Traffic crashes probability: A socioeconomic and educational approach

Obregón-Biosca, Saúl Antonio; Romero-Navarrete, José A.; Betanzo-Quezada, Eduardo

doi:10.1016/j.trf.2018.06.041

Cited by 10 publications

(2 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The increasing usage of vehicles in modern times has resulted in undesirable consequences, such as traffic congestion, accidents, injuries, fatalities, and financial losses. A survey conducted by the National Highway Traffic Safety Administration (NHTSA) and Virginia Tech Transportation Institute (VTTI) revealed that a minimum of 80% of accidents and 65% of near-accidents that take place every day on roads and highways are associated with distractions or poor decision-making while driver driving on roads and highways [4,5]. Additionally, secondary tasks such as visual, auditory, and haptic-related tasks, like using vehicle displays, listening to the radio, or using a smartphone, can still affect driving safety [6].…”

Section: Introductionmentioning

confidence: 99%

An Efficient Deep Learning Model Based on Driver Behaviour Detection Within CAN-BUS Signals

Gheni,

Abdul-Rahaim

2024

RIA

View full text Add to dashboard Cite

Intelligent Transportation Systems (ITS) have extensively utilized driver behavior monitoring systems to mitigate the risk of traffic accidents caused by factors such as aggression and distraction. However, existing methods often rely on computer vision techniques, raising concerns about privacy violations and vulnerability to spoofing attacks. These attacks can potentially result in inaccurate analysis of driver behavior and compromise the effectiveness of the system. To mitigate this issue, the proposed system relies on in-vehicle sensors and the driving signal obtained from the CAN-BUS, which provide direct and reliable measurements of driver behavior. By analyzing real-time data collected from multiple drivers, the hybrid deep learning model is trained to recognize patterns and characteristics indicative of safe and unsafe driving behavior. The driving signal obtained from the Controller Area Network bus (CAN-BUS), including acceleration, RPM, speed, accelerator pedal value, and throttle position signal, etc., is utilized to recognize safe and unsafe driver behavior. The utilization of a hybrid deep learning model, which combines Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM), is a deliberate choice in order to harness the respective advantages of both methods. This decision is driven by the aim to overcome the challenges encountered by previous approaches by capitalizing on the strengths of CNN and LSTM. The model is trained and tested on a real-time dataset collected from multiple drivers. Experimental results demonstrate the effectiveness of the proposed method in accurately detecting driver behavior, addressing the public health concern of traffic accidents.

show abstract

Section: Introductionmentioning

confidence: 99%

An Efficient Deep Learning Model Based on Driver Behaviour Detection Within CAN-BUS Signals

Gheni,

Abdul-Rahaim

2024

RIA

View full text Add to dashboard Cite

show abstract

“…However, there exist multiple measures that can be implemented to help lessen road fatalities and injuries counts (Elvik & Høye, 2020). A viable and sustainable initiative to improve road safety is enhancing the traffic culture (Obregón-Biosca et al, 2018).…”

Section: Implications and Recommendations For Future Researchmentioning

confidence: 99%

Analyzing Drivers’ Passing Decision on Two-Lane Two-Way Highways. (c2022)

Sabek¹

View full text Add to dashboard Cite

Passing maneuvers on rural two-lane highways have significant implications on safety, highway performance, and traffic operations. This research seeks to better understand drivers’ passing behavior by examining the interplay between drivers’ psychological traits and traffic variables influencing this decision. A driving simulator session followed by a self-report questionnaire were used to understand drivers’ decision to pass a lead vehicle or continue following it. A total of 160 licensed drivers were exposed to four randomized passing situations associated with different levels of risk. The lead vehicle was set to be a truck in all four scenarios, but its speed and the passing gap size were altered. The full-scale driving simulator captured observed driving behavior through performance metrics such as speed, lateral deviation, and travelled distance. The demographics and psychological factors including impulsiveness, mindfulness, and depression were collected through the self-report questionnaire. Results revealed that, irrespective of the passing situation and risk involved, the propensity to overtake lead vehicles is associated with lower attitude towards rule violations and speeding. With riskier overtaking situations, effects of impulsiveness and mindfulness become more significant. Concerning a driver’s current state and feeling, motorists who have been depressed lately are more likely to perform overtaking in specific situations. Such findings can be incorporated to enhance driving educational campaigns and curricula aiming to promote safe mobility and lessen the social and economic burdens of high-impact crashes.

show abstract