Semi-Supervised Multiresolution Classification Using Adaptive Graph Filtering With Application to Indirect Bridge Structural Health Monitoring
Semi-Supervised Multiresolution Classification Using Adaptive Graph Filtering With Application to Indirect Bridge Structural Health Monitoring
复制标题
DOI：
10.1109/tsp.2014.2313528
复制
发表时间：
2014-06-01
影响因子：
5.4
通讯作者：
Kovacevic, Jelena
中科院分区：
文献类型：
--
作者：
Chen, Siheng;Cerda, Fernando;Kovacevic, Jelena
我们提出了一个多分辨率分类框架与半监督学习图与应用程序的间接桥梁结构健康监测。在现实世界的应用中，分类面临着两个主要挑战：可靠的特征可能难以提取，很少有标记的信号可用于训练。我们提出了一种新的分类框架来解决这些问题：我们使用多分辨率框架来处理信号中的非平稳性，并在每个局部时频区域中提取特征，并使用半监督学习来训练标记和未标记的信号。我们进一步提出了一个自适应图滤波器的半监督分类，允许分类未标记以及看不见的信号，并纠正错误标记的信号。我们验证了间接桥梁结构健康监测的建议框架，并表明它的性能显着优于以前的方法。
We present a multiresolution classification framework with semi-supervised learning on graphs with application to the indirect bridge structural health monitoring. Classification in real-world applications faces two main challenges: reliable features can be hard to extract and few labeled signals are available for training. We propose a novel classification framework to address these problems: we use a multiresolution framework to deal with nonstationarities in the signals and extract features in each localized time-frequency region and semi-supervised learning to train on both labeled and unlabeled signals. We further propose an adaptive graph filter for semi-supervised classification that allows for classifying unlabeled as well as unseen signals and for correcting mislabeled signals. We validate the proposed framework on indirect bridge structural health monitoring and show that it performs significantly better than previous approaches.