计算机科学
循环神经网络
稳健性(进化)
规范化(社会学)
雷达
人工智能
利用
人工神经网络
深度学习
数据挖掘
模式识别(心理学)
机器学习
电信
生物化学
化学
计算机安全
社会学
人类学
基因
作者
Paolo Notaro,Magdalini Paschali,Carsten Hopke,David Wittmann,Nassir Navab
出处
期刊:Cornell University - arXiv
日期:2019-01-01
被引量:6
标识
DOI:10.48550/arxiv.1911.07683
摘要
Radar pulse streams exhibit increasingly complex temporal patterns and can no longer rely on a purely value-based analysis of the pulse attributes for the purpose of emitter classification. In this paper, we employ Recurrent Neural Networks (RNNs) to efficiently model and exploit the temporal dependencies present inside pulse streams. With the purpose of enhancing the network prediction capability, we introduce two novel techniques: a per-sequence normalization, able to mine the useful temporal patterns; and attribute-specific RNN processing, capable of processing the extracted information effectively. The new techniques are evaluated with an ablation study and the proposed solution is compared to previous Deep Learning (DL) approaches. Finally, a comparative study on the robustness of the same approaches is conducted and its results are presented.
科研通智能强力驱动
Strongly Powered by AbleSci AI