基于时间编码超表面的跌倒特征模拟与Wi-Fi感知数据集辅助构建

陈少楠; 顾家铭; 徐超; 孙一淼; 王思然; 陈展野; 刘硕; 李会东; 戴俊彦; 何源; 程强

doi:10.12000/JR24247

基于时间编码超表面的跌倒特征模拟与Wi-Fi感知数据集辅助构建

DOI: 10.12000/JR24247 CSTR: 32380.14.JR24247

陈少楠¹,
顾家铭^{2, 3},
徐超^{2, 3},
孙一淼^{2, 3},
王思然¹,
陈展野¹,
刘硕¹,
李会东¹,
戴俊彦^1, ,,
何源^{2, 3},
程强^1, ,

1.
东南大学毫米波全国重点实验室南京 210000
2.
清华大学软件学院北京 100084
3.
北京信息科学与技术国家研究中心(清华大学) 北京 100084

基金项目: 国家重点研发计划(No.2023YFB3811504, 2023YFB3811502, 2024YFB2907800)，国家杰出青年科学基金项目(N0.62225108)，中央高校基本科研业务费专项资金(No.2242022k60003)，国家自然科学基金(No.62288101, 62201139, U22A2001)，江苏省应用数学科学研究中心(N0.BK20233002)，江苏省基础研究计划重点项目(N0.BK20243028)，中央高校基本科研业务费专项资金(N0.2242024RCB0005)

详细信息

作者简介:
陈少楠，博士生，主要研究方向为时间编码超表面及其在雷达技术中的应用

顾家铭，博士生，主要研究方向为无线网络、低功耗物联网、无线感知

徐　超，本科生，主要研究方向为低功耗物联网、无线感知

孙一淼，博士生，主要研究方向为无线感知、移动计算和射频计算

王思然，博士，主要研究方向为信息超材料及其在雷达、目标特性和无线通信中的应用

陈展野，博士，副教授，主要研究方向为新型电磁调控系统信息处理、雷达数字仿真与数据增广以及雷达运动目标检测

刘　硕，博士，教授，主要研究方向为新型人工电磁材料

李会东，博士，副研究员，主要研究方向为新型编码漏波天线、反射(透射)阵天线

戴俊彦，博士，副教授，主要研究方向为超表面、可重构智能表面、时空调制技术和无线通信系统

何源，博士，副教授，主要研究方向为物联网、无线网络、移动和普适计算

程　强，博士，教授，主要研究方向为超材料设计理论及其应用

通讯作者:
戴俊彦 junyand@seu.edu.cn

程强 qiangcheng@seu.edu.cn

责任主编：陈彦 Corresponding Editor: CHEN Yan
中图分类号: TN820
计量
- 文章访问数:
- HTML全文浏览量:
- PDF下载量:
- 被引次数: 0
出版历程
- 收稿日期: 2024-12-11
- 修回日期: 2025-02-27
- 网络出版日期: 2025-04-09

Fall Feature Simulation and Wi-Fi Sensing Dataset Construction Based on Time-domain Digital Coding Metasurface

CHEN Shaonan¹,
GU Jiaming^{2, 3},
XU Chao^{2, 3},
SUN Yimiao^{2, 3},
WANG Siran¹,
CHEN Zhanye¹,
LIU Shuo¹,
LI Huidong¹,
DAI Junyan^{1
, ,},
HE Yuan^{2, 3},
CHENG Qiang^{1
, ,}

1.
State Key Laboratory of Millimeter Waves, Southeast University, Nanjing 210000, China
2.
School of Software, Tsinghua University, Beijing 100084, China
3.
Beijing National Research Center for Information Science and Technology (Tsinghua University), Beijing 100084, China

Funds: This work is supported by the National Key Research and Development Program of China (2023YFB3811504, 2023YFB3811502, 2024YFB2907800), the National Science Foundation (NSFC) for Distinguished Young Scholars of China (62225108), the Fundamental Research Funds for the Central Universities (2242022k60003), the National Natural Science Foundation of China (62288101, 62201139, U22A2001), the Jiangsu Provincial Scientific Research Center of Applied Mathematics (BK20233002), the Jiangsu Science and Technology Research Plan (BK20243028), and the Fundamental Research Funds for the Central Universities (2242024RCB0005)

More Information

Corresponding author: DAI Junyan, junyand@seu.edu.cn; CHENG Qiang, qiangcheng@seu.edu.cn

