Estimating helmet wearing rates via a scalable, low-cost algorithm: a novel integration of deep learning and google street view.

INTRODUCTION: Wearing a helmet reduces the risk of head injuries substantially in the event of a motorcycle crash. Countries around the world are committed to promoting helmet use, but the progress has been slow and uneven. There is an urgent need for large-scale data collection for situation assessment and intervention evaluation. METHODS: This study proposes a scalable, low-cost algorithm to estimate helmet-wearing rates. Applying the state-of-the-art deep learning technique for object detection to images acquired from Google Street View, the algorithm has the potential to provide accurate estimates at the global level. RESULTS: Trained on a sample of 3995 images, the algorithm achieved high accuracy. The out-of-sample prediction results for all three object classes (helmets, drivers, and passengers) reveal a precision of 0.927, a recall value of 0.922, and a mean average precision at 50 (mAP50) of 0.956. DISCUSSION: The remarkable model performance suggests the algorithm's capacity to generate accurate estimates of helmet-wearing rates from an image source with global coverage. The significant enhancement in the availability of helmet usage data resulting from this approach could bolster progress tracking and facilitate evidence-based policymaking for helmet wearing globally.

Factors associated with work-related musculoskeletal disorders in commercial motorcyclists.

This study aimed to explore the prevalence of work-related musculoskeletal disorders (WMSDs) and to investigate factors associated with WMSDs in commercial motorcyclists in Indonesia. This cross-sectional study involved commercial motorcyclists operating in Indonesia. Data were collected using an anonymous questionnaire, including the Indonesian Version of the Nordic Musculoskeletal Questionnaire, occupational driving posture questionnaire, and occupational factor-related questions. The questionnaire was distributed at four rest stops located in Central Jakarta, Indonesia. The result showed that 40% of participants (129/322) were having WMSDs. Older age, overweight body mass index (BMI), obese body mass index, nonregular physical activity, driving duration (> 8 h/day), seniority (≥5 years), and poor driving posture were significant risk factors for WMSDs in commercial motorcyclists. Based on the risk factors identified in this study, the development of preventive strategies among commercial motorcyclists is warranted.

Investigating and modeling motorcycle crash rates at urban unsignalized intersections in India.

OBJECTIVE: The present study focuses on understanding the behavior of motorized 2-wheeler (MTW) riders at urban unsignalized intersections in India. In the Indian context, over 60% of road crash fatalities are attributed to vulnerable road users, with MTWs serving as the predominant contributors, accounting for 44% of total fatalities. Notably, unsignalized intersections have emerged as critical sites for accidents involving vulnerable road users. METHODS: Postencroachment time is used to assess traffic conflicts of MTW users. Furthermore, the study employs the exceedance property of extreme value theory to calculate crash probabilities. Tobit and grouped random parameters Tobit regression models are developed to model crash probabilities, incorporating variables such as traffic volume, traffic composition, gap acceptance time, intersection characteristics, and intersection conflict area at 4 urban unsignalized intersections in Surat, India. RESULTS: MTW riders have the lowest gap acceptance time among vehicles in the traffic stream. Cars and other heavy vehicles readily accept gaps when MTWs are in the conflicting stream at unsignalized intersections, which increases traffic conflicts. MTWs have the highest crash rates in the traffic stream. Among the developed models, the grouped random parameters Tobit regression captures the spatial unobserved heterogeneity of the study sites and outperforms the simple Tobit regression model. The results also indicate that MTW riders are exposed to a higher risk of crashes while turning at unsignalized intersections. The presence of a central traffic island has varied implications; it raises crash rates at 3-legged intersections but lowers them at 4-legged intersections for 2-wheelers. CONCLUSION: The study concludes that MTW crash rates are influenced by traffic and intersectional factors. Increased gap acceptance time correlates with lower crash rates. Countermeasure selections require detailed investigations, because it was observed that the presence of central traffic islands has varied effects on crash rates at 3-legged and 4-legged unsignalized intersections.

Effects of risky bus driving behaviors on motorcyclists' and car drivers' traffic safety perceptions in mixed traffic flow.

