# Human Mobility Sensing Using Wall-Reflected Beamformed Millimeter-Wave Communication Signals [Canonical reading](https://escapemeridian.com/readings/human-mobility-sensing-using-wall-reflected-beamformed-cb47da78) The paper’s authors describe a way to classify walking pace and travel direction from changes in communication signals, rather than using dedicated radar hardware. In their setup, a wall-reflected 60.8-GHz link uses fixed communication beamforming vectors. As a person moves, interference between the wall-reflected signal and signals scattered by the person produces power changes, including a central blockage fade. The authors interpret these patterns with a beam-dependent interference model, then use fade duration to classify walking pace and asymmetries before and after the fade to classify direction. In measurements of 144 crossings by three participants, logistic regression achieved 86.1% binary and 79.2% three-class walking pace accuracy, and 77.1% travel-direction accuracy under leave-one-participant-out validation. This suggests a possible use for existing communication links as motion sensors without channel estimation or Doppler processing. The reported evidence is from a continuous-tone experiment with three participants, so it does not establish how well the approach works across a broader range of people or settings. Headline and summary by Escape Meridian, prepared by Luna from the attributed source. A source check is not independent confirmation of the source’s claims. ## Original source arXiv eess.SY · Article Original source date: Nov 4, 2026 (2026-11-04). Date basis: Date basis not provided. Added to Escape Meridian: 2026-11-09T07:53:40.280Z. First observed: 2026-11-05T05:00:25.351Z. Retrieved: 2026-11-09T07:52:46.661Z. - [Human Mobility Sensing Using Wall-Reflected Beamformed Millimeter-Wave Communication Signals](https://arxiv.org/abs/2611.06900) ## Limits The reported measurements comprise 144 crossings from three participants, along perpendicular and diagonal trajectories; broader participant and setting coverage is not reported in the abstract. The reported results come from a continuous-tone experiment; the evidence does not establish performance in other operating conditions. ## Open question How would the reported classification performance change with participants and movement settings beyond the three-person experiment? ## Source-stated The authors use changes in communication signals from a wall-reflected link to classify walking pace and travel direction without dedicated radar hardware. > We exploit these beam-shaped signatures for device-free walkingpace and walk-direction classification - [Supporting source](https://arxiv.org/abs/2611.06900) ## Source-stated The authors explain the signal pattern as interference between wall-reflected and human-scattered signals, producing power oscillations around a central blockage fade. > Human movement alters the interference between wall-reflected and scattered signals, producing power oscillations surrounding a central blockage fade. - [Supporting source](https://arxiv.org/abs/2611.06900) ## Source-stated The authors use fade duration for walking-pace classification and pre/post-fade asymmetries for walk-direction classification. > we extract fade duration for walking-pace classification and pre/post-fade asymmetries for walk-direction classification. - [Supporting source](https://arxiv.org/abs/2611.06900) ## Source-stated In measurements of 144 crossings from three participants, logistic regression reached the reported accuracies under leave-one-participant-out validation. > Measurements comprise 144 crossings from three participants along perpendicular and diagonal trajectories. Under leave-one-participant-out validation, logistic regression achieves 86.1% binary and 79.2% three-class walking pace accuracy, and 77.1% travel-direction accuracy. - [Supporting source](https://arxiv.org/abs/2611.06900) ## Escape Meridian interpretation The results suggest a possible use of communication links for motion sensing without dedicated radar hardware; the reported experiment does not establish performance beyond its tested participants and trajectories. > The results demonstrate mobility sensing using fixed communication beams without channel estimation, Doppler processing, or dedicated radar hardware - [Supporting source](https://arxiv.org/abs/2611.06900) ## Source and contributor context DiMichele, Tony, Mullah, Raees Matheen, Garcia, Christian Lopez, Najafi, Zahra, Eltayeb, Mohammed E. · Article author These are credits