Abstract
Traditional finger-tracking methods using sensors, cameras, and other devices are limited by high costs, environmental sensitivity, and inadequate user privacy protection. To address these challenges, we propose ARFG, an attach-free RFID finger-tracking system based on Generative Adversarial Network (GAN). ARFG captures time-series reflection signal changes resulting from finger movements in front of RFID tag arrays. These signals are transformed into feature maps that serve as inputs for DS-GAN, a fully supervised classification model using a semi-supervised algorithm. ARFG achieves accurate recognition of finger traces, with soft thresholding used to overcome the challenge of limited dataset training of conventional GANs. Extensive experiments demonstrate ARFG’s high accuracy, with average accuracy of 94.69% and up to 97.50% in conditions with few samples, various traces, users, finger speeds, and surroundings, showcasing its robustness and cross environmental capabilities.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Chang, X., Ma, Z., Lin, M., Yang, Y., Hauptmann, A.G.: Feature interaction augmented sparse learning for fast kinect motion detection. IEEE Trans. Image Process. 26(8), 3911–3920 (2017)
Gupta, H.P., Chudgar, H.S., Mukherjee, S., Dutta, T., Sharma, K.: A continuous hand gestures recognition technique for human-machine interaction using accelerometer and gyroscope sensors. IEEE Sens. J. 16(16), 6425–6432 (2016)
Ma, Y., Hui, X., Kan, E.C.: 3d real-time indoor localization via broadband nonlinear backscatter in passive devices with centimeter precision. In: Proceedings of the 22nd Annual International Conference on Mobile Computing and Networking, pp. 216–229 (2016)
Shangguan, L., Jamieson, K.: Leveraging electromagnetic polarization in a two antenna whiteboard in the air. In: Proceedings of the 12th International on Conference on emerging Networking EXperiments and Technologies, pp. 443–456 (2016)
Ding, H., et al.: A platform for free-weight exercise monitoring with passive tags. IEEE Trans. Mob. Comput. 16(12), 3279–3293 (2017)
Zou, Y., Xiao, J., Han, J., Wu, K., Li, Y., Ni, L.M.: Grfid: a device-free rfid-based gesture recognition system. IEEE Trans. Mob. Comput. 16(2), 381–393 (2016)
Wang, C., et al.: Multi touch in the air: Device-free finger tracking and gesture recognition via cots rfid. In: IEEE INFOCOM 2018-IEEE Conference on Computer Communications, pp. 1691–1699. IEEE (2018)
Zhang, S., et al.: Real-time and accurate gesture recognition with commercial rfid devices. IEEE Trans. Mobile Comput. (2022)
Haque, A.: Ec-gan: Low-sample classification using semi-supervised algorithms and gans (student abstract). In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 15797–15798 (2021)
Zhao, M., Zhong, S., Fu, X., Tang, B., Pecht, M.: Deep residual shrinkage networks for fault diagnosis. IEEE Trans. Industr. Inf. 16(7), 4681–4690 (2019)
Zhang, H., Goodfellow, I., Metaxas, D., Odena, A.: Self-attention generative adversarial networks. In: International Conference on Machine Learning, pp. 7354–7363. PMLR (2019)
Ren, Z., Yuan, J., Meng, J., Zhang, Z.: Robust part-based hand gesture recognition using kinect sensor. IEEE Trans. Multimedia 15(5), 1110–1120 (2013)
Xie, L., Wang, C., Liu, A.X., Sun, J., Lu, S.: Multi-touch in the air: concurrent mi-cromovement recognition using rf signals. IEEE/ACM Trans. Networking 26(1), 231–244 (2017)
Ha, U., Leng, J., Khaddaj, A., Adib, F.: Food and liquid sensing in practical environments using {RFIDs}. In: 17th USENIX Symposium on Networked Systems Design and Implementation (NSDI 20), pp. 1083–1100 (2020)
Ma, Z., et al.: Rf-siamese: approaching accurate rfid gesture recognition with one sample. IEEE Trans. Mobile Comput. (2022)
Gong, T., Kim, Y., Shin, J., Lee, S.J.: Metasense: few-shot adaptation to untrained conditions in deep mobile sensing. In: Proceedings of the 17th Conference on Embedded Networked Sensor Systems, pp. 110–123 (2019)
Ding, S., Chen, Z., Zheng, T., Luo, J.: Rf-net: a unified meta-learning framework for rf-enabled one-shot human activity recognition. In: Proceedings of the 18th Conference on Embedded Networked Sensor Systems, pp. 517–530 (2020)
Itoh, K.: Analysis of the phase unwrapping algorithm. Appl. Opt. 21(14), 2470 (1982)
Pearson, K.: Vii. note on regression and inheritance in the case of two parents. Proc. Royal Soc. London 58(347–352), 240–242 (1895)
Lee, D.H., et al.: Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks. In: Workshop on Challenges in Representation Learning, ICML, vol. 3, p. 896 (2013)
Acknowledgements
This paper is supported by the 2021 Fujian Foreign Cooperation Project(No. 2021I0001): Research on Human Behavior Recognition Based on RFID and Deep Learning; 2021 Project of Xiamen University (No. 20213160A0474): Zijin International Digital Operation Platform Research and Consulting; State Key Laboratory of Process Automation in Mining & Metallurgy, Beijing Key Laboratory of Process Automation in Mining & Metallurgy(No. BGRIMM-KZSKL-2022-14): Research and application of mine operator positioning based on RFID and deep learning; National Key R&D Program of China-Sub-project of Major Natural Disaster Monitoring, Early Warning and Prevention(No. 2020YFC1522604).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Li, S. et al. (2023). ARFG: Attach-Free RFID Finger-Tracking with Few Samples Based on GAN. In: Huang, DS., Premaratne, P., Jin, B., Qu, B., Jo, KH., Hussain, A. (eds) Advanced Intelligent Computing Technology and Applications. ICIC 2023. Lecture Notes in Computer Science, vol 14087. Springer, Singapore. https://doi.org/10.1007/978-981-99-4742-3_64
Download citation
DOI: https://doi.org/10.1007/978-981-99-4742-3_64
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-4741-6
Online ISBN: 978-981-99-4742-3
eBook Packages: Computer ScienceComputer Science (R0)