The research, led by G. Bravo and colleagues including H.I. Castellucci and Martin Lavallière, comes at a moment when the demographics of work are shifting worldwide. By 2050, the United Nations projects that 16.4 percent of the global population will be 65 or older, and by 2030 roughly 20 percent of the labor force in many countries will consist of older adults. Transport is no exception. Commercial driving is physically and cognitively demanding, involving prolonged sitting, irregular schedules, sustained vigilance, and split-second decisions, all of which interact with the gradual sensory, motor, and cognitive erosion that accompanies aging. Understanding whether older professional drivers can still meet the demands of the job is therefore not an abstract question but one with direct consequences for road safety, workforce planning, and retirement policy.

The study team recruited every driver employed at two transport companies in central Chile, one passenger transport firm in Rancagua and one freight company in Concón. Of 811 drivers invited, 226 volunteered. All were men, with an average age of 51.2 years, and the sample was divided into three stages of working life: 58 younger drivers aged 30 to 44, 125 drivers aged 45 to 59 approaching retirement, and 43 older drivers aged 60 to 76. The researchers assessed body composition, grip strength, lower-limb endurance, and cardiorespiratory fitness, then administered a standardized psychotechnical test battery of the same type used by Chilean municipal transit authorities when issuing and renewing professional licenses. Work ability was measured with the Work Ability Index, a validated seven-item questionnaire that scores a worker’s capacity to meet job demands on a scale from 7 to 49.

The work ability results were striking in their uniformity. Among the 160 drivers who completed the questionnaire, 83 percent rated their work ability as good or excellent, with a mean score of 41.3. Contrary to expectations, the oldest group posted the highest average score at 42.50, compared with 41.45 for the middle group and 40.46 for the youngest. Neither simple nor covariate-adjusted regression models found a statistically significant association between age group and work ability. The authors suggest that a strong local cultural value attached to employment, providing purpose, social belonging, and family income, may help explain why older drivers perceive themselves as fully capable. The finding also aligns with prior reviews showing that age alone does not reliably predict declining work ability among professional drivers, particularly where workplace health and safety protocols are well established.

The psychomotor tests told a more nuanced story. In the lever test, which requires both hands to guide a needle along a track as quickly as possible, older drivers committed significantly more errors than their younger colleagues, averaging 6.70 errors versus 3.24, and their maximum error time was more than twice as long. After adjusting for body composition and fitness covariates, drivers aged 60 to 76 still showed an average increase of 3.19 errors and 0.69 seconds of maximum error time compared with the reference group. The bimanual coordination test, in which participants use rotary controls with both hands to steer two points along separate paths, revealed the largest gaps: older drivers averaged 35.02 errors versus 25.81 for the youngest group, an adjusted difference of 8.22 errors and 4.50 additional seconds of error time, both statistically significant.

The Lahy Dotting Test, which measures visuomotor coordination, rhythm, and concentration by requiring participants to touch black circles appearing on a rotating disk, produced a curious pattern. Older drivers achieved significantly fewer correct responses, 33.19 on average versus 37.31 for the youngest group, but they completed their correct responses faster, taking 11.22 seconds compared with 14.30 seconds for the young group. The authors interpret this speed-accuracy trade-off as consistent with age-related changes in executive function and visuospatial processing, where older participants may sacrifice thoroughness for pace. Meanwhile, the two tests most directly tied to emergency driving responses, the braking reaction time test and the speed anticipation test, showed no significant differences across age groups at all, with average braking reaction times hovering around 0.30 seconds in every group.

The absence of reaction time differences deserves particular attention. Laboratory studies of the general population consistently show that older adults react more slowly to visual stimuli, with one cited analysis finding older drivers display roughly 17 percent longer reaction times and make more than twice as many pedal errors as younger drivers. The authors suggest several explanations for the discrepancy. Professional drivers benefit from training and experience that shortens perception-to-braking latency. The controlled testing environment, in which participants knew exactly which signal to expect, may have minimized the mental load that typically exposes age-related slowing. In real traffic, where drivers must monitor intersections, pedestrians, and overtaking maneuvers simultaneously, the cognitive demands are far higher, and prior simulator studies have shown older drivers’ reaction times lengthen under mental load. The authors also note that obstructive sleep apnea, which is highly prevalent among professional drivers and increases with age, can impair vigilance and psychomotor performance, though it was not assessed in this study.

Importantly, the authors caution against interpreting poorer coordination scores as evidence of unsafe driving. All participants were active professionals who had recently passed Chile’s mandatory medical and psychotechnical licensing examinations, meaning the sample reflects a healthy-worker population. The magnitude of the observed differences was generally small, and the oldest group showed greater variability, suggesting that some older drivers perform as well as or better than younger peers while others lag further behind. Because the study did not measure on-road performance or collision outcomes, it cannot establish whether these psychomotor differences translate into safety risks. Safety managers in the transport sector often value older drivers for their work ethic, loyalty, superior trip management, and compensatory strategies such as driving more cautiously and avoiding high-demand situations, behaviors that may offset modest declines in raw processing speed.

The findings point toward targeted rather than blanket interventions. At the organizational level, the authors advocate a systemic approach built on the Total Worker Health framework, integrating health promotion, risk assessment, worker participation, and the Work Ability Index as a screening tool to monitor capacity over time. At the individual level, they propose that future studies test whether physical training targeting flexibility, coordination, and movement speed can improve performance on the specific tests that showed age-related declines, and whether educational programs combining theory with on-road practice can strengthen attention and situational awareness. The study’s limitations, including its cross-sectional design, convenience sample, all-male cohort, differential questionnaire completion across age groups, and unrecorded testing times, mean the results are hypothesis-generating rather than definitive. Still, the central message is clear: aging does not uniformly erode the capacities that matter for professional driving, and individualized monitoring, rather than age-based generalizations, is the path to keeping experienced drivers safely on the road.

