Search Results (341)

Road traffic crashes (RTCs) have emerged as a major global cause of fatalities, with the number of accident-related deaths rising rapidly each day. To mitigate this issue, it is essential to develop early prediction methods that help drivers and riders understand accident statistics relevant to their region. These methods should consider key factors such as speed limits, compliance with traffic signs and signals, pedestrian crossings, right-of-way rules, weather conditions, driver negligence, fatigue, and the impact of excessive speed on RTC occurrences. Raising awareness of these factors enables individuals to exercise greater caution, thereby contributing to accident prevention. A promising approach to improving road traffic accident severity classification is the stacking ensemble method, which leverages multiple machine learning models. This technique addresses challenges such as imbalanced datasets and high-dimensional features by combining predictions from various base models into a meta-model, ultimately enhancing classification accuracy. The ensemble approach exploits the diverse strengths of different models, capturing multiple aspects of the data to improve predictive performance. The effectiveness of stacking depends on the careful selection of base models with complementary strengths, ensuring robust and reliable predictions. Additionally, advanced feature engineering and selection techniques can further optimize the model’s performance. Within the field of artificial intelligence, various machine learning (ML) techniques have been explored to support decision making in tackling RTC-related issues. These methods aim to generate precise reports and insights. However, the stacking method has demonstrated significantly superior performance compared to existing approaches, making it a valuable tool for improving road safety. Full article

Concealed smartphone use while driving (CSUWD), a prevalent and covert form of distracted driving, poses significant threats to road safety. However, the psychological determinants underlying this illegal behavior remain underexplored. A two-wave longitudinal study based on the expanding theory of planned behavior (TPB) investigates the intention and prospective behavior of CSUWD in China. In the first wave, 256 respondents assessed the standard TPB constructs, alongside extended constructs of descriptive norms, moral norms, and perceived risks. Subsequently, 156 participants reported their actual behavior in the second wave. Hierarchical multiple regression results revealed that the traditional TPB variables accounted for 57.1% of intention variance and 45.2% of behavior variance, while extended variables contributed an additional 11.7% to intention variance. All variables, except perceived crash risk, emerged as significant determinants of intention. Notably, the perceived risk of being caught and fined inversely correlated with intention, suggesting a potential disinhibition effect. Both perceived behavioral control and intention were significant determinants of subsequent behavior. The findings underscore the validity of TPB in predicting CSUWD, informing the design of non-legal interventions (e.g., public education advertisement, road awareness campaigns, and technological interventions) to mitigate CSUWD-related distracted driving and promote sustainable transportation systems. Full article

Traffic safety is undergoing a profound transformation, driven by advances in data science, sensing technologies, and computational modeling. Proactive approaches are enabling the early identification of potential hazards, real-time decision-making, and the development of smarter, safer transportation systems. This Special Issue summarizes recent progress in traffic safety assessment, highlighting the application of emerging tools such as machine learning, explainable artificial intelligence, and computer vision. These innovations are used to predict crash risks, evaluate surrogate safety measures, and automate the analysis of behavioral data, contributing to more inclusive and adaptive safety frameworks, particularly for vulnerable road users such as pedestrians and cyclists. The research also addresses key challenges, including data integration across diverse sources, aligning safety metrics with human perception, and ensuring the scalability of models in complex environments. By advancing both technical methodologies and human-centered evaluation, these developments signal a shift toward more intelligent, transparent, and equitable approaches to traffic safety assessment and policy-making. Full article

Understanding the determinants of crash injury severity is essential for developing effective safety strategies and reducing traffic-related losses. This study proposes a hybrid analytical framework that integrates interpretable machine learning with statistical modeling to address the limitations of existing approaches. A Random Forest (RF) classifier, combined with Shapley Additive Explanations (SHAP), was first employed to capture nonlinear relationships and identify key predictors of injury outcomes, including safety equipment, age, gender, and the presence of fixed obstacles. Random Forest was chosen for its strong predictive performance in capturing nonlinear relationships, while SHAP provides transparent explanations of model predictions. To ensure statistical rigor and quantify associations, a Partial Proportional Odds (PPO) model was subsequently applied, allowing for the relaxation of the proportional odds assumption (POA) and enabling the estimation of marginal effects. The results consistently highlight the protective role of safety equipment and the increased risks associated with fixed obstacles, adverse weather, and nighttime conditions. For instance, seatbelt use is associated with a 29.61% higher probability of no injury, whereas fixed obstacles are associated with a 29.36% lower probability and a higher risk of severe injury. These findings support safety campaigns that encourage protective equipment use and infrastructure policies aimed at reducing roadside obstacles and improving nighttime visibility. Future research will focus on accounting unobserved heterogeneity and validating the framework across multi-regional datasets to improve its generalizability and policy relevance. Full article

