The exhaust emissions and frequent traffic incidents caused by traffic congestion have affected the operation and development of urban transport systems.Monitoring and accurately forecasting urban traffic operation is...The exhaust emissions and frequent traffic incidents caused by traffic congestion have affected the operation and development of urban transport systems.Monitoring and accurately forecasting urban traffic operation is a critical task to formulate pertinent strategies to alleviate traffic congestion.Compared with traditional short-time traffic prediction,this study proposes a machine learning algorithm-based traffic forecasting model for daily-level peak hour traffic operation status prediction by using abundant historical data of urban traffic performance index(TPI).The study also constructed a multi-dimensional influencing factor set to further investigate the relationship between different factors on the quality of road network operation,including day of week,time period,public holiday,car usage restriction policy,special events,etc.Based on long-term historical TPI data,this research proposed a daily dimensional road network TPI prediction model by using an extreme gradient boosting algorithm(XGBoost).The model validation results show that the model prediction accuracy can reach higher than 90%.Compared with other prediction models,including Bayesian Ridge,Linear Regression,ElatsicNet,SVR,the XGBoost model has a better performance,and proves its superiority in large high-dimensional data sets.The daily dimensional prediction model proposed in this paper has an important application value for predicting traffic status and improving the operation quality of urban road networks.展开更多
Based on analyzing the remote sensing images of Wuhan City in 1998,2002 and 2008,information about the land use changes along rail traffic routes before and after the construction of these routes are extracted,and 9 l...Based on analyzing the remote sensing images of Wuhan City in 1998,2002 and 2008,information about the land use changes along rail traffic routes before and after the construction of these routes are extracted,and 9 landscape indexes are applied to quantitatively study the change trend of its land use pattern.The results show that the construction of rail traffic routes has brought enormous changes to the land use pattern along the routes,say,built-up area has become the dominant type which has been rapidly concentrating into patches;the amounts of small patches,such as grass land,have gradually declined and shown an imbalanced distribution.展开更多
As an important parameter to describe the sudden nature of network traffic, Hurst index typically conducts behaviors of both self-similarity and long-range dependence. With the evolution of network traffic over time, ...As an important parameter to describe the sudden nature of network traffic, Hurst index typically conducts behaviors of both self-similarity and long-range dependence. With the evolution of network traffic over time, more and more data are generated. Hurst index estimation value changes with it, which is strictly consistent with the asymptotic property of long-range dependence. This paper presents an approach towards dynamic asymptotic estimation for Hurst index. Based on the calculations in terms of the incremental part of time series, the algorithm enjoys a considerable reduction in computational complexity. Moreover, the local sudden nature of network traffic can be readily captured by a series of real-time Hurst index estimation values dynamically. The effectiveness and tractability of the proposed approach are demonstrated through the traffic data from OPNET simulations as well as real network, respectively.展开更多
The driver’s visibility is degraded when weather conditions deteriorate, which affects the traffic flow and induces traffic congestion or accidents. In particular, traffic accidents can be?led to chain reaction colli...The driver’s visibility is degraded when weather conditions deteriorate, which affects the traffic flow and induces traffic congestion or accidents. In particular, traffic accidents can be?led to chain reaction collisions, with high rate of fatality, when fog occurs in contrast to other weather factors that may restrict visibility. For the development of a traffic risk index, a deviation of the vehicle’s speed was set for the traffic risk index by referring to previous study results. In addition, factors that affected the deviation in a vehicle’s speed were selected as independent variables based on the traffic flow analysis during occurrences of fog. The visible distance, traffic volume, and speed were selected as the independent variables to estimate the optimal parameters in the regression model. The traffic risk index model during occurrences of fog proposed in this study is an exponential model, with the visible distance and the traffic volume defined as independent variables. According to the study model, traffic risk increased as the visible distance decreased and the traffic volume was lower. Thus, the visible distance that can affect traffic flow during occurrences of fog can be determined in the future based on the results of this study. The study results will be expected to contribute to not only traffic safety improvements, but also the facilitation of traffic flow as drivers and traffic operation managers intuitively recognize the level of risk.展开更多
The growing use of vehicles with the development of China brings greater pressure on the existing road traffic network. Based on the domestic and international research experiences and the domestic congestion situatio...The growing use of vehicles with the development of China brings greater pressure on the existing road traffic network. Based on the domestic and international research experiences and the domestic congestion situations, this paper selected six indicators that affect the traffic conditions. As each single indicator cannot reflect the detailed traffic quality separately, the dynamic comprehensive evaluation principle is adopted.Then we used the principle of "Variation Driven" to determine the weight vector of each sub-indicator, and established a multi-indicator comprehensive evaluation system through the dynamic weight of each sub-indicator. Finally, the rationality and feasibility of the system is demonstrated by case analysis. This provides a strong theoretical foundation and basis to mitigate traffic congestion.展开更多
Predicting tourism traffic demand accurately plays an important role in making effective policies for tourist administration. It helps to distribute the resources reasonably and avoid the tourism congestions. This pap...Predicting tourism traffic demand accurately plays an important role in making effective policies for tourist administration. It helps to distribute the resources reasonably and avoid the tourism congestions. This paper considered the noise interference and proposed a hybrid model, combining ensemble empirical mode decomposition (EEMD), deep belief network (DBN) and Google trends, for tourism traffic demand prediction. This model firstly applied dislocation weighted synthesis method to combine Google trends into a search composite index, and then it denoised the series with EEMD. EEMD extracted the high frequency noise from the original series. The low frequency series of search composite index would be used to forecast the low frequency tourism traffic series. Taking the inbound tourism in Shanghai as an example, this paper trained the model and predicted the next 12 months tourism arrivals. The conclusion demonstrated that the forecast error of EEMD-DBN model is lower remarkably than the baselines of ARIMA, GM(1,1), FTS, SVM, CES and DBN model. This revealed that nosing processing is necessary and EEMD-DBN forecast model can improve the prediction accuracy.展开更多
基金funded by the National Natural Science Foundation of China(NFSC)(No.52072011)。
文摘The exhaust emissions and frequent traffic incidents caused by traffic congestion have affected the operation and development of urban transport systems.Monitoring and accurately forecasting urban traffic operation is a critical task to formulate pertinent strategies to alleviate traffic congestion.Compared with traditional short-time traffic prediction,this study proposes a machine learning algorithm-based traffic forecasting model for daily-level peak hour traffic operation status prediction by using abundant historical data of urban traffic performance index(TPI).The study also constructed a multi-dimensional influencing factor set to further investigate the relationship between different factors on the quality of road network operation,including day of week,time period,public holiday,car usage restriction policy,special events,etc.Based on long-term historical TPI data,this research proposed a daily dimensional road network TPI prediction model by using an extreme gradient boosting algorithm(XGBoost).The model validation results show that the model prediction accuracy can reach higher than 90%.Compared with other prediction models,including Bayesian Ridge,Linear Regression,ElatsicNet,SVR,the XGBoost model has a better performance,and proves its superiority in large high-dimensional data sets.The daily dimensional prediction model proposed in this paper has an important application value for predicting traffic status and improving the operation quality of urban road networks.
