pith. sign in

arxiv: 2604.22695 · v1 · submitted 2026-04-24 · 📡 eess.SP · cs.LG

Time-Localized Parametric Decomposition of Respiratory Airflow for Sub-Breath Analysis

Victoria Ribeiro Rodrigues , Paul W. Davenport , Nicholas J. Napoli This is my paper

Pith reviewed 2026-05-08 10:19 UTC · model grok-4.3

classification 📡 eess.SP cs.LG
keywords respiratory airflowparametric decompositionsub-breath analysisintrabreath morphologybasis functionscognitive fatiguesignal decompositionrespiratory motor control
0
0 comments X

The pith

Decomposing each breath into a few time-localized parametric components reveals sub-breath timing and coordination that standard tidal-volume metrics miss.

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

The paper develops a method to represent inspiratory airflow as a sum of a small number of parameterized basis functions, each defined by its own amplitude, start time, and duration. Conventional analysis uses only whole-breath summaries such as total volume or peak flow, which hide the internal sequence of events within a single breath. By fitting Half-Sine, Gaussian, and Beta shapes through constrained optimization, the approach reconstructs signals with low error and extracts timing features that distinguish cognitive-fatigue states arising from dual-task breathing demands. A sympathetic reader would care because these features supply a direct window into neuromuscular coordination and compensatory adjustments that global descriptors obscure.

Core claim

Inspiratory airflow can be expressed as a sum of time-localized parametric primitives (Half-Sine, Gaussian, and Beta) whose amplitude, onset, and duration are recovered by nonlinear optimization; across 8,276 breaths the four-component model achieves mean squared error below 0.001, and the resulting sub-breath timing and coordination descriptors raise Matthews correlation coefficient for cognitive-fatigue classification by up to 30.7 percent relative to classical respiratory metrics.

What carries the argument

The time-localized parametric decomposition of airflow, in which each component is a physiologically grounded basis function equipped with explicit amplitude, onset time, and duration parameters recovered by constrained nonlinear fitting.

Load-bearing premise

The three chosen basis functions are sufficient to represent the relevant shapes inside every breath without systematic bias or the need for extra components.

What would settle it

A new dataset of breaths whose morphologies produce reconstruction errors that remain high even after adding more components, or whose timing features fail to improve fatigue classification above classical metrics, would falsify the central claim.

Figures

Figures reproduced from arXiv: 2604.22695 by Nicholas J. Napoli, Paul W. Davenport, Victoria Ribeiro Rodrigues.

Figure 1
Figure 1. Figure 1: Comparison of spectral and time–frequency represen view at source ↗
Figure 3
Figure 3. Figure 3: The raw airflow signal (black) is decomposed using view at source ↗
Figure 2
Figure 2. Figure 2: The raw airflow signal (black) is decomposed using view at source ↗
Figure 4
Figure 4. Figure 4: The raw airflow signal (black) is decomposed using view at source ↗
Figure 5
Figure 5. Figure 5: Illustration of timing and amplitude relationships view at source ↗
Figure 6
Figure 6. Figure 6: Mean squared error by number of components for the Hal view at source ↗
Figure 7
Figure 7. Figure 7: Confusion matrices for the top-performing classific view at source ↗
read the original abstract

Respiratory airflow signals provide critical insight into breathing mechanics, yet conventional analysis methods remain limited in their ability to characterize the internal structure of individual breaths. Traditional approaches treat airflow as a quasi-periodic signal and rely on global descriptors such as tidal volume or peak flow, obscuring sub-breath events that reflect neuromuscular coordination and compensatory breathing strategies. This study introduces a parametric framework for decomposing inspiratory airflow into a small number of time-localized components with explicit amplitude, onset time, and duration parameters. Unlike spectral or data-adaptive methods, the proposed approach employs physiologically grounded basis functions, Half-Sine, Gaussian, and Beta, to represent intrabreath waveform morphology through constrained nonlinear optimization. Evaluation across 8,276 breaths demonstrates high reconstruction accuracy (mean squared error $<$ 0.001 for four-component models) and robust parameter precision under moderate noise. Component-derived features describing sub-breath timing and coordination improved classification of cognitive fatigue states arising from cognitive-respiratory competition by up to 30.7% in Matthews correlation coefficient compared with classical respiratory metrics. These results establish that modeling airflow as a sum of parameterized, time-localized primitives provides an interpretable and precise foundation for quantifying intrabreath organization, compensatory breathing dynamics, and respiratory motor control adaptation under cognitive-respiratory dual-task demands.

