A Lightweight Network with Dual Encoder and Cross Feature Fusion for Cement Pavement Crack Detection

Automatic crack detection of cement pavement chiefly benefits from the rapid development of deep learning,with convolutional neural networks(CNN)playing an important role in this field.However,as the performance of crack detection in cement pavement improves,the depth and width of the network structure are significantly increased,which necessitates more computing power and storage space.This limitation hampers the practical implementation of crack detection models on various platforms,particularly portable devices like small mobile devices.To solve these problems,we propose a dual-encoder-based network architecture that focuses on extracting more comprehensive fracture feature information and combines cross-fusion modules and coordinated attention mechanisms formore efficient feature fusion.Firstly,we use small channel convolution to construct shallow feature extractionmodule(SFEM)to extract low-level feature information of cracks in cement pavement images,in order to obtainmore information about cracks in the shallowfeatures of images.In addition,we construct large kernel atrous convolution(LKAC)to enhance crack information,which incorporates coordination attention mechanism for non-crack information filtering,and large kernel atrous convolution with different cores,using different receptive fields to extract more detailed edge and context information.Finally,the three-stage feature map outputs from the shallow feature extraction module is cross-fused with the two-stage feature map outputs from the large kernel atrous convolution module,and the shallow feature and detailed edge feature are fully fused to obtain the final crack prediction map.We evaluate our method on three public crack datasets:DeepCrack,CFD,and Crack500.Experimental results on theDeepCrack dataset demonstrate the effectiveness of our proposed method compared to state-of-the-art crack detection methods,which achieves Precision(P)87.2%,Recall(R)87.7%,and F-score(F1)87.4%.Thanks to our lightweight crack detectionmodel,the parameter count of the model in real-world detection scenarios has been significantly reduced to less than 2M.This advancement also facilitates technical support for portable scene detection.

Cluster DetectionMethod of Endogenous Security Abnormal Attack Behavior in Air Traffic Control Network

In order to enhance the accuracy of Air Traffic Control(ATC)cybersecurity attack detection,in this paper,a new clustering detection method is designed for air traffic control network security attacks.The feature set for ATC cybersecurity attacks is constructed by setting the feature states,adding recursive features,and determining the feature criticality.The expected information gain and entropy of the feature data are computed to determine the information gain of the feature data and reduce the interference of similar feature data.An autoencoder is introduced into the AI(artificial intelligence)algorithm to encode and decode the characteristics of ATC network security attack behavior to reduce the dimensionality of the ATC network security attack behavior data.Based on the above processing,an unsupervised learning algorithm for clustering detection of ATC network security attacks is designed.First,determine the distance between the clustering clusters of ATC network security attack behavior characteristics,calculate the clustering threshold,and construct the initial clustering center.Then,the new average value of all feature objects in each cluster is recalculated as the new cluster center.Second,it traverses all objects in a cluster of ATC network security attack behavior feature data.Finally,the cluster detection of ATC network security attack behavior is completed by the computation of objective functions.The experiment took three groups of experimental attack behavior data sets as the test object,and took the detection rate,false detection rate and recall rate as the test indicators,and selected three similar methods for comparative test.The experimental results show that the detection rate of this method is about 98%,the false positive rate is below 1%,and the recall rate is above 97%.Research shows that this method can improve the detection performance of security attacks in air traffic control network.

Enhanced Topic-Aware Summarization Using Statistical Graph Neural Networks

The rapid expansion of online content and big data has precipitated an urgent need for efficient summarization techniques to swiftly comprehend vast textual documents without compromising their original integrity.Current approaches in Extractive Text Summarization(ETS)leverage the modeling of inter-sentence relationships,a task of paramount importance in producing coherent summaries.This study introduces an innovative model that integrates Graph Attention Networks(GATs)with Transformer-based Bidirectional Encoder Representa-tions from Transformers(BERT)and Latent Dirichlet Allocation(LDA),further enhanced by Term Frequency-Inverse Document Frequency(TF-IDF)values,to improve sentence selection by capturing comprehensive topical information.Our approach constructs a graph with nodes representing sentences,words,and topics,thereby elevating the interconnectivity and enabling a more refined understanding of text structures.This model is stretched to Multi-Document Summarization(MDS)from Single-Document Summarization,offering significant improvements over existing models such as THGS-GMM and Topic-GraphSum,as demonstrated by empirical evaluations on benchmark news datasets like Cable News Network(CNN)/Daily Mail(DM)and Multi-News.The results consistently demonstrate superior performance,showcasing the model’s robustness in handling complex summarization tasks across single and multi-document contexts.This research not only advances the integration of BERT and LDA within a GATs but also emphasizes our model’s capacity to effectively manage global information and adapt to diverse summarization challenges.

