Traffic forecasting in Bogota, Colombia, with attention temporal graph convolutional network (A3T-GCN)
| dc.contributor.advisor | Riascos Ochoa, Javier | |
| dc.creator | Bernal Sánchez, Juan Andrés | |
| dc.creator | Riascos Ochoa, Javier | |
| dc.date.accessioned | 2025-06-16T22:19:14Z | |
| dc.date.available | 2025-06-16T22:19:14Z | |
| dc.date.created | 2024-10-24 | |
| dc.description.abstract | En el contexto de la gestión del tráfico urbano, los Sistemas Inteligentes de Transporte (SIT) avanzados requieren modelos de predicción del tráfico flexibles, eficientes y precisos. Estos modelos son esenciales para mejorar la seguridad vial, reducir la congestión y proporcionar asistencia a los usuarios y a las autoridades municipales. Sin embargo, los modelos convencionales, como ARIMA, las máquinas de vectores de apoyo y las redes neuronales artificiales (RNA), tienen una capacidad limitada para captar la no linealidad y la dinámica espaciotemporal de los datos de tráfico. Para hacer frente a estos retos, este estudio emplea el modelo A3T-GCN, que integra mecanismos de atención y redes convolucionales gráficas para procesar eficazmente los datos de tráfico. En concreto, este estudio se centra en la predicción de los flujos de tráfico en Bogotá, una ciudad conocida por su grave congestión de tráfico. Para adaptar el modelo A3T-GCN a este contexto, se utilizaron datos de velocidad de tráfico de la Plataforma Abierta de Datos de Bogotá. Los resultados demuestran el rendimiento superior del enfoque propuesto en comparación con los modelos ARIMA y RNA convencionales. Se observaron notables mejoras en RMSE, MAE, precisión y varianza explicada, así como estabilidad a lo largo de diversos horizontes de predicción. Además, el modelo se empleó para simular un escenario de congestión de tráfico, ilustrando así su capacidad de respuesta y adaptación a cambios repentinos en las series temporales de velocidad. Los resultados demuestran la validez y adaptabilidad del modelo A3T-GCN para la previsión del tráfico en Bogotá y destacan su potencial como herramienta fiable para los usuarios y las autoridades de gestión urbana. | spa |
| dc.description.abstractenglish | In the context of urban traffic management, advanced Intelligent Transportation Systems (ITS) require flexible, efficient, and accurate traffic prediction models. Such models are essential for enhancing road safety, reducing congestion, and providing assistance to users and city authorities. However, conventional models such as ARIMA, Support Vector Machines, and Artificial Neural Networks (ANN) are constrained in their ability to capture the nonlinearity and spatiotemporal dynamics of traffic data. To address these challenges, this study employs the A3T-GCNmodel, which integrates attention mechanisms and graph convolutional networks to effectively process traffic data. Specifically, this study focuses on the prediction of traffic flows in Bogotá, a city known for its severe traffic congestion. To adapt the A3T-GCN model to this context, traffic speed data from the Bogotá Open Data Platform was used. The results demonstrate the superior performance of the proposed approach in comparison to conventional ARIMA and ANN models. Notable improvements were observed in RMSE, MAE, accuracy, and explained variance, as well as stability across diverse forecast horizons. Furthermore, the model was employed to simulate a traffic congestion scenario, thereby illustrating its capacity to respond to and adapt to sudden changes in the speed time series. The findings demonstrate the validity and adaptability of the A3T-GCN model for traffic forecasting in Bogotá and highlight its potential as a reliable tool for users and urban management authorities. | spa |
| dc.format.extent | 12 páginas | spa |
| dc.format.mimetype | application/pdf | spa |
| dc.identifier.uri | https://hdl.handle.net/20.500.12010/36879 | |
| dc.language.iso | eng | spa |
| dc.relation.references | G. Dimitrakopoulos, D. Panagiotis, Intelligent transportation systems, Sustainable cities and society 5 (2010) 77–84 | spa |
| dc.relation.references | S. Shaheen, F. Rachel, Intelligent transportation systems, UC Berkeley: Transportation Sustainability Research Center (2013). | spa |
| dc.relation.references | ] D. Billings, J.-S. Yang, Application of the arima models to urban roadway travel time prediction- a case study, 2006 IEEE International Conference on Systems, Man and Cybernetics 3 (2006) 2529–2534. | spa |
| dc.relation.references | S. R. Chandra, A.-D. Haitham, Predictions of freeway traffic speeds and volumes using vector autoregressive models, Journal of Intelligent Transportation Systems 13 (2009) 53–72. | spa |
| dc.relation.references | J. Kamruzzaman, R. Sarker, I. Ahmad, Svm based models for predicting foreign currency exchange rates, Third IEEE International Conference on Data Mining (2003) 557–560. | spa |
| dc.relation.references | N. G. Polson, S. O. Vadim, Deep learning for short-term traffic flow prediction, Transportation Research Part C: Emerging Technologies 79 (2017) 1–17 | spa |
| dc.relation.references | I. O. Olayode, L. K. Tartibu, M. O. Okwu, Prediction and modeling of traffic flow of human-driven vehicles at a signalized road intersection using artificial neural network model: A south african road transportation system scenario, Transportation Engineering 6 (2003) 100095. | spa |