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 / 1 minor

Summary. The paper introduces a parametric decomposition of inspiratory airflow into a sum of time-localized basis functions (Half-Sine, Gaussian, Beta) with explicit parameters for amplitude, onset, and duration. These are fitted via constrained nonlinear optimization to 8,276 breaths, yielding MSE below 0.001 for four-component models. Component-derived timing and coordination features are then used to classify cognitive fatigue states under dual-task conditions, achieving up to 30.7% higher Matthews correlation coefficient than classical global respiratory metrics. The work positions this as an interpretable foundation for quantifying intrabreath organization and compensatory dynamics.

Significance. If the reconstruction accuracy and classification gains hold under proper validation, the method supplies a physiologically motivated, parameter-efficient alternative to global descriptors or spectral techniques for sub-breath analysis. The large breath count and low reported MSE are concrete strengths that could support applications in assessing respiratory motor control adaptation. The parametric form enables direct quantification of timing offsets and coordination that are otherwise obscured, offering a falsifiable route to studying compensatory strategies.

major comments (3)
  1. [Abstract] Abstract: The central empirical claims (MSE < 0.001 for four-component fits and 30.7% MCC gain) are presented without any description of the optimization constraints, noise model, initialization strategy, or convergence criteria. This directly affects evaluability of both the reconstruction fidelity and the downstream parameter reliability.
  2. [Methods / Evaluation] Basis selection and evaluation: The claim that the Half-Sine/Gaussian/Beta set is collectively sufficient for unbiased intrabreath morphology is load-bearing for all interpretability assertions, yet no phase-aligned residual waveforms, residual autocorrelation, or head-to-head comparison against splines or additional components is provided. Without these, parameter estimates may absorb unmodeled structure, undermining claims about compensatory dynamics.
  3. [Results] Classification results: The reported MCC improvement is an empirical comparison that uses the fitted decomposition parameters as classifier inputs. No details are given on cross-validation procedure, classifier type, feature selection from the decomposition parameters, or statistical significance of the 30.7% gain. This leaves open the possibility that the gain is not robust or is partly circular.
minor comments (1)
  1. [Abstract] The abstract states 8,276 breaths but provides no information on the number of subjects, recording conditions, or breath selection criteria; adding these would improve reproducibility and context for the reported statistics.

Simulated Author's Rebuttal

3 responses · 0 unresolved

We are grateful to the referee for the insightful comments that will help improve the manuscript's clarity and methodological transparency. Below we provide point-by-point responses to the major comments, indicating the revisions we will make.

read point-by-point responses

  1. Referee: [Abstract] Abstract: The central empirical claims (MSE < 0.001 for four-component fits and 30.7% MCC gain) are presented without any description of the optimization constraints, noise model, initialization strategy, or convergence criteria. This directly affects evaluability of both the reconstruction fidelity and the downstream parameter reliability.

    Authors: We concur that the abstract and methods lack sufficient detail on the optimization process, which is critical for evaluating the reported results. In the revised manuscript, we will augment the Methods section with explicit descriptions of the constrained nonlinear optimization setup, including the constraints applied (such as bounds on parameters to ensure physiological plausibility), the noise model employed (additive white Gaussian noise), the initialization strategy (based on preliminary peak detection), and the convergence criteria (relative change in cost function below a threshold). These additions will allow readers to better assess the reliability of the parameter estimates and the reconstruction accuracy. revision: yes

  2. Referee: [Methods / Evaluation] Basis selection and evaluation: The claim that the Half-Sine/Gaussian/Beta set is collectively sufficient for unbiased intrabreath morphology is load-bearing for all interpretability assertions, yet no phase-aligned residual waveforms, residual autocorrelation, or head-to-head comparison against splines or additional components is provided. Without these, parameter estimates may absorb unmodeled structure, undermining claims about compensatory dynamics.

    Authors: We recognize the importance of validating the basis set's adequacy to support our interpretability claims. Although the low MSE suggests effective modeling, we agree that additional diagnostics are warranted. In the revision, we will include phase-aligned average residual waveforms, plots of residual autocorrelation to demonstrate lack of systematic structure, and comparative reconstruction errors using spline approximations with similar parameter counts. These will provide evidence that the selected basis functions capture the essential intrabreath features without significant bias. revision: yes

  3. Referee: [Results] Classification results: The reported MCC improvement is an empirical comparison that uses the fitted decomposition parameters as classifier inputs. No details are given on cross-validation procedure, classifier type, feature selection from the decomposition parameters, or statistical significance of the 30.7% gain. This leaves open the possibility that the gain is not robust or is partly circular.

