Recognition Method of Auroral Kilometric Radiation Based on Fusion of VGG16 and Self-attention Mechanism

提出了一种能准确识别极光千米波(Auroral Kilometric Radiation, AKR)的方法, 为进一步研究极光千米波在地球辐射带能量粒子剧烈变化过程中的作用提供支撑. 首先采用VGG16卷积神经网络作为基础模型, 从原始数据中提取出有助于识别AKR的局部特征. 之后引入嵌入VGG16网络的定制化自注意力机制(Self-attention mechanism embedded in VGG network, SAM-V), 该机制有助于捕捉功率谱图中不同时间点或频率上的信号可能存在的关联, 减小其他杂波的影响, 提高识别准确性. 同时, 采用线性学习率预热和动态衰减策略使模型更快地收敛并提高泛化能力. 实验结果表明, 改进后的模型平均识别准确率在93%左右, 比原始VGG16平均提高约3.3%, 并且召回率和精确度等指标均有所改善.

Authors

Publication Details

Journal
Chinese Journal of Space Science
Published
2025-01-01
DOI
https://doi.org/10.11728/cjss2025.03.2024-0043
Primary Topic
Inertial Sensor and Navigation
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Recognition Method of Auroral Kilometric Radiation Based on Fusion of VGG16 and Self-attention Mechanism

Heye WANG, Xuncai Guo, tianyu liu, Sai Zhang et al.
Chinese Journal of Space Science
Inertial Sensor and Navigation
article

Recognition Method of Auroral Kilometric Radiation Based on Fusion of VGG16 and Self-attention Mechanism

Heye WANG, Xuncai Guo, tianyu liu, Sai Zhang, Shuyi Zhao, Yanlin Huang
article en

Abstract

提出了一种能准确识别极光千米波(Auroral Kilometric Radiation, AKR)的方法, 为进一步研究极光千米波在地球辐射带能量粒子剧烈变化过程中的作用提供支撑. 首先采用VGG16卷积神经网络作为基础模型, 从原始数据中提取出有助于识别AKR的局部特征. 之后引入嵌入VGG16网络的定制化自注意力机制(Self-attention mechanism embedded in VGG network, SAM-V), 该机制有助于捕捉功率谱图中不同时间点或频率上的信号可能存在的关联, 减小其他杂波的影响, 提高识别准确性. 同时, 采用线性学习率预热和动态衰减策略使模型更快地收敛并提高泛化能力. 实验结果表明, 改进后的模型平均识别准确率在93%左右, 比原始VGG16平均提高约3.3%, 并且召回率和精确度等指标均有所改善.

Chinese Journal of Space ScienceVol. 45(3)
Openalex Percentile: Top 82%
Inertial Sensor and Navigation
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.