OBJECTIVE: This study investigates traffic safety perceptions of motorcyclists and car drivers toward risky bus driving behaviors (RBDBs) in mixed traffic flow (MTF). METHODS: The study identified 10 RBDBs and employed images in a unique questionnaire survey. Further, permutation tests were employed to compare perceptions of motorcyclists in scenarios involving bus-motorcycle-car flow and bus-motorcycle flow and to compare their perceptions to those of car drivers'. Moreover, heteroskedastic generalized ordered logit regression models were utilized to predict traffic safety perceptions of motorcyclists and car drivers toward RBDBs. RESULTS: High-speed bus driving is perceived as the most dangerous situation, while continuous flashing of lights at vehicles in front is perceived as the least dangerous. The permutation test revealed that motorcyclists tend to perceive RBDBs as less dangerous in bus-motorcycle flow than in mixed flow with cars, while car drivers consider them safer than motorcyclists. The regression model revealed that among the RBDBs, bus moving at high speeds, abruptly overtaking, abruptly changing lanes, and suddenly pulling over at bus stops are perceived as the most dangerous by motorcyclists and car drivers. The study also discusses the relationships between the socio-demographic characteristics of motorcyclists/car drivers and their safety perception toward RBDBs. CONCLUSIONS: These findings could inform the development of interventions to reduce RBDBs and improve traffic safety for motorcyclists and car drivers.

A contribuição da Ergonomia para a segurança no trabalho / Ergonomics contribution to occupational safety

Resumo Introdução: processos de alto risco com elevadas taxas de acidentes desafiam a segurança. Por outro lado, sistemas ultrasseguros conquistaram ótimos indicadores. Em ambos, a prevenção parece ter chegado a um limite - em um deles, porque parece impotente para gerar prevenção; no outro, porque foi tão bem-sucedida que parece impossível avançar. Objetivo: evidenciar a contribuição da Ergonomia em prol da segurança, nas situações descritas, suas possibilidades ainda por explorar, entre elas a Ergonomia de concepção na integração homem-máquina (sistemas informatizados). Método: análise comparativa dos achados oriundos de estudos ergonômicos em sistemas de produção com altas taxas de acidentes e sistemas ultrasseguros. Discussão: a análise da atividade dos motofretistas mostrou que existem alternativas de ação ainda não exploradas entre as relações de trabalho desfavoráveis e a percepção de inevitabilidade dos acidentes. Nos sistemas ultrasseguros, o aparente limite pode ser superado com os avanços recentes na análise da ação e cognição situadas e na construção de espaços de debate que permitam o retorno da experiência de campo. Em sistemas informatizados, as práticas de projeto colaborativo, que se valem da experiência dos trabalhadores para alimentar as dinâmicas de aprendizagem e a confiabilidade técnica, são possibilidades ainda pouco praticadas na Engenharia de Segurança.

Abstract Introduction: while high-risk processes with high accident rates challenge safety, High Reliability Organization (HRO) achieve excellent indicators. In both cases, prevention seems to have reached a limit. In the former, because it seems powerless to generate prevention; in the latter, because it has been so successful that it seems impossible to reach greater levels. Objective: to highlight the contribution of Ergonomics to safety in these situations, pointing out unexplored possibilities such as design Ergonomics in man-machine integration (computerized systems). Method: comparative analysis of findings from ergonomic studies on production systems with high accident rates and HRO. Discussion: analysis of the motorcycle freight drivers' activity revealed alternatives yet to be explored between unfavorable work relations and the perceived inevitability of accidents. The apparent limit of HRO can be overcome with recent advances in the analysis of situated action and cognition and by building debate spaces based on field experience. Collaborative design practices, which draw on worker experience to feed learning dynamics and technical reliability, remains a poorly explored possibility in Safety Engineering when it comes to computerized systems.

Health Promotion Interventions on Helmet Use: A Systematic Review and Meta-Analysis of Pre-Test and Post-Test Studies.

