基于图注意力网络的半监督SAR舰船目标检测

基于深度学习的合成孔径雷达(SAR)舰船目标检测近年得到了快速发展。然而,传统有监督学习需要大量的标记样本来训练网络。针对此问题,该文提出一种基于图注意力网络(GAT)的半监督SAR舰船目标检测方法。首先,设计了对称卷积神经网络用于海陆分割。随后,完成超像素分割并将超像素块建模为GAT的节点,利用感兴趣区域池化层提取节点的多尺度特征。GAT采用注意力机制自适应地汇聚邻接节点特征实现对无标记节点的分类。最后,将预测为舰船目标的超像素块定位到SAR图像中并获得精细检测结果。在实测高分辨SAR图像数据集上验证了所提方法。结果表明该方法可以在少量标记样本下,以低虚警率实现对舰船目标的可靠检测。     

基于弱关联挖掘技术的电网故障自动诊断研究

针对电网故障进行诊断的过程中,故障信息存在不完整或不确定性,甚至存在关键信息丢失的情况,造成故障诊断难以得出正确结论的问题,提出一种基于弱关联挖掘技术的电网故障自动诊断方法。首先进行支持度计算,得到电网故障的表述参数,并将电网故障类别看作是贝叶斯网络的父节点,将挖掘的弱关联规则作为子节点,构建基于弱关联挖掘的贝叶斯网络模型,对各父节点的先验概率及各子节点的条件概率进行计算,完成对电网故障的自动诊断。仿真实验结果表明,采用所提方法对电网故障进行自动诊断,正确性高,容错性好,实用性强,具有很高的诊断精度。     

标签传播算法在社会网络中的应用研究

近年来,社会网络簇结构挖掘取得了长足的进展,广泛应用在社会网、生物网和万维网等领域中。如何挖掘社会网络中各种潜在结构和信息成为研究热点。标签传播算法是一种能够利用少量已标记节点的标签信息去预测大量的未标记节点的标签的半监督学习算法。介绍了标签传播算法理论,给出了标签算法的特点,总结了标签传播算法在社会网络中的应用及发展趋势。     

子网络级模拟故障诊断的神经网络实现

利用容差模拟电路节点电压灵敏度序列守恒定理,得到了模拟电路元件的软、硬故障统一样本。然后利用统一样本集训练BP神经网络,并将神经网络用于子网络级模拟故障诊断。实例验证表明,软、硬故障统一样本集使得用于神经网络训练所需样本数目大大减少,但经过训练的神经网络可以诊断容差模拟电路的全部软、硬故障,而且诊断正确率较高。     

一种基于SLS_SVM的滚动轴承故障诊断方法

为提高滚动轴承故障诊断分类器的训练正确率,以及缩短训练时间,根据其训练集即含有标签样本,也含有无标签样本的特点,将LS_SVM与半监督学习相结合,充分利用训练集中的有效信息,给出一种基于SLS_SVM的滚动轴承故障诊断方法。将该方法与标准SVM和半监督学习SVM方法相比,其不但能提高训练正确率,也能缩短训练所需时间。通过诊断试验,验证了该算法的有效性以及高效性。     

基于迁移BN-CNN框架的小样本工业过程故障诊断

针对工业故障诊断过程中训练样本不足导致的诊断性能低下问题，文中以迁移学习和深度学习方法为基础，提出一种迁移BN-CNN(Batch Normalization-Convolutional Neural Network)框架。为了减少网络对初始化方法的依赖，在卷积神经网络中引入批归一化层，对网络的隐藏层进行归一化处理。针对目标域标签数据不充足问题，通过基于样本的迁移学习方法扩充目标域的标记数据量，引入基于模型的迁移学习方法，通过充足的源域数据预训练BN-CNN网络，并利用数据量扩充后的目标域微调该网络部分参数，降低了少量样本训练深度神经网络的难度，得到了更适合目标域的故障诊断模型。采用TE工业数据集对该方法进行对比验证，实验结果表明，文中所提方法对于小样本工业过程故障具有较好的诊断性能，其平均精度值为0.804。     

基于CS-LSTM-attention的轴承故障诊断

作为旋转机械设备的常用部件,轴承容易受到损伤而影响整个机械设备的运行,因此对其进行故障监测和诊断十分重要。轴承振动信号是一种时间序列数据,基于卷积神经网络的故障诊断模型对时序特征的提取具有局限性。针对上述问题,文中提出了一种基于卷积神经网络(CNN)、改进长短时记忆神经网络(LSTM)和注意力机制(Attention)的轴承故障诊断模型。首先,利用卷积神经网络初步提取经小波变换处理后的时频数据的特征,对数据等段均分后输入LSTM,进一步提取时序特征,再加入Attention模块对不同时刻的特征进行权重参数学习,最后结合全连接层与激活函数完成故障诊断。     

