Hongxia Ge
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Hongxia Ge has a total of 69 co-authors. Here are the top co-authors by number of shared publications:
- Rongjun Cheng
Faculty of Maritime and Transportation, Ningbo University, Ningbo 315211, China
21 shared publications Rong-Jun Cheng
Faculty of Maritime and Transportation, Ningbo University, Ningbo, 315211, China
7 shared publications- Siu Ming Lo
Department of Architecture and Civil Engineering, City University of Hong Kong, Hong Kong, P.R. China
6 shared publications Rongjun Cheng
Faculty of Maritime and Transportation, Ningbo University, Ningbo 315211, China
4 shared publicationsPeng-Jun Zheng
Ningbo University
3 shared publicationsWeilin Ren
Faculty of Maritime and Transportation, Ningbo University, Ningbo 315211, China
3 shared publications
Latest Publications
- Open Access
- 16 June 2022
- Published by MDPI AG in Sustainability
- Vol. 14 (12) , 7371
Self-Attention ConvLSTM for Spatiotemporal Forecasting of Short-Term Online Car-Hailing Demand
As a flourishing basic transportation service in recent years, online car-hailing has made great achievements in metropolitan cities. Accurate spatiotemporal forecasting plays a significant role in the deployment of a network for online car-hailing demand services. A self-attention mechanism in convolutional long short-term memory (ConvLSTM) is proposed to accurately predict the online car-hailing demand. It can more effectively address the disadvantage that ConvLSTM is not good at capturing spatial correlation over a large spatial extent. Furthermore, it can generate features by aggregating pair-wise similarity scores of features at all positions of input and memory, and thus obtain the function of long-range spatiotemporal dependencies. First, the online car-hailing trajectories dataset was converted into images after geographic grid matching, and image enhancement was performed by cropping. Then, the effectiveness of the ConvLSTM embedded with a self-attention mechanism (SA-ConvLSTM) was demonstrated by comparing it to existing models. The experimental results showed that the proposed model performed better than the existing models, and including spatiotemporal information in images would perform better predictions than including spatial information in time-series pixels.
- 16 June 2022
- Published by MDPI AG in Sustainability
- Vol. 14 (12) , 7371
Open AccessSelf-Attention ConvLSTM for Spatiotemporal Forecasting of Short-Term Online Car-Hailing Demand
As a flourishing basic transportation service in recent years, online car-hailing has made great achievements in metropolitan cities. Accurate spatiotemporal forecasting plays a significant role in the deployment of a network for online car-hailing demand services. A self-attention mechanism in convolutional long short-term memory (ConvLSTM) is proposed to accurately predict the online car-hailing demand. It can more effectively address the disadvantage that ConvLSTM is not good at capturing spatial correlation over a large spatial extent. Furthermore, it can generate features by aggregating pair-wise similarity scores of features at all positions of input and memory, and thus obtain the function of long-range spatiotemporal dependencies. First, the online car-hailing trajectories dataset was converted into images after geographic grid matching, and image enhancement was performed by cropping. Then, the effectiveness of the ConvLSTM embedded with a self-attention mechanism (SA-ConvLSTM) was demonstrated by comparing it to existing models. The experimental results showed that the proposed model performed better than the existing models, and including spatiotemporal information in images would perform better predictions than including spatial information in time-series pixels.
- Open Access
- 30 March 2022
- Published by MDPI AG in Sustainability
- Vol. 14 (7) , 4083
Short-Term Travel Demand Prediction of Online Ride-Hailing Based on Multi-Factor GRU Model
In recent years, online ride-hailing has become an indispensable part of residents’ travel mode. Therefore, the prediction of online ride-hailing travel demand has become extremely important. In the era of big data, the application of big data in the field of transportation is becoming more extensive. Based on the open data of ride-hailing trips in Haikou City, Hainan Province, provided by the Didi platform and combined with the rainfall data of Haikou City, this paper proposes a gate recurrent unit (GRU) model considering rainfall factors and rest days factors for short-term trip demand prediction. The K-fold cross-validation method is adopted to adjust the parameters of the model to the optimal ones through the training set. The improved GRU model is compared with the original GRU model and other classic models, and the model is evaluated by root mean square error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE), and R2 score indexes. Finally, it is proved that the GRU model proposed in this paper greatly improves the prediction accuracy of short-term online ride-hailing travel demand.
