Feature Extraction by Multi-Scale Principal Component Analysis and Classification in Spectral Domain

Feature extraction of signals plays an important role in classification problems because of data dimension reduction property and potential improvement of a classification accuracy rate. Principal component analysis (PCA), wavelets transform or Fourier transform methods are often used for feature extraction. In this paper, we propose a multi-scale PCA, which combines discrete wavelet transform, and PCA for feature extraction of signals in both the spatial and temporal domains. Our study shows that the multi-scale PCA combined with the proposed new classification methods leads to high classification accuracy for the considered signals.

Multi-Scale Mixed Attention Tea Shoot Instance Segmentation Model

Tea leaf picking is a crucial stage in tea production that directly influences the quality and value of the tea.Traditional tea-picking machines may compromise the quality of the tea leaves.High-quality teas are often handpicked and need more delicate operations in intelligent picking machines.Compared with traditional image processing techniques,deep learning models have stronger feature extraction capabilities,and better generalization and are more suitable for practical tea shoot harvesting.However,current research mostly focuses on shoot detection and cannot directly accomplish end-to-end shoot segmentation tasks.We propose a tea shoot instance segmentation model based on multi-scale mixed attention(Mask2FusionNet)using a dataset from the tea garden in Hangzhou.We further analyzed the characteristics of the tea shoot dataset,where the proportion of small to medium-sized targets is 89.9%.Our algorithm is compared with several mainstream object segmentation algorithms,and the results demonstrate that our model achieves an accuracy of 82%in recognizing the tea shoots,showing a better performance compared to other models.Through ablation experiments,we found that ResNet50,PointRend strategy,and the Feature Pyramid Network(FPN)architecture can improve performance by 1.6%,1.4%,and 2.4%,respectively.These experiments demonstrated that our proposed multi-scale and point selection strategy optimizes the feature extraction capability for overlapping small targets.The results indicate that the proposed Mask2FusionNet model can perform the shoot segmentation in unstructured environments,realizing the individual distinction of tea shoots,and complete extraction of the shoot edge contours with a segmentation accuracy of 82.0%.The research results can provide algorithmic support for the segmentation and intelligent harvesting of premium tea shoots at different scales.

Ship recognition based on HRRP via multi-scale sparse preserving method

In order to extract the richer feature information of ship targets from sea clutter, and address the high dimensional data problem, a method termed as multi-scale fusion kernel sparse preserving projection(MSFKSPP) based on the maximum margin criterion(MMC) is proposed for recognizing the class of ship targets utilizing the high-resolution range profile(HRRP). Multi-scale fusion is introduced to capture the local and detailed information in small-scale features, and the global and contour information in large-scale features, offering help to extract the edge information from sea clutter and further improving the target recognition accuracy. The proposed method can maximally preserve the multi-scale fusion sparse of data and maximize the class separability in the reduced dimensionality by reproducing kernel Hilbert space. Experimental results on the measured radar data show that the proposed method can effectively extract the features of ship target from sea clutter, further reduce the feature dimensionality, and improve target recognition performance.

RealFuVSR:Feature enhanced real-world video super-resolution

Background Recurrent recovery is a common method for video super-resolution(VSR)that models the correlation between frames via hidden states.However,the application of this structure in real-world scenarios can lead to unsatisfactory artifacts.We found that in real-world VSR training,the use of unknown and complex degradation can better simulate the degradation process in the real world.Methods Based on this,we propose the RealFuVSR model,which simulates real-world degradation and mitigates artifacts caused by the VSR.Specifically,we propose a multiscale feature extraction module(MSF)module that extracts and fuses features from multiple scales,thereby facilitating the elimination of hidden state artifacts.To improve the accuracy of the hidden state alignment information,RealFuVSR uses an advanced optical flow-guided deformable convolution.Moreover,a cascaded residual upsampling module was used to eliminate noise caused by the upsampling process.Results The experiment demonstrates that RealFuVSR model can not only recover high-quality videos but also outperforms the state-of-the-art RealBasicVSR and RealESRGAN models.

