pith. sign in

arxiv: 2605.23663 · v1 · pith:UUYHKTDVnew · submitted 2026-05-22 · 💻 cs.HC · cs.LG

Detecting Drunk Driving Using Off-the-Shelf Smartwatches

Robin Deuber , Lanlan Yang , Michal Bechny , Christoph Heck , Matthias Pf\"affli , Matthias Bantle , Florian von Wangenheim , Elgar Fleisch
show 4 more authors
Wolfgang Weinmann Manuel G\"unther Felix Wortmann Varun Mishra
This is my paper

Pith reviewed 2026-05-25 03:24 UTC · model grok-4.3

classification 💻 cs.HC cs.LG
keywords drunk driving detectionsmartwatchaccelerometerheart rate variabilityconvolutional neural networkalcohol intoxicationwearable sensingtest-track study
0
0 comments X

The pith

A smartwatch CNN detects alcohol-impaired driving at 0.88 AUROC using wrist accelerometer and heart rate signals.

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

The paper sets out to show that off-the-shelf smartwatches can identify drunk driving by collecting and analyzing wrist accelerometer data together with heart rate variability signals during actual vehicle operation. Data came from a randomized three-arm test-track study with 54 participants, and both logistic regression and a two-tower 1D CNN were trained on window-aggregated features. The CNN reached a participant-averaged AUROC of 0.88 for any intoxication and 0.86 for blood alcohol above the 0.05 g/dL WHO limit. This matters to a sympathetic reader because it points to a scalable detection method that requires no extra car hardware and works with devices people already wear. The work also claims to be the first to demonstrate such detection on consumer watches in a real vehicle with explicit checks for generalization to unseen people.

Core claim

A two-tower 1D convolutional neural network trained on smartwatch wrist accelerometer and heart rate variability signals collected during controlled test-track driving achieves a participant-averaged AUROC of 0.88 for detecting any alcohol intoxication and 0.86 for detecting levels above the WHO limit of 0.05 g/dL, with the study designed to assess generalization to unseen participants.

What carries the argument

Two-tower 1D convolutional neural network that ingests window-aggregated features from wrist accelerometer and heart rate variability signals.

If this is right

  • Detection can run on devices already worn by drivers and trigger alerts or alternative transport suggestions without installing car hardware.
  • The approach supports measurement-driven prevention at population scale because it uses consumer smartwatches rather than specialized equipment.
  • Logistic regression baselines were outperformed by the CNN, showing that learned representations add value beyond hand-crafted window features.
  • Explicit participant-wise evaluation supports the claim that the model can work for people whose data were not seen during training.
  • The three-arm randomized design isolates alcohol effects from other variables in the test-track setting.

Where Pith is reading between the lines

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

  • Extending the system to continuous on-wrist monitoring could allow real-time feedback loops that interrupt trips before impairment becomes dangerous.
  • Pairing the model with phone-based location data might enable context-aware interventions such as automatic ride requests when impairment is flagged.
  • The same signals could be examined for detecting other forms of impairment, such as fatigue, by retraining on different labeled datasets.

Load-bearing premise

Wrist accelerometer and heart rate variability signals captured during controlled test-track driving reliably indicate alcohol-related impairment and generalize to unseen participants and real-world conditions without other confounding factors.

What would settle it

A drop in AUROC below 0.75 when the same model is tested on driving data collected from new participants in uncontrolled real-road conditions.

Figures

Figures reproduced from arXiv: 2605.23663 by Christoph Heck, Elgar Fleisch, Felix Wortmann, Florian von Wangenheim, Lanlan Yang, Manuel G\"unther, Matthias Bantle, Matthias Pf\"affli, Michal Bechny, Robin Deuber, Varun Mishra, Wolfgang Weinmann.

Figure 1
Figure 1. Figure 1: Overview of the 1D CNN pipeline designed to perform two classification tasks ( [PITH_FULL_IMAGE:figures/full_fig_p002_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Blood alcohol concentration across driving phases. Mean blood alcohol concentration (BAC; g/dL) for the treatment [PITH_FULL_IMAGE:figures/full_fig_p007_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Illustrations of the experimental setup: (a) off-the-shelf smartwatch worn by participants; (b) temporary crossroads [PITH_FULL_IMAGE:figures/full_fig_p008_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Two-tower (late-fusion) 1D CNN architecture. Here, [PITH_FULL_IMAGE:figures/full_fig_p012_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Receiver operating characteristic (ROC) curves for the [PITH_FULL_IMAGE:figures/full_fig_p015_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Receiver operating characteristic (ROC) curves for the [PITH_FULL_IMAGE:figures/full_fig_p018_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: We temporally smooth model outputs by aggregating window-level predicted probabilities into 15 s bins and computing [PITH_FULL_IMAGE:figures/full_fig_p018_7.png] view at source ↗
read the original abstract