Bridge the Gap Between Full-Reference and No-Reference:A Totally Full-Reference Induced Blind Image Quality Assessment via Deep Neural Networks

Blind image quality assessment(BIQA)is of fundamental importance in low-level computer vision community.Increasing interest has been drawn in exploiting deep neural networks for BIQA.Despite of the notable success achieved,there is a broad consensus that training deep convolutional neural networks(DCNN)heavily relies on massive annotated data.Unfortunately,BIQA is typically a small sample problem,resulting the generalization ability of BIQA severely restricted.In order to improve the accuracy and generalization ability of BIQA metrics,this work proposed a totally opinion-unaware BIQA in which no subjective annotations are involved in the training stage.Multiple full-reference image quality assessment(FR-IQA)metrics are employed to label the distorted image as a substitution of subjective quality annotation.A deep neural network(DNN)is trained to blindly predict the multiple FR-IQA score in absence of corresponding pristine image.In the end,a selfsupervised FR-IQA score aggregator implemented by adversarial auto-encoder pools the predictions of multiple FR-IQA scores into the final quality predicting score.Even though none of subjective scores are involved in the training stage,experimental results indicate that our proposed full reference induced BIQA framework is as competitive as state-of-the-art BIQA metrics.

Brain Functional Network Generation Using Distribution-Regularized Adversarial Graph Autoencoder with Transformer for Dementia Diagnosis

The topological connectivity information derived from the brain functional network can bring new insights for diagnosing and analyzing dementia disorders.The brain functional network is suitable to bridge the correlation between abnormal connectivities and dementia disorders.However,it is challenging to access considerable amounts of brain functional network data,which hinders the widespread application of data-driven models in dementia diagnosis.In this study,a novel distribution-regularized adversarial graph auto-Encoder(DAGAE)with transformer is proposed to generate new fake brain functional networks to augment the brain functional network dataset,improving the dementia diagnosis accuracy of data-driven models.Specifically,the label distribution is estimated to regularize the latent space learned by the graph encoder,which canmake the learning process stable and the learned representation robust.Also,the transformer generator is devised to map the node representations into node-to-node connections by exploring the long-term dependence of highly-correlated distant brain regions.The typical topological properties and discriminative features can be preserved entirely.Furthermore,the generated brain functional networks improve the prediction performance using different classifiers,which can be applied to analyze other cognitive diseases.Attempts on the Alzheimer’s Disease Neuroimaging Initiative(ADNI)dataset demonstrate that the proposed model can generate good brain functional networks.The classification results show adding generated data can achieve the best accuracy value of 85.33%,sensitivity value of 84.00%,specificity value of 86.67%.The proposed model also achieves superior performance compared with other related augmentedmodels.Overall,the proposedmodel effectively improves cognitive disease diagnosis by generating diverse brain functional networks.

Identification of Anomaly Scenes in Videos Using Graph Neural Networks

Generally,conventional methods for anomaly detection rely on clustering,proximity,or classification.With themassive growth in surveillance videos,outliers or anomalies find ingenious ways to obscure themselves in the network and make conventional techniques inefficient.This research explores the structure of Graph neural networks(GNNs)that generalize deep learning frameworks to graph-structured data.Every node in the graph structure is labeled and anomalies,represented by unlabeled nodes,are predicted by performing random walks on the node-based graph structures.Due to their strong learning abilities,GNNs gained popularity in various domains such as natural language processing,social network analytics and healthcare.Anomaly detection is a challenging task in computer vision but the proposed algorithm using GNNs efficiently performs the identification of anomalies.The Graph-based deep learning networks are designed to predict unknown objects and outliers.In our case,they detect unusual objects in the form of malicious nodes.The edges between nodes represent a relationship of nodes among each other.In case of anomaly,such as the bike rider in Pedestrians data,the rider node has a negative value for the edge and it is identified as an anomaly.The encoding and decoding layers are crucial for determining how statistical measurements affect anomaly identification and for correcting the graph path to the best possible outcome.Results show that the proposed framework is a step ahead of the traditional approaches in detecting unusual activities,which shows a huge potential in automatically monitoring surveillance videos.Performing autonomous monitoring of CCTV,crime control and damage or destruction by a group of people or crowd can be identified and alarms may be triggered in unusual activities in streets or public places.The suggested GNN model improves accuracy by 4%for the Pedestrian 2 dataset and 12%for the Pedestrian 1 dataset compared to a few state-of the-art techniques.

