BS-Breath: Respiration Sensing with Cell-free Massive MIMO

2025-02-17 · Haoqiu Xiong, Robbert Beerten, Zhuangzhuang Cui, Yang Miao, Sofie Pollin

This paper demonstrates the feasibility of respiration pattern estimation utilizing a communication-centric cellfree massive MIMO OFDM Base Station (BS). The sensing target is typically positioned near the User Equipment (UE), which transmits uplink pilots to the BS. Our results demonstrate the potential of massive MIMO systems for accurate and reliable vital sign estimation. Initially, we adopt a single antenna sensing solution that combines multiple subcarriers and a breathing projection to align the 2D complex breathing pattern to a single displacement dimension. Then, Weighted Antenna Combining (WAC) aggregates the 1D breathing signals from multiple antennas. The results demonstrate that the combination of space-frequency resources specifically in terms of subcarriers and antennas yields higher accuracy than using only a single antenna or subcarrier. Our results significantly improved respiration estimation accuracy by using multiple subcarriers and antennas. With WAC, we achieved an average correlation of 0.8 with ground truth data, compared to 0.6 for single antenna or subcarrier methods, a 0.2 correlation increase. Moreover, the system produced perfect breathing rate estimates. These findings suggest that the limited bandwidth (18 MHz in the testbed) can be effectively compensated by utilizing spatial resources, such as distributed antennas.

📄 PDF Abstract BibTeX arXiv:2502.12114

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

BASE 설명 없음

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

ADOPT Please enter a description about the method here

Noncontact Respiratory Anomaly Detection Using Infrared Light-Wave Sensing

2023-01-09 · Md Zobaer Islam, Brenden Martin, Carly Gotcher, Tyler Martinez 외

Human respiratory rate and its pattern convey essential information about the physical and psychological states of the subject. Abnormal breathing can indicate fatal health issues leading to further diagnosis and treatme…

Anomaly Detection

A Deep Learning Framework using Passive WiFi Sensing for Respiration Monitoring

2017-04-19 · U. M. Khan, Z. Kabir, S. A. Hassan, S. H. Ahmed

This paper presents an end-to-end deep learning framework using passive WiFi sensing to classify and estimate human respiration activity. A passive radar test-bed is used with two channels where the first channel provide…

Activity Recognition Deep Learning Human Activity Recognition Time Series+1

MobiVital: Self-supervised Time-series Quality Estimation for Contactless Respiration Monitoring Using UWB Radar

2025-03-14 · Ziqi Wang, Derek Hua, Wenjun Jiang, Tianwei Xing 외

Respiration waveforms are increasingly recognized as important biomarkers, offering insights beyond simple respiration rates, such as detecting breathing irregularities for disease diagnosis or monitoring breath patterns…

Time Series

Evolutionary Optimization of 1D-CNN for Non-contact Respiration Pattern Classification

2023-12-20 · Md Zobaer Islam, Sabit Ekin, John F. O'Hara, Gary Yen

In this study, we present a deep learning-based approach for time-series respiration data classification. The dataset contains regular breathing patterns as well as various forms of abnormal breathing, obtained through n…

Anomaly Detection Classification Deep Learning Time Series+1

Respiratory Anomaly Detection using Reflected Infrared Light-wave Signals

2023-11-02 · Md Zobaer Islam, Brenden Martin, Carly Gotcher, Tyler Martinez 외

In this study, we present a non-contact respiratory anomaly detection method using incoherent light-wave signals reflected from the chest of a mechanical robot that can breathe like human beings. In comparison to existin…