arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2010.00178cs.LGeess.SP
收藏

深度学习射频系统的训练数据增强

Training Data Augmentation for Deep Learning Radio Frequency Systems

Ted and Karyn Hume Center for National Security and Technology(特德与卡琳·休姆国家安全与技术中心);Adapdix Corporation(Adapdix公司)

William H. Clark, Steven Hauser, William C. Headley, Alan J. Michaels

摘要:

机器学习的应用受三个主要组成部分的影响,这些组成部分对最终的性能指标有贡献。在神经网络的范畴内,特别是深度学习,前两个是正在训练的模型的架构和使用的训练方法。这项工作的重点是第三个组成部分,在训练过程中使用的数据。出现的主要问题是“数据中有什么”和“数据中有什么重要的?”将自动调制分类(AMC)的射频机器学习(RFML)领域作为用于态势感知的工具的一个示例,对合成、捕获和增强数据的使用进行检查和比较,以提供关于实现所需性能水平所需的可用数据的数量和质量的见解。在这项工作中讨论了三个问题:(1)在不考虑合成内的环境的情况下部署合成训练系统时,预计该系统有多有用,(2)如何在RFML域中利用增强,以及最后,(3)传输信道引起的信号退化的影响知识对系统的性能有什么贡献。一般来说,每个被检查的数据类型都对最终应用程序有有用的贡献,但是与预期用例密切相关的捕获数据将始终提供更重要的信息并实现最大的性能。尽管捕获的数据有很多好处,但实时收集所带来的困难和成本往往使实现峰值性能所需的数据量变得不切实际。本文有助于量化真实数据和合成数据之间的平衡,提供具体的例子,其中训练数据的大小和来源参数变化。

英文摘要:

Applications of machine learning are subject to three major components that contribute to the final performance metrics. Within the category of neural networks, and deep learning specifically, the first two are the architecture for the model being trained and the training approach used. This work focuses on the third component, the data used during training. The primary questions that arise are ``what is in the data'' and ``what within the data matters?'' Looking into the Radio Frequency Machine Learning (RFML) field of Automatic Modulation Classification (AMC) as an example of a tool used for situational awareness, the use of synthetic, captured, and augmented data are examined and compared to provide insights about the quantity and quality of the available data necessary to achieve desired performance levels. There are three questions discussed within this work: (1) how useful a synthetically trained system is expected to be when deployed without considering the environment within the synthesis, (2) how can augmentation be leveraged within the RFML domain, and lastly, (3) what impact knowledge of degradations to the signal caused by the transmission channel contributes to the performance of a system. In general, the examined data types each have useful contributions to a final application, but captured data germane to the intended use case will always provide more significant information and enable the greatest performance. Despite the benefit of captured data, the difficulties and costs that arise from live collection often make the quantity of data needed to achieve peak performance impractical. This paper helps quantify the balance between real and synthetic data, offering concrete examples where training data is parametrically varied in size and source.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