卷积优化的变分自编码聚类方法

传统的变分自编码器将样本展平后直接作为输入数据,当样本为图像数据时,采用这样的方法进行学习效果欠佳.本文提出一种卷积优化的变分自编码器,用多个可变层数的卷积网络预处理图像数据.每个卷积网络设置了不同的参数处理输入数据,再将不同层卷积结果拼接后,作为变分自编码器的输入.在变分自编码模型中增加一个类别编码器,用于计算每个样本的类别分布和原样本集中类别分布的差异,实现聚类.实验证明,本文提出的卷积优化方法相较于无优化的变分自编码器在聚类准确率上得到较大提高,生成图像的质量得到了改善,各类别生成样本在边缘及形状等方面的多样性也都有不同程度的增加.     

基于非对称卷积自编码器和支持向量机的入侵检测模型

网络入侵检测系统在防护网络安全中占据重要地位,随着科技不断发展,目前的入侵技术没有考虑到检测技术的可扩展性、可持续性以及训练时间长短,无法应对现代复杂多变的网络异常流量。针对这些问题,提出了一种新的深度学习方法,使用无监督的非对称卷积自编码器,对数据进行特征学习。另外,提出了一种新的基于非对称卷积自编码器和多类支持向量机相结合的方法。在 KDD99 数据集上进行了实验,实验结果表明,该方法取得了良好的结果,与其他方法相比显著减少了训练时间,进一步提高了网络入侵检测技术。     

基于S-RNPAE算法的间歇过程早期故障监测

针对具有多变量、非线性和高维度特点的间歇过程数据使得早期故障信号易被噪声干扰且故障幅值低导致故障监测效果不佳的问题,提出一种基于堆叠鲁棒邻域保持自编码(stack-robust neighborhood preserving autoencoder,S-RNPAE)的间歇过程早期故障监测方法.首先,通过$L_{2,1     

基于联合卷积自编码网络的多聚焦图像融合方法

受相机景深的限制,单次成像无法对不同景深的内容全部清晰成像.多聚焦图像融合技术可以将不同聚焦层次的图像融合为一幅全聚焦的图像,其中如何得到准确的聚焦映射是多聚焦图像融合中的关键问题.对此,利用卷积神经网络强大的特征提取能力,设计具有公共分支和私有分支的联合卷积自编码网络以学习多源图像的特征,公共分支学习多幅图像之间的公共特征,每幅图像的私有分支学习该图像区别于其他图像的私有特征.基于私有特征计算图像的活动测度,得到图像聚焦区域映射,据此设计融合规则以融合两幅多聚焦图像,最终得到全聚焦的融合图像.在公开数据集上的对比实验结果显示:主观评测上,所提出的方法能够较好地融合聚焦区域,视觉效果自然清晰;客观指标上,该方法在多个评价指标上优于对比方法.     

基于一维卷积自编码器—高斯混合模型的间歇过程故障检测

传统基于数据驱动的间歇过程故障检测方法往往需要对数据的分布进行假设,其模型多阶段划分不精确,导致故障检测率受到影响.对此提出一种基于一维卷积自编码器—高斯混合模型（One dimensional convolution-auto encoder-Gaussian mixture model,1DC-AE-GMM）的检测新方法.该方法不需要对原始数据进行假设,首先对原始数据进行等长和缩放处理,并以最小重构误差的原则在具有卷积和多个中间层的深层神经网络上进行训练,以非线性的方式自动、精确地进行阶段划分和特征提取;然后在网络的编码层上建立高斯混合模型并进行聚类,在提取特征的同时大大减少了建立模型的计算量;最后结合马氏距离提出全局概率检测指标,实现故障检测.通过在一类半导体蚀刻过程的仿真实验,结果表明该方法可以有效地提高故障检测率.     

基于卷积自编码神经网络的心电信号降噪

心电信号由于在采集过程中会受到外界环境的干扰导致其形态特征被严重淹没,从而对医生的诊断和远程智能分析造成干扰。基于此,提出了一种基于卷积自编码神经网络的心电信号降噪算法。该方法利用自编码器的编码、解码特性,通过卷积的方法构建深层神经网络来学习从含噪心电信号到干净心电信号的端对端映射。卷积层捕获心电信号的细节特征,同时消除噪声;解码部分能够对特征图进行上采样并恢复心电信号细节,从而得到干净的心电信号。实验中采用信噪比和均方根误差为指标,将该方法与小波阈值法、S变换法、BP神经网络法和指导滤波法进行比较。实验结果表明,该降噪方法整体降噪精度更优,同时信号的低频成分也得到了很好的保持。该方法可做到在消除心电信号中复杂噪声的同时完整保留心电信号的形态,为心血管疾病的智能诊断和心电图的特征检测奠定了基础。     

