Boost Spectrum Prediction With Temporal-Frequency Fusion Network via Transfer Learning
Boost Spectrum Prediction With Temporal-Frequency Fusion Network via Transfer Learning
复制标题
通过迁移学习利用时频融合网络增强频谱预测
DOI：
10.1109/tmc.2021.3136941
复制
发表时间：
2023-06-01
影响因子：
7.9
通讯作者：
He, Shibo
中科院分区：
文献类型：
--
作者：
Li, Kehan;Li, Chao;He, Shibo
而无线电频谱预测对于频谱共享和异常检测等频谱管理至关重要。然而，由于频谱内和外部因素的干扰，精确的频谱预测是具有挑战性的。为了解决这些复杂的内部和外部相关性，我们开发了一个名为TF（2）AN的模型，该模型由三个部分组成：1）基于图像处理的鲁棒信号检测算法，2）基于注意力的长短期记忆网络，以捕获时频相关性，3）考虑异质外部因素的广义融合模块。该结构在单站观测数据充足的情况下，对频谱预测具有显著的效果。但是，当单站导出的数据不足时，深度学习模型的性能就会下降很多。考虑到在实践中部署了多个监测站，新的挑战变成了如何通过利用来自多个站或频带的数据来增强我们的模型。因此，我们进一步提出了T-TF（2）AN，这是一个基于迁移学习的框架，用于频谱预测中的数据增强和知识共享。与TF（2）AN相比，该算法具有更好的性能.此外，还讨论了模型的可解释性和训练效率分别通过两个案例研究。
and predicting the radio spectrum is vital for spectrum management, such as spectrum sharing and anomaly detection. Nevertheless, the precise spectrum prediction is challenging due to the interference from both intra-spectrum and external factors. To tackle these complex internal and external correlations, we develop a model named TF(2)AN, consisting of three components: 1) a robust signal detection algorithm based on image processing, 2) an attention-based Long Short-term Memory network to capture the temporal-frequency correlations, 3) a generalized fusion module to take the heterogeneous external factors into account. This structure shows prominent effectiveness for spectrum prediction on a single monitoring station with sufficient data. However, when the data derived from a single station is insufficient, the performance of the deep learning model will decline a lot. Considering that more than one monitoring station is deployed in practice, the new challenge becomes how to enhance our model by leveraging the data from multiple stations or frequency bands. Therefore, we further propose T-TF(2)AN, a transfer learning-based framework for data augmentation and knowledge sharing in spectrum prediction. Compared to TF(2)AN, better performance is achieved. Besides, the model interpretability and training efficiency are also discussed with two case studies, respectively.