pith. sign in

arxiv: 2605.18588 · v1 · pith:AKW4UOXMnew · submitted 2026-05-18 · 📊 stat.ME · q-bio.QM

OSSMM: An Open-Source Sleep Monitor and Modulator

Jonny Giordano , Fergal Stapleton , Gabriel Palma , Barak A. Pearlmutter This is my paper

Pith reviewed 2026-05-20 08:30 UTC · model grok-4.3

classification 📊 stat.ME q-bio.QM
keywords open-source sleep monitorwearable headbandCTPU electrodessleep stagingmachine learning classificationfrontal biosignalsdifferential EEGaffordable sleep research
0
0 comments X

The pith

A low-cost open-source headband using two frontal electrodes without ground reference captures biosignals for four-stage sleep classification by machine learning.

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

The paper presents OSSMM, a wearable headband and Android app built from 3D prints and commercial parts at under 40 euros material cost. It shows that a differential signal from two frontal CTPU electrodes, without any dedicated ground, yields spectral features in canonical EEG bands that let standard machine learning models classify sleep into Wake, Light Sleep, Deep Sleep, and REM stages. Performance reaches a macro F1-score of 0.770 and accuracy of 0.776 when compared to a validated non-contact reference monitor in one participant over 15 nights. The system also records movement, pulse, and EOG while including a vibration motor for potential modulation, all without gels or specialized equipment. Open release of designs and code aims to let others replicate or extend the platform for broader sleep research.

Core claim

The central claim is that inexpensive reusable CTPU electrodes from fitness straps, placed frontally to record a differential signal without a ground reference, produce a biosignal whose power spectrum in standard frequency bands supplies the dominant features for conventional machine learning to achieve four-stage sleep staging at macro F1 of 0.770 and accuracy of 0.776 over 15 nights in one subject, with the signal also showing spindle-like signatures.

What carries the argument

The two frontal CTPU electrodes recording a ground-reference-free differential biosignal whose spectral content in EEG bands serves as the primary input driving the sleep-stage classifier.

If this is right

  • Sleep staging becomes feasible with far fewer electrodes and simpler wiring than conventional multi-channel EEG setups.
  • The fully open hardware and software let researchers build, modify, and deploy their own low-cost monitors without commercial licensing barriers.
  • Wireless capture of multiple biosignals including putative EEG supports extended home recordings without daily electrode replacement.
  • An onboard vibration motor creates the possibility of closed-loop experiments that both monitor and attempt to modulate sleep in real time.

Where Pith is reading between the lines

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

  • The minimal electrode count could shorten setup time and improve comfort for users conducting multi-week sleep studies at home.
  • Replicating the device across different age groups or clinical populations would test whether the same spectral features remain discriminative.
  • Pairing the monitor with the vibration modulator invites experiments on whether targeted stimulation during specific sleep stages alters next-day cognitive measures.

Load-bearing premise

That the classification performance seen in a single participant across 15 nights shows the two-electrode frontal configuration works for practical sleep staging beyond this one case.

What would settle it

Collecting data from several additional participants with simultaneous polysomnography and finding macro F1 scores well below 0.7 would indicate the minimal electrode setup does not generalize reliably.

Figures

Figures reproduced from arXiv: 2605.18588 by Barak A. Pearlmutter, Fergal Stapleton, Gabriel Palma, Jonny Giordano.

Figure 1
Figure 1. Figure 1: OSSMM headband compared with C1 coin. A major challenge in sleep research is collecting data in an ecological manner, minimizing disturbance during measure￾ment. Size and felt-weight were therefore minimized as much as possible [PITH_FULL_IMAGE:figures/full_fig_p002_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: The OSSMM Headband with interchangeable parts [PITH_FULL_IMAGE:figures/full_fig_p003_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: REM observation in Night 14 capturing portions of [PITH_FULL_IMAGE:figures/full_fig_p005_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Spectrogram and time-series plot of the EOG channel [PITH_FULL_IMAGE:figures/full_fig_p005_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Classification performance between SVM, RF, and XGB [PITH_FULL_IMAGE:figures/full_fig_p006_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Random Forest Classifier: (a) Normalized confusion matrix on withheld test data, and (b) top 10 feature importance [PITH_FULL_IMAGE:figures/full_fig_p007_6.png] view at source ↗
read the original abstract