基于Apex帧光流和卷积自编码器的微表情识别

针对跨库微表情识别问题,提出了一种基于Apex帧光流和卷积自编码器的微表情识别方法。该方法包括预处理、特征提取、微表情分类三部分。预处理部分对微表情进行Apex帧定位以及人脸检测和对齐;特征提取部分首先计算预处理过的Apex帧的TVL1光流,然后使用得到的水平和竖直光流分量图像训练卷积自编码器得到最优结构和参数;最后将两个分量自编码器中间层的特征融合后作为微表情的特征;微表情分类就是使用支持向量机（Support Vector Machine,SVM）对上一步中提取到的特征进行分类。实验结果较基准方法（LBP-TOP）有了很大的提高,UF1提高了0.134 4,UAR提高了0.140 6。该方法为微表情特征提取和识别提供了新的思路。     

深度卷积自编码图像聚类算法

针对现有深度卷积嵌入聚类算法(deep convolutional embedded clustering,DCEC)的网络特征损失过大,对复杂图像没有提取有效特征的问题,提出一个具有17层网络结构的无监督深度聚类框架,并在编码层加入下采样层,减少参数和防止过拟合;在解码层加入上采样层还原下采样造成的细节损失。分别结合DEC(deep embedded clustering)算法的损失函数和IDEC(improved deep embedded clustering)算法的采用局部结构保留优势的损失函数,得到两种基于卷积自编码的深度学习图像聚类算法DEC_DCNN(deep embedded clustering based on deep convolutional neural network)和IDEC_DCNN(improved deep embedded clustering based on deep convolutional neural network),并使用自适应矩估计(adaptive moment estimation,Adam)和小批量随机梯度下降(mini-batch stochastic gradient decent,mini-batch SGD)两种优化方法调整模型参数。3个经典图像数据集的实验结果显示,提出的17层网络结构对图像特征具有很好的鲁棒性和通用性,基于该网络结构的深度聚类算法取得了远优于现有深度聚类算法的结果,其聚类准确率均优于对比算法;对深度聚类算法DEC_DCNN和IDEC_DCNN的聚类结果准确率、指标值AMI(adjusted mutual information)和ARI(adjusted rand index)进行比较,IDEC_DCNN比DEC_DCNN的聚类性能更好,说明IDEC_DCNN算法的性能更优越。     

基于教与学优化的可变卷积自编码器的医学图像分类方法

针对传统手工方法优化卷积神经网络(CNN)参数时存在耗时长、不准确,以及参数设置影响算法性能等问题,提出一种基于教与学优化(TLBO)的可变卷积自编码器(CAE)算法.该算法设计了可变长度的个体编码策略,从而快速构建CAE结构,并堆叠CAE为一个CNN;此外,充分利用优秀个体的结构信息来引导算法朝着更有希望的区域搜索,...     

Anomaly detection of defects on concrete structures with the convolutional autoencoder

This paper reports the application of deep learning for implementing the anomaly detection of defects on concrete structures, so as to facilitate the visual inspection of civil infrastructure. A convolutional autoencoder was trained as a reconstruction-based model, with the defect-free images, to rapidly and reliably detect defects from the large volume of image datasets. This training process was in the unsupervised mode, with no label needed, thereby requiring no prior knowledge and saving an enormous amount of time for label preparation. The built anomaly detector favors minimizing the reconstruction errors of defect-free images, which renders high reconstruction errors of defects, in turn, detecting the location of defects. The assessment shows that the proposed anomaly detection technique is robust and adaptable to defects on wide ranges of scales. Comparison was also made with the segmentation results produced by other automatic classical methods, revealing that the results made by the anomaly map outperform other segmentation methods, in terms of precision, recall, F₁ measure and F₂ measure, without severe under- and over-segmentation. Further, instead of merely being a binary map, each pixel of the anomaly map is represented by the anomaly score, which acts as a risk indicator for alerting inspectors, wherever defects on concrete structures are detected.     

卷积自编码器融合核近似技术的异常检测模型

图像中的异常检测是计算机视觉中非常重要的研究主题, 它可以定义为单分类问题;针对图像数据集的规模大,维度高等特性,一种新的深度卷积自编码器(Convolutional Autoencoder, CAE)与核近似单分类支持向量机(One Class Support Vector Machine, OCSVM)相结合的异常检测模型CAE-OCSVM被提出;模型中的深度卷积自编码器负责学习图像的本质特征表示,然后使用随机傅里叶特征对卷积自编码器学习本质特征进行核近似,核近似后输入线性单类支持向量机进行图像异常检测。核近似技术克服了核学习技术时间复杂度高的问题;同时深度卷积自编码器与核近似单类支持向量机通过梯度下降法实现了端到端的学习;模型的AUC性能在四个公开的图像基准数据集上进行了实验验证,同时模型与其它常用的异常检测模型在不同的异常率的情况下进行了性能对比;实验结果证实CAE-OCSVM模型在四个公开图像数据集上的性能都优于其它异常检测模型,表明了CAE-OCSVM模型更适合大规模高维数据集的异常检测     

基于栈式卷积自编码的视觉SLAM闭环检测

同时定位与构图(SLAM)主要用于解决移动机器人在未知环境中进行地图构建和导航的问题,是移动机器人实现自主移动的基础.闭环检测是视觉SLAM的关键步骤,对构建一致性地图和减少位姿累积误差具有重要作用.当前的闭环检测方法通常采用传统的SIFT、SURF等特征,很容易受到环境影响,为了提高闭环检测的准确性和鲁棒性,提出基于无监督栈式卷积自编码(CAEs)模型的特征提取方法,运用训练好的CAEs卷积神经网络对输入图像进行学习,将输出的特征应用于闭环检测.实验结果表明:与传统的BoW方法及其他基于深度学习模型的方法相比,所提出的算法能够有效降低图像特征的维数并改善特征描述的效果,可以在机器人SLAM闭环检测环节获得更好的精确性和鲁棒性.     

