pith. sign in

arxiv: 2605.24525 · v1 · pith:LL3F4PJ4new · submitted 2026-05-23 · 📡 eess.IV · eess.SP

A Signal Extraction Approach for Remote Heart Rate Variability Assessment Using Proxy Measure in a Driving Simulator

{\DJ}or{\dj}e D. Ne\v{s}kovi\'c , Nadica Miljkovi\'c This is my paper

Pith reviewed 2026-06-30 12:15 UTC · model grok-4.3

classification 📡 eess.IV eess.SP
keywords remote photoplethysmographyheart rate variabilitydriving simulatorsignal extractionmotion artifactssuperpixel regionspulse rateECG validation
0
0 comments X

The pith

Remote photoplethysmography extracts pulse rate and heart rate variability from facial videos in a driving simulator with errors low enough to match electrocardiography statistics.

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

The paper tests remote photoplethysmography algorithms including 2SR, CHROM, POS, and PCA on superpixel regions of the face to monitor heart activity without contact during baseline and simulated driving tasks. It adds two peak enhancement techniques based on the Lp norm and fractional-order derivatives, plus a signal-to-noise ratio check on 20-second segments to handle motion. Results from 29 participants show pulse rate errors as low as 1.92 bpm and heart rate variability measures that preserve the same statistical patterns as simultaneous ECG recordings. This setup matters for developing non-contact ways to track driver physiology in controlled moving environments where electrodes are impractical.

Core claim

In recordings from 29 participants, the 2SR algorithm combined with fractional-order derivative enhancement and 20 superpixel regions yields a mean absolute error of 1.92 bpm for pulse rate against ECG, while the best configurations reach 0.061 s MAE for SDNN and 0.081 s for RMSSD; inter-beat interval detection reaches an F1 score of 0.93, and all rPPG-derived parameters reproduce the statistical structure of the reference ECG across both baseline and driving conditions, with CHROM recommended for HRV and Lp norm at p around 6-7 as an effective enhancer.

What carries the argument

Application of spatial subspace rotation or chrominance methods to 10 or 20 superpixel facial regions, sharpened by Lp-norm or fractional-order derivative peak enhancement, followed by signal-to-noise ratio filtering of 20-second segments to reduce motion artifacts.

If this is right

  • 2SR with FOD and 20 superpixels gives the lowest pulse rate error, while CHROM with Lp norm performs best for HRV parameters.
  • Optimal settings cluster around p=6-7 for the Lp norm and fractional orders of 1.0-1.4.
  • All tested configurations reproduce the reference ECG statistical structure for both baseline and driving conditions.
  • FOD requires caution because it can introduce slow changes in the rPPG waveform shape.

Where Pith is reading between the lines

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

  • The same pipeline could support fatigue or stress monitoring in real vehicles if motion patterns remain comparable to the simulator.
  • Extending the SNR quality filter to variable-length segments might reduce data loss in longer recordings.
  • Combining the recommended CHROM configuration with other facial or vehicle sensors could test robustness beyond isolated video input.

Load-bearing premise

The signal-to-noise ratio assessment on 20-second segments removes motion artifacts without discarding valid physiological signals or creating selection bias in the retained data.

What would settle it

A new dataset of driving simulator recordings where rPPG-derived SDNN and RMSSD values show statistically different distributions from simultaneous ECG values after identical processing would falsify the reproduction of statistical structure.

Figures

Figures reproduced from arXiv: 2605.24525 by {\DJ}or{\dj}e D. Ne\v{s}kovi\'c, Nadica Miljkovi\'c.

Figure 1
Figure 1. Figure 1: Block diagram of proposed method for rPPG performance. Abbreviations are: Red Green Blue (RGB), Pulse Rate [PITH_FULL_IMAGE:figures/full_fig_p004_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Display of rPPG signal extraction after applying the CHROM, PCA (the first Principal Component [PITH_FULL_IMAGE:figures/full_fig_p006_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: The impact of different p values on the application of the Lp norm on rPPG signal with reference ECG presented in graphs. For p = 1, the Lp norm actually does not change the extracted rPPG signal. The second metric (SNR 0.7–3 Hz) integrates PSD over the full physiological HR band of 0.7 Hz – 3 Hz, with a ±0.1 Hz notch at 2 Hz excluded from both signal and noise calculations to suppress a recurring non-phys… view at source ↗
Figure 4
Figure 4. Figure 4: The impact of different values of the Fractional Order Derivative (FOD) for the application of GL FOD for peak enhancement in rPPG signal with presented reference ECG. The value of FOD of 1 is equal to the application of standardized Pan-Tompkins algorithm. Also, the extracted rPPG without peak enhancement is used. A notable change in peak location is noticed due to the slow changes of rPPG signal, making … view at source ↗
Figure 5
Figure 5. Figure 5: Example of regions that proved to be the most useful for extracting the rPPG signal in one subject when 20 SP are [PITH_FULL_IMAGE:figures/full_fig_p011_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Comparison of SNR values (useful part of PSD defined within a band range from 0.7 Hz to 3 Hz) across two peak [PITH_FULL_IMAGE:figures/full_fig_p012_6.png] view at source ↗
Figure 11
Figure 11. Figure 11: Example of a 20 s long ECG segment containing a pathological beat (confirmed by a cardiologist) and the [PITH_FULL_IMAGE:figures/full_fig_p021_11.png] view at source ↗
read the original abstract

