Fujian Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Fujian Wang has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Fengjie Fu
College of Civil Engineering and Architecture, Zhejiang University, Zhejiang, China
2 shared publications - Sheng Jin
Institute of Intelligent Transportation Systems, College of Civil Engineering and Architecture, Zhejiang University, Hangzhou 310058, China
2 shared publications Chengyu Gong
Institute of Transportation Engineering, College of Civil Engineering and Architecture, Zijingang Campus, Zhejiang University, P.O. Box 310058, Hangzhou, China
1 shared publication- Dianhai Wang
Zhejiang University
1 shared publication - Dongfang Ma
State Key Laboratory of Ocean Sensing & Ocean College, Zhejiang University, Zhoushan 316021, China
1 shared publication - Dongfang Ma
Ocean College, Zhejiang University, Zhejiang, People’s Republic of China
1 shared publication
Latest Publications
- Open Access
- 1 January 2023
- Published by European Alliance for Innovation n.o.
Statistical Distribution and Influencing Factor Analysis of the Impact Range of the Traffic Accident
In order to provide a reference for managers to control traffic flow after traffic accidents, multivariate ANOVA is used to study the significant influencing factors of the impact range of the traffic accident. The impact range of the traffic accident is the length of the road extent affected by the accident. Through the real traffic accident dataset of Humboldt County, California, the distribution characteristics of the impact range of the accident were analyzed, and then the factors influencing the impact range of the accident such as weather, peak time, day/night, season, weekend and intersection were analyzed by the intersubjective effect test, and then the factors with significant influence were analyzed by the post-hoc test to further determine the significances of differences among different categories within the factors. The results show that the distribution of the impact range of the accident has the phenomenon of right skewness, and the lognormal distribution fitting effect is the best. Intersection, weather, and peak hour have significant effects on the impact range of the accident. In addition, the effects of sunny day and rainy day on the impact range of the accident are significantly different, the effects of sunny day and haze on the impact range of the accident are significantly different, the effects of cloudy day and rainy day on the impact range of the accident are significantly different, and the effects of morning peak and off-peak on the impact range of the accident are significantly different.
- 1 January 2023
- Published by European Alliance for Innovation n.o.
Open AccessStatistical Distribution and Influencing Factor Analysis of the Impact Range of the Traffic Accident
In order to provide a reference for managers to control traffic flow after traffic accidents, multivariate ANOVA is used to study the significant influencing factors of the impact range of the traffic accident. The impact range of the traffic accident is the length of the road extent affected by the accident. Through the real traffic accident dataset of Humboldt County, California, the distribution characteristics of the impact range of the accident were analyzed, and then the factors influencing the impact range of the accident such as weather, peak time, day/night, season, weekend and intersection were analyzed by the intersubjective effect test, and then the factors with significant influence were analyzed by the post-hoc test to further determine the significances of differences among different categories within the factors. The results show that the distribution of the impact range of the accident has the phenomenon of right skewness, and the lognormal distribution fitting effect is the best. Intersection, weather, and peak hour have significant effects on the impact range of the accident. In addition, the effects of sunny day and rainy day on the impact range of the accident are significantly different, the effects of sunny day and haze on the impact range of the accident are significantly different, the effects of cloudy day and rainy day on the impact range of the accident are significantly different, and the effects of morning peak and off-peak on the impact range of the accident are significantly different.
- Open Access
- 1 February 2021
- Published by IOP Publishing in IOP Conference Series: Earth and Environmental Science
- Vol. 638 (1) , 012029
Freeway Short-Term Travel Time Prediction Based on LightGBM Algorithm
In order to realize the prediction of freeway travel time, a short-term travel time prediction model based on LightGBM (Light Gradient Boosting Machine) is proposed under the influence of weather factors, time period factors, and traffic factors. These factors are called as the features used for increase prediction accuracy. The travel time of a single vehicle is determined by license plate recognition data of two adjacent video monitors in Shaoxing section of Shanghai-Hangzhou-Ningbo Freeway, and a better travel time data set is constructed by data preprocessing. The feature data are determined by Pearson correlation. Based on the analysis of main optimization parameters in LightGBM, the short-term average travel time is predicted, the MAE (Mean Absolute Error) and MAPE (Mean Absolute Percentage Error) obtained by experiments are satisfying, indicating that LightGBM model has high accuracy and good fit. Finally, through comparison with KNN (K-Nearest Neighbor) model and GBDT (Gradient Boosting Decision Tree) model, the prediction accuracy and training speed both show that LightGBM has good advantages in predicting short-term freeway travel time.
