pith. sign in

arxiv: 2605.00900 · v1 · submitted 2026-04-28 · 📡 eess.SP

Floor Plan-Agnostic Detection of Gait Speed Drifts Using Ambient Sensors

Marina Vicini , Martin Rudorfer , Zhuangzhuang Dai , Ahmad Beltagui , Luis J. Manso This is my paper

Pith reviewed 2026-05-09 20:52 UTC · model grok-4.3

classification 📡 eess.SP
keywords gait speed driftambient sensorsfloor plan agnosticdrift detectionhealth monitoringnon-parametric statistical testsensor transitionsolder adults
0
0 comments X

The pith

Ambient sensors detect gait speed drifts without needing a home floor plan

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

The paper introduces a method to detect changes in gait speed, an important indicator of health decline in older adults, using only data from ambient sensors placed in the home. Instead of relying on a detailed floor plan, it selects informative transitions between sensors and tracks variations in how long it takes to move between them. Statistical tests compare recent transition times to an earlier baseline, with daily results combined for a reliable signal of drift. This matters for making continuous monitoring practical in more homes where layout information is unavailable or impractical to obtain.

Core claim

The authors claim that by identifying informative sensor-to-sensor transitions and analyzing fluctuations in their durations with non-parametric statistical tests on sequences against a baseline, followed by aggregating daily test results, gait speed drifts can be detected robustly using sparse ambient sensors alone, achieving performance comparable to or better than a state-of-the-art method that requires floor plan information, as demonstrated in simulations over four different home layouts.

What carries the argument

Selection and duration analysis of informative sensor-to-sensor transitions using non-parametric change detection tests with daily aggregation.

If this is right

  • This allows gait monitoring in homes without available floor plans.
  • It reduces the setup complexity for ambient sensor systems.
  • The approach supports scalable deployment for older adult health monitoring.
  • Daily aggregation improves the robustness of drift detection.

Where Pith is reading between the lines

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

  • If transition durations reliably proxy gait speed, this could extend to detecting other movement-related health changes.
  • Validation in real homes with ground-truth gait measurements would be a next step to confirm the simulation results.
  • The method might integrate with other sensor-based systems for comprehensive in-home health tracking.

Load-bearing premise

That the simulated data for four home layouts accurately reflects the noise, variability, and movement patterns in actual homes with real residents.

What would settle it

Observing in a real-world setting with independent gait speed measurements, such as from wearable devices, that the method's detected drifts do not align with actual changes in walking speed.

Figures

Figures reproduced from arXiv: 2605.00900 by Ahmad Beltagui, Luis J. Manso, Marina Vicini, Martin Rudorfer, Zhuangzhuang Dai.

Figure 1
Figure 1. Figure 1: The four simulated studio apartment layouts used in [PITH_FULL_IMAGE:figures/full_fig_p001_1.png] view at source ↗
Figure 1
Figure 1. Figure 1: Nine gait speeds, from 0.4 m/s to 1.2 m/s in steps of 0.1 m/s, were simulated. This range was selected to cover speeds indicative of various health states, from frail individuals in acute care (approx. 0.45 m/s) to healthy older adults (0.94−1.26 m/s) [37]. This also includes the critical clinical lower bound of 0.8 m/s, which is predictive of poor outcomes. For our experiments, we simulated a sudden drift… view at source ↗
Figure 2
Figure 2. Figure 2: Schematic overview of the proposed floor plan-agnostic gait speed drift detection pipeline. The process consists of [PITH_FULL_IMAGE:figures/full_fig_p005_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Performance comparison between the proposed floor plan-agnostic method (blue) and the floor plan-dependent baseline [PITH_FULL_IMAGE:figures/full_fig_p006_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Parameter sensitivity analysis plots. The plots show the impact on F1-Score when varying key hyperparameters. The [PITH_FULL_IMAGE:figures/full_fig_p007_4.png] view at source ↗
read the original abstract

Gait speed is a vital health indicator for older adults, as changes in gait speed can reflect physiological and functional decline. Ambient sensors offer a promising, privacy-preserving solution for continuous in-home monitoring of gait speed; although it is often limited by methods requiring a home floor plan, which is frequently unfeasible. This paper proposes a novel, floor plan-agnostic method to detect gait speed drifts using only sparse ambient sensors. Our approach identifies informative sensor-to-sensor transitions and analyses fluctuations in their duration. For each sequence a non-parametric statistical test detects changes between a recent period and an initial baseline; and daily test results are aggregated to provide a robust drift detection response. We evaluate our method on a simulated dataset across four different home layouts, showing performance comparable to, and in some cases exceeding, a state-of-the-art baseline that requires floor plan information. This work demonstrates a feasible approach for scalable, cost effective gait drift detection monitoring, providing a foundation for future validation in complex real-world environments.

