基于经验模态分解的加权呼吸波形重构算法

doi:10.11996/JG.j.2095-302X.2025040847

图学学报 ›› 2025, Vol. 46 ›› Issue (4): 847-854.DOI: 10.11996/JG.j.2095-302X.2025040847

• 计算机图形学与虚拟现实 • 上一篇下一篇

基于经验模态分解的加权呼吸波形重构算法

郭林林(), 姚敏, 张文清, 张佳, 孙建德()

山东师范大学信息科学与工程学院，山东济南 250358

收稿日期:2024-09-30 修回日期:2025-05-29 出版日期:2025-08-30 发布日期:2025-08-11
通讯作者:孙建德(1978-)，男，教授，博士。主要研究方向为多媒体信息处理、分析、理解及应用。E-mail：jiandesun@hotmail.com
第一作者:郭林林(1988-)，女，讲师，博士。主要研究方向为新一代信息技术下的智能无线感知技术。E-mail：linlin_teresa@sdnu.edu.cn
基金资助:
山东省自然科学基金青年面上专项(ZR2024QF275);济南市“新高校20条”-科研带头人工作室项目(2021GXRC081)

Weighted respiration waveform reconstruction algorithm based on empirical modal decomposition

GUO Linlin(), YAO Min, ZHANG Wenqing, ZHANG Jia, SUN Jiande()

School of Information Science and Engineering, Shandong Normal University, Jinan Shandong 250358, China

Received:2024-09-30 Revised:2025-05-29 Published:2025-08-30 Online:2025-08-11
First author：GUO Linlin (1988-), lecturer, Ph.D. Her main research interests cover intelligent wireless sensing technologies in the next-generation IT. E-mail：linlin_teresa@sdnu.edu.cn
Supported by:
Natural Science Foundation of Shandong Province(ZR2024QF275);Jinan City’s “New Higher Education Institutions 20 Measures” Funding Project - Research Leader’s Studio(2021GXRC081)

摘要/Abstract

摘要：

基于Wi-Fi信号的呼吸速率估计技术凭借其非接触式的优势吸引了学术界和工业界的广泛关注。然而，如何提取高质量呼吸波形确保呼吸速率估计的精度是一直困扰研究人员的难题。提出了一种基于经验模态分解(EMD)的加权呼吸波形重构算法(WEMD)，旨在提高不同环境下个体呼吸速率估计的精准度和鲁棒性。首先，利用呼吸信噪比(BNR)和I/O分解及投影方法，筛选出周期性较好的子载波并生成多条呼吸波形。其次，通过主成分分析(PCA)技术校准呼吸波形、经验模态分解方法分解和估计不同频率分量与原始呼吸模式的相关性。最后，通过设计的自适应加权算法对不同呼吸波形进行重构融合实现高精准的个体呼吸速率估计。实验结果表明，WEMD算法在4个室内环境下获得平均94%以上的人体呼吸速率估计精准度。该方法不仅有效地解决低质量Wi-Fi数据对呼吸速率估计精度的影响，而且也能够精准估计不均匀呼吸的速率，实现在不同环境下高精度地监测人体呼吸，以保证估计误差在10%以内。

关键词: 无线感知, 信道状态信息, 经验模态分解, 呼吸波形重构, 呼吸速率估计

Abstract:

Respiration rate estimation based on Wi-Fi signals has garnered significant attention from academic and industrial communities due to its non-contact advantage. However, extracting high-quality respiration waveforms to ensure accurate respiration rate estimation has been a persistent challenge for researchers. In this paper, a weighted respiration waveform reconstruction algorithm based on empirical mode decomposition (EMD), referred to as (weighted empirical mode decomposition) WEMD, was proposed to improve the accuracy and robustness of respiration rate estimation under different environments. First, subcarriers with better periodicity were selected using breathing-to-noise ratio (BNR) and I/O decompose methods, and various respiration waveforms were generated. Second, principal component analysis (PCA) was applied to calibrate respiration waveforms, and EMD was employed to decompose respiration waveforms. Finally, an adaptive weighting mechanism was designed to reconstruct them by estimating the correlation between different frequency components and the original respiratory pattern. Experimental results demonstrated that the WEMD algorithm achieved an average respiration estimation accuracy of over 94% in four indoor experimental environments. The WEMD algorithm not only effectively addressed the impact of the low-quality Wi-Fi data on personal respiration estimation, but also accurately estimated irregular respiration rates, achieving high-precision respiratory rate monitoring across various environments, with an error below 10%.

Key words: wireless sensing, channel state information, empirical mode decomposition, respiratory waveform reconstruction, respiration rate estimation

中图分类号:

TP391
TN92

郭林林, 姚敏, 张文清, 张佳, 孙建德. 基于经验模态分解的加权呼吸波形重构算法[J]. 图学学报, 2025, 46(4): 847-854.

GUO Linlin, YAO Min, ZHANG Wenqing, ZHANG Jia, SUN Jiande. Weighted respiration waveform reconstruction algorithm based on empirical modal decomposition[J]. Journal of Graphics, 2025, 46(4): 847-854.