    Authors: We appreciate this observation regarding the classification analysis. To address concerns about robustness and potential circularity, the revised manuscript will detail the cross-validation strategy (subject-independent folds), the specific classifier employed, the process for selecting and extracting features from the decomposition parameters (e.g., timing and coordination metrics), and the statistical evaluation of the MCC improvement, including confidence intervals or significance tests. This will substantiate that the performance gain is reliable and not artifactual. revision: yes

Circularity Check

0 steps flagged

No circularity in derivation or claims

full rationale

The paper defines a decomposition method using Half-Sine, Gaussian, and Beta bases fitted by constrained nonlinear optimization to raw airflow signals, then extracts timing/coordination features for downstream classification. Reconstruction MSE and MCC gains are reported as empirical outcomes on held-out breaths, not quantities algebraically forced by the fitting equations themselves. No self-citations, uniqueness theorems, or ansatzes are invoked to justify the basis set or performance; the central claim rests on external data validation rather than reducing to its own inputs by construction. This matches the expected non-circular case for a signal-processing method paper.

Axiom & Free-Parameter Ledger

2 free parameters · 2 axioms · 0 invented entities

The central claim rests on the choice of three specific basis functions, the decision to use four components, and the assumption that constrained nonlinear optimization will reliably recover physiologically meaningful parameters; no new physical entities are postulated.

free parameters (2)
  • number of components
    Fixed at four in the reported models; chosen to balance reconstruction accuracy and interpretability.
  • basis-function parameters (amplitude, onset, duration)
    Fitted per breath via nonlinear optimization; these are the primary free parameters of the decomposition.
axioms (2)
  • domain assumption Half-Sine, Gaussian, and Beta functions are physiologically grounded representations of intrabreath airflow morphology
    Invoked to justify the choice of basis set over purely data-driven or spectral alternatives.
  • domain assumption Constrained nonlinear optimization converges to a unique or stable solution for each breath
    Required for the extracted timing and amplitude features to be reliable and comparable across breaths.

pith-pipeline@v0.9.0 · 5535 in / 1559 out tokens · 30120 ms · 2026-05-08T10:19:29.118362+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

60 extracted references · 60 canonical work pages

  1. [1]

    Noninvasive Estimation of Respiratory Mechan ics in Spontaneously Breathing V entilated Patients: A Constrain ed Optimiza- tion Approach,

    F. Vicario, A. Albanese, N. Karamolegkos, D. Wang, A. Sei ver, and N. W. Chbat, “Noninvasive Estimation of Respiratory Mechan ics in Spontaneously Breathing V entilated Patients: A Constrain ed Optimiza- tion Approach,” IEEE Transactions on Biomedical Engineering , vol. 63, pp. 775–787, Apr. 2016

    work page 2016

  2. [2]

    Respiration,

    J. Gray and F. Grodin, “Respiration,” Annual Review Physiology, vol. 13, no. 2, pp. 217–232, 1951

    work page 1951

  3. [3]

    Automated Detection of Sleep Apnea and Hypopnea Events Bas ed on Robust Airflow Envelope Tracking in the Presence of Breath ing Artifacts,

    M. Ciołek, M. Nied´ zwiecki, S. Sieklicki, J. Drozdowski , and J. Siebert, “Automated Detection of Sleep Apnea and Hypopnea Events Bas ed on Robust Airflow Envelope Tracking in the Presence of Breath ing Artifacts,” IEEE Journal of Biomedical and Health Informatics , vol. 19, pp. 418–429, Mar. 2015

    work page 2015

  4. [4]

    Effects of hypercapnia and hypocapnia on ve ntilatory variability and the chaotic dynamics of ventilatory flow in h umans,

    M.-N. Fiamma, C. Straus, S. Thibault, M. Wysocki, P . Baco nnier, and T. Similowski, “Effects of hypercapnia and hypocapnia on ve ntilatory variability and the chaotic dynamics of ventilatory flow in h umans,” American Journal of Physiology-Regulatory, Integrative a nd Compara- tive Physiology , vol. 292, pp. R1985–R1993, May 2007

    work page 2007

  5. [5]

