Traffic Accidents Research Articles

PV-YOLO: A lightweight pedestrian and vehicle detection model based on improved YOLOv8

With the frequent occurrence of urban traffic accidents, fast and accurate detection of pedestrian and vehicle targets has become one of the key technologies for intelligent assisted driving systems. To meet the efficiency and lightweight requirements of smart devices, this paper proposes a lightweight pedestrian and vehicle detection model based on the YOLOv8n model, named PV-YOLO. In the proposed model, receptive-field attention convolution (RFAConv) serves as the backbone network because of its target feature extraction ability, and the neck utilizes the bidirectional feature pyramid network (BiFPN) instead of the original path aggregation network (PANet) to simplify the feature fusion process. Moreover, a lightweight detection head is introduced to reduce the computational burden and improve the overall detection accuracy. In addition, a small target detection layer is designed to improve the accuracy for small distant targets. Finally, to reduce the computational burden further, the lightweight C2f module is utilized to compress the model. The experimental results on the BDD100K and KITTI datasets demonstrate that the proposed PV-YOLO can achieve higher detection accuracy than YOLOv8n and other baseline methods with less model complexity.

Reduce Speed Limits to Minimize Potential Harm and Maximize the Health Benefits of Street Trees

Urban greening is threatened by the concern that street trees increase traffic-related injury/death. Associations between all serious and fatal traffic crashes and street tree percentages were examined in Sydney, Australia. Associations were adjusted for confounding factors relating to driver behavior (speeding, fatigue, and use of alcohol) and road infrastructure, including alignment (e.g., straight, curved), surface condition (e.g., dry, wet, ice), type (e.g., freeway, roundabout), and speed limit. Models indicated that 10% more street trees were associated with 3% and 20% higher odds of serious or fatal injuries and 20% tree collisions on roads of any speed, respectively. However, further analysis stratified by speed limit revealed contrasting results. Along roads of 70 km/h or greater, 10% more street trees were associated with 8% higher odds of serious or fatal injury and 25% higher odds of death. Comparable associations were not found between street trees and serious or fatal injuries along roads below 70 km/h. Reducing speed limits below 70 km/h saves lives and may mitigate risks of serious or fatal traffic accidents associated with street trees, enabling greener, cooler, healthier cities.

Hybrid deep learning model with VMD-BiLSTM-GRU networks for short-term traffic flow prediction

Accelerating urbanization and the rapid development of intelligent transportation systems have rendered short-term traffic flow prediction an important research field. Accurate prediction of traffic flow is beneficial for the optimization of traffic planning, improvement of road utilization, reduction of traffic congestion, and reduction in the incidence of traffic accidents. However, data pertaining to traffic flow are typically influenced by a multitude of factors, resulting in data that exhibit a considerable degree of nonlinearity and complexity. To address the issue of noise in raw traffic flow data, this study proposes a hybrid model that combines variational modal decomposition (VMD), a bidirectional long short-term memory network (BiLSTM), and a gated recurrent unit (GRU) for short-term traffic flow prediction. To validate the effectiveness of the model, an experimental validation was conducted based on traffic flow data from UK highways, and the performance of the model was compared with common benchmark models. The experimental results demonstrate that the proposed method yields superior prediction results in terms of mean absolute error, coefficient of determination, and root-mean-square error compared to existing prediction techniques, thereby substantiating its efficacy in short-term traffic flow prediction.

The method of driver fatigue detection in intelligent driving

Abstract. Fatigue driving is one of the main causes of traffic accidents, and currently available methods for detecting driver fatigue include sensor detection and intelligent driving assistance. The importance of driver fatigue detection lies in timely detection of the driver condition, which helps reduce fatigue driving accidents. The research on fatigue detection technology has also provided more sensors and data processing techniques for intelligent driving systems, promoting the improvement and optimization of intelligent driving systems. This article reviews the technologies available for fatigue detection, summarizes existing research on driver fatigue detection, analyzes various modal detection methods and the use of AI in fatigue monitoring, and proposes future research and development trends for fatigue detection systems. This paper discussed three parts of fatigue monitoring technology: sensor technology, data processing technology, and algorithm optimization, and analyzed their advantages, disadvantages, and future development trends. The conclusion is that fatigue monitoring technology should use the advantages of different sensors and combine them with intelligent driving. The accuracy of this technology still needs to be improved.