This study proposes a hybrid deep learning framework for predicting vehicle crash frequency (F_i) using nationwide traffic accident and traffic volume data from the United States (2019–2022). Crash frequency is defined as the product of exposure frequency ($N_a$) and crash risk rate ($\lambda$), a structure widely adopted for its ability to separate physical exposure from the crash likelihood. $N_a$ was computed using an extended Safety Performance Function (SPF) that incorporates roadway traffic volume, segment length, number of lanes, and traffic density, while $\lambda$ was estimated using a multilayer perceptron-based deep neural network (DNN) with inputs such as impact speed, road surface condition, and vehicle characteristics. The DNN integrates rectified linear unit (ReLU) activation, batch normalization, dropout layers, and the Huber loss function to capture nonlinearity and over-dispersion beyond the capability of traditional statistical models. Model performance, evaluated through five-fold cross-validation, achieved R² = 0.7482, MAE = 0.1242, and MSE = 0.0485, demonstrating a strong capability to identify high-risk areas. Compared to traditional regression approaches such as Poisson and negative binomial models, which are often constrained by equidispersion assumptions and limited flexibility in capturing nonlinear effects, the proposed framework demonstrated substantially improved predictive accuracy and robustness. Unlike prior studies that loosely combined SPF terms with machine learning, this study explicitly decomposes F_i into $N_a$ and $\lambda$, ensuring interpretability while leveraging DNN flexibility for crash risk estimation. This dual-layer integration provides a unique methodological contribution by jointly achieving interpretability and predictive robustness, validated with a nationwide dataset, and highlights its potential for evidence-based traffic safety assessments and policy development. Full article

This study investigates the severity of injuries sustained by over seven million participants involved in road traffic incidents in Poland between 2015 and 2024, with a view to supporting sustainable mobility and the United Nations Sustainable Development Goals. Road safety is a crucial dimension of sustainable development, directly linked to public health, urban liveability, and the socio-economic costs of transportation systems. Using a harmonised participant-level dataset, this research identifies key demographic, behavioural, and environmental factors associated with injury outcomes. A novel five-level injury severity variable was developed by integrating inconsistent records on fatalities and injuries. Descriptive analyses revealed clear seasonal and weekly patterns, as well as substantial differences by participant type and driving licence status. Pedestrians and passengers faced the highest risk, with fatality rates more than five times higher than those of drivers. An XGBoost classifier was trained to predict injury severity, and SHAP analysis was applied to interpret the model’s outputs at the feature level. Participant role emerged as the most important predictor, followed by driving licence status, vehicle type, lighting conditions, and road geometry. These findings provide actionable insights for sustainable road safety interventions, including stronger protection for pedestrians and passengers, stricter enforcement against unlicensed driving, and infrastructural improvements such as better lighting and safer road design. By combining machine learning with interpretability tools, this study offers an analytical framework that can inform evidence-based policies aimed at reducing crash-related harm and advancing sustainable transport development. Full article

The significant impact of road traffic accidents on public health requires clear and effective policies to combat them. However, public action can only be truly effective when supported by robust monitoring tools. This project aims to evaluate the effectiveness of a set of machine learning algorithms in predicting road accidents in Switzerland, utilizing open-access Confederation drive crash databases combined with environmental and socio-economic factors. Three different algorithms are tested: Logistic Regression Model (LRM), Random Forest with Ranger (RF), and Artificial Neural Network (ANN) with Keras. Among the predictive factors, road types are shown to be of high importance in all models. Regarding model performance, all the applied algorithms show a high level of accuracy, with all models achieving over 90%. The Random Forest algorithm, optimised using the Ranger application, exhibited the best performance, particularly in terms of specificity (0.88 compared to 0.34 and 0.40 for LRM and Keras, respectively) and negative predictive value (0.96 compared to 0.65 for LRM and 0.68 for Keras). These results suggest that this approach could support public policy for traffic management, if data collection and sharing activities are constantly carried out. Full article

