Zero-Shot Dynamic Neural Network Adaptation in Tactical Wireless Systems
Zero-Shot Dynamic Neural Network Adaptation in Tactical Wireless Systems
复制标题
DOI：
10.1109/milcom58377.2023.10356318
复制
发表时间：
2023-10
期刊：
影响因子：
--
通讯作者：
Shahriar Rifat;Jonathan Ashdown;K. Turck;Francesco Restuccia
中科院分区：
文献类型：
--
作者：
Shahriar Rifat;Jonathan Ashdown;K. Turck;Francesco Restuccia
基于深度神经网络的模型在无线领域的众多应用中引起了人们的兴趣，包括频谱智能、调制识别和无线电指纹识别等。一个关键的挑战，目前抑制了这种模型在现实世界的战术场景中的应用是，它们的性能从根本上改变不断变化的动态无线信道条件。现有的工作通过使用尽可能少的样本进行有效的微调或调整来解决这个问题。然而，在这个过程中涉及到一些关于新条件的先验知识。在本文中，我们首次提出了零触发动态神经网络自适应（zDNA）（即，没有任何额外的训练样本）。具体来说，我们表明，通过只改变仿射变换参数和归一化的学习功能，在不同层的神经网络在一个在线的方式没有任何标记的样本，我们可以实现上级性能的动态条件。我们提出的方法在公开可用的RadioML 2018.01A数据集上进行了评估，以测试其对动态变化的信噪比（SNR）条件的适应性。在所有看不见的测试场景中的性能改进一致性（在低SNR状态下高达24%）证明了我们的框架在现实环境中的适用性。
Models based on deep neural networks have attracted interest in a myriad of applications in the wireless landscape, including spectrum intelligence, modulation recognition, and radio fingerprinting, among others. One key challenge that is currently inhibiting the application of such models in real-world tactical scenarios is that their performance radically changes with continuously changing dynamic wireless channel conditions. Existing work tackle this by performing efficient fine-tuning or adaptation using as few samples as possible. However, some prior knowledge about the new conditions is involved in the process. In this paper, we propose for the first time zero-shot dynamic neural network adaptation (zDNA) (i.e., without any additional training samples) of wireless classification models after deployment in unseen conditions. Specifically, we show that by changing only the affine transformation parameters and normalizing the learned features in different layers of the neural network in an online manner without any labeled samples, we can achieve superior performance in dynamic conditions. Our proposed approach is evaluated on the publicly available RadioML 2018.01A dataset, to test its adaptability to dynamically changing signal-to-noise ratio (SNR) conditions. Performance improvement consistency in all unseen test scenarios (up to 24% in low SNR regime) demonstrates the applicability of our framework in real-world contexts.