Gender-Specific Multi-Task Micro-Expression Recognition Using Pyramid CGBP-TOP Feature

Micro-expression recognition has attracted growing research interests in the field of compute vision.However,micro-expression usually lasts a few seconds,thus it is difficult to detect.This paper presents a new framework to recognize micro-expression using pyramid histogram of Centralized Gabor Binary Pattern from Three Orthogonal Panels(CGBP-TOP)which is an extension of Local Gabor Binary Pattern from Three Orthogonal Panels feature.CGBP-TOP performs spatial and temporal analysis to capture the local facial characteristics of micro-expression image sequences.In order to keep more local information of the face,CGBP-TOP is extracted based on pyramid subregions of the micro-expression video frame.The combination of CGBP-TOP and spatial pyramid can represent well and truly the facial movements of the micro-expression image sequences.However,the dimension of our pyramid CGBP-TOP tends to be very high,which may lead to high data redundancy problem.In addition,it is clear that people of different genders usually have different ways of micro-expression.Therefore,in this paper,in order to select the relevant features of micro-expression,the gender-specific sparse multi-task learning method with adaptive regularization term is adopted to learn a compact subset of pyramid CGBP-TOP feature for micro-expression classification of different sexes.Finally,extensive experiments on widely used CASME II and SMIC databases demonstrate that our method can efficiently extract micro-expression motion features in the micro-expression video clip.Moreover,our proposed approach achieves comparable results with the state-of-the-art methods.

半监督空谱局部判别分析的高光谱影像特征提取

为充分利用高光谱影像中蕴含的空谱特征,提出了一种半监督空谱局部判别分析的高光谱影像特征提取算法(S4LFDA)。鉴于高光谱数据集具有空间一致性,首先将像元进行空间重构,保存高光谱数据的近邻关系;其次引入光谱信息散度重构像元间的相似度;为了充分利用大量无标签样本提高算法性能,采用模糊C均值聚类算法对样本进行聚类分析得到伪标签;然后通过增加规范化项到局部力导引算法(FDA)的类内散度矩阵和类间散度矩阵中,以此保持无标签样本的聚类结构一致性;最后通过局部FDA算法来保持有标签样本类间散度最大化和类内散度最小化并求解最佳投影向量。S4LFDA算法既保持了数据集在光谱域的可分性,又保持了像元在空间区域内的近邻关系,合理利用有标签样本及无标签样本,提高了算法的分类性能。在Pavia University和Indian Pines数据集上进行实验,总体分类精度达到95.60%和94.38%。与其他维数约简算法相比,该算法有效提高了地物分类性能。

基于运动特征的骨骼行为识别方法

针对现有的骨骼行为识别方法对人体行为的运动信息利用不足的问题,提出一种基于运动特征的时空注意力图卷积(STA-GCN)行为识别模型。对动作捕捉设备采集到的关节点运动轨迹和速度信息进行建模,在时间和空间构建注意力权重矩阵,结合图卷积网络进行特征提取,能够关注到具有判别力的关节点和时间帧。通过在自建动作捕捉数据集和NTU-RGB+D数据集的CS和CV标准上进行实验,其结果表明,该模型增强了对人体骨骼行为信息的理解能力,验证了模型对行为识别的有效性。

基于空频域特征提取的小样本图像分类算法

小样本学习的目的是使用极少的样本训练模型,并在有限的数据集上构建一种有效的模型,以实现对新样本的准确预测。关于小样本图像分类的研究大多只从空域的角度去提取图像的特征进行学习,且在计算相似性分数时采用单一的度量模式,极大地降低了图像分类的准确性。为此,提出了一种基于空频域特征提取的小样本图像分类算法网络(FENet),从空域和频域角度出发,提取图像特征,并结合图像到图像的度量与图像到类的度量方式,引入干扰因子,提高模型的鲁棒性和泛化性。在CUB-200-2011、Stanford-Cars、Stanford-Dogs 3个数据集上进行了大量的实验,结果表明,FENet在一定程度上能提升小样本图像分类的准确性。