    Neural Mechanisms Under lying Breathing Complexity,

    A. Hess, L. Y u, I. Klein, M. D. Mazancourt, G. Jebrak, H. Ma l, O. Brugière, M. Fournier, M. Courbage, G. Dauriat, E. Schoum an- Clayes, C. Clerici, and L. Mangin, “Neural Mechanisms Under lying Breathing Complexity,” PLOS ONE , vol. 8, p. e75740, Oct. 2013

    work page 2013

  6. [6]

    A Novel Functional Neuron Group for Respiratory Rhythm Generation in the V entral Medulla,

    H. Onimaru and I. Homma, “A Novel Functional Neuron Group for Respiratory Rhythm Generation in the V entral Medulla,” Journal of Neuroscience, vol. 23, pp. 1478–1486, Feb. 2003

    work page 2003

  7. [7]

    Napoli, Characterizing uncertainty in sensor fusion to improve predictive models

    N. Napoli, Characterizing uncertainty in sensor fusion to improve predictive models . Online Archive of University of Virginia, 2018. pages: 1-201

    work page 2018

  8. [8]

    Effect of Gas Density on Res istance to Respiratory Gas Flow in Man,

    A. B. Otis and W. C. Bembower, “Effect of Gas Density on Res istance to Respiratory Gas Flow in Man,” Journal of Applied Physiology , vol. 2, pp. 300–306, Dec. 1949

    work page 1949

  9. [9]

    Effect of chest cage restrictio n on perception of added airflow resistance,

    F. Zechman and R. Wiley, “Effect of chest cage restrictio n on perception of added airflow resistance,” Respiration Physiology, vol. 31, pp. 71–79, Sept. 1977

    work page 1977

  10. [10]

    Physiologic Effects of Respirator Dead Space and Resistance Loading:,

    P . Harber, R. J. Tamimie, A. Bhattacharya, and M. Barber , “Physiologic Effects of Respirator Dead Space and Resistance Loading:,” Journal of Occupational and Environmental Medicine , vol. 24, pp. 681–684, Sept. 1982

    work page 1982

  11. [11]

    Respiratory Changes in Response to Cognit ive Load: A Systematic Review,

    M. Grassmann, E. Vlemincx, A. V on Leupoldt, J. M. Mittel städt, and O. V an Den Bergh, “Respiratory Changes in Response to Cognit ive Load: A Systematic Review,” Neural Plasticity , vol. 2016, pp. 1–16, 2016

    work page 2016

  12. [12]

    Exercise-induced respira tory muscle fatigue: implications for performance,

    L. M. Romer and M. I. Polkey, “Exercise-induced respira tory muscle fatigue: implications for performance,” Journal of Applied Physiology , vol. 104, pp. 879–888, Mar. 2008

    work page 2008

  13. [13]

    Respiratory physiology: adaptations to high-level exercise,

    D. C. McKenzie, “Respiratory physiology: adaptations to high-level exercise,” British Journal of Sports Medicine , vol. 46, pp. 381–384, May 2012

    work page 2012

  14. [14]

    Relationship between neu romuscu- lar respiratory drive and ventilatory output,

    J. Milic-Emili and W. A. Zin, “Relationship between neu romuscu- lar respiratory drive and ventilatory output,” in Comprehensive phys- iology, pp. 631–646, John Wiley & Sons, Ltd, 2011. tex.eprint: https://onlinelibrary.wiley.com/doi/pdf/10.1002/cphy.cp030335

    work page doi:10.1002/cphy.cp030335 2011

  15. [15]

    Exploring inspiratory occlusion metrics to assess respir atory drive in patients under acute intermittent hypoxia,

    V . R. Rodrigues, W. L. Olsen, E. Sajjadi, B. K. Smith, and N. J. Napoli, “Exploring inspiratory occlusion metrics to assess respir atory drive in patients under acute intermittent hypoxia,” Respiratory Physiology & Neurobiology, vol. 304, p. e103922, 2022

    work page 2022

  16. [16]

    A program for cycle-by-cycle shape analysis of biological rhythms. A pplication to respiratory rhythm,

    J.-P . Bachy, A. Eberhard, P . Baconnier, and G. Benchetr it, “A program for cycle-by-cycle shape analysis of biological rhythms. A pplication to respiratory rhythm,” Computer Methods and Programs in Biomedicine , vol. 23, no. 3, pp. 297 – 307, 1986

    work page 1986

  17. [17]

    Frequency and ti me domain analysis of airflow breath patterns in patients with chronic obstructive airway disease,