Subject of Research: Age-related differences in work ability and psychomotor skills among professional heavy vehicle drivers

Article Title: Age-related differences in work ability and psychomotor skills among professional heavy vehicle drivers in Chile: A cross-sectional study

Article References: Bravo, G., Campos, A., Lavallière, M., & Castellucci, H. (2026). Age-related differences in work ability and psychomotor skills among professional heavy vehicle drivers in Chile: A cross-sectional study. Heliyon, 12(15), Article e45564. https://doi.org/10.1016/j.heliyon.2026.e45564

Image Credits: AI Generated

DOI: 10.1016/j.heliyon.2026.e45564

Keywords: work ability, psychomotor skills, aging workforce, professional drivers, heavy vehicles, occupational health, Chile, reaction time, visuomotor coordination, Work Ability Index, road safety, cross-sectional study

The core insight of the work is that the models that power modern chatbots, known as vision-language models, can do more than describe a scene. They can be taught to make bounded, auditable safety decisions. But the researchers found that off-the-shelf versions of these models fail at the task in a dangerous and instructive way. When general-purpose models were asked, without any task-specific training, to watch short video clips of an intersection and recommend an action, the larger seven-billion-parameter model intervened on nearly every clip it saw, including clips of completely normal traffic where the correct answer was to do nothing. Its apparent accuracy on hazardous events was an artifact of always sounding the alarm. The smaller three-billion-parameter model, meanwhile, produced outputs in the wrong format, so the signal controller could not execute them at all. For a safety layer, the decisive failure is not missing a hazard but crying wolf on every quiet street corner, eroding both traffic flow and trust.

To fix this, the team built a training dataset of 1,020 video clips generated inside the CARLA driving simulator, each roughly two to three seconds long and captured by two fixed virtual cameras whose views are stacked into a single composite image of the intersection. The clips cover nine combinations of weather and lighting, from clear noon to hard rain at night, and fall into three classes: jaywalking, red-light running, and normal traffic. Every clip was labeled automatically by a deterministic expert policy that maps each event and signal state to an ideal intervention. A jaywalker triggers a long all-red hold of eight to ten seconds, calibrated to the geometry of the crosswalks, which span about 14.5 to 15 meters; a red-light runner triggers a shorter hold of five seconds for cars and six for heavy vehicles, enough to clear the intersection before conflicting movements are released; normal traffic triggers no action at all.

One of the most technically interesting parts of the pipeline addresses a subtle data problem. The object detector that anchors the system, a YOLOv10-l model, performs well in daylight but nearly collapses at night and in heavy rain. In the first collection pass, the detector found around 40 jaywalking pedestrians per daytime condition but only six on a clear night and a single one under hard rain at night. Because the pedestrians were scripted actors whose positions the simulator knows exactly, the researchers projected ground-truth positions onto the camera images using pinhole camera geometry, recovering correct labels for 128 of the 348 jaywalking samples. Crucially, the projection changes only the labels, not the video itself, so the model still has to learn to recognize faint, barely visible hazards from raw pixels alone.

The fine-tuning itself is remarkably efficient. The researchers started with Qwen2.5-VL-3B-Instruct, a compact open model, and applied low-rank adaptation, a technique that freezes the original network and injects a small number of trainable update matrices into its attention and feed-forward layers. Only 37.15 million parameters, less than one percent of the model, were trained, and the vision encoder was left untouched. Training took about 40 minutes on a single workstation GPU, with loss decaying smoothly from 1.13 to 0.004 over three passes through the data. The model was trained to emit a strict JSON decision document: whether to intervene and why, how long to hold all-red, which legal signal combination to run, per-phase green times, safety notes, and a confidence level. Every field is range-checked by a separate rule-constrained controller, which rejects anything malformed, out of bounds, or inconsistent with traffic-engineering constraints. The AI never touches the signal directly.

The evaluation was deliberately harsh. Three of the nine weather conditions, wet sunset, clear night, and hard rain at night, were withheld entirely from training, and the fine-tuned model was tested on 313 clips from those unseen conditions. It achieved perfect schema validity, perfect adherence to controller bounds, and a perfect intervene-or-do-nothing decision on every single clip, with a mean hold-time error of just 0.15 seconds. Its false-positive rate on the 108 normal-traffic clips was zero, with a statistical upper bound of 3.4 per hundred. The zero-shot seven-billion-parameter baseline, by contrast, scored only 0.655 on decision accuracy, exactly the fraction of event clips in the test set, because it intervened on all of them, and its hold-time errors averaged over four seconds. Notably, a seven-billion-parameter model fine-tuned with the identical recipe performed no better than the three-billion one, and the smaller model was also faster, with a median decision time of 2.77 seconds versus 3.20 seconds for its larger zero-shot rival. Adaptation, not scale, is what makes these models usable inside a control loop.

The system also generalized beyond its training environment. At a second simulated intersection in a different virtual town, with different road geometry, surroundings, and camera positions, and with no retraining whatsoever, the fine-tuned model again made the correct decision on all 135 test clips. The only degradation was in hold timing: it recommended nine-second holds where the site-specific expert target was eight seconds, a one-second error that still fell within the mandated eight-to-ten-second band. Textual explanations produced at the new site referred to its actual crosswalks and approaches rather than echoing the training scene, suggesting the model carried across an imitated policy rather than a memory of one location’s appearance.

In closed-loop operation, where the full sensing, reasoning, and control stack ran live against scripted violation scenarios, the safety benefits were substantial but came with a measurable cost. Compared with blind fixed-time signal control, the ground-truth pedestrian exposure fraction, the share of total crosswalk-occupancy time overlapping a conflicting green, was 67.6 percent lower at low demand and 73.0 percent lower at medium demand, with every random seed favoring the AI layer. Against a stronger actuated pedestrian-clearance baseline, the reductions were 55.4 and 71.6 percent. An analysis showed the gains came not merely from serving less conflicting green but from shifting that green away from moments when pedestrians were actually present. The price, at medium demand, was a 105.9 percent increase in average stopped delay and a 13.8 percent throughput drop, though the researchers caution that the scripted scenarios inject hazardous events far more often than real intersections experience, inflating the intervention frequency and its delay burden by construction.

