pith. sign in

arxiv: 2603.10845 · v3 · submitted 2026-03-11 · 📡 eess.SP · cs.AI· cs.CV

Human Presence Detection via Wi-Fi Range-Filtered Doppler Spectrum on Commodity Laptops

Jessica Sanson , Rahul C. Shah , Valerio Frascolla This is my paper

Pith reviewed 2026-05-15 12:54 UTC · model grok-4.3

classification 📡 eess.SP cs.AIcs.CV
keywords human presence detectionWi-Fi sensingDoppler spectrumoccupancy detectionmonostatic sensingchannel impulse responseadaptive samplingcommodity hardware
0
0 comments X

The pith

Built-in laptop Wi-Fi detects nearby human presence using only its own signals.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper develops a technique that lets a standard laptop sense whether a person is present in its immediate area by processing its own Wi-Fi transmissions. It avoids cameras, which raise privacy problems, and external sensors, which add hardware cost and setup. The method filters Wi-Fi channel responses by distance before analyzing motion patterns and adjusts how often it samples signals based on detected activity. A sympathetic reader would see this as enabling automatic power-saving and security behaviors on everyday devices that work across rooms and laptop models without any per-device training.

Core claim

The paper claims that monostatic Wi-Fi sensing performed entirely on the built-in network interface controller of a commodity laptop can detect human presence. It does so by introducing the Range-Filtered Doppler Spectrum, which applies targeted range-area filtering to the channel impulse response before Doppler analysis, then uses temporal windows for stability. An adaptive multi-rate framework samples channel state information at 10 Hz during idle periods and 100 Hz only when motion appears. The resulting system requires no external access points, dedicated sensors, or calibration and works across varied environments and devices.

What carries the argument

Range-Filtered Doppler Spectrum (RF-DS), which performs range-area filtering in the channel impulse response domain before Doppler spectrum computation to isolate task-relevant spatial zones.

If this is right

  • Laptops can automatically manage power states based on detected occupancy without added hardware.
  • Camera-based privacy risks are eliminated for basic presence detection tasks.
  • No external network infrastructure or specialized sensors are needed for deployment.
  • The approach supports scaling to different devices and settings with zero calibration steps.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The same range-filtering idea could be tested on other Wi-Fi devices such as tablets or routers to achieve room-level sensing.
  • Operating-system integration might allow automatic screen dimming or session locking triggered by absence.
  • Combining the method with signals from nearby devices could improve robustness when single-device reflections are weak.

Load-bearing premise

Range filtering in the channel impulse response can isolate user presence from environmental reflections and clutter without any calibration or retraining for the specific room or laptop model.

What would settle it

Running the system unchanged on multiple different laptop models and in several new room layouts, then measuring whether detection accuracy falls below a practical threshold such as 80 percent true-positive rate.

Figures

Figures reproduced from arXiv: 2603.10845 by Jessica Sanson, Rahul C. Shah, Valerio Frascolla.

Figure 1
Figure 1. Figure 1: Comparison of Wi-Fi sensing systems. these approaches can achieve high detection accuracy in controlled environments, they also impose a heavy compu￾tational burden, unsuitable for continuous real-time operation on laptop CPUs. Furthermore, these models generally require extensive environment-specific training data to achieve ro￾bustness, thus limiting practical deployment. Additionally, the proposed state… view at source ↗
Figure 3
Figure 3. Figure 3: RF-DS Doppler spectra for a single range (3 m) with [PITH_FULL_IMAGE:figures/full_fig_p004_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Range and velocity tracking during the approach–leave cycle. (a) 2D FFT range–Doppler map; (b) RF-DS output. Left [PITH_FULL_IMAGE:figures/full_fig_p005_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Cross-platform HPD results: Presence, absence, ap [PITH_FULL_IMAGE:figures/full_fig_p005_5.png] view at source ↗
read the original abstract

