How to Reduce Work-Related Road Deaths? Driver Fatigue Monitoring – Case Study
archive: archived pipeline: cataloged verified
Get this paper ↗ (DOI — opens at the source; we link to it, we don't host it)
Summary
This paper addresses the critical issue of work-related road deaths, which constitute the leading cause of occupational fatalities, with driver fatigue identified as a primary risk factor alongside speeding. The authors propose a novel approach to achieving "Vision Zero" by developing a fatigue identification model for commercial vehicle drivers that assesses risk *before* a shift begins, rather than detecting fatigue during driving. This pre-shift assessment aims to prevent fatigued drivers from operating vehicles, thereby avoiding the high-risk scenarios associated with in-vehicle detection systems. The study is motivated by the significant shortage of professional drivers in Serbia and Europe, which leads to overtime work and increased fatigue, as well as the limitations of existing detection methods that rely on intrusive monitoring or reactive in-car sensors. The methodology involves an eight-step algorithm to design the fatigue model, utilizing expert knowledge, budget allocation, and the composite rank method. Eleven influential factors were selected based on literature review and criteria such as relevance and measurability: sleep quality, sleep quantity, driving time (daily, weekly, fortnightly), daily rest, fatigue prevention measures, driver age, monthly mileage, and vehicle type. Eleven experts in road traffic safety assigned weights to these factors and their subcategories using a budget allocation technique (allocating 100,000 euros to represent importance). These weights were aggregated using the composite rank method to determine weighting coefficients. The model calculates a fatigue level ($F_j$) for each driver by summing these coefficients. The study was conducted as a case study in Serbia, involving 1,340 commercial vehicle drivers (truck, bus, and delivery) from 15 transportation companies. Data were collected via tachometer analysis for objective driving/rest metrics and pre-shift interviews for subjective sleep and fatigue data. The results indicate that sleep quality was the most influential factor, having a 2.92 times stronger impact than the least influential factor, vehicle type. The model categorized drivers into five fatigue classes: Unfatigued, Slightly Fatigued, Moderately Fatigued, Very Fatigued, and Completely Fatigued. Application of the model revealed that 28.0% of drivers were unfatigued, while 4.0% were in a state of complete fatigue before starting their shifts. The remaining drivers fell into intermediate fatigue categories. For instance, drivers with poor sleep quality, excessive fortnightly driving times, and insufficient daily rest received higher fatigue scores. The findings align with official statistics showing that approximately 3–5% of fatal traffic accidents involving commercial vehicles in Serbia are attributed to driver fatigue. The significance of this research lies in providing a non-intrusive, objective-based tool for transportation companies to monitor driver fitness before shifts. Unlike camera-based or physiological monitoring systems, this model does not distract drivers during operation and relies on readily available data such as tachometer records and simple pre-shift questionnaires. The authors conclude that implementing such monitoring can help mitigate the risks associated with driver shortages and overtime, contributing to global road safety goals. Future improvements could involve replacing subjective self-reports with certified smartwatches to track sleep and activity objectively.
Key finding
Application of the pre-shift fatigue identification model revealed that 4% of commercial vehicle drivers were completely fatigued and 28% were unfatigued before starting their shifts, demonstrating the model's utility in identifying high-risk drivers prior to operation.
Methodology
field_study
Sample size: 1340
Provenance
The full processing record for this entry. Every stage of this paper's journey through the pipeline is logged — what ran, with which tool and model, how many attempts it took, and when it last completed.
| Stage | Outcome | Tool | Model | Prompt | Attempts | Completed |
|---|---|---|---|---|---|---|
| discover | success | Crossref | — | — | 1 | 2026-06-05 |
| archive | success | canonical_url | — | — | 1 | 2026-06-06 |
| extract | success | cached | — | — | 3 | 2026-06-10 |
| clean | success | clean | — | — | 1 | 2026-06-07 |
| chunk | success | chunk | — | — | 1 | 2026-06-07 |
| embed | success | embed | Qwen/Qwen3-Embedding-8B | — | 1 | 2026-06-07 |
| promote | success | — | — | — | 1 | 2026-06-05 |
| summarize | success | llm | qwen3.6-27b-prismaquant | summ-v5 | 2 | 2026-06-10 |
| tag | success | vector_similarity | — | — | 15 | 2026-06-11 |
| verify | success | — | — | — | 2 | 2026-06-10 |
Summary generated by qwen3.6-27b-prismaquant on 2026-06-10; verification: verified.
Topics
Ranked by relevance to this paper. Hover a topic for its definition.
- truck driver fatigue
- drowsiness detection algorithms
- shift work driving
- time on task
- sleep deprivation
- exposure measurement
Information type
What kind of knowledge this paper contributes, grouped by family — independent of topic (what it is about) and method (how it was studied).
- Empirical Findings: physiological data, observational prevalence
- Theoretical Contribution: theory or model