In a few years, most investment firms will deploy Generative AI (GenAI) and large language models (LLMs) for reduced-cost stock trading decisions. If GenAI-run investment decisions from most firms are heavily coordinated, they could all give a “sell” signal simultaneously, triggering market crashes. Likewise, simultaneous “buy” signals from GenAI-run investment decisions could cause market bubbles with algorithmically inflated prices. In this way, coordinated actions from LLMs introduce systemic risk into the global financial system. Existing risk analysis for GenAI focuses on endogenous risk from model performance. In comparison, exogenous risk from external factors like macroeconomic changes, natural disasters, or sudden regulatory changes, is understudied. This research fills the gap by creating a framework for measuring exogenous (systemic) risk from LLMs acting in the stock trading system. This research develops a concrete, quantitative framework to understand the systemic risk brought by using GenAI in stock investment by measuring the covariance between LLM stock price predictions across three industries (technology, automobiles, and communications) produced by eight large language models developed across the United States, Europe, and China. This paper also identifies potential data-driven technical, cultural, and regulatory mechanisms for governing AI to prevent negative financial and societal consequences. Full article

Predicting driver injury severity is critical for enhancing road safety, but it is complicated because fatal accidents inherently create class imbalance within datasets. This study conducts a comparative analysis of machine-learning (ML) and deep-learning (DL) models for multi-class driver injury severity prediction using a comprehensive dataset of 107,195 traffic accidents from the Adana, Mersin, and Antalya provinces in Turkey (2018–2023). To address the significant imbalance between fatal, injury, and non-injury classes, the hybrid SMOTE-ENN algorithm was employed for data balancing. Subsequently, feature selection techniques, including Relief-F, Extra Trees, and Recursive Feature Elimination (RFE), were utilized to identify the most influential predictors. Various ML models (K-Nearest Neighbors (KNN), XGBoost, Random Forest) and DL architectures (Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), Recurrent Neural Network (RNN)) were developed and rigorously evaluated. The findings demonstrate that traditional ML models, particularly KNN (0.95 accuracy, 0.95 F1-macro) and XGBoost (0.92 accuracy, 0.92 F1-macro), significantly outperformed DL models. The SMOTE-ENN technique proved effective in managing class imbalance, and RFE identified a critical 25-feature subset including driver fault, speed limit, and road conditions. This research highlights the efficacy of well-preprocessed ML approaches for tabular crash data, offering valuable insights for developing robust predictive tools to improve traffic safety outcomes. Full article

This research addresses the challenge of predicting operating vehicles’ speeds (V85) on single-carriageway road tangents. While most previous models rely on preceding segment speeds or focus on curves, this research develops an independent prediction model specifically for road tangents, based on empirical data collected in Croatia. A total of 46 locations across 23 road cross-sections were analysed, with operating speeds measured using field radar surveys and fixed traffic counters. Following a comprehensive correlation and multicollinearity analysis of 24 geometric, environmental, and traffic-related variables, a multiple linear regression model was developed using a training dataset (36 locations) and validated on a separate test set (10 locations). The model includes nine statistically significant predictors: shoulder type (gravel), edge line quality (excellent and satisfactory), pavement quality (excellent), average summer daily traffic (ASDT), crash ratio, edge lane presence, overtaking allowed, and heavy goods vehicle share. The model demonstrated strong predictive performance (R² = 0.89, RMSE = 5.24), with validation results showing an average absolute deviation of 2.43%. These results confirm the model’s reliability and practical applicability in road design and traffic safety assessments. Full article

Identification of causal factors in traffic crashes has always been a significant challenge in road safety studies. Traditional crash prediction models are limited in elucidating the underlying causal mechanisms in road crashes. This research explores the application of three graphic models, namely, the Gaussian graphical model (GGM), causal Bayesian network (CBN) and graphic extreme gradient boosting (XGBoost), through a case study using highway–railroad-grade crossing (HRGC) inventory and collision data from Canada. The three modelling approaches have generally yielded consistent findings on various risk factors such as crossing control type, track angle, and exposure, showing their potential for identifying causal relationships through the interpretation of causal graphs. With the ability to make better causal inferences from crash data, the effectiveness of safety countermeasures could be more accurately and reliably estimated. Full article

