Human Fall Detection Method Beyond the Sensing Range of IR-UWB Using Ambient Vibration

Wang Dongzi; Guo Zhengxin; Gui Linqing; Sheng Biyun; Cai Hui; Xiao Fu

doi:10.7544/issn1000-1239.202440386

Journal of Computer Research and Development > 2024 > 61(11): 2721-2738. > DOI: 10.7544/issn1000-1239.202440386 CSTR: 32373.14.issn1000-1239.202440386

Wang Dongzi, Guo Zhengxin, Gui Linqing, Sheng Biyun, Cai Hui, Xiao Fu. Human Fall Detection Method Beyond the Sensing Range of IR-UWB Using Ambient Vibration[J]. Journal of Computer Research and Development, 2024, 61(11): 2721-2738. DOI: 10.7544/issn1000-1239.202440386

Citation:

PDF (4078 KB)

Human Fall Detection Method Beyond the Sensing Range of IR-UWB Using Ambient Vibration

Wang Dongzi^1,,
Guo Zhengxin^{1, 2},
Gui Linqing^{1, 2},
Sheng Biyun^{1, 2},
Cai Hui^{1, 2},
Xiao Fu^{1, 2, ,}

1.
School of Computer Science & Technology, Nanjing University of Posts and Telecommunications, Nanjing 210023
2.
Jiangsu High Technology Research Key Laboratory for Wireless Sensor Networks (Nanjing University of Posts and Telecommunications), Nanjing 210023

Funds: This work was supported by the National Natural Science Foundation of China for Distinguished Young Scholars (62125203), the National Natural Science Foundation of China (61932013) , and the Key Research and Development Program of Jiangsu Province (BE2022798).

More Information

Author Bio:
Wang Dongzi: born in 1996. PhD candidate. Student member of CCF. His main research interest includes wireless sensing

Guo Zhengxin: born in 1993. PhD, lecturer. Member of CCF. His main research interests include wireless sensing and mobile computing

Gui Linqing: born in 1984. PhD, professor, PhD supervisor. Member of CCF. His main research interests include intelligent perception and computing of the Internet of things, and Internet of things security

Sheng Biyun: born in 1989. PhD, associate professor, master supervisor. Member of CCF. Her main research interests include human behavior recognition, identity authentication, deep learning, and cross domain sensing

Cai Hui: born in 1993. PhD, lecturer, master supervisor. Member of CCF. Her main research interests include privacy and security, federated learning, data science and big data computing, mobile crowd-sensing networks, and game theory

Xiao Fu: born in 1980. PhD, professor, PhD supervisor. Senior member of CCF. His main research interests include IoT sensing, IoT security technologies, and data center networks
Received Date: May 30, 2024
Revised Date: July 29, 2024
Available Online: September 04, 2024

Graphical Abstract

Abstract

Abstract

Fall detection is crucial in elderly healthcare, traditionally relying on wearable devices for sensing. To avoid the burden and discomfort caused by wearable devices, contact-free methods using radio frequency (RF) signals have emerged as a promising alternative due to their ubiquity and non-invasiveness. Existing contact-free methods predominantly extract physiological motion features, e.g., the speed and acceleration of human falls from RF signals and analyze the motion time series to determine if a fall event has occurred. While current methods achieve high detection accuracy in line-of-sight (LoS) scenarios, they still face limitations in sensing range and non-light-of-sight (NLoS). To address this, we propose a method using the commercial off-the-shelf (COTS) impulse radio-ultra wideband (IR-UWB) devices to detect human falls beyond the sensing range. The key insight of our method is identifying ambient vibration features induced by falls outside the sensing range to determine fall events. By developing the IQ entropy and farthest points-pair distance algorithm, signal features from subtle vibrations caused by falls are extracted. We implement a UWFall prototype system built on COTS IR-UWB devices and conduct extensive experimental evaluations under various environments. The results demonstrate that UWFall system achieves a recognition accuracy over 90% with one single transceiver. Furthermore, the detection accuracy for falls beyond 7 meters exceeds 86%, and this system maintains high robustness in NLoS scenarios.
- fall detection,
- radio frequency sensing,
- Internet of things,
- IR-UWB radar,
- wireless sensing

