Multi-Band Spectrum Prediction Algorithm Based on HGCN and Simplified ReLU-GRU

The increasing scarcity of spectrum resources, coupled with rising demand, has made effective spectrum management crucial. However, the complexity and spatio-temporal variability of spectral data present significant challenges for accurate spectrum prediction. This paper proposes a novel multi-band spectrum prediction model that integrates a hypergraph convolutional neural network (HGCN) with a simplified rectified linear unit-gated recurrent unit (ReLU-GRU) network which eliminate the reset gate. In this framework, the HGCN employs hypergraphs to represent spectral data, where nodes correspond to individual frequency bands and hyperedges capture multivariate relationships among them. The simplified ReLU-GRU is used to model the temporal dependencies between frequency bands, effectively fusing the extracted features for enhanced prediction performance. By replacing the traditional hyperbolic tangent (tanh) activation function with a linear rectification function (ReLU) in the state update process, the model mitigates the issue of gradient vanishing and accelerates the training process. To further improve convergence, an attention mechanism is incorporated to weight the output of hidden states. Experimental evaluation on a real-world spectral dataset from sensors in St. Gallen demonstrates that the proposed model achieves a 4.43% improvement in prediction accuracy compared to the traditional LSTM model and a 0.56% improvement over the GCN-GRU model, exhibiting superior stability. The results also show that the simplified ReLU-GRU is particularly effective in predicting highly variable data, outperforming the traditional tanh-GRU, especially in scenarios with significant fluctuations.

• Publication year

  2026

• Venue

  IEEE Transactions on Cognitive Communications and Networking

• Publication date

  Unknown publication date

• Fields of study

  Computer Science, Engineering

• Identifiers
  DOI 10.1109/TCCN.2026.3657092
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• A-GCRNN: Attention Graph Convolution Recurrent Neural Network for Multi-Band Spectrum Prediction

  2024cited by this paper
• An Autoformer-CSA Approach for Long-Term Spectrum Prediction

  2023cited by this paper
• Joint Multidimensional Pattern for Spectrum Prediction Using GNN

  2023cited by this paper
• RFML-Driven Spectrum Prediction: A Novel Model-Enabled Autoregressive Network

  2022cited by this paper
• Knowledge Graph Completion Based on GCN of Multi-Information Fusion and High-Dimensional Structure Analysis Weight

  2022cited by this paper
• Study of Spectrum Prediction Techniques in Cognitive Radio Networks

  2022cited by this paper
• Multi channel spectrum prediction algorithm based on GCN and LSTM

  2022cited by this paper
• Intelligent Spectrum Occupancy Prediction for Realistic Measurements: GRU based Approach

  2022cited by this paper
• Graph Self-Supervised Learning: A Survey

  2021cited by this paper
• Large-scale real-world radio signal recognition with deep learning

  2021cited by this paper
• Graph Convolutional Neural Network for Human Action Recognition: A Comprehensive Survey

  2021cited by this paper
• A Temporal-Spatial Spectrum Prediction Using the Concept of Homotopy Theory for UAV Communications

  2021cited by this paper
• Spectrum prediction based on GAN and deep transfer learning: A cross-band data augmentation framework

  2021cited by this paper
• SR2CNN: Zero-Shot Learning for Signal Recognition

  2020cited by this paper
• Temporal Multi-Graph Convolutional Network for Traffic Flow Prediction

  2020cited by this paper
• View-GCN: View-Based Graph Convolutional Network for 3D Shape Analysis

  2020cited by this paper
• Spectrum Prediction Method for ISM Bands Based on LSTM

  2020cited by this paper
• Contour Stella Image and Deep Learning for Signal Recognition in the Physical Layer

  2020cited by this paper
• Deep Learning Aided Spectrum Prediction for Satellite Communication Systems

  2020cited by this paper
• Hypergraph Convolution and Hypergraph Attention

  2019cited by this paper
• A Comprehensive Survey on Graph Neural Networks

  2019cited by this paper
• Cross-Modality Microblog Sentiment Prediction via Bi-Layer Multimodal Hypergraph Learning

  2019cited by this paper
• Convolutional LSTM-based Long-Term Spectrum Prediction for Dynamic Spectrum Access

  2019cited by this paper
• T-GCN: A Temporal Graph Convolutional Network for Traffic Prediction

  2018cited by this paper
• Graph Neural Networks: A Review of Methods and Applications

  2018cited by this paper
• Hypergraph Neural Networks

  2018influential reference
• Electrosense: Open and Big Spectrum Data

  2017cited by this paper
• Improving Speech Recognition by Revising Gated Recurrent Units

  2017cited by this paper
• Spectrum prediction via long short term memory

  2017cited by this paper
• Learning Convolutional Neural Networks for Graphs

  2016cited by this paper
• On the limits of predictability in real-world radio spectrum state dynamics: from entropy theory to 5G spectrum sharing

  2015cited by this paper
• Multimodal hypergraph learning for microblog sentiment prediction

  2015cited by this paper
• DeepWalk: online learning of social representations

  2014cited by this paper
• Spectral Networks and Locally Connected Networks on Graphs

  2013cited by this paper
• An autoregressive approach for spectrum occupancy modeling and prediction based on synchronous measurements

  2011cited by this paper
• ]Video object segmentation by hypergraph cut

  2009cited by this paper
• Bidirectional recurrent neural networks

  1997cited by this paper

• No citing papers are available for this paper.