REVIEW 3 major objections 5 minor 15 references
Assessing Workers Perceived Risk During Construction Task Using A Wristband-Type Biosensor
T0 review · 3 major / 5 minor · reviewed 2026-08-14 · deepseek-v4-flash
Pith's one-line read EDA features from wristband biosensors can recognize construction workers' perceived risk as low or high, with a K-nearest-neighbor classifier reaching 76.9% accuracy.
desk verdict Real field EDA data and a six-classifier benchmark, but the stated construct (perceived risk) is not what the labels measure; the 76.9% accuracy supports activity classification, not risk perception. read the letter →
The pith
A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.
The reading
What carries the argument
The load-bearing object is the electrodermal activity signal, the skin's electrical conductance driven by the sympathetic nervous system, and its processing pipeline: a high-pass filter and moving average remove artifacts, a convex-optimization decomposition splits the signal into tonic electrodermal level and phasic electrodermal response, and 10-second windows with 9-second overlap yield 11 time- and frequency-domain features. Six supervised classifiers are compared on an undersampled, balanced dataset, and K-nearest neighbor gives the highest accuracy, which the paper takes as evidence that nonparametric classification fits the EDA feature space better than parametric models.
What would settle it
Collect real-time self-reports (for example, randomly timed brief prompts on a worn device) from the same workers, then test whether the classifier's high-risk predictions agree with those self-reports; if agreement is no better than chance once activity labels are held fixed, the EDA features are tracking activity category rather than perceived risk. A cheaper check is to re-run the classification under block-wise validation that keeps all windows from the same worker in one fold, which removes the leakage from overlapping windows.
Extended reading notes
Core claim
The paper's central claim is that features computed from wristband-measured electrodermal activity can separate episodes of high perceived risk from low perceived risk during ongoing construction work. Decomposing EDA into tonic (EDL) and phasic (EDR) components, segmenting into 10-second windows, and training a K-nearest-neighbor classifier on eight workers' field data produced 76.9 percent test accuracy, with recall generally exceeding precision. The authors conclude this demonstrates a feasible, noninvasive route to continuous, objective monitoring of perceived risk, replacing survey- and interview-based assessment.
Load-bearing premise
The load-bearing premise is that the video-based risk labels assigned by the research team are a valid proxy for what each worker actually perceived, because if that premise fails the accuracy only shows EDA distinguishes two activity categories, not perceived risk; a secondary premise treats overlapping 10-second windows as independent samples in the random split.
Editorial extensions
If this is right
- If the central claim is correct, perceived risk could be monitored continuously during work, without stopping workers for surveys or interviews.
- A wristband-based system could issue real-time alerts when a worker's EDA indicates a high-risk episode, enabling immediate intervention.
- The framework could extend beyond EDA by adding other physiological streams such as PPG and skin temperature, which the paper names as future work.
- Because EDA is the only sympathetic signal not contaminated by the parasympathetic system, it offers a cleaner physiological channel for arousal-based risk perception than other wearable signals.
- The accuracy and recall figures imply that false negatives on high-risk episodes are relatively rare, which matters if the goal is safety alerting.
Reading between the lines
- Editorial inference: The 76.9 percent figure may partly reflect classification of activity types rather than of perceived states, since the ground truth is a video-based activity label; direct validation against workers' self-reports is needed before treating the model as a perception monitor.
- Editorial inference: The nine-second overlap between consecutive 10-second windows means adjacent training and test samples share almost all their signal; a block-wise or per-worker cross-validation would likely give a lower, more honest accuracy estimate.
- Editorial inference: Perceived risk is personal and threshold-dependent, so a model calibrated per worker, or conditioned on individual baselines, might outperform the current population-level KNN classifier.
- Editorial inference: The framework could be tested in a controlled lab setting where risk level is manipulated and self-reported, which would separate the signal's response to actual hazard from its response to activity-related movement artifacts.
Signed reviews
Editorial analysis
A structured set of objections, weighed in public.
Referee Report
Summary. The paper proposes a wristband-based EDA sensing and supervised-learning framework intended to recognize construction workers' perceived risk during ongoing work. EDA signals were collected from eight construction workers on real sites, and two research team members labeled video-recorded activities as high-risk or low-risk. After artifact removal and EDA decomposition into tonic and phasic components, the authors extracted 11 time- and frequency-domain features from 10-second windows with 9-second overlap. Six classifiers were compared; KNN achieved 76.9% accuracy on a randomly undersampled, randomly split 80/20 training/test protocol repeated 20 times. The authors conclude that EDA features have the capability to recognize workers' perceived risk under different activity risk levels.