Functional outcomes of tension band wiring versus hook plating in displaced, closed, and isolated distal clavicle fractures in adults: a comparative retrospective study.

Clavicle fractures are common among young people, generally as a consequence of car accidents, bike falls, and contact sports injuries. 15-20% of all clavicle fractures involve the lateral end of the bone. Thus, the distal clavicle fractures, in particular, have a high non-union rate ranging from 21 to 33% when treated non-operatively, underscoring the usual advice for operative treatment. While significant research has been conducted on clavicle fractures and their treatment options, no definitive guidelines or optimal approaches have been established. Hence, the aim of this study was to assess the clinical and radiological results of the two highly used surgical techniques, Tension Band Wiring (TBW) and Hook plate ones, in addition to investigating the associated functional recovery and outcomes. Between August 2019 and 2022, An analytical retrospective comparative study, was done on 38 patients (20 TBW and 18 Hook plate) diagnosed with unstable fracture of the lateral third of clavicle (Neer 2), aged between 18 and 65 years old, and followed up for more than 12 months. TBW technique was used in 20 patients (14 males and 6 females) with mean age 39.25 years and Hook plate was used in 18 patients (14 males,4 females) with mean age of 43.11 years. The union rate was 100% in Hook plate group and 95% in TBW group. The mean time of bony union to occur was (9.55) weeks in TBW group and (8.94) weeks in Hook plate group. The mean of constant-Murley score in the last follow-up was 85.32 in the TBW group and 87.38 in the Hook plate group. superficial infection occurred in 3 cases in TBW group (15%). Four patients complained of impingement, three patients complained of acromial erosion and one patient complained of acromial osteolysis in the Hook plate group. Both TBW and Hook plate are a good choice for the fixation of displaced distal clavicle fractures with good functional and radiological outcomes, where Hook plate have some advantages such as rigid fixation and early motion of the affected shoulder.

Efficacy of Acupuncture in Reducing Accidental Injury Risk in Stroke Patients: A National-Scale Cohort Study

BackgroundFalls among stroke patients pose a significant health concern, leading to injuries, reduced mobility, and functional limitations. Recent research has suggested the potential benefits of acupuncture in enhancing balance and motor function in stroke patients. However, large-scale, long-term studies on acupuncture's role in reducing the risk of accidental injuries are scarce. This study aimed to evaluate acupuncture's effectiveness in decreasing the risk of accidental injuries in stroke patients. Materials and methodsThis study employed a large-scale cohort design, utilizing data from the 2000 Longitudinal Generation Tracking Database (LGTD 2000) in Taiwan, covering two million individuals. The cohort comprised stroke patients hospitalized between 2001 and 2012, with follow-up periods of at least six years to estimate accidental injury incidence and risk. Acupuncture treatments during both inpatient and outpatient phases after stroke diagnosis were included. Accidental injury data, including vehicular accidents and falls, were extracted from specialized hospitalization records. Hazard ratios were calculated, adjusting for variables like comorbidities, hypnotic medication usage, and demographic factors. ResultA total of 108,196 newly diagnosed stroke patients were included in the final cohort, with 42,083 receiving acupuncture treatment and 66,113 not receiving acupuncture. The acupuncture group exhibited a significantly lower incidence rate of accidental injuries (10.2 per 1,000 person-years) compared to the non-acupuncture group (15.8 per 1,000 person-years). After adjusting for various covariates, the acupuncture group had a reduced risk of accidental injuries with an adjusted hazard ratio (aHR) of 0.74 (95% CI: 0.51-0.92). Subgroup analyses revealed consistent protective effects of acupuncture across different patient profiles and treatment characteristics, including age, sex, comorbidities, and hypnotic medication usage. ConclusionThis study provides evidence supporting the potential of acupuncture as an adjunctive therapy to reduce the risk of accidental injuries among stroke patients. Regardless of stroke subtype, age, or comorbidity burden, acupuncture was associated with a lower risk of accidental injuries.

