High-performance traffic volume prediction: An evaluation of RNN, GRU, and CNN for accuracy and computational trade-offs
Predicting urban traffic volume presents significant challenges due to complex temporal dependencies and fluctuations driven by environmental and situational factors. This study addresses these challenges by evaluating the effectiveness of three deep learning architectures— Recurrent Neural Network...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
EDP Sciences
2024-01-01
|
| Series: | BIO Web of Conferences |
| Online Access: | https://www.bio-conferences.org/articles/bioconf/pdf/2024/67/bioconf_icobeaf2024_02034.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841526757632507904 |
|---|---|
| author | Pranolo Andri Saifullah Shoffan Bella Utama Agung Wibawa Aji Prasetya Bastian Muhammad Hardiyanti P Cicin |
| author_facet | Pranolo Andri Saifullah Shoffan Bella Utama Agung Wibawa Aji Prasetya Bastian Muhammad Hardiyanti P Cicin |
| author_sort | Pranolo Andri |
| collection | DOAJ |
| description | Predicting urban traffic volume presents significant challenges due to complex temporal dependencies and fluctuations driven by environmental and situational factors. This study addresses these challenges by evaluating the effectiveness of three deep learning architectures— Recurrent Neural Network (RNN), Gated Recurrent Unit (GRU), and Convolutional Neural Network (CNN)—in forecasting hourly traffic volume on Interstate 94. Using a standardized dataset, each model was assessed on predictive accuracy, computational efficiency, and suitability for real-time applications, with Mean Absolute Percentage Error (MAPE), Root Mean Square Error (RMSE), R2 coefficient, and computation time as performance metrics. The GRU model demonstrated the highest accuracy, achieving a MAPE of 2.105%, RMSE of 0.198, and R2 of 0.469, but incurred the longest computation time of 7917 seconds. Conversely, CNN achieved the fastest computation time at 853 seconds, with moderate accuracy (MAPE of 2.492%, RMSE of 0.214, R2 of 0.384), indicating its suitability for real- time deployment. The RNN model exhibited intermediate performance, with a MAPE of 2.654% and RMSE of 0.215, reflecting its limitations in capturing long-term dependencies. These findings highlight crucial trade- offs between accuracy and efficiency, underscoring the need for model selection aligned with specific application requirements. Future work will explore hybrid architectures and optimization strategies to enhance further predictive accuracy and computational feasibility for urban traffic management. |
| format | Article |
| id | doaj-art-b720b98096804238873fca462eaf0879 |
| institution | Kabale University |
| issn | 2117-4458 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | EDP Sciences |
| record_format | Article |
| series | BIO Web of Conferences |
| spelling | doaj-art-b720b98096804238873fca462eaf08792025-01-16T11:19:46ZengEDP SciencesBIO Web of Conferences2117-44582024-01-011480203410.1051/bioconf/202414802034bioconf_icobeaf2024_02034High-performance traffic volume prediction: An evaluation of RNN, GRU, and CNN for accuracy and computational trade-offsPranolo Andri0Saifullah Shoffan1Bella Utama Agung2Wibawa Aji Prasetya3Bastian Muhammad4Hardiyanti P Cicin5Department of Informatics, Faculty of Industrial Technology, Universitas Ahmad DahlanDepartment of Informatics, Universitas Pembangunan Nasional Veteran YogyakartaDepartment of Electrical Engineering and Informatics, Faculty of Engineering, Universitas Negeri MalangDepartment of Electrical Engineering and Informatics, Faculty of Engineering, Universitas Negeri MalangScientific Publication, Universitas Ahmad DahlanAssociation for Scientific Computing Electrical and EngineeringPredicting urban traffic volume presents significant challenges due to complex temporal dependencies and fluctuations driven by environmental and situational factors. This study addresses these challenges by evaluating the effectiveness of three deep learning architectures— Recurrent Neural Network (RNN), Gated Recurrent Unit (GRU), and Convolutional Neural Network (CNN)—in forecasting hourly traffic volume on Interstate 94. Using a standardized dataset, each model was assessed on predictive accuracy, computational efficiency, and suitability for real-time applications, with Mean Absolute Percentage Error (MAPE), Root Mean Square Error (RMSE), R2 coefficient, and computation time as performance metrics. The GRU model demonstrated the highest accuracy, achieving a MAPE of 2.105%, RMSE of 0.198, and R2 of 0.469, but incurred the longest computation time of 7917 seconds. Conversely, CNN achieved the fastest computation time at 853 seconds, with moderate accuracy (MAPE of 2.492%, RMSE of 0.214, R2 of 0.384), indicating its suitability for real- time deployment. The RNN model exhibited intermediate performance, with a MAPE of 2.654% and RMSE of 0.215, reflecting its limitations in capturing long-term dependencies. These findings highlight crucial trade- offs between accuracy and efficiency, underscoring the need for model selection aligned with specific application requirements. Future work will explore hybrid architectures and optimization strategies to enhance further predictive accuracy and computational feasibility for urban traffic management.https://www.bio-conferences.org/articles/bioconf/pdf/2024/67/bioconf_icobeaf2024_02034.pdf |
| spellingShingle | Pranolo Andri Saifullah Shoffan Bella Utama Agung Wibawa Aji Prasetya Bastian Muhammad Hardiyanti P Cicin High-performance traffic volume prediction: An evaluation of RNN, GRU, and CNN for accuracy and computational trade-offs BIO Web of Conferences |
| title | High-performance traffic volume prediction: An evaluation of RNN, GRU, and CNN for accuracy and computational trade-offs |
| title_full | High-performance traffic volume prediction: An evaluation of RNN, GRU, and CNN for accuracy and computational trade-offs |
| title_fullStr | High-performance traffic volume prediction: An evaluation of RNN, GRU, and CNN for accuracy and computational trade-offs |
| title_full_unstemmed | High-performance traffic volume prediction: An evaluation of RNN, GRU, and CNN for accuracy and computational trade-offs |
| title_short | High-performance traffic volume prediction: An evaluation of RNN, GRU, and CNN for accuracy and computational trade-offs |
| title_sort | high performance traffic volume prediction an evaluation of rnn gru and cnn for accuracy and computational trade offs |
| url | https://www.bio-conferences.org/articles/bioconf/pdf/2024/67/bioconf_icobeaf2024_02034.pdf |
| work_keys_str_mv | AT pranoloandri highperformancetrafficvolumepredictionanevaluationofrnngruandcnnforaccuracyandcomputationaltradeoffs AT saifullahshoffan highperformancetrafficvolumepredictionanevaluationofrnngruandcnnforaccuracyandcomputationaltradeoffs AT bellautamaagung highperformancetrafficvolumepredictionanevaluationofrnngruandcnnforaccuracyandcomputationaltradeoffs AT wibawaajiprasetya highperformancetrafficvolumepredictionanevaluationofrnngruandcnnforaccuracyandcomputationaltradeoffs AT bastianmuhammad highperformancetrafficvolumepredictionanevaluationofrnngruandcnnforaccuracyandcomputationaltradeoffs AT hardiyantipcicin highperformancetrafficvolumepredictionanevaluationofrnngruandcnnforaccuracyandcomputationaltradeoffs |