Explore the vast range of titles available.

Background Road traffic injuries and fatalities remain a significant public health issue worldwide. Serbia achieved a 48% reduction in road traffic mortality from 2010 to 2019 (from 13.9 to 7.8 per 100,000); however, mortality rates remain higher than the EU average (46 deaths per 1,000,000 population in 2022). This study highlights key aspects of the epidemiology of road traffic mortality in AP Vojvodina. Methods A retrospective, observational study was conducted. Data were obtained from official statistical reports provided by the Statistical Office of the Republic of Serbia for 2018–2023. The dataset includes demographic and geographic information on road traffic fatalities. Mortality rates per 10,000 registered vehicles were also calculated. Results A total of 882 fatalities were recorded between 2018 and 2023, with an average annual mortality rate of 8.1/100,000. The overall road traffic fatality rate was 2.15 per 10,000 registered vehicles (based on a total of 4,092,735 registered vehicles). Males accounted for the majority of fatalities, with a male-to-female ratio of 3.7:1 (N = 693, 78.6%; N = 189, 21.4%). The mean age of the victims was 49.9 years (SD = 19.6). The highest mortality was observed among individuals aged 20–39 (26.9%) and 60–69 (18.7%). More than one-third of fatalities occurred among vehicle occupants (N = 308, 35%), followed by pedestrians (N = 182, 20.6%). In terms of temporal patterns, the majority of fatalities (55%) occurred on Sundays. Geographically, the highest mortality rates were observed in the West Bačka (11/100,000) and North Banat (10/100,000) districts, while the lowest rates were reported in the South Banat and North Bačka districts (6.8/100,000). Conclusions These findings highlight the need for targeted traffic safety interventions, particularly focusing on high-risk groups, regions, and time periods. Key messages • Targeted, district-specific interventions are needed to improve road safety and reduce mortality further. • Implementing a multisectoral approach—integrating education, law enforcement, infrastructure improvements, and public health campaigns—can enhance overall road safety in AP Vojvodina. Topic Road traffic accidents, epidemiology, fatalities.

Road accidents have increased rapidly in recent years for a variety of reasons. Analyzing and visualizing road accidents through heatmaps can help improve policies for their prevention by informing about areas with a high-risk of road accidents.The purpose of this research is to build a model for the analysis and visualization of road accidents through heatmaps. Information about road accidents is extracted from the news of the main online media portals through scripts in the Python language and Web Scraping techniques. From the extraction of about 30,000 articles from news portals for one year, only 829 were selected in the end that provided information about road accidents.As a result, and contribution of this research, a corpus was built with the geographic coordinates of road accidents and on this data our model was applied for the analysis and visualization of high-risk areas of road accidents using heatmaps. The visualization of heatmaps was done through a Python script, where it was applied to the geographic coordinates of road accidents.

BackgroundA growing number of studies investigated the factors that contribute to driving under the influence (DUI) of alcohol in relation to gender. However, a gendered approach of the scientific evidence is missing in the literature. To fill this gap, a gender-driven systematic review on real case studies of the last two decades was performed. In addition to the gender of the drivers involved, major independent variables such as the period of recruitment, the type of drivers recruited, and the geographical area where the study was conducted, were examined. Afterwards, a meta-analysis was performed comparing alcohol-positive rates (APR) between male and female drivers in three subgroups of drivers: those involved in road traffic accidents, those randomly tested on the road, and volunteers.MethodsThree databases were searched for eligible studies in October 2023. Real-case studies reporting APR in man and women convicted for DUI of alcohol worldwide were included. Univariate analysis by ANOVA with post-hoc tests identified the independent variables with a significant impact on the dependent variable APR, according to a relationship subsequently investigated by standard multiple linear regression. The meta-analysis of random effects estimates was performed to investigate the change in overall effect size (measured by Cohen’s d standardized mean difference test) and 95% confidence interval (CI).ResultsAmong papers addressing driver gender, univariate analysis of independent variables revealed a higher Alcohol Positive Rate (APR) in men, particularly in drivers involved in crashes, with a noticeable decrease over time. Analyzing the gender of drivers involved in crashes, the meta-analysis showed that men had a significantly higher APR (30.7%; 95%CI 26.8–35.0) compared to women (13.2%; 95%CI 10.7–16.1). However, in drivers randomly tested, there was no significant difference in APR between genders (2.1% for men and 1.4% for women), while in volunteers, there was a statistically significant difference in APR with 3.4% (95%CI 1.5–7.6) for men and 1.1% (95%CI 0.5–2.7) for women.ConclusionDespite a progressive decrease in the epidemiological prevalence of alcohol-related DUI over time, this phenomenon remains at worryingly high levels among drivers involved in road traffic accidents in both genders, with a higher prevalence in men. It’s important for policymakers, professionals, and scientists to consider gender when planning research, analysis, interventions, and policies related to psychoactive substances, such as alcohol or other licit drugs. Forensic sciences can play a vital role in this regard, enabling a thorough analysis of gender gaps in different populations.