Bibliometric Analysis of Traffic Accident Prediction Studies from 2003 to 2023: Trends, Patterns and Future Directions

Traffic accidents are one of the main causes of fatalities and serious injuries among both adults and children worldwide. Due to the ongoing significant socio-economic losses brought on by traffic accidents, precise estimation of the risk of accidents is crucial to reducing subsequent incidents. For this reason, a significant proportion of the studies in the literature include studies on estimating the risk, severity, frequency, location and duration of accidents. The objective of this article is to identify patterns, gaps and future research trends in traffic accident prediction studies conducted between 2003 and 2023. A bibliometric study is carried out to investigate the links and trends in traffic accident and forecasting studies, with a focus on identifying dominant narratives and networks within the academic community. In the keyword search, 1,566 articles were analysed using the Web of Science main collection and bibliometric indicators such as annual publications and citations, top 10, authors, journals, institutions, most cited articles, and a citation analysis of the articles was presented. The results obtained suggest that the discernible patterns identified in this bibliometric analysis of traffic accidents and their predictions will find a much broader application in new paradigms that are ready to catalyse transformative advances in this field, such as artificial intelligence, machine learning and Industry 4.0 applications.

Development of Autonomous Vehicle Evaluation Scenarios Based on Car-to-Bicycle, Car-to-Pedestrian, and Car-to-Animal Traffic Accidents

Development of Autonomous Vehicle Evaluation Scenarios Based on Car-to-Bicycle, Car-to-Pedestrian, and Car-to-Animal Traffic Accidents

Emerging Role of Prefrontal Lobe Involving Visual Function in a Case with Whiplash-Associated Disorders

Whiplash, often resulting from vehicle accidents, can cause bony or soft tissue injuries leading to clinical symptoms related to the cervical spine or brain. However, diagnosing whiplash objectively is challenging, as acute phase abnormalities in the cervical spine or brain are difficult to detect through anatomic/ structural imaging. We present a case of a 54-year-old woman suffering from Whiplash-Associated Disorder (WAD) without abnormal structural abnormalities. Using brain perfusion single-photon emission computed tomography (SPECT) to measure regional cerebral blood flow, hypoperfusion was observed in the bilateral prefrontal regions and parietal/occipital lobes, which was associated with her visual impairment. We support the nociceptive-vascular hypothesis and propose an additional role for the prefrontal lobe in contributing to WAD in patients following whiplash injury. Further investigation is needed to monitor the effects of brain perfusion after treatment using SPECT.

Enhancing Road Safety with Smart Infrastructure: Development and Implementation of Advanced Zebra Crossings and Speed Breaking

Abstract: This study addresses a critical issue in road safety by proposing innovative solutions to mitigate accidents caused by speeding and reckless driving, particularly in high-risk areas such as highways, hospitals, and schools. With road traffic accidents accounting for approximately 1.3 million fatalities annually, along with 20 to 50 million injuries or disabilities, the inefficacy of traditional traffic control systems is a growing concern. Factors such as poor visibility, adverse weather, and driver distractions further compromise the effectiveness of conventional signs and signals. This research introduces a "smart zebra crossing" system that integrates ultrasonic sensors and embedded LED lights to provide real-time alerts to both drivers and pedestrians, thereby enhancing visibility and safety, especially under low-light conditions. Additionally, a "smart speed breaking" system is proposed, which dynamically adjusts its height based on vehicle speed, detected through ultrasonic sensors, prompting drivers to decelerate when necessary. Both systems are linked to a central traffic management network, facilitating real-time adjustments in speed limits and providing alerts to connected vehicles. The integration of these technologies represents a significant advancement in road safety, offering an adaptive, intelligent solution for improving traffic management and reducing the risk of accidents, particularly in vulnerable zones.