FullText(HTML)

References (31)

References

[1]	Chen Zhe, Zheng Tianyue, Cai Chao, et al. Wider is better? contact-free vibration sensing via different COTS-RF technologies[C]//Proc of the IEEE Conf on Computer Communications. Piscataway, NJ: IEEE, 2023: 1−10
[2]	Siwadamrongpong W, Chinrungrueng J, Hasegawa S, et al. Fall detection and prediction based on IMU and EMG sensors for elders[C]//Proc of the 19th Int Joint Conf on Computer Science and Software Engineering. Piscataway, NJ: IEEE, 2022: 1−6
[3]	Mohamed H H, Siti H Y, Anis N I, et al. Wearable smart phone sensor fall detection system[J]. International Journal of Interactive Mobile Technologies, 2022, 16(12): 72−93 doi: 10.3991/ijim.v16i12.30105
[4]	Chen Yi, Xiao Fu, Huan Haiping, et al. RF-IDH: An intelligent fall detection system for hemodialysis patients via COTS RFID[J]. Future Generation Computer Systems, 2020, 113: 13−24 doi: 10.1016/j.future.2020.06.047
[5]	Kottari K N, Delibasis K K, Maglogiannis I G. Real-time fall detection using uncalibrated Fisheye cameras[J]. IEEE Transactions on Cognitive and Developmental Systems, 2020, 12(3): 588−600 doi: 10.1109/TCDS.2019.2948786
[6]	Lian Jie, Yuan Xu, Li Ming, et al. Fall detection via inaudible acoustic sensing[J]. Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies, 2021, 5(3): 1−21
[7]	Hu Yuqian, Zhang Feng, Wu Chenshu, et al. DeFall: Environment-independent passive fall detection using WiFi[J]. IEEE Internet of Things Journal, 2022, 9(11): 8515−8530 doi: 10.1109/JIOT.2021.3116136
[8]	Jin Feng, Sengupta A, Cao Siyang. mmFall: Fall detection using 4-D mmWave radar and a hybrid variational RNN autoEncoder[J]. IEEE Transactions on Automation Science and Engineering, 2022, 19(23): 1245−1257
[9]	Sanaz K, Stefano S, Federico V, et al. Device-free RF human body fall detection and localization in industrial workplaces[J]. IEEE Internet of Things Journal, 2017, 4(2): 351−362 doi: 10.1109/JIOT.2016.2624800
[10]	Takashi N, Mondher B, Kohei Y, et al. Wi-Fi-based fall detection using spectrogram image of channel state information[J]. IEEE Internet of Things Journal, 2022, 9(18): 17220−17234 doi: 10.1109/JIOT.2022.3152315
[11]	Li Wenxuan, Zhang Dongheng, Li Yadong, et al. Real-time fall detection using mmwave radar[C]//Proc of the 2022 IEEE Int Conf on Acoustics, Speech and Signal Processing. Piscataway, NJ: IEEE, 2022: 16−20
[12]	Lin Guiping, Men Jing, Lin Enmin, et al. Peak amplitude curve based arm motion recognition using IR-UWB radar[C]//Proc of the 98th Vehicular Technology Conf. Piscataway, NJ: IEEE, 2023: 1−6
[13]	Taekjin H, Wonho K, Gyunghyun C. IR-UWB sensor based fall detection method using CNN algorithm[J]. Sensors, 2020, 20(20): 5948−5969 doi: 10.3390/s20205948
[14]	Ding Rong, Jin Haiming, Xiang Dong, et al. Soil moisture sensing with UAV-Mounted IR-UWB radar and deep learning[C]//Proc of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies. New York: ACM, 2023, 7(1): 1−25
[15]	Jiang Xikang, Lin Zhang, Lei Li. Multi-task learning radar transformer (MLRT): A personal identification and fall detection network based on IR-UWB radar[J]. Sensors, 2023, 23(12): 5632−5643 doi: 10.3390/s23125632
