融合数据增强与改进ResNet34的奶牛热红外图像乳腺炎检测

乳腺炎是奶牛生产养殖中最为严重的疾病之一,奶牛乳腺炎的早期检测可以为后续治疗提供依据,从而提高疾病治疗效率,降低养殖风险。为了对自然行走的奶牛实现快速、高精度的“一步式”乳腺炎疾病检测,提出了一种基于热红外图像,融合数据增强与改进ResNet34的奶牛乳腺炎疾病检测方法。相对于现有的“多步式”奶牛红外图像乳腺炎检测方法,该方法无需奶牛关键部分如乳房和眼睛的定位以及温度提取等,可有效避免“多步式”造成的误差累计,从而实现更高效的乳腺炎检测。首先,将包含奶牛关键部位的局部图片水平拼接成信息完整的整体图片,结合RandAugment数据增强方法扩增训练样本;其次,采用ResNet34残差网络作为实验的基础网络,并根据热红外图像特性对模型进行如下改进：（1）精简网络内部冗余层使得模型更轻量化;（2）中间层添加辅助分类器弥补由于模型精简带来的特征损失;（3）将改进的多融合池化层代替原有单一池化层,使得特征提取内容更丰富。随机选取3 298张热红外图像（66头奶牛）作为实验对象,并设置多组对比实验,结果表明: 与传统ResNet34相比改进后ResNet34模型分类准确率提高3.4%,基于改进ResNet34并融合迁移学习和数据增强的模型验证准确率达到90.3%,测试准确率为88.4%,分类时间仅需3.39×10-3 s。为了保证实验数据集的样本独立性,进一步将奶牛个体数量按照3∶1∶1划分为训练集、验证集和测试集,测得模型测试准确率达到80.3%,证明所提出模型具有很好的鲁棒性。根据测试结果,计算出模型查准率为91.2%、查全率为91.6%、F1分数为91.4%,与前人所做实验相比准确率提高了5.1%,特异度提升5.3%。该研究方法可以为初期奶牛乳腺疾病筛选和医学诊断提供辅助和参考。     

ResNet及其在医学图像处理领域的应用:研究进展与挑战

残差神经网络(ResNet)是深度学习领域的研究热点,广泛应用于医学图像处理领域.该文对残差神经网络从以下几个方面进行综述:首先,阐述残差神经网络的基本原理和模型结构;然后,从残差单元、残差连接和网络整体结构3方面总结了残差神经网络的改进机制;其次,从与DenseNet,U-Net,Inception结构和注意力机制结...     

基于改进深度残差网络算法的智能干扰识别

现网运维人力成本高、效率低,如何快速精准识别网络干扰类型、提高运维人员工作效率,成为亟待解决的问题。提出一种基于改进深度残差网络（ResNet）的智能干扰识别方法,通过对接运营商北向网管的通信干扰数据接口,对干扰数据进行采集和预处理,并结合现网专家经验对历史干扰数据类型进行标注和校正,形成离线干扰数据集。再将干扰频域信息进行图像化生成干扰频谱波形图,并针对不同干扰类型进行图像处理和数据处理。之后根据业务特点对传统ResNet算法进行改进,通过提取单一干扰类型特征,确定各特征在复合干扰类型中的权重,达到对任意干扰类型识别的目的。最后通过导入已训练好的模型对干扰数据进行在线识别,有效提高干扰识别的准确率和效率。     

Framework for COVID-19 Segmentation and Classification Based on Deep Learning of Computed Tomography Lung Images

Corona Virus Disease 2019 (COVID-19) has affected millions of people worldwide and caused more than 6.3 million deaths (World Health Organization, June 2022). Increased attempts have been made to develop deep learning methods to diagnose COVID-19 based on computed tomography (CT) lung images. It is a challenge to reproduce and obtain the CT lung data, because it is not publicly available. This paper introduces a new generalized framework to segment and classify CT images and determine whