Wireless Fall Detection: An Integrative Investigation of Deep Learning Innovations, Challenges and Future Directions

Chenyu Liu

doi:10.54097/k0fmnk74

Authors

Chenyu Liu

DOI:

https://doi.org/10.54097/k0fmnk74

Keywords:

Wi-Fi Channel State Information (CSI); Wireless Sensing; Fall Detection.

Abstract

The fall-detection equipment is critical for addressing accidental falls among the aging population, which has a huge health effect. The traditional wearable devices and monitors were not widely developed due to limitations in convenience and privacy. Therefore, non-invasive detection equipment leveraging Wi-Fi Channel State Information has become increasingly popular as a promising alternative to protect older adults efficiently. However, the practical deployment proved to be more challenging, including the generalization problem across different environments, users, and actions. This review provides an integrative analysis of wireless falling detection methods leveraging deep-learning models, information modelling, and cross-modal learning to study their core mechanisms in signal processing and data augmentation. Moreover, for challenges such as studying similar behaviors, data scarcity, and computational processes, this work also provides future study directions like lightweight architecture and cross-modal systems. This review aims to offer critical insights to support the development of more robust fall detection systems.

References

[1] Wang Z, Ramamoorthy V, Gal U, Guez A. Possible life saver: a review on human fall detection technology. Robotics. (2020); 9(3):55. https://doi.org/10.3390/robotics9030055.

[2] Ma Y, Zhou G, Wang S. WiFi sensing with channel state information: a survey. ACM Computing Surveys (CSUR). (2020); 52(3):1-36. https://doi.org/10.1145/3310194.

[3] Hu Y, Zhang F, Wu C, Wang B, Liu KJ. DeFall: environment-independent passive fall detection using WiFi. IEEE Internet of Things Journal. (2022); 9(11):8515-8530. https://doi.org/10.1109/JIOT.2021.3116136.

[4] Yang Z, Zhang Y, Zhang Q. Rethinking fall detection with Wi-Fi. IEEE Transactions on Mobile Computing. (2023); 22(10):6126-6143. https://doi.org/10.1109/TMC.2022.3188779.

[5] Chi G, Zhang G, Ding X, Ma Q, Yang Z, Du Z. XFall: domain adaptive Wi-Fi-based fall detection with cross-modal supervision. IEEE Journal on Selected Areas in Communications. (2024); 42(9):2457-2471. https://doi.org/10.1109/JSAC.2024.3413997.

[6] Chen Z, Zhao Y, Chen G, Yang Y, Huang W, Xu C-Z. DapFall: dynamic amplitude probability density profile-based Wi-Fi CSI sensing for fall detection. IEEE Sensors Journal. (2025); 25(8):14252-14265. https://doi.org/10.1109/JSEN.2025.3544552.

[7] Wang C, Tang L, Zhou M, Ding Y, Zhuang X, Wu J. Indoor human fall detection algorithm based on wireless sensing. Tsinghua Science and Technology. (2022); 27(6):1002-1015. https://doi.org/10.26599/TST.2022.9010011.

[8] Wang H, Xu S, Chen Y, Su C. LFD-YOLO: a lightweight fall detection network with enhanced feature extraction and fusion. Scientific Reports. (2025); 15(1):5069. https://doi.org/10.1038/s41598-025-89214-7.

[9] Xiao Y, Zhu J, Zhang S, Liu X, Guo S. Fall-Attention: an attention-based fall detection method for adjoint activities. IEEE Transactions on Mobile Computing. (2024); 23(7):7895-7909. https://doi.org/10.1109/TMC.2023.3344125.

[10] Alzubaidi L, Bai J, Al-Sabaawi A, Santamaría J, Albahri AS, Al-Dabbagh BS, Fadhel MA, Manoufali M, Zhang J, Al-Timemy AH, Duan Y. A survey on deep learning tools dealing with data scarcity: definitions, challenges, solutions, tips, and applications. Journal of Big Data. 2023 Apr 14;10(1):46.