    S. Abboud, I. Bruderman, and D. Sadeh, “Frequency and ti me domain analysis of airflow breath patterns in patients with chronic obstructive airway disease,” Computers and Biomedical Research , vol. 19, no. 3, pp. 266 – 273, 1986

    work page 1986

  18. [18]

    Individuality of breathing patterns in adults assessed ov er time,

    G. Benchetrit, S. Shea, T. Dinh, S. Bodocco, P . Baconnie r, and A. Guz, “Individuality of breathing patterns in adults assessed ov er time,” Res- piration Physiology, vol. 75, no. 2, pp. 199 – 209, 1989

    work page 1989

  19. [19]

    Methods for averaging irregu lar respiratory flow profiles in awake humans,

    J. Sato and P . A. Robbins, “Methods for averaging irregu lar respiratory flow profiles in awake humans,” Journal of Applied Physiology , vol. 90, no. 2, pp. 705–712, 2001

    work page 2001

  20. [20]

    Assessment of Airflow and Oximetry Signals to De tect Pediatric Sleep Apnea-Hypopnea Syndrome Using AdaBoost,

    J. Jiménez-García, G. C. Gutiérrez-Tobal, M. García, L . Kheirandish- Gozal, A. Martín-Montero, D. Álvarez, F. Del Campo, D. Gozal , and R. Hornero, “Assessment of Airflow and Oximetry Signals to De tect Pediatric Sleep Apnea-Hypopnea Syndrome Using AdaBoost,” Entropy, vol. 22, p. 670, June 2020

    work page 2020

  21. [21]

    Breathi ng Pattern Characterization in Chronic Heart Failure Patients Using t he Respiratory Flow Signal,

    A. Garde, L. Sörnmo, R. Jané, and B. F. Giraldo, “Breathi ng Pattern Characterization in Chronic Heart Failure Patients Using t he Respiratory Flow Signal,” Annals of Biomedical Engineering , vol. 38, pp. 3572– 3580, Dec. 2010

    work page 2010

  22. [22]

    N on- contact sleep stage detection using canonical correlation analysis of respiratory sound,

    B. Xue, B. Deng, H. Hong, Z. Wang, X. Zhu, and D. D. Feng, “N on- contact sleep stage detection using canonical correlation analysis of respiratory sound,” IEEE Journal of Biomedical and Health Informatics , vol. 24, no. 2, pp. 614–625, 2020

    work page 2020

  23. [23]

    Re spiratory anomaly and disease detection using multi-level temporal c onvolutional networks,

    K.-N. T. Le, G. Byun, S. M. Raza, D.-T. Le, and H. Choo, “Re spiratory anomaly and disease detection using multi-level temporal c onvolutional networks,” IEEE Journal of Biomedical and Health Informatics , vol. 29, no. 7, pp. 4834–4846, 2025

    work page 2025

  24. [24]

    Automatic respiratory event scoring in obstructive sleep apnea using a long short-term memory neural network,

    S. Nikkonen, H. Korkalainen, A. Leino, S. Myllymaa, B. D uce, T. Lep- pänen, and J. Töyräs, “Automatic respiratory event scoring in obstructive sleep apnea using a long short-term memory neural network,” IEEE Journal of Biomedical and Health Informatics , vol. 25, no. 8, pp. 2917– 2927, 2021

    work page 2021

  25. [25]

    R. N. Bracewell, The fourier transform and its applications . New Y ork: McGraw-Hill, 3rd ed., 2000

    work page 2000

  26. [26]

    Cohen, Time-frequency analysis

    L. Cohen, Time-frequency analysis. Englewood Cliffs, NJ: Prentice Hall, 1995

    work page 1995

  27. [27]

    Short term spectral analysis, synthesis, an d modification by discrete Fourier transform,

    J. Allen, “Short term spectral analysis, synthesis, an d modification by discrete Fourier transform,” IEEE Transactions on Acoustics, Speech, and Signal Processing , vol. 25, pp. 235–238, June 1977

    work page 1977

  28. [28]

    Theory of communication,

    D. Gabor, “Theory of communication,” Journal of the Institution of Electrical Engineers-Part III: Radio and Communication En gineering, vol. 93, no. 26, pp. 429–457, 1946

    work page 1946

  29. [29]

    The analys is of patients’ airflow with respect to early detection of sleep apnea,

    M. Ciolek, S. Sieklicki, and J. Drozdowski, “The analys is of patients’ airflow with respect to early detection of sleep apnea,” in 3rd Inter- JOURNAL OF LATEX CLASS FILES, VOL. 14, NO. 8, AUGUST 2015 18 national Conference on Human System Interaction , (Rzeszow, Poland), pp. 241–245, IEEE, May 2010

    work page 2015

  30. [30]