| dc.relation.references | B. Becerra, Bogotá es la cuarta ciudad del mundo con peor tráfico vehicular según traffic index, 2022. URL: https://www.larepublica.co/globoeconomia/ bogota-cuarta-ciudad-en-el-mundo-con-el-peor-trafico-vehicular-segun-nuevo-ranking-3325102#: ~:text=Transporte-,Bogot%C3%A1%20es%20la%20cuarta%20ciudad%20del%20mundo,tr%C3% A1fico%20vehicular%20seg%C3%BAn%20Traffic%20Index&text=De%20acuerdo%20con%20la% 20m%C3%A1s,cuarta%20en%20todo%20el%20mundo. | spa |
| dc.relation.references | A. F. Ramírez, C. Valencia, Spatiotemporal correlation study of traffic accidents with fatalities and injuries in bogotá (colombia), Accident Analysis and Prevention 149 (2021) 105848. | spa |
| dc.relation.references | J. Rodriguez, J. Jattin, Y. Soracipa, Probabilistic temporal prediction of the deaths caused by traffic in colombia. mortality caused by traffic prediction, Accident Analysis and Prevention 135 (2020) 105332 | spa |
| dc.relation.references | S. Castellanos, A. Baena, J. C. Ramírez, Predictive modelling of traffic accidents in bogotá, colombia: Uncovering key contributing factors, in: CEUR Workshop Proceedings, CEUR, Guayaquil, 2023, pp. 112–117. | spa |
| dc.relation.references | B. Jiandong, et al., Attention temporal graph convolutional network for traffic forecasting., ISPRS International Journal of Geo-Information 10 (2021) 485. | spa |
| dc.relation.references | A. Taghreed, E. Khalid, B. Magdi, S. Taysseer, S. Sumit, Forecasting traffic congestion using arima modeling, 2019 15th International Wireless Communications and Mobile Computing Conference (IWCMC) 3 (2019) 1227–1232. | spa |
| dc.relation.references | K. S. Vasantha, L. Vanajakshi, Short-term traffic flow prediction using seasonal arima model with limited input data, European Transport Research Review 7 (2015) 1–9 | spa |
| dc.relation.references | A. Novales, Modelos vectoriales autoregresivos (var), Universidad Complutense de Madrid 58 (2017). | spa |
| dc.relation.references | E. Zivot, W. Jiahui, Vector autoregressive models for multivariate time series, Modeling financial time series with S-PLUS® (2006) 385–429. | spa |
| dc.relation.references | D. Zeng, et al, Short term traffic flow prediction using hybrid arima and ann models, 2008 Workshop on Power Electronics and Intelligent Transportation System (2008) 621–625. doi | spa |
| dc.relation.references | M. S. Ghanim, D. Muley, M. Kharbeche, Ann-based traffic volume prediction models in response to covid-19 imposed measures, Sustainable cities and society 81 (2022) 103830. | spa |
| dc.relation.references | P. V. V. Theja, L. Vanajakshi, Short term prediction of traffic parameters using support vector machines technique, 2010 3rd International Conference on Emerging Trends in Engineering and Technology 79 (2010) 70–75. | spa |
| dc.relation.references | V. Lelitha, L. R. Rilett, A comparison of the performance of artificial neural networks and support vector machines for the prediction of traffic speed, IEEE Intelligent Vehicles Symposium, 2004 (2004) 194–199. | spa |
| dc.relation.references | S. D. D. Movilidad, Datos abiertos secretaria distrital de movilidad, 2024. URL: https://datos. movilidadbogota.gov.co/. | spa |
| dc.relation.references | T. N. Kipf, M. Welling, Semi-supervised classification with graph convolutional networks, ICLR (2017). | spa |
| dc.relation.references | L. Zhao, et al, T-gcn: A temporal graph convolutional network for traffic prediction, IEEE Transactions on Intelligent Transportation Systems 21 (2020) 3848–3858. | spa |
| dc.relation.references | C. Li, et al, Short-term wind speed interval prediction based on ensemble gru model, IEEE transactions on sustainable energy 11 (2019) 1370–1380. | spa |
| dc.relation.references | M. Khodayar, K. Okyay, M. E. Khodayar, Rough deep neural architecture for short-term wind speed forecasting, IEEE Transactions on Industrial Informatics 13 (2017) 2770–2779. | spa |
| dc.relation.references | B. Rozemberczki, et al, Pytorch geometric temporal: Spatiotemporal signal processing with neural machine learning models, Proceedings of the 30th ACM international conference on information and knowledge management (2021) 4564– 4573 | spa |
| dc.relation.references | Lehaifeng, T-gcn, 2022. URL: https://github.com/lehaifeng/T-GCN/tree/master/A3T-GCN. | spa |
| dc.relation.references | R. Mohamed, A3tgcn_seoul_data, 2021. URL: https://www.kaggle.com/code/mhmdrdwn/ a3tgcn-seoul-data/notebook. | spa |
| dc.subject | Dependencia espacial | |
| dc.subject | Dependencia temporal | |
| dc.subject | Simulación de tráfico | |
| dc.subject | Tráfico urbano latinoamericano | |
| dc.subject | Deep learning | spa |
| dc.subject.keyword | Spatial dependence | |
| dc.subject.keyword | Temporal dependence | |
| dc.subject.keyword | Traffic simulation | |
| dc.subject.keyword | Latin American urban traffic | |
| dc.subject.keyword | Deep learning | spa |
| dc.subject.lemb | Tránsito urbano - Modelos matemáticos | |
| dc.subject.lemb | Sistemas inteligentes de transporte - Aplicaciones de inteligencia artificial | |
| dc.subject.lemb | Análisis de series temporales - Datos de tráfico | |
| dc.title | Traffic forecasting in Bogota, Colombia, with attention temporal graph convolutional network (A3T-GCN) | spa |
| dc.type.coar | http://purl.org/coar/resource_type/c_6501 | spa |
Archivos
Bloque original
1 - 1 de 1
Cargando...
- Nombre:
- TRABAJO_DE_GRADO.pdf
- Tamaño:
- 4.96 MB
- Formato:
- Adobe Portable Document Format
- Descripción:
- Documento reservado