We present the Open-Source Sleep Monitor and Modulator (OSSMM), an open-source hardware and software platform for accessible sleep research. The OSSMM comprises a small wearable headband built from 3D prints and affordable commercial-off-the-shelf (COTS) components at a material cost under 40 euros, supported by a companion Android application. The system requires no conductive gels, disposable electrodes, or specialized equipment, and captures multiple biosignals movement, pulse, electrooculography (EOG), and putative electroencephalography (EEG) with wireless connectivity for data storage and potential sleep modulation capability via an onboard vibration motor. A proof-of-concept single-participant evaluation across 15 nights demonstrated that the captured biosignals support four-stage sleep classification (Wake, Light Sleep, Deep Sleep, REM) using conventional machine learning methods, with the best-performing model achieving a Macro F1-score of 0.770 and accuracy of 0.776 against a validated non-contact sleep monitor ($\kappa$=0.63 with PSG). Two technical findings are of particular note. First, inexpensive, reusable conductive thermoplastic polyurethane (CTPU) electrodes from commercial fitness chest straps captured a differential signal whose spectral properties in canonical EEG frequency bands, including signatures consistent with sleep spindles, are the principal features driving classification. Second, this signal is obtained from just two frontal electrodes without a dedicated ground reference, suggesting that practical sleep staging is achievable with simpler configurations than typically employed. All hardware designs, software, and build instructions are openly available to support replication and modification by the research community.

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 / 3 minor

Summary. The paper presents OSSMM, an open-source low-cost wearable headband (<40 euros in COTS parts) with 3D-printed components, an Android companion app, and wireless data handling for capturing movement, pulse, EOG, and putative EEG biosignals. A proof-of-concept single-participant study over 15 nights shows that a differential signal from two frontal reusable CTPU electrodes (no dedicated ground) yields spectral features in canonical bands, including spindle-like signatures, that support conventional ML-based four-stage sleep classification (Wake, Light Sleep, Deep Sleep, REM) with best-model Macro F1 of 0.770 and accuracy of 0.776 against a non-contact reference (κ=0.63 vs PSG). All designs, software, and instructions are released openly.

Significance. If the empirical findings hold under broader testing, the work supplies a genuinely accessible, modifiable platform that could expand sleep research beyond specialized labs by demonstrating usable staging signals from a minimal two-electrode frontal montage. The open-source release of hardware, firmware, and analysis code is a concrete strength that directly supports replication and community-driven improvement.

major comments (2)
  1. [Abstract and proof-of-concept evaluation] Abstract and proof-of-concept evaluation: the reported Macro F1 of 0.770 and accuracy of 0.776 rest entirely on within-subject cross-validation from one participant across 15 nights. Anatomical factors (frontal bone thickness, hair density, contact impedance) can alter common-mode rejection and spectral content; without data from additional subjects the claim that this two-electrode configuration without ground reference supports practical, generalizable sleep staging remains untested and load-bearing for the central contribution.
  2. [Evaluation section] Evaluation section: the reference standard is a non-contact monitor whose own agreement with PSG is only moderate (κ=0.63). This introduces an upper bound on achievable performance metrics and should be accompanied by explicit discussion of how label noise affects the reported F1 and accuracy figures.
minor comments (3)
  1. [Methods] The manuscript would benefit from a supplementary table listing the exact feature set (band powers, spindle detection metrics, etc.) and the hyper-parameter search ranges used for each classifier.
  2. [Hardware description] Figure showing electrode placement should include measured inter-electrode distance and a note on how the differential signal is obtained without an explicit ground.
  3. [Data and code availability] The repository link and commit hash for the analysis code should be stated in the main text to facilitate immediate replication.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive and detailed comments. We address each major comment below and outline the revisions we will make to strengthen the manuscript.

read point-by-point responses

  1. Referee: [Abstract and proof-of-concept evaluation] Abstract and proof-of-concept evaluation: the reported Macro F1 of 0.770 and accuracy of 0.776 rest entirely on within-subject cross-validation from one participant across 15 nights. Anatomical factors (frontal bone thickness, hair density, contact impedance) can alter common-mode rejection and spectral content; without data from additional subjects the claim that this two-electrode configuration without ground reference supports practical, generalizable sleep staging remains untested and load-bearing for the central contribution.