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

2 major / 2 minor

Summary. The paper proposes a floor plan-agnostic method for detecting gait speed drifts with ambient sensors. It identifies informative sensor-to-sensor transitions, tracks fluctuations in their durations, applies non-parametric statistical tests comparing recent windows against an initial baseline for each sequence, and aggregates daily test outcomes to produce a drift detection signal. The approach is evaluated on a simulated dataset spanning four distinct home layouts and is reported to achieve performance comparable to (and in some cases exceeding) a state-of-the-art baseline that requires explicit floor-plan information.

Significance. If the simulation faithfully captures real sensor timing, missed detections, path variability, and day-to-day gait fluctuations, the method would remove a major deployment barrier for continuous in-home gait monitoring. This could enable scalable, privacy-preserving health tracking for older adults without the need for manual floor-plan acquisition or wearable devices. The use of standard non-parametric tests and aggregation is a strength, as it avoids introducing additional fitted parameters.

major comments (2)
  1. [Evaluation section] Evaluation section: All quantitative claims of comparability to the floor-plan baseline rest on a single simulated dataset across four layouts. The manuscript provides no explicit description of how the simulator maps variable gait speeds to transition durations under realistic path choices, incorporates sensor timing jitter or missed detections, or models normal day-to-day variability; without these mappings the reported performance equivalence cannot be taken as evidence that the floor-plan-agnostic detector will maintain its operating point in the field.
  2. [Evaluation section] Evaluation section: No error bars, confidence intervals, or statistical significance tests on the performance metrics are reported. This omission is load-bearing because the central claim is that the method is “comparable to, and in some cases exceeding,” the baseline; without variability measures it is impossible to determine whether observed differences are meaningful or artifacts of the particular simulation runs.
minor comments (2)
  1. [Abstract] The abstract states that “daily test results are aggregated” but does not specify the aggregation rule (e.g., majority vote, threshold on fraction of positive tests). Adding one sentence would improve reproducibility.
  2. [Figures] Figure captions and axis labels in the experimental results should explicitly state the performance metric (e.g., precision, recall, or F1) and the exact simulation parameters used for each layout.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive comments, which highlight important aspects of the evaluation that require clarification and strengthening. We address each major comment below and will revise the manuscript accordingly.

read point-by-point responses

  1. Referee: [Evaluation section] All quantitative claims of comparability to the floor-plan baseline rest on a single simulated dataset across four layouts. The manuscript provides no explicit description of how the simulator maps variable gait speeds to transition durations under realistic path choices, incorporates sensor timing jitter or missed detections, or models normal day-to-day variability; without these mappings the reported performance equivalence cannot be taken as evidence that the floor-plan-agnostic detector will maintain its operating point in the field.

    Authors: We agree that the current manuscript lacks sufficient detail on the simulation model, which limits the interpretability of the results. In the revised version, we will expand the Evaluation section with an explicit description of the simulator, including: (1) the mapping from gait speed to transition durations based on path lengths and walking speeds; (2) incorporation of realistic path variability; (3) modeling of sensor timing jitter and missed detections; and (4) day-to-day gait fluctuations drawn from empirical distributions. This addition will allow readers to assess the fidelity of the simulation and the robustness of the performance claims. revision: yes

  2. Referee: [Evaluation section] No error bars, confidence intervals, or statistical significance tests on the performance metrics are reported. This omission is load-bearing because the central claim is that the method is “comparable to, and in some cases exceeding,” the baseline; without variability measures it is impossible to determine whether observed differences are meaningful or artifacts of the particular simulation runs.