028. Traumatic Diaphragmatic Rupture with Unstable Hemodynamic: A Case Report of a Rare Surgical Trauma Emergency

Background: Traumatic diaphragmatic rupture (TDR) with unstable hemodynamics is a life-threatening condition often masked by other injuries, necessitating timely diagnosis and treatment. This case report illustrates the significance of rapid response and resuscitation in managing a 17-year-old female patient with TDR following a severe traffic accident. Case: A 17-year-old female patient was admitted after a motorcycle accident, arriving at the hospital 4 hours and 10 minutes post-incident. She displayed respiratory distress (SpO2: 80% on FM) and severe hemodynamic instability (BP: 70/40 mmHg, HR: 121 bpm). Grade IV traumatic diaphragmatic rupture (AAST) was confirmed alongside multiple injuries. Resuscitation began with intubation, 1 L of crystalloid fluid, and a 1-unit PRC transfusion. Initial management improved her BP to 80/60 mmHg; however, it later dropped to 60/40 mmHg. A FAST Ultrasonography (USG) revealed free echogenic fluid in the hepatorenal space, prompting emergency exploratory laparotomy. Intraoperatively, a diaphragmatic rupture was identified, with herniation of the liver, stomach, and colon. Surgical interventions included diaphragmatic repair and chest tube insertion. Postoperatively, the patient required vasopressors (dobutamine and epinephrine) to stabilize her hemodynamics (BP: 100/60 mmHg, HR: 83 bpm). Conclusion: Early diagnosis and aggressive resuscitation are vital in managing TDR with unstable hemodynamics, underscoring the necessity for rapid assessment and intervention.

ANALISIS PENINGKATAN PENGGUNAAN SEPEDA MOTOR DI KOTA DENPASAR

Currently, the motorcycle population in big cities in Indonesia is increasing very rapidly. Motorcycles are the most popular mode of transportation in Denpasar City. The increase in the use of motorcycles (SPM) has an impact on congestion, air pollution and high traffic accidents involving SPM. This study aims to analyze the increase in the use of SPM in Denpasar City, involving the variables of Household Characteristics, Costs, and Advantages of SPM. Primary data collection was carried out by distributing questionnaires, as many as 400 copies distributed throughout the sub-districts in Denpasar City. The questionnaire contains a Likert scale, containing statements, where respondents provide their perceptions through the available answer choices. Analysis of public perception data was analyzed using multiple linear regression statistical methods. Based on the results of the analysis, the variables of Household Characteristics, Costs, and Advantages of SPM have a significant positive effect on the Increase in the use of SPM, each with tcount = 6.110; 6.847; and 7.865> ttable = 1.966; and all sig values. 0.000 < 0.05. The influence of the three variables together is Fcount = 209.162 > Ftable = 0.072. Sig. value = 0.000 < 005. The equation model obtained is: Y = 0.296X1 + 0.294X2 + 0.290X3 + e.

A Five-year Study of Spinal Disorders among Patients Presenting to the National Trauma Center of Nepal: An Observational Study

Introduction: Spinal cord injuries result in severe neurological impairments and disabilities. With an estimated 15.4 million cases globally in 2021, spinal cord injuries are more common in low- and middle-income countries, yet research in these areas is limited. This study aimed to find the pattern of spinal injuries and outcomes associated with spine injuries over a five-year duration at a tertiary trauma care center. Methods: This observational cross-section study was conducted at the National Trauma Center, Kathmandu from 2075 to 2080 B.S. with ethical clearance from the Nepal Health Research Council (Reference number: 968). Total-population sampling was used. A structured proforma was employed as the primary data collection tool. Data was analyzed using SPSS. Results: Of the 20843 patients, 2070 (9.93%) had spinal injuries. The median age was 43 (IQR 32-56) years, with 1391 (67.20%) male patients. The median hospital stay was 12 (IQR 7-20) days. Falls accounted for 1221 (58.99%) cases, and road traffic accidents for 195 (9.42%). Spinal fractures were present in 1076 (51.98%) patients with 456 (42.38%) in lumbar vertebra. There were 225 (10.87%) cases of subluxation with 214 (95.11%) in cervical level. Conclusions: The study provides insights into the patterns and outcomes of spinal injuries over five years of time. The mortality rate and cases of patients leaving against medical advice highlight areas for improvement in patient care and follow-up.

