scholarly journals Traffic speed prediction using ensemble kalman filter and differential evolution

2019 ◽  
Vol 259 ◽  
pp. 02001
Author(s):  
Lukáš Rapant
Keyword(s):  
Kalman Filter ◽  
Ensemble Kalman Filter ◽  
Intelligent Transportation System ◽  
Transmission Model ◽  
Traffic Data ◽  
Cell Transmission Model ◽  
Traffic State ◽  
Machine Learning Approach ◽  
Speed Prediction ◽  
Traffic Speed

Importance of traffic state prediction steadily increases with growing volume of traffic. Ability to predict traffic speed in short to medium horizon (i.e. up to one hour) is one of the main tasks of every newly developed Intelligent Transportation System. There are two possible approaches to this prediction. The first is to utilize physical properties of the traffic flow to construct an exact or approximate numerical model. This approach is, however, almost impossible to implement on a larger scale given the difficulty to obtain enough traffic data to describe the starting and boundary conditions of the model. The other option is to use historical traffic data and relate information and patterns they contain to the current traffic state by application of some form of statistical or machine learning approach. We propose to use combination of Ensemble Kalman filter and Cell Transmission Model for this task. These models combine properties of physical model with ability to incorporate uncertainty of the traffic data.

scholarly journals Development of Macroscopic Cell-Based Logistic Lane Change Prediction Model

2021 ◽  
Vol 2021 ◽  
pp. 1-17
Author(s):  
Christina Ng ◽  
Susilawati Susilawati ◽  
Md Abdus Samad Kamal ◽  
Irene Mei Leng Chew
Keyword(s):  
Prediction Model ◽  
Transmission Model ◽  
Lane Change ◽  
Traffic Data ◽  
Cell Transmission Model ◽  
Traffic State ◽  
Proposed Model ◽  
Significant Difference ◽  
The Mean ◽  
Change Prediction

This paper aims at developing a macroscopic cell-based lane change prediction model in a complex urban environment and integrating it into cell transmission model (CTM) to improve the accuracy of macroscopic traffic state estimation. To achieve these objectives, first, based on the observed traffic data, the binary logistic lane change model is developed to formulate the lane change occurrence. Second, the binary logistic lane change is integrated into CTM by refining CTM formulations on how the vehicles in the cell are moving from one cell to another in a longitudinal manner and how cell occupancy is updated after lane change occurrences. The performance of the proposed model is evaluated by comparing the simulated cell occupancy of the proposed model with cell occupancy of US-101 next generation simulation (NGSIM) data. The results indicated no significant difference between the mean of the cell occupancies of the proposed model and the mean of cell occupancies of actual data with a root-mean-square-error (RMSE) of 0.04. Similar results are found when the proposed model was further tested with I80 highway data. It is suggested that the mean of cell occupancies of I80 highway data was not different from the mean of cell occupancies of the proposed model with 0.074 RMSE (0.3 on average).

scholarly journals Global Spatial-Temporal Graph Convolutional Network for Urban Traffic Speed Prediction

2020 ◽  
Vol 10 (4) ◽  
pp. 1509 ◽  
Author(s):  
Liang Ge ◽  
Siyu Li ◽  
Yaqian Wang ◽  
Feng Chang ◽  
Kunyan Wu
Keyword(s):  
Weather Conditions ◽  
Urban Traffic ◽  
Traffic Data ◽  
Convolutional Network ◽  
Temporal Dimension ◽  
Temporal Correlations ◽  
Speed Prediction ◽  
External Component ◽  
Temporal Graph ◽  
Traffic Speed

Traffic speed prediction plays a significant role in the intelligent traffic system (ITS). However, due to the complex spatial-temporal correlations of traffic data, it is very challenging to predict traffic speed timely and accurately. The traffic speed renders not only short-term neighboring and multiple long-term periodic dependencies in the temporal dimension but also local and global dependencies in the spatial dimension. To address this problem, we propose a novel deep-learning-based model, Global Spatial-Temporal Graph Convolutional Network (GSTGCN), for urban traffic speed prediction. The model consists of three spatial-temporal components with the same structure and an external component. The three spatial-temporal components are used to model the recent, daily-periodic, and weekly-periodic spatial-temporal correlations of the traffic data, respectively. More specifically, each spatial-temporal component consists of a dynamic temporal module and a global correlated spatial module. The former contains multiple residual blocks which are stacked by dilated casual convolutions, while the latter contains a localized graph convolution and a global correlated mechanism. The external component is used to extract the effect of external factors, such as holidays and weather conditions, on the traffic speed. Experimental results on two real-world traffic datasets have demonstrated that the proposed GSTGCN outperforms the state-of-the-art baselines.