This study evaluates remote Photopletismography (rPPG) algorithms, Spatial Subspace Rotation (2SR), Chrominance-based method (CHROM), Plane-Orthogonal-to-Skin (POS), and Principal Component Analysis (PCA), applied to selected superpixel-based facial regions (with target counts of 10 and 20 regions) for monitoring in a driving simulator. Two novel peak enhancement approaches, based on the Lp norm and Fractional-Order Derivative (FOD), are introduced to enable robust Heart Rate Variability (HRV) estimation. A signal-to-noise ratio-based quality assessment of 20 s segments serves as a data cleaning mechanism to mitigate motion artifacts inherent to dynamic recording conditions. In a sample of 29 participants recorded during baseline and driving simulation conditions, Pulse Rate (PR) is calculated with clinically acceptable accuracy across configurations (validated against simultaneous Electrocardiography (ECG) recordings), achieving the lowest Mean Absolute Error (MAE) of 1.92 bpm (sd = 1.72) using 2SR with FOD and 20 superpixel regions. The best-case MAE reached 0.061 s for Standard Deviation of Normal-to-Normal intervals (SDNN) and 0.081 s for Root Mean Square of Successive Differences (RMSSD), with inter-beat interval detection yielding an F1 score of 0.93. Optimal parameters clustered around p = 6-7 for Lp norm and fractional orders of 1.0-1.4. All rPPG-derived parameters reproduced the statistical structure of the reference ECG across conditions and configurations. Caution is advised when using FOD due to slow changes in the rPPG waveform. Overall, 2SR is recommended for PR, while CHROM for HRV estimation, using Lp norm with 20 superpixels, providing clear methodological guidance for rPPG monitoring in driving simulators

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 evaluates rPPG algorithms (2SR, CHROM, POS, PCA) on superpixel facial regions (10 or 20) for remote PR and HRV monitoring in a driving simulator. It introduces Lp-norm and fractional-order derivative (FOD) peak enhancement, applies SNR-based quality assessment to 20 s segments for motion-artifact mitigation, and validates against simultaneous ECG in 29 participants. It reports lowest MAE of 1.92 bpm (sd=1.72) for PR using 2SR+FOD+20 regions, best-case MAEs of 0.061 s (SDNN) and 0.081 s (RMSSD), F1=0.93 for IBI detection, reproduction of ECG statistical structure, optimal parameters p=6-7 and fractional order 1.0-1.4, and recommends 2SR for PR and CHROM for HRV with Lp norm and 20 superpixels.

Significance. If the central claims hold, the work supplies concrete, directly validated performance numbers for rPPG under realistic motion, together with explicit parameter ranges and configuration recommendations that could guide practical deployment in simulators or vehicles. The simultaneous ECG reference and reporting of both PR and HRV metrics (SDNN, RMSSD) plus F1 scores constitute a clear strength.

major comments (2)
  1. [Abstract / Methods (SNR quality assessment)] Abstract (data-cleaning paragraph) and Methods (SNR quality assessment): the manuscript states that an SNR-based gate on 20 s segments is used to remove motion artifacts but supplies no quantitative check that the retained segments preserve the original distribution of HRV statistics. No Kolmogorov-Smirnov test, paired comparison of SDNN/RMSSD before vs. after filtering, or per-condition discard fraction is reported. Because the headline claim that “all rPPG-derived parameters reproduced the statistical structure of the reference ECG” is made on the filtered data only, this omission is load-bearing for the validity of the reproduction result.
  2. [Results (parameter optimization)] Results (parameter-optimization paragraph): the reported optimal ranges (p = 6-7, fractional order 1.0-1.4) are presented without stating whether they were obtained by participant-wise cross-validation, nested validation, or post-hoc selection on the pooled data. If the latter, the quoted “best-case” MAEs may be optimistically biased and the recommendation of specific configurations requires re-evaluation.
minor comments (2)
  1. [Abstract] Abstract: the phrase “clinically acceptable accuracy” is used without citing the specific clinical tolerance thresholds (e.g., <5 bpm or <10 % error) against which the 1.92 bpm MAE is judged.
  2. [Methods] Notation: Lp norm order p and fractional order are introduced without an explicit equation or reference to the precise definition employed (e.g., the fractional derivative operator).

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive comments, which highlight important aspects of methodological transparency. We address each major comment below and will revise the manuscript to incorporate the requested clarifications and additional analyses.

read point-by-point responses

  1. Referee: [Abstract / Methods (SNR quality assessment)] Abstract (data-cleaning paragraph) and Methods (SNR quality assessment): the manuscript states that an SNR-based gate on 20 s segments is used to remove motion artifacts but supplies no quantitative check that the retained segments preserve the original distribution of HRV statistics. No Kolmogorov-Smirnov test, paired comparison of SDNN/RMSSD before vs. after filtering, or per-condition discard fraction is reported. Because the headline claim that “all rPPG-derived parameters reproduced the statistical structure of the reference ECG” is made on the filtered data only, this omission is load-bearing for the validity of the reproduction result.