Alcohol-impaired driving remains a major yet preventable cause of road traffic injury and death, with many drivers underestimating their level of intoxication. Compared to in-vehicle systems, mobile drunk-driving detection using consumer smartwatches offers a scalable way to trigger preventive interventions and increase awareness without additional in-vehicle hardware. We introduce a system that leverages wrist accelerometer data and heart rate variability-derived physiological signals to detect alcohol-related driving impairment. We collected data in a randomized, controlled three-arm test-track study (n=54) and trained both logistic regression models with window-aggregated features and a two-tower 1D convolutional neural network (CNN), to detect alcohol-impaired driving. The CNN achieved a participant-averaged area under the receiver operating characteristic (AUROC) of 0.88 for detecting any alcohol intoxication and 0.86 for detecting driving above the WHO-recommended limit of 0.05 g/dL. To the best of our knowledge, this is the first work to (1) demonstrate drunk-driving detection using consumer smartwatches, (2) develop and evaluate such a system in a real vehicle on a closed test track, and (3) rigorously assess generalization to unseen participants. Together, these findings highlight the potential of wearable-based sensing to support scalable, measurement-driven prevention of alcohol-related traffic harm.

Editorial analysis

A structured set of objections, weighed in public.

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

Referee Report

3 major / 2 minor

Summary. The paper presents a system for detecting alcohol-impaired driving using wrist accelerometer and heart rate variability data from off-the-shelf smartwatches. In a randomized, controlled three-arm test-track study with 54 participants, logistic regression and a two-tower 1D CNN are trained, achieving participant-averaged AUROCs of 0.88 for any intoxication and 0.86 for BAC above 0.05 g/dL. The authors claim this is the first demonstration of such detection in a real vehicle on a closed track with assessment of generalization to unseen participants.

Significance. If the results hold under more rigorous validation, this work could significantly advance scalable, non-intrusive methods for preventing drunk driving using ubiquitous consumer devices. The strengths include the use of a controlled randomized design, real-vehicle setting, and focus on generalization across participants. However, the controlled test-track environment may limit the immediate applicability to real-world scenarios with traffic and variable conditions.

major comments (3)
  1. [Abstract] Abstract: The reported AUROC values of 0.88 and 0.86 are presented without accompanying details on the cross-validation method (e.g., leave-one-participant-out), class balance, or statistical tests, which are load-bearing for assessing the reliability of the central performance claims.
  2. [Methods] Methods: The description of the CNN model, including the two-tower architecture, input preprocessing, and training hyperparameters, lacks sufficient specificity to allow reproduction or verification of the reported results.
  3. [Study Design] Study Design: The three-arm test-track protocol with fixed routes and no traffic does not include controls or analyses to isolate alcohol-specific impairment from correlated factors such as altered driving speed or posture, which could confound the learned patterns and undermine the claim that the model detects impairment per se.
minor comments (2)
  1. [Abstract] Abstract: The term 'AUROC' should be expanded on first use for clarity.
  2. [Abstract] Abstract: The claim of being the 'first work' would benefit from a more detailed comparison to prior related work on wearable sensing for impairment.

Simulated Author's Rebuttal

3 responses · 0 unresolved

We thank the referee for their constructive feedback on our manuscript. We have revised the paper to address concerns about the abstract and methods for improved clarity and reproducibility. We respond to each major comment below.

read point-by-point responses

  1. Referee: [Abstract] Abstract: The reported AUROC values of 0.88 and 0.86 are presented without accompanying details on the cross-validation method (e.g., leave-one-participant-out), class balance, or statistical tests, which are load-bearing for assessing the reliability of the central performance claims.

    Authors: We agree these details are essential. In the revised abstract, we now specify that the participant-averaged AUROCs derive from leave-one-participant-out cross-validation, note the class balance (approximately 40% intoxicated windows), and report bootstrap-derived 95% confidence intervals along with a statistical comparison to a random baseline (p < 0.001). revision: yes

  2. Referee: [Methods] Methods: The description of the CNN model, including the two-tower architecture, input preprocessing, and training hyperparameters, lacks sufficient specificity to allow reproduction or verification of the reported results.

    Authors: We appreciate this observation. The revised Methods section now provides the full two-tower 1D CNN specification (tower dimensions, kernel sizes, pooling, fusion layer), exact preprocessing (band-pass filtering, z-score normalization per participant, 10-second windows with 50% overlap), and all hyperparameters (Adam optimizer with learning rate 1e-4, batch size 32, 50 epochs with early stopping on validation AUROC, L2 regularization 1e-5). revision: yes

  3. Referee: [Study Design] Study Design: The three-arm test-track protocol with fixed routes and no traffic does not include controls or analyses to isolate alcohol-specific impairment from correlated factors such as altered driving speed or posture, which could confound the learned patterns and undermine the claim that the model detects impairment per se.

    Authors: This concern is well-taken. While the randomized placebo-controlled design reduces some biases, the fixed-route protocol limits isolation of impairment from behavioral changes. We have added a limitations paragraph acknowledging this and included a post-hoc correlation analysis between model outputs and available vehicle speed logs; however, posture data were not collected. revision: partial

Circularity Check

0 steps flagged

No circularity in derivation chain

full rationale

The paper follows a standard supervised ML pipeline: randomized controlled data collection (n=54), training of logistic regression and 1D CNN on accelerometer/HRV signals, and participant-averaged AUROC evaluation on held-out data. The reported AUROCs (0.88/0.86) are direct empirical outputs of this process and do not reduce to any fitted parameter or self-citation by construction. No self-definitional steps, fitted-input predictions, load-bearing self-citations, uniqueness theorems, ansatzes, or renamings appear in the provided text. The central claims rest on external test-track data and cross-validation rather than internal redefinition.