    Authors: We agree that the evaluation is confined to a single participant and constitutes a proof-of-concept rather than a demonstration of generalizability. The manuscript already frames the work in these terms, but we will revise the abstract and add an explicit limitations paragraph in the discussion to state that inter-subject anatomical variability may affect signal quality and that multi-subject validation is required before any claim of practical, generalizable sleep staging can be made. The primary contribution remains the open-source platform intended to enable such validation by the community. revision: yes

  2. Referee: [Evaluation section] Evaluation section: the reference standard is a non-contact monitor whose own agreement with PSG is only moderate (κ=0.63). This introduces an upper bound on achievable performance metrics and should be accompanied by explicit discussion of how label noise affects the reported F1 and accuracy figures.

    Authors: We accept this point. The moderate agreement of the reference device with PSG introduces label noise that bounds the attainable metrics. We will revise the evaluation section to include a dedicated discussion of this limitation, explaining how the reported κ=0.63 constrains interpretation of the Macro F1 and accuracy values and noting the implications of label noise for the observed performance. revision: yes

Circularity Check

0 steps flagged

No circularity: empirical ML results on collected biosignals

full rationale

The paper reports hardware design and a proof-of-concept evaluation consisting of data collection over 15 nights from one participant followed by standard supervised machine-learning classification of four sleep stages. Performance figures (Macro F1 0.770, accuracy 0.776) are obtained by training and testing models on spectral features extracted from the recorded signals and comparing against a non-contact reference; no equations, fitted parameters, or self-citations are invoked that would make these metrics equivalent to the inputs by construction. The derivation chain is therefore self-contained empirical measurement rather than a closed logical loop.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

The platform rests on standard domain assumptions about biosignal interpretation and ML applicability rather than new free parameters or invented entities; the key untested premise is generalization from single-subject data.

axioms (1)
  • domain assumption A differential signal recorded from two frontal CTPU electrodes without dedicated ground reference contains spectral content in canonical EEG bands sufficient for four-stage sleep classification.
    This premise is invoked when the authors conclude that simpler electrode configurations than typically employed are practical for sleep staging.

pith-pipeline@v0.9.0 · 5825 in / 1419 out tokens · 38441 ms · 2026-05-20T08:30:08.892927+00:00 · methodology

discussion (0)

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

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

What do these tags mean?
matches
The paper's claim is directly supported by a theorem in the formal canon.
supports
The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends
The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses
The paper appears to rely on the theorem as machinery.
contradicts
The paper's claim conflicts with a theorem or certificate in the canon.
unclear
Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

36 extracted references · 36 canonical work pages

  1. [1]

    Cerebral states during sleep, as studied by human brain potentials

    A. L. Loomis, E. N. Harvey, and G. A. Hobart, “Cerebral states during sleep, as studied by human brain potentials.”Journal of experimental psychology, vol. 21, no. 2, p. 127, 1937

    work page 1937

  2. [2]

    Regularly occurring periods of eye motility, and concomitant phenomena, during sleep,

    E. Aserinsky and N. Kleitman, “Regularly occurring periods of eye motility, and concomitant phenomena, during sleep,”Science, vol. 118, no. 3062, pp. 273–274, 1953

    work page 1953

  3. [3]

    REM sleep reduction effects on depression syndromes,

    G. W. V ogel, A. Thurmond, P. Gibbons, K. Sloan, M. Boyd, and M. Walker, “REM sleep reduction effects on depression syndromes,” Archives of General Psychiatry, vol. 32, no. 6, pp. 765–777, 1975

    work page 1975

  4. [4]

    History of the development of sleep medicine in the united states,

    J. W. Shepard, D. J. Buysse, A. L. Chesson, W. C. Dement, R. Goldberg, C. Guilleminault, C. D. Harris, C. Iber, E. Mignot, M. M. Mitleret al., “History of the development of sleep medicine in the united states,” Journal of clinical sleep medicine, vol. 1, no. 01, pp. 61–82, 2005

    work page 2005

  5. [5]

