A time-frequency feature prediction network for time-varying radio frequency interference
Open Access
- 1 June 2023
- journal article
- research article
- Published by EDP Sciences in Xibei Gongye Daxue Xuebao/Journal of Northwestern Polytechnical University
- Vol. 41 (3) , 587-594
Abstract
The time-varying radio frequency interference has strong nonlinear dynamic characteristics, which is difficult to be predicted by linear method effectively, making the anti-interference decision without sufficient information support. To solve this problem, a recurrent neural network for spectrum prediction based on time-frequency correlation features is proposed. A sliding window is used to characterize the two-dimensional correlation of time-frequency series, and the spectrum prediction problem is transformed into a problem similar to spatiotemporal sequence prediction. A gradient bridge structure across time frames is added to reduce the attenuation of the gradient in the long time and multi-level network propagation. The training efficiency and network performance are improved by the loss function with better matching. Simulation and experimental results verify the validity of the network prediction results. 时变射频干扰非线性强, 难以用线性方法进行有效预测, 进而使抗干扰决策缺少信息支撑。针对该问题提出了基于时频相关特征的频谱预测递归神经网络, 通过滑窗模型表征时频序列的二维相关性, 将频谱预测问题转化为类似于空时序列预测的问题, 增加跨时间帧的梯度桥结构以减轻梯度在长时间、多层级网络传播时的衰减现象, 用匹配性更高的损失函数提高训练效率和网络性能。仿真和实验结果验证了该网络预测结果的有效性。Keywords
This publication has 12 references indexed in Scilit:
- Reweighted Tensor Factorization Method for SAR Narrowband and Wideband Interference Mitigation Using Smoothing Multiview Tensor ModelIEEE Transactions on Geoscience and Remote Sensing, 2020
- Convolutional LSTM-based Long-Term Spectrum Prediction for Dynamic Spectrum Access2019
- A Novel Tensor Technique for Simultaneous Narrowband and Wideband Interference Suppression on Single-Channel SAR SystemIEEE Transactions on Geoscience and Remote Sensing, 2019
- Avoidance of Time-Varying Radio Frequency Interference With Software-Defined Cognitive RadarIEEE Transactions on Aerospace and Electronic Systems, 2018
- High Range Resolution Profile Estimation via a Cognitive Stepped Frequency TechniqueIEEE Transactions on Aerospace and Electronic Systems, 2018
- Spectrum availability prediction in cognitive aerospace communications: A deep learning perspective2017
- Cognitive radars in spectrally dense environmentsIEEE Aerospace and Electronic Systems Magazine, 2016
- WBI Suppression for SAR Using Iterative Adaptive MethodIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2015
- Convolutional neural networks at constrained time cost2015
- Sparse models and sparse recovery for ultra-wideband SAR applicationsIEEE Transactions on Aerospace and Electronic Systems, 2014