Early Diagnosis of Lung Tumors for Extending Patients’ Life Using Deep Neural Networks

The medical community has more concern on lung cancer analysis.Medical experts’physical segmentation of lung cancers is time-consuming and needs to be automated.The research study’s objective is to diagnose lung tumors at an early stage to extend the life of humans using deep learning techniques.Computer-Aided Diagnostic(CAD)system aids in the diagnosis and shortens the time necessary to detect the tumor detected.The application of Deep Neural Networks(DNN)has also been exhibited as an excellent and effective method in classification and segmentation tasks.This research aims to separate lung cancers from images of Magnetic Resonance Imaging(MRI)with threshold segmentation.The Honey hook process categorizes lung cancer based on characteristics retrieved using several classifiers.Considering this principle,the work presents a solution for image compression utilizing a Deep Wave Auto-Encoder(DWAE).The combination of the two approaches significantly reduces the overall size of the feature set required for any future classification process performed using DNN.The proposed DWAE-DNN image classifier is applied to a lung imaging dataset with Radial Basis Function(RBF)classifier.The study reported promising results with an accuracy of 97.34%,whereas using the Decision Tree(DT)classifier has an accuracy of 94.24%.The proposed approach(DWAE-DNN)is found to classify the images with an accuracy of 98.67%,either as malignant or normal patients.In contrast to the accuracy requirements,the work also uses the benchmark standards like specificity,sensitivity,and precision to evaluate the efficiency of the network.It is found from an investigation that the DT classifier provides the maximum performance in the DWAE-DNN depending on the network’s performance on image testing,as shown by the data acquired by the categorizers themselves.

结合LSTM自编码器与集成学习的井漏智能识别方法

为了解决传统的井漏智能识别模型因井漏样本数量受限导致其识别准确率低的问题,提出了一种长短期记忆(long short-term memory,LSTM)网络与自编码器(auto-encoder,AE)相结合、集成LSTM-AE的井漏智能识别方法。首先,采用正常样本训练多个包含不同隐藏层神经元数目的LSTM-AE模型,利用重构得分筛选出识别效果较好的几个模型作为基识别器;然后,采用集成学习对多个基识别器的识别结果进行加权融合,解决单一模型因对样本局部特征过度学习导致的误报与漏报问题,提高模型的识别准确率。从某油田18口井的钻井数据中选取了6000组正常钻进状态下的立压、出口流量、池体积数据,对集成LSTM-AE模型进行训练和测试,结果表明,提出方法的识别准确率达到了94.7%,优于其他常用的智能模型的识别结果,为井漏识别提供了一种新的技术途径。

End-to-end aspect category sentiment analysis based on type graph convolutional networks

For the existing aspect category sentiment analysis research,most of the aspects are given for sentiment extraction,and this pipeline method is prone to error accumulation,and the use of graph convolutional neural network for aspect category sentiment analysis does not fully utilize the dependency type information between words,so it cannot enhance feature extraction.This paper proposes an end-to-end aspect category sentiment analysis(ETESA)model based on type graph convolutional networks.The model uses the bidirectional encoder representation from transformers(BERT)pretraining model to obtain aspect categories and word vectors containing contextual dynamic semantic information,which can solve the problem of polysemy;when using graph convolutional network(GCN)for feature extraction,the fusion operation of word vectors and initialization tensor of dependency types can obtain the importance values of different dependency types and enhance the text feature representation;by transforming aspect category and sentiment pair extraction into multiple single-label classification problems,aspect category and sentiment can be extracted simultaneously in an end-to-end way and solve the problem of error accumulation.Experiments are tested on three public datasets,and the results show that the ETESA model can achieve higher Precision,Recall and F1 value,proving the effectiveness of the model.

