ST-SSMs: Spatial-Temporal Selective State of Space Model for Traffic Forecasting

arXiv:2404.13257v1 Announce Type: new
Abstract: Accurate and efficient traffic prediction is crucial for planning, management, and control of intelligent transportation systems. Most state-of-the-art methods for traffic prediction effectively predict both long-term and short-term by employing spatio-temporal neural networks as prediction models, together with transformers to learn global information on prediction objects (e.g., traffic states of road segments). However, these methods often have a high computational cost to obtain good performance. This paper introduces an innovative approach to traffic flow prediction, …

abstract art arxiv control cs.lg forecasting global information intelligent intelligent transportation learn long-term management networks neural networks planning prediction prediction models space spatial ssms state systems temporal together traffic transformers transportation type