    Authors: We acknowledge that the absence of variability measures and statistical tests weakens the presentation of the comparative results. In the revision, we will report error bars or confidence intervals for all performance metrics (e.g., precision, recall, F1) aggregated across multiple simulation runs and the four layouts. We will also include statistical significance tests (e.g., paired t-tests or Wilcoxon tests) comparing our method to the floor-plan baseline, with appropriate corrections for multiple comparisons, to substantiate claims of comparability or superiority. revision: yes

Circularity Check

0 steps flagged

No circularity: method uses standard statistical tests on observed durations with independent simulation-based evaluation.

full rationale

The paper's core procedure identifies sensor transitions, measures their durations, applies a non-parametric test comparing recent windows to a baseline, and aggregates daily results. These steps are described as direct applications of existing statistical methods without any fitted parameters being renamed as predictions, self-referential definitions, or load-bearing self-citations that close a loop. The quantitative claims rest on empirical performance against a separate baseline on simulated layouts, which does not reduce the detector construction to its own inputs by definition. No equations or uniqueness theorems are invoked that collapse the result to the input data.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

The central claim rests on domain assumptions about sensor data reflecting gait and on the fidelity of the simulation; no free parameters or invented entities are explicitly introduced in the abstract.

axioms (1)
  • domain assumption Sparse ambient sensors produce transition durations that reliably proxy gait speed changes
    Invoked when the method treats duration fluctuations as direct indicators of gait drift

pith-pipeline@v0.9.0 · 5485 in / 1181 out tokens · 41914 ms · 2026-05-09T20:52:30.981878+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

43 extracted references · 24 canonical work pages

  1. [1]

    Sensor Data Simulation with Wandering Behavior for the Elderly Living Alone,

    K. Tanaka, M. Kudo, and K. Kimura, “Sensor Data Simulation with Wandering Behavior for the Elderly Living Alone,” in2022 26th International Conference on Pattern Recognition (ICPR). Montreal, QC, Canada: IEEE, Aug. 2022, pp. 885–891. [Online]. Available: https://ieeexplore.ieee.org/document/9956332/

    work page arXiv 2022

  2. [2]

    Sensor Data Simulation for Anomaly Detection of the Elderly Living Alone,

    ——, “Sensor Data Simulation for Anomaly Detection of the Elderly Living Alone,”IEEE Internet of Things Journal, vol. 11, no. 19, pp. 31 675–31 686, Oct. 2024. [Online]. Available: https: //ieeexplore.ieee.org/document/10579811/

    work page arXiv 2024

  3. [3]

    When Frail Older People Relocate in Very Old Age, Who Makes the Decision?

    F. Scheibl, M. Farquhar, J. Buck, S. Barclay, C. Brayne, and J. Fleming, “When Frail Older People Relocate in Very Old Age, Who Makes the Decision?”Innovation in Aging, vol. 3, no. 4, p. igz030, Aug

  4. [4]

    Available: https://academic.oup.com/innovateage/article/ doi/10.1093/geroni/igz030/5564381

    [Online]. Available: https://academic.oup.com/innovateage/article/ doi/10.1093/geroni/igz030/5564381

    work page doi:10.1093/geroni/igz030/5564381

  5. [5]

    W. H. Organization,World Report on Ageing and Health. World Health Organization, 2015

    2015

  6. [6]

    Make time for gait speed: vital to staging the aging,

    T. M. Wildes, “Make time for gait speed: vital to staging the aging,”Blood, vol. 134, no. 4, pp. 334–336, July 2019. [Online]. Available: https://ashpublications.org/blood/article/134/4/334/ 260682/Make-time-for-gait-speed-vital-to-staging-the

    2019

  7. [7]

    Walking Speed: The Functional Vital Sign,

    A. Middleton, S. L. Fritz, and M. Lusardi, “Walking Speed: The Functional Vital Sign,”Journal of Aging and Physical Activity, vol. 23, no. 2, pp. 314–322, Apr. 2015. [Online]. Available: https: //journals.humankinetics.com/view/journals/japa/23/2/article-p314.xml

    2015

  8. [8]

    Gait speed at usual pace as a predictor of adverse outcomes in community-dwelling older people an International Academy on Nutrition and Aging (IANA) Task Force,

    G. Abellan Van Kan, Y . Rolland, S. Andrieu, J. Bauer, O. Beauchet, M. Bonnefoy, M. Cesari, L. Donini, S. Gillette-Guyonnet, M. Inzitari, F. Nourhashemi, G. Onder, P. Ritz, A. Salva, M. Visser, and B. Vellas, “Gait speed at usual pace as a predictor of adverse outcomes in community-dwelling older people an International Academy on Nutrition and Aging (IAN...