    REM sleep dysregulation in depression: state of the art,

    L. Palagini, C. Baglioni, A. Ciapparelli, A. Gemignani, and D. Riemann, “REM sleep dysregulation in depression: state of the art,”Sleep medicine reviews, vol. 17, no. 5, pp. 377–390, 2013

    work page 2013

  6. [6]

    EEG frontal alpha asymmetry and dream affect: Alpha oscillations over the right frontal cortex during rem sleep and presleep wakefulness predict anger in REM sleep dreams,

    P. Sikka, A. Revonsuo, V . Noreika, and K. Valli, “EEG frontal alpha asymmetry and dream affect: Alpha oscillations over the right frontal cortex during rem sleep and presleep wakefulness predict anger in REM sleep dreams,”Journal of Neuroscience, vol. 39, no. 24, pp. 4775–4784, 2019

    work page 2019

  7. [7]

    Closed- loop slow-wave tACS improves sleep-dependent long-term memory generalization by modulating endogenous oscillations,

    N. Ketz, A. P. Jones, N. B. Bryant, V . P. Clark, and P. K. Pilly, “Closed- loop slow-wave tACS improves sleep-dependent long-term memory generalization by modulating endogenous oscillations,”Journal of Neuroscience, vol. 38, no. 33, pp. 7314–7326, 2018

    work page 2018

  8. [8]

    Darien, IL: American Academy of Sleep Medicine, 2023

    AASM,AASM Manual for the Scoring of Sleep and Associated Events, version 3 ed. Darien, IL: American Academy of Sleep Medicine, 2023

    work page 2023

  9. [9]

    An economic evaluation of home versus laboratory-based diagnosis of obstructive sleep apnea,

    R. D. Kim, V . K. Kapur, J. Redline-Bruch, M. Rueschman, D. H. Auckley, R. M. Benca, N. R. Foldvary-Schafer, C. Iber, P. C. Zee, C. L. Rosenet al., “An economic evaluation of home versus laboratory-based diagnosis of obstructive sleep apnea,”Sleep, vol. 38, no. 7, pp. 1027–1037, 2015

    work page 2015

  10. [10]

    Effects of REM sleep awakenings and related wakening paradigms on the ultradian sleep cycle and the symptoms in depression,

    M. Gr ¨ozinger, P. K ¨ogel, and J. R ¨oschke, “Effects of REM sleep awakenings and related wakening paradigms on the ultradian sleep cycle and the symptoms in depression,”Journal of psychiatric research, vol. 36, no. 5, pp. 299–308, 2002

    work page 2002

  11. [11]

    A validation of six wearable devices for estimating sleep, heart rate and heart rate variability in healthy adults,

    D. J. Miller, C. Sargent, and G. D. Roach, “A validation of six wearable devices for estimating sleep, heart rate and heart rate variability in healthy adults,”Sensors, vol. 22, no. 16, p. 6317, 2022

    work page 2022

  12. [12]

    Deepsleepnet: A model for automatic sleep stage scoring based on raw single-channel EEG,

    A. Supratak, H. Dong, C. Wu, and Y . Guo, “Deepsleepnet: A model for automatic sleep stage scoring based on raw single-channel EEG,”IEEE transactions on neural systems and rehabilitation engineering, vol. 25, no. 11, pp. 1998–2008, 2017

    work page 1998

  13. [13]

    Validation of sleep stage classification using non-contact radar technology and machine learning (somnofy®),

    S. Toften, S. Pallesen, M. Hrozanova, F. Moen, and J. Grønli, “Validation of sleep stage classification using non-contact radar technology and machine learning (somnofy®),”Sleep Medicine, vol. 75, pp. 54–61, 2020

    work page 2020

  14. [14]

    A deep learning method approach for sleep stage classification with EEG spectrogram,

    C. Li, Y . Qi, X. Ding, J. Zhao, T. Sang, and M. Lee, “A deep learning method approach for sleep stage classification with EEG spectrogram,” International journal of environmental research and public health, vol. 19, no. 10, p. 6322, 2022

    work page 2022

  15. [15]

    Accuracy of three commercial wearable devices for sleep tracking in healthy adults,