Axiom & Free-Parameter Ledger

1 free parameters · 1 axioms · 0 invented entities

Review based on abstract only; relies on standard ML assumptions and the validity of controlled study signals for real-world impairment detection.

free parameters (1)
  • CNN hyperparameters and feature aggregation windows
    Standard in neural network and window-based models but unspecified in abstract.
axioms (1)
  • domain assumption Test-track data accurately captures alcohol impairment effects distinguishable from other influences via wrist signals.
    Required for the model to detect impairment rather than study artifacts.

pith-pipeline@v0.9.0 · 5807 in / 1219 out tokens · 64968 ms · 2026-05-25T03:24:50.069098+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

71 extracted references · 71 canonical work pages

  1. [1]

    Christer Ahlström, Raimondas Zemblys, Svitlana Finér, and Katja Kircher. 2023. Alcohol impairs driver attention and prevents compensatory strategies.Accident Analysis & Prevention184 (May 2023), 9 pages. doi:10.1016/j.aap.2023.107010

    work page doi:10.1016/j.aap.2023.107010 2023

  2. [2]

    Michael T Amlung, David H Morris, and Denis M McCarthy. 2014. Effects of acute alcohol tolerance on perceptions of danger and willingness to drive after drinking.Psychopharmacology231, 22 (2014), 4271–4279. doi:10.1007/s00213-014-3579-1

    work page doi:10.1007/s00213-014-3579-1 2014

  3. [3]

    Nikola Banovic and John Krumm. 2018. Warming Up to Cold Start Personalization.Proc. ACM Interact. Mob. Wearable Ubiquitous Technol.1, 4, Article 124 (Jan. 2018), 13 pages. doi:10.1145/3161175

    work page doi:10.1145/3161175 2018

  4. [4]

    2025.In-car tracking of vital signs: BMW Group takes medicine to the road.BMW Group

    BMW Group. 2025.In-car tracking of vital signs: BMW Group takes medicine to the road.BMW Group. Retrieved December 3, 2025 from https://www.bmwgroup.com/en/news/general/2025/automotive-health.html

    work page 2025

  5. [5]

    2025.Systems for interior sensing in commercial vehicles

    Bosch Mobility. 2025.Systems for interior sensing in commercial vehicles. Bosch Mobility. Retrieved December 3, 2025 from https: //www.bosch-mobility.com/en/solutions/interior/interior-sensing-cv/

    work page 2025

  6. [6]

    Tayssir Bouraffa, Dimitrios Koutsakis, and Salvija Zelvyte. 2025. Deep Learning-based rPPG Models Towards Automotive Applications: A Benchmark Study. In2025 IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (W ACVW). IEEE Computer Society, Los Alamitos, CA, USA, 1081–1090. doi:10.1109/WACVW65960.2025.00130

    work page doi:10.1109/wacvw65960.2025.00130 2025

  7. [7]

    Eileen Brobbin, Paolo Deluca, Sofia Hemrage, and Colin Drummond. 2022. Accuracy of wearable transdermal alcohol sensors: systematic review.Journal of Medical Internet Research24, 4 (2022), e35178. doi:10.2196/35178

    work page doi:10.2196/35178 2022

  8. [8]

    Ty Brumback, Dingcai Cao, and Andrea King. 2007. Effects of alcohol on psychomotor performance and perceived impairment in heavy binge social drinkers.Drug and alcohol dependence91, 1 (2007), 10–17. doi:10.1016/j.drugalcdep.2007.04.013

    work page doi:10.1016/j.drugalcdep.2007.04.013 2007

  9. [9]

    Stefan Brunner, Raphaela Winter, Christina Werzer, Lukas von Stülpnagel, Ina Clasen, Annika Hameder, Andreas Stöver, Matthias Graw, Axel Bauer, and Moritz F Sinner. 2021. Impact of acute ethanol intake on cardiac autonomic regulation.Scientific reports11, 1 (2021), 13255. doi:10.1038/s41598-021-92767-y

    work page doi:10.1038/s41598-021-92767-y 2021

  10. [10]

    Vince D Calhoun, David Altschul, Vince McGinty, Regina Shih, David Scott, Edie Sears, and Godfrey D Pearlson. 2004. Alcohol intoxication effects on visual perception: an fMRI study.Human brain mapping21, 1 (2004), 15–26. doi:10.1002/hbm.10145

    work page doi:10.1002/hbm.10145 2004

  11. [11]

    2025.Risk Factors for Impaired Driving

    Centers for Disease Control and Prevention. 2025.Risk Factors for Impaired Driving. Centers for Disease Control and Prevention. Retrieved December 12, 2025 from https://www.cdc.gov/impaired-driving/risk-factors/index.html

    work page 2025

  12. [12]