    Authors: We agree that quantitative verification of the SNR filtering's impact on HRV distributions is necessary to support the reproduction claim. In the revised manuscript, we will add a Kolmogorov-Smirnov test comparing SDNN and RMSSD distributions before versus after the SNR gate, paired comparisons where appropriate, and the per-condition fraction of discarded segments. These additions will be reported in the Methods and Results sections. revision: yes

  2. Referee: [Results (parameter optimization)] Results (parameter-optimization paragraph): the reported optimal ranges (p = 6-7, fractional order 1.0-1.4) are presented without stating whether they were obtained by participant-wise cross-validation, nested validation, or post-hoc selection on the pooled data. If the latter, the quoted “best-case” MAEs may be optimistically biased and the recommendation of specific configurations requires re-evaluation.

    Authors: The reported ranges were identified via grid search on the pooled dataset. We acknowledge this can introduce optimistic bias in the best-case MAEs. In the revision, we will explicitly describe the optimization procedure, note the potential for bias as a limitation, and add a participant-wise cross-validation analysis to re-evaluate and confirm the robustness of the recommended configurations (p=6-7, fractional order 1.0-1.4). revision: yes

Circularity Check

0 steps flagged

No significant circularity; results are direct empirical comparisons to ECG reference

full rationale

The paper's central claims consist of MAE, SDNN/RMSSD errors, and F1 scores obtained by comparing rPPG-derived quantities (from 2SR/CHROM/POS/PCA with Lp-norm or FOD peak enhancement) against simultaneous ECG recordings on the same 20 s segments. These metrics are computed externally and do not reduce, by any equation in the paper, to quantities defined by the paper's own fitted parameters or preprocessing choices. The SNR-based segment filter is a data-cleaning step whose effect on the retained distribution is not itself used to define the reported accuracies. No self-citation chains, uniqueness theorems, or ansatzes imported from prior author work appear in the provided text; the derivation chain is standard signal processing followed by independent validation against an external reference.

Axiom & Free-Parameter Ledger

2 free parameters · 2 axioms · 0 invented entities

The work is an empirical validation study that relies on standard domain assumptions from rPPG literature rather than new mathematical derivations; free parameters are the tuned values for the introduced enhancement methods.

free parameters (2)
  • Lp norm order p = 6-7
    Optimal parameters clustered around p = 6-7 for the Lp norm peak enhancement method.
  • fractional order = 1.0-1.4
    Optimal fractional orders of 1.0-1.4 for the FOD peak enhancement method.
axioms (2)
  • domain assumption Facial video color changes can serve as a proxy for cardiac pulse despite head motion in a driving simulator
    Central premise enabling all rPPG comparisons to ECG in dynamic conditions.
  • domain assumption SNR-based segment selection removes motion artifacts without systematically biasing HRV statistics
    Invoked as the data cleaning mechanism to mitigate motion artifacts.

pith-pipeline@v0.9.1-grok · 5899 in / 1619 out tokens · 31593 ms · 2026-06-30T12:15:47.003301+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

81 extracted references · 73 canonical work pages

  1. [1]

    Cao, R., Azimi, I., Sarhaddi, F., Niela -Vilen, H., Axelin, A., Liljeberg, P., & Rahmani, A. M. (2022). Accuracy assessment of oura ring nocturnal heart rate and heart rate variability in comparison with electrocardiography in time and frequency domains: co mprehensive analysis. Journal of Medical Internet Research , 24(1), e27487. https://doi.org/10.2196/27487

    work page doi:10.2196/27487 2022

  2. [2]

    On the reliability of wearable technology: A tutorial on measuring heart rate and heart rate variability in the wild

    Dudarev, V.; Barral, O.; Zhang, C.; Davis, G.; Enns, J.T. On the reliability of wearable technology: A tutorial on measuring heart rate and heart rate variability in the wild. Sensors 2023, 23, 5863. https://doi.org/10.3390/s23135863

    work page doi:10.3390/s23135863 2023

  3. [3]

    E., & Politis, I

    Barka, R. E., & Politis, I. (2024). Driving into the future: A scoping review of smartwatch use for real -time driver monitoring. Transportation Research Interdisciplinary Perspectives , 25, 101098. https://doi.org/10.1016/j.trip.2024.101098

    work page doi:10.1016/j.trip.2024.101098 2024

  4. [4]

    A., Polak, A

    Prucnal, M. A., Polak, A. G., & Kazienko, P. (2025). Improving the quality of pulse rate variability derived from wearable devices using adaptive, spectrum and nonlinear filtering. Biomedical Signal Processing and Control, 102, 107336. https://doi.org/10.1016/j.bspc.2024.107336

    work page doi:10.1016/j.bspc.2024.107336 2025

  5. [5]

    S., Hegarty-Craver, M., Boyce, M

    Gaur, P., Temple, D. S., Hegarty-Craver, M., Boyce, M. D., Holt, J. R., Wenger, M. F., ... & Dausch, D. E. (2024). Continuous monitoring of heart rate variability in free -living conditions using wearable sensors: Exploratory observational study. JMIR Formative Research, 8, e53977. https://doi.org/10.2196/53977

    work page doi:10.2196/53977 2024

  6. [6]

    A., & De Waard, D

    Brookhuis, K. A., & De Waard, D. (2010). Monitoring drivers’ mental workload in driving simulators using physiological measures. Accident Analysis & Prevention, 42(3), 898-903. https://doi.org/10.1016/j.aap.2009.06.001

    work page doi:10.1016/j.aap.2009.06.001 2010

  7. [7]

    Xiao, H., Liu, T., Sun, Y., Li, Y., Zhao, S., & Avolio, A. (2024). Remote photoplethysmography for heart rate measurement: A review. Biomedical Signal Processing and Control , 88, 105608. https://doi.org/10.1016/j.bspc.2023.105608

    work page doi:10.1016/j.bspc.2023.105608 2024

  8. [8]

