Next Article in Journal
Multi-Instance Multi-Scale Graph Attention Neural Net with Label Semantic Embeddings for Instrument Recognition
Previous Article in Journal
Vector Signals and Invariant Systems: Re-Tooling Linear Systems Theory
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Signals
Volume 6
Issue 2
10.3390/signals6020029
signals-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

Comparative Analysis of Attention Mechanisms in Densely Connected Network for Network Traffic Prediction

by
Myeongjun Oh
1,
Sung Oh
1,
Jongkyung Im
1,
Myungho Kim
2,
Joung-Sik Kim
2,
Ji-Yeon Park
2,
Na-Rae Yi
2 and
Sung-Ho Bae
1,*
1
Department of Artificial Intelligence, Kyunghee University, 1732, Deogyeong-daero, Giheung-gu, Yongin-si 17104, Republic of Korea
2
Hanwha, 188 Pangyoyeok-ro, Bundang-gu, Seongnam-si 13524, Republic of Korea
*
Author to whom correspondence should be addressed.
Signals 2025, 6(2), 29; https://doi.org/10.3390/signals6020029
Submission received: 28 April 2025 / Revised: 9 June 2025 / Accepted: 11 June 2025 / Published: 19 June 2025
Browse Figures
Versions Notes

Abstract

Recently, STDenseNet (SpatioTemporal Densely connected convolutional Network) showed remarkable performance in predicting network traffic by leveraging the inductive bias of convolution layers. However, it is known that such convolution layers can only barely capture long-term spatial and temporal dependencies. To solve this problem, we propose Attention-DenseNet (ADNet), which effectively incorporates an attention module into STDenseNet to learn representations for long-term spatio-temporal patterns. Specifically, we explored the optimal positions and the types of attention modules in combination with STDenseNet. Our key findings are as follows: i) attention modules are very effective when positioned between the last dense module and the final feature fusion module, meaning that the attention module plays a key role in aggregating low-level local features with long-term dependency. Hence, the final feature fusion module can easily exploit both global and local information; ii) the best attention module is different depending on the spatio-temporal characteristics of the dataset. To verify the effectiveness of the proposed ADNet, we performed experiments on the Telecom Italia dataset, a well-known benchmark dataset for network traffic prediction. The experimental results show that, compared to STDenseNet, our ADNet improved RMSE performance by 3.72%, 2.84%, and 5.87% in call service (Call), short message service (SMS), and Internet access (Internet) sub-datasets, respectively.
Keywords: spatiotemporal data prediction; DenseNet; attention mechanism spatiotemporal data prediction; DenseNet; attention mechanism

Share and Cite

MDPI and ACS Style

Oh, M.; Oh, S.; Im, J.; Kim, M.; Kim, J.-S.; Park, J.-Y.; Yi, N.-R.; Bae, S.-H. Comparative Analysis of Attention Mechanisms in Densely Connected Network for Network Traffic Prediction. Signals 2025, 6, 29. https://doi.org/10.3390/signals6020029

AMA Style

Oh M, Oh S, Im J, Kim M, Kim J-S, Park J-Y, Yi N-R, Bae S-H. Comparative Analysis of Attention Mechanisms in Densely Connected Network for Network Traffic Prediction. Signals. 2025; 6(2):29. https://doi.org/10.3390/signals6020029

Chicago/Turabian Style

Oh, Myeongjun, Sung Oh, Jongkyung Im, Myungho Kim, Joung-Sik Kim, Ji-Yeon Park, Na-Rae Yi, and Sung-Ho Bae. 2025. "Comparative Analysis of Attention Mechanisms in Densely Connected Network for Network Traffic Prediction" Signals 6, no. 2: 29. https://doi.org/10.3390/signals6020029

APA Style

Oh, M., Oh, S., Im, J., Kim, M., Kim, J.-S., Park, J.-Y., Yi, N.-R., & Bae, S.-H. (2025). Comparative Analysis of Attention Mechanisms in Densely Connected Network for Network Traffic Prediction. Signals, 6(2), 29. https://doi.org/10.3390/signals6020029

Article Metrics

Back to TopTop