Physical Model versus Artificial Neural Network (ANN) Model: A Comparative Study on Modeling Car-Following Behavior at Signalized Intersections
Many studies have simulated traffic behavior at signalized intersections using various Car-Following (CF) models. However, the performance of which CF Model is superior at signalized intersections has not been thoroughly analyzed and evaluated. In this study, two novel Artificial Neural Network (ANN...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-01-01
|
| Series: | Journal of Advanced Transportation |
| Online Access: | http://dx.doi.org/10.1155/2022/8482846 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832554785164754944 |
|---|---|
| author | Lan Yang Shan Fang Guoyuan Wu He Sheng Zhigang Xu Mengxiao Zhang Xiangmo Zhao |
| author_facet | Lan Yang Shan Fang Guoyuan Wu He Sheng Zhigang Xu Mengxiao Zhang Xiangmo Zhao |
| author_sort | Lan Yang |
| collection | DOAJ |
| description | Many studies have simulated traffic behavior at signalized intersections using various Car-Following (CF) models. However, the performance of which CF Model is superior at signalized intersections has not been thoroughly analyzed and evaluated. In this study, two novel Artificial Neural Network (ANN) CF models, the Convolutional Neural Network—Long Short-term Memory (CNN-LSTM) and the Convolution-LSTM (Conv-LSTM)—are first applied to predict CF behaviors at signalized intersections. Both models can extract spatial and temporal information to address the long-term dependency problem more effectively. Based on the filtered NGSIM dataset, we conduct a comparative empirical study of three conventional CF models and five ANN CF models. The dataset is divided into two categories based on the characteristics of CF behavior at signalized intersections: continuous and discontinuous. The experiments demonstrated that ANN CF models outperformed conventional CF models when the output was the velocity in two categories of traffic flow but only failed to do so when the output was acceleration in discontinuous traffic flow. The proposed models were capable of accurately predicting acceleration, but the traffic fluctuations also existed as time passed. Additionally, it was discovered that while the ANN CF model is preferable for traffic flow simulation, the conventional CF model still cannot be ignored for discontinuous traffic flow simulation, particularly when acceleration is required. |
| format | Article |
| id | doaj-art-6483e5c2266749fca38f06e1c33bba96 |
| institution | Kabale University |
| issn | 2042-3195 |
| language | English |
| publishDate | 2022-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Journal of Advanced Transportation |
| spelling | doaj-art-6483e5c2266749fca38f06e1c33bba962025-02-03T05:50:31ZengWileyJournal of Advanced Transportation2042-31952022-01-01202210.1155/2022/8482846Physical Model versus Artificial Neural Network (ANN) Model: A Comparative Study on Modeling Car-Following Behavior at Signalized IntersectionsLan Yang0Shan Fang1Guoyuan Wu2He Sheng3Zhigang Xu4Mengxiao Zhang5Xiangmo Zhao6School of Information EngineeringSchool of Information EngineeringCenter for Environmental Research and TechnologySchool of Information EngineeringSchool of Information EngineeringSchool of Information EngineeringSchool of Information EngineeringMany studies have simulated traffic behavior at signalized intersections using various Car-Following (CF) models. However, the performance of which CF Model is superior at signalized intersections has not been thoroughly analyzed and evaluated. In this study, two novel Artificial Neural Network (ANN) CF models, the Convolutional Neural Network—Long Short-term Memory (CNN-LSTM) and the Convolution-LSTM (Conv-LSTM)—are first applied to predict CF behaviors at signalized intersections. Both models can extract spatial and temporal information to address the long-term dependency problem more effectively. Based on the filtered NGSIM dataset, we conduct a comparative empirical study of three conventional CF models and five ANN CF models. The dataset is divided into two categories based on the characteristics of CF behavior at signalized intersections: continuous and discontinuous. The experiments demonstrated that ANN CF models outperformed conventional CF models when the output was the velocity in two categories of traffic flow but only failed to do so when the output was acceleration in discontinuous traffic flow. The proposed models were capable of accurately predicting acceleration, but the traffic fluctuations also existed as time passed. Additionally, it was discovered that while the ANN CF model is preferable for traffic flow simulation, the conventional CF model still cannot be ignored for discontinuous traffic flow simulation, particularly when acceleration is required.http://dx.doi.org/10.1155/2022/8482846 |
| spellingShingle | Lan Yang Shan Fang Guoyuan Wu He Sheng Zhigang Xu Mengxiao Zhang Xiangmo Zhao Physical Model versus Artificial Neural Network (ANN) Model: A Comparative Study on Modeling Car-Following Behavior at Signalized Intersections Journal of Advanced Transportation |
| title | Physical Model versus Artificial Neural Network (ANN) Model: A Comparative Study on Modeling Car-Following Behavior at Signalized Intersections |
| title_full | Physical Model versus Artificial Neural Network (ANN) Model: A Comparative Study on Modeling Car-Following Behavior at Signalized Intersections |
| title_fullStr | Physical Model versus Artificial Neural Network (ANN) Model: A Comparative Study on Modeling Car-Following Behavior at Signalized Intersections |
| title_full_unstemmed | Physical Model versus Artificial Neural Network (ANN) Model: A Comparative Study on Modeling Car-Following Behavior at Signalized Intersections |
| title_short | Physical Model versus Artificial Neural Network (ANN) Model: A Comparative Study on Modeling Car-Following Behavior at Signalized Intersections |
| title_sort | physical model versus artificial neural network ann model a comparative study on modeling car following behavior at signalized intersections |
| url | http://dx.doi.org/10.1155/2022/8482846 |
| work_keys_str_mv | AT lanyang physicalmodelversusartificialneuralnetworkannmodelacomparativestudyonmodelingcarfollowingbehavioratsignalizedintersections AT shanfang physicalmodelversusartificialneuralnetworkannmodelacomparativestudyonmodelingcarfollowingbehavioratsignalizedintersections AT guoyuanwu physicalmodelversusartificialneuralnetworkannmodelacomparativestudyonmodelingcarfollowingbehavioratsignalizedintersections AT hesheng physicalmodelversusartificialneuralnetworkannmodelacomparativestudyonmodelingcarfollowingbehavioratsignalizedintersections AT zhigangxu physicalmodelversusartificialneuralnetworkannmodelacomparativestudyonmodelingcarfollowingbehavioratsignalizedintersections AT mengxiaozhang physicalmodelversusartificialneuralnetworkannmodelacomparativestudyonmodelingcarfollowingbehavioratsignalizedintersections AT xiangmozhao physicalmodelversusartificialneuralnetworkannmodelacomparativestudyonmodelingcarfollowingbehavioratsignalizedintersections |