基于多尺度混合注意力卷积神经网络的关系抽取模型

针对基于卷积神经网络(CNN)的关系抽取获取句子语义信息时缺少不同尺度语义特征信息的获取以及对关键信息的关注的问题,提出基于多尺度混合注意力CNN的关系抽取模型。首先,将关系抽取建模为二维化表示的标签预测;其次,通过多尺度的特征信息提取与融合,获得更细粒度的多尺度空间信息;然后,通过注意力与卷积的结合自适应地细化特征图,使模型关注重要的上下文信息;最后,使用两个预测器共同预测实体对之间的关系标签。实验结果表明,多尺度混合卷积注意力模型能够获取多尺度语义特征信息,而通道注意力和空间注意力通过权重捕捉通道和空间的关键信息,以此来提升关系抽取的性能。所提模型在数据集SemEval(SemEval-2010 task 8)、TACRED(TAC Relation Extraction Dataset)、Re-TACRED(Revised-TACRED)和SciERC(Entities,Relations,and Coreference for Scientific knowledge graph construction)上的F1值分别达到90.32%、70.74%、85.71%和89.66%。

改进2DCNN时空特征提取的动作识别研究

基于深度学习的视频动作识别方法处理时间信息的方式主要有两种,一是利用光流表示相邻帧之间的运动信息,但其无法有效建模长程时间特征,二是利用3D卷积对时空信号进行混合建模,但其引入了大量的参数,导致内存消耗和计算量剧增.针对上述问题,本文提出了一种改进2D CNN时空特征提取的动作识别方法,在2D CNN中嵌入时空门控和动作注意力聚合(Spatial-temporal Gate and Motion Attention-aggregation,SGMA)模块增强其时空特征提取能力.SGMA包含时空动态门控和动作注意力聚合两个子模块,时空动态门控能够可视化各通道特征的运动比例因子并依此逐通道分离运动强相关特征和运动弱相关特征,动作注意力聚合利用运动强相关特征构建金字塔结构来提取不同时间跨度的运动特征,并使用注意力机制自适应聚合各时间跨度特征实现长程时间建模,运动弱相关特征经过2D卷积提取空间特征后融合动作注意力聚合模块的输出最终获得强有力的时空特征表达.在相同帧采样策略下,本文方法在Something-SomethingV1&V2验证集上的Top1准确度比基准TSM分别提高了4.4%和6.2%.

基于全局与局部感知网络的超高清图像去雾方法

当前,为实现图像全局建模的目的,基于多层感知机(multi-layer perceptron,MLP)的模型通常需要将图像上的像素进行平铺,之后实施一个自注意力机制或“混合”增强方案以获得图像的长范围依赖。然而,这些方法通常消耗大量的计算资源来弥补图像重建丢失的空间拓扑信息。特别是对于超高清图像去雾任务,大量堆积MLP的模型在资源受限的设备上执行一张超高清带雾图像时会出现内存溢出的问题。为了解决这个问题,本文提出了一种可以在单个GPU上对分辨率为4 k的图像进行实时去雾(110 f/s)的模型,该模型的建模过程中保持了图像空间结构信息,同时具有低计算复杂度的优点。

基于多尺度时空优化的空气质量预测方法

本文提出一种基于多尺度时空优化的空气质量预测方法(multi-scale spatial-temporal network for air quality prediction,MSSTN-AQP),结合空气质量系统中存在的长短期时间依赖关系和动态空间依赖性,提高长期空气质量预测的准确性。首先,通过构建多尺度时空特征提取模块,从多源异构数据中提取时空特征。其次,构建动态空间特征提取模块。通过将图卷积网络与注意力机制进行有效结合,捕捉空气质量网络中的全局空间特征,用于对多种空间依赖关系的联合建模。最后,构建时间特征提取模块,对Transformer模型进行改进与优化。自适应时间Transformer模块主要用于模拟跨多个时间步长的双向时间依赖关系。此外,将上述时空特征提取模块进行有效集成化,构建端到端的空气质量预测模型。为了验证模型的有效性,在两个真实数据集中进行实验验证。实验结果表明,MSSTN-AQP在预测精度上更具优势,尤其是在长期的空气质量预测任务中优势更加明显。