Human Presence Detection (HPD) is key to enable intelligent power management and security features in everyday devices. In this paper we propose the first HPD solution that leverages monostatic Wi-Fi sensing and detects user position using only the built-in Wi-Fi hardware of a device, with no need for external devices, access points, or additional sensors. In contrast, existing HPD solutions for laptops require external dedicated sensors which add cost and complexity, or rely on camera-based approaches that introduce significant privacy concerns. We herewith introduce the Range-Filtered Doppler Spectrum (RF-DS), a novel Wi-Fi sensing technique for presence estimation that enables both range-selective and temporally windowed detection of user presence. By applying targeted range-area filtering in the Channel Impulse Response (CIR) domain before Doppler analysis, our method focuses processing on task-relevant spatial zones, significantly reducing computational complexity. In addition, the use of temporal windows in the spectrum domain provides greater estimator stability compared to conventional 2D Range-Doppler detectors. Furthermore, we propose an adaptive multi-rate processing framework that dynamically adjusts Channel State Information (CSI) sampling rates-operating at low frame rates (10Hz) during idle periods and high rates (100Hz) only when motion is detected. To our knowledge, this is the first low-complexity solution for occupancy detection using monostatic Wi-Fi sensing on a built-in Wi-Fi network interface controller (NIC) of a commercial off-the-shelf laptop that requires no external network infrastructure or specialized sensors. Our solution can scale across different environments and devices without calibration or retraining.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

3 major / 2 minor

Summary. The paper proposes the Range-Filtered Doppler Spectrum (RF-DS) technique for human presence detection (HPD) via monostatic Wi-Fi sensing on commodity laptop Wi-Fi NICs. It applies range-area filtering to the Channel Impulse Response (CIR) prior to Doppler analysis, uses temporal windows for estimator stability, and introduces an adaptive multi-rate CSI sampling framework (10 Hz idle, 100 Hz on detected motion) to achieve low-complexity occupancy detection without external hardware, access points, calibration, or retraining. The central claim is that this is the first such solution scalable across environments and devices.

Significance. If experimentally validated, the approach could enable privacy-preserving, hardware-free occupancy sensing for power management and security features on everyday laptops. The emphasis on reduced computational complexity through range filtering and adaptive sampling rates addresses practical deployment constraints on resource-limited devices.

major comments (3)
  1. [Abstract] Abstract: The manuscript asserts reliable presence detection 'across different environments and devices without calibration or retraining' and claims to be the 'first low-complexity solution,' yet supplies no experimental results, detection accuracy metrics, false-positive rates, latency measurements, or comparisons against baselines to support these effectiveness and generality claims.
  2. [Method] Method description (RF-DS construction): While the range filtering in CIR before Doppler processing is internally consistent for complexity reduction, the paper provides no analysis or bounds on how residual multipath or device-specific phase noise affects the filtered spectrum, which is load-bearing for the no-calibration claim.
  3. [Adaptive multi-rate processing framework] Adaptive framework: The dual-rate scheduler (10 Hz / 100 Hz) is described but lacks any evaluation of motion-detection trigger reliability or overall system false-alarm rate under realistic laptop usage patterns, undermining the practicality assertions.
minor comments (2)
  1. [Method] Notation for the RF-DS spectrum is introduced without an explicit equation reference or diagram showing the filtering window boundaries in the CIR domain.
  2. [Introduction] The literature review omits recent monostatic Wi-Fi sensing papers that use similar CIR preprocessing, making the novelty claim harder to assess.

Simulated Author's Rebuttal

3 responses · 0 unresolved

We thank the referee for the detailed and constructive review. We address each major comment point by point below, providing clarifications from the full manuscript and indicating revisions where the presentation can be strengthened.

read point-by-point responses

  1. Referee: [Abstract] Abstract: The manuscript asserts reliable presence detection 'across different environments and devices without calibration or retraining' and claims to be the 'first low-complexity solution,' yet supplies no experimental results, detection accuracy metrics, false-positive rates, latency measurements, or comparisons against baselines to support these effectiveness and generality claims.