Assessing braking performance on wet-road through water-depth estimation and vehicle-pavement dynamic simulation

ABSTRACT The presence of water on wet roads due to rainfall has emerged as a critical factor influencing driving safety. During severe weather, the non-uniform water distribution on the road can significantly diminish pavement friction, elevating the risk of traffic accident. Furthermore, the tire-pavement friction coefficient varies with vehicle velocity, rendering wet braking analysis complex. Conventional braking risk analysis often assumes a fixed friction coefficient, neglecting the impact of uneven pavement-induced water depth irregularities. This paper introduces a novel braking performance assessment method based on water-depth estimation and vehicle-pavement simulation. The uneven water-depth distribution is first estimated using LiDAR-measured pavement geometry. A co-simulation framework is then proposed to analyze the tire-pavement friction and study the dynamic braking performance. The 85th percentile stopping distance is adopted as the evaluation index for quantifying braking risk. Results from case studies highlight the substantial influence of rainfall intensity and vehicle velocity on braking risk. Additionally, pavement rutting accumulates deeper water depth, thereby elevating braking safety risks. The proposed model offers a novel perspective on vehicle braking risk analysis and can serve as a valuable safety indicator for highway transportation management and decision-making in driving strategies during wet weather conditions.

Application of Multi-criteria Decision-making Methods for Forensic Analysis of Mechanical Parts in Vehicle Accidents using q-Rung Orthopair Fuzzy Numbers

This study explores the application of a Multi-Criteria Decision-Making (MCDM) approach based on q-rung orthopair fuzzy numbers to identify the origin of mechanical parts found at vehicle accident scenes. The primary objective is to determine the most likely vehicle to which these parts belong by evaluating key criteria such as compatibility, damage level, serial number matching, and color compatibility. Q-rung orthopair fuzzy numbers offer an advanced method to handle the inherent uncertainty and vagueness associated with forensic evaluations, particularly in scenarios where data is incomplete or imprecise. The proposed methodology involves defining the criteria, assigning membership and non-membership degrees using q-rung orthopair fuzzy sets, and applying an aggregation process to effectively rank alternatives. This approach facilitates flexible decision-making by accommodating different levels of confidence and uncertainty, making it particularly suitable for forensic applications where evidence is often ambiguous. The findings demonstrate that integrating q-rung orthopair fuzzy numbers into the MCDM framework significantly enhances the accuracy and reliability of identifying vehicle components involved in accidents. The proposed methodology provides a systematic tool to support forensic investigations, aiding in the determination of liability and contributing to more robust outcomes in mechanical evidence analysis.

Knowledge And Practice Regarding Prehospital Care After Road Traffic Accidents Among Three-Wheel Drivers and Associated Factors in Selected Police Areas in Colombo District, Sri Lanka

Introduction: Road traffic injuries are an increasingly significant public health issue worldwide. Knowledge and practice of prehospital care is a crucial responsibility of every citizen of the country. Pre-hospital care is delivered by a civilian first responder, who is usually another driver. The study aims to describe the knowledge and practice of prehospital care after a road traffic injury among three-wheel drivers and associated factors in selected police areas in the Colombo District. Methods: A communitybased descriptive cross-sectional study was carried out in three Colombo Municipality police areas. A sample of 384 full-time three-wheel drivers above the age of 18 years, registered in these police areas were recruited using a simple random sampling method. A structured pre-tested intervieweradministered questionnaire was used for data collection. Descriptive analysis was used to determine the level of knowledge and practices regarding prehospital care. SPSS version 25 was used for data entry and analysis. Significance was taken as p<0.05. Results: Mean age of three-wheel drivers was 40.98 (SD±11.01). Only 31.5% of the drivers had first aid training. The majority (52.9%) of the drivers had good knowledge and 65.2% had poor practice towards prehospital care. Advanced age (>45 years) and having first aid training were significantly associated with good knowledge (p<0.05). Drivers with previous training within the last ten years (p=0.031) and having less hires per day (<10) were significantly associated with better first aid practice (p=0.001). Conclusion: Although knowledge regarding prehospital care was adequate, practice of prehospital care was inadequate. Findings of the study call for ongoing first-aid training for all three-wheel drivers.Keywords: Prehospital care, First aid, Knowledge, Practice, Road traffic accidents