基于改进YOLOv5s的交通标识检测算法

针对交通标识在图像中占比小、检测精度低且周围环境复杂等问题,提出一种基于改进YOLOv5s的算法.首先,在主干网络部分添加注意力机制ECA(Efficient Channel Attention,高效通道注意力),增强网络的特征提取能力,有效解决了周围环境复杂的问题;其次,提出HASPP(Hybrid Atrous Spatial Pyramid Pooling,混合空洞空间金字塔池化),增强了网络结合上下文的能力;最后,修改网络中的Neck结构,使高层特征与底层特征有效融合,同时避免了跨卷积层造成的信息丢失.实验结果表明,改进后的算法在交通标识数据集上取得了94.4%的平均检测精度、74.1%的召回率以及94.0%的精确率,较原始算法分别提升了3.7、2.8、3.4个百分点.

基于CNN-BLSTM-XGB的入侵检测

针对当前网络入侵检测方法存在特征信息提取不全面,多分类检测准确率偏低的问题,提出一种基于CNN-BLSTM-XGB的混合网络入侵检测方法。建立基于卷积神经网络(CNN)与双向长短期记忆网络(BLSTM)的网络结构CNN-BLSTM,用于提取网络入侵数据的空间与时间特征;使用Keras序贯模型中的Concatenate层对这两种特征进行融合;用极端梯度提升(XGBoost)取代传统的完全连接层,获取从输入层到融合层的特征信息进行分类。在NSL-KDD和CICIDS2017数据集上分别进行的实验结果表明,该方法可以分别达到99.72%、99.87%的多分类检测准确率,与现有的主流方法比较,具有更高的检测准确率。

多尺度特征融合注意力新冠肺炎病灶分割网络

新冠病毒传染性极强,尽早的诊断和治疗是减少疫情造成损失的关键因素。为辅助医生诊断新冠病情,高效、准确地从肺部CT切片中分割新冠病灶,提出了一种改进的编码器-解码器深度神经网络———多尺度融合注意力网络MSANet(Multi-scale Attention Network),以图像分割效果较为出色的U-Net网络为基础,通过全局池化层和设置空洞卷积的采样率,增大网络感受野,捕获多尺度信息,实现对大目标的有效分割;使用通道注意力与空间注意力,在空间维度上建模,有效提取图像深层特征。测试结果表明,改进后的算法与U-Net网络相比,分割的平均交并比提升了1.46%,类别平均像素准确率提升了0.8%,准确率提升了1.17%。

基于双分支交互的实时语义分割算法

针对双分支实时语义分割算法存在双分支交互差、多尺度上下文信息提取不完善等问题,提出了基于双分支交互的实时语义分割网络(dual-branch interactive multi-scale fusion network for real-time semantic segmentation,DIMFNet)。算法以引导聚合双边语义分割网络(bilateral network with guided aggregation for real-time semantic segmentation,BiseNetV2)的双分支结构为基准进行改进,空间分支提取空间细节特征,上下文分支提取深层上下文特征。结合注意力思想提出注意力引导高级语义融合模块(attention guide high-level semantics fusion module,AGHSM)实现双分支的交互融合,以获得更好的空间特征表示;对金字塔池化模块进行改进,提出采用多层聚合金字塔池化模块(multi-layer aggregation pyramid pooling module,MAPPM)提取多尺度上下文特征,以获得更好的上下文特征表示。算法在Cityscapes数据集上进行消融实验并与现有实时语义分割网络进行对比,验证了各模块的有效性,以124.5 f/s达到了77.9%的平均交并比(mean intersection over union,MIoU);在CamVid数据集上以211.1 f/s达到了75.1%的MIoU。相比现有的实时语义分割网络,本文算法更好地权衡了分割的精度和速度。

Abnormal Traffic Detection for Internet of Things Based on an Improved Residual Network

