Respiration sensing improves with new antenna adaptation method
SR-TTA: Spatial-Redundancy Test-Time Adaptation for Interference-Robust Respiration Sensing
Machine Learning
Summary
Measuring breathing using antennas in 6G networks is tricky when other motions interfere at similar frequencies. The authors show that a new approach using learned antenna weights combined with a special way to adapt these weights during use can filter out interference without needing labeled data. Their method keeps breathing monitoring accurate even in challenging conditions and works well on real recordings when combined with a one-time calibration. This technology could fit into future 6G network setups to provide reliable respiration sensing.
What this means in practice
- •For telecom network engineers: Integrate interference-robust respiration sensing into cell-free massive MIMO base stations using label-free adaptation methods during deployment.
- •For medical device developers: Develop non-contact respiratory monitoring systems leveraging antenna arrays and adaptive signal fusion resistant to motion interferences.$Commercial implications: Enables improved contactless breathing monitors that function reliably in real-world environments, appealing for healthcare product development.
Authors
Jingyuan Liu, Zheng Chang, Haoqiu Xiong, Zhuangzhuang Cui, Sofie Pollin
Abstract
Future 6G networks aim to expose sensing as a native service by reusing communication infrastructure. We study respiration sensing on a cell-free massive multiple-input multiple-output (MIMO) base station, where a 64-antenna channel must be fused into a breathing waveform. The state-of-the-art hand-crafted fusion is near-optimal in benign conditions. It collapses, however, under strong in-band motion interference, whose frequency falls inside the respiration band. We show that a learned complex-weight beamformer recovers respiration by spatial nulling, and that the remaining gap to a per-recording oracle can be closed at deployment by label-free test-time adaptation. Crucially, we identify which label-free signal makes this work. Frequency- and variance-based criteria cannot separate an in-band interferer from breathing. Our spatial-redundancy test-time adaptation (SR-TTA), which maximizes consistency across random antenna subsets under an out-of-band spectral veto, preserves benign performance in our tests. The respiration-rate error drops from 5.8 to 0.8 breaths per minute (bpm) under simulated in-band interference, and the pipeline maps onto the Open Radio Access Network (O-RAN) architecture as O-RAN distributed-unit (O-DU) range-gating, an adaptation xApp, and a calibration rApp. On real testbed recordings, a one-time cross-subject calibration plus SR-TTA reduces failures from 47% to 7%, drawing level with the hand-crafted combiner using label-free test-time adaptation.