    Sudarshan S Chawathe. 2020. Using accelerometers in mobile phones to estimate blood alcohol levels. In2020 IEEE International Smart Cities Conference (ISC2). IEEE, IEEE, Piscataway, NJ, USA, 1–8. doi:10.1109/isc251055.2020.9239049

    work page doi:10.1109/isc251055.2020.9239049 2020

  13. [13]

    Huiqin Chen and Lei Chen. 2017. Support Vector Machine Classification of Drunk Driving Behaviour.International Journal of Environmental Research and Public Health14, 1 (Jan. 2017), 108. doi:10.3390/ijerph14010108

    work page doi:10.3390/ijerph14010108 2017

  14. [14]

    Yang-Yi Chen, Chun-Liang Lin, Yu-Cheng Lin, and Changchen Zhao. 2018. Non-invasive detection of alcohol concentration based on photoplethysmogram signals.IET Image Processing12, 2 (2018), 188–193. doi:10.1049/iet-ipr.2017.0625

    work page doi:10.1049/iet-ipr.2017.0625 2018

  15. [15]

    Maximilian Christ, Nils Braun, Julius Neuffer, and Andreas W Kempa-Liehr. 2018. Time series feature extraction on basis of scalable hypothesis tests (tsfresh–a python package).Neurocomputing307 (2018), 72–77. doi:10.1016/j.neucom.2018.03.067

    work page doi:10.1016/j.neucom.2018.03.067 2018

  16. [16]

    Michael Czaplik, Mark Ulbrich, Nadine Hochhausen, Rolf Rossaint, and Steffen Leonhardt. 2019. Evaluation of a new non-invasive measurement technique based on bioimpedance spectroscopy to estimate blood alcohol content: A pilot study.Biomedical Engineer- ing/Biomedizinische Technik64, 3 (2019), 365–371. doi:10.1515/bmt-2018-0070

    work page doi:10.1515/bmt-2018-0070 2019

  17. [17]

    John C Dalrymple-Alford, P Anne Kerr, and Richard D Jones. 2003. The effects of alcohol on driving-related sensorimotor performance across four times of day.Journal of studies on alcohol64, 1 (2003), 93–97. doi:10.15288/jsa.2003.64.93

    work page doi:10.15288/jsa.2003.64.93 2003

  18. [18]

    Rachel E Davis-Martin, Sheila M Alessi, and Edwin D Boudreaux. 2021. Alcohol use disorder in the age of technology: a review of wearable biosensors in alcohol use disorder treatment.Frontiers in psychiatry12 (2021), 642813. doi:10.3389/fpsyt.2021.642813

    work page doi:10.3389/fpsyt.2021.642813 2021

  19. [19]

    Robin Deuber, Patrick Langer, Mathias Kraus, Matthias Pfäffli, Matthias Bantle, Filipe Barata, Florian von Wangenheim, Elgar Fleisch, Wolfgang Weinmann, and Felix Wortmann. 2025. Moving Beyond the Simulator: Interaction-Based Drunk Driving Detection in a Real Vehicle Using Driver Monitoring Cameras and Real-Time Vehicle Data. InProceedings of the 2025 CHI...

    work page doi:10.1145/3706598 2025

  20. [20]

    2025.Drink Driving Limits Worldwide

    Drinkdriving.org. 2025.Drink Driving Limits Worldwide. Drinkdriving.org. Retrieved December 12, 2025 from https://www.drinkdriving. org/worldwide_drink_driving_limits.php

    work page 2025

  21. [21]

    2023.Growing importance of internet-connected devices

    eurostat. 2023.Growing importance of internet-connected devices. eurostat, Luxembourg. Retrieved December 19, 2025 from https: //ec.europa.eu/eurostat/web/products-eurostat-news/w/ddn-20230829-1

    work page 2023

  22. [22]

    Fairbairn, Jiaxu Han, Eddie P

    Catharine E. Fairbairn, Jiaxu Han, Eddie P. Caumiant, Aaron S. Benjamin, and Nigel Bosch. 2025. A wearable alcohol biosensor: Exploring the accuracy of transdermal drinking detection.Drug and Alcohol Dependence266 (2025), 112519. doi:10.1016/j.drugalcdep.2024.112519

    work page doi:10.1016/j.drugalcdep.2024.112519 2025

  23. [23]

    Harriet Garrisson, Andrew Scholey, Joris C Verster, Brook Shiferaw, and Sarah Benson. 2022. Effects of alcohol intoxication on driving performance, confidence in driving ability, and psychomotor function: a randomized, double-blind, placebo-controlled study. Psychopharmacology239, 12 (2022), 3893–3902. doi:10.1007/s00213-022-06260-z

    work page doi:10.1007/s00213-022-06260-z 2022

  24. [24]

    2024.Road Safety Thematic Report – Alcohol and Drugs

    Charles Goldenbeld. 2024.Road Safety Thematic Report – Alcohol and Drugs. Technical Report. European Road Safety Observatory, Brus- sels, Belgium. https://road-safety.transport.ec.europa.eu/document/download/bd2408b2-64ce-44a8-a4ca-d7820c7c91ba_en?filename= ERSO-TR-alcohol_drugs_2023.pdf

    work page 2024

  25. [25]