Along with the progression of Internet of Things(IoT)technology,network terminals are becoming continuously more intelligent.IoT has been widely applied in various scenarios,including urban infrastructure,transportation,industry,personal life,and other socio-economic fields.The introduction of deep learning has brought new security challenges,like an increment in abnormal traffic,which threatens network security.Insufficient feature extraction leads to less accurate classification results.In abnormal traffic detection,the data of network traffic is high-dimensional and complex.This data not only increases the computational burden of model training but also makes information extraction more difficult.To address these issues,this paper proposes an MD-MRD-ResNeXt model for abnormal network traffic detection.To fully utilize the multi-scale information in network traffic,a Multi-scale Dilated feature extraction(MD)block is introduced.This module can effectively understand and process information at various scales and uses dilated convolution technology to significantly broaden the model’s receptive field.The proposed Max-feature-map Residual with Dual-channel pooling(MRD)block integrates the maximum feature map with the residual block.This module ensures the model focuses on key information,thereby optimizing computational efficiency and reducing unnecessary information redundancy.Experimental results show that compared to the latest methods,the proposed abnormal traffic detection model improves accuracy by about 2%.

Integrating Transformer and Bidirectional Long Short-Term Memory for Intelligent Breast Cancer Detection from Histopathology Biopsy Images

Breast cancer is a significant threat to the global population,affecting not only women but also a threat to the entire population.With recent advancements in digital pathology,Eosin and hematoxylin images provide enhanced clarity in examiningmicroscopic features of breast tissues based on their staining properties.Early cancer detection facilitates the quickening of the therapeutic process,thereby increasing survival rates.The analysis made by medical professionals,especially pathologists,is time-consuming and challenging,and there arises a need for automated breast cancer detection systems.The upcoming artificial intelligence platforms,especially deep learning models,play an important role in image diagnosis and prediction.Initially,the histopathology biopsy images are taken from standard data sources.Further,the gathered images are given as input to the Multi-Scale Dilated Vision Transformer,where the essential features are acquired.Subsequently,the features are subjected to the Bidirectional Long Short-Term Memory(Bi-LSTM)for classifying the breast cancer disorder.The efficacy of the model is evaluated using divergent metrics.When compared with other methods,the proposed work reveals that it offers impressive results for detection.

基于空时模型的航空管路卡箍故障诊断研究

针对航空液压管路卡箍振动信号受强噪声干扰,导致航空卡箍故障难以精准识别的问题,提出一种空时模型的航空卡箍故障诊断新方法。建立空间特征提取模型,对航空卡箍的故障特征进行局部融合。在空间模型中引入GRU模块,提取航空卡箍故障信号中的全局特征。结果表明:设计的空时故障诊断模型可实现航空卡箍故障的精准识别。与目前所用的深度卷积神经网络模型、门控循环单元神经网络模型、循环神经网络模型、支持向量机和误差反向传播神经网络模型等5种先进的故障诊断方法进行对比分析,所提方法对航空卡箍故障识别具有优越性。

钢材表面缺陷检测的YOLOv5s算法优化研究

针对YOLOv5对钢材缺陷复杂特征提取能力不足且检测结果易受背景环境干扰等问题,提出一种基于YOLOv5s的钢材表面缺陷检测算法。该算法在Backbone的核心特征提取模块C3中引入CBAM注意力,提升Backbone层对于关键信息的关注度;利用CARAFE替换最近邻插值算法,降低了上采样操作对于特征信息造成的损失;提出用融合跨阶段局部网络的金字塔池化结构SPPCPSC替换YOLOv5中的SPPF,提升网络的表达能力和感知能力。实验结果表明,提出YOLOv5s改进模型在NEU-DET数据集上的mAP@0.5达到了76.6%,比YOLOv5s提升2.3个百分点,模型参数量与基线模型基本一致,而CARAFE是导致改进模型检测速度降低的主要原因。除此,实验结果还发现CARAFE与SPPCSPC_group组合使用,对于模型的检测准确度有良好的提升作用。