CSCN: an efficient snapshot ensemble learning based sparse transformer model for long-range spatial-temporal traffic flow prediction

• Tipo: Artigo em Revista Científica Internacional
• Data: 2025

Autores

Kumar, R (Autor) Outra; João Mendes-Moreira (Autor) FEUP; Chandra, J (Autor) Outra

Revista

Título: Data Mining and Knowledge Discovery

Vol. 39

ISSN: 1384-5810

Editora: Springer Nature

Indexação

ISI Web of Knowledge - 0 Citações

Scopus - 0 Citações

Outras Informações

ID Authenticus: P-018-WTZ

DOI: 10.1007/s10618-025-01104-8

Abstract (EN): Intelligent Transportation Systems aim to alleviate traffic congestion and enhance urban traffic management. Transformer-based methods have shown promise in traffic prediction due to their capability to handle long-range dependencies. However, they disregard local context during parallel processing and can be computationally expensive for large traffic networks. On the other hand, they miss the hierarchical information hidden in regions of large traffic networks. To address these issues, we introduce CSCN, a novel framework that clusters traffic sensors based on data similarity, employs clustered multi-head self-attention for efficient hierarchical pattern learning, and utilizes causal convolutional attention for capturing local temporal trends. In addition to these advancements, we integrate snapshot ensemble learning into CSCN, allowing for the exploitation of diverse snapshots obtained during training to enrich predictive performance. Evaluations of real-world data highlight CSCN's superiority in traffic flow prediction, showcasing its potential for enhancing transportation systems with improved accuracy and efficiency.

Idioma: Inglês

Tipo (Avaliação Docente): Científica

Nº de páginas: 38