Deep learning (DL) models show considerable promise in detecting driver drowsiness, a major contributor to road traffic crashes. This systematic review evaluates the performance, contexts of application, and implementation challenges of DL-based drowsiness detection systems. Conducted in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) 2020 guidelines, the review includes peer-reviewed empirical studies published between 2015 and 2025 that develop and validate DL models using data collected in real or simulated driving environments. Studies were identified through systematic searches in PubMed, Scopus, Web of Science, ScienceDirect, and IEEE Xplore, last updated in March 2025. Due to methodological heterogeneity, findings are synthesized narratively. Eighty-one studies meet the inclusion criteria. Most employ Convolutional Neural Networks, Recurrent Neural Networks, or hybrid architectures and use behavioral, physiological, or multimodal inputs. Reported median values for accuracy and F1-score exceed 0.95 under both simulated and real-world conditions. However, studies frequently lack demographic diversity, standardized performance reporting, and robust validation protocols. Key limitations include limited dataset transparency, inconsistent evaluation metrics, and insufficient attention to ethical and privacy considerations. While DL models exhibit strong predictive performance, their real-world deployment remains limited by practical and methodological constraints. Future research should place emphasis on the development of inclusive datasets, the conduct of multi-context evaluations, the advancement of real-world deployment strategies, and the rigorous adherence to ethical standards. Full article

In clinical decision support systems (CDSSs), where accurate classification of drug–drug interactions (DDIs) can directly affect treatment safety and outcomes, identifying drug interactions is a major challenge, introducing a scalable approach for classifying DDIs utilizing a finely-tuned biomedical language model. The method shown here uses BiomedBERT, a domain-specific version of bidirectional encoder representations from transformers (BERT) that was pre-trained on biomedical literature, to reduce the number of resources needed during fine-tuning. Low-rank adaptation (LoRA) was used to fine-tune the model on the DrugBank dataset. The objective was to classify DDIs into two clinically distinct categories, that is, synergistic and antagonistic interactions. A pseudo-labeling strategy was created to deal with the problem of not having enough labeled data. A curated ground-truth dataset was constructed using polarity-labeled interaction entries from DrugComb and verified DrugBank antagonism pairs. The fine-tuned model is used to figure out what kinds of interactions there are in the rest of the unlabeled data. A checkpointing system saves predictions and confidence scores in small pieces, which means that the process can be continued and is not affected by system crashes. The framework is designed to log every prediction it makes, allowing results to be refined later, either manually or through automated updates, without discarding low-confidence cases, as traditional threshold-based methods often do. The method keeps a record of every output it generates, making it easier to revisit earlier predictions, either by experts or with improved tools, without depending on preset confidence cutoffs. It was built with efficiency in mind, so it can handle large amounts of biomedical text without heavy computational demands. Rather than focusing on model novelty, this research demonstrates how existing biomedical transformers can be adapted to polarity-aware DDI classification with minimal computational overhead, emphasizing deployment feasibility and clinical relevance. Full article

This study examines the impact of reproductive inequality on the long-term survival of Homo sapiens by comparing two reproductive models: the Pareto (power-law) distribution of unequal reproduction and the Gaussian (normal) distribution of equal reproduction. We conducted simulations to explore how genetic diversity, measured by heterozygosity, evolves over time. The results predict population crashes due to genetic bottlenecks under both models, but with large differences in timing. We refer to Pareto reproductive inequality as the Genghis Khan effect. This effect accelerates the loss of genetic diversity, increasing the species’ vulnerability to environmental stressors, resource depletion, and genetic drift, and thereby raising the risk of an earlier population collapse. Our findings showcase the importance of reproductive balance for the prolonged presence of Homo sapiens on this planet. Full article

Traffic crashes represent a major challenge for road safety, public health, and mobility management in complex urban environments, particularly in metropolitan areas characterized by intense traffic flows, high population density, and strong commuter dynamics. The development of short-term traffic crash prediction models represents a fundamental line of analysis in road safety research within the scientific community. Among these efforts, macro-level modeling plays a key role by enabling the analysis of the spatiotemporal relationships between diverse factors at an aggregated zonal scale. However, in cities like Bogotá, predicting short-term traffic crashes remains challenging due to the complexity of these spatiotemporal dynamics, underscoring the need for models that more effectively integrate spatial and temporal data. This paper presents a strategy based on deep learning techniques to predict short-term spatiotemporal traffic crashes in Bogotá using 2019 data on socioeconomic, land use, mobility, weather, lighting, and crash records across TMAU and TAZ zones. The results showed that the strategy performed with a model called SpatioConvGru-Net with top performance at the TMAU level, achieving $R^2$ = 0.983, MSE = 0.017, and MAPE = 5.5%. Its hybrid design captured spatiotemporal patterns better than CNN, LSTM, and others. Performance improved at the TAZ level using transfer learning. Full article