基于图卷积半监督学习的论文作者同名消歧方法研究

为解决学者与成果的精确匹配问题,该文提出了一种基于图卷积半监督学习的论文作者同名消歧方法。该方法使用SciBERT预训练语言模型计算论文题目、关键字获得论文节点语义表示向量,利用论文的作者和机构信息获得论文的合作网络和机构关联网络邻接矩阵,并从论文合作网络中采集伪标签获得正样本集和负样本集,将这些作为输入利用图卷积神经网络进行半监督学习,获得论文节点嵌入表示进行论文节点向量聚类,实现对论文作者同名消歧。实验结果表明,与其他消歧方法相比,该方法在实验数据集上取得了更好的效果。     

基于半监督生成对抗网络的乳腺癌图像分类

本文针对仅有少量带标签样本时如何提高大量未标 注样本分类的的鲁棒性和准确性问题,提出一种 基于改进的半监督生成对抗网络(semi-supvised generative adversarial networks,SGAN) 的乳腺癌图像分类方法。该方法在输出层使用Softmax 函数 替代 Sigmoid 函数实现多分类。首先将随机向量输入到生成网络中,生成伪样本并标记为伪样本 类进行训 练。接着将真实标签样本、真实无标签样本和伪样本输入到判别网络中,输出为不同类概率 值;然后采 用半监督训练方法反向传播更新参数;最后实现对乳腺癌病理图像的分类,标注样本数量分 别为25、 50和200,最终准 确率达到95.5%。实验结果表明,当标注 样本有限时,本文算法的准确 率具有良好 的鲁棒性。本文算法相比于使用卷积神经网络和迁移学习(tranfer learning,TL)等分类方法准确率有了显著提高。     

基于BP神经网络的大规模电路模块级故障快速诊断方法

根据大规模电路故障诊断网络撕裂法和交叉撕裂搜索方法,采用基于误差反向传播算法的多层前向神经网络(BP神经网络)记载多次撕裂信息,提出了一种新型基于BP神经网络的大规模电路模块级快速诊断方法。该方法能快速有效地并行处理定位故障模块,具有测前工作量小,实时诊断性强等优点。     

A novel semi-supervised canonical correlation analysis and extensions for multi-view dimensionality reduction

Canonical correlation analysis (CCA) is an efficient method for dimensionality reduction on two-view data. However, as an unsupervised learning method, CCA cannot utilize partly given label information in multi-view semi-supervised scenarios. In this paper, we propose a novel two-view semi-supervised learning method, called semi-supervised canonical correlation analysis based on label propagation (LPbSCCA). LPbSCCA incorporates a new sparse representation based label propagation algorithm to infer label information for unlabeled data. Specifically, it firstly constructs dictionaries consisting of all labeled samples; and then obtains reconstruction coefficients of unlabeled samples using sparse representation technique; at last, by combining given labels of labeled samples, estimates label information for unlabeled ones. After that, it constructs soft label matrices of all samples and probabilistic within-class scatter matrices in each view. Finally, in order to enhance discriminative power of features, it is formulated to maximize the correlations between samples of the same class from cross views, while minimizing within-class variations in the low-dimensional feature space of each view simultaneously. Furthermore, we also extend a general model called LPbSMCCA to handle data from multiple (more than two) views. Extensive experimental results from several well-known datasets demonstrate that the proposed methods can achieve better recognition performances and robustness than existing related methods.     

基于三元采样图卷积网络的半监督遥感图像检索

该文提出了一种基于三元采样图卷积网络的度量学习方法,以实现遥感图像的半监督检索。所提方法由三元图卷积网络(TGCN)和基于图的三元组采样(GTS)两部分组成。TGCN由3个具有共享权重的并行卷积神经网络和图卷积网络组成,用以提取图像的初始特征以及学习图像的图嵌入。通过同时学习图像特征以及图嵌入,TGCN能够得到用于半监督图像检索的有效图结构。接着,通过提出的GTS算法对图结构内隐含的图像相似性信息进行评价,以选择合适的困难三元组(Hard Triplet),并利用困难三元组组成的样本集合对模型进行有效快速的模型训练。通过TGCN和GTS的组合,提出的度量学习方法在两个遥感数据集上进行了测试。实验结果表明,TGCN-GTS具有以下两方面的优越性：TGCN能够根据图像及图结构学习到有效的图嵌入特征及度量空间;GTS有效评估图结构内隐含的图像相似性信息选择合适的困难三元组,显著提升了半监督遥感图像检索效果。     