摘要

摘要: 随着Wi-Fi感知技术在智能健康监测领域的广泛应用，如何构建高质量的数据集成为亟待解决的关键问题。特别是在监测异常行为(如跌倒)时，传统方法依赖于人体的反复实验，这既存在安全隐患，又面临伦理困境。为应对这一挑战，该文提出了一种基于时间编码超表面的辅助数据样本采集方法。通过模拟人体的运动特征，时间编码超表面可以有效替代人体实验，用于辅助构建Wi-Fi感知数据集。为此该文设计了一款具备0～360°全相位调制能力的时间编码超表面验证了该方案的可行性。实验结果表明，超表面生成的信号能够较好地保留人体运动特征，有效补充真实样本，降低数据采集复杂度，并显著提升模型的监测准确性。该方法为Wi-Fi感知技术的数据采集提供了一种创新且可行的解决方案。
- Wi-Fi感知 /
- 时间编码超表面 /
- 运动特征生成 /
- 数据集构建 /
- LeNet分类网络
Abstract: With the widespread application of Wi-Fi sensing technology in intelligent health monitoring, constructing high-quality perception datasets has become a key challenge. Particularly in monitoring abnormal behaviors, such as falls, traditional methods rely on repeated human experiments, which not only poses safety risks but also raises ethical concerns. To address these issues, this paper proposes a time-domain digital coding metasurface-assisted data acquisition method. By simulating the Doppler effect and micro-Doppler characteristics of the human body, the time-domain digital coding metasurface can effectively replace human experiments and assist in constructing Wi-Fi sensing datasets. To verify the feasibility of this method, we develop a time-domain digital coding metasurface with 0°–360° full-phase modulation capability. Experimental results show that the signals generated by the metasurface retain the motion characteristics of the human body, complement real samples, reduce the complexity of data collection, and finally improve the monitoring accuracy of the classification model significantly. This method provides an innovative and feasible solution for data acquisition for Wi-Fi sensing technology.
- Wi-Fi sensing /
- Time-domain digital coding metasurface /
- Motion feature generation /
- Dataset construction /
- LeNet-based classification network

HTML全文

图 1 基于时间编码数字超表面的人体跌倒行为特征模拟的示意图

Figure 1. Schematic diagram of human fall behavior feature simulation based on time-domain digital coding metasurface

下载: 全尺寸图片幻灯片

图 2 时间编码超表面的结构及其电磁特性

Figure 2. Structure and electromagnetic characteristics of time-domain digital coding metasurface

下载: 全尺寸图片幻灯片

图 3 3组实验的场景构建

Figure 3. Scene construction of three experimental groups

下载: 全尺寸图片幻灯片

图 4 LeNet网络模型架构

Figure 4. LeNet network architecture

下载: 全尺寸图片幻灯片

图 5 5类动作(分别对应跌倒、跑近、跑远、走近、走远)的时频分析结果

Figure 5. Time-frequency analysis results of five types of actions (corresponding to falling down, running closer, running away, approaching and walking away respectively)

下载: 全尺寸图片幻灯片

图 6 时间编码超表面生成运动特征信号的质量检测

Figure 6. Quality detection of motion feature signals generated by time-encoding metasurface

下载: 全尺寸图片幻灯片

参考文献(38)