The study is equally candid about its limits, and the most consequential one lies upstream of the AI. At night, the object detector recovers only about 10.7 percent of ground-truth crosswalk occupancy from the same imagery, compared with 62.6 percent in daylight, and under clear-night conditions the closed-loop safety improvement shrank to a statistically insignificant 15.2 percent. A semantic layer cannot protect a pedestrian it cannot see. All results come from simulation, with safety-critical events injected by script rather than observed in natural traffic, so no claim of real-world transfer is made. Still, the authors argue the central conclusion stands: domain adaptation, not model scale, is what allows a vision-language model to operate reliably within a controller’s constraints, and the path to deployment now runs through weather-robust perception, sensor fusion, and shadow-mode validation on real traffic cameras. If that perception gap closes, the vision of intersections that watch, understand, and briefly freeze to protect the most vulnerable road users moves a significant step closer to reality.

Subject of Research: A lightweight vision-language AI safety layer for pedestrian protection at signalized intersections

Article Title: A Fine-Tuned Lightweight Vision-Language Safety Layer with Weather-Generalising Decisions at Signalized Intersections

Article References: Afshari, A., Lee, J., & Mashal, Y. (2026). A Fine-Tuned Lightweight Vision-Language Safety Layer with Weather-Generalising Decisions at Signalized Intersections. Machine Learning with Applications, 26, Article 101032. https://doi.org/10.1016/j.mlwa.2026.101032

Image Credits: AI Generated

DOI: 10.1016/j.mlwa.2026.101032

Keywords: vision-language models, traffic signal control, pedestrian safety, fine-tuning, LoRA, CARLA simulator, computer vision, intelligent transportation systems, weather generalization, all-red hold, machine learning, road safety

The team assembled a retrospective longitudinal dataset spanning fourteen quarters, from the last quarter of 2020 through the first quarter of 2024, yielding 518 state-quarter observations. That granularity matters. Most previous analyses of Nigerian road safety have relied on annual aggregates or single-state case studies, which can obscure the seasonal rhythms and regional disparities that drive risk. By working at the state-quarter level, the researchers could track how crash burden shifted over time and across jurisdictions, and could calculate three key indicators for each state: the fatality rate, defined as deaths per crash; the casualty rate; and a severity index that captures how dangerous a typical collision becomes once it occurs.

The headline numbers tell a story of crisis followed by cautious relief. Reported crashes climbed to a peak of 13,656 in 2022, a year that also claimed 6,456 lives on Nigerian roads. In 2023, the crash count fell by 22.3 percent, a decline that will strike many readers as genuinely good news. But the study’s most sobering finding is what did not change. The fatality rate per crash, the probability that a collision produces a death, held steady between 0.47 and 0.48 deaths per crash from 2021 through 2023. In other words, fewer crashes happened, but each crash remained just as lethal. The decline in total deaths tracked the decline in crash numbers almost mechanically, suggesting that whatever reduced crash frequency did nothing to make the crashes that did occur more survivable.

Geographically, the analysis reveals a striking decoupling of crash frequency from crash lethality. The Federal Capital Territory recorded the highest number of crashes of any jurisdiction, 4,852 over the study period, yet its fatality rate was a comparatively low 0.224, meaning fewer than one in four of its crashes proved fatal. Contrast that with northern states such as Sokoto, Katsina and Kaduna, which logged fewer crashes in absolute terms but suffered substantially higher death rates per crash. A collision on a highway through Sokoto is, on the evidence of this dataset, roughly twice as likely to kill someone as a collision in the capital. The authors attribute this pattern to differences in road conditions, vehicle standards, speed profiles and the speed and quality of emergency medical response, factors that determine whether a crash becomes a statistic or a tragedy.

Population adjustment reshuffles the league table entirely. When crashes and fatalities are expressed per 100,000 residents, states that appeared moderate in raw counts emerge as carrying disproportionate burdens, while some populous states with high raw numbers turn out to have unremarkable per-capita rates. This distinction is not academic hair-splitting. Road safety budgets are finite, and a state with a modest crash count but a small population and a high fatality rate may deserve far more attention per naira spent than a sprawling urban center whose crash numbers simply reflect the volume of traffic. The study’s per-capita calculations make clear that part of the apparent geographic concentration of crashes is an artifact of where people live rather than where driving is genuinely most dangerous.

What causes these crashes? The researchers drew on the causal factors recorded by Federal Road Safety Corps officers at crash scenes, and two categories dominated: speed violations and vehicle-related defects. This is consistent with a long line of road safety research showing that kinetic energy is the fundamental killer in road trauma. The relationship between impact speed and fatality risk is steeply nonlinear; a collision at 100 kilometers per hour releases far more than twice the destructive energy of one at 50, and the human body’s tolerance for sudden deceleration has hard physiological limits. Vehicle-related issues, including brake failure, tire blowouts and faulty lighting, compound the problem, particularly on long-haul routes where commercial vehicles travel enormous distances under economic pressure to move fast and maintain poorly.

To look beyond the observed period, the team built an ensemble forecast combining three complementary statistical approaches: an ordinary least squares linear trend, exponential smoothing with a smoothing parameter of 0.7, and an autoregressive integrated moving average model of order (0,1,0) with drift. Each method captures different features of a time series. The linear trend extrapolates the average direction of change; exponential smoothing weights recent quarters more heavily, allowing the forecast to respond quickly to the post-2022 decline; and the ARIMA specification models the quarter-to-quarter random walk behavior of the counts. Averaging across such an ensemble hedges against the failure modes of any single model. The consensus projection is that quarterly crash numbers will likely remain high in the short term, though the authors emphasize that forecast uncertainty widens as the horizon extends, a reminder that statistical extrapolation is a guide, not a guarantee.