文摘Based on analyzing the remote sensing images of Wuhan City in 1998,2002 and 2008,information about the land use changes along rail traffic routes before and after the construction of these routes are extracted,and 9 landscape indexes are applied to quantitatively study the change trend of its land use pattern.The results show that the construction of rail traffic routes has brought enormous changes to the land use pattern along the routes,say,built-up area has become the dominant type which has been rapidly concentrating into patches;the amounts of small patches,such as grass land,have gradually declined and shown an imbalanced distribution.
文摘As an important parameter to describe the sudden nature of network traffic, Hurst index typically conducts behaviors of both self-similarity and long-range dependence. With the evolution of network traffic over time, more and more data are generated. Hurst index estimation value changes with it, which is strictly consistent with the asymptotic property of long-range dependence. This paper presents an approach towards dynamic asymptotic estimation for Hurst index. Based on the calculations in terms of the incremental part of time series, the algorithm enjoys a considerable reduction in computational complexity. Moreover, the local sudden nature of network traffic can be readily captured by a series of real-time Hurst index estimation values dynamically. The effectiveness and tractability of the proposed approach are demonstrated through the traffic data from OPNET simulations as well as real network, respectively.
文摘The driver’s visibility is degraded when weather conditions deteriorate, which affects the traffic flow and induces traffic congestion or accidents. In particular, traffic accidents can be?led to chain reaction collisions, with high rate of fatality, when fog occurs in contrast to other weather factors that may restrict visibility. For the development of a traffic risk index, a deviation of the vehicle’s speed was set for the traffic risk index by referring to previous study results. In addition, factors that affected the deviation in a vehicle’s speed were selected as independent variables based on the traffic flow analysis during occurrences of fog. The visible distance, traffic volume, and speed were selected as the independent variables to estimate the optimal parameters in the regression model. The traffic risk index model during occurrences of fog proposed in this study is an exponential model, with the visible distance and the traffic volume defined as independent variables. According to the study model, traffic risk increased as the visible distance decreased and the traffic volume was lower. Thus, the visible distance that can affect traffic flow during occurrences of fog can be determined in the future based on the results of this study. The study results will be expected to contribute to not only traffic safety improvements, but also the facilitation of traffic flow as drivers and traffic operation managers intuitively recognize the level of risk.
基金Supported by National Natural Science Foundation of China(No.61572523)Philosophy Social Science Project of Tai an City(No.18skx028)+2 种基金Online Course Construction Project of Shandong University of Science and Technology(No.ZXK201829)Excellent Teaching Team of Shan Dong University of Science and Technology(No.JXTD20180509)Technology program of Tai an City(No.2018C0270)
文摘The growing use of vehicles with the development of China brings greater pressure on the existing road traffic network. Based on the domestic and international research experiences and the domestic congestion situations, this paper selected six indicators that affect the traffic conditions. As each single indicator cannot reflect the detailed traffic quality separately, the dynamic comprehensive evaluation principle is adopted.Then we used the principle of "Variation Driven" to determine the weight vector of each sub-indicator, and established a multi-indicator comprehensive evaluation system through the dynamic weight of each sub-indicator. Finally, the rationality and feasibility of the system is demonstrated by case analysis. This provides a strong theoretical foundation and basis to mitigate traffic congestion.
文摘Predicting tourism traffic demand accurately plays an important role in making effective policies for tourist administration. It helps to distribute the resources reasonably and avoid the tourism congestions. This paper considered the noise interference and proposed a hybrid model, combining ensemble empirical mode decomposition (EEMD), deep belief network (DBN) and Google trends, for tourism traffic demand prediction. This model firstly applied dislocation weighted synthesis method to combine Google trends into a search composite index, and then it denoised the series with EEMD. EEMD extracted the high frequency noise from the original series. The low frequency series of search composite index would be used to forecast the low frequency tourism traffic series. Taking the inbound tourism in Shanghai as an example, this paper trained the model and predicted the next 12 months tourism arrivals. The conclusion demonstrated that the forecast error of EEMD-DBN model is lower remarkably than the baselines of ARIMA, GM(1,1), FTS, SVM, CES and DBN model. This revealed that nosing processing is necessary and EEMD-DBN forecast model can improve the prediction accuracy.