    Classıfıcation of sleep apnea by using wavelet transform and artificial neural netwo rks,

    M. Emin Tagluk, M. Akin, and N. Sezgin, “Classıfıcation of sleep apnea by using wavelet transform and artificial neural netwo rks,” Expert Systems with Applications , vol. 37, pp. 1600–1607, Mar. 2010

    work page 2010

  31. [31]

    Wavelet Analysis of Overnight Airflow to Detect Obstructiv e Sleep Apnea in Children,

    V . Barroso-García, G. C. Gutiérrez-Tobal, D. Gozal, F. V aquerizo-Villar, D. Álvarez, F. Del Campo, L. Kheirandish-Gozal, and R. Horne ro, “Wavelet Analysis of Overnight Airflow to Detect Obstructiv e Sleep Apnea in Children,” Sensors, vol. 21, p. 1491, Feb. 2021

    work page 2021

  32. [32]

    Machine Learnin g Based Auto- matic Classification of Respiratory Signals using Wavelet T ransform,

    A. Y adav, M. K. Dutta, and J. Prinosil, “Machine Learnin g Based Auto- matic Classification of Respiratory Signals using Wavelet T ransform,” in 2020 43rd International Conference on Telecommunications and Signal Processing (TSP) , pp. 545–549, July 2020

    work page 2020

  33. [33]

    Signal processing usi ng Fourier & wavelet transform for pulse oximetry,

    J. Kim, S. Kim, D. Lee, and H. Lim, “Signal processing usi ng Fourier & wavelet transform for pulse oximetry,” in Technical Digest. CLEO/Pacific Rim 2001. 4th Pacific Rim Conference on Lasers an d Electro-Optics (Cat. No.01TH8557) , vol. 2, pp. II–II, July 2001

    work page 2001

  34. [34]

    A theory for multiresolution signal decomp osition: The wavelet representation,

    S. Mallat, “A theory for multiresolution signal decomp osition: The wavelet representation,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 11, no. 7, pp. 674–693, 1989

    work page 1989

  35. [35]

    Orthonormal bases of compactly suppor ted wavelets,

    I. Daubechies, “Orthonormal bases of compactly suppor ted wavelets,” Communications on Pure and Applied Mathematics , vol. 41, no. 7, pp. 909–996, 1988

    work page 1988

  36. [36]

    CNN-MoE based framework for classification of respiratory anomalies and lung disease detection,

    L. Pham, H. Phan, R. Palaniappan, A. Mertins, and I. McLo ughlin, “CNN-MoE based framework for classification of respiratory anomalies and lung disease detection,” IEEE Journal of Biomedical and Health Informatics, vol. 25, no. 8, pp. 2938–2947, 2021

    work page 2021

  37. [37]

    A lightweight CNN model for detecting respiratory disease s from lung auscultation sounds using EMD-CWT-based hybrid scalogram ,

    S. B. Shuvo, S. N. Ali, S. I. Swapnil, T. Hasan, and M. I. H. Bhuiyan, “A lightweight CNN model for detecting respiratory disease s from lung auscultation sounds using EMD-CWT-based hybrid scalogram ,” IEEE Journal of Biomedical and Health Informatics , vol. 25, no. 7, pp. 2595– 2603, 2021

    work page 2021

  38. [38]

    Detect ion of Sleep Disordered Breathing and Its Central/Obstructive Ch aracter Using Nasal Cannula and Finger Pulse Oximeter,

    D. Sommermeyer, D. Zou, L. Grote, and J. Hedner, “Detect ion of Sleep Disordered Breathing and Its Central/Obstructive Ch aracter Using Nasal Cannula and Finger Pulse Oximeter,” Journal of Clinical Sleep Medicine, vol. 08, no. 05, pp. 527–533

    work page

  39. [39]

    Rapid screening test for sle ep apnea using a nonlinear and nonstationary signal processing technique ,

    J. I. Salisbury and Y . Sun, “Rapid screening test for sle ep apnea using a nonlinear and nonstationary signal processing technique ,” Medical Engineering & Physics , vol. 29, pp. 336–343, Apr. 2007

    work page 2007

  40. [40]