基于深度SSDAE网络的刀具磨损状态识别

针对刀具磨损状态识别过程中采集数据量大、干扰信号复杂且需人为选择特征参数的问题,为提高刀具磨损状态识别模型的鲁棒性与泛化性,提出了一种数据驱动下深度堆叠稀疏降噪自编码(stacking sparse denoising auto-encoder,简称SSDAE)网络的刀具磨损状态识别方法,实现隐藏在数据中深层次的数据特征自动挖掘。首先,将原始振动信号分解为一系列固有模态分量(intrinsic mode function,简称IMF),并采用皮尔逊相关系数法选取了最优固有模态来组合一个新的信号;其次,采用SSDAE网络自适应提取特征后对刀具磨损阶段进行了状态识别,识别精度达到98%;最后,对网络模型进行实验验证,并与最常用的刀具磨损状态识别方法进行了对比。实验结果表明,所提出的方法能够很好地处理非平稳振动信号,对不同刀具磨损阶段状态的识别效果良好,并具有较好的泛化性能和可靠性。

基于NVAE和OB-Mix的小样本数据增强方法

由于深度学习模型对海量标注数据的依赖性较高,导致目前许多前沿性目标检测理论难以适用于工业检测领域。为此,提出一种基于NVAE图像生成和OB-Mix数据增强的小样本数据扩充方法。具体方法是通过NVAE构建检测目标的数据分布模型,再通过采样潜变量的方式生成与真实目标图像属于同一分布的全新目标图像。在得到生成目标图像后,提出了OB-Mix数据增强策略,将生成目标图像与背景图像进行随机位置融合以构建出新的图像数据,从而提高网络的定位能力及泛化能力。方法在仅使用474张标注图像以及400张无检测目标的背景图像情况下,使YOLOv5的检测精确率达到95.86%,相比于不使用该方法的结果提高了17.60个百分点。

新一代通用视频编码标准H.266/VVC:现状与发展

相比于上一代标准,新一代通用视频编码标准(H.266/VVC)在同等质量下能够节省大约50%的码率,且适用于多种多样的视频应用场景。论文从H.266/VVC的关键技术出发,对标准的现状、实现和应用发展进行深入探讨。H.266/VVC沿用既往标准中的双层码流体系和混合编码框架,针对帧内预测、帧间预测、变换、量化、环路滤波等所有主要编码模块进行了技术革新,并为屏幕内容视频等应用提供了高效的专用编码工具。H.266/VVC标准目前已处于实用化阶段,官方参考软件VTM和开源编解码器VVenC/VVdeC是目前最具代表性的软件编解码实现。对H.266/VVC的性能分析可以看出:H.266/VVC针对高分辨率视频取得的编码增益更为突出;主要编码工具对性能的贡献通常以复杂度为代价,但也有部分编码工具在提升编码性能的同时可降低整体编码复杂度。H.266/VVC的硬件实现面临诸多挑战,发展明显滞后于软件实现,现有研究主要集中在对具体编码模块的硬件加速方面。H.266/VVC标准发布之后,下一代视频编码标准的发展目前仍围绕混合编码框架进行探索,聚焦在两大方向:超越VVC的增强压缩关注更为先进的、非神经网络的编码工具,基于神经网络的视频编码则探索采用神经网络的编码工具。除此之外,部分或完全跳出现有混合编码框架的端到端视频编码也在飞速发展,未来视频编码标准与神经网络结合成为趋势,但面临着计算资源依赖和稳定结构两方面的考验。

