RT info:eu-repo/semantics/conferenceObject
T1 Online Active Learning For LSTM-Based Network Traffic Prediction
A1 Casaseca de la Higuera, Juan Pablo
A1 Aguiar Pérez, Javier Manuel
A1 Amado Caballero, Patricia
A1 Morgado, Antonio J.
A1 Silva Moreira, Joana da
A1 Luo, Chunbo
A1 Wang, Xinheng
K1 Redes LSTM
K1 Aprendizaje en línea
K1 Aprendizaje activo
K1 Predicción del tráfico de red
AB This paper introduces an online active deep learning framework tailored for intelligent and sustainable aerial-terrestrial IoT networks. The framework utilizes Long Short-Term Memory (LSTM) models, enhanced with active learning and incremental updates, to address the challenges of dynamic network traffic prediction. Model updates are selectively applied, prioritizing samples with higher prediction errors, enabling the system to adapt dynamically to evolving traffic patterns and improving predictive accuracy. The proposed approach accommodates non-stationary data streams and prioritizes critical information, establishing a robust foundation for effective network management. The framework's performance was validated using the Milan traffic dataset, demonstrating its effectiveness compared to non-weighted online learning methods and static models.
PB IEEE Computer Society
SN 978-1-6654-5734-7
YR 2025
FD 2025
LK https://uvadoc.uva.es/handle/10324/78604
UL https://uvadoc.uva.es/handle/10324/78604
LA eng
NO Zhu, Yingbo and Vichare, Parag and Shakir, Muhammad Zeeshan and Sturley, Hamish and Salva-Garcia, Pablo and Salau, Nurudeen. 2025 International Conference on Software, Knowledge, Information Management & Applications (SKIMA). Paisley: United Kingdom, 2025, p. 1-7.
NO Producción Científica
DS UVaDOC
RD 29-nov-2025