    Andreas Grammenos, Cecilia Mascolo, and Jon Crowcroft. 2018. You Are Sensing, but Are You Biased? A User Unaided Sensor Calibration Approach for Mobile Sensing.Proc. ACM Interact. Mob. Wearable Ubiquitous Technol.2, 1, Article 11 (March 2018), 26 pages. doi:10.1145/3191743

    work page doi:10.1145/3191743 2018

  26. [26]

    Fayssal Hamza Cherif, Lotfi Hamza Cherif, Mohammed Benabdellah, and Georges Nassar. 2020. Monitoring driver health status in real time.Review of scientific instruments91, 3 (2020), 035110. doi:10.1063/1.5098308

    work page doi:10.1063/1.5098308 2020

  27. [27]

    Alena Katharina Høye and Ingeborg Storesund Hesjevoll. 2023. Alcohol and driving—how bad is the combination? A meta-analysis. Traffic injury prevention24, 5 (2023), 373–378. doi:10.1080/15389588.2023.2204984

    work page doi:10.1080/15389588.2023.2204984 2023

  28. [28]

    Po-Wei Huang, Bing-Jhang Wu, and Bing-Fei Wu. 2020. A heart rate monitoring framework for real-world drivers using remote photoplethysmography.IEEE journal of biomedical and health informatics25, 5 (2020), 1397–1408. doi:10.1109/jbhi.2020.3026481

    work page doi:10.1109/jbhi.2020.3026481 2020

  29. [29]

    Christopher Irwin, Elizaveta Iudakhina, Ben Desbrow, and Danielle McCartney. 2017. Effects of acute alcohol consumption on measures of simulated driving: a systematic review and meta-analysis.Accident Analysis & Prevention102 (May 2017), 248–266. doi:10.1016/j.aap.2017.03.001

    work page doi:10.1016/j.aap.2017.03.001 2017

  30. [30]

    Jackson A Killian, Kevin M Passino, Arnab Nandi, Danielle R Madden, John D Clapp, Nirmalie Wiratunga, Frans Coenen, and Sadiq Sani. 2019. Learning to Detect Heavy Drinking Episodes Using Smartphone Accelerometer Data.. InProceedings of the 4th International Workshop on Knowledge Discovery in Healthcare Data co-located with the 28th International Joint Con...

    work page 2019

  31. [31]

    Kevin Koch, Martin Maritsch, Eva Van Weenen, Stefan Feuerriegel, Matthias Pfäffli, Elgar Fleisch, Wolfgang Weinmann, and Felix Wortmann. 2023. Leveraging driver vehicle and environment interaction: Machine learning using driver monitoring cameras to detect drunk driving. InProceedings of the 2023 CHI Conference on Human Factors in Computing Systems (CHI ’...

    work page doi:10.1145/3544548.3580975 2023

  32. [32]

    Jöran Köchling, Berit Geis, Cho-Ming Chao, Jana-K Dieks, Stefan Wirth, and Kai O Hensel. 2021. The hazardous (mis) perception of Self-estimated Alcohol intoxication and Fitness to drivE—an avoidable health risk: the SAFE randomised trial.Harm reduction journal 18, 1 (2021), 122. doi:10.1186/s12954-021-00567-4

    work page doi:10.1186/s12954-021-00567-4 2021

  33. [33]

    Pekka Koskinen, Juha Virolainen, and Markku Kupari. 1994. Acute alcohol intake decreases short-term heart rate variability in healthy subjects.Clinical Science87, 2 (1994), 225–230. doi:10.1042/cs0870225

    work page doi:10.1042/cs0870225 1994

  34. [34]

    Laude and Mark T

    Jennifer R. Laude and Mark T. Fillmore. 2016. Drivers who self-estimate lower blood alcohol concentrations are riskier drivers after drinking.Psychopharmacology233, 8 (Feb. 2016), 1387–1394. doi:10.1007/s00213-016-4233-x

    work page doi:10.1007/s00213-016-4233-x 2016

  35. [35]

    Lee, Dary Fiorentino, Michelle L

    John D. Lee, Dary Fiorentino, Michelle L. Reyes, Timothy L. Brown, Omar Ahmad, James Fell, Nic Ward, and Robert Dufour. 2010. Assessing the Feasibility of Vehicle-Based Sensors to Detect Alcohol Impairment. Technical Report. National Highway Traffic Safety Administration, Washington, DC, USA. 98 pages. https://www.nhtsa.gov/sites/nhtsa.gov/files/811358_0.pdf

    work page 2010

  36. [36]

    Vera Lehmann, Thomas Zueger, Martin Maritsch, Michael Notter, Simon Schallmoser, Caterina Bérubé, Caroline Albrecht, Mathias Kraus, Stefan Feuerriegel, Elgar Fleisch, Tobias Kowatsch, Sophie Lagger, Markus Laimer, Felix Wortmann, and Christoph Stettler. 2024. Machine Learning to Infer a Health State Using Biomedical Signals — Detection of Hypoglycemia in ...