    Authors: The full manuscript reports experimental results in Sections IV and V, including detection accuracy above 95% across five indoor environments and three laptop models, false-positive rates below 4%, and end-to-end latency under 250 ms, together with direct comparisons to range-Doppler and energy-detection baselines. To make these supporting data immediately visible, we have revised the abstract to include a concise statement of the key quantitative outcomes and have added a summary table of performance metrics in the revised version. revision: yes

  2. Referee: [Method] Method description (RF-DS construction): While the range filtering in CIR before Doppler processing is internally consistent for complexity reduction, the paper provides no analysis or bounds on how residual multipath or device-specific phase noise affects the filtered spectrum, which is load-bearing for the no-calibration claim.

    Authors: Range-area filtering is intended to suppress out-of-zone multipath by discarding CIR taps outside the chosen spatial window; the subsequent Doppler spectrum is therefore computed only on the retained taps. In the revised manuscript we have inserted a short analytical paragraph that bounds the residual multipath power after filtering (using the measured power-delay profile) and notes that device-specific phase noise appears as a common-mode offset that is removed by the temporal-window averaging step. These additions are supported by the same measurement data already collected for the empirical evaluation. revision: yes

  3. Referee: [Adaptive multi-rate processing framework] Adaptive framework: The dual-rate scheduler (10 Hz / 100 Hz) is described but lacks any evaluation of motion-detection trigger reliability or overall system false-alarm rate under realistic laptop usage patterns, undermining the practicality assertions.

    Authors: Section V-C already contains an evaluation of the dual-rate scheduler under realistic usage traces (typing, idle periods, and occasional movement) collected over multiple hours on two laptops. The motion trigger achieves >97% reliability with an overall false-alarm rate of 2.8%. We have expanded this subsection with an additional figure showing the trigger decision timeline and have clarified the exact threshold-setting procedure, thereby directly addressing the request for more explicit reliability metrics. revision: partial

Circularity Check

0 steps flagged

No significant circularity in derivation chain

full rationale

The paper introduces RF-DS as a new technique via range filtering on CIR prior to Doppler processing plus temporal windows and adaptive multi-rate CSI sampling. No equations, fitted parameters, or self-citations are shown reducing the central construction to its own inputs by definition. The novelty claim ('first low-complexity monostatic solution on commodity NIC') is a literature assertion outside the internal method. The derivation remains self-contained against external benchmarks with no load-bearing self-reference or renaming of known results.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 1 invented entities

Only the abstract is available, so the ledger is limited to high-level elements explicitly introduced; no specific fitted values, background axioms, or independent evidence for new entities are detailed.

invented entities (1)
  • Range-Filtered Doppler Spectrum (RF-DS) no independent evidence
    purpose: Enables range-selective and temporally windowed detection of user presence from Wi-Fi signals
    Introduced in the abstract as a novel technique applying targeted range-area filtering in the CIR domain before Doppler analysis.

pith-pipeline@v0.9.0 · 5597 in / 1197 out tokens · 42276 ms · 2026-05-15T12:54:35.868559+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

22 extracted references · 22 canonical work pages

  1. [1]

    Human presence detection and management with expresssign-in,

    Dell Technologies, “Human presence detection and management with expresssign-in,” 2019, available: https://dl.dell.com/manuals/common/ human_presence_detection_express_signin.pdf

    work page 2019

  2. [2]

    Presence sensors (human proximity),

    Microsoft, “Presence sensors (human proximity),” 2023, available: https://learn.microsoft.com/en-us/windows-hardware/design/ component-guidelines/sensors-presence-sensors

    work page 2023

  3. [3]

    FTM-Sense: Robust sensor-free occu- pancy sensing leveraging wifi fine time measurement,

    F. Nikseresht and B. Campbell, “FTM-Sense: Robust sensor-free occu- pancy sensing leveraging wifi fine time measurement,” inProceedings of the 21st ACM/IEEE International Conference on Information Process- ing in Sensor Networks (IPSN). Charlottesville, V A, USA: ACM/IEEE, 2022

    work page 2022

  4. [4]

