Nature

Research on traffic flow prediction of progressive graph convolutional networks based on spatio-temporal self-attention mechanism

Traffic flow forecasting is a cornerstone of Intelligent Transportation Systems (ITS), aiming to infer future traffic states from historical observations to support congestion mitigation, route ...
Nature

Cross-domain transformer spatial-temporal fusion network for traffic flow forecasting

Forecasting traffic patterns is essential for smart city projects and the analysis of spatial-temporal data. Precise traffic flow forecasting can offer data-driven guidance and strategic planning for ...
Science Daily

Researchers develop fastest possible flow algorithm

Computer scientists have written a network flow algorithm that computes almost as fast as is mathematically possible. This algorithm computes the maximum traffic flow with minimum transport costs for ...
Quanta Magazine

Researchers Achieve ‘Absurdly Fast’ Algorithm for Network Flow

A team of computer scientists has come up with a dramatically faster algorithm for one of the oldest problems in computer science: maximum flow. The problem asks how much material can flow through a ...