Overcoming challenges in crash prediction modeling using discretized duration approach: An investigation of sampling approaches

Thapa, Diwas; Paleti, Rajesh; Mishra, Sabyasachee

doi:10.1016/j.aap.2022.106639

Cited by 12 publications

(3 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Non-bicyclists tend to avoid biking due to perceived dangers or lack of safe route options. High-speed traffic and a high proportion of vehicular traffic raise cyclists' safety concerns [10] [34] [35] [36] [37]. Another study explored individual preferences for cycling environments and found the willingness of people to travel up to 20 minutes extra for a better facility [38].…”

Section: Literature Reviewmentioning

confidence: 99%

“…Creating environments that support safe and efficient cycling requires thoughtful transportation planning, particularly in high-traffic areas such as university campuses. Proactive measures in conflicting zones are crucial for cyclist safety, with prediction frameworks reducing the likelihood of incidents that cyclists may face in transitional road spaces [9] [10]. Bicycling constitutes an integral part of non-motorized transport, with its benefits including but not limited to low access costs, moderate travel speeds, environment-friendliness, and improved health and well-being making it more appealing to younger and low-income users i.e., college and university students [7] [11] [12] [13].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Exploring University Campus Community&#8217;s Perceptions and Barriers toward Biking: A Case Study of the University of Tennessee Knoxville

Usman,

Adeel

2024

JTTs

View full text Add to dashboard Cite

Bicycling constitutes an integral component of sustainable non-motorized means of travel. Despite the immense benefits of bicycling, the modal share of bicycling is quite low, specifically among young and low-income commuters e.g., college and university students. This study explores the perceptions of and barriers to bicycling of the campus community at the University of Tennessee, Knoxville with the aim to identify the factors that could enhance bike use among students at the university campus as well as highlight the barriers that keep young population away from biking. An online survey about bike use at the university campus was administered and responses to the survey were recorded. On the methodological front, a binary logit model was estimated with students' willingness to use bikes at campus as the dependent variable. The survey results revealed that about 47% of the students considered vehicular traffic as the reason for feeling unsafe while biking and emphasized having separate bike routes. Most of the respondents highlighted the need to change clothes after biking in summer or carry things as the reason for not selecting bikes as a mode of transport at the campus, whereas inadequate bike lanes, paths, or trails, insufficient lighting along bike routes, and the lack of adequate bicycle parking were highlighted as the major barriers deterring bike use within the campus. The study suggests development of a campus bike network with proper bike lanes, bike runnels, installation of safety cameras and better lighting at the campus, and bike-supporting infrastructure such as communal showers to be provided in campus buildings to encourage bike use among university students. The study findings can assist campus transportation planners in devising a sustainable campus transportation plan incorporating the influencing factors and deterrents of bike use in a university campus setting.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Exploring University Campus Community&#8217;s Perceptions and Barriers toward Biking: A Case Study of the University of Tennessee Knoxville

Usman,

Adeel

2024

JTTs

View full text Add to dashboard Cite

show abstract

“…Generally, traffic accident prediction can be described as a classification issue or a regression issue. For example, some scholars aim to predict whether accidents will occur in a specific spot (e.g., a road section) during a certain period (e.g., hours, days) [10][11][12]. Others use regression models to predict the number of accidents at a given time and place [13,14].…”

Section: Introductionmentioning

confidence: 99%

Improving Traffic Safety through Traffic Accident Risk Assessment

Zhou

Zhang³

2023

Sustainability

View full text Add to dashboard Cite

The continuous development of sensors and the Internet of Things has produced a large amount of traffic data with location information. The improvement of traffic safety benefits from the availability of traffic accident data. Managers can patrol and control relevant areas in advance with limited police resources, according to the short-term traffic accident predictions. As a result, the possibility of accidents can be reduced, and the level of traffic safety can be improved. The traditional approach to accident prediction relies too much on the subjective experience of traffic managers. Inspired by the deep learning technology in the field of computer vision, this study first divides the road network into regular grids and takes the number of traffic accidents in each grid as the pixel value of an image. Then, a traffic accident prediction approach based on a bi-directional ConvLSTM U-Net with densely connected convolutions (BCDU-Net) is proposed. This method mines the regular information hidden in the accident data and introduces densely connected convolutions to further extract the deep spatial-temporal features contained in the traffic accident sequence. Thus, the issues of gradient disappearance and model over-fitting caused by the traditional model in model training can be avoided. Finally, the simulation experiment is carried out on the historical traffic accident data of Yinzhou District, Ningbo City. Results show that BCDU-Net has better accuracy and precision than other models in three data sets: motor vehicle accidents, non-motor vehicle accidents, and single-vehicle accidents. Therefore, the BCDU-Net is more suitable for traffic accident prediction and has good application prospects for improving road safety.

show abstract

Traffic Graph Convolutional Network for Dynamic Urban Travel Speed Estimation

Ngo

Mishra

2022

Netw Spat Econ

View full text Add to dashboard Cite

Overcoming challenges in crash prediction modeling using discretized duration approach: An investigation of sampling approaches

Cited by 12 publications

References 27 publications

Exploring University Campus Community&#8217;s Perceptions and Barriers toward Biking: A Case Study of the University of Tennessee Knoxville

Exploring University Campus Community&#8217;s Perceptions and Barriers toward Biking: A Case Study of the University of Tennessee Knoxville

Improving Traffic Safety through Traffic Accident Risk Assessment

Traffic Graph Convolutional Network for Dynamic Urban Travel Speed Estimation

Contact Info

Product

Resources

About

Overcoming challenges in crash prediction modeling using discretized duration approach: An investigation of sampling approaches

Cited by 12 publications

References 27 publications

Exploring University Campus Community&amp;#8217;s Perceptions and Barriers toward Biking: A Case Study of the University of Tennessee Knoxville

Exploring University Campus Community&amp;#8217;s Perceptions and Barriers toward Biking: A Case Study of the University of Tennessee Knoxville

Improving Traffic Safety through Traffic Accident Risk Assessment

Traffic Graph Convolutional Network for Dynamic Urban Travel Speed Estimation

Contact Info

Product

Resources

About

Exploring University Campus Community’s Perceptions and Barriers toward Biking: A Case Study of the University of Tennessee Knoxville

Exploring University Campus Community’s Perceptions and Barriers toward Biking: A Case Study of the University of Tennessee Knoxville