Background: We aimed to review the effectiveness of health promotion interventions in the use of helmet and to identify the types of effective health promotion strategies among the examined studies. Methods: A systematic search was performed on the PubMed, Scopus, Cochrane, and Embase databases up to 1 Aug 2022 to find the studies evaluated the effectiveness of health promotion interventions for helmet use among target population. In this systematic review and meta-analysis, interventions with pre- post-test design were included. The dependent variable of the study is the percentage of participants who responded positively toward helmet use in the baseline and after the interventions. Random-effects models were used to pool study results. Results: Overall, 1,675 articles were found in the initial search and entered into the Endnote software. Of these, 917 duplicate articles were removed, leaving 758 articles were screened based on title and abstract. Finally, 12 eligible articles were included in the review and five with pre and post-test design were included in the meta-analysis. The overall random-effects pooled estimation of persons wearing helmets before and after interventions was 70% (95%CI 21 -119; P<0.001), without a heterogeneity (I2 =0%; P=0.94), which means that the average percentage of changing to helmet use is 70%. Community-based education program was the most commonly applied for interventional studies. The next most commonly used approaches were campaign designing. Conclusion: Wearing helmet approximately increased 70% among participant. Health promotion strategies may target helmet-wearing behavior to reduce head injuries in motorcyclist road traffic accidents.

How supplementary sign features can improve traffic safety among motorcyclists? The effect of capitalization and information length on road sign comprehension.

OBJECTIVES: Supplementary signs are essential to improve riders' understanding of road signs. In order to attract the rider's attention and ensure the information on the supplementary sign is effectively delivered, a study on the effective ways to display the information in the supplementary sign is needed. The current study examined the effects of capitalization and information length in supplementary signs on road sign comprehension among riders. METHOD: A randomized 2 (capitalization: all letters capitalized vs the first letter capitalized) × 2 (information length: long vs. short) factorial design experiment was conducted on 131 young motorcyclists in the Jakarta area. Road sign comprehension was measured using sign comprehension time and sign comprehension level. RESULT: A 2 × 2 factorial ANOVA analysis showed a significant effect of information length on sign comprehension time: less information in supplementary signs can increase sign comprehension time. Additionally, a significant interaction was found between capitalization and information length on sign comprehension level: sign comprehension levels would be improved if supplementary signs were presented with capitalization at the beginning of each word and had a long information length. CONCLUSION: This study suggests that there is a need to consider the capitalization and length of information in designing supplementary traffic signs. The effective design of supplementary signs could help riders to comprehend the road sign quickly and accurately, thus improving traffic safety.

Factors influencing drink driving intention among motorcyclists in Vietnam.

OBJECTIVE: Reducing drink driving amongst motorcyclists has been deemed as a potential area for improving road traffic safety in most developing countries. However, research efforts paid on determining the underlying factors of drink driving intention amongst this road user group has been still scant. To fill this gap, this study explored the factors influencing motorcyclists' intention to drink and drive in Vietnam. METHODS: A questionnaire survey was conducted with a sample of 451 Vietnamese motorcycle riders. The theory of planned behavior (TPB) was utilized as a frame of reference to address this issue. Apart from the TPB standard variables (i.e., attitudes, subjective norms, perceived behavioral control) and extended TPB variables which have been previously investigated in literature (i.e., descriptive norm, past behavior, and risk perception), the present research introduced four extended factors to TPB including social sanctions, physical loss, perception of drink driving enforcement, and perceived ability to influence traffic police to avoid punishment. RESULTS: The results showed significant effects of attitudes toward drink driving, perceived behavioral control, past behavior and social sanctions on motorcyclists' drink driving intention. In addition, the data showed that both new context-based variables (i.e., "perception of drink driving enforcement" and "perceived ability to influence traffic police to avoid punishment") were significantly related to drink driving intention. CONCLUSIONS: Various underlying factors of motorcyclists' intention to drink and drive were identified under the TPB framework. The findings provide useful information for road safety interventions in Vietnam. In particular, making enforcement activities more visible to motorcyclists and putting more effort into reducing corruption and other illegal activities in the traffic police sector could be effective measures for obtaining desirable drink driving behaviors.

Helmet Use and Jaw and Tooth Injuries in Motorcyclists Admitted to a Referral Hospital.

