空间科学学报2025，Vol.45Issue(3)：677-688,12.DOI:10.11728/cjss2025.03.2024-0043
基于VGG16与自注意力机制融合的极光千米波识别
Recognition Method of Auroral Kilometric Radiation Based on Fusion of VGG16 and Self-attention Mechanism
王鹤野 1郭雪豆 1张赛 1黄泱泱 1刘天乐 2赵舒雅1
作者信息
- 1. 长沙理工大学物理与电子科学学院 长沙 410114
- 2. 长沙理工大学电气与信息工程学院 长沙 410114
- 折叠
摘要
Abstract
An enhanced image recognition algorithm for Auroral Kilometric Radiation(AKR)detec-tion is presented by integrating a self-attention mechanism into the VGG16 Convolutional Neural Net-work(CNN)architecture.The primary goal is to improve the flexibility and detection accuracy of AKR identification,which is crucial for understanding the dynamic changes in Earth's radiation belts and the associated energetic particle variations.The methodology begins with employing the VGG16 CNN as the foundational model to extract local features from raw data that are instrumental in AKR recognition.Subsequently,a custom Self-Attention Mechanism(SAM-V)is embedded in the VGG network.The Self-Attention Mechanism(SAM),originally designed for sequential data processing,is adapted to work with the VGG16 network.Traditional integration of SAM with VGG16 could potentially increase the model's complexity and computational cost,leading to potential feature sparsity issues.However,the proposed custom SAM-V generates queries,keys,and values through defined convolutional layers,offering more control over feature input and output.This customization implies shared parameters,reducing the num-ber of model parameters,thereby mitigating the risk of overfitting and enhancing the model's generaliza-tion capabilities.This approach is particularly adept at capturing correlations in power spectral density across different time points or frequencies,minimizing the impact of noise and improving recognition ac-curacy.Additionally,a linear learning rate warm-up and dynamic decay strategy are employed to accel-erate model convergence and enhance generalization.The experimental results demonstrate that the im-proved model achieves an average recognition accuracy of approximately 93%,which represents a 3.3%increase compared to the original VGG16 model.Furthermore,other performance metrics such as recall rate and precision have also seen significant improvements.In conclusion,the integration of a custom self-attention mechanism into the VGG16 network has yielded a more efficient and accurate model for AKR detection.This advancement not only bolsters the study of auroral kilometric radiation but also has broader implications for the analysis of Earth's radiation belt dynamics and energetic particle behav-ior.The model's enhanced generalization capabilities and improved accuracy underscore the potential for applying similar techniques to other image recognition tasks within the field of space physics and be-yond.关键词
VGG16卷积神经网络/自注意力机制/极光千米波/学习率策略Key words
VGG16 convolutional neural network/Self-attention mechanism/Auroral kilometric radiation/Learning rate policy分类
信息技术与安全科学引用本文复制引用
王鹤野,郭雪豆,张赛,黄泱泱,刘天乐,赵舒雅..基于VGG16与自注意力机制融合的极光千米波识别[J].空间科学学报,2025,45(3):677-688,12.