  9. [9]

    Available: https://linkinghub.elsevier.com/retrieve/pii/ S1279770723019887

    [Online]. Available: https://linkinghub.elsevier.com/retrieve/pii/ S1279770723019887

  10. [10]

    Meaningful Change in Walking Speed,

    K. Chui, E. Hood, and D. Klima, “Meaningful Change in Walking Speed,”Topics in Geriatric Rehabilitation, vol. 28, no. 2, pp. 97–103, Apr. 2012. [Online]. Available: https://journals.lww.com/ 00013614-201204000-00004

    2012

  11. [11]

    A Short Physical Performance Battery Assessing Lower Extremity Function: Association With Self-Reported Disability and Prediction of Mortality and Nursing Home Admission,

    J. M. Guralnik, E. M. Simonsick, L. Ferrucci, R. J. Glynn, L. F. Berkman, D. G. Blazer, P. A. Scherr, and R. B. Wallace, “A Short Physical Performance Battery Assessing Lower Extremity Function: Association With Self-Reported Disability and Prediction of Mortality and Nursing Home Admission,”Journal of Gerontology, vol. 49, no. 2, pp. M85–M94, Mar. 1994. ...

    work page doi:10.1093/geronj/49.2.m85 1994

  12. [12]

    Gait Velocity as a Single Predictor of Adverse Events in Healthy Seniors Aged 75 Years and Older,

    M. Montero-Odasso, M. Schapira, E. R. Soriano, M. Varela, R. Kaplan, L. A. Camera, and L. M. Mayorga, “Gait Velocity as a Single Predictor of Adverse Events in Healthy Seniors Aged 75 Years and Older,”The Journals of Gerontology Series A: Biological Sciences and Medical Sciences, vol. 60, no. 10, pp. 1304–1309, Oct. 2005. [Online]. Available: https://acad...

    work page doi:10.1093/gerona/60.10.1304 2005

  13. [13]

    Walking Speed Estimation and Gait Classification Using Plantar Pressure and On-Device Deep Learning,

    H. Cho, “Walking Speed Estimation and Gait Classification Using Plantar Pressure and On-Device Deep Learning,”IEEE Sensors Journal, vol. 23, no. 19, pp. 23 336–23 347, Oct. 2023. [Online]. Available: https://ieeexplore.ieee.org/document/10224815/

    work page arXiv 2023

  14. [14]

    Detecting Fall Risk and Frailty in Elders with Inertial Motion Sensors: A Survey of Significant Gait Parameters,

    L. Ruiz-Ruiz, A. R. Jimenez, G. Garcia-Villamil, and F. Seco, “Detecting Fall Risk and Frailty in Elders with Inertial Motion Sensors: A Survey of Significant Gait Parameters,”Sensors, vol. 21, no. 20, p. 6918, Oct. 2021. [Online]. Available: https://www.mdpi.com/1424-8220/21/20/6918

    2021

  15. [15]

    Maruyama, H

    T. Maruyama, H. Toda, S. Kanoga, M. Tada, and Y . Endo,Accuracy Evaluation of Human Gait Estimation by a Sparse Set of Inertial Measurement Units. Singapore: Springer Singapore, 2021, pp. 51–61. [Online]. Available: https://doi.org/10.1007/978-981-15-8944-7 4

    work page doi:10.1007/978-981-15-8944-7 2021

  16. [16]

    A Novel Approach for Improving Gait Speed Estimation Using a Single Inertial Measurement Unit Embedded in a Smartphone: Validity and Reliability Study,

    P.-A. Lee, W. Yu, J. Zhou, T. Tsai, B. Manor, and O.-Y . Lo, “A Novel Approach for Improving Gait Speed Estimation Using a Single Inertial Measurement Unit Embedded in a Smartphone: Validity and Reliability Study,”JMIR mHealth and uHealth, vol. 12, pp. e52 166–e52 166, Aug. 2024. [Online]. Available: https://mhealth.jmir.org/2024/1/e52166