Significance. If the central claim were supported, this would be a meaningful step toward continuous, objective, noninvasive monitoring of construction workers' perceived risk, addressing a real limitation of survey-based methods. The use of field data from actual construction sites, the focus on EDA as a sympathetically innervated signal, and the systematic comparison of several classifiers are strengths. The paper also clearly describes the data collection and preprocessing pipeline. However, the significance hinges entirely on whether the ground-truth labels actually measure the construct the paper claims to predict, and on whether the reported accuracy reflects genuine generalization. As it stands, the evidence supports only activity-risk classification based on expert video annotation, not the recognition of workers' subjective perceived risk.
major comments (3)
- [Section 3 (Field Data Collection) and Section 4 (Results and Discussion)] The ground-truth labels are not workers' perceived risk; they are risk levels assigned by two research team members from video observation. The abstract and conclusion repeatedly claim that the model recognizes workers' perceived risk, but no self-reports, physiological validation, or any other independent measure of the workers' subjective risk state were collected. The paper even criticizes self-report bias in the introduction, yet uses researcher-assigned activity labels without any validation. Section 4 explicitly acknowledges that subjects may have perceived risk from stimuli not visible in the video, which could mislabel true high-risk samples as low-risk. This is a load-bearing construct-validity problem: the 76.9% accuracy demonstrates that EDA features can distinguish activities categorized as high- or low-risk by the research team, not that they can recognize the workers' internal perceived risk. Without an independent validation of the labels against workers' self-reports or a controlled experimental manipulation, the central claim of the paper is unsupported.
- [Section 2.2 (Feature Extraction) and Section 2.3 (Classification)] The 10-second windows with 9-second overlap (i.e., a 1-second moving step) create highly autocorrelated, non-independent samples. The random 80/20 split of these overlapping windows into training and test sets means that windows from the same worker and the same continuous time period can appear in both partitions, which leaks temporally adjacent information and inflates the reported accuracy. The evaluation also does not block by subject, so all eight subjects' windows can appear in both training and test, further overestimating performance. This issue is fixable by using non-overlapping windows and subject-level cross-validation, but even after such a fix, the construct-validity concern in the first major comment remains.
- [Section 2.3 (Classification) and Table 3] The classification protocol randomly undersamples the majority class to balance the two classes, then reports accuracy on this artificially balanced test set. Under such a protocol, a trivial classifier that always predicts the minority class would achieve 50% accuracy, and the reported numbers are not comparable to accuracy on the natural class distribution. Moreover, the paper averages accuracy over 20 random repetitions but does not report the variance, standard deviation, or confidence interval across these repetitions, so the stability of the 76.9% figure cannot be assessed. This statistical reporting should be corrected or at least supplemented with per-split variability.
minor comments (5)
- [Keywords line] The keywords line still contains the template placeholder 'Type your keywords here, separated by semicolons' followed by the actual keywords; this placeholder should be removed.
- [Section 2.3 (Classification)] The algorithm name 'Banging Tree' appears to be a typo for 'Bagging Tree'; please correct it.
- [Section 4 (Results and Discussion)] The phrase 'the prevision and recall' contains a typo: 'prevision' should be 'precision'.
- [Figure numbering] The figure numbering is inconsistent: Section 2.1 refers to 'Figure 2. Data Pre-processing', while Section 3 refers to a wristband and labeling examples as 'Figure 2' and later as 'Figure 3'; the text and figure captions should be aligned.
- [General] The paper would benefit from reporting the standard deviation or 95% confidence interval of the accuracy across the 20 random splits, as well as results from subject-independent cross-validation, so readers can gauge the robustness of the comparisons.
Circularity Check
No significant circularity: the classifier accuracy is an empirical label-classification result; label-proxy and overlapping-window issues are validity and independence flaws, not circular reductions.
full rationale
This is an empirical supervised-learning study rather than a derivation chain, and no predicted quantity is equivalent to a fitted input by construction. The EDA features are computed from wristband signals, the target labels are assigned from video by two annotators in Section 3, and the reported accuracy is computed on a held-out random subset of windows in Section 2.3. The only self-citation, reference [11], is used as a literature pointer about increased attention to wearable physiological monitoring and is not load-bearing for the classifier result. Two substantive limitations exist but are not circularity: the ground-truth labels operationalize activity risk as judged by the research team rather than workers' self-reported perceived risk, so the 76.9% accuracy supports classification of those activity labels rather than the internal psychological construct; and the 10-second windows with 9-second overlap combined with a window-level random split in Sections 2.2 and 2.3 creates temporal leakage that inflates the accuracy. These are construct-validity and statistical-independence problems, not cases in which a prediction reduces to its inputs by construction. Therefore the circularity score is 0.
Assumptions & free parameters
free parameters (4)
- Analysis window length and step =
10 seconds with 9-second overlap
- High-pass filter cutoff =
0.05 Hz
- Class balancing undersampling ratio =
1:1 after random undersampling
- Classifier hyperparameters =
Not reported
assumptions (4)
- domain assumption EDA is a valid indicator of sympathetic arousal and thus of perceived risk.
- domain assumption Expert video-based activity labels reliably represent workers' perceived risk.
- domain assumption Overlapping 10-second windows can be treated as independent samples for training and testing.
- domain assumption cvxEDA convex decomposition correctly separates tonic and phasic components in wristband EDA.