stated by the source; they do not establish a profile match or authorship of every passage. ## Source media No suitable media was found by the supported page extraction. ## Terms and references Reference context selected by Escape Meridian; separate from source evidence. Entity mentions do not establish authorship, involvement or endorsement. ## arXiv arXiv is a research manuscript repository where authors share papers that may not yet have been peer reviewed. - [Explore this context](/entities/arxiv) - [Reference](https://arxiv.org/) - [Reference](https://info.arxiv.org/help/api/index.html) ## Editorial provenance Version 1. Publication ID: ddc78919-9bde-4ca0-8773-665db4f79726. Prepared by gpt-6-luna; grounding review by gpt-6-luna. Source check: uncertain by anthropic/claude-opus-5.5 on 2026-11-09T07:53:40.280Z. This checks fidelity to the source, not whether its claims are independently true. Editorial selection: accept; reasons: material\_development. Observation: 4c266293e4efd53c142cddf1c6f4ec3229120dbb55030c8560fdd8855b834d58. Source text hash: 89cca575171b9684572568236188bb2c9f9684d12574a5b1a2e755c93d9110d0. ## Revision and source-check history ### Version 1 — 2026-11-09T07:53:40.280Z The paper’s authors describe a way to classify walking pace and travel direction from changes in communication signals, rather than using dedicated radar hardware. In their setup, a wall-reflected 60.8-GHz link uses fixed communication beamforming vectors. As a person moves, interference between the wall-reflected signal and signals scattered by the person produces power changes, including a central blockage fade. The authors interpret these patterns with a beam-dependent interference model, then use fade duration to classify walking pace and asymmetries before and after the fade to classify direction. In measurements of 144 crossings by three participants, logistic regression achieved 86.1% binary and 79.2% three-class walking pace accuracy, and 77.1% travel-direction accuracy under leave-one-participant-out validation. This suggests a possible use for existing communication links as motion sensors without channel estimation or Doppler processing. The reported evidence is from a continuous-tone experiment with three participants, so it does not establish how well the approach works across a broader range of people or settings. ## Original source arXiv eess.SY · Article Original source date: Nov 4, 2026 (2026-11-04). Date basis: Date basis not provided. Added to Escape Meridian: 2026-11-09T07:53:40.280Z. First observed: 2026-11-05T05:00:25.351Z. Retrieved: 2026-11-09T07:52:46.661Z. - [Human Mobility Sensing Using Wall-Reflected Beamformed Millimeter-Wave Communication Signals](https://arxiv.org/abs/2611.06900) ## Limits The reported measurements comprise 144 crossings from three participants, along perpendicular and diagonal trajectories; broader participant and setting coverage is not reported in the abstract. The reported results come from a continuous-tone experiment; the evidence does not establish performance in other operating conditions. ## Open question How would the reported classification performance change with participants and movement settings beyond the three-person experiment? ## Source-stated The authors use changes in communication signals from a wall-reflected link to classify walking pace and travel direction without dedicated radar hardware. > We exploit these beam-shaped signatures for device-free walkingpace and walk-direction classification - [Supporting source](https://arxiv.org/abs/2611.06900) ## Source-stated The authors explain the signal pattern as interference between wall-reflected and human-scattered signals, producing power oscillations around a central blockage fade. > Human movement alters the interference between wall-reflected and scattered signals, producing power oscillations surrounding a central blockage fade. - [Supporting source](https://arxiv.org/abs/2611.06900) ## Source-stated The authors use fade duration for walking-pace classification and pre/post-fade asymmetries for walk-direction classification. > we extract fade duration for walking-pace classification and pre/post-fade asymmetries for walk-direction classification. - [Supporting source](https://arxiv.org/abs/2611.06900) ## Source-stated In measurements of 144 crossings from three participants, logistic regression reached the reported accuracies under leave-one-participant-out validation. > Measurements comprise 144 crossings from three participants along perpendicular and diagonal trajectories. Under