A Predicting Method of Urban Traffic Network Volume Based on STARIMA Model

Guan, Deyong; Huang, Lei; Qu, Qiankun

doi:10.1061/9780784480915.376

Cited by 5 publications

(2 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For example, Guan et al. (2018) used the multiple distribution of turning rates at intersections to quantify the spatio‐temporal dependency and then used it to modify a pre‐trained space‐time autoregressive integrated moving average (STARIMA) model. Rodrigues et al (2020) uses a large‐scale dataset to present an exploratory taxi demand analysis in which two forecast models (ARIMA and Artificial Neural Network) of short‐term taxi demand are developed and compared.…”

Section: Related Workmentioning

confidence: 99%

Spatio‐temporal neural network for taxi demand prediction using multisource urban data

Xiang

Yan

et al. 2022

Transactions in GIS

View full text Add to dashboard Cite

Predicting traffic demand is a crucial problem to saving energy and resource pre‐allocation as well as traffic construction planning. The problem is also challenging owing to its non‐linear changing process and complex spatio‐temporal dependencies. Most existing studies train prediction models on traffic data itself and ignore the impact of exogenous factors, thus leading to unsatisfactory performance. To address this issue, we propose a deep neural network, which utilizes multisource urban data to capture specific geospatial and temporal dependencies, for city‐scale taxi demand forecasting. In terms of time dependency, a temporal guidance block is developed to enhance the correlation between time intervals by incorporating time metadata. To capture the geospatial dependencies, we build three parallel geospatial guidance branches that integrate multiple urban data, including population data, POIs, and road networks, to guide the modeling. Each branch contains a geocontext‐aware convolutional layer for extracting geospatial features and a self‐attention mechanism for capturing long‐range spatial dependencies. Extensive experiments have been conducted to demonstrate the superiority of our model over the existing methods, and the prediction error is 16% lower than the state‐of‐the‐art model. We also explore the sensitivity to its parameters and discuss the contributions and limitations of the proposed method.

show abstract

Section: Related Workmentioning

confidence: 99%

Spatio‐temporal neural network for taxi demand prediction using multisource urban data

Xiang

Yan

et al. 2022

Transactions in GIS

View full text Add to dashboard Cite

show abstract

“…Estudos posteriores buscaram incluir a característica dinâmica do fluxo e se utilizaram da associação do modelo STARIMA com o modelo DTRP (Dynamic Turn Ratio Prediction), sendo necessária a definição de taxas de conversão de e para os links e a atualização em tempo real da matriz de pesos (DUAN et al, 2019;GUAN;QU, 2018;MIN et al, 2009). Este tipo de aplicação dinâmica depende de grande quantidade de sensores monitorando a rede de modo a possibilitar o acompanhamento ou determinação das taxas de conversão.…”

Section: Estimação Com Uso De Modelos Autorregressivos Espaço-temporaisunclassified

Estimação das características de tráfego em tempo próximo ao real para uso em sistemas de previsão e controle de tráfego.

Barros¹

View full text Add to dashboard Cite

Agradeço à Deus, pela saúde e capacidade em desenvolver este trabalho até o fim.À minha esposa Silvia, pelo amor, carinho, companhia, pelos inúmeros mimos durante o desenvolvimento desta pesquisa, pela compreensão das muitas horas de dedicação aos estudos e apoio incondicional na caminhada.Ao meu filho Paulo Vitor, pelo carinho, conselhos, companhia e valoroso apoio na parte científica e computacional. Por entender minhas ausências durante os longos trabalhos de pesquisa.Aos meus pais, in memoriam, pelo amor ao longo da vida e pelo direcionamento aos estudos.À minha irmã e meus irmãos, cunhado, cunhadas, sobrinhos e sobrinhas e demais familiares que sempre me apoiaram e incentivaram.

show abstract

Identifying key grid cells for crowd flow predictions based on CNN-based models with the Grad-CAM kit

et al. 2022

View full text Add to dashboard Cite

A Predicting Method of Urban Traffic Network Volume Based on STARIMA Model

Cited by 5 publications

References 11 publications

Spatio‐temporal neural network for taxi demand prediction using multisource urban data

Spatio‐temporal neural network for taxi demand prediction using multisource urban data

Estimação das características de tráfego em tempo próximo ao real para uso em sistemas de previsão e controle de tráfego.

Identifying key grid cells for crowd flow predictions based on CNN-based models with the Grad-CAM kit

Contact Info

Product

Resources

About