    R. Robbins, M. D. Weaver, J. P. Sullivan, S. F. Quan, K. Gilmore, S. Shaw, A. Benz, S. Qadri, L. K. Barger, C. A. Czeisleret al., “Accuracy of three commercial wearable devices for sleep tracking in healthy adults,” Sensors, vol. 24, no. 20, p. 6532, 2024

    work page 2024

  16. [16]

    A performance validation of six commercial wrist-worn wearable sleep-tracking devices for sleep stage scoring compared to polysomnography,

    A.-M. Schyvens, B. Peters, N. C. Van Oost, J.-M. Aerts, F. Masci, A. Neven, H. Dirix, G. Wets, V . Ross, and J. Verbraecken, “A performance validation of six commercial wrist-worn wearable sleep-tracking devices for sleep stage scoring compared to polysomnography,”Sleep Advances, vol. 6, no. 2, p. zpaf021, 2025

    work page 2025

  17. [17]

    Antidepressant effects of selective slow wave sleep deprivation in major depression: a high-density EEG investigation,

    E. C. Landsness, M. R. Goldstein, M. J. Peterson, G. Tononi, and R. M. Benca, “Antidepressant effects of selective slow wave sleep deprivation in major depression: a high-density EEG investigation,”Journal of psychiatric research, vol. 45, no. 8, pp. 1019–1026, 2011

    work page 2011

  18. [18]

    REM sleep reduction, mood regulation and remission in untreated depression,

    R. Cartwright, E. Baehr, J. Kirkby, S. Pandi-Perumal, and J. Kabat, “REM sleep reduction, mood regulation and remission in untreated depression,” Psychiatry Research, vol. 121, no. 2, pp. 159–167, 2003

    work page 2003

  19. [19]

    Induction of self awareness in dreams through frontal low current stimulation of gamma activity,

    U. V oss, R. Holzmann, A. Hobson, W. Paulus, J. Koppehele-Gossel, A. Klimke, and M. A. Nitsche, “Induction of self awareness in dreams through frontal low current stimulation of gamma activity,”Nature neuroscience, vol. 17, no. 6, pp. 810–812, 2014

    work page 2014

  20. [20]

    Enhanced emotional reactivity after selective REM sleep deprivation in humans: an fMRI study,

    A. Rosales-Lagarde, J. L. Armony, Y . del R´ıo-Portilla, D. Trejo-Mart´ınez, R. Conde, and M. Corsi-Cabrera, “Enhanced emotional reactivity after selective REM sleep deprivation in humans: an fMRI study,”Frontiers in behavioral neuroscience, vol. 6, p. 25, 2012

    work page 2012

  21. [21]

    IEEE code of ethics,

    IEEE, “IEEE code of ethics,” https://www.ieee.org/content/dam/ieee-org/ ieee/web/org/about/corporate/ieee-code-of-ethics.pdf, June 2020, adopted by the IEEE Board of Directors, June 2020. Accessed: 2025-10-02

    work page 2020

  22. [22]

    The consensus sleep diary: standardizing prospective sleep self-monitoring,

    C. E. Carney, D. J. Buysse, S. Ancoli-Israel, J. D. Edinger, A. D. Krystal, K. L. Lichstein, and C. M. Morin, “The consensus sleep diary: standardizing prospective sleep self-monitoring,”Sleep, vol. 35, no. 2, pp. 287–302, 2012

    work page 2012

  23. [23]

    [Online]

    Nordic Semiconductor,nRF52840 Product Specification, Nordic Semiconductor ASA, Trondheim, Norway, 2019, hosted on Seeed Studio Wiki. [Online]. Available: https://files.seeedstudio.com/wiki/XIAO- BLE/Nano BLE MCU-nRF52840 PS v1.1.pdf

    work page 2019

  24. [24]

    [Online]

    World Famous Electronics LLC,Pulse Sensor Data Sheet, World Famous Electronics LLC, Nov 2024, accessed: March 15, 2025. [Online]. Available: https://cdn.shopify.com/s/files/1/0100/6632/files/PulseSensor Datasheet 2024-Nov.pdf

    work page 2024

  25. [25]

    Analog Devices,Single-Lead, Heart Rate Monitor Front End AD8232, Analog Devices, Inc., Norwood, MA, USA, 2012, rev. C. [Online]. Available: https://www.analog.com/media/en/technical-documentation/ data-sheets/AD8232.pdf

    work page 2012

  26. [26]