Background and Aim: The use of helmets has been reported to reduce the incidence and severity of head injuries in motorcyclists. However, there remains a significant gap in knowledge regarding the effectiveness of helmets, especially in preventing jaw and tooth injuries. Patients and Methods: In this retrospective analytical study record, all traffic accidents that occurred continuously from 2017 to 2019 in which the motorcyclists were on at least one side of the collision based on inclusion criteria. Data from injury variables in medical records were merged with data related to helmet use in the trauma registration system in Excel software. Then, the final analysis was performed with STATA software version 14 at a significance level of < 0.05. Results: In total, 1807 people participated in the study, and 160 (9.37) people used helmets. The incidence rate of jaw and tooth injuries was 86 (5.04%). Logistic regression implied that the odds ratio for helmet use was 0.7, which considering the p value of 0.419, shows no significant relationship between wearing helmets and jaw and tooth injuries. Conclusion: Helmets alone cannot prevent jaw and tooth injuries, and designers should design helmets that protect the head and the jaw and tooth. In prevention programs and campaigns for motorcyclists, every age, gender, job, grade group and marital status are target groups.

Motorcycle rider error and engagement in distracting activities: A study using the Attention-Related Driving Errors Scale (ARDES-M).

Research on motorcycle rider distraction and inattention is limited, especially when compared to that on car drivers. This study examines motorcycle rider error and its relationship with engagement in distracting activities. Additionally, it provides an adaptation of the Attention-Related Driving Errors Scale for use with motorcycle riders (ARDES-M). A sample of 418 motorcyclists responded to a web questionnaire consisting of the ARDES-M, a self-report measure of Involvement in Distracting Activities (IDA), a measure of everyday inattention (ARCES, Attention Related Cognitive Errors Scale) and socio-demographic and riding-related questions. Riding errors were associated with a higher level of engagement in distracting activities and a greater propensity for inattention in daily life. ARDES-M scores were associated with various types of self-reported traffic crashes and near-crashes, while self-reported distractions (IDA) were only linked with near-crashes. The most widely self-reported distracting activities were using map navigation, listening to the radio or to music and adjusting vehicle devices. The various uses of cell phones were relatively minor. Young riders reported higher levels of engagement in distracting activities and committing more riding errors. The ARDES-M showed good psychometric properties for the sample in Spain.

Piloting a hospital-based road traffic injury surveillance system in Nairobi County, Kenya, 2018-2019.

BACKGROUND: Kenya's estimated road traffic injury (RTI) death rate is 27.8/100,000 population, which is 1.5 times the global rate. Some RTI data are collected in Kenya; however, a systematic and integrated surveillance system does not exist. Therefore, we adopted and modified the World Health Organization's injury surveillance guidelines to pilot a hospital-based RTI surveillance system in Nairobi County, Kenya. METHODS: We prospectively documented all RTI cases presenting at two public trauma hospitals in Nairobi County from October 2018-April 2019. RTI cases were defined as injuries involving ≥1 moving vehicles on public roads. Demographics, injury circumstances, and outcome information were collected using standardized case report forms. The Kampala Trauma Score (KTS) was used to assess injury severity. RTI cases were characterized with descriptive statistics. RESULTS: Of the 1,840 RTI cases reported during the seven-month period, 73.2% were male. The median age was 29.8 years (range 1-89 years). Forty percent (n = 740) were taken to the hospital by bystanders. Median time for hospital arrival was 77 min. Pedestrians constituted 54.1% (n = 995) of cases. Of 400 motorcyclists, 48.0% lacked helmets. Similarly, 65.7% of bicyclists (23/35) lacked helmets. Among 386 motor vehicle occupants, 59.6% were not using seat belts (19.9% unknown). Seven percent of cases (n = 129) reported alcohol use (49.0% unknown), and 8.8% (n = 161) reported mobile phone use (59.7% unknown). Eleven percent of cases (n = 199) were severely injured (KTS <11), and 220 died. CONCLUSION: We demonstrated feasibility of a hospital-based RTI surveillance system in Nairobi County. Integrating information from crash scenes and hospitals can guide prevention.

Exploring influences on the intention of motorcyclists to drink and ride: An investigation in a fourth-tier city of China.

