Wenchen Yang

Bio: Wenchen Yang is an academic researcher from Tongji University. The author has contributed to research in topics: Traffic flow & Fuzzy control system. The author has an hindex of 4, co-authored 7 publications receiving 174 citations.

Optimized two-stage fuzzy control for urban traffic signals at isolated intersection and Paramics simulation

Abstract: This paper presents two adaptive two-stage fuzzy controllers for traffic signals at isolated intersections. Firstly, a two-stage combination fuzzy controller is designed. For traffic status variables in two-stage controller leading to the inefficiency of traffic states weakening under low traffic flow, the controller introduces 0–1 combination and determines the combination of traffic status variables of fuzzy controller's inputs from the perspective of structural optimization. Secondly, aiming at the problems of fuzzy controller parameter empirical settings and functional disability of learning, a two-stage fuzzy logic traffic signal controller with online optimization is proposed; this controller introduces the rolling horizon framework and optimizes the parameters of membership functions and controller rules by using hybrid genetic algorithm. The performance of two proposed models is validated via online Paramics-based simulation platform, and extensive simulation tests have demonstrated the potential of developed controllers for adaptive traffic signal control.

Urban traffic signal two-stage combination fuzzy control and Paramics simulation

Abstract: In the light of more traffic status variables are considered under low traffic flow in traffic intensity-based two-stage fuzzy control for urban traffic signals, thus leading to the inefficiency of traffic states weakening at isolated intersections This paper introduces a two-stage combination fuzzy optimal controller for traffic signals at urban isolated intersections: the proposed controller adopts 0–1 combination; depending on the traffic status at intersections, the combination of variables of traffic status of fuzzy controller's inputs will be determined; and the single-stage controller is applied under low traffic flow, while the traffic intensity-based two-stage fuzzy controller is used under medium or high traffic flow Experiment is carried on a typical urban isolated intersection and performance of proposed model and algorithm is validated via Paramics Furthermore, four kinds of control strategies are extensively simulated on different simulations scenes Simulation results indicate that the proposed controller is able to choose status variables based on traffic status features at isolated intersections and the signal strategy derived from the proposed controller is more effective

Adaptive Control Method of Multi-Phase Intersection Based on Traffic Status Identification

Abstract: Adaptive signal control methods have the ability to improve operations at isolated intersections. However, most of these experiences mainly focus on one specific traffic status, so other traffic characteristics are not fully considered. In this paper, the traffic status of an isolated intersection is identified using a two-dimensional fundamental diagram divided into four levels. An adaptive traffic signal control method based on traffic status identification is proposed. Different signal control performance indexes (PIs) are chosen in different traffic levels. Appropriate evaluation parameters are selected for the PIs according to real-time traffic characteristics. An enumeration algorithm is put forward to solve the optimized model of PIs. Then, a signalized intersection in Shenzhen city is studied through theoretical calculation and simulation evaluation via a microscopic traffic simulation software, Paramics. The results indicate that the signal strategy derived from the proposed method is more effective than the original F. Webster method strategy, because the proposed PIs outperform those of F. Webster on all four traffic levels.

Golden ratio genetic algorithm based approach for modelling and analysis of the capacity expansion of urban road traffic network

Abstract: This paper presents the modelling and analysis of the capacity expansion of urban road traffic network (ICURTN). Thebilevel programming model is first employed to model the ICURTN, in which the utility of the entire network is maximized with the optimal utility of travelers' route choice. Then, an improved hybrid genetic algorithm integrated with golden ratio (HGAGR) is developed to enhance the local search of simple genetic algorithms, and the proposed capacity expansion model is solved by the combination of the HGAGR and the Frank-Wolfe algorithm. Taking the traditional one-way network and bidirectional network as the study case, three numerical calculations are conducted to validate the presented model and algorithm, and the primary influencing factors on extended capacity model are analyzed. The calculation results indicate that capacity expansion of road network is an effective measure to enlarge the capacity of urban road network, especially on the condition of limited construction budget; the average computation time of the HGAGR is 122 seconds, which meets the real-time demand in the evaluation of the road network capacity.