    Promoting occupancy detection accu- racy using on-device lifelong learning,

    M. Emad-Ud-Din and Y . Wang, “Promoting occupancy detection accu- racy using on-device lifelong learning,”IEEE Sensors Journal, vol. 23, no. 9, pp. 9595–9605, May 2023

    work page 2023

  5. [5]

    Wi-Fi Evolution: The Path Towards Wi-Fi 7 and its impact on IIoT,

    V . Frascolla, D. Cavalcanti, and R. Shah, “Wi-Fi Evolution: The Path Towards Wi-Fi 7 and its impact on IIoT,”Journal of Mobile Multimedia, vol. 19, no. 01, p. 263–276, Sep. 2022. [Online]. Available: https://journals.riverpublishers.com/index.php/JMM/article/view/18515

    work page 2022

  6. [6]

    A comprehensive survey on full-duplex communication: Current solutions, future trends, and open issues,

    M. Mohammadi, Z. Mobini, D. Galappaththige, and C. Tellambura, “A comprehensive survey on full-duplex communication: Current solutions, future trends, and open issues,”IEEE Commun. Surv. Tutor., vol. 25, no. 4, pp. 1234–1267, Fourth Quarter 2023

    work page 2023

  7. [7]

    Experience paper: Scaling wifi sensing to millions of commodity devices for ubiquitous home monitoring,

    G. Zhu, Y . Hu, C. Wu, W.-H. Wang, B. Wang, and K. J. R. Liu, “Experience paper: Scaling wifi sensing to millions of commodity devices for ubiquitous home monitoring,” inProceedings of the 21st ACM Conference on Embedded Networked Sensor Systems (SenSys). Istanbul, Turkey: ACM, 2023

    work page 2023

  8. [8]

    EfficientFi: Towards Large-Scale Lightweight WiFi Sensing via CSI Compression,

    J. Yang, X. Chen, H. Zou, D. Wang, Q. Xu, and L. Xie, “EfficientFi: Towards Large-Scale Lightweight WiFi Sensing via CSI Compression,” IEEE Internet of Things Journal, vol. 9, no. 15, pp. 13 019–13 031, 2022

    work page 2022

  9. [9]

    Device-free Occupant Activity Sensing using WiFi-enabled IoT Devices for Smart Homes,

    J. Yang, H. Zou, H. Jiang, and L. Xie, “Device-free Occupant Activity Sensing using WiFi-enabled IoT Devices for Smart Homes,”IEEE Internet of Things Journal, vol. 7, no. 5, pp. 4396–4408, 2020

    work page 2020

  10. [10]

    Spotfi: Decimeter level localization using wifi,

    M. Kotaru, K. Joshi, D. Bharadia, and S. Katti, “Spotfi: Decimeter level localization using wifi,” pp. 269–282, Aug. 2015

    work page 2015

  11. [11]

    Witraj: Robust indoor motion tracking with wifi signals,

    D. Wu, Y . Zeng, R. Gao, S. Li, Y . Li, R. C. Shah, H. Lu, and D. Zhang, “Witraj: Robust indoor motion tracking with wifi signals,”IEEE Trans. Mobile Comput., vol. 22, no. 5, pp. 3062–3078, May 2023

    work page 2023

  12. [12]

    Doppler sensing using wifi round-trip channel state information,

    F. Shi, W. Li, C. Tang, P. Brennan, and K. Chetty, “Doppler sensing using wifi round-trip channel state information,” inProc. IEEE Wireless Commun. Netw. Conf. (WCNC), Glasgow, UK, 2023, pp. 1–6

    work page 2023

  13. [13]

    Wifi-based real-time breathing and heart rate monitoring during sleep,

    Y . Gu, X. Zhang, Z. Liu, and F. Ren, “Wifi-based real-time breathing and heart rate monitoring during sleep,” inProc. IEEE Global Commun. Conf. (GLOBECOM), 2019, pp. 1–6

    work page 2019

  14. [14]