    Sakib, S., Hasan, Z., & Roy, N. (2025). A state‐of‐the‐art survey of remote photoplethysmography for contactless health parameters sensing. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 15(3), e70039. https://doi.org/10.1002/widm.70039

    work page doi:10.1002/widm.70039 2025

  9. [9]

    Seo, H., Kim, S., & Lee, E. C. (2025). Estimation of respiratory signals from remote photoplethysmography of RGB facial videos. Electronics, 14(11), 2152. https://doi.org/10.3390/electronics14112152

    work page doi:10.3390/electronics14112152 2025

  10. [10]

    Measuring pulse rate with a webcam

    Lewandowska, M.; Nowak, J. Measuring pulse rate with a webcam. J. Med. Imaging Health Inform . 2012, 2, 87 –

    2012

  11. [11]

    https://doi.org/10.1166/jmihi.2012.1064

    work page doi:10.1166/jmihi.2012.1064 2012

  12. [12]

    Validation of heart rate extraction using video imaging on a built -in camera system of a smartphone

    Kwon, S.; Kim, H.; Park, K.S. Validation of heart rate extraction using video imaging on a built -in camera system of a smartphone. In Proceedings of the 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, San Diego, CA, USA, 28 August –1 September 2012; IEEE: Piscataway, NJ, USA, 2012; pp. 2174–2177. https://doi....

    work page doi:10.1109/embc.2012.6346392 2012

  13. [13]

    Non -contact, automated cardiac pulse measurements using video imaging and blind source separation

    Poh, M.Z.; McDuff, D.J.; Picard, R.W. Non -contact, automated cardiac pulse measurements using video imaging and blind source separation. Opt. Express 2010, 18, 10762–10774. https://doi.org/10.1364/OE.18.010762

    work page doi:10.1364/oe.18.010762 2010

  14. [14]

    Optimal color channel combination across skin tones for remote heart rate measurement in camera -based photoplethysmography

    Ernst, H.; Scherpf, M.; Malberg, H.; Schmidt, M. Optimal color channel combination across skin tones for remote heart rate measurement in camera -based photoplethysmography. Biomedical Signal Processing and Control 2021, 68, 102644. https://doi.org/10.1016/j.bspc.2021.102644. 23

    work page doi:10.1016/j.bspc.2021.102644 2021

  15. [15]

    Non -Contact In-Car Monitoring of Heart Rate: Evaluating the Eulerian Video Magnification Algorithm in a Driving Simulator Study

    Renner, P.; Gleichauf, J.; Winkelmann, S. Non -Contact In-Car Monitoring of Heart Rate: Evaluating the Eulerian Video Magnification Algorithm in a Driving Simulator Study. In Proceedings of the Mensch und Computer 2024 , Karlsruhe, Germany, 1–4 September 2024; pp. 651–654. https://doi.org/10.1145/3670653.3677493

    work page doi:10.1145/3670653.3677493 2024

  16. [16]

    Dasari, A., Prakash, S. K. A., Jeni, L. A., & Tucker, C. S. (2021). Evaluation of biases in remote photoplethysmography methods. NPJ digital medicine, 4(1), 91. https://doi.org/10.1038/s41746-021-00462-z

    work page doi:10.1038/s41746-021-00462-z 2021

  17. [17]

    C., Stuijk, S., & De Haan, G

    Wang, W., Den Brinker, A. C., Stuijk, S., & De Haan, G. (2016). Algorithmic principles of remote PPG. IEEE Transactions on Biomedical Engineering, 64(7), 1479-1491. https://doi.org/10.1109/TBME.2016.2609282

    work page doi:10.1109/tbme.2016.2609282 2016

  18. [18]

    Elgendi, M., Martinelli, I., & Menon, C. (2024). Optimal signal quality index for remote photoplethysmogram sensing. npj Biosensing, 1, 5. https://doi.org/10.1038/s44328-024-00002-1

    work page doi:10.1038/s44328-024-00002-1 2024

  19. [19]

    De Haan, G., & Jeanne, V. (2013). Robust pulse rate from chrominance -based rPPG. IEEE Transactions on Biomedical Engineering, 60(10), 2878-2886. https://doi.org/10.1109/TBME.2013.2266196

    work page doi:10.1109/tbme.2013.2266196 2013

  20. [20]

    Wang, W., Stuijk, S., & De Haan, G. (2015). A novel algorithm for remote photoplethysmography: Spatial subspace rotation. IEEE Transactions on Biomedical Engineering , 63(9), 1974 -1984. https://doi.org/10.1109/TBME.2015.2508602

    work page doi:10.1109/tbme.2015.2508602 2015

  21. [21]

    Eulerian video magnification for revealing subtle changes in the world

    Wu, H.Y.; Rubinstein, M.; Shih, E.; Guttag, J.; Durand, F.; Freeman, W. Eulerian video magnification for revealing subtle changes in the world. ACM Trans. Graph. (TOG) 2012, 31, 1–8. https://doi.org/10.1145/2185520.2185561

    work page doi:10.1145/2185520.2185561 2012

  22. [22]