- 30 March 2022
- Published by MDPI AG in Sustainability
- Vol. 14 (7) , 4083
Open AccessShort-Term Travel Demand Prediction of Online Ride-Hailing Based on Multi-Factor GRU Model
In recent years, online ride-hailing has become an indispensable part of residents’ travel mode. Therefore, the prediction of online ride-hailing travel demand has become extremely important. In the era of big data, the application of big data in the field of transportation is becoming more extensive. Based on the open data of ride-hailing trips in Haikou City, Hainan Province, provided by the Didi platform and combined with the rainfall data of Haikou City, this paper proposes a gate recurrent unit (GRU) model considering rainfall factors and rest days factors for short-term trip demand prediction. The K-fold cross-validation method is adopted to adjust the parameters of the model to the optimal ones through the training set. The improved GRU model is compared with the original GRU model and other classic models, and the model is evaluated by root mean square error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE), and R2 score indexes. Finally, it is proved that the GRU model proposed in this paper greatly improves the prediction accuracy of short-term online ride-hailing travel demand.
- 1 March 2022
- Published by IOP Publishing in Chinese Physics B
- Vol. 31 (4) , 040502
Traffic flow prediction based on BILSTM model and data denoising scheme
Accurate prediction of road traffic flow is a significant part in the intelligent transportation systems. Accurate prediction can alleviate traffic congestion, and reduce environmental pollution. For the management department, it can make effective use of road resources. For individuals, it can help people plan their own travel paths, avoid congestion, and save time. Owing to complex factors on the road, such as damage to the detector and disturbances from environment, the measured traffic volume can contain noise. Reducing the influence of noise on traffic flow prediction is a piece of very important work. Therefore, in this paper we propose a combination algorithm of denoising and BILSTM to effectively improve the performance of traffic flow prediction. At the same time, three denoising algorithms are compared to find the best combination mode. In this paper, the wavelet (WL) denoising scheme, the empirical mode decomposition (EMD) denoising scheme, and the ensemble empirical mode decomposition (EEMD) denoising scheme are all introduced to suppress outliers in traffic flow data. In addition, we combine the denoising schemes with bidirectional long short-term memory (BILSTM) network to predict the traffic flow. The data in this paper are cited from performance measurement system (PeMS). We choose three kinds of road data (mainline, off ramp, on ramp) to predict traffic flow. The results for mainline show that data denoising can improve prediction accuracy. Moreover, prediction accuracy of BILSTM+EEMD scheme is the highest in the three methods (BILSTM+WL, BILSTM+EMD, BILSTM+EEMD). The results for off ramp and on ramp show the same performance as the results for mainline. It is indicated that this model is suitable for different road sections and long-term prediction.
- 1 March 2022
- Published by IOP Publishing in Chinese Physics B
- Vol. 31 (4) , 040502
Traffic flow prediction based on BILSTM model and data denoising scheme
Accurate prediction of road traffic flow is a significant part in the intelligent transportation systems. Accurate prediction can alleviate traffic congestion, and reduce environmental pollution. For the management department, it can make effective use of road resources. For individuals, it can help people plan their own travel paths, avoid congestion, and save time. Owing to complex factors on the road, such as damage to the detector and disturbances from environment, the measured traffic volume can contain noise. Reducing the influence of noise on traffic flow prediction is a piece of very important work. Therefore, in this paper we propose a combination algorithm of denoising and BILSTM to effectively improve the performance of traffic flow prediction. At the same time, three denoising algorithms are compared to find the best combination mode. In this paper, the wavelet (WL) denoising scheme, the empirical mode decomposition (EMD) denoising scheme, and the ensemble empirical mode decomposition (EEMD) denoising scheme are all introduced to suppress outliers in traffic flow data. In addition, we combine the denoising schemes with bidirectional long short-term memory (BILSTM) network to predict the traffic flow. The data in this paper are cited from performance measurement system (PeMS). We choose three kinds of road data (mainline, off ramp, on ramp) to predict traffic flow. The results for mainline show that data denoising can improve prediction accuracy. Moreover, prediction accuracy of BILSTM+EEMD scheme is the highest in the three methods (BILSTM+WL, BILSTM+EMD, BILSTM+EEMD). The results for off ramp and on ramp show the same performance as the results for mainline. It is indicated that this model is suitable for different road sections and long-term prediction.