图/表 15

表1 呼吸感知的相关工作

Table 1 Related works on respiration sensing

文献	识别技术	年份
文献[1-2]	Wi-Fi	2021, 2022
文献[3]	Wi-Fi	2024
文献[4]	Wi-Fi	2024
文献[5]	Wi-Fi	2023
文献[6-7]	Wi-Fi	2022, 2024
文献[8]	Acoustic	2023
文献[9-10]	Wi-Fi	2018
文献[11-13]	RF, Wi-Fi	2015, 2017 2018
文献[14-20]	Wi-Fi	2016—2019, 2021, 2022

图1 室内无线信号的传播路径

Fig. 1 Propagation path of indoor radio signals

图2 人体呼吸速率估计框架

Fig. 2 Framework for personal respiration estimation

图3 原始CSI和CSI Ratio ((a) 天线1接收的原始CSI振幅；(b) 天线2接收的原始CSI振福；(c) 天线1与天线2比值为CSI Ratio)

Fig. 3 Raw CSI and CSI Ratio ((a) Raw CSI amplitude from the first antenna; (b) Raw CSI amplitude from the second antenna; (c) CSI Ratio: the rate and the first antenna and the second antenna)

图4 数据预处理((a) 原始CSI Ratio；(b) 去噪CSI Ratio)

Fig. 4 Data preprocessing ((a) Raw CSI Ratio; (b) Denoised CSI Ratio)

图5 子载波选择((a) 30条子载波的CSI Ratio；(b) 选择4条子载波的CSI Ratio)

Fig. 5 Subcarrier selection ((a) CSI Ratio of thirty subcarriers; (b) CSI Ratio of the selected four subcarriers)

图6 单个子载波投影示例((a) 选定的单个子载波；(b) 单个子载波投影生成多条呼吸模式)

Fig. 6 Example of a single subcarrier projection ((a) Selected one subcarrier; (b) Multiple respiration pattern produced by the selected subcarrier)

图7 呼吸模式组合

Fig. 7 Combination of respiration patterns

图8 PCA校准呼吸波形

Fig. 8 PCA calibrates respiration waveform

图9 呼吸波形重构

Fig. 9 Respiration Waveform reconstruction

图10 呼吸波形融合

Fig. 10 Respiration Waveform fusion

图11 自相关结果

Fig. 11 Autocorrelation results

图12 实验设备((a) 接收端；(b) 命令配置界面；(c) 可视化界面)

Fig. 12 Experimental equipment ((a) Receiver; (b) Command configuration interface; (c) Visual interface for Wi-Fi CSI)

图13 实验环境((a) 走廊；(b) 会议室；(c) 办公室；(d) 卧室)

Fig. 13 Experimental environment ((a) Corridor; (b) Meeting room; (c) Office; (d) Bedroom)

图14 3种呼吸速率估计方法

Fig. 14 Comparison of three respiration estimation methods ((a) MRC; (b) MRC-PCA; (c) WEMD)