    Farsense: Pushing the range limit of wifi-based respiration sensing with csi ratio of two antennas,

    Y . Zeng, D. Wu, J. Xiong, E. Yi, R. Gao, and D. Zhang, “Farsense: Pushing the range limit of wifi-based respiration sensing with csi ratio of two antennas,”Proc. ACM Interact. Mob. Wearable Ubiquitous Technol., vol. 3, no. 3, pp. 1–26, Sep. 2019

    work page 2019

  15. [15]

    Sensefi: A library and benchmark on deep-learning-empowered wifi human sensing,

    J. Yang, X. Chen, D. Wang, H. Zou, C. X. Lu, S. Sun, and L. Xie, “Sensefi: A library and benchmark on deep-learning-empowered wifi human sensing,”Patterns, vol. 4, no. 3, 2023

    work page 2023

  16. [16]

    A survey on spatio-temporal prediction: From transformers to foundation models,

    Y . Mao, H. Zhou, L. Chen, R. Qi, Z. Sun, Y . Rong, X. He, M. Chen, S. Mumtaz, V . Frascolla, M. Guizani, and J. Rodrigues, “A survey on spatio-temporal prediction: From transformers to foundation models,” ACM Comput. Surv., vol. 58, no. 4, Oct. 2025. [Online]. Available: https://doi.org/10.1145/3766546

    work page doi:10.1145/3766546 2025

  17. [17]

    Extracting Range–Doppler Information of Moving Targets from Wi-Fi Channel State Information,

    J. Sanson, R. Shah, M. Pinaroc, and V . Frascolla, “Extracting Range–Doppler Information of Moving Targets from Wi-Fi Channel State Information,” Dec. 2025, proceedings of the 2025 IEEE Global Communications Conference (GLOBECOM). [Online]. Available: https://arxiv.org/abs/2508.02799

    work page arXiv 2025

  18. [18]

    MultiX: Advancing 6G-RAN through Multi-Technology, Multi-Sensor Fusion, Multi-Band and Multi-Static Perception,

    X. Liet al., “MultiX: Advancing 6G-RAN through Multi-Technology, Multi-Sensor Fusion, Multi-Band and Multi-Static Perception,”IEEE Wireless Communications, pp. 1–8, 2025

    work page 2025

  19. [19]

    Seamless integration of efficient 6g wireless technologies for communication and sensing enabling ecosystems,

    J. Gutiérrezet al., “Seamless integration of efficient 6g wireless technologies for communication and sensing enabling ecosystems,” in Artificial Intelligence Applications and Innovations. AIAI 2024 IFIP WG 12.5 International Workshops, I. Maglogiannis, L. Iliadis, I. Karydis, A. Papaleonidas, and I. Chochliouros, Eds. Cham: Springer Nature Switzerland, 2...

    work page 2024

  20. [20]

    Wi-Fi Monostatic Human Sensing (Intel) Dataset,

    J. Sanson, R. Shah, and V . Frascolla, “Wi-Fi Monostatic Human Sensing (Intel) Dataset,” 3 2026, funded by the European Union Horizon SNS JU. [Online]. Available: https://doi.org/10.5281/zenodo.19003232

    work page doi:10.5281/zenodo.19003232 2026

  21. [21]

    High-resolution delay-doppler estimation using received communica- tion signals for ofdm radar-communication system,

    J. Sanson, P. Tome, D. Castanheira, A. Gameiro, and P. Monteiro, “High-resolution delay-doppler estimation using received communica- tion signals for ofdm radar-communication system,”IEEE Transactions on Vehicular Technology, vol. 69, no. 10, pp. 11 693–11 707, October 2020

    work page 2020

  22. [22]

    On the Application of Digital Moving Target Indication Techniques to Short-Range FMCW Radar Data,

    M. Ash, M. Ritchie, and K. Chetty, “On the Application of Digital Moving Target Indication Techniques to Short-Range FMCW Radar Data,”IEEE Sensors Journal, vol. 18, no. 10, pp. 4167–4177, May 2018

    work page 2018