    Pulse rate assessment: Eulerian video magnification vs

    Miljković, N.; Trifunovi´c, D. Pulse rate assessment: Eulerian video magnification vs. electrocardiography recordings. In Proceedings of the 12th Symposium on Neural Network Applications in Electrical Engineering (NEUREL), Belgrade, Serbia, 25 –27 November 2014; IEEE: Piscataway, NJ, USA, 2012; pp. 17 –20. https://doi.org/10.1109/NEUREL.2014.7011447

    work page doi:10.1109/neurel.2014.7011447 2014

  23. [23]

    D., Stojmenova Pečečnik, K., Sodnik, J., & Miljković, N

    Nešković, Đ. D., Stojmenova Pečečnik, K., Sodnik, J., & Miljković, N. (2025). Contactless pulse rate assessment: Results and insights for application in driving simulators. Applied Sciences , 15(17), 9512. https://doi.org/10.3390/app15179512

    work page doi:10.3390/app15179512 2025

  24. [24]

    G., & Ahuja, N

    Nagar, S., Hasegawa-Johnson, M., Beiser, D. G., & Ahuja, N. (2024). R2I-rPPG: A robust region of interest selection method for remote photoplethysmography to extract heart rate. arXiv preprint arXiv:2410.15851 . https://doi.org/10.48550/arXiv.2410.15851

    work page doi:10.48550/arxiv.2410.15851 2024

  25. [25]

    Pai, A., Veeraraghavan, A., & Sabharwal, A. (2021). HRVCam: robust camera -based measurement of heart rate variability. Journal of biomedical optics, 26(2), 022707-022707. https://doi.org/10.1117/1.JBO.26.2.022707

    work page doi:10.1117/1.jbo.26.2.022707 2021

  26. [26]

    McDuff, D. (2023). Camera measurement of physiological vital signs. ACM Computing Surveys , 55(9), 1 -40. https://doi.org/10.1145/3558518

    work page doi:10.1145/3558518 2023

  27. [27]

    Bobbia, S., Luguern, D., Benezeth, Y., Nakamura, K., Gomez, R., & Dubois, J. (2018). Real -time temporal superpixels for unsupervised remote photoplethysmography. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 1341-1348

    2018

  28. [28]

    Medarević, J., Miljković, N., Stojmenova Pečečnik, K., & Sodnik, J. (2025). Distress detection in VR environment using Empatica E4 wristband and Bittium Faros 360. Frontiers in Physiology , 16, 1480018. https://doi.org/10.3389/fphys.2025.1480018

    work page doi:10.3389/fphys.2025.1480018 2025

  29. [29]

    G., Kim, S

    Yu, S. G., Kim, S. E., Kim, N. H., Suh, K. H., & Lee, E. C. (2021). Pulse rate variability analysis using remote photoplethysmography signals. Sensors, 21(18), 6241. https://doi.org/10.3390/s21186241

    work page doi:10.3390/s21186241 2021

  30. [30]

    Shaffer F., Ginsberg J. P. (2017). An overview of heart rate variability metrics and norms. Frontiers in Public Health 5, 258. https://doi.org/10.3389/fpubh.2017.00258

    work page doi:10.3389/fpubh.2017.00258 2017

  31. [31]

    Finžgar, M., & Podržaj, P. (2020). Feasibility of assessing ultra -short-term pulse rate variability from video recordings. PeerJ, 8, e8342. https://doi.org/10.7717/peerj.8342

    work page doi:10.7717/peerj.8342 2020

  32. [32]

    Pander, T., Przybyła, T., & Czabański, R. (2013). An application of the Lp -norm in robust weighted averaging of biomedical signals. Journal of Medical Informatics & Technologies, 22

    2013

  33. [33]

    Tanasković, I., & Miljković, N. (2023). A new algorithm for fetal heart rate detection: Fractional order calculus approach. Medical Engineering & Physics, 118, 104007. https://doi.org/10.1016/j.medengphy.2023.104007

    work page doi:10.1016/j.medengphy.2023.104007 2023

  34. [34]

    Miljković, N., Popović, N., Djordjević, O., Konstantinović, L., & Šekara, T. B. (2017). ECG artifact cancellation in surface EMG signals by fractional order calculus application. Computer Methods and Programs in Biomedicine , 140, 259-264. https://doi.org/10.1016/j.cmpb.2016.12.017

    work page doi:10.1016/j.cmpb.2016.12.017 2017

  35. [35]

    Design of head -up display interfaces for automated vehicles

    Stojmenova Pečečnik, K., Tomažič, S., Sodnik, J., (2023). Design of head -up display interfaces for automated vehicles. International Journal of Human -Computer Studies. 177, 103060. https://doi.org/10.1016/j.ijhcs.2023.103060

    work page doi:10.1016/j.ijhcs.2023.103060 2023

  36. [36]

    Đ, Miljković N , (2026)

    Nešković D. Đ, Miljković N , (2026). Supplementary Material for Manuscript A Signal Extraction Approach for Remote Heart Rate Variability Assessment Using Proxy Measure in a Driving Simulator , Zenodo https://doi.org/10.5281/zenodo.20354210

    work page doi:10.5281/zenodo.20354210 2026

  37. [37]

    Li, P., Benezeth, Y., Nakamura, K., Gomez, R., & Yang, F. (2019). Model-based region of interest segmentation for remote photoplethysmography. In the 14th International Conference on Computer Vision Theory and Applications , pp. 383-388, SCITEPRESS-Science and Technology Publications. https://dx.doi.org/10.5220/0007389803830388

    work page doi:10.5220/0007389803830388 2019

  38. [38]