参考文献 26

[1]	ZHANG F, WU C S, WANG B B, et al. SMARS: sleep monitoring via ambient radio signals[J]. IEEE Transactions on Mobile Computing, 2021, 20(1): 217-231.
[2]	ZENG X L, WANG B B, WU C S, et al. Intelligent Wi-Fi based child presence detection system[C]// 2022 IEEE International Conference on Acoustics, Speech and Signal Processing. New York: IEEE Press, 2022: 11-15.
[3]	XIE X C, ZHANG D H, LI Y D, et al. Robust WiFi respiration sensing in the presence of interfering individual[J]. IEEE Transactions on Mobile Computing, 2024, 23(8): 8447-8462.
[4]	ZHANG Y W, HAN F Y, YANG P L, et al. Wi-Cyclops: room-scale WiFi sensing system for respiration detection based on single-antenna[J]. ACM Transactions on Sensor Networks, 2024, 20(4): 94.
[5]	LI B F, REN Y L, WANG Y C, et al. SpaceBeat: identity-aware multi-person vital signs monitoring using commodity WiFi[J]. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, 2024, 8(3): 113.
[6]	ZHANG S J, ZHENG T Y, WANG H B, et al. Quantifying the physical separability of RF-based multi-person respiration monitoring via SINR[C]// The 20th ACM Conference on Embedded Networked Sensor Systems. New York: ACM, 2022: 47-60.
[7]	HU J Y, JIANG H B, ZHENG T Y, et al. M²-Fi: multi-person respiration monitoring via handheld WiFi devices[C]// 2024 IEEE Conference on Computer Communications. New York: IEEE Press, 2024: 1221-1230.
[8]	WU Y, LI F, XIE Y D, et al. SymListener: detecting respiratory symptoms via acoustic sensing in driving environments[J]. ACM Transactions on Sensor Networks, 2023, 19(1): 3.
[9]	LIU J, WANG Y, CHEN Y Y, et al. Tracking vital signs during sleep leveraging off-the-shelf WiFi[C]// The 16th ACM International Symposium on Mobile Ad Hoc Networking and Computing. New York: ACM, 2015: 267-276.
[10]	LIU J, CHEN Y Y, WANG Y, et al. Monitoring vital signs and postures during sleep using WiFi signals[J]. IEEE Internet of Things Journal, 2018, 5(3): 2071-2084.
[11]	YUE S C, HE H, WANG H, et al. Extracting multi-person respiration from entangled RF signals[J]. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, 2018, 2(2): 86.
[12]	ADIB F, MAO H Z, KABELAC Z, et al. Smart homes that monitor breathing and heart rate[C]// The 33rd Annual ACM Conference on Human Factors in Computing Systems. New York: ACM, 2015: 837-846.
[13]	HSU C Y, AHUJA A, YUE S C, et al. Zero-effort in-home sleep and insomnia monitoring using radio signals[J]. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, 2017, 1(3): 59.
[14]	WU D, ZENG Y W, ZHANG F S, et al. WiFi CSI-based device-free sensing: from Fresnel zone model to CSI-ratio model[J]. CCF Transactions on Pervasive Computing and Interaction, 2022, 4(1): 88-102.
[15]	YU B H, WANG Y X, NIU K, et al. WiFi-Sleep: sleep stage monitoring using commodity Wi-Fi devices[J]. IEEE Internet of Things Journal, 2021, 8(18): 13900-13913.
[16]	WANG H, ZHANG D Q, MA J Y, 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. New York: ACM, 2016: 25-36.
[17]	ZENG Y W, WU D, GAO R Y, et al. FullBreathe: full human respiration detection exploiting complementarity of CSI phase and amplitude of WiFi signals[J]. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, 2018, 2(3): 148.
[18]	LI X, ZHANG D Q, XIONG J, et al. Training-free human vitality monitoring using commodity Wi-Fi devices[J]. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, 2018, 2(3): 121.
[19]	ZHANG F S, ZHANG D Q, XIONG J, et al. From Fresnel diffraction model to fine-grained human respiration sensing with commodity Wi-Fi devices[J]. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, 2018, 2(1): 53.
[20]	ZENG Y W, WU D, XIONG J, et al. FarSense: pushing the range limit of WiFi-based respiration sensing with CSI ratio of two antennas[J]. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, 2019, 3(3): 121.
[21]	谢磊, 王楚豫, 宁静仪. 见微知著: 基于无线信号的微状态感知[J]. 中国计算机学会通讯, 2024, 20(3): 16-21.
	XIE L, WANG C Y, NING J Y. Micro state sensing based on wireless signal[J]. Communications of the CCF, 2024, 20(3): 16-21 (in Chinese).
[22]	卢洋, 陈林慧, 姜晓恒, 等. SDENet: 基于多尺度注意力质量感知的合成缺陷数据评价网络[J]. 图学学报, 2025, 46(1): 94-103. DOI
	LU Y, CHEN L H, JIANG Y H, et at. SDENet: a synthetic defect data evaluation network based on multi-scale attention quality perception[J]. Journal of Graphics, 2025, 46(1): 94-103 (in Chinese). DOI
[23]	HUANG N E, SHEN Z, LONG S R, et al. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis[J]. Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences, 1998, 454(1971): 903-995.
[24]	王欣雨, 刘慧, 朱积成, 等. 基于高低频特征分解的深度多模态医学图像融合网络[J]. 图学学报, 2024, 45(1): 65-77. DOI
	WANG X Y, LIU H, ZHU J C, et al. Deep multimodal medical image fusion network based on high-low frequency feature decomposition[J]. Journal of Graphics, 2024, 45(1): 65-77 (in Chinese). DOI
[25]	KOMATY A, BOUDRAA A O, AUGIER B, et al. EMD-based filtering using similarity measure between probability density functions of IMFs[J]. IEEE Transactions on Instrumentation and Measurement, 2014, 63(1): 27-34.
[26]	AYENU-PRAH A, ATTOH-OKINE N. A criterion for selecting relevant intrinsic mode functions in empirical mode decomposition[J]. Advances in Adaptive Data Analysis, 2010, 2(1): 1-24.

基于经验模态分解的加权呼吸波形重构算法

Weighted respiration waveform reconstruction algorithm based on empirical modal decomposition

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 15

参考文献 26

相关文章 3

编辑推荐

Metrics

本文评价

[1]	赵慧超, 胡坤, 王小超. 结合纹理复杂度与 BEMD 的灰度水印图像算法[J]. 图学学报, 2022, 43(4): 659-666.
[2]	马增强，张俊甲，王梦奇，阮婉莹. 基于改进 EEMD 和谱峭度的滚动轴承故障诊断[J]. 图学学报, 2017, 38(5): 663-669.
[3]	张晓宇，戴芳，甘明辉，王赛芳. 基于经验模态分解的图像拼接[J]. 图学学报, 2011, 32(1): 59-66.