- 1 February 2021
- Published by IOP Publishing in IOP Conference Series: Earth and Environmental Science
- Vol. 638 (1) , 012029
Open AccessFreeway Short-Term Travel Time Prediction Based on LightGBM Algorithm
In order to realize the prediction of freeway travel time, a short-term travel time prediction model based on LightGBM (Light Gradient Boosting Machine) is proposed under the influence of weather factors, time period factors, and traffic factors. These factors are called as the features used for increase prediction accuracy. The travel time of a single vehicle is determined by license plate recognition data of two adjacent video monitors in Shaoxing section of Shanghai-Hangzhou-Ningbo Freeway, and a better travel time data set is constructed by data preprocessing. The feature data are determined by Pearson correlation. Based on the analysis of main optimization parameters in LightGBM, the short-term average travel time is predicted, the MAE (Mean Absolute Error) and MAPE (Mean Absolute Percentage Error) obtained by experiments are satisfying, indicating that LightGBM model has high accuracy and good fit. Finally, through comparison with KNN (K-Nearest Neighbor) model and GBDT (Gradient Boosting Decision Tree) model, the prediction accuracy and training speed both show that LightGBM has good advantages in predicting short-term freeway travel time.
- Open Access
- 1 November 2016
- Published by Elsevier in KSCE Journal of Civil Engineering
- Vol. 20 (7) , 2955-2964
Recognition of critical links for gating using queue detector data
- 1 November 2016
- Published by Elsevier in KSCE Journal of Civil Engineering
- Vol. 20 (7) , 2955-2964
Open AccessRecognition of critical links for gating using queue detector data
- 4 June 2016
- Published by Springer Nature in International Journal of Civil Engineering
- Vol. 14 (5) , 281-293
Gating Control for a Single Bottleneck Link Based on Traffic Load Equilibrium
- 4 June 2016
- Published by Springer Nature in International Journal of Civil Engineering
- Vol. 14 (5) , 281-293
Gating Control for a Single Bottleneck Link Based on Traffic Load Equilibrium
- 13 July 2015
- Published by American Society of Civil Engineers (ASCE)
- p. 466-475
Operational Analysis of an Intelligent Traffic Management System on the Zijingang Campus of Zhejiang University
Anintelligent traffic management system (ITMS) was established on Zijingang Campus of Zhejiang University to control traffic flow. This paper aims to investigate the traffic flow and assess the ITMS system using the queueing approach. As the results show, the probability distribution of car residence time obeys gamma distribution. More than 4/5 of the cars are free to get into the campus, which proves the non-profit property of the toll gate. The probability distribution of arrival time and service time fits the negative exponential distribution and normal distribution, respectively. Then,the M/G/K model based on queueing theory was applied to investigate traffic capacity. The queueing length and waiting time in 2-lane and 3-lane conditions were calculated and service level was judged as C-level. The results can provide useful information for easing traffic congestion onthe campus.
- 13 July 2015
- Published by American Society of Civil Engineers (ASCE)
- p. 466-475
Operational Analysis of an Intelligent Traffic Management System on the Zijingang Campus of Zhejiang University
Anintelligent traffic management system (ITMS) was established on Zijingang Campus of Zhejiang University to control traffic flow. This paper aims to investigate the traffic flow and assess the ITMS system using the queueing approach. As the results show, the probability distribution of car residence time obeys gamma distribution. More than 4/5 of the cars are free to get into the campus, which proves the non-profit property of the toll gate. The probability distribution of arrival time and service time fits the negative exponential distribution and normal distribution, respectively. Then,the M/G/K model based on queueing theory was applied to investigate traffic capacity. The queueing length and waiting time in 2-lane and 3-lane conditions were calculated and service level was judged as C-level. The results can provide useful information for easing traffic congestion onthe campus.