Road Safety is a matter of great concern throughout the world. As number of casualties is increasing more than 4% annually in all age groups. It has been predicted that due to road accidents causality rate will grow around 8% till 2030. It’s entirely admissible and saddening to let citizens get killed in road accidents. As a result, to handle this sort of situation, an in-depth analysis is required. The Data of Road accidents are very heterogeneous in nature so analysis of such type of data is tricky. Segmentation is the main task for analyzing such data. So, K-means clustering method is mainly used for it as proposed in the research work. Second task of this model is to extract the data, images and hidden patterns by using Supervised Machine Learning algorithm that will help to form the policies for the prevention from road accidents. The combination of segmentation machine learning algorithm produces meaning full information.

Approximately 1.25–1.30 million people die annually in road traffic accidents worldwide, and up to 50 million are injured. The UN General Assembly Resolution 74/229 emphasizes the utmost importance of addressing the issue of reducing road traffic accidents. Achieving the ambitious goal of reducing road traffic fatalities and injuries by at least 50% during 2021–2030 is associated with numerous challenges, one of which is ensuring the reliability of official statistics. The accuracy of official data in reflecting the actual situation depends on multiple factors: the quality of the data collection and identification system for road accidents, the responsibility of the officials, and, to a significant extent, the willingness and ability of those in charge to present desired outcomes as reality, thereby distorting the relevant statistics. The issue of inaccurate statistical data and its negative impact on subsequent socio-economic management processes has long been recognized. Different countries address this issue with varying degrees of success. Using data on the characteristics of the road traffic accident rate as an example, the problem of statistical data accuracy in Russia and African countries is considered. A comparison of such countries was chosen to illustrate the real problem of the low credibility of official statistical information available for analysis. Unfortunately, the low quality of statistical information does not allow for drawing accurate conclusions about the actual situation in Russia and African countries, and hence, competently and rationally managing socio-economic processes. This conclusion is based both on the analysis of the results of previous studies and on the original statistical analysis of officially available information.

Acute alcohol intoxication impairs cognitive and psychomotor abilities leading to various public health hazards such as road traffic accidents and alcohol-related violence. Intoxicated individuals are usually identified by measuring their blood alcohol concentration (BAC) using breathalyzers that are expensive and labor intensive. In this paper, we developed the Audio-based Deep Learning Algorithm to Identify Alcohol Inebriation (ADLAIA) that can instantly predict an individual's intoxication status based on a 12-s recording of their speech. ADLAIA was trained on a publicly available German Alcohol Language Corpus that comprises a total of 12,360 audio clips of inebriated and sober speakers (total of 162, aged 21–64, 47.7% female). ADLAIA's performance was determined by computing the unweighted average recall (UAR) and accuracy of inebriation prediction. ADLAIA was able to identify inebriated speakers – with a BAC of 0.05% or higher – with an UAR of 68.09% and accuracy of 67.67%. ADLAIA had a higher performance (UAR of 75.7%) in identifying intoxicated speakers (BAC > 0.12%). Being able to identify intoxicated individuals solely based on their speech, ADLAIA could be integrated into mobile applications and used in environments (such as bars, sports stadiums) to get instantaneous results about inebriation status of individuals. •ADLAIA can outperform humans in identifying alcohol-inebriated individuals based solely on 12 seconds of their speech.•ADLAIA could be integrated into mobile applications and used as a preliminary tool for identifying alcohol-inebriation.•ADLAIA was able to identify inebriated speakers – with BAC of 0.05% or higher – with an UAR of 68.09% and accuracy of 67.67%.

