Crash prediction based on traffic platoon characteristics using floating car trajectory data and the machine learning approach

Wang, Junhua; Luo, Tianyang; Fu, Ting

doi:10.1016/j.aap.2019.105320

Cited by 49 publications

(15 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Junhua Wanga used Two modeling approaches are implemented, including a conditional logistic regression model and a support vector machine model, and contrasted with forecasting crashes. The technique is evaluated based on the data obtained from the Shanghai Middle Ring Expressway, one of the major rings in Shanghai city, China [15].…”

Section: Related Workmentioning

confidence: 99%

“…A data preparation method, involving crash data filtering, floating car data filtering, and data matching on the road network, is introduced for the safety analysis purpose. And it contains:  Dataset selection: The performance of real-time crash prediction relies greatly upon, in addition to the performance of the prediction model applied, a timeefficient and reliable data collection method [15].…”

Section: A Data Source and Gatheringmentioning

confidence: 99%

“…Real-time crash prediction helps identify and prevent crashes before they happen. Therefore, it has become a hot topic in the ITS industry, both crash and non-crash events are needed in crash prediction [15]. So, the proposed traffic management model applied in Maryland U.S. datasets to define the factors which contributed to the accident in this study four classifier algorithms applied to define the most powerful algorithm in Accident Occurrence prediction and the better classifier in this work-study is SVM which achieved accuracy 98.84% better than the other classifier used, and lowest classifier accuracy is K-Nearest Neighbor which achieved accuracy 98.26% as shown in Table VI and Fig.…”

Section: E Maryland Us Dataset (Accident Occurrence)mentioning

confidence: 99%

See 2 more Smart Citations

A Model for Traffic Management based on Text Mining Techniques

Naguib¹,

Abdel-Galil²,

AbdelGaber³

2020

IJACSA

View full text Add to dashboard Cite

Section: Related Workmentioning

confidence: 99%

Section: A Data Source and Gatheringmentioning

confidence: 99%

Section: E Maryland Us Dataset (Accident Occurrence)mentioning

confidence: 99%

See 1 more Smart Citation

A Model for Traffic Management based on Text Mining Techniques

Naguib¹,

Abdel-Galil²,

AbdelGaber³

2020

IJACSA

View full text Add to dashboard Cite

“…Expressway safety has remained as a major concern in traffic system management. With higher operating speed, crashes on expressway are more likely to lead to huge life and property loss compared with other types of road [1]. According to preliminary estimates from National Highway Traffic Safety Administration (NHTSA), 36120 people died in motor vehicle crashes on highway in USA in 2019 [2].…”

Section: Introductionmentioning

confidence: 99%

Crash Prediction on Expressway Incorporating Traffic Flow Continuity Parameters Based on Machine Learning Approach

Tian

Peng

Liu

et al. 2021

Journal of Advanced Transportation

View full text Add to dashboard Cite

Real-time crash prediction helps identify and prevent the occurrence of traffic crash. For years, various real-time crash prediction models have been investigated to provide effective information for proactive traffic management. When building real-time crash prediction model, a suitable variable space together with a specific time interval for traffic data aggregation and an appropriate modelling algorithm should be applied. Regarding the intercorrelation problem with variable space, comprehensive real-time crash prediction model considering available traffic data characteristics in applicable circumstances needs to be explored. Taking Xi’an G3001 Expressway as study area, real road traffic and accident data during the period from January 2014 to January 2019 on this expressway are applied for real-time crash prediction. To better capture traffic flow characteristics on expressway and improve the practicality of real-time crash prediction model, two new variables (segment difference coefficient and lane difference coefficient) describing the smoothness and continuity of traffic flow in spatial dimension are developed and incorporated in building the crash prediction model to solve the intercorrelation problem with variable space. Random forest (RF) is then adopted to specify the quantitative relationship between specific variable and crash risk. Real-time crash prediction model based on support vector machine (SVM) using new composed variable space is built. The results show that simplified variable space could contribute to the same classification power in currently used real-time crash prediction models compared with traditional variable space. Moreover, the prediction model based on SVM reaches an accuracy level of 0.9, which performs better than other currently used prediction models.

show abstract

“…Real‐time collected data from the Microwave Vehicle Detection System were used for safety conditions monitoring on an expressway with average segments length around 1 mile [20]. FCD was also used to develop crash prediction models: a dynamic Bayesian network was applied on an expressway divided into segments of 1–2 km [24], and data from a big taxi fleet were used in order to calibrate support vector machine models on an expressway, divided into segments of 500 m length [25]. Operating speed profiles, obtained over 32 runs of floating vehicles and computed with an aggregation of 100 m were compared to a safe speed model on a 2.4 km highway with known geometrical parameters [26].…”

Section: Introductionmentioning

confidence: 99%