The authors are careful, and rightly so, to distinguish description from prescription. Their policy recommendations, a shift toward risk-based road safety strategies centered on speed regulation, vehicle safety checks and enhanced emergency response systems, are explicitly framed as inferences from the observed patterns rather than as evidence of intervention effectiveness. This is an important caveat. Knowing that northern states have high fatality rates per crash does not by itself prove that speed cameras or ambulance networks would reduce them; it identifies where such interventions should be trialed and evaluated. Nigeria’s road safety authorities now have a statistical map of where the lethality problem lives, but converting that map into saved lives requires controlled implementation and rigorous before-and-after measurement, the kind of evidence that has transformed road safety in countries like Sweden and Australia.

The study’s methodological choices also offer a template for other countries with fragmented road safety data. The fatality rate per crash is a deceptively simple metric with powerful diagnostic value: it separates the question of how often crashes happen from the question of how deadly they are when they do, and the two demand different remedies. Better road engineering, vehicle standards and post-crash care lower the fatality rate; traffic management, enforcement and driver education lower crash frequency. Nigeria’s flat fatality rate amid falling crash counts suggests that decades of effort have moved the first lever barely at all. The World Health Organization has long argued that post-crash response is the most neglected pillar of road safety in low- and middle-income countries, and this dataset gives that argument a precise national geography.

For a country of more than 220 million people, where roads carry the overwhelming majority of passenger and freight movement, the stakes of this research are hard to overstate. Nearly 6,500 deaths in a single year is not an abstract number; it is a rolling public health emergency that disproportionately strikes working-age adults, the demographic backbone of any economy. What this study delivers is clarity: a verified, quarter-by-quarter, state-by-state accounting of where crashes cluster, where they kill, and where the two diverge. The finding that lethality is concentrated in places with fewer crashes should redirect attention and resources toward the corridors and communities where a collision is most likely to end a life. The data now exist. The question the study leaves open, and one that Nigerian policymakers must now answer, is whether the will exists to act on them.

Subject of Research: Spatiotemporal analysis of road traffic crash fatality risk across Nigerian states from 2020 to 2024

Article Title: Spatiotemporal dynamics and fatality risk patterns of road traffic crashes in Nigeria (2020–2024)

Article References: Hassan, M., Nadarajah, S., & Ogunsola, I. (2026). Spatiotemporal dynamics and fatality risk patterns of road traffic crashes in Nigeria (2020–2024). Discover Sustainability. https://doi.org/10.1007/s43621-026-04760-y

Image Credits: AI Generated

DOI: 10.1007/s43621-026-04760-y

Keywords: road traffic crashes, Nigeria, fatality rate, spatiotemporal analysis, Federal Road Safety Corps, road safety, trend projection, ARIMA, exponential smoothing, public health, speed violations, vehicle safety

The review, led by Karim Asif Sattar and colleagues at Universiti Putra Malaysia, is the first comprehensive systematic literature review to focus specifically on explainable artificial intelligence, or XAI, in road traffic crash severity prediction. Previous surveys had examined machine learning models or neural network applications in isolation, but none had systematically synthesized the explainability and interpretability techniques layered on top of them. The researchers searched Web of Science and Scopus, retrieving 3,616 records, of which 2,768 remained after duplicate removal. Through a PRISMA-guided screening process involving two independent reviewers, they whittled the pool down to 237 peer-reviewed journal articles, each of which applied at least one machine learning or deep learning technique to crash severity prediction. The timing of the review window was deliberate: before 2014, the field was dominated by traditional statistical approaches, whereas the past decade witnessed the rapid adoption of ensemble learning, deep neural networks, and post hoc explanation methods such as SHAP and LIME.

The central tension the review exposes is the classic trade-off between accuracy and interpretability. Logistic regression and decision trees are transparent, but they struggle with high-dimensional data and nonlinear relationships. Artificial neural networks and ensemble models capture complex patterns with impressive accuracy, yet their inner workings are notoriously opaque, the so-called black box problem. In a domain where decisions affect human lives, from emergency dispatch to infrastructure investment, that opacity is not merely an academic inconvenience. The authors argue that both strong predictive performance and model interpretability are essential for deploying decision-support systems in emergency response applications, where the swift dispatch of medical personnel to accident locations can mean the difference between recovery and fatality.

On the modeling side, the review found that machine learning techniques were used more frequently than deep learning approaches, with roughly a third of studies employing both. Random forest was the single most popular algorithm, appearing in 109 applications, followed by decision tree variants and support vector machines. Boosting methods such as XGBoost, gradient boosting decision trees, and AdaBoost featured prominently, and newer frameworks like LightGBM and CatBoost showed steady growth in adoption over the review period. Among deep learning architectures, artificial neural networks led the pack, with convolutional neural networks and long short-term memory models gaining traction, the latter particularly for sequential and time-series crash data. Graph neural networks, which represent crash records as nodes in a network, showed limited but increasing adoption toward the end of the period.

Perhaps the most striking finding concerns feature selection, which the authors categorize as ablation methods: techniques used to identify, rank, or eliminate input variables during model development. Approximately 64 percent of the reviewed studies employed such methods. The toolbox is remarkably diverse, spanning wrapper-based approaches like Boruta and recursive feature elimination, regularization techniques such as LASSO and elastic net, information-theoretic measures including information gain and gain ratio, statistical tests like chi-square and Pearson correlation, and even nature-inspired optimization algorithms including genetic algorithms, coyote optimization, and multi-objective evolutionary frameworks like NSGA-II and PESA-II. In one illustrative case, the PESA-II algorithm reduced a feature set from 31 variables to 13 while achieving a prediction accuracy of 94.7 percent, demonstrating how aggressive dimensionality reduction can coexist with strong performance.