[1]	REN Yili, WANG Yichao, CHEN Yingying, et al. A vision-based approach for commodity WiFi sensing[C]. The 20th ACM Conference on Embedded Networked Sensor Systems, Boston, USA, 2022: 800–801. doi: 10.1145/3560905.3568068.
[2]	ZHANG Jie, TANG Zhanyong, LI Meng, et al. CrossSense: Towards cross-site and large-scale WiFi sensing[C]. The 24th Annual International Conference on Mobile Computing and Networking, New Delhi, India, 2018: 305–320. doi: 10.1145/3241539.3241570.
[3]	MA Yongsen, ZHOU Gang, and WANG Shuangquan. WiFi sensing with channel state information: A survey[J]. ACM Computing Surveys (CSUR), 2020, 52(3): 46. doi: 10.1145/3310194.
[4]	JIANG Hongbo, CAI Chao, MA Xiaoqiang, et al. Smart home based on WiFi sensing: A survey[J]. IEEE Access, 2018, 6: 13317–13325. doi: 10.1109/ACCESS.2018.2812887.
[5]	SUN Yimiao, HE Yuan, ZHANG Jiacheng, et al. BIFROST: Reinventing WiFi signals based on dispersion effect for accurate indoor localization[C]. The 21st ACM Conference on Embedded Networked Sensor Systems, Istanbul, Turkiye, 2023: 376–389. doi: 10.1145/3625687.3625786.
[6]	CHEN Yulong, GUO Junchen, SUN Yimiao, et al. ElaSe: Enabling real-time elastic sensing resource scheduling in 5G vRAN[C]. 2024 IEEE/ACM 32nd International Symposium on Quality of Service (IWQoS), Guangzhou, China, 2024: 1–10. doi: 10.1109/IWQoS61813.2024.10682934.
[7]	MONJUR M, LIU Jia, XU Jingye, et al. Data distribution dynamics in real-world WiFi-based patient activity monitoring for home healthcare[C]. 2024 IEEE 12th International Conference on Healthcare Informatics (ICHI), Orlando, USA, 2024: 228–233. doi: 10.1109/ICHI61247.2024.00037.
[8]	CHEN H H, LIN Chilun, and CHANG C H. WiFi-based detection of human subtle motion for health applications[J]. Bioengineering, 2023, 10(2): 228. doi: 10.3390/bioengineering10020228.
[9]	GU Zhihao, HE Taiwei, WANG Ziqi, et al. Device-free human activity recognition based on dual-channel transformer using WiFi signals[J]. Wireless Communications and Mobile Computing, 2022, 2022(1): 4598460. doi: 10.1155/2022/4598460.
[10]	WANG Hao, ZHANG Daqing, MA Junyi, et al. Human respiration detection with commodity WiFi devices: Do user location and body orientation matter?[C]. 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing, Heidelberg, Germany, 2016: 25–36. doi: 10.1145/2971648.2971744.
[11]	SUN Xian, WANG Peijin, YAN Zhiyuan, et al. FAIR1M: A benchmark dataset for fine-grained object recognition in high-resolution remote sensing imagery[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2022, 184: 116–130. doi: 10.1016/j.isprsjprs.2021.12.004.
[12]	ZHANG Wei, TANG Ping, and ZHAO Lijun. Remote sensing image scene classification using CNN-CapsNet[J]. Remote Sensing, 2019, 11(5): 494. doi: 10.3390/rs11050494.
[13]	IGUAL R, MEDRANO C, and PLAZA I. A comparison of public datasets for acceleration-based fall detection[J]. Medical Engineering & Physics, 2015, 37(9): 870–878. doi: 10.1016/j.medengphy.2015.06.009.
[14]	KWOLEK B and KEPSKI M. Human fall detection on embedded platform using depth maps and wireless accelerometer[J]. Computer Methods and Programs in Biomedicine, 2014, 117(3): 489–501. doi: 10.1016/j.cmpb.2014.09.005.
[15]	MA Chao, SHIMADA A, UCHIYAMA H, et al. Fall detection using optical level anonymous image sensing system[J]. Optics & Laser Technology, 2019, 110: 44–61. doi: 10.1016/j.optlastec.2018.07.013.
[16]	LIU Mengwei, ZHANG Yujia, WANG Jiachuang, et al. A star-nose-like tactile-olfactory bionic sensing array for robust object recognition in non-visual environments[J]. Nature Communications, 2022, 13(1): 79. doi: 10.1038/s41467-021-27672-z.
[17]	HAO Xuejie, LIU Lu, YANG Rongjin, et al. A review of data augmentation methods of remote sensing image target recognition[J]. Remote Sensing, 2023, 15(3): 827. doi: 10.3390/rs15030827.
[18]	SHORTEN C and KHOSHGOFTAAR T M. A survey on image data augmentation for deep learning[J]. Journal of Big Data, 2019, 6(1): 60. doi: 10.1186/s40537-019-0197-0.
[19]	DUONG H T and NGUYEN-THI T A N. A review: Preprocessing techniques and data augmentation for sentiment analysis[J]. Computational Social Networks, 2021, 8(1): 1. doi: 10.1186/s40649-020-00080-x.