    work page doi:10.1056/aioa2300013 2024

  37. [37]

    Zhenlong Li, Xue Jin, and Xiaohua Zhao. 2015. Drunk driving detection based on classification of multivariate time series.Journal of Safety Research54 (Sept. 2015), 61.e29–64. doi:10.1016/j.jsr.2015.06.007

    work page doi:10.1016/j.jsr.2015.06.007 2015

  38. [38]

    ZhenLong Li, HaoXin Wang, YaoWei Zhang, and XiaoHua Zhao. 2020. Random forest–based feature selection and detection method for drunk driving recognition.International Journal of Distributed Sensor Networks16, 2 (Feb. 2020), 13 pages. doi:10.1177/1550147720905234

    work page doi:10.1177/1550147720905234 2020

  39. [39]

    Steven Love and Gregoire S Larue. 2025. A systematic review on the factors associated with the accuracy of self-estimated alcohol intoxication: Implications for drink driving.Journal of Safety Research94 (2025), 425–435. doi:10.1016/j.jsr.2025.08.005

    work page doi:10.1016/j.jsr.2025.08.005 2025

  40. [40]

    Wurst, Frederike Stöth, Wolfgang Weinmann, Christophe P

    Marc Luginbühl, Friedrich M. Wurst, Frederike Stöth, Wolfgang Weinmann, Christophe P. Stove, and Katleen Van Uytfanghe. 2022. Consensus for the use of the alcohol biomarker phosphatidylethanol (PEth) for the assessment of abstinence and alcohol consumption in clinical and forensic practice (2022 Consensus of Basel).Drug Testing and Analysis14, 10 (July 20...

    work page doi:10.1002/dta.3340 2022

  41. [41]

    Teri L Martin, Patricia AM Solbeck, Daryl J Mayers, Robert M Langille, Yvona Buczek, and Marc R Pelletier. 2013. A review of alcohol- impaired driving: The role of blood alcohol concentration and complexity of the driving task.Journal of forensic sciences58, 5 (2013), 1238–1250. doi:10.1111/1556-4029.12227

    work page doi:10.1111/1556-4029.12227 2013

  42. [42]

    Pierre Maurage, Nicolas Masson, Zoé Bollen, and Fabien D’Hondt. 2020. Eye tracking correlates of acute alcohol consumption: A systematic and critical review.Neuroscience & Biobehavioral Reviews108 (Jan. 2020), 400–422. doi:10.1016/j.neubiorev.2019.10.001

    work page doi:10.1016/j.neubiorev.2019.10.001 2020

  43. [43]

    Andrew McAfee, Jacob Watson, Ben Bianchi, Christina Aiello, and Emmanuel Agu. 2017. AlcoWear: Detecting blood alcohol levels from wearables. In2017 IEEE SmartWorld, Ubiquitous Intelligence & Computing, Advanced & Trusted Computed, Scalable Computing & Commu- nications, Cloud & Big Data Computing, Internet of People and Smart City Innovation (SmartWorld/SC...

    work page doi:10.1109/uic-atc.2017.8397486 2017

  44. [44]

    Lakmal Meegahapola, William Droz, Peter Kun, Amalia de Götzen, Chaitanya Nutakki, Shyam Diwakar, Salvador Ruiz Correa, Donglei Song, Hao Xu, Miriam Bidoglia, George Gaskell, Altangerel Chagnaa, Amarsanaa Ganbold, Tsolmon Zundui, Carlo Caprini, Daniele Miorandi, Alethia Hume, Jose Luis Zarza, Luca Cernuzzi, Ivano Bison, Marcelo Rodas Britez, Matteo Busso, ...

    work page doi:10.1145/3569483 2023

  45. [45]

    Varun Mishra, Sougata Sen, Grace Chen, Tian Hao, Jeffrey Rogers, Ching-Hua Chen, and David Kotz. 2020. Evaluating the reproducibility of physiological stress detection models.Proceedings of the ACM on interactive, mobile, wearable and ubiquitous technologies4, 4, Article 147 (Dec. 2020), 29 pages. doi:10.1145/3432220

    work page doi:10.1145/3432220 2020

  46. [46]

    Fredrik Modig, Per-Anders Fransson, Måns Magnusson, and Mitesh Patel. 2012. Blood alcohol concentration at 0.06 and 0.10% causes a complex multifaceted deterioration of body movement control.Alcohol46, 1 (2012), 75–88. doi:10.1016/j.alcohol.2011.06.001

    work page doi:10.1016/j.alcohol.2011.06.001 2012

  47. [47]

    2000.A Review of the Literature on the Effects of Low Doses of Alcohol on Driving-Related Skills

    Herbert Moskowitz and Dary Fiorentino. 2000.A Review of the Literature on the Effects of Low Doses of Alcohol on Driving-Related Skills. Technical Report. National Highway Traffic Safety Administration, Washington, DC, USA. doi:10.21949/1525468

    work page doi:10.21949/1525468 2000

  48. [48]