On the explainability side, SHAP, which stands for SHapley Additive exPlanations, emerged as the undisputed champion. Grounded in cooperative game theory, SHAP assigns each feature a contribution value for individual predictions, guaranteeing a unique attribution solution with properties including local accuracy, missingness, and consistency. The review documented a marked increase in SHAP usage from 2019 to 2024, applied alongside XGBoost, LightGBM, random forest, CatBoost, and decision trees, among others. Its appeal lies in providing both global and local explanations with intuitive visualizations that help communicate findings to policymakers. Yet the technique is not without drawbacks: computational costs can balloon on large datasets, and the additive decomposition assumption may not fully capture complex feature interactions, while strongly correlated features can produce unstable attribution values.

Other explainability techniques occupy important niches. LIME, or Local Interpretable Model-Agnostic Explanations, approximates a complex model with a simple surrogate around individual observations, making it valuable for case-level investigation. In one study, LIME revealed that clear weather conditions were positively associated with fatal accidents in three of four examined cases, suggesting drivers become careless in good conditions, a factor that global importance rankings might have obscured. Partial dependence plots and individual conditional expectation curves visualize how predictions shift as features change, with one analysis finding that driving speeds exceeding 60 kilometers per hour in residential zones increased injury accident likelihood by around 10 percent. Accumulated local effects plots offer an advantage over partial dependence by remaining robust to correlated features, while permutation feature importance and leave-one-covariate-out methods estimate importance by measuring performance degradation when features are shuffled or removed.

The practical payoff of this transparency is already visible in the literature. Studies on work zone crashes identified lane closures, work zone length, and annual average daily truck traffic as major severity contributors, informing safer work zone design and dynamic warning systems. Research on rural mountainous freeways linked steep grades, sharp curves, and driver unfamiliarity with severe outcomes, supporting interventions such as adaptive speed limits, geofencing-based driver warnings, and connected-vehicle technologies. Truck crash studies using SHAP with XGBoost revealed that crash configuration matters most for both passenger car and truck driver injuries, while freight-focused analyses tied population density and freeway lane mileage to injury severity, prompting calls for dedicated freight corridors. The review also synthesized policy recommendations spanning speed enforcement, mandatory restraint use, pedestrian fencing, rumble strips, and stricter driving-hour regulations for truck operators.

The authors are careful to note the review’s limitations: the search was restricted to two databases and English-language journal articles, conference papers were excluded, and no formal risk-of-bias assessment was conducted. Because the included studies differed substantially in datasets, severity definitions, and validation procedures, the reported frequencies of technique use should not be read as evidence of predictive superiority. Still, the trajectory is clear. The review points toward future directions including counterfactual explanations, integrated gradients, causal XAI approaches, and domain-adapted large language models, alongside persistent challenges in establishing causal rather than merely associative relationships between crash factors and injury severity. As transportation agencies increasingly consider algorithmic decision support for emergency response and road safety planning, this decade-long map suggests that the era of unexplainable black boxes in crash prediction is steadily, and necessarily, coming to a close.

Subject of Research: Explainable machine learning and deep learning approaches for predicting road traffic crash severity

Article Title: A systematic mapping review of explainable machine and deep learning approaches for road traffic crash severity prediction: A decade-long review (2014-2024)

Article References: Sattar, K. A., Ishak, I., Suriani, L., Rum, S. N. M., & Masiur Rahman, S. (2026). A systematic mapping review of explainable machine and deep learning approaches for road traffic crash severity prediction: A decade-long review (2014-2024). Heliyon, 12(15), Article e45513. https://doi.org/10.1016/j.heliyon.2026.e45513

Image Credits: AI Generated

DOI: 10.1016/j.heliyon.2026.e45513

Keywords: explainable AI, road traffic crashes, crash severity prediction, machine learning, deep learning, SHAP, LIME, feature selection, random forest, XGBoost, systematic review, road safety

The theoretical motivation behind the study rests on a distinction that has shaped self-esteem research for decades. Global self-esteem, famously measured by Morris Rosenberg’s 1965 scale, reflects a person’s overall evaluation of their own worth. But since the 1970s, researchers such as Richard Shavelson and Herbert Marsh have argued that self-concept is hierarchical and multidimensional: general feelings of self-worth sit atop a structure of domain-specific evaluations covering academic ability, physical appearance, social relationships and more. Meta-analytic work, including a 2022 synthesis of longitudinal studies by Lea Dapp, Sandra Krauss and Ulrich Orth, has shown that these domain-specific feelings can feed upward into global self-esteem, and that the domains are meaningfully different from one another. Driving, the Spanish-led team argues, is a domain where this specificity matters enormously, because driving self-worth is entangled with anger, risk-taking and aggression in ways that general self-esteem only partly captures.

The evidence for that entanglement is substantial. Global self-esteem has repeatedly been shown to predict anger and aggressive behaviour both on and off the road, and studies of driving anger, going back to Jerry Deffenbacher’s Driving Anger Scale in 1994, have documented how hostile emotions behind the wheel translate into dangerous conduct. Earlier work by Herrero-Fernández and colleagues had already suggested that self-esteem acts as a distal predictor of trait driving anger, and a companion study published in 2026 in Transportation Research Part F pointed to driving self-esteem specifically as a moderator of the link between general anger and anger on the road. What was missing was a validated way to measure that driving-specific self-evaluation directly, rather than inferring it from general scales. The DSEQ was designed to fill exactly that gap.

To build the questionnaire, the researchers generated an item pool covering the everyday texture of driving self-worth: feeling like a good or skilled driver, staying calm on uphill starts, handling overtaking on two-way roads, feeling insecure every time one gets behind the wheel, or preferring that a licensed passenger take over because they would do it better. The final published item set, presented bilingually in Spanish and English, includes statements such as ‘I am a good driver’, ‘I feel fearful every time I approach a large roundabout or one with many lanes’ and ‘Nowadays, I would easily pass the practical driving test.’ The team then administered the items to 530 Spanish drivers with an average age of 30.55 years, of whom 67.4 percent were women, and subjected the responses to a battery of modern psychometric techniques.