- 1 January 2022
- Published by IOP Publishing in Chinese Physics B
- Vol. 31 (1) , 010504
An extended smart driver model considering electronic throttle angle changes with memory
Based on the fact that the electronic throttle angle effect performs well in the traditional car following model, this paper attempts to introduce the electronic throttle angle into the smart driver model (SDM) as an acceleration feedback control term, and establish an extended smart driver model considering electronic throttle angle changes with memory (ETSDM). In order to show the practicability of the extended model, the next generation simulation (NGSIM) data was used to calibrate and evaluate the extended model and the smart driver model. The calibration results show that, compared with SDM, the simulation value based on the ETSDM is better fitted with the measured data, that is, the extended model can describe the actual traffic situation more accurately. Then, the linear stability analysis of ETSDM was carried out theoretically, and the stability condition was derived. In addition, numerical simulations were explored to show the influence of the electronic throttle angle changes with memory and the driver sensitivity on the stability of traffic flow. The numerical results show that the feedback control term of electronic throttle angle changes with memory can enhance the stability of traffic flow, which shows the feasibility and superiority of the proposed model to a certain extent.
- 1 January 2022
- Published by IOP Publishing in Chinese Physics B
- Vol. 31 (1) , 010504
An extended smart driver model considering electronic throttle angle changes with memory
Based on the fact that the electronic throttle angle effect performs well in the traditional car following model, this paper attempts to introduce the electronic throttle angle into the smart driver model (SDM) as an acceleration feedback control term, and establish an extended smart driver model considering electronic throttle angle changes with memory (ETSDM). In order to show the practicability of the extended model, the next generation simulation (NGSIM) data was used to calibrate and evaluate the extended model and the smart driver model. The calibration results show that, compared with SDM, the simulation value based on the ETSDM is better fitted with the measured data, that is, the extended model can describe the actual traffic situation more accurately. Then, the linear stability analysis of ETSDM was carried out theoretically, and the stability condition was derived. In addition, numerical simulations were explored to show the influence of the electronic throttle angle changes with memory and the driver sensitivity on the stability of traffic flow. The numerical results show that the feedback control term of electronic throttle angle changes with memory can enhance the stability of traffic flow, which shows the feasibility and superiority of the proposed model to a certain extent.
- 1 December 2021
- Published by IOP Publishing in Chinese Physics B
- Vol. 30 (12) , 120506
Stabilization strategy of a car-following model with multiple time delays of the drivers*
An extended car-following model with multiple delays is constructed to describe driver’s driving behavior. Through stability analysis, the stability condition of this uncontrolled model is given. To dampen the negative impact of the driver’s multiple delays (i.e., stability condition is not satisfied), a novel control strategy is proposed to assist the driver in adjusting vehicle operation. The control strategy consists of two parts: the design of control term as well as the design of the parameters in the term. Bifurcation analysis is performed to illustrate the necessity of the design of parameters in control terms. In the course of the design of parameters in the control term, we improve the definite integral stability method to reduce the iterations by incorporating the characteristics of bifurcation, which can determine the appropriate parameters in the control terms more quickly. Finally, in the case study, we validate the control strategy by utilizing measured data and configuring scenario, which is closer to the actual traffic. The results of validation show that the control strategy can effectively stabilize the unstable traffic flow caused by driver’s delays.
- 1 December 2021
- Published by IOP Publishing in Chinese Physics B
- Vol. 30 (12) , 120506
Stabilization strategy of a car-following model with multiple time delays of the drivers*
An extended car-following model with multiple delays is constructed to describe driver’s driving behavior. Through stability analysis, the stability condition of this uncontrolled model is given. To dampen the negative impact of the driver’s multiple delays (i.e., stability condition is not satisfied), a novel control strategy is proposed to assist the driver in adjusting vehicle operation. The control strategy consists of two parts: the design of control term as well as the design of the parameters in the term. Bifurcation analysis is performed to illustrate the necessity of the design of parameters in control terms. In the course of the design of parameters in the control term, we improve the definite integral stability method to reduce the iterations by incorporating the characteristics of bifurcation, which can determine the appropriate parameters in the control terms more quickly. Finally, in the case study, we validate the control strategy by utilizing measured data and configuring scenario, which is closer to the actual traffic. The results of validation show that the control strategy can effectively stabilize the unstable traffic flow caused by driver’s delays.
- Open Access
- 12 November 2021
- Published by MDPI AG in Mathematics
- Vol. 9 (22) , 2879
An Extended Car-Following Model Based on Visual Angle and Electronic Throttle Effect
With the continuous advancement of electronic technology, auto parts manufacturing institutions are gradually applying electronic throttles to automobiles for precise control. Based on the visual angle model (VAM), a car-following model considering the electronic throttle angle of the preceding vehicle is proposed. The stability conditions are obtained through linear stability analysis. By means of nonlinear analysis, the time-dependent Ginzburg–Landau (TDGL) equation is derived first, and then the modified Korteweg-de-Vries (mKdV) equation is derived. The relationship between the two is thus obtained. Finally, in the process of numerical simulations and exploration, it is shown how the visual angle and electronic throttle affect the stability of traffic flow. The simulation results in MATLAB software verify the validity of the model, indicating that the visual angle and electronic throttle can improve traffic stability.