基于映射空间编码的高速运动轨道图像去模糊研究

针对轨道缺陷检测系统因镜头抖动或相机快速移动而导致所采集图像较为模糊的问题,提出一种基于最大后验概率估计思想的映射空间编码的高速运动轨道图像去模糊算法。首先,该算法使用深度编解码器和残差网络分别对数据集中清晰图像到模糊图像的映射关系和模糊核进行编码,为了保证编码时频率信息的完整性,算法在传统的残差模块上引入快速傅里叶变换通道构成双通道残差网络,以补偿多次特征提取带来的频率损失;其次,算法采用深度图像先验(Deep Image Prior,DIP)将潜在的清晰图像和模糊核进行参数化,再利用先验得到的模糊核和清晰图像来调用编码空间中的映射关系;最后,通过交替优化潜在的清晰图像和模糊核,从而去逼近一个真实未知的映射,进而实现真实场景下高速运动轨道图像的去模糊。实验结果表明,双通道残差模块提取的特征图频率信息分量强度普遍高于传统的残差模块,相较于使用传统残差模块实现该算法,采用双通道残差模块可使峰值信噪比(Peak Signal-to-Noise Ratio,PSNR)提升0.84 dB,结构相似性(Structural Similarity,SSIM)提高0.025 1。与现有的深度学习去模糊算法相比,提出的去模糊算法对高速轨道检测系统所采集图像的去模糊效果更佳,在性能方面相较于最好的去模糊算法,PSNR提高了1.84 dB,SSIM提升了0.017 3,显著提升了采集图像的质量。研究结果可为下一步识别轨道部件是否存在缺陷提供清晰图像。

基于改进VGG16的自编码器视频异常检测算法

在使用自编码器结构的神经网络处理视频异常检测任务时,U-Net风格的自编码器由于编码器层数深度过浅,导致在面对复杂的数据集时,不能充分抽取更多有用的特征信息。同时,在训练模型时使用MSE(均方误差),仅考虑了预测帧与真实帧之间的像素级相似性,对于复杂场景,像素级相似性可能无法准确判断预测帧与真实帧之间的相似性。针对以上问题,对基于U-Net风格的自编码器进行改进,提出了一种使用改进的VGG16作为编码器的视频异常检测算法,同时在均方误差的基础上添加结构相似性(SSIM)损失函数。改进的VGG16去掉了全连接层,并加入了残差连接防止特征退化,添加SSIM在计算像素级相似性的同时计算图像的亮度、对比度和结构等方面的相似性来优化网络。实验结果表明,改进后的算法,在Ped2数据集上检测效果达到95.91%,在Avenue数据集上检测效果达到84.89%,与改进前的方法相比分别提高了0.80%和0.19%,验证了所提方法的有效性。

面向天文多普勒差分测速的太阳/行星光谱对生成方法

为了提供天文多普勒差分测速所需的同步太阳/行星光谱对,提出了一种变分自编码器(VAE)和对偶生成对抗网络(Dual GAN)相融合的VAE-Dual GAN。首先,实测太阳光谱经过VAE编码到隐空间,实现了光谱到光谱域的扩充;然后,由Dual GAN将隐空间映射到伪行星光谱;最后,利用伪行星光谱生成重构太阳光谱。此外,利用编码和生成重建损失加强对网络的约束。VAE-Dual GAN利用Dual GAN的转换学习能力完成了两个光谱域的转换,生成同步太阳/行星光谱对。实验结果表明,VAE-Dual GAN可生成高质量的太阳/行星光谱对,将天文多普勒差分测速精度提高60%以上。

时空邻域感知的时序兴趣点推荐

如何捕捉用户行为的动态变化和依赖关系是当前兴趣点推荐的一个重要问题,主要面临着数据稀疏、时空序列特征提取难以及用户个性化差异不易捕捉等挑战。为了解决这些挑战,提出了一种基于时空邻域感知及隐含状态变化的时序兴趣点推荐方法。该方法将用户行为的学习转换成了潜在状态的学习,并以一种结合距离信息的方式引入空间信息,有效地捕捉了用户的移动特征。首先,利用变分自编码器表征用户的潜在状态,再通过图神经网络学习到潜在状态之间的依赖关系,从而捕捉到用户行为的时序依赖;然后,利用注意力机制和径向基函数来捕捉用户与地点候选集之间的空间依赖,进而评估用户访问每个地点的概率,实现兴趣点推荐。在三个真实数据集上进行了实验比较和分析,显示了该方法相比于现有的基准算法具有更好的时序推荐性能。