[20]	GAO Xin, DENG Fang, and YUE Xianghu. Data augmentation in fault diagnosis based on the Wasserstein generative adversarial network with gradient penalty[J]. Neurocomputing, 2020, 396: 487–494. doi: 10.1016/j.neucom.2018.10.109.
[21]	LAN Lan, YOU Lei, ZHANG Zeyang, et al. Generative adversarial networks and its applications in biomedical informatics[J]. Frontiers in Public Health, 2020, 8: 164. doi: 10.3389/fpubh.2020.00164.
[22]	WANG Siran, CHEN Mingzheng, KE Junchen, et al. Asynchronous space-time-coding digital metasurface[J]. Advanced Science, 2022, 9(24): 2200106. doi: 10.1002/advs.202200106.
[23]	ZHOU Qunyan, DAI Junyan, FANG Zuqi, et al. Generalized high-precision and wide-angle DOA estimation method based on space-time-coding digital metasurfaces[J]. IEEE Internet of Things Journal, 2024, 11(23): 38196–38206. doi: 10.1109/JIOT.2024.3445451.
[24]	ZHOU Qunyan, WU Junwei, WANG Siran, et al. Two-dimensional direction-of-arrival estimation based on time-domain-coding digital metasurface[J]. Applied Physics Letters, 2022, 121(18): 181702. doi: 10.1063/5.0124291.
[25]	CUI Tiejun, QI Meiqing, WAN Xiang, et al. Coding metamaterials, digital metamaterials and programmable metamaterials[J]. Light: Science & Applications, 2014, 3(10): e218. doi: 10.1038/lsa.2014.99.
[26]	LI Lianlin, CUI Tiejun, JI Wei, et al. Electromagnetic reprogrammable coding-metasurface holograms[J]. Nature Communications, 2017, 8(1): 197. doi: 10.1038/s41467-017-00164-9.
[27]	ZHAO Jie, YANG Xi, DAI Junyan, et al. Programmable time-domain digital-coding metasurface for non-linear harmonic manipulation and new wireless communication systems[J]. National Science Review, 2019, 6(2): 231–238. doi: 10.1093/nsr/nwy135.
[28]	DAI Junyan, YANG Liuxi, KE Junchen, et al. High-efficiency synthesizer for spatial waves based on space-time-coding digital metasurface[J]. Laser & Photonics Reviews, 2020, 14(6): 1900133. doi: 10.1002/lpor.201900133.
[29]	LI Shiyuan, WANG Jianyang, FANG Xinyu, et al. Jamming of ISAR imaging with time-modulated metasurface partially covered on targets[J]. IEEE Antennas and Wireless Propagation Letters, 2023, 22(2): 372–376. doi: 10.1109/LAWP.2022.3212923.
[30]	KE Junchen, CHEN Xiangyu, TANG Wankai, et al. Space-frequency-polarization-division multiplexed wireless communication system using anisotropic space-time-coding digital metasurface[J]. National Science Review, 2022, 9(11): nwac225. doi: 10.21203/rs.3.rs-1509959/v1.
[31]	WANG Siran, DAI Junyan, ZHOU Qunyan, et al. Manipulations of multi-frequency waves and signals via multi-partition asynchronous space-time-coding digital metasurface[J]. Nature Communications, 2023, 14(1): 5377. doi: 10.1038/s41467-023-41031-0.
[32]	KE Junchen, DAI Junyan, ZHANG Junwei, et al. Frequency-modulated continuous waves controlled by space-time-coding metasurface with nonlinearly periodic phases[J]. Light: Science & Applications, 2022, 11(1): 273. doi: 10.1038/s41377-022-00973-8.
[33]	WANG Siran, DAI Junyan, KE Junchen, et al. Radar micro-Doppler signature generation based on time-domain digital coding metasurface[J]. Advanced Science, 2024, 11(19): 2306850. doi: 10.1002/advs.202306850.
[34]	HE Yuan, ZHANG Jia, XI Rui, et al. Detection and identification of non-cooperative UAV using a COTS mmWave radar[J]. ACM Transactions on Sensor Networks, 2024, 20(2): 44. doi: 10.1145/3638767.
[35]	CHEN Yande, HE Yuan, SUN Yimiao, et al. mmTAI: Biometrics-assisted multi-person tracking with mmWave radar[C]. 2024 IEEE 30th International Conference on Parallel and Distributed Systems (ICPADS), Belgrade, Serbia, 2024: 26–33. doi: 10.1109/ICPADS63350.2024.00014.
[36]	ZHANG Jia, XI Rui, HE Yuan, et al. A survey of mmWave-based human sensing: Technology, platforms and applications[J]. IEEE Communications Surveys & Tutorials, 2023, 25(4): 2052–2087. doi: 10.1109/COMST.2023.3298300.
[37]	JAGANATHAN D, BALSUBRAMANIAM S, SURESHKUMAR V, et al. Concatenated modified LeNet approach for classifying pneumonia images[J]. Journal of Personalized Medicine, 2024, 14(3): 328. doi: 10.3390/jpm14030328.
[38]	TANG Chong, VISHWAKARMA S, LI Wenda, et al. Augmenting experimental data with simulations to improve activity classification in healthcare monitoring[C]. 2021 IEEE Radar Conference, Atlanta, USA, 2021: 1–6. doi: 10.1109/RadarConf2147009.2021.9455314.