[16]	Chen Di, Xiong Gang, Wang Lizhe, et al. Variable length sequential iterable convolutional recurrent network for UWB-IR vehicle target recognition[J]. IEEE Transactions on Geoscience and Remote Sensing, 2023, 61: 1−11
[17]	Dang Xiaochao, Zhang Jinlong, Hao Zhanjun. A non-contact detection method for multi-person vital signs based on IR-UWB radar[J]. Sensors, 2022, 22(16): 6116−6136 doi: 10.3390/s22166116
[18]	Khan F, Azou S, Youssef R, et al. An IR-UWB multi-sensor approach for collision avoidance in indoor environments[J]. IEEE Transactions on Instrumentation and Measurement, 2022, 71: 1−13
[19]	Kwon H B, Choi S H, Lee D, et al. Attention-based LSTM for non-contact sleep stage classification using IR-UWB radar[J]. IEEE Journal of Biomedical and Health Informatics, 2021, 25(10): 3844−3853 doi: 10.1109/JBHI.2021.3072644
[20]	Ali K, Liu A X. Fine-grained vibration based sensing using a smartphone[J]. IEEE Transactions on Mobile Computing, 2022, 21(11): 3971−3985 doi: 10.1109/TMC.2021.3067679
[21]	Fagert J, Bonde A, Srinidhi S, et al. Clean Vibes: Hand washing monitoring using structural vibration sensing[J]. ACM Transactions on Computing for Healthcare, 2022, 3(3): 1−25
[22]	Feng Yuanhao, Zhang Youwei, Yang Panlong. RF-Ear⁺: A mechanical identification and troubleshooting system based on contactless vibration sensing[J]. IEEE Transactions on Mobile Computing, 2023, 22(12): 7310−7326 doi: 10.1109/TMC.2022.3210150
[23]	Yang Xin, Yang Song, Liu Jian. Enabling finger-touch-based mobile user authentication via physical vibrations on IoT devices[J]. IEEE Transactions on Mobile Computing, 2022, 21(10): 3565−3580 doi: 10.1109/TMC.2021.3057083
[24]	Maria V, Li Fangyu, Zhao Liang, et al. Vibration sensing-based human and infrastructure safety/health monitoring: A survey[J]. Digital Signal Processing, 2022, 125: 103572−103585 doi: 10.1016/j.dsp.2022.103572
[25]	Wang Ziqi, Chen Zhe, Singh A D. UWHear: Through-wall extraction and separation of audio vibrations using wireless signals[C]//Proc of the 18th Conf on Embedded Networked Sensor Systems. New York: ACM, 2020: 1−14
[26]	Maître J, Bouchard K, Gaboury S. et al. Fall detection with UWB radars and CNN-LSTM architecture[J]. IEEE Journal of Biomedical and Health Informatics, 2021, 25(4): 1273−1283 doi: 10.1109/JBHI.2020.3027967
[27]	Wu Kaishun, Huang Yandao, Qiu Minghui, et al. Toward device-free and user-independent fall detection using floor vibration[J]. ACM Transactions on Sensor Networks, 2023, 19(1): 1550−1859
[28]	Guo Zhengxin, Wang Dongzi, Gui Linqing, et al. UWTracking: Passive human tracking under LOS/NLOS scenarios using IR-UWB radar[J]. IEEE Transactions on Mobile Computing, 2024, 5(1): 1−17
[29]	Zhang Fusang, Xiong Jie, Chang Zhaoxin, et al. Mobi2Sense: Empowering wireless sensing with mobility[C]//Proc of the 28th Annual Int Conf on Mobile Computing and Networking. New York: ACM, 2022: 268−281
[30]	Sadreazami H, Bolic M, Rajan S. et al. Fall detection using Standoff radar-based sensing and deep convolutional neural network[J]. IEEE Transactions on Circuits and Systems II: Express Briefs, 2020, 67(1): 197−201
[31]	Jiang Xikang, Zhang Jinhui, Zhang Lin. FedRadar: Federated multi-task transfer learning for radar-based Internet of medical things[J]. IEEE Transactions on Network and Service Management, 2023, 20(2): 1459−1469 doi: 10.1109/TNSM.2023.3281133