Spatiotemporal Prediction Using Hierarchical Bayesian Modeling
| Autor: | Khalid Elgazzar, Taghreed Alghamdi, Taysseer Sharaf |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Spatial correlation
Hierarchy (mathematics) business.industry Computer science Gaussian 05 social sciences Bayesian probability MathematicsofComputing_NUMERICALANALYSIS 050801 communication & media studies Pattern recognition Covariance Bayesian inference symbols.namesake 0508 media and communications 0502 economics and business symbols Feature (machine learning) 050211 marketing Artificial intelligence business Gaussian process |
| Zdroj: | ICCSPA |
| DOI: | 10.1109/iccspa49915.2021.9385767 |
| Popis: | Hierarchical Bayesian models (HBM) are powerful tools that can be used for spatiotemporal analysis. The hierarchy feature associated with Bayesian modeling enhances the accuracy and precision of spatiotemporal predictions. This paper leverages the hierarchy of Bayesian models using the Gaussian process to predict long-term traffic status in urban settings. The Gaussian process is used with different covariance matrices: exponential, Gaussian, spherical, and Matern to capture the spatial correlation. Performance evaluation on traffic data shows that the exponential covariance yields the best precision in spatial analysis with the Gaussian process, while the Gaussian covariance outperforms the others in temporal forecasting. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|