- 12 November 2021
- Published by MDPI AG in Mathematics
- Vol. 9 (22) , 2879
Open AccessAn Extended Car-Following Model Based on Visual Angle and Electronic Throttle Effect
With the continuous advancement of electronic technology, auto parts manufacturing institutions are gradually applying electronic throttles to automobiles for precise control. Based on the visual angle model (VAM), a car-following model considering the electronic throttle angle of the preceding vehicle is proposed. The stability conditions are obtained through linear stability analysis. By means of nonlinear analysis, the time-dependent Ginzburg–Landau (TDGL) equation is derived first, and then the modified Korteweg-de-Vries (mKdV) equation is derived. The relationship between the two is thus obtained. Finally, in the process of numerical simulations and exploration, it is shown how the visual angle and electronic throttle affect the stability of traffic flow. The simulation results in MATLAB software verify the validity of the model, indicating that the visual angle and electronic throttle can improve traffic stability.
- 9 November 2021
- Published by World Scientific Pub Co Pte Ltd in Modern Physics Letters B
- Vol. 36 (01)
Heterogeneous traffic flow model under connected vehicles environment considering cyberattacks
Under the Vehicle-to-Vehicle (V2V) environment, connected vehicles (CVs) can share the traveling information with each other to keep the traffic flow stable. However, the open network cooperation environment makes CVs vulnerable to cyberattacks, which leads to changes in driving behavior. The existing theories divide cyberattacks into three types: bogus information, replay/delay and collusion cyberattacks. In addition, the mixed flow consisting of truck and car is a common form of road traffic. In order to clarify the potential impact of cyberattacks on mixed traffic flow, this paper proposes an extended car-following model considering cyberattacks under CVs environment. Subsequently, the stability of the model is analyzed theoretically, and the stability condition of the model is obtained. The numerical simulation is carried out and the result shows that the cyberattacks lead to different degrees of traffic behavior hazards such as queue time extension, congestion and even rear end collision. Among them, cooperative attack is the most serious.
- 9 November 2021
- Published by World Scientific Pub Co Pte Ltd in Modern Physics Letters B
- Vol. 36 (01)
Heterogeneous traffic flow model under connected vehicles environment considering cyberattacks
Under the Vehicle-to-Vehicle (V2V) environment, connected vehicles (CVs) can share the traveling information with each other to keep the traffic flow stable. However, the open network cooperation environment makes CVs vulnerable to cyberattacks, which leads to changes in driving behavior. The existing theories divide cyberattacks into three types: bogus information, replay/delay and collusion cyberattacks. In addition, the mixed flow consisting of truck and car is a common form of road traffic. In order to clarify the potential impact of cyberattacks on mixed traffic flow, this paper proposes an extended car-following model considering cyberattacks under CVs environment. Subsequently, the stability of the model is analyzed theoretically, and the stability condition of the model is obtained. The numerical simulation is carried out and the result shows that the cyberattacks lead to different degrees of traffic behavior hazards such as queue time extension, congestion and even rear end collision. Among them, cooperative attack is the most serious.
- 7 September 2021
- Published by Emerald Publishing in Engineering Computations
- Vol. 39 (3) , 1038-1050
An extended car-following model considering the effect of two-sided lateral gap with uncertain velocity on curved road
Purpose: The goal of this study is to explore the effect of two-sided lateral gap with uncertain velocity on the stability of traffic flow on a curved road.Design/methodology/approach: In this paper, an extended car-following model considering the effect of two-sided lateral gap with uncertain velocity on a curved road is proposed. The effects of different lateral positions and radius of different sizes can be considered as control signals. The stability condition of the new model is obtained by the control theory. The numerical simulations are carried out to analyze how the control signal and lateral positions and radius of curved road affect traffic flow stability. The results show that driving between two lanes and inaccurate speed estimates both have a negative effect on traffic flow stability, and the stability also decreases with the increase in the radius of curved road.Findings: (1) Simulation of influencing factors of vehicle lateral position indicates that if the driver drives between two lanes, it would have a negative impact on traffic flow. (2) When the speed is fixed, the traffic flow becomes more and more unstable with the increase in the radius of the curve. (3) The stability of traffic flow will be affected when the driver estimates the speed of the vehicle ahead. Therefore, whether it is manual driving or future intelligent vehicle driving, it is necessary to accurately judge the speed of the front vehicle.Originality/value: There is little research on two-sided lateral gap with uncertain velocity for the stability of traffic flow on a curved road. The enhanced model constructed in this study can better reflect the real traffic, which can also give some theoretical reference for the development of connected and autonomous vehicles (CAVs).