Hybrid robust convolutional autoencoder for unsupervised anomaly detection of machine tools under noises

Anomaly detection of machine tools plays a vital role in the machinery industry to sustain efficient operation and avoid catastrophic failures. Compared to traditional machine learning and signal processing methods, deep learning has greater adaptive capability and end-to-end convenience. However, challenges still exist in recent research in anomaly detection of machine tools based on deep learning despite the marvelous endeavors so far, such as the necessity of labeled data for model training and insufficient consideration of noise effects. During machine operation, labeled data is often difficult to obtain; the collected data contains varying degrees of noise disturbances. To address the above challenges, this paper develops a hybrid robust convolutional autoencoder (HRCAE) for unsupervised anomaly detection of machine tools under noises. A parallel convolutional distribution fitting (PCDF) module is constructed, which can effectively fuse multi-sensor information and enhance network robustness by training in parallel to better fit the data distribution with unsupervised learning. A fused directional distance (FDD) loss function is designed to comprehensively consider the distance and angle differences among the data, which can effectively suppress the influence of noises and further improve the model robustness. The proposed method is validated by real computer numerical control (CNC) machine tool data, obtaining better performance of unsupervised anomaly detection under different noises compared to other popular unsupervised improved autoencoder methods.     

Unsupervised deep learning approach for network intrusion detection combining convolutional autoencoder and one-class SVM

Applied Intelligence - With the rapid advancement in network technologies, the need for cybersecurity has gained increasing momentum in recent years. As a primary defense mechanism, an intrusion...     

Residual attention convolutional autoencoder for feature learning and fault detection in nonlinear industrial processes

Neural Computing and Applications - Deep learning has been successfully applied in process monitoring in recent years due to its powerful feature extraction. However, these monitoring methods are...     

Aerial image dehazing using a deep convolutional autoencoder

Aerial images and videos are extensively used for object detection and target tracking. However, due to the presence of thin clouds, haze or smoke from buildings, the processing of aerial data can be challenging. Existing single-image dehazing methods that work on ground-to-ground images, do not perform well on aerial images. Moreover, current dehazing methods are not capable for real-time processing. In this paper, a new end-to-end aerial image dehazing method using a deep convolutional autoencoder is proposed. Using the convolutional autoencoder, the dehazing problem is divided into two parts, namely, encoder, which aims extract important features to dehaze hazy regions and decoder, which aims to reconstruct the dehazed image using the down-sampled image received from the encoder. In this proposed method, we also exploit the superpixels in two different scales to generate synthetic thin cloud data to train our network. Since this network is trained in an end-to-end manner, in the test phase, for each input hazy aerial image, the proposed algorithm outputs a dehazed version without requiring any other information such as transmission map or atmospheric light value. With the proposed method, hazy regions are dehazed and objects within hazy regions become more visible while the contrast of non-hazy regions is increased. Experimental results on synthetic and real hazy aerial images demonstrate the superiority of the proposed method compared to existing dehazing methods in terms of quality and speed.

     

Feature learning using convolutional denoising autoencoder for activity recognition

Neural Computing and Applications - Wearable technology offers a prospective solution to the increasing demand for activity monitoring in pervasive healthcare. Feature extraction and selection are...     

非对称卷积编码器的聚类算法

基于深度神经网络的非监督学习方法通过联合优化特征表示和聚类指派,大大提升了聚类任务的性能。但大量的参数降低了运行速度,另外,深度模型提取的特征的区分能力也影响聚类性能。为此,提出一种新的聚类算法(asymmetric fully-connected layers convolutional auto-encoder, AFCAE),其中卷积编码器结合非对称全连接进行无监督的特征提取,然后K-means算法对所得特征执行聚类。网络采用3×3和2×2的小卷积核,大大减少了参数个数,降低了算法复杂性。在MNIST上AFCAE获得0.960的聚类精度,比联合训练的DEC(deep embedding clustering)方法(0.840)提高了12个百分点。在6个图像数据集上实验结果表明AFCAE网络有优异的特征表示能力,能出色完成下游的聚类任务。     

MMD-encouraging convolutional autoencoder: a novel classification algorithm for imbalanced data

Applied Intelligence - Imbalanced data classification problem is widely existed in commercial activities and social production. It refers to the scenarios with considerable gap of sample amount...