    Benezeth, Y., Bobbia, S., Nakamura, K., Gomez, R., & Dubois, J. (2019). Probabilistic signal quality metric for reduced complexity unsupervised remote photoplethysmography. In 2019 13th International Symposium on Medical Information and Communication Technology (ISMICT) , pp. 1 -5, IEEE. https://doi.org/10.1109/ISMICT.2019.8744004. 24

    work page doi:10.1109/ismict.2019.8744004 2019

  39. [39]

    (2023, July)

    Huang, Y., Huang, D., Huang, J., Lu, H., He, M., & Wang, W. (2023, July). Camera wavelength selection for multi- wavelength pulse transit time based blood pressure monitoring. In 2023 45th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC) (pp. 1 -5). IEEE. https://doi.org/10.1109/EMBC40787.2023.10340068

    work page doi:10.1109/embc40787.2023.10340068 2023

  40. [40]

    G., Ernst, S., Blazek, V.,

    Saritas, T., Greber, R., Venema, B., Puelles, V. G., Ernst, S., Blazek, V., ... & Schlieper, G. (2019). Non -invasive evaluation of coronary heart disease in patients with chronic kidney disease using photoplethysmography. Clinical kidney journal, 12(4), 538-545. https://doi.org/10.1093/ckj/sfy135

    work page doi:10.1093/ckj/sfy135 2019

  41. [41]

    Xi, L., Wu, X., Chen, W., Wang, J., & Zhao, C. (2022). Weighted combination and singular spectrum analysis based remote photoplethysmography pulse extraction in low -light environments. Medical engineering & physics , 105, 103822. https://doi.org/10.1016/j.medengphy.2022.103822

    work page doi:10.1016/j.medengphy.2022.103822 2022

  42. [42]

    C., & Lin, Y

    Lin, Y. C., & Lin, Y. H. (2017). A study of color illumination effect on the SNR of rPPG signals. In 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp. 4301-4304, IEEE. https://doi.org/10.1109/EMBC.2017.8037807

    work page doi:10.1109/embc.2017.8037807 2017

  43. [43]

    Pan, J., & Tompkins, W. J. (1985). A real -time QRS detection algorithm. IEEE Tansactions on Biomedical Engineering, (3), 230-236. https://doi.org/10.1109/TBME.1985.325532

    work page doi:10.1109/tbme.1985.325532 1985

  44. [44]

    Guler, S., Golparvar, A., Ozturk, O., Dogan, H., & Yapici, M. K. (2023). Optimal digital filter selection for remote photoplethysmography (rPPG) signal conditioning. Biomedical Physics & Engineering Express , 9(2), 027001. https://iopscience.iop.org/article/10.1088/2057-1976/acaf8a/meta

    work page doi:10.1088/2057-1976/acaf8a/meta 2023

  45. [45]

    Liao, G., Lu, H., Shan, C., & Wang, W. (2023). Plethysmographic waveform features and hemodynamic features for camera-based blood pressure estimation. IEEE Transactions on Instrumentation and Measurement , 73, 1-14. https://doi.org/10.1109/TIM.2023.3338714

    work page doi:10.1109/tim.2023.3338714 2023

  46. [46]

    B., Ben-David, K., Morris, M., Wittels, H

    Kantrowitz, A. B., Ben-David, K., Morris, M., Wittels, H. L., Wishon, M. J., McDonald, S. M., ... & Wittels, S. H. (2025). Pulse rate variability is not the same as heart rate variability: Findings from a large, diverse clinical population study. Frontiers in Physiology, 16, 1630032. https://doi.org/10.3389/fphys.2025.1630032

    work page doi:10.3389/fphys.2025.1630032 2025

  47. [47]

    Schäfer, A., & Vagedes, J. (2013). How accurate is pulse rate variability as an estimate of heart rate variability?: A review on studies comparing photoplethysmographic technology with an electrocardiogram. International Journal of Cardiology, 166(1), 15-29. https://doi.org/10.1016/j.ijcard.2012.03.119

    work page doi:10.1016/j.ijcard.2012.03.119 2013

  48. [48]

    Allen, J., & Murray, A. (2002). Age -related changes in peripheral pulse timing characteristics at the ears, fingers and toes. Journal of Human Hypertension, 16(10), 711-717. https://doi.org/10.1038/sj.jhh.1001478

    work page doi:10.1038/sj.jhh.1001478 2002

  49. [49]

    Allen, J., & Murray, A. (2000). Variability of photoplethysmography peripheral pulse measurements at the ears, thumbs and toes. IEE Proceedings -Science, Measurement and Technology , 147(6), 403 -407. https://doi.org/10.1049/ip-smt:20000846

    work page doi:10.1049/ip-smt:20000846 2000

  50. [50]

    Hsieh, F., & Chen, T. L. (2025). A novel R -peak detection algorithm. IEEE Access , 13, 210351 -210359. https://doi.org/10.1109/ACCESS.2025.3643153

    work page doi:10.1109/access.2025.3643153 2025

  51. [51]

    AAMI, A., & EC57, A. A. M. I. (2008). Testing and reporting performance results of cardiac rhythm and st segment measurement algorithms. American National Standards Institute, Arlington, VA, USA, 43

    2008

  52. [52]

