Fine-grained Spatial-temporal MLP Architecture for Metro Origin-Destination Prediction

arXiv:2404.15734v1 Announce Type: new
Abstract: Accurate prediction of metro traffic is crucial for optimizing metro scheduling and enhancing overall transport efficiency. Analyzing fine-grained and comprehensive relations among stations effectively is imperative for metro Origin-Destination (OD) prediction. However, existing metro OD models either mix information from multiple OD pairs from the station's perspective or exclusively focus on a subset of OD pairs. These approaches may overlook fine-grained relations among OD pairs, leading to difficulties in predicting potential anomalous conditions. To address …

abstract architecture arxiv cs.cv efficiency fine-grained however information mlp multiple perspective prediction relations scheduling spatial temporal the station traffic transport type