    EMD and PCA for the Prediction of Sleep Apnoea: A Comparative Study,

    H. Robertson, J. Soraghan, C. Idzikowski, and B. Conway , “EMD and PCA for the Prediction of Sleep Apnoea: A Comparative Study, ” in 2007 IEEE International Symposium on Signal Processing and Info rmation Technology, pp. 419–424, Dec. 2007

    work page 2007

  41. [41]

    Ensemb le em- pirical mode decomposition with principal component analy sis: a novel approach for extracting respiratory rate and heart rate fro m photoplethys- mographic signal,

    M. A. Motin, C. K. Karmakar, and M. Palaniswami, “Ensemb le em- pirical mode decomposition with principal component analy sis: a novel approach for extracting respiratory rate and heart rate fro m photoplethys- mographic signal,” IEEE Journal of Biomedical and Health Informatics , vol. 22, no. 3, pp. 766–774, 2018

    work page 2018

  42. [42]

    Estimation of respiratory rate from photople thysmo- graphic imaging videos compared to pulse oximetry,

    W. Karlen, A. Garde, D. Myers, C. Scheffer, J. M. Ansermi no, and G. A. Dumont, “Estimation of respiratory rate from photople thysmo- graphic imaging videos compared to pulse oximetry,” IEEE Journal of Biomedical and Health Informatics , vol. 19, no. 4, pp. 1331–1338, 2015

    work page 2015

  43. [43]

    Automatic differenti ation of normal and continuous adventitious respiratory sounds using ense mble empirical mode decomposition and instantaneous frequency,

    M. Lozano, J. A. Fiz, and R. Jané, “Automatic differenti ation of normal and continuous adventitious respiratory sounds using ense mble empirical mode decomposition and instantaneous frequency,” IEEE Journal of Biomedical and Health Informatics , vol. 20, no. 2, pp. 486–497, 2016

    work page 2016

  44. [44]

    Novel breath ing pattern analysis: Symmetric Projection Attractor Reconstruction improves iden- tification of impending COPD re-exacerbations – a retrospec tive cohort analysis,

    M. Serna-Pascual, R. F. D’Cruz, M. V olovaya, C. J. Jolle y, N. Hart, G. F. Rafferty, J. Steier, P . J. Aston, and M. Nandi, “Novel breath ing pattern analysis: Symmetric Projection Attractor Reconstruction improves iden- tification of impending COPD re-exacerbations – a retrospec tive cohort analysis,” ERJ Open Research , vol. 9, pp. 00164–2023, July 2023

    work page 2023

  45. [45]

    Comprehensive analysis system for automat ed respira- tory cycle segmentation and crackle peak detection,

    I. McLane, E. Lauwers, T. Stas, I. Busch-Vishniac, K. Id es, S. V erhulst, and J. Steckel, “Comprehensive analysis system for automat ed respira- tory cycle segmentation and crackle peak detection,” IEEE Journal of Biomedical and Health Informatics , vol. 26, no. 4, pp. 1847–1860, 2022

    work page 2022

  46. [46]

    Attractor reconstr uction of breath- ing dynamics: Characterising respiratory dysfunction in C OPD,

    P . Chanchotisatien and D. Arvind, “Attractor reconstr uction of breath- ing dynamics: Characterising respiratory dysfunction in C OPD,” IEEE Journal of Biomedical and Health Informatics , vol. 29, no. 12, pp. 8687– 8694, 2025

    work page 2025

  47. [47]

    Inclusi on of respiratory frequency information in heart rate variabili ty analysis for stress assessment,

    A. Hernando, J. Lázaro, E. Gil, A. Arza, J. M. Garzón, R. L ópez-Antón, C. de la Cámara, P . Laguna, J. Aguiló, and R. Bailón, “Inclusi on of respiratory frequency information in heart rate variabili ty analysis for stress assessment,” IEEE Journal of Biomedical and Health Informatics , vol. 20, no. 4, pp. 1016–1025, 2016

    work page 2016

  48. [48]

    Quantifying posttr aumatic stress disorder symptoms during traumatic memories using i nterpretable markers of respiratory variability,

    A. H. Gazi, J. A. Sanchez-Perez, G. L. Saks, E. A. P . Alday , A. Haffar, H. Ahmed, D. Herraka, N. Tarlapally, N. L. Smith, J. D. Bremne r, A. J. Shah, O. T. Inan, and V . V accarino, “Quantifying posttr aumatic stress disorder symptoms during traumatic memories using i nterpretable markers of respiratory variability,” IEEE Journal of Biomedical and Healt...

    work page 2024

  49. [49]