Road safety is a worldwide problem and should be a top concern for transportation professionals everywhere. According to the World Health Organization (WHO), approximately 1.3 million people die because of road traffic crashes around the world. Statistics from around the world show the dangers of roadways for drivers and vulnerable users alike. Based on an early estimate of motor vehicle traffic fatalities for 2021 from the National Highway Traffic Safety Administration, 42,915 people died in motor vehicle traffic crashes in the US--the highest number of fatalities since 2005 and an increase of 10.5 percent compared to 2020. Based on the Transport Canada's National Collision Database statistics for 2021, 1,768 people were killed in motor vehicles, up 1.3 percent from 2020--but this number is at its lowest since Transport Canada started collecting the data in the 1970s. Based on a news article by the European Commission, published on Mar 28, 2022, an estimated 19,800 people were killed in road crashes in 2021. This represents 1,000 more deaths (up 5 percent) compared to 2020, but represents 3,000 (down 13 percent) fewer fatalities compared to the pre-pandemic period in 2019.

In Hungary, the visible presence of police in public spaces is a common tool for maintaining traffic safety. While previous studies have primarily focused on the amount of time police spend in public areas, they often neglect the significance of targeted interventions aimed at specific violations. This study examines both aspects: the general police presence and targeted measures. It analyses the relationship between police visibility and the number of alcohol-related road traffic accidents involving personal injuries, as well as the correlation between alcohol-related accidents and the number of breathalyser tests conducted. Nationallevel data from 2019 and 2024 are used for the analysis. Findings indicate a strong positive correlation between time spent in public areas and the number of alcohol-related personal injury road traffic accidents (the average correlation coefficient at the county level is 0.7985), suggesting that visibility alone may not effectively reduce accidents. In addition, a weak positive correlation is observed between alcohol-related accidents and the number of breathalyser tests (the average correlation coefficient is 0.0338), indicating that targeted controls have a weak, almost negligible impact. There is a weak correlation (on average 0.3334) between the number of targeted inspections (breathalyser tests) and the number of positive results. The weak positive relationship may stem, on the one hand, from the high level of latency characteristic of the offence under examination and, on the other hand, from other contributing factors. The results indicate that the most common, yet least effective, tool for addressing the problem is the application or increase of general police presence. Similarly, targeted interventions do not appear to have a measurable impact on the number of alcohol-related traffic accidents involving personal injury.

Early detection of accidents and rescue are of paramount importance in the reduction of fatalities. Social media data, which has evolved to become an important source of sharing information, plays a great role in building machine learning-based models for classifying posts related to accidents. Since the context of the word “accident” is difficult to determine in a posting, various works in literature have developed better classifiers for predicting whether the posting is actually related to an accident. However, an ensemble of classifiers are known to provide better performance than the basic models. Therefore, in this direction, we present a novel weighted majority voting-based ensemble approach for context classification of tweets (WM-ECCT) to detect whether the tweets are related or unrelated to road accidents. For the proposed ensemble model, the weighting scheme is based on the principle of false prediction to true prediction ratio. Also, the proposed model uses the multi-inducer technique and bootstrap sampling to reduce misclassification rates. Moreover, we propose a context-aware labeling approach for the annotation of tweets into related and unrelated categories. Experiments conducted reveal that the proposed ensemble model outperforms the different standalone machine learning and ensemble models on various performance measures.

Recreating a road traffic accident scheme is a task of current importance. There are several main problems when drawing up a plan of accident: a long-term collection of all information about an accident, inaccuracies, and errors during manual data fixation. All these disadvantages affect further decision-making during a detailed analysis of an accident. The purpose of this work is to automate the entire process of operational reconstruction of an accident site to ensure high accuracy of measuring the distances of the relative location of objects on the sites. First the operator marks the area of a road accident and the UAV scans and collects data on this area. We constructed a three-dimensional scene of an accident. Then, on the three-dimensional scene, objects of interest are segmented using a deep learning model SWideRNet with Axial Attention. Based on the marked-up data and image Transformation method, a two-dimensional road accident scheme is constructed. The scheme contains the relative location of segmented objects between which the distance is calculated. We used the Intersection over Union (IoU) metric to assess the accuracy of the segmentation of the reconstructed objects. We used the Mean Absolute Error to evaluate the accuracy of automatic distance measurement. The obtained distance error values are small (0.142 ± 0.023 m), with relatively high results for the reconstructed objects’ segmentation (IoU = 0.771 in average). Therefore, it makes it possible to judge the effectiveness of the proposed approach.