- 7 September 2021
- Published by Emerald Publishing in Engineering Computations
- Vol. 39 (3) , 1038-1050
An extended car-following model considering the effect of two-sided lateral gap with uncertain velocity on curved road
Purpose: The goal of this study is to explore the effect of two-sided lateral gap with uncertain velocity on the stability of traffic flow on a curved road.Design/methodology/approach: In this paper, an extended car-following model considering the effect of two-sided lateral gap with uncertain velocity on a curved road is proposed. The effects of different lateral positions and radius of different sizes can be considered as control signals. The stability condition of the new model is obtained by the control theory. The numerical simulations are carried out to analyze how the control signal and lateral positions and radius of curved road affect traffic flow stability. The results show that driving between two lanes and inaccurate speed estimates both have a negative effect on traffic flow stability, and the stability also decreases with the increase in the radius of curved road.Findings: (1) Simulation of influencing factors of vehicle lateral position indicates that if the driver drives between two lanes, it would have a negative impact on traffic flow. (2) When the speed is fixed, the traffic flow becomes more and more unstable with the increase in the radius of the curve. (3) The stability of traffic flow will be affected when the driver estimates the speed of the vehicle ahead. Therefore, whether it is manual driving or future intelligent vehicle driving, it is necessary to accurately judge the speed of the front vehicle.Originality/value: There is little research on two-sided lateral gap with uncertain velocity for the stability of traffic flow on a curved road. The enhanced model constructed in this study can better reflect the real traffic, which can also give some theoretical reference for the development of connected and autonomous vehicles (CAVs).
- 18 August 2021
- Published by Taylor & Francis in Transportmetrica B: Transport Dynamics
- Vol. 10 (1) , 111-138
Nonlinear and bifurcation analysis for a novel heterogeneous continuum model and numerical tests
In this paper, an improved heterogeneous continuum model is presented accounting for multiple optimal velocity functions with probabilities, in which self-stabilizing effect and velocity uncertainty are considered simultaneously. The linear stability criterion of this new model is obtained by applying linear stability theory. By means of nonlinear analysis method, the Korteweg-de Vries-Burgers (KdV-Burgers) equation is deduced to discuss the evolution process of traffic flow density wave. Through bifurcation analysis, the conditions and stability of the Hopf bifurcation for the new model are derived in detail. Numerical simulations are performed to study the influences of above mentioned factors on the stability of traffic flow. Fuel consumption and emissions are also explored in this paper. It is notable that when the Hopf bifurcation point is selected as the initial point of density evolution, significant periodic oscillations will occur in the traffic flow. The results of numerical simulations coincide well with the theoretical analysis.
- 18 August 2021
- Published by Taylor & Francis in Transportmetrica B: Transport Dynamics
- Vol. 10 (1) , 111-138
Nonlinear and bifurcation analysis for a novel heterogeneous continuum model and numerical tests
In this paper, an improved heterogeneous continuum model is presented accounting for multiple optimal velocity functions with probabilities, in which self-stabilizing effect and velocity uncertainty are considered simultaneously. The linear stability criterion of this new model is obtained by applying linear stability theory. By means of nonlinear analysis method, the Korteweg-de Vries-Burgers (KdV-Burgers) equation is deduced to discuss the evolution process of traffic flow density wave. Through bifurcation analysis, the conditions and stability of the Hopf bifurcation for the new model are derived in detail. Numerical simulations are performed to study the influences of above mentioned factors on the stability of traffic flow. Fuel consumption and emissions are also explored in this paper. It is notable that when the Hopf bifurcation point is selected as the initial point of density evolution, significant periodic oscillations will occur in the traffic flow. The results of numerical simulations coincide well with the theoretical analysis.
- 1 July 2021
- Published by Elsevier in Physica A: Statistical Mechanics and its Applications
- Vol. 574, 125972
Bifurcation control of optimal velocity model through anticipated effect and response time-delay feedback methods
- 1 July 2021
- Published by Elsevier in Physica A: Statistical Mechanics and its Applications
- Vol. 574, 125972
Bifurcation control of optimal velocity model through anticipated effect and response time-delay feedback methods