    2024

  17. [17]

    Gait Speed Tracking System Using UWB Radar,

    B. Lau, S. Haider, A. Boroomand, G. Shaker, J. Boger, and P. Morita, “Gait Speed Tracking System Using UWB Radar,” in 12th European Conference on Antennas and Propagation (EuCAP 2018). London, UK: Institution of Engineering and Technology, 2018, pp. 899 (4 pp.)–899 (4 pp.). [Online]. Available: https: //digital-library.theiet.org/content/conferences/10.10...

    work page doi:10.1049/cp.2018.1258 2018

  18. [18]

    Use of Millimeter Wave FMCW Radar to Capture Gait Parameters,

    H. Abedi, “Use of Millimeter Wave FMCW Radar to Capture Gait Parameters,”American Journal of Biomedical Science & Research, vol. 6, no. 2, pp. 122–123, Nov

  19. [19]

    Available: https://biomedgrid.com/fulltext/volume6/ use-of-high-frequency-radar-to-capture-gait-parameters.001009.php

    [Online]. Available: https://biomedgrid.com/fulltext/volume6/ use-of-high-frequency-radar-to-capture-gait-parameters.001009.php

  20. [20]

    Concurrent validity of the Microsoft Kinect for Windows v2 for measuring spatiotemporal gait parameters,

    E. Dolatabadi, B. Taati, and A. Mihailidis, “Concurrent validity of the Microsoft Kinect for Windows v2 for measuring spatiotemporal gait parameters,”Medical Engineering & Physics, vol. 38, no. 9, pp. 952–958, Sept. 2016. [Online]. Available: https://linkinghub.elsevier. com/retrieve/pii/S1350453316301291

    2016

  21. [21]

    Extracting Gait Velocity and Stride Length from Surrounding Radio Signals,

    C.-Y . Hsu, Y . Liu, Z. Kabelac, R. Hristov, D. Katabi, and C. Liu, “Extracting Gait Velocity and Stride Length from Surrounding Radio Signals,” inProceedings of the 2017 CHI Conference on Human Factors in Computing Systems. Denver Colorado USA: ACM, May 2017, pp. 2116–2126. [Online]. Available: https://dl.acm.org/doi/10.1145/3025453.3025937

    work page doi:10.1145/3025453.3025937 2017

  22. [22]

    GaitWay: Monitoring and Recognizing Gait Speed Through the Walls,

    C. Wu, F. Zhang, Y . Hu, and K. J. R. Liu, “GaitWay: Monitoring and Recognizing Gait Speed Through the Walls,”IEEE Transactions on Mobile Computing, vol. 20, no. 6, pp. 2186–2199, June 2021. [Online]. Available: https://ieeexplore.ieee.org/document/9003416/

    work page arXiv 2021

  23. [23]

    Unsupervised detection and analysis of changes in everyday physical activity data,

    G. Sprint, D. J. Cook, and M. Schmitter-Edgecombe, “Unsupervised detection and analysis of changes in everyday physical activity data,”Journal of Biomedical Informatics, vol. 63, pp. 54–65, Oct

  24. [24]

    Available: https://linkinghub.elsevier.com/retrieve/pii/ S1532046416300740

    [Online]. Available: https://linkinghub.elsevier.com/retrieve/pii/ S1532046416300740

  25. [25]

    Unlocking the power of proactive and preventative care services: A practical blueprint for planning, implementing and scaling up,

    Association of Directors of Adult Social Services (ADASS) and TEC Services Association (TSA), “Unlocking the power of proactive and preventative care services: A practical blueprint for planning, implementing and scaling up,” ADASS and TSA, Tech. Rep., 2025. [Online]. Available: https://www.tsa-voice.org.uk/

    2025

  26. [26]

    Un- supervised Machine Learning for Developing Personalised Behaviour Models Using Activity Data,

    L. Fiorini, F. Cavallo, P. Dario, A. Eavis, and P. Caleb-Solly, “Un- supervised Machine Learning for Developing Personalised Behaviour Models Using Activity Data,”Sensors, vol. 17, no. 5, p. 1034, May

  27. [27]

