Coverage Prediction in Mobile Communication Networks: A Deep Learning Approach With a Tabular Foundation Model DOI
Weiwei Jiang, Ao Liu, Yang Zhang

et al.

Internet Technology Letters, Journal Year: 2025, Volume and Issue: 8(3)

Published: April 29, 2025

ABSTRACT Accurate coverage prediction in mobile communication networks is crucial for optimizing performance and ensuring reliable service. However, traditional methods often struggle with the complexity dynamic nature of wireless environments. This study introduces a novel approach leveraging deep learning model tabular foundation model, TabPFN, which utilizes in‐context transformer‐based architecture to surpass existing techniques. Experimental validation on real‐world dataset demonstrates model's superior accuracy adaptability, outperforming gradient boosting decision trees supervised models terms root mean square error (RMSE), absolute (MAE), coefficient determination ( R 2 ).

Language: Английский

Privacy-preserving approach for IoT networks using statistical learning with optimization algorithm on high-dimensional big data environment DOI Creative Commons
Fatma S. Alrayes, Mohammed Maray, Asma Alshuhail

et al.

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: Jan. 27, 2025

Language: Английский

Citations

0
Federated learning for misbehaviour detection with variational autoencoders and Gaussian mixture models DOI Creative Commons
Enrique Mármol Campos, Aurora González-Vidal, José L. Hernández-Ramos

et al.

International Journal of Information Security, Journal Year: 2025, Volume and Issue: 24(2)

Published: March 12, 2025

Language: Английский

Citations

0
A Lightweight Intrusion Detection System for Internet of Things: Clustering and Monte Carlo Cross-Entropy Approach DOI Creative Commons

Abdulmohsen Almalawi

Sensors, Journal Year: 2025, Volume and Issue: 25(7), P. 2235 - 2235

Published: April 2, 2025

Our modern lives are increasingly shaped by the Internet of Things (IoT), as IoT devices monitor and manage everything from our homes to workplaces, becoming an essential part health systems daily infrastructure. However, this rapid growth in has introduced significant security challenges, leading increased vulnerability cyber attacks. To address these machine learning-based intrusion detection (IDSs)-traditionally considered a primary line defense-have been deployed detect malicious activities networks. Despite this, IDS solutions often struggle with inherent resource constraints devices, including limited computational power memory. overcome limitations, we propose approach enhance efficiency. First, introduce recursive clustering method for data condensation, integrating compactness entropy-driven sampling select highly representative subset larger dataset. Second, adopt Monte Carlo Cross-Entropy combined stability metric features consistently most stable relevant features, resulting lightweight, efficient, high-accuracy IoT-based IDS. Evaluation proposed on three datasets real (N-BaIoT, Edge-IIoTset, CICIoT2023) demonstrates comparable classification accuracy while significantly reducing training testing times 45× 15×, respectively, lowering memory usage 18×, compared competitor approaches.

Language: Английский

Citations

0
Coverage Prediction in Mobile Communication Networks: A Deep Learning Approach With a Tabular Foundation Model DOI
Weiwei Jiang, Ao Liu, Yang Zhang

et al.

Internet Technology Letters, Journal Year: 2025, Volume and Issue: 8(3)

Published: April 29, 2025

ABSTRACT Accurate coverage prediction in mobile communication networks is crucial for optimizing performance and ensuring reliable service. However, traditional methods often struggle with the complexity dynamic nature of wireless environments. This study introduces a novel approach leveraging deep learning model tabular foundation model, TabPFN, which utilizes in‐context transformer‐based architecture to surpass existing techniques. Experimental validation on real‐world dataset demonstrates model's superior accuracy adaptability, outperforming gradient boosting decision trees supervised models terms root mean square error (RMSE), absolute (MAE), coefficient determination ( R 2 ).

Language: Английский

Citations

0