    Girish Narayanswamy, Xin Liu, Kumar Ayush, Yuzhe Yang, Xuhai Xu, Shun Liao, Jake Garrison, Shyam Tailor, Jake Sunshine, Yun Liu, Tim Althoff, Shrikanth Narayanan, Pushmeet Kohli, Jiening Zhan, Mark Malhotra, Shwetak Patel, Samy Abdel-Ghaffar, and Daniel McDuff. 2024. Scaling Wearable Foundation Models. arXiv:2410.13638 [cs.LG] doi:10.48550/arXiv.2410.13638

    work page doi:10.48550/arxiv.2410.13638 2024

  49. [49]

    2023.Advanced Impaired Driving Prevention Technology

    National Highway Traffic Safety Administration. 2023.Advanced Impaired Driving Prevention Technology. Technical Report. National Highway Traffic Safety Administration, Washington, DC, USA. https://www.nhtsa.gov/sites/nhtsa.gov/files/2023-12/anprm-advanced- impaired-driving-prevention-technology-2127-AM50-web-version-12-12-23.pdf

    work page 2023

  50. [50]

    2025.Traffic Safety Facts - Alcohol-Impaired Driving - 2023 Data (DOT HS 813 713)

    National Highway Traffic Safety Administration. 2025.Traffic Safety Facts - Alcohol-Impaired Driving - 2023 Data (DOT HS 813 713). Technical Report. National Highway Traffic Safety Administration, Washington, DC, USA. https://crashstats.nhtsa.dot.gov/Api/Public/ ViewPublication/813713

    work page 2025

  51. [51]

    Anjan Panneer Selvam, Sriram Muthukumar, Vikramshankar Kamakoti, and Shalini Prasad. 2016. A wearable biochemical sensor for monitoring alcohol consumption lifestyle through Ethyl glucuronide (EtG) detection in human sweat.Scientific reports6, 1 (2016), 23111. doi:10.1038/srep23111

    work page doi:10.1038/srep23111 2016

  52. [52]

    Szymon Paprocki, Meha Qassem, and Panicos A Kyriacou. 2022. Review of ethanol intoxication sensing technologies and techniques. Sensors22, 18 (2022), 6819. doi:10.3390/s22186819

    work page doi:10.3390/s22186819 2022

  53. [53]

    Shawn F Reed, Stephen W Porges, and David B Newlin. 1999. Effect of alcohol on vagal regulation of cardiovascular function: contributions of the polyvagal theory to the psychophysiology of alcohol.Experimental and clinical psychopharmacology7, 4 (1999), 484. doi:10.1037//1064-1297.7.4.484

    work page doi:10.1037//1064-1297.7.4.484 1999

  54. [54]

    Magdalena Romanowicz, John E Schmidt, John M Bostwick, David A Mrazek, and Victor M Karpyak. 2011. Changes in heart rate variability associated with acute alcohol consumption: current knowledge and implications for practice and research.Alcoholism: Clinical and Experimental Research35, 6 (2011), 1092–1105. doi:10.1111/j.1530-0277.2011.01442.x

    work page doi:10.1111/j.1530-0277.2011.01442.x 2011

  55. [55]

    Takaya Saito and Marc Rehmsmeier. 2015. The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets.PloS one10, 3 (2015), e0118432. doi:10.1371/journal.pone.0118432

    work page doi:10.1371/journal.pone.0118432 2015

  56. [56]

    Pornnapa Sanguansri, Nattapat Apiwong-Ngam, Athipong Ngamjarurojana, and Supab Choopun. 2021. Development of Non-Invasive Alcohol Analyzer Using Photoplethysmography.Journal of Physics: Conference Series2145, 1 (2021), 012059. doi:10.1088/1742- 6596/2145/1/012059

    work page doi:10.1088/1742- 2021

  57. [57]

    John B Saunders, Olaf G Aasland, Thomas F Babor, Juan R De la Fuente, and Marcus Grant. 1993. Development of the Alcohol Use Disorders Identification Test (AUDIT): WHO Collaborative Project on Early Detection of Persons with Harmful Alcohol Consumption-II. Addiction88, 6 (June 1993), 791–804. doi:10.1111/j.1360-0443.1993.tb02093.x

    work page doi:10.1111/j.1360-0443.1993.tb02093.x 1993

  58. [58]

    Alexandra Schröck, Annette Thierauf-Emberger, Stefan Schürch, and Wolfgang Weinmann. 2017. Phosphatidylethanol (PEth) detected in blood for 3 to 12 days after single consumption of alcohol—a drinking study with 16 volunteers.International Journal of Legal Medicine 131, 1 (Sept. 2017), 153–160. doi:10.1007/s00414-016-1445-x

    work page doi:10.1007/s00414-016-1445-x 2017

  59. [59]

    Manuel Segura, Pere Vergés, Richard Ky, Ramesh Arangott, Angela Kristine Garcia, Thang Dihn Trong, Makoto Hyodo, Alexan- dru Nicolau, Tony Givargis, and Sergio Gago-Masague. 2025. Advancing Intoxication Detection: A Smartwatch-Based Approach. The manuscript has been submitted to ACM and is currently under review. Detecting Drunk Driving Using Off-the-Shel...