    Heart rate monitor - AD8232: Schematic,

    SparkFun Electronics, “Heart rate monitor - AD8232: Schematic,” SparkFun Electronics, Boulder, CO, USA, Technical Drawing, 2014, cardiac monitor configuration for the AD8232. [Online]. Avail- able: https://cdn.sparkfun.com/datasheets/Sensors/Biometric/AD8232 Heart Rate Monitor v10.pdf

    work page 2014

  27. [27]

    Ten-twenty electrode system of the international federation,

    H. H. Jasper, “Ten-twenty electrode system of the international federation,” Electroencephalogr Clin Neurophysiol, vol. 10, pp. 371–375, 1958

    work page 1958

  28. [28]

    Skin irritation test,

    Jiangsu Kerbio Medical Technology Group Co., Ltd., “Skin irritation test,” Jiangsu Kerbio Medical Technology Group Co., Ltd., Changzhou, Jiangsu, China, Tech. Rep. SSMT-R-2024-02665-02A, Jun. 2024, biocompatibility test report for Siraya Tech Flex TPU filament, conducted according to ISO 10993-23:2021 standard

    work page 2024

  29. [29]

    In vitro cytotoxicity test,

    ——, “In vitro cytotoxicity test,” Jiangsu Kerbio Medical Technology Group Co., Ltd., Changzhou, Jiangsu, China, Tech. Rep. SSMT-R-2024- 02665-01A, Jun. 2024, biocompatibility test report for Siraya Tech Flex TPU filament, conducted according to ISO 10993-5:2009 standard

    work page 2024

  30. [30]

    Skin sensitization test,

    ——, “Skin sensitization test,” Jiangsu Kerbio Medical Technology Group Co., Ltd., Changzhou, Jiangsu, China, Tech. Rep. SSMT-R-2024-02665- 03A, Jun. 2024, biocompatibility test report for Siraya Tech Flex TPU filament , conducted according to ISO 10993-10:2021 standard

    work page 2024

  31. [31]

    Scikit-learn: Machine learning in python,

    F. Pedregosa, G. Varoquaux, A. Gramfort, V . Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V . Dubourget al., “Scikit-learn: Machine learning in python,”the Journal of machine Learning research, vol. 12, pp. 2825–2830, 2011

    work page 2011

  32. [32]

    Xgboost: A scalable tree boosting system,

    T. Chen and C. Guestrin, “Xgboost: A scalable tree boosting system,” inProceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, 2016, pp. 785–794

    work page 2016

  33. [33]

    SMOTE: synthetic minority over-sampling technique,

    N. V . Chawla, K. W. Bowyer, L. O. Hall, and W. P. Kegelmeyer, “SMOTE: synthetic minority over-sampling technique,”Journal of artificial intelligence research, vol. 16, pp. 321–357, 2002

    work page 2002

  34. [34]

    EEG normal sleep,

    C. S. Nayak and A. C. Anilkumar, “EEG normal sleep,” inStatPearls [Internet]. Treasure Island, FL: StatPearls Publishing, May 2023, last updated May 23, 2023. Bookshelf ID: NBK537023. [Online]. Available: https://www.ncbi.nlm.nih.gov/books/NBK537023/

    work page 2023

  35. [35]

    Comparison of a single-channel EEG sleep study to polysomnography,

    B. P. Lucey, J. S. Mcleland, C. D. Toedebusch, J. Boyd, J. C. Morris, E. C. Landsness, K. Yamada, and D. M. Holtzman, “Comparison of a single-channel EEG sleep study to polysomnography,”Journal of sleep research, vol. 25, no. 6, pp. 625–635, 2016

    work page 2016

  36. [36]

    Interhemispheric differences of electroencephalogra- phy signal characteristics in different sleep stages,

    M. Tashakori, M. Rusanen, T. Karhu, L. Grote, R. K. Nath, T. Lepp ¨anen, and S. Nikkonen, “Interhemispheric differences of electroencephalogra- phy signal characteristics in different sleep stages,”Sleep Medicine, vol. 117, pp. 201–208, 2024

    work page 2024