Autoencoder Long-Term Recurrent Convolutional Network. Proceedings of the 2018 IEEE International Conference on Communications (ICC), Kansas City, MO, USA.10.1109/ICC.2018.8422895 ↗
3. Learning Gestures From WiFi: A Siamese Recurrent Convolutional Architecture10.1109/JIOT.2019.2941527 ↗
4. SenseFi: A Library and Benchmark on Deep-Learning-Empowered WiFi Human Sensing10.1016/j.patter.2023.100703 ↗
5. WiFi Sensing with Channel State Information: A Survey
6. Zou, H., Zhou, Y., Yang, J., Gu, W., Xie, L., and Spanos, C. (2018, January 2–7). WiFi-Based Human Identification via Convex Tensor Shapelet Learning. Proceedings of the 32nd AAAI Conference on Artificial Intelligence, New Orleans, LA, USA.10.1609/aaai.v32i1.11497 ↗
7. A Survey on Behavior Recognition Using WiFi Channel State Information10.1109/MCOM.2017.1700082 ↗
8. A Survey on Human Behavior Recognition Using Channel State Information10.1109/ACCESS.2019.2949123 ↗
9. Zhang, J., Tang, Z., Li, M., Fang, D., Nurmi, P., and Wang, Z. (November, January 29). CrossSense: Towards Cross-Site and Large-Scale WiFi Sensing. Proceedings of the 24th Annual International Conference on Mobile Computing and Networking, New Delhi, India.
10. CSI Phase Fingerprinting for Indoor Localization with a Deep Learning Approach10.1109/JIOT.2016.2558659 ↗
11. Ferrari, V., Hebert, M., Sminchisescu, C., and Weiss, Y. (2018). AMC: AutoML for Model Compression and Acceleration on Mobile Devices. Computer Vision—ECCV 2018, Springer.
12. He, Y., Zhang, X., and Sun, J. (2017, January 22–29). Channel Pruning for Accelerating Very Deep Neural Networks. Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy.10.1109/ICCV.2017.155 ↗
13. Han, S., Pool, J., Tran, J., and Dally, W. (2015, January 7–12). Learning both Weights and Connections for Efficient Neural Network. Proceedings of the Advances in Neural Information Processing Systems, Montreal, QC, Canada.
14. Liu, Z., Li, J., Shen, Z., Huang, G., Yan, S., and Zhang, C. (2017, January 22–29). Learning Efficient Convolutional Networks through Network Slimming. Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy.10.1109/ICCV.2017.298 ↗
15. A Survey of Model Compression and Acceleration for Deep Neural Networks10.1109/MSP.2017.2765695 ↗
16. Han, S., Mao, H., and Dally, W.J. (2016, January 2–4). Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding. Proceedings of the International Conference on Learning Representations (ICLR), San Juan, Puerto Rico.
17. Efficient Processing of Deep Neural Networks: A Tutorial and Survey10.1109/JPROC.2017.2761740 ↗
18. EfficientFi: Toward Large-Scale Lightweight WiFi Sensing via CSI Compression10.1109/JIOT.2021.3139958 ↗
19. Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., and Adam, H. (2017). MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications. arXiv.
20. Molchanov, P., Tyree, S., Karras, T., Aila, T., and Kautz, J. (2017, January 24–26). Pruning Convolutional Neural Networks for Resource Efficient Inference. Proceedings of the International Conference on Learning Representations (ICLR), Toulon, France.
21. Pasandi, M.M., Hajabdollahi, M., Karimi, N., and Samavi, S. (2019, January 12–14). Modeling of Pruning Techniques for Deep Neural Networks Simplification. Proceedings of the International Conference on Digital Image Processing, Shanghai, China.10.1109/MVIP49855.2020.9116891 ↗
22. Storage Efficient and Dynamic Flexible Runtime Channel Pruning via Deep Reinforcement Learning
23. Luo, R., Tian, F., Qin, T., Chen, E., and Liu, T.-Y. (2018, January 3–8). Neural Architecture Optimization. Proceedings of the 32nd Conference on Neural Information Processing Systems (NeurIPS), Montreal, QC, Canada.
24. Wi-LADL: A Wireless-Based Lightweight Attention Deep Learning Method for Human–Vehicle Recognition10.1109/JSEN.2022.3232243 ↗