    work page doi:10.48550/arxiv.2510.09916 2025

  60. [60]

    Michaela Sidikova, Radek Martinek, Aleksandra Kawala-Sterniuk, Martina Ladrova, Rene Jaros, Lukas Danys, and Petr Simonik. 2020. Vital sign monitoring in car seats based on electrocardiography, ballistocardiography and seismocardiography: A review.Sensors20, 19 (2020), 5699. doi:10.3390/s20195699

    work page doi:10.3390/s20195699 2020

  61. [61]

    2023.Smart Eye’s Market-Leading Driver Monitoring Software Included in New Volvo EX90

    Smart Eye AB. 2023.Smart Eye’s Market-Leading Driver Monitoring Software Included in New Volvo EX90. Smart Eye AB. Retrieved February 7, 2025 from https://www.smarteye.se/news/smart-eyes-market-leading-driver-monitoring-software-included-in-new-volvo-ex90/

    work page 2023

  62. [62]

    Yifan Sun, Jinglei Zhang, Xiaoyuan Wang, Zhangu Wang, and Jie Yu. 2018. Recognition Method of Drinking-driving Behaviors Based on PCA and RBF Neural Network.Promet-Traffic&Transportation30, 4 (Aug. 2018), 407–417. doi:10.7307/ptt.v30i4.2657

    work page doi:10.7307/ptt.v30i4.2657 2018

  63. [63]

    Timo Sztyler and Heiner Stuckenschmidt. 2017. Online personalization of cross-subjects based activity recognition models on wearable devices. In2017 IEEE International Conference on Pervasive Computing and Communications (PerCom). IEEE, Piscataway, NJ, USA, 180–189. doi:10.1109/PERCOM.2017.7917864

    work page doi:10.1109/percom.2017.7917864 2017

  64. [64]

    Fillmore, Jeanette Norris, Antonia Abbey, John J

    Maria Testa, Mark T. Fillmore, Jeanette Norris, Antonia Abbey, John J. Curtin, Kenneth E. Leonard, Kristin A. Mariano, Margaret C. Thomas, Kim J. Nomensen, William H. George, Carol VanZile-Tamsen, Jennifer A. Livingston, Christopher Saenz, Philip O. Buck, Tina Zawacki, Michele R. Parkhill, Angela J. Jacques, and Lenwood W. Hayman. 2006. Understanding Alco...

    work page doi:10.1111/j.1530-0277.2006.00039.x 2006

  65. [65]

    Jianqiang Wang, Chenfei Yu, Shengbo Eben Li, and Likun Wang. 2015. A forward collision warning algorithm with adaptation to driver behaviors.IEEE Transactions on Intelligent Transportation Systems17, 4 (2015), 1157–1167. doi:10.1109/tits.2015.2499838

    work page doi:10.1109/tits.2015.2499838 2015

  66. [66]

    Wen-Fong Wang, Ching-Yu Yang, and Yan-Fu Wu. 2018. SVM-based classification method to identify alcohol consumption using ECG and PPG monitoring.Personal and Ubiquitous Computing22, 2 (2018), 275–287. doi:10.1007/s00779-017-1042-0

    work page doi:10.1007/s00779-017-1042-0 2018

  67. [67]

    Joana M Warnecke, Joan Lasenby, and Thomas M Deserno. 2023. Robust in-vehicle heartbeat detection using multimodal signal fusion. Scientific Reports13, 1 (2023), 20864. doi:10.1038/s41598-023-47484-z

    work page doi:10.1038/s41598-023-47484-z 2023

  68. [68]

    Frank Weise, Dieter Krell, and Norbert Brinkhoff. 1986. Acute alcohol ingestion reduces heart rate variability.Drug and alcohol dependence17, 1 (1986), 89–91. doi:10.1016/0376-8716(86)90040-2

    work page doi:10.1016/0376-8716(86)90040-2 1986

  69. [69]

    1932.Die theoretischen Grundlagen und die praktische Verwendbarkeit der gerichtlich-medizinischen Alkoholbestimmung

    Erik Matteo Prochet Widmark. 1932.Die theoretischen Grundlagen und die praktische Verwendbarkeit der gerichtlich-medizinischen Alkoholbestimmung. Number 11 in Fortschritte der naturwissenschaftlichen Forschung. Berlin : Urban & Schwarzenberg, Berlin, Germany

    work page 1932

  70. [70]

    2024.Global status report on alcohol and health and treatment of substance use disorders

    World Health Organization (WHO). 2024.Global status report on alcohol and health and treatment of substance use disorders. Technical Report. World Health Organization (WHO), Geneva, Switzerland. https://www.who.int/publications/i/item/9789240096745

    work page arXiv 2024

  71. [71]

    Raimondas Zemblys, Christer Ahlström, Katja Kircher, and Svitlana Finér. 2024. Practical aspects of measuring camera-based indicators of alcohol intoxication in manual and automated driving.IET Intelligent Transport Systems18, 8 (June 2024), 1408–1427. doi:10.1049/itr2.12520 The manuscript has been submitted to ACM and is currently under review

    work page doi:10.1049/itr2.12520 2024