Cite this review
Pith. "Pith review of Assessing Workers Perceived Risk During Construction Task Using A Wristband-Type Biosensor." pith.science (2026). https://pith.science/paper/WAE4SZ7L
@misc{pith2026190805133,
author = {Pith},
title = {Pith review of: Assessing Workers Perceived Risk During Construction Task Using A Wristband-Type Biosensor},
year = {2026},
howpublished = {\url{https://pith.science/paper/WAE4SZ7L}},
note = {Machine review of arXiv:1908.05133}
}
read the original abstract
The construction industry has demonstrated a high frequency and severity of accidents. Construction accidents are the result of the interaction between unsafe work conditions and workers unsafe behaviors. Given this relation, perceived risk is determined by an individual response to a potential work hazard during the work. As such, risk perception is critical to understand workers unsafe behaviors. Established methods of assessing workers perceived risk have mainly relied on surveys and interviews. However, these post-hoc methods, which are limited to monitoring dynamic changes in risk perception and conducting surveys at a construction site, may prove cumbersome to workers. Additionally, these methods frequently suffer from self-reported bias. To overcome the limitations of previous subjective measures, this study aims to develop a framework for the objective and continuous prediction of construction workers perceived risk using physiological signals [e.g., electrodermal activity (EDA)] acquired from workers wristband-type biosensors. To achieve this objective, physiological signals were collected from eight construction workers while they performed regular tasks in the field. Various filtering methods were applied to exclude noises recorded in the signal and to extract various features of the signals as workers experienced different risk levels. Then, a supervised machine-learning model was trained to explore the applicability of the collected physiological signals for the prediction of risk perception. The results showed that features based on EDA data collected from wristbands are feasible and useful to the process of continuously monitoring workers perceived risk during ongoing work. This study contributes to an in-depth understanding of construction workers perceived risk by developing a noninvasive means of continuously monitoring workers perceived risk.
Reference graph
Works this paper leans on
-
[1]
BLS, National Census of Fatal Occupational Injuries In 2017, U.S
U.S. BLS, National Census of Fatal Occupational Injuries In 2017, U.S. Bureau of Labor and Statictics, 2018
work page 2017
-
[2]
BLS, 2017 Survey of Occupational Injuries & Illnesses Charts Package, U.S
U.S. BLS, 2017 Survey of Occupational Injuries & Illnesses Charts Package, U.S. Bureau of Labor and Statictics, 2018
work page 2017
-
[3]
KOSHA, Statistics of Occupational Incident by Industry, Korea Occupational Safety and Health Agency, 2019
work page 2019
- [4]
- [5]
-
[6]
L. John, M. Anthony, Measuring the occupational health and safety performance of construc tion companies in Australia, Facilities, 19 (2001) 131-139
work page 2001
-
[7]
H.W. Heinrich, D. Petersen, N.R. Roos, J. Brown, S. Hazlett, Industrial accident prevention: a safety management approach, McGraw-Hill, New York, 1980
work page 1980
-
[8]
G.J.S. Wilde, The Theory of Risk Hom eostasis: Implications for Safety and Health, Risk Analysis, 2 (1982) 209 - 225
work page 1982
Show all 15 references
-
[9]
Hallowell, Safety risk perception in construction companies in the Pacific Northwest of the USA, Construction Management and Economics, 28 (2010) 403-413
M. Hallowell, Safety risk perception in construction companies in the Pacific Northwest of the USA, Construction Management and Economics, 28 (2010) 403-413
2010
-
[10]
Larson, M
R. Larson, M. Csikszentmihalyi, The experience sampling method, Flow and the foundations of positive psychology, Springer2014, pp. 21-34
-
[11]
B. Choi, H. Jebelli, S. Lee, Feasibility analysis of electrodermal activity (EDA) acquired from wearable sensors to assess construction workers’ perceived risk, Safety Science, 115 (2019) 110 -120
2019
-
[12]
Habibnezhad, J
M. Habibnezhad, J. Puckett, M. Fardhosseini, H. Jebelli, T. Stentz, L. Pratama, Experiencing extreme height for the first time: the influence of height, self-judgment of fear and a moving structural beam on the heart rate and postural sway during the quiet stance, 36th Interna...
2019
-
[13]
Boucsein, Electrodermal activity, Springer Science & Business Media2012
W. Boucsein, Electrodermal activity, Springer Science & Business Media2012
-
[14]
Drachen, L.E
A. Drachen, L.E. Nacke, G. Yannakakis, A.L. Pedersen, Correlation between heart rate, electrodermal activity and player experience in first-person shooter games, Proceedings of the 5th ACM SIGGRAPH Symposium on Video Games, ACM, Los Angeles, California, 2010, pp. 49-54
2010
-
[15]
Greco, G
A. Greco, G. Valenza, A. Lanata, E.P. Scilingo, L. Citi, cvxEDA: A convex optimization approach to electrodermal activity processing, IEEE Transactions on Biomedical Engineering, 63 (2016) 797 -804. View publication statsView publication stats
2016
Reviewed August 14, 2026 · model on record in the stance chip above.
Discussion (0). Continue with ORCID to comment.