    Available: https://www.mdpi.com/1424-8220/17/5/1034

    [Online]. Available: https://www.mdpi.com/1424-8220/17/5/1034

  28. [28]

    Anomaly Detection in Elderly Daily Behavior in Ambient Sensing Environments,

    O. Aran, D. Sanchez-Cortes, M.-T. Do, and D. Gatica-Perez, “Anomaly Detection in Elderly Daily Behavior in Ambient Sensing Environments,” inHuman Behavior Understanding, M. Chetouani, J. Cohn, and A. A. Salah, Eds. Cham: Springer International Publishing, 2016, vol. 9997, pp. 51–67, series Title: Lecture Notes in Computer Science. [Online]. Available: htt...

    work page doi:10.1007/978-3-319-46843-3 2016

  29. [29]

    A Survey on Ambient Sensor-Based Abnormal Behaviour Detection for Elderly People in Healthcare,

    Y . Wang, X. Wang, D. Arifoglu, C. Lu, A. Bouchachia, Y . Geng, and G. Zheng, “A Survey on Ambient Sensor-Based Abnormal Behaviour Detection for Elderly People in Healthcare,”Electronics, vol. 12, no. 7, p. 1539, Mar. 2023. [Online]. Available: https: //www.mdpi.com/2079-9292/12/7/1539

    2023

  30. [30]

    Integrating Temporal Context into Streaming Data for Human Activity Recognition in Smart Home,

    M. Vicini, M. Rudorfer, Z. Dai, and L. J. Manso, “Integrating Temporal Context into Streaming Data for Human Activity Recognition in Smart Home,” inProceedings of the International Conference on Ubiquitous Computing and Ambient Intelligence (UCAmI 2024), J. Bravo, C. Nugent, and I. Cleland, Eds. Cham: Springer Nature Switzerland, 2024, vol. 1212, pp. 238–...

    work page doi:10.1007/978-3-031-77571-0 2024

  31. [31]

    Unsupervised statistical concept drift detection for behaviour abnormality detection,

    B. Friedrich, T. Sawabe, and A. Hein, “Unsupervised statistical concept drift detection for behaviour abnormality detection,”Applied Intelligence, vol. 53, no. 3, pp. 2527–2537, Feb. 2023. [Online]. Available: https://link.springer.com/10.1007/s10489-022-03611-3

    work page doi:10.1007/s10489-022-03611-3 2023

  32. [32]

    Unobtrusive and Ubiquitous In-Home Monitoring: A Methodology for Continuous Assessment of Gait Velocity in Elders,

    S. Hagler, D. Austin, T. Hayes, J. Kaye, and M. Pavel, “Unobtrusive and Ubiquitous In-Home Monitoring: A Methodology for Continuous Assessment of Gait Velocity in Elders,”IEEE Transactions on Biomedical Engineering, vol. 57, no. 4, pp. 813–820, Apr. 2010. [Online]. Available: http://ieeexplore.ieee.org/document/5339193/

    work page arXiv 2010

  33. [33]

    Motion Pattern Generation and Recognition for Mobility Assessments in Domestic Environments:,

    T. Frenken, E.-E. Steen, M. Brell, W. Nebel, and A. Hein, “Motion Pattern Generation and Recognition for Mobility Assessments in Domestic Environments:,” inProceedings of the 1st International Living Usability Lab Workshop on AAL Latest Solutions, Trends and Applications. Rome, Italy: SciTePress - Science and and Technology Publications, 2011, pp. 3–12. [...

    work page doi:10.5220/0003299400030012 2011

  34. [34]

    Unobtrusive assessment of walking speed in the home using inexpensive PIR sensors,

    T. Hayes, S. Hagler, D. Austin, J. Kaye, and M. Pavel, “Unobtrusive assessment of walking speed in the home using inexpensive PIR sensors,” in2009 Annual International Conference of the IEEE Engineering in Medicine and Biology Society. Minneapolis, MN: IEEE, Sept. 2009, pp. 7248–7251. [Online]. Available: http: //ieeexplore.ieee.org/document/5334746/

    work page arXiv 2009

  35. [35]

