Estimation of Deterioration Levels of Transmission Towers via Deep Learning Maximizing Canonical Correlation Between Heterogeneous Features
Estimation of Deterioration Levels of Transmission Towers via Deep Learning Maximizing Canonical Correlation Between Heterogeneous Features
复制标题
DOI：
10.1109/jstsp.2018.2849593
复制
发表时间：
2018-08-01
影响因子：
7.5
通讯作者：
Haseyama, Miki
中科院分区：
文献类型：
--
作者：
Maeda, Keisuke;Takahashi, Sho;Haseyama, Miki
本文介绍了通过深度学习最大化异质特征之间规范相关性的估计，估计了传输塔的恶化水平。在提出的方法中，我们新构建了一个基于局部接收场（LRF）的相关性最大程度地使深度学习机器（CMDELM）。对于准确的恶化水平估计，有必要获得有效代表恶化水平的语义信息。但是，由于传输塔的训练数据量很小，因此很难使用许多隐藏的图层（例如一般深度学习方法）执行特征转换。在CMDELM-LRF中，新插入了一个隐藏的层，它最大化了视觉特征和从检查文本数据获得的文本特征之间的规范相关性。具体而言，通过使用最大化规范相关性作为隐藏层的权重参数获得的投影，可以实现用于提取语义信息的特征转换，而无需设计许多隐藏的图层。这是本文的主要贡献。因此，CMDELM-LRF从少量训练数据中实现了准确的恶化水平估计。
This paper presents estimation of deterioration levels of transmission towers via deep learning maximizing the canonical correlation between heterogeneous features. In the proposed method, we newly construct a correlation-maximizing deep extreme learning machine (CMDELM) based on a local receptive field (LRF). For accurate deterioration level estimation, it is necessary to obtain semantic information that effectively represents deterioration levels. However, since the amount of training data for transmission towers is small, it is difficult to perform feature transformation by using many hidden layers such as general deep learning methods. In CMDELM-LRF, one hidden layer, which maximizes the canonical correlation between visual features and text features obtained from inspection text data, is newly inserted. Specifically, by using projections obtained by maximizing the canonical correlation as weight parameters of the hidden layer, feature transformation for extracting semantic information is realized without designing many hidden layers. This is the main contribution of this paper. Consequently, CMDELM-LRF realizes accurate deterioration level estimation from a small amount of training data.