The analytical approach was deliberately conservative. Because questionnaire responses are ordinal rather than continuous, the team used polychoric correlations rather than ordinary Pearson coefficients in their exploratory factor analyses, and applied parallel analysis to decide how many factors the data genuinely supported. The initial results hinted at a multidimensional structure, but the researchers traced this pattern to item wording effects, the well-documented tendency of positively and negatively phrased statements to cluster separately regardless of content, a phenomenon also seen in the Rosenberg Self-Esteem Scale itself. Once wording artifacts were accounted for, the data supported a unidimensional structure: a single underlying dimension of driving self-esteem. The team reinforced this conclusion with dedicated unidimensionality indices, including UniCo, ECV and MIREAL, statistics developed by Pere Ferrando and Urbano Lorenzo-Seva to test whether a scale truly measures one thing rather than several bundled together.

The final model showed adequate fit and high reliability, meaning the items consistently tap the same construct. Crucially, the researchers also tested measurement invariance across gender, confirming that the questionnaire functions equivalently for men and women at the configural, metric and scalar levels. This matters because gender differences in self-esteem are among the most replicated findings in social psychology, and any comparison between male and female drivers would be meaningless if the scale itself behaved differently in each group. With invariance established, researchers can now compare driving self-esteem across genders with confidence that any observed differences reflect real psychological differences rather than measurement artifacts.

Validity evidence came from relationships with external variables. As expected, driving self-esteem correlated positively with global self-esteem, confirming that the new scale is related to, but distinct from, the general construct. More strikingly, it correlated negatively with several dimensions of driving anger, the emotional responses measured by Deffenbacher’s framework, including anger at discourtesy, slow driving and other common provocations. Drivers who feel competent and secure behind the wheel appear to be less easily provoked into anger on the road, a pattern consistent with theories linking threatened self-worth to hostile reactions.

The incremental validity results were more nuanced. In hierarchical regression analyses, the team tested whether the DSEQ explained additional variance in driving anger outcomes beyond what global self-esteem already accounted for. The answer was yes, but selectively: the questionnaire added small but meaningful increases in explained variance for anger related to discourtesy and slow driving, while showing no incremental contribution for other dimensions. The authors interpret this as evidence of modest, domain-specific incremental validity, which is precisely what a domain-specific instrument should show. A driving-specific measure should not outperform general self-esteem everywhere; it should add predictive power exactly where the driving context is most psychologically relevant.

The practical implications extend well beyond the laboratory. Traffic psychology has long grappled with the paradox that overconfident drivers can be as dangerous as insecure ones, with studies showing that high implicit self-esteem predicts risky behaviours such as dangerous mobile phone use while driving. A validated measure of driving self-esteem gives intervention designers a target: programmes aimed at recalibrating drivers’ self-evaluations, whether inflated or deflated, can now assess whether they actually shift the construct they intend to change. The scale also opens the door to studying how driving self-esteem develops over the lifespan, how it relates to self-rated driving ability in older adults, and whether it moderates the well-documented pathway from driving anger to aggressive behaviour. The researchers note that the English version of the items is a direct translation of the original Spanish, and they advise any team adapting the DSEQ into other languages to follow the International Test Commission’s guidelines for test translation and adaptation.

For a field that has catalogued scales and inventories extensively, a 2026 review in Transportation Research Part F documented just how crowded the measurement landscape has become, the arrival of a new instrument demands justification. The DSEQ earns it by targeting a construct that general measures cannot reach: the specific self-worth a driver carries into the cabin. With a unidimensional structure, strong reliability, gender invariance and demonstrated incremental validity in the domains where driving anger bites hardest, the questionnaire gives researchers a precise instrument for one of the most consequential self-evaluations people make. Given that road traffic injuries remain a leading cause of death worldwide, understanding how drivers feel about themselves behind the wheel, and how those feelings fuel or defuse anger in traffic, is far more than an academic exercise. It is a step toward predicting, and ultimately preventing, the hostile encounters that turn ordinary journeys into dangerous ones.

Subject of Research: Development and validation of a self-report questionnaire measuring driving-specific self-esteem in Spanish drivers

Article Title: Development and validation of the driving self-esteem questionnaire

Article References: Herrero-Fernández, D., Bogdan-Ganea, S. R., Martín-Ayala, J. L., & Vistorte, A. O. R. (2026). Development and validation of the driving self-esteem questionnaire. Current Psychology, 45(19), Article 1562. https://doi.org/10.1007/s12144-026-10124-6

Image Credits: AI Generated

DOI: 10.1007/s12144-026-10124-6

Keywords: driving self-esteem, DSEQ, psychometrics, driving anger, self-esteem, traffic psychology, questionnaire validation, measurement invariance, factor analysis, aggressive driving, Current Psychology, road safety

The core insight behind the new framework, called LATM for Lightweight and Adaptive Trust Management, is that the content of a V2X message often betrays its own authenticity. A genuine warning about a stalled vehicle ahead must be physically plausible: it must come from a plausible distance, describe an event consistent with the sender’s reported speed, and fit the environmental context in which it was transmitted. A fabricated message, by contrast, tends to violate one or more of these physical and logical constraints. By systematically checking such constraints, the researchers argue, a receiving vehicle can make a fast and reasonably reliable judgment about whether a message deserves to be acted upon, without waiting for certificate checks or cryptographic verification to complete.

Technically, LATM computes a dynamic Trust Score from six key parameters. The first is distance-to-event validity, which asks whether the sender could plausibly have observed the reported event from its stated location. The second is signal speed validity, which examines whether the sender’s velocity is consistent with the message content and the surrounding traffic situation. The third is speed–content coherence, a related but distinct check that probes whether the described event matches what a vehicle moving at that speed would realistically encounter. The fourth is environmental compliance, which tests whether the message fits the broader context, such as urban street geometry or highway conditions. The fifth and sixth parameters draw on the sender’s history: sender reputation captures the track record of the transmitting vehicle, while historical trust accumulates the outcomes of previous interactions with that sender over time. Together, these six dimensions form a multidimensional fingerprint of message plausibility.