Enhanced Lagged Cell-Transmission Model for Dynamic Traffic Assignment

2008 ◽  
Vol 2085 (1) ◽  
pp. 76-85 ◽  
Author(s):  
W. Y. Szeto
Keyword(s):  
Intelligent Transportation System ◽  
Traffic Assignment ◽  
Dynamic Traffic Assignment ◽  
Computation Time ◽  
Transmission Model ◽  
Flow Density ◽  
Cell Transmission Model ◽  
Dynamic Traffic ◽  
Special Cases ◽  
Cell Transmission

The lagged cell-transmission model (L-CTM) is an enhanced version of the CTM. Both can be incorporated into a dynamic traffic assignment framework for offline transport planning and policy evaluation and online intelligent transportation system applications. In contrast to the CTM, the L-CTM adopts a nonconcave flow-density relation, which can be used to predict the existence of rather dense traffic in queues coasting toward the end of the queue or to help disprove the existence of this phenomenon. However, this study shows that the L-CTM can yield unrealistic densities, namely, negative densities and densities higher than theoretical jam density, the former of which has not been addressed in the literature. To cope with these unrealistic results, this study improves the L-CTM by introducing one more term in each sending and receiving function of the model. The improved model, the enhanced L-CTM (EL-CTM), is proved to yield nonnegative densities not greater than the jam density but can still allow the use of nonconcave density relations. The EL-CTM yields Lighthill-Whitham-Richards solutions when cell lengths and time intervals tend to zero and includes the CTM and the L-CTM as special cases. The EL-CTM is also shown to give more accurate solutions than the L-CTM (and hence also the CTM) does under a small increase in computation time. Hence the EL-CTM is believed to be more suitable for both online and offline applications in the future.

scholarly journals Calibration Framework based on Bluetooth Sensors for Traffic State Estimation Using a Velocity based Cell Transmission Model

2014 ◽  
Vol 3 ◽  
pp. 972-981 ◽  
Author(s):  
Andreas Allström ◽  
Alexandre M. Bayen ◽  
Magnus Fransson ◽  
David Gundlegård ◽  
Anthony D. Patire ◽  
...  
Keyword(s):  
State Estimation ◽  
Transmission Model ◽  
Cell Transmission Model ◽  
Traffic State ◽  
Traffic State Estimation ◽  
Cell Transmission

scholarly journals Traffic Speed Prediction for Highway Operations Based on a Symbolic Regression Algorithm

2017 ◽  
Vol 29 (4) ◽  
pp. 433-441 ◽  
Author(s):  
Li Linchao ◽  
Tomislav Fratrović ◽  
Zhang Jian ◽  
Ran Bin
Keyword(s):  
Symbolic Regression ◽  
Real World Data ◽  
Significant Information ◽  
Traffic State ◽  
Proposed Model ◽  
Microwave Sensor ◽  
Speed Prediction ◽  
Traffic Speed ◽  
Real Time Information ◽  
Time Information

Due to the increase of congestion on highways, providing real-time information about the traffic state has become a crucial issue. Hence, it is the aim of this research to build an accurate traffic speed prediction model using symbolic regression to generate significant information for travellers. It is built based on genetic programming using Pareto front technique. With real world data from microwave sensor, the performance of the proposed model is compared with two other widely used models. The results indicate that the symbolic regression is the most accurate among these models. Especially, after an incident occurs, the performance of the proposed model is still the best which means it is robust and suitable to predict traffic state of highway under different conditions.

Sign in / Sign up

Export Citation Format

Share Document