    A., Sidorov, I

    Kamshilin, A. A., Sidorov, I. S., Babayan, L., Volynsky, M. A., Giniatullin, R., & Mamontov, O. V. (2016). Accurate measurement of the pulse wave delay with imaging photoplethysmography. Biomedical optics express, 7(12), 5138-

    2016

  53. [53]

    https://doi.org/10.1364/BOE.7.005138

    work page doi:10.1364/boe.7.005138

  54. [54]

    Fariha, M. A. Z., Ikeura, R., Hayakawa, S., & Tsutsumi, S. (2020, June). Analysis of Pan -Tompkins algorithm performance with noisy ECG signals. In Journal of Physics: Conference Series (Vol. 1532, No. 1, p. 012022). IOP Publishing. https://iopscience.iop.org/article/10.1088/1742-6596/1532/1/012022/meta

    work page doi:10.1088/1742-6596/1532/1/012022/meta 2020

  55. [55]

    Mager, J. (2015). Automatic threshold selection of the peaks over threshold method. Technical University of Munich Department of Mathematics, 114, Master Thesis, Available online: https://mediatum.ub.tum.de/doc/1254349/document.pdf, Accessed on February 26, 2026

    work page arXiv 2015

  56. [56]

    Robust confidence intervals for effect sizes: A comparative study of Cohen’s d and Cliff’s delta under non -normality and heterogeneous variances

    Hess, M.R.; Kromrey, J.D. Robust confidence intervals for effect sizes: A comparative study of Cohen’s d and Cliff’s delta under non -normality and heterogeneous variances. In Proceedings of the Annual Meeting of the American Educational Research Association, San Diego, CA, USA, 12–16 April 2004; Volume 1

    2004

  57. [57]

    F., & Sehgal, N

    Talukdar, D., De Deus, L. F., & Sehgal, N. (2023). The Evaluation of Remote Monitoring Technology Across Participants With Different Skin Tones. Cureus, 15(9). https://doi.org/10.7759/cureus.45075

    work page doi:10.7759/cureus.45075 2023

  58. [58]

    & Zhao, Z

    Wang, K., Wei, Y., Tang, J., Wang, Y., Li, Z., Tong, M., ... & Zhao, Z. (2024, December). Camera -based hrv prediction for remote learning environments. In 2024 IEEE Smart World Congress (SWC) (pp. 1165-1173). IEEE. https://doi.org/10.1109/SWC62898.2024.00185

    work page doi:10.1109/swc62898.2024.00185 2024

  59. [59]

    Y., & Dung, L

    Huang, R. Y., & Dung, L. R. (2016). Measurement of heart rate variability using off -the-shelf smart phones. Biomedical Engineering Online, 15(1), 11. https://doi.org/10.1186/s12938-016-0127-8

    work page doi:10.1186/s12938-016-0127-8 2016

  60. [60]

    L., Chin, J

    Odinaev, I., Wong, K. L., Chin, J. W., Goyal, R., Chan, T. T., & So, R. H. (2023). Robust heart rate variability measurement from facial videos. Bioengineering, 10(7), 851. https://doi.org/10.3390/bioengineering10070851

    work page doi:10.3390/bioengineering10070851 2023

  61. [61]

    Unifying frame rate and temporal dilations for improved remote pulse detection

    Speth, J.; Vance, N.; Flynn, P.; Bowyer, K.; Czajka, A. Unifying frame rate and temporal dilations for improved remote pulse detection. Comput. Vis. Image Underst . 2021, 210, 103246. https://doi.org/10.1016/j.cviu.2021.103246

    work page doi:10.1016/j.cviu.2021.103246 2021

  62. [62]

    Unsupervised skin tissue segmentation for remote photoplethysmography

    Bobbia, S.; Macwan, R.; Benezeth, Y.; Mansouri, A.; Dubois, J. Unsupervised skin tissue segmentation for remote photoplethysmography. Pattern Recognition Letter 2019, 124, 82–90. https://doi.org/10.1016/j.patrec.2017.10.017. 25

    work page doi:10.1016/j.patrec.2017.10.017 2019

  63. [63]

    D., Ahmed, A., & Wegerif, S

    van Putten, L. D., Ahmed, A., & Wegerif, S. (2025). Remote photoplethysmography for contactless pulse rate monitoring: algorithm development and accuracy assessment. Physiological Measurement , 46(11), 115004. https://iopscience.iop.org/article/10.1088/1361-6579/ae1804/meta

    work page doi:10.1088/1361-6579/ae1804/meta 2025

  64. [64]

    Sun, Z., Junttila, J., Tulppo, M., Seppänen, T., & Li, X. (2022). Non -contact atrial fibrillation detection from face videos by learning systolic peaks. IEEE Journal of Biomedical and Health Informatics , 26(9), 4587 -4598. https://doi.org/10.1109/JBHI.2022.3193117

    work page doi:10.1109/jbhi.2022.3193117 2022

  65. [65]

    H., Landesberg, A., & Behar, J

    Kotzen, K., Charlton, P. H., Landesberg, A., & Behar, J. A. (2021, September). Benchmarking photoplethysmography peak detection algorithms using the electrocardiogram signal as a reference. In 2021 Computing in Cardiology (CinC) (Vol. 48, pp. 1-4). IEEE. https://doi.org/10.23919/CinC53138.2021.9662889

    work page doi:10.23919/cinc53138.2021.9662889 2021

  66. [66]

