Logo do repositório
 
Publicação

Business Process Remaining Time Prediction Based on Bidirectional QRNN with Attention Mechanism

2026-04Artigo científico Acesso aberto
Ver registo simples
dc.contributor.authorGuo, Na
dc.contributor.authorLu, Ting
dc.contributor.authorLiu, Cong
dc.contributor.authorXu, Xingrong
dc.contributor.authorZeng, Qingtian
dc.contributor.institutionNOVA Information Management School (NOVA IMS)
dc.contributor.institutionInformation Management Research Center (MagIC) - NOVA Information Management School
dc.contributor.pblSocieta Italiana di Istochimica / PAGEPress Publications
dc.date.accessioned2026-04-20T13:36:01Z
dc.date.available2026-04-20T13:36:01Z
dc.date.issued2026-04
dc.descriptionGuo, N., Lu, T., Liu, C., Xu, X., & Zeng, Q. (2026). Business Process Remaining Time Prediction Based on Bidirectional QRNN with Attention Mechanism. Emerging Science Journal, 10(2), 627-637. https://doi.org/10.28991/ESJ-2026-010-02-01
dc.description.abstractBusiness process prediction is essential for monitoring workflows and ensuring service quality. A key task in this area, remaining time prediction, focuses on estimating process duration and has been extensively studied. While Long Short-Term Memory (LSTM)networks are widely adopted, their limited parallelization and sequential modeling capabilities constrain performance. To address these limitations, we propose a remaining time prediction approach based on a bidirectional Quasi-Recurrent Neural Network (QRNN) with an attention mechanism. Specifically, the bidirectional QRNN is employed to construct the prediction model, while the attention mechanism enhances its ability to extract feature information. Next, a transfer training iteration strategy based on different trace prefix lengths is designed to address the imbalance in trace lengths. Then, a Word2Vec-based event representation learning approach is introduced to generate similarity vector of adjacent events, further improving prediction accuracy. Finally, using five publicly real-life event logs, the proposed approach is evaluated against state-of-the-art approaches. Experimental results demonstrate that it improves average prediction accuracy by nearly 15% while reducing average model training time by approximately 26%.en
dc.description.versionpublishersversion
dc.description.versionpublished
dc.format.extent11
dc.format.extent1405039
dc.identifier.doi10.28991/ESJ-2026-010-02-01
dc.identifier.issn2610-9182
dc.identifier.otherPURE: 154798552
dc.identifier.otherPURE UUID: b19e3efd-d479-4bba-98e4-9f56cfc96221
dc.identifier.otherScopus: 105035727950
dc.identifier.urihttp://hdl.handle.net/10362/202375
dc.identifier.urlhttps://www.scopus.com/pages/publications/105035727950
dc.language.isoeng
dc.peerreviewedyes
dc.relationhttps://doi.org/10.54499/UID/04152/2025
dc.relationhttps://doi.org/10.54499/UID/PRR/04152/2025
dc.subjectProcess Mining
dc.subjectRemaining Time Prediction
dc.subjectQuasi-Recurrent Neural Network
dc.subjectRepresentation Learning
dc.subjectGeneral
dc.subjectSDG 9 - Industry, Innovation, and Infrastructure
dc.titleBusiness Process Remaining Time Prediction Based on Bidirectional QRNN with Attention Mechanismen
dc.typejournal article
degois.publication.firstPage627
degois.publication.issue2
degois.publication.lastPage637
degois.publication.titleEmerging Science Journal
degois.publication.volume10
dspace.entity.typePublication
rcaap.rightsopenAccess

Ficheiros

Principais
A mostrar 1 - 1 de 1
Miniatura
Nome:
Business_Process_Remaining_Time_Prediction.pdf
Tamanho:
1.34 MB
Formato:
Adobe Portable Document Format
Ver/Abrir

Coleções

NIMS: MagIC - Artigos em revista internacional com arbitragem científica (Peer-Review articles in international journals)