OBJECTIVE: The analysis of motorcyclists' intention to drink and ride can help reduce the possibility of accidents caused by the relevant behavior of motorcyclists. The main objectives of this study are to identify important factors in motorcyclists' intention to drink and ride and to make some recommendations that could effectively reduce their riding intention after drinking. METHODS: To explore the effects of demographic and psychological variables on motorcyclists' behavioral intention to drink and ride, a questionnaire based on the extended theory of planned behavior was designed. Two hundred and five fully completed questionnaires were collected through a survey in Shaoguan, China. A hierarchical regression model was used to analyze observed data. RESULTS: The final hierarchical regression model explained 37.5% of the variance in intention to drink and ride. While initial tests showed that gender, marital status and age influenced some TPB variables, gender was the only demographic variable found to be significant on the riding intention after drinking alcohol in the hierarchical regression analysis. Among the psychological factors quantified by the extended theory of planned behavior, all factors had significant effects on intention except for risk perception, and subjective norms were the most influential factor. CONCLUSIONS: The extended theory of planned behavior can be well used to examine the factors that influence motorcyclists' intention to drink and ride. A more nuanced understanding of these factors can be found in the results.

Characteristics of crash-involved drink and drug car drivers and motorcyclists.

OBJECTIVE: Drug driving is an issue of growing concern among Australian jurisdictions, including South Australia. In order to have an appropriate response to drug driving in regard to policy and enforcement, it is important to have sound knowledge about the patterns of drug use among motorists and the associated risks of this behavior. METHOD: To this end, this study examined the characteristics of 1,277 hospitalized road users in South Australia in the years 2014 to 2017, with reference to whether or not they tested positive for alcohol or other drugs (the three drugs tested for according to the South Australian Road Traffic Act (1961): THC, methamphetamine, MDMA). This examination used a database combining hospital data, police-reported crash data, licensing information, and the result of alcohol and drug tests conducted by Forensic Science SA. RESULTS: It was found that more motorists were positive for one or more of the three illicit drugs than for alcohol, reversing long established trends. Comparisons were made between alcohol and drug free motorists, alcohol positive motorists, drug positive motorists, and motorists positive for both drugs and alcohol, with drivers of cars and motorcyclists analyzed separately where possible. Findings include: that those combining drugs and alcohol only comprise a small proportion of hospitalized motorists; that drug drivers tend to be younger than other hospitalized motorists; that drivers are more likely to test positive to alcohol or methamphetamine, while motorcyclists are more likely to test positive to THC; motorists testing positive to drugs and/or alcohol tend to exhibit a range of other risky behaviors; and motorists testing positive to drugs and/or alcohol tend to sustain more severe injuries in the event of a crash. CONCLUSIONS: Preventing drink and drug driving is important not only for reducing crash numbers but also injury severity in the event of a crash. Substance use differs by road user type and age, which has potential implications for enforcement practices.

The Prevalence of Crash and Associated Factors Among Commercial Motorcyclist in Owo, Western Nigeria.

Objective: To determine the prevalence of crash and associated factors among commercial motorcyclists in Owo, Ondo State, Nigeria. Methods: This study is a descriptive cross-sectional study. Data was collected by using pre-tested structured questionnaires administered to commercial motorcyclists. Collected information was socio-demographic characteristics of the respondents, riding experience, formal training, possession of valid drivers' licence, motorcycle ownership status, mobile phone usage, history of crash in the previous one year, riding hours per day, helmet use, carrying more than one passenger, riding against traffic and daily income. Results: The study were enrolled 502 individuals with a mean age of 31.5±8.7. The ratio of men to women was 250:1. All respondents who admitted to engage in the study had at least one risky behaviour in the past (95.4% admitted to transporting one passenger more than the legal) and 56.6% admit to a prior history of traffic offences. The crashes' predictive factors include respondent age, cell phone use while riding, prior traffic offences, carrying more than one pillion rider, use of stimulants such as kolanut and bitter kola, alcohol drink riding, and admission of fault in the prior of crashes. Conclusion: Commercial motorcyclists in Owo, Ondo State Nigeria engaged in risky behaviours that raised their likelihood of being involved in crashes. The objectives of public enlightenment and driver education at these behaviours could help to reduce the occurrence of crashes among them.

Commercial motorcyclists and road safety measures compliance. A case study of Dodoma city, central Tanzania.