基于Transformer的多尺度遥感语义分割网络

为了提升遥感图像语义分割效果,本文针对分割目标类间方差小、类内方差大的特点,从全局上下文信息和多尺度语义特征2个关键点提出一种基于Transformer的多尺度遥感语义分割网络(muliti-scale Transformer network,MSTNet)。其由编码器和解码器2个部分组成,编码器包含基于Transformer改进的视觉注意网络(visual attention network,VAN)主干和基于空洞空间金字塔池化(atrous spatial pyramid pooling, ASPP)结构改进的多尺度语义特征提取模块(multi-scale semantic feature extraction module, MSFEM)。解码器采用轻量级多层感知器(multi-layer perception,MLP)配合编码器设计,充分分析所提取的包含全局上下文信息和多尺度表示的语义特征。MSTNet在2个高分辨率遥感语义分割数据集ISPRS Potsdam和LoveDA上进行验证,平均交并比(mIoU)分别达到79.50%和54.12%,平均F1-score(m F1)分别达到87.46%和69.34%,实验结果验证了本文所提方法有效提升了遥感图像语义分割的效果。

融合改进自编码器和残差网络的入侵检测模型

互联网中存在大量隐私数据,因此防止网络入侵成为保护网络安全的关键问题。为提高网络入侵检测的准确率并解决其收敛慢问题,设计一种改进的堆叠自动编码器和残差网络(ISAE-ResNet)入侵检测模型。融合栈式自编码器和残差网络,首先将预处理后的数据输入到改进的栈式自编码器中,该栈式自编码器由2个副编码器和1个主编码器组成,数据经过副编码器和主编码器训练后重构出新的特征来防止过拟合问题;然后将解码层的权重捆绑到编码层进行优化,使模型参数减半来进行降维,提高模型的收敛速度;最后将处理过的数据输入到改进的残差网络中,并基于改进的ResNet网络设计一种加入软阈值函数的残差模块,通过降低数据中的噪声来提高模型准确率。在CIC-IDS-2017数据集上的实验结果表明,该模型准确率为98.67%,真正例率为95.93%,误报率为0.37%,损失函数值快速收敛至0.042,在准确率、真正例率、误报率和收敛速度方面均超过对比入侵检测模型,具有较高的有效性和可行性。

基于分割点改进孤立森林的网络入侵检测方法

随着网络攻击的不断增多和日益复杂化,传统基于监督的网络入侵检测算法不能准确识别没有类别标记或特征不明显的网络访问链接,而对于无监督的网络入侵检测算法,也存在检测效率和准确率低等问题。针对如何进一步提升网络入侵检测性能,提出使用自编码器(AE)与分割点改进孤立森林模型对网络入侵进行检测。首先,对无监督自编码器进行L1正则化,以增强自编码器的稀疏性,通过学习数据内在结构,自适应地提取具有判别性的特征,完成入侵攻击的特征提取;然后,使用改进的孤立森林分离异常点,即使用最大化均值与标准差之商来确定分割点划分最佳超平面来构建隔离树,使隔离树在相关子空间中具有更强隔离异常值的能力,并通过遍历所有隔离树中数据点的平均路径长度得到异常得分来判定异常流量。在KDDCUP99和UNSW-NB15数据集上的实验结果表明,与6种传统无监督方法相比,该方法较传统孤立森林准确率和召回率均提升约20%,F1值和曲线下面积(AUC)值均提升约10%,较其他无监督方法相比大幅降低了误码率。

结合传递比与栈式自编码器的结构损伤识别

如何从土木结构响应数据中挖掘损伤特征并有效分类,是实现损伤模式识别的关键。为此,以框架结构为分析对象,搭建设有自编码器隐藏层和Softmax分类层的栈式自编码器网络,采用无监督联合有监督的混合学习机制;基于有限元分析获取框架不同工况下的传递比函数值,构建训练集、验证集和测试集样本;通过预训练确定自编码器隐藏层的参数值如权重和偏置值,避免网络出现过拟合;采用微调方式进一步调整预训练后的网络参数值,再结合验证集实现对网络超参数的调整;将实测传递比数据输入网络,实现对框架节点损伤的评估。结果表明:所提方法能有效进行损伤特征的提取和分类,准确识别框架节点的单、双损伤工况,相较于传统浅层神经网络具有更高的识别准确度和更好的抗噪性。