类不均衡的半监督高斯过程分类算法

针对传统的监督学习方法难以解决真实数据集标记信息少、训练样本集中存在类不均衡的问题,提出了类不均衡的半监督高斯过程分类算法。算法引入自训练的半监督学习思想,结合高斯过程分类算法计算后验概率,向未标记数据中注入类标记以获得更多准确可信的标记数据,使得训练样本的类分布相对平衡,分类器自适应优化以获得较好的分类效果。实验结果表明,在类不均衡的训练样本及标记信息过少的情况下,该算法通过自训练分类器获得了有效标记,使分类精度得到了有效提高,为解决类不均衡数据分类提供了一个新的思路。     

Weakly supervised learning based on hypergraph manifold ranking

Significant challenges still remain despite the impressive recent advances in machine learning techniques, particularly in multimedia data understanding. One of the main challenges in real-world scenarios is the nature and relation between training and test datasets. Very often, only small sets of coarse-grained labeled data are available to train models, which are expected to be applied on large datasets and fine-grained tasks. Weakly supervised learning approaches handle such constraints by maximizing useful training information in labeled and unlabeled data. In this research direction, we propose a weakly supervised approach that analyzes the dataset manifold to expand the available labeled set. A hypergraph manifold ranking algorithm is exploited to represent the contextual similarity information encoded in the unlabeled data and identify strong similarity relations, which are taken as a path to label expansion. The expanded labeled set is subsequently exploited for a more comprehensive and accurate training process. The proposed model was evaluated jointly with supervised and semi-supervised classifiers, including Graph Convolutional Networks. The experimental results on image and video datasets demonstrate significant gains and accurate results for different classifiers in diverse scenarios.     

基于改进CNN的轴承声学故障诊断

针对轴承振动信号在复杂机械中难采集和跨转速域工况下传统故障诊断方法精度低的问题,文中提出了一种基于Teager能量算子和卷积神经网络的滚动轴承声学故障诊断方法,即TEO-CNN。将轴承声学信号的Teager能量算子作为模型的输入,使用卷积神经网络学习输入的抽象特征,并结合全局平均池化层和全连接层实现轴承健康状态识别。模型验证基于轴承声学实验数据,并通过构建不同的轴承声学数据集模拟跨转速域工况。试验结果表明,与传统卷积神经网络和机器学习模型相比,TEO-CNN表现出明显的优势,并且在跨转速域工况下的预测精度始终高于95%。     

Graph-based semi-supervised learning with multiple labels

Conventional graph-based semi-supervised learning methods predominantly focus on single label problem. However, it is more popular in real-world applications that an example is associated with multiple labels simultaneously. In this paper, we propose a novel graph-based learning framework in the setting of semi-supervised learning with multiple labels. This framework is characterized by simultaneously exploiting the inherent correlations among multiple labels and the label consistency over the graph. Based on the proposed framework, we further develop two novel graph-based algorithms. We apply the proposed methods to video concept detection over TRECVID 2006 corpus and report superior performance compared to the state-of-the-art graph-based approaches and the representative semi-supervised multi-label learning methods.     

基于LMD和Fisher判别的风力发电机组齿轮箱滚动轴承故障诊断方法

风力发电机组齿轮箱等旋转机械故障振动信号具有调制特征,因此有针对性地提出了一种基于局部均值分解(Local Mean Decomposition,LMD)和Fisher判别的故障诊断方法。首先对振动信号进行LMD分解,可得若干个的乘积函数(Product Function,PF)分量,以相关系数为依据进行PF分量筛选和信号重构,并对重构信号进行故障特征提取,然后以多组典型故障样本的特征量来训练得到Fisher判别式,最后利用判别式对待判样本进行分类,由判别结果可知滚动轴承的工作状态、故障部位及故障程度。分析从试验台采集的各类故障样本集和从某实际风场监测的数据,证明了所提取故障特征量的准确性,同时也验证了所提出方法在旋转机械故障诊断方面的有效性。     

Semi-supervised learning on large-scale geotagged photos for situation recognition

Photos are becoming spontaneous, objective, and universal sources of information. This paper explores evolving situation recognition using photo streams coming from disparate sources combined with the advances of deep learning. Using visual concepts in photos together with space and time information, we formulate the situation detection into a semi-supervised learning framework and propose new graph-based models to solve the problem. To extend the method for unknown situations, we introduce a soft label method that enables the traditional semi-supervised learning framework to accurately predict predefined labels as well as effectively form new clusters. To overcome the noisy data which degrades graph quality, leading to poor recognition results, we take advantage of two kinds of noise-robust norms which can eliminate the adverse effects of outliers in visual concepts and improve the accuracy of situation recognition. Finally, we demonstrate the idea and the effectiveness of the proposed models on Yahoo Flickr Creative Commons 100 Million.