返回
Binder Identification Using Pattern Recognition on Phantom Measurements
DOI:10.1109/TIM.2015.2505983.png)
摘要
En 中文
This paper proposes an automatic method for the identification of twisted pairs (TPs) sharing the same binder, based on the analysis of phantom circuit measurements. This type of circuit is often used for improving data transmission rates in communication systems, but in this paper, phantoming is used to reveal if a four-wire loop composed of two TPs is close enough and well balanced in order to be considered in the same binder. The method uses four features extracted from scattering parameter measures in phantom-mode between two TPs. These features are related to the presence of periodicities and impedance mismatch between the measurement device and the four-wire transmission line. The identification is done via application of two pattern recognition techniques, support vector machines and K-means, on scattering parameter obtained from the phantom-mode measurement of two TPs. This paper also describes a method to determine the length of the two TPs that share the same binder. Laboratory results confirm the accuracy of the proposed methods.
Keyword:
Binder identification
digital subscriber line (DSL)
K-means
phantom-mode measurement
support vector machine (SVM)
AI总结
对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
5.9
论文数:
1.9W
被引数:
5.8W