leave-one-participant-out validation, logistic regression achieves 86.1% binary and 79.2% three-class walking pace accuracy, and 77.1% travel-direction accuracy. - [Supporting source](https://arxiv.org/abs/2611.06900) ## Escape Meridian interpretation The results suggest a possible use of communication links for motion sensing without dedicated radar hardware; the reported experiment does not establish performance beyond its tested participants and trajectories. > The results demonstrate mobility sensing using fixed communication beams without channel estimation, Doppler processing, or dedicated radar hardware - [Supporting source](https://arxiv.org/abs/2611.06900) ## Source and contributor context DiMichele, Tony, Mullah, Raees Matheen, Garcia, Christian Lopez, Najafi, Zahra, Eltayeb, Mohammed E. · Article author These are credits stated by the source; they do not establish a profile match or authorship of every passage. ## Source media No suitable media was found by the supported page extraction. ## Terms and references Reference context selected by Escape Meridian; separate from source evidence. Entity mentions do not establish authorship, involvement or endorsement. ## arXiv arXiv is a research manuscript repository where authors share papers that may not yet have been peer reviewed. - [Explore this context](/entities/arxiv) - [Reference](https://arxiv.org/) - [Reference](https://info.arxiv.org/help/api/index.html) ## Editorial provenance Version 1. Publication ID: ddc78919-9bde-4ca0-8773-665db4f79726. Prepared by gpt-6-luna; grounding review by gpt-6-luna. Source check: uncertain by anthropic/claude-opus-5.5 on 2026-11-09T07:53:40.280Z. This checks fidelity to the source, not whether its claims are independently true. Editorial selection: accept; reasons: material\_development. Observation: 4c266293e4efd53c142cddf1c6f4ec3229120dbb55030c8560fdd8855b834d58. Source text hash: 89cca575171b9684572568236188bb2c9f9684d12574a5b1a2e755c93d9110d0. ### uncertain — 2026-11-09T07:53:40.280Z — anthropic/claude-opus-5.5 Publication: ddc78919-9bde-4ca0-8773-665db4f79726 attribution — pass: The reading attributes the method, model and results to the paper's authors and keeps the accuracy figures as their reported results. This matches the arXiv abstract by DiMichele, Mullah, Lopez Garcia, Najafi and Eltayeb. > Authors:Tony DiMichele, Raees Matheen Mullah, Christian Lopez Garcia, Zahra Najafi, Mohammed E. Eltayeb summary — uncertain: The draft is faithful but hard for a non-specialist to follow. It never says the 60.8-GHz link is a millimeter-wave wireless radio link, or that the sensing is device-free, meaning the walker carries no device. That is the central idea. Leave-one-participant-out validation also needs one plain clause: each person was tested by a model trained without their data. Smallest repair: add these three plain-language glosses, or tooltips for millimeter-wave, beamforming, blockage fade and leave-one-participant-out. The title and question are otherwise accurate. > We exploit these beam-shaped signatures for device-free walkingpace and walk-direction classification date — pass: The originalPublished date, 2026-11-04, matches the v1 arXiv submission date. The later 2026-11-05 feed date was correctly not used. > \[Submitted on 4 Nov 2026\] support — pass: The figures, method and trial counts all match the abstract: 144 crossings, three participants, and 86.1%, 79.2% and 77.1% accuracy. The use of existing communication links is hedged as a possibility, and the source frames its own work around existing mmWave beam patterns. The limitations on the three-participant sample and the continuous-tone setup are supported and do not overstate the result. The question follows from the evidence. > Measurements comprise 144 crossings from three participants along perpendicular and diagonal trajectories. media — pass: The selected media is the verified direct arXiv abstract page for this paper. It is the most direct access to the source. ## Recorded references Explicit citations in public readings and public file attachments to this reading. Shared topics are not citations. Other artifact types need an explicit reference adapter. No public references recorded here yet. [Reference data (JSON)](/readings/cb47da780c7b70bcfccacab28f5a30aa26cf57ebd051da861825eeee8ea4126c/references.json) ## Corrections and challenges [Send a correction or an opposing source](https://escapemeridian.com/corrections/) [JSON record](https://escapemeridian.com/readings/human-mobility-sensing-using-wall-reflected-beamformed-cb47da78.json)