To test the approach, the team generated a dedicated dataset simulating both valid and invalid message scenarios across diverse urban and highway environments. This synthetic corpus allowed the researchers to expose the algorithm to a wide range of legitimate traffic events as well as adversarial injections, including spoofed hazard warnings and manipulated position data. The algorithm was implemented using spatial and temporal analysis, meaning that it evaluates not only where an event claims to be but also how the situation evolves over time. A genuine emergency braking event, for example, produces a coherent temporal signature across multiple observers, whereas an injected fake event typically fails to maintain that coherence as vehicles move through the scene.

One of the most practically important findings of the study concerns the calibration of the decision threshold. Through iterative testing, the researchers discovered that accepting messages only when their Trust Score exceeds 0.64 minimizes false acceptances of malicious or erroneous messages while still maintaining acceptable rejection rates for invalid content. This threshold represents a carefully tuned compromise between two competing failure modes. If the threshold is set too low, dangerous fake messages slip through and could trigger unnecessary braking, erratic maneuvers, or worse. If it is set too high, legitimate warnings are discarded, and the safety benefits of V2X evaporate. The identification of a specific operating point gives system designers a concrete, evidence-based starting point for deployment.

The decision to avoid cryptographic methods as the primary line of defense is a deliberate design choice with significant implications. Cryptographic authentication, such as digital signatures on every message, imposes computational overhead, latency, and certificate-management burdens that can be challenging for resource-constrained onboard units and for networks that must process messages at millisecond timescales. LATM does not claim to replace cryptography entirely; rather, it offers a complementary, content-centric layer that evaluates the semantic and physical plausibility of messages. In scenarios where cryptographic credentials have been stolen or where insider attacks originate from legitimately authenticated vehicles, a trust-based content check may catch threats that signature verification alone would miss.

The study situates itself within a rich lineage of trust-management research for vehicular ad hoc networks. Earlier frameworks have explored reputation-based announcement schemes, Bayesian inference models for road messages, data-centric trust establishment in ephemeral networks, and, more recently, blockchain-based anonymous reputation systems and machine-learning-driven trust heuristics for the Internet of Vehicles. What distinguishes LATM is its emphasis on lightness and adaptivity: the six-parameter scoring scheme is designed to be computationally inexpensive enough for real-time operation while remaining flexible enough to adjust to changing network conditions. The authors describe the result as a lightweight, adaptive, and real-time solution for V2X security that can strengthen future intelligent traffic systems.

The threat model addressed by the work is sobering. Message spoofing allows an attacker to impersonate a vehicle or fabricate events, potentially causing chains of sudden braking that increase accident risk rather than reducing it. Trust manipulation targets the reputation mechanisms themselves, attempting to inflate the standing of malicious nodes or deflate that of honest ones. GPS manipulation corrupts the location data on which so many safety applications depend, making a vehicle appear somewhere it is not. Because these attacks exploit the data layer rather than the communication channel, they can be effective even against networks with strong link security, which is precisely the gap that content-based trust evaluation aims to close.

The broader context of this research is the rapid evolution of connected and autonomous mobility. Surveys of V2X technology describe its expansion from dedicated short-range communications into 5G-based location-aware services and, on the horizon, 6G vehicular networks promising ultra-reliable low-latency links. Smart intersections, cooperative adaptive cruise control, and coordinated platooning all depend on vehicles trusting the information they receive from strangers on the road. As these applications mature, the cost of a single accepted false message grows from an inconvenience to a potential catastrophe. Frameworks like LATM address the fundamental epistemological problem of vehicular networking: how does a car, meeting thousands of anonymous peers over its lifetime, decide what is true?

There are, of course, open questions that future work must address. The evaluation relied on a simulated dataset, and the authors note in the article’s data availability statement that no external datasets were generated or analysed during the study, which means real-world validation on physical testbeds and public-road pilots remains an important next step. Adversaries may also adapt, learning to craft messages that satisfy the six plausibility checks, which would push researchers toward richer contextual models and hybrid defenses combining trust scoring with cryptographic and machine-learning techniques. Nevertheless, the study’s central result, that a threshold of roughly 0.64 on a six-parameter Trust Score can meaningfully separate genuine messages from malicious ones in real time, offers a concrete and computationally modest building block for the secure vehicular networks of the coming decade. As cars become rolling nodes in a planetary communication mesh, the ability to judge trustworthiness on the fly, cheaply and adaptively, may prove to be one of the most consequential safety technologies of the intelligent transportation era.

Subject of Research: Lightweight adaptive trust management for securing vehicle-to-everything communication networks

Article Title: LATM: Lightweight and Adaptive Trust Management for Robust V2X Communication

Article References: LATM: Lightweight and Adaptive Trust Management for Robust V2X Communication. (n.d.). https://doi.org/10.1007/s11036-026-02552-2

Image Credits: AI Generated

DOI: 10.1007/s11036-026-02552-2

Keywords: V2X communication, trust management, vehicular networks, road safety, message spoofing, GPS manipulation, sender reputation, intelligent transportation systems, adaptive security, lightweight algorithms, autonomous vehicles, cybersecurity

The team’s starting point was a simple but consequential observation: in terrain as complex as that of Hanzhong City in Shaanxi Province, China, the factors that make a road dangerous are not distributed evenly in space. Steep gradients, winding alignments, and the friction between built-up areas and the surrounding topography create pockets of elevated risk that a single citywide crash rate or safety index simply cannot capture. Rather than relying solely on historical crash data, which is often sparse and biased toward locations where incidents have already been recorded, the researchers set out to model the underlying environmental difficulty of moving through the urban landscape and to combine that model with a structured assessment of human, vehicle, road, and management factors.