Objective: Road traffic accidents have been reported to contribute a greater proportion of deaths. Motorcyclists are among the high-risk group within road users to succumb to road traffic accidents. Road traffic accidents reflect the co-occurrence of multiple causes that involve road infrastructure, vehicle, and people. Understanding the level of compliance with road safety measures and their associated factors among commercial motorcyclists is important approach in the steps towards road traffic accident prevention. Study design: A cross-sectional study of commercial motorcyclists from two districts in Dodoma region was conducted in 2020. Methods: Multistage sampling method was used to recruit motorcyclists from registered parking stations. At first stage, purposive sampling was used to select the two districts, while in the second stage simple random sampling by lottery method was employed in the selection of wards and parking stations. Descriptive and Chi-square test analyses determined the compliance level. Bivariate and multivariate logistic regression analyses were performed to determine the associated factors. Results: A total of 378 male commercial motorcyclists participated in the study. Majority (87.8%) were within the age range of 18-29 years. A significant proportion of participants (61.9%) had adequate knowledge and 59.5% showed positive attitude towards road safety measures. Only 39.7% reported to have good level of compliance with road safety measures. Married motorcyclists and those with good road safety practice regarding road safety measures were more likely to comply with road safety measures than their counterpart. Conclusion: Good road safety practices and marital status were predictors of good compliance with road safety measures. Coordinated approaches, including continuing provision of road safety education and enforcement of road safety measures are needed to control the way motorcyclist behave on the road.

Temporal Instability of Factors Affecting Injury Severity in Helmet-Wearing and Non-Helmet-Wearing Motorcycle Crashes: A Random Parameter Approach with Heterogeneity in Means and Variances.

Not wearing a helmet, not properly strapping the helmet on, or wearing a substandard helmet increases the risk of fatalities and injuries in motorcycle crashes. This research examines the differences in motorcycle crash injury severity considering crashes involving the compliance with and defiance of helmet use by motorcycle riders and highlights the temporal variation in their impact. Three-year (2017-2019) motorcycle crash data were collected from RESCUE 1122, a provincial emergency response service for Rawalpindi, Pakistan. The available crash data include crash-specific information, vehicle, driver, spatial and temporal characteristics, roadway features, and traffic volume, which influence the motorcyclist's injury severity. A random parameters logit model with heterogeneity in means and variances was evaluated to predict critical contributory factors in helmet-wearing and non-helmet-wearing motorcyclist crashes. Model estimates suggest significant variations in the impact of explanatory variables on motorcyclists' injury severity in the case of compliance with and defiance of helmet use. For helmet-wearing motorcyclists, key factors significantly associated with increasingly severe injury and fatal injuries include young riders (below 20 years of age), female pillion riders, collisions with another motorcycle, large trucks, passenger car, drivers aged 50 years and above, and drivers being distracted while driving. In contrast, for non-helmet-wearing motorcyclists, the significant factors responsible for severe injuries and fatalities were distracted driving, the collision of two motorcycles, crashes at U-turns, weekday crashes, and drivers above 50 years of age. The impact of parameters that predict motorcyclist injury severity was found to vary dramatically over time, exhibiting statistically significant temporal instability. The results of this study can serve as potential motorcycle safety guidelines for all relevant stakeholders to improve the state of motorcycle safety in the country.

The role of inexperience in motorcycle crashes among novice and returning motorcycle riders.

OBJECTIVES: To examine the crash trends of younger novice and older novice/returning motorcycle riders. METHODS: We used a linked database of North Carolina crash and licensing data from 1991 through 2018 that included 103,142 younger novice and 98,540 older novice/returning motorcycle riders. We examined the percent of riders who crashed each month after obtaining a motorcycle license. RESULTS: Crash rates peak for both younger novice and older novice/returning motorcycle riders immediately after licensure. Crash rates decline rapidly, and the rate of decrease resembles a power function. The improvement rate (IR) for younger novice riders is 0.42; that is, the crash rate for younger novices declines by approximately 42% as experience doubles. CONCLUSION: The crash curve for novice motorcyclists is similar to that of novice car drivers and is consistent with a learning process. PRACTICAL APPLICATIONS: The crash trends of novice motorcycle riders indicate that current training, licensing, and educational efforts are not adequately preparing new riders. Additional efforts to develop more effective training, and research to inform a well-calibrated graduated licensing process for new riders are needed.

Investigating the Difference in Factors Contributing to the Likelihood of Motorcyclist Fatalities in Single Motorcycle and Multiple Vehicle Crashes.

