Ontology-Assisted Dynamic Spatiotemporal Feature Extraction for Short-Term Traffic Forecasting
Authors:
Open Access
- 22 January 2026
- journal article
- Published by IGI Global Scientific Publishing in International Journal on Semantic Web and Information Systems
- Vol. 22 (1) , 1-23
Abstract
Short-term traffic flow prediction is essential for intelligent transportation systems, enabling signal control, route planning, and congestion mitigation. However, existing methods often overlook flow fluctuations and underutilize temporal positional information, limiting spatiotemporal modeling performance. Therefore, this study proposed a dynamic spatiotemporal feature extraction (DSTFE) model that integrated temporal information and fluctuation features (TIFF) for enhanced traffic prediction—DSTFE-TIFF. Specifically, DSTFE-TIFF employed trigonometric time encoding to capture multiscale patterns and an exponentially weighted sliding window to emphasize recent, abrupt changes. These features were then integrated through a time-weighted attention framework, which modeled both local and long-range dependencies to form comprehensive spatiotemporal representations. Experiments on three data sets—the traffic-speed data set in the Los Angeles County road network, traffic-flow data set in the San Francisco Bay area, and traffic-flow data set in California—showed that DSTFE-TIFF achieved state-of-the-art performance, reducing key error metrics (mean absolute error, root mean square error, mean absolute percentage error) by over 22% on average versus baselines, demonstrating its effectiveness and robustness.Keywords
This publication has 30 references indexed in Scilit:
- Confined attention mechanism enabled Recurrent Neural Network framework to improve traffic flow predictionEngineering Applications of Artificial Intelligence, 2024
- Spatial linear transformer and temporal convolution network for traffic flow predictionScientific Reports, 2024
- Spatial-temporal graph neural network based on gated convolution and topological attention for traffic flow predictionApplied Intelligence, 2023
- Dynamic spatial–temporal graph convolutional recurrent networks for traffic flow forecastingExpert Systems with Applications, 2023
- A combined method for short-term traffic flow prediction based on recurrent neural networkAlexandria Engineering Journal, 2021
- Human action recognition using convolutional LSTM and fully-connected LSTM with different attentionsNeurocomputing, 2020
- Cloud traffic prediction based on fuzzy ARIMA model with low dependence on historical dataTransactions on Emerging Telecommunications Technologies, 2019
- Real time adaptive non‐linear estimator/predictor design for traffic systems with inadequate detectorsIET Intelligent Transport Systems, 2014
- Urban traffic flow forecasting using Gauss–SVR with cat mapping, cloud model and PSO hybrid algorithmNeurocomputing, 2013
- New Introduction to Multiple Time Series Analysis2005