The methodological core of the study rests on two complementary models. The first is the Minimum Cumulative Resistance model, a technique borrowed from landscape ecology, where it was originally developed to estimate habitat isolation and to identify least-cost corridors across fragmented terrain. In this adaptation, the researchers converted four environmental variables—elevation, slope, land use, and distance from built-up areas—into a weighted resistance surface at a 30-meter raster resolution. Each cell in the surface carries a resistance value reflecting how difficult or hazardous movement through that cell is likely to be. Cumulative cost surfaces were then computed across the city, and from them the team derived candidate low-resistance connections, pathways that thread through the terrain along routes of comparatively low environmental friction.

The second component is an Extension Matter-Element evaluation, a fuzzy assessment method capable of handling the ambiguity inherent in safety indicators that do not map cleanly onto binary categories. The researchers first constructed a five-dimensional indicator system covering human, vehicle, road, management, and environmental conditions. The system was developed through grounded-theory coding, a qualitative method that systematically extracts categories from source material, followed by expert screening to validate and refine the resulting indicators. Thirteen socio-technical indicators survived this process and were integrated, alongside the environmental resistance output, onto a common five-grade scale within the Extension Matter-Element framework. By expressing all dimensions of road safety in a shared grading language, the model allows environmental difficulty and socio-technical performance to be evaluated together rather than in isolation.

Applied to Hanzhong City, the framework produced strikingly uneven results. The mean environmental resistance calculated across all valid 30-meter raster cells was 2.31, corresponding to Grade III on the five-grade scale. But the district and county averages ranged from 2.049, a Grade II reading, to 2.816, which falls at Grade V—the most severe category. That spread of nearly 0.8 resistance units across administrative units within a single metropolitan area illustrates precisely the problem the study was designed to address: a city-level average of 2.31 describes almost no individual district accurately. Some parts of Hanzhong operate under substantially easier environmental conditions than the average suggests, while others face resistance levels approaching the worst grade on the scale.

The integrated Extension Matter-Element evaluation yielded an overall correlation vector of (−0.21190, −0.23455, −0.12958, −0.16203, −0.34748) across the five grades. Under the maximum-correlation rule, the smallest negative value—−0.12958, associated with Grade III—determines the classification, placing Hanzhong’s overall road-safety condition at Grade III. The researchers are careful to note what this figure does and does not mean. The outputs represent relative environmental difficulty and integrated road-safety conditions, not observed crash probability, and the candidate connections generated by the resistance model are preliminary spatial references for transport planning rather than engineering-ready road alignments. This distinction matters for any agency hoping to translate the maps directly into construction plans; the framework identifies where conditions are comparatively favorable or adverse, not where a specific road should be paved.

Twenty-one candidate low-resistance connections were retained from the analysis, forming a network of preliminary corridors that could inform future transport planning in and around Hanzhong. In the logic of the Minimum Cumulative Resistance model, these connections represent paths that accumulate the least environmental friction between key locations, analogous to the wildlife corridors that landscape planners design to connect fragmented habitats. Transposed into the urban road-safety context, they suggest where new links or upgrades might encounter the least terrain-imposed difficulty, and conversely, where the environment itself contributes most heavily to hazardous conditions. For a mountainous city contemplating expansion, such a map is a form of foresight: it flags the terrain-driven constraints before capital is committed to alignments that fight the landscape rather than follow it.

The study’s indicator system deserves attention in its own right. By grounding the selection of the thirteen socio-technical indicators in grounded-theory coding rather than adopting an off-the-shelf checklist, the researchers anchored the assessment in a systematic reading of the road-safety literature and expert judgment. The five dimensions—human, vehicle, road, management, and environment—reflect a widely accepted systems view of traffic safety, in which crashes emerge from interactions among road users, vehicles, infrastructure, and institutional oversight rather than from any single failing factor. Embedding this socio-technical assessment within a spatial resistance framework is the study’s central innovation, bridging two research traditions that have rarely been combined: spatial road-safety analysis, which emphasizes geography, and multi-criteria evaluation, which emphasizes structured indicator systems.

The broader significance of the work lies in its challenge to the averaging instinct that dominates urban safety reporting. As motorization accelerates in the mountainous regions of China and other rapidly urbanizing countries, the number of cities whose road networks are carved into complex terrain will only grow. Frameworks like the one developed for Hanzhong offer those cities a way to allocate scarce safety resources according to the actual spatial distribution of difficulty and vulnerability, rather than according to administrative boundaries that bear little relation to the topography. The researchers acknowledge that their outputs are relative and preliminary, but the direction is clear: the next generation of road-safety assessment in complex terrain will be drawn cell by cell across the landscape, not summarized in a single number at city hall.

For the scientific community, the study also demonstrates the continued versatility of the Minimum Cumulative Resistance model nearly three decades after its introduction in landscape ecological planning. Its migration from habitat connectivity to urban road safety illustrates how spatial cost-surface methods can be reinterpreted for new domains when paired with domain-appropriate indicator systems and rigorous validation. Whether the framework can be extended with dynamic data—real-time traffic, weather, or incident feeds—remains an open question, and the authors’ caution about the gap between modeled resistance and observed crash outcomes invites future empirical testing. For now, Hanzhong’s resistance maps and twenty-one candidate corridors stand as a proof of concept that the terrain itself can be made legible to safety planners, one 30-meter cell at a time.

Subject of Research: Spatially integrated assessment of urban road-safety conditions in mountainous cities using environmental resistance and socio-technical indicators

Article Title: Spatially integrated assessment of urban road-safety conditions in complex terrain: coupling environmental resistance with socio-technical indicators

Article References: Spatially integrated assessment of urban road-safety conditions in complex terrain: coupling environmental resistance with socio-technical indicators. (n.d.). https://doi.org/10.1007/s11069-026-08406-0

Image Credits: AI Generated

DOI: 10.1007/s11069-026-08406-0

Keywords: road safety, mountainous city, Minimum Cumulative Resistance, Extension Matter-Element model, environmental resistance, spatial assessment, Hanzhong City, transport planning, urban terrain, traffic safety indicators, GIS, Natural Hazards