    Boccignone, G., Conte, D., Cuculo, V., d’Amelio, A., Grossi, G., & Lanzarotti, R. (2020). An open framework for remote-PPG methods and their assessment. Ieee Access , 8, 216083 -216103. https://doi.org/10.1109/ACCESS.2020.3040936

    work page doi:10.1109/access.2020.3040936 2020

  67. [67]

    Spiegelberg, J., & Rusz, J. (2017). Can we use PCA to detect small signals in noisy data?. Ultramicroscopy, 172, 40-46. https://doi.org/10.1016/j.ultramic.2016.10.008

    work page doi:10.1016/j.ultramic.2016.10.008 2017

  68. [68]

    Caroppo, A., Manni, A., Rescio, G., Siciliano, P., & Leone, A. (2024). Vital signs estimation in elderly using camera- based photoplethysmography. Multimedia Tools and Applications , 83(24), 65363 -65386. https://doi.org/10.1007/s11042-023-18053-3

    work page doi:10.1007/s11042-023-18053-3 2024

  69. [69]

    Comparison of Apple watch vs KardiaMobile: A tale of two devices

    Lee, C.; Lee, C.; Fernando, C.; Chow, C.M. Comparison of Apple watch vs KardiaMobile: A tale of two devices. CJC Open 2022, 4, 939–945. https://doi.org/10.1016/j.cjco.2022.07.011

    work page doi:10.1016/j.cjco.2022.07.011 2022

  70. [70]

    J., Chahal, T., Stinchcombe, A., Mullen, N., Weaver, B., & Bédard, M

    Johnson, M. J., Chahal, T., Stinchcombe, A., Mullen, N., Weaver, B., & Bédard, M. (2011). Physiological responses to simulated and on -road driving. International journal of Psychophysiology , 81(3), 203 -208. https://doi.org/10.1016/j.ijpsycho.2011.06.012

    work page doi:10.1016/j.ijpsycho.2011.06.012 2011

  71. [71]

    Bondarenko, M., Menon, C., & Elgendi , M. (2025). The role of face regions in remote photoplethysmography for contactless heart rate monitoring. npj Digital Medicine, 8(1), 479. https://doi.org/10.1038/s41746-025-01814-9

    work page doi:10.1038/s41746-025-01814-9 2025

  72. [72]

    Kiddle, A., Barham, H., Wegerif, S., & Petronzio, C. (2023). Dynamic region of interest selection in remote photoplethysmography: Proof -of-concept study. JMIR Formative Research , 7, e44575. https://formative.jmir.org/2023/1/e44575

    2023

  73. [73]

    Y., Lee, K., & Sohn, C

    Kim, D. Y., Lee, K., & Sohn, C. B. (2021). Assessment of roi selection for facial video-based rPPG. Sensors, 21(23),

    2021

  74. [74]

    https://doi.org/10.3390/s21237923

    work page doi:10.3390/s21237923

  75. [75]

    Premkumar, S., & Hemanth, D. J. (2022, August). Intelligent remote photoplethysmography-based methods for heart rate estimation from face videos: A survey. Informatics, 9(3), 57. MDPI. https://doi.org/10.3390/informatics9030057

    work page doi:10.3390/informatics9030057 2022

  76. [76]

    Soares, S., Ferreira, S., & Couto, A. (2020). Driving simulator experiments to study drowsiness: A systematic review. Traffic Injury Prevention, 21(1), 29-37. https://doi.org/10.1080/15389588.2019.1706088

    work page doi:10.1080/15389588.2019.1706088 2020

  77. [77]

    R., & Strayer, D

    Lohani, M., Payne, B. R., & Strayer, D. L. (2019). A review of psychophysiological measures to assess cognitive states in real-world driving. Frontiers in Human Neuroscience, 13, 57. https://doi.org/10.3389/fnhum.2019.00057

    work page doi:10.3389/fnhum.2019.00057 2019

  78. [78]

    & Zaunseder, S

    Rasche, S., Trumpp, A., Waldow, T., Gaetjen, F., Plötze, K., Wedekind, D., ... & Zaunseder, S. (2016). Camera - based photoplethysmography in critical care patients. Clinical Hemorheology and Microcirculation , 64(1), 77-90. https://doi.org/10.3233/CH-162048

    work page doi:10.3233/ch-162048 2016

  79. [79]

    P., Kaminer, K., Nussinovitch, M., Segev, S., Volovitz, B., & Nussinovitch, N

    Nussinovitch, U., Elishkevitz, K. P., Kaminer, K., Nussinovitch, M., Segev, S., Volovitz, B., & Nussinovitch, N. (2011). The efficiency of 10‐second resting heart rate for the evaluation of short‐term heart rate variability indices. Pacing and Clinical Electrophysiology, 34(11), 1498-1502. https://doi.org/10.1111/j.1540-8159.2011.03178.x

    work page doi:10.1111/j.1540-8159.2011.03178.x 2011

  80. [80]

    J., Kirchhof, P., Lip, G

    Developed with the Special Contribution of the European Heart Rhythm Association (EHRA), Endorsed by the European Association for Cardio -Thoracic Surgery (EACTS), Authors/Task Force Members, Camm, A. J., Kirchhof, P., Lip, G. Y., ... & Zupan, I. (2010). Guidelines for the management of atrial fibrillation: the Task Force for the Management of Atrial Fibr...

    work page doi:10.1093/eurheartj/ehq278 2010

Showing first 80 references.