    Breathing pattern in humans: diversit y and individuality,

    G. Benchetrit, “Breathing pattern in humans: diversit y and individuality,” Respiration Physiology, vol. 122, pp. 123–129, Sept. 2000

    work page 2000

  50. [50]

    Drive and timing co mponents of ventilation,

    J. Milic-Emili and M. M. Grunstein, “Drive and timing co mponents of ventilation,” Chest, vol. 70, pp. 131–133, July 1976

    work page 1976

  51. [51]

    Char acterizing and Modeling Breathing Dynamics: Flow Rate, Rhythm, Period , and Frequency,

    N. J. Napoli, V . R. Rodrigues, and P . W. Davenport, “Char acterizing and Modeling Breathing Dynamics: Flow Rate, Rhythm, Period , and Frequency,” Frontiers in Physiology , vol. 12, 2022

    work page 2022

  52. [52]

    The empirical mode decompos ition and the Hilbert spectrum for nonlinear and non-stationary t ime series analysis,

    N. E. Huang, Z. Shen, S. R. Long, M. C. Wu, H. H. Shih, Q. Zhe ng, N.- C. Y en, C. C. Tung, and H. H. Liu, “The empirical mode decompos ition and the Hilbert spectrum for nonlinear and non-stationary t ime series analysis,” Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences , vol. 454, pp. 903–995, Mar. 1998

    work page 1998

  53. [53]

    An interior poi nt algorithm for large-scale nonlinear programming,

    R. H. Byrd, M. E. Hribar, and J. Nocedal, “An interior poi nt algorithm for large-scale nonlinear programming,” SIAM Journal on Optimization , vol. 9, pp. 877–900, Jan. 1999

    work page 1999

  54. [54]

    A trust region method based on interior point techniques for nonlinear programming,

    R. H. Byrd, J. C. Gilbert, and J. Nocedal, “A trust region method based on interior point techniques for nonlinear programming,” Mathematical Programming, vol. 89, pp. 149–185, Nov. 2000

    work page 2000

  55. [55]

    An inter ior algorithm for nonlinear optimization that combines line search and tr ust region steps,

    R. Waltz, J. Morales, J. Nocedal, and D. Orban, “An inter ior algorithm for nonlinear optimization that combines line search and tr ust region steps,” Mathematical Programming, vol. 107, pp. 391–408, Nov. 2005

    work page 2005

  56. [56]

    Chest wall restriction device for modeling re spiratory challenges and dysfunction,

    V . Ribeiro Rodrigues, L. Mejia, R. G. Zucchi, P . W. Daven port, and N. J. Napoli, “Chest wall restriction device for modeling re spiratory challenges and dysfunction,” Frontiers in Medical Engineering , vol. 3, May 2025

    work page 2025

  57. [57]

    Respiratory Care of Patients With Neuro muscular Dis- ease,

    J. O. Benditt, “Respiratory Care of Patients With Neuro muscular Dis- ease,” Respiratory Care, vol. 64, pp. 679–688, June 2019

    work page 2019

  58. [58]

    Methods and Applicat ions in Res- piratory Physiology: Respiratory Mechanics, Drive and Mus cle Function in Neuromuscular and Chest Wall Disorders,

    N. Patel, K. Chong, and A. Baydur, “Methods and Applicat ions in Res- piratory Physiology: Respiratory Mechanics, Drive and Mus cle Function in Neuromuscular and Chest Wall Disorders,” Frontiers in Physiology , vol. 13, p. 838414, June 2022

    work page 2022

  59. [59]

    Timing of activation of different inspiratory muscles dur ing incremental inspiratory loading in healthy adults: A cross-sectional s tudy,

    U. Matsumura, A. Rodrigues, T. Mori, P . Rassam, M. V an Ho llebeke, D. Rozenberg, L. Brochard, E. C. Goligher, D. Roblyer, and W. D. Reid, “Timing of activation of different inspiratory muscles dur ing incremental inspiratory loading in healthy adults: A cross-sectional s tudy,” Canadian Journal of Respiratory Therapy: CJRT = Revue Canadienne de l a Thér...

    work page 2025

  60. [60]

    Neural respiratory drive and breathlessness in COPD,

    C. J. Jolley, Y . M. Luo, J. Steier, G. F. Rafferty, M. I. Po lkey, and J. Moxham, “Neural respiratory drive and breathlessness in COPD,” European Respiratory Journal , vol. 45, pp. 355–364, Jan. 2015

    work page 2015