MEASUREMENT AND CHARACTERISTIC ANALYSIS OF SKELETAL GEOMETRIC PARAMETERS IN CHINESE HUMANS

Problem: Significant differences exist between the body dimensions of Chinese and Western individuals, and these differences affect the injury characteristics of passengers in traffic accidents. Most current parametric finite element human models are based on Western body data, which does not adequately assess the injury risks for Chinese individuals. Therefore, it is imperative to establish a digital model that reflects the anatomical features of Chinese humans. This requires comprehensive anthropometric data specific to the Chinese population. Aim: This study aims to collect and analyze skeletal geometric parameters from various representative regions in China across different age groups to fill the gap in Chinese anthropometric data. Additionally, it seeks to explore regional and age-related differences in these parameters, providing a scientific basis for developing finite element models that reflect the characteristics of the Chinese population. Methods: Clinical CT data of skeletal geometric parameters were collected from 224 individuals across seven representative regions of China, including parameters of the head, chest, and lower limbs. Descriptive statistics, K-W tests, and U-tests were used to analyze regional differences. Spearman correlation and linear regression analyses were employed to assess the impact of age. Furthermore, weighted averages and weighted variances of skeletal geometric parameters were calculated to reflect the characteristics of individuals from various regions across the country, which will be applied in the development of Chinese human models. Results: The results indicate significant regional differences in the skeletal geometric parameters of Chinese individuals, exhibiting regional patterns between the north–south and east–west areas. While skeletal geometric parameters showed significant differences with age, no clear statistical pattern was observed. Conclusion: This study systematically extracts and analyzes the skeletal geometric parameters of the Chinese population from regional and age perspectives for the first time. These data will be applied in the development of Chinese human models, providing crucial support for improving passenger safety in traffic accidents, enhancing vehicle safety design, and establishing anthropometric standards suitable for the Chinese context.

Prevention of traffic accidents through the moral knowledge approach in upper secondary students

Road traffic accidents that are very high among students can be overcome by instilling Moral Knowledge or Moral Knowledge, which is an important thing to teach. If students already know morals, they will have moral awareness which will be embedded consistently between knowledge and actions (moral action). This type of research is qualitative descriptive, in-depth interviews and questionnaires carry out the data collection method. The results showed that students' moral knowledge related to traffic ethics on the road had not been fully formed. The stages that can be done in understanding moral knowledge in students to reduce the number of traffic accidents among students are moral awareness so that students can distinguish between right and wrong actions or perceptions, prohibitions and recommendations, and good or bad behavior. Second, character education to foster habits (Habitation) towards noble moral values. Third, moral action is to practice noble moral values in daily behavior.

A clinical case of diaphyseal fracture and nonunion of the humerus

A 33-year-old female patient was admitted following a car accident, presenting with a diaphyseal fracture of the humerus (wedge-shaped, intact, classified as type B2 according to the AO classification). Osteosynthesis using a plate was initially performed; however, an incorrect choice of plate thickness led to migration of the metal structure three days post-operation. The causes of this error, diagnostic approaches, and corrective surgical treatment are discussed. To prevent such complications, careful selection of the osteosynthesis method and implant type is essential, along with close attention to the donor site during bone autografting.

Cranioplasty Approaches for Cranial Defects: A Case Series

Abstract Cranial defects are commonly caused due to road traffic accidents, tumor, postneurosurgery, or congenital deformities. Protection of the cranial structures, maintaining cerebrospinal fluid dynamics, and esthetics are some of the prime considerations while restoration of such defects. The use of autograft or allograft materials such as bone from a self or another donor site from ribs, ilium, tibia, scapula, and fascia and procedures such as split-thickness cranioplasty were carried out in the past. However, in larger defects, alloplastic materials such as celluloids, methyl methacrylate, hydroxyapatite, polyethylene, silicone, and metals such as titanium, aluminum, and stainless steel, were used for restoration. Irrespective of the material of choice, it is desirable of the prosthetic material to demonstrate low thermal conductivity, optimal strength, low infection rate, longevity, close adaptation to the defect, and fixability with plates to adjacent bone. Before digital imaging, conventional impressions were made, and approximations were done to fabricate cranial plates. With the advent of digital technology and bone imaging techniques with alongside the development of printed and milled materials, accurate cranial prosthesis can be fabricated. We cannot disregard conventional techniques as these are still used in places where access to digital technology is limited and also for patients who cannot afford the cost incurred with digital technology. The case series presents one case, which was fabricated with a conventional method, and two cases with two different approaches using digital technology. The paper aims to present various advantages, limitations, and nuances needed while the fabrication of such a prosthesis with these three methods.