T-GCN: A Temporal Graph Convolutional Network for Traffic Prediction

Abstract: Accurate and real-time traffic forecasting plays an important role in the intelligent traffic system and is of great significance for urban traffic planning, traffic management, and traffic control. However, traffic forecasting has always been considered an “open” scientific issue, owing to the constraints of urban road network topological structure and the law of dynamic change with time. To capture the spatial and temporal dependences simultaneously, we propose a novel neural network-based traffic forecasting method, the temporal graph convolutional network (T-GCN) model, which is combined with the graph convolutional network (GCN) and the gated recurrent unit (GRU). Specifically, the GCN is used to learn complex topological structures for capturing spatial dependence and the gated recurrent unit is used to learn dynamic changes of traffic data for capturing temporal dependence. Then, the T-GCN model is employed to traffic forecasting based on the urban road network. Experiments demonstrate that our T-GCN model can obtain the spatio-temporal correlation from traffic data and the predictions outperform state-of-art baselines on real-world traffic datasets. Our tensorflow implementation of the T-GCN is available at https://www.github.com/lehaifeng/T-GCN .

Short-term traffic flow rate forecasting based on identifying similar traffic patterns

Abstract: The ability to timely and accurately forecast the evolution of traffic is very important in traffic management and control applications. This paper proposes a non-parametric and data-driven methodology for short-term traffic forecasting based on identifying similar traffic patterns using an enhanced K-nearest neighbor (K-NN) algorithm. Weighted Euclidean distance, which gives more weight to recent measurements, is used as a similarity measure for K-NN. Moreover, winsorization of the neighbors is implemented to dampen the effects of dominant candidates, and rank exponent is used to aggregate the candidate values. Robustness of the proposed method is demonstrated by implementing it on large datasets collected from different regions and by comparing it with advanced time series models, such as SARIMA and adaptive Kalman Filter models proposed by others. It is demonstrated that the proposed method reduces the mean absolute percent error by more than 25%. In addition, the effectiveness of the proposed enhanced K-NN algorithm is evaluated for multiple forecast steps and also its performance is tested under data with missing values. This research provides strong evidence suggesting that the proposed non-parametric and data-driven approach for short-term traffic forecasting provides promising results. Given the simplicity, accuracy, and robustness of the proposed approach, it can be easily incorporated with real-time traffic control for proactive freeway traffic management.

Multistep speed prediction on traffic networks: A deep learning approach considering spatio-temporal dependencies

Abstract: Multistep traffic forecasting on road networks is a crucial task in successful intelligent transportation system applications. To capture the complex non-stationary temporal dynamics and spatial correlations in multistep traffic-condition prediction, we propose a novel deep learning framework named attention graph convolutional sequence-to-sequence model (AGC-Seq2Seq). In the proposed deep learning framework, spatial and temporal dependencies are modeled through the Seq2Seq model and graph convolution network separately, and the attention mechanism along with a newly designed training method based on the Seq2Seq architecture is proposed to overcome the difficulty in multistep prediction and further capture the temporal heterogeneity of traffic pattern. We conduct numerical tests to compare AGC-Seq2Seq with other benchmark models using two real-world datasets. The results indicate that our model yields the best prediction performance in terms of various prediction error measures. Furthermore, the variations of spatio-temporal correlations of traffic conditions under different perdition steps and road segments are revealed.

Temporal Graph Convolutional Network for Urban Traffic Flow Prediction Method.

Abstract: Accurate and real-time traffic forecasting plays an important role in the Intelligent Traffic System and is of great significance for urban traffic planning, traffic management, and traffic control. However, traffic forecasting has always been considered an open scientific issue, owing to the constraints of urban road network topological structure and the law of dynamic change with time, namely, spatial dependence and temporal dependence. To capture the spatial and temporal dependence simultaneously, we propose a novel neural network-based traffic forecasting method, the temporal graph convolutional network (T-GCN) model, which is in combination with the graph convolutional network (GCN) and gated recurrent unit (GRU). Specifically, the GCN is used to learn complex topological structures to capture spatial dependence and the gated recurrent unit is used to learn dynamic changes of traffic data to capture temporal dependence. Then, the T-GCN model is employed to traffic forecasting based on the urban road network. Experiments demonstrate that our T-GCN model can obtain the spatio-temporal correlation from traffic data and the predictions outperform state-of-art baselines on real-world traffic datasets. Our tensorflow implementation of the T-GCN is available at this https URL.