    Ambient Assessment of Daily Activity and Gait Velocity,

    L. Walsh, B. Greene, A. Burns, and C. N ´ı Scanaill, “Ambient Assessment of Daily Activity and Gait Velocity,” inProceedings of the 5th International ICST Conference on Pervasive Computing Technologies for Healthcare. Dublin, Republic of Ireland: IEEE, 2011. [Online]. Available: http://eudl.eu/doi/10.4108/icst.pervasivehealth.2011. 246077

    work page doi:10.4108/icst.pervasivehealth.2011 2011

  36. [36]

    Real-time Gait Speed Evaluation at Home,

    K. Chapron, K. Bouchard, and S. Gaboury, “Real-time Gait Speed Evaluation at Home,” inProceedings of the 5th EAI International Conference on Smart Objects and Technologies for Social Good. Valencia Spain: ACM, Sept. 2019, pp. 55–60. [Online]. Available: https://dl.acm.org/doi/10.1145/3342428.3342665

    work page doi:10.1145/3342428.3342665 2019

  37. [37]

    Real-time gait speed evaluation at home in a multi residents context,

    ——, “Real-time gait speed evaluation at home in a multi residents context,”Multimedia Tools and Applications, vol. 80, no. 9, pp. 12 931–12 949, Apr. 2021. [Online]. Available: https: //link.springer.com/10.1007/s11042-020-08962-y

    work page doi:10.1007/s11042-020-08962-y 2021

  38. [38]

    Detecting Anomaly and Its Sources in Activities of Daily Living,

    S. W. Yahaya, A. Lotfi, and M. Mahmud, “Detecting Anomaly and Its Sources in Activities of Daily Living,”SN Computer Science, vol. 2, no. 1, p. 14, Feb. 2021. [Online]. Available: http://link.springer.com/10.1007/s42979-020-00418-2

    work page doi:10.1007/s42979-020-00418-2 2021

  39. [39]

    Unobtrusive Assessment of Mobility,

    M. Pavel, T. L. Hayes, A. Adami, H. Jimison, and J. Kaye, “Unobtrusive Assessment of Mobility,” in2006 International Conference of the IEEE Engineering in Medicine and Biology Society. New York, NY: IEEE, Aug. 2006, pp. 6277–6280. [Online]. Available: http://ieeexplore.ieee.org/document/4463244/

    work page arXiv 2006

  40. [40]

    Continuous Gait Velocity Analysis Using Ambient Sensors in a Smart Home,

    A. Nait Aicha, G. Englebienne, and B. Kr\”ose, “Continuous Gait Velocity Analysis Using Ambient Sensors in a Smart Home,” in Ambient Intelligence, B. De Ruyter, A. Kameas, P. Chatzimisios, and I. Mavrommati, Eds. Cham: Springer International Publishing, 2015, vol. 9425, pp. 219–235, series Title: Lecture Notes in Computer Science. [Online]. Available: htt...

    2015

  41. [41]

    Continuous measuring of the indoor walking speed of older adults living alone,

    A. Nait Aicha, G. Englebienne, and B. Kr ¨ose, “Continuous measuring of the indoor walking speed of older adults living alone,”Journal of Ambient Intelligence and Humanized Computing, vol. 9, no. 3, pp. 589–599, June 2018. [Online]. Available: http://link.springer.com/10.1007/s12652-017-0456-x

    work page doi:10.1007/s12652-017-0456-x 2018

  42. [42]

    Gait Speed as a Measure in Geriatric Assessment in Clinical Settings: A Systematic Review,

    N. M. Peel, S. S. Kuys, and K. Klein, “Gait Speed as a Measure in Geriatric Assessment in Clinical Settings: A Systematic Review,”The Journals of Gerontology: Series A, vol. 68, no. 1, pp. 39–46, Jan. 2013. [Online]. Available: https://academic.oup.com/ biomedgerontology/article-lookup/doi/10.1093/gerona/gls174

    work page doi:10.1093/gerona/gls174 2013

  43. [43]

    On a Test of Whether one of Two Random Variables is Stochastically Larger than the Other,

    H. B. Mann and D. R. Whitney, “On a Test of Whether one of Two Random Variables is Stochastically Larger than the Other,”The Annals of Mathematical Statistics, vol. 18, no. 1, pp. 50–60, 1947, publisher: Institute of Mathematical Statistics. [Online]. Available: http://www.jstor.org/stable/2236101

    work page arXiv 1947