In order to better understand the factors affecting the likelihood of motorcyclists' fatal injuries, motorcycle-involved crashes were investigated based on the involvement of the following vehicles: single motorcycle (SM), multiple motorcycles (MM) and motorcycle versus vehicle (MV) crashes. METHOD: Binary logit and mixed logit models that consider the heterogeneity of parameters were applied to identify the critical factors that increase the likelihood of motorcyclist fatality. RESULTS: Mixed logit models were found to have better fitting performances. Factors that increase the likelihood of motorcyclist fatality include lanes separated by traffic islands, male motorcyclists, and riding with BAC values of less than the legally limited value. Collisions with trees or utility poles lead to the highest likelihood of fatality in SM crashes. The effects of curved roads, same-direction swipe crashes, youth, and unlicensed motorcyclists are only significant in the likelihood of fatality in SM crashes. CONCLUSIONS: Motorcyclists tend to be killed if they collide with large engine-size motorcycles and vehicles, unlicensed motorcyclists, or drivers with speeding related or right-of-way violations with positive BAC values. Driving or riding should be prohibited for any amount of alcohol or for anyone with a positive BAC value. Law enforcement should focus on unlicensed, speeding motorcyclists and drivers, and those who violate the right of way or perform improper turns. Roadside objects and facilities should be checked for appropriate placement and be equipped with reflective devices or injury protection facilities.

Dataset of traffic accidents in motorcyclists in Bogotá, Colombia.

According to the World Health Organization, in 2016, Colombia obtained the tenth position worldwide, the third in the continent and the second in South America, according to the accident rate of 9.7 motorcycle fatalities per 100,000 populations. Between 2012 and 2021, the number of deceased and injured motorcyclists among all road users was 50%, with an annual average of 3140 fatal victims and 20,800 injured victims. Bogotá, Cali, and Medellín were the cities with the most accidents. In Bogota in 2017, the deaths of motorcyclists on the roads were around 32% of the road actors. This data article presents the dataset used to analyze and predict the severity of motorcyclist road accidents in Bogota in the article entitled "Extraction of decision rules using genetic algorithms and simulated annealing for prediction of severity of traffic accidents by motorcyclists" [1]. The data set was consolidated from the registration of 175,245 traffic accidents and the report of 337,828 road actors involved in crashes in Bogotá between January 2013 and February 2018. The data was compiled, processed, and enriched with additional information about infrastructure and weather conditions. The data corresponds to 35,693 motorcyclist traffic accidents, represented by 28 variables, and classified into five categories: road actors, motorcyclists and individuals involved, weather conditions and timing, road conditions and location and characteristics of the accident. The data on motorcyclist traffic accidents opens up a scenario to deepen and compare road safety in Latin America, where studies on vulnerable road users are limited. According to severity, the data on motorcycle traffic accidents recorded 28% with material damage, 69% with injured and 3% with fatal victims.

Modeling Motorcyclists' Aggressive Driving Behavior Using Computational and Statistical Analysis of Real-Time Driving Data to Improve Road Safety and Reduce Accidents.

Driving behavior is considered one of the most important factors in all road crashes, accounting for 40% of all fatal and serious accidents. Moreover, aggressive driving is the leading cause of traffic accidents that jeopardize human life and property. By evaluating data collected by various collection devices, it is possible to detect dangerous and aggressive driving, which is a huge step toward altering the situation. The utilization of driving data, which has arisen as a new tool for assessing the style of driving, has lately moved the concentration of aggressive recognition research. The goal of this study is to detect dangerous and aggressive driving profiles utilizing data gathered from motorcyclists and smartphone APPs that run on the Android operating system. A two-stage method is used: first, determine driver profile thresholds (rules), then differentiate between non-aggressive and aggressive driving and show the harmful conduct for producing the needed outcome. The data were collected from motorcycles using -Speedometer GPS-, an application based on the Android system, supplemented with spatiotemporal information. After the completion of data collection, preprocessing of the raw data was conducted to make them ready for use. The next steps were extracting the relevant features and developing the classification model, which consists of the transformation of patterns into features that are considered a compressed representation. Lastly, this study discovered a collection of key characteristics which might be used to categorize driving behavior as aggressive, normal, or dangerous. The results also revealed major safety issues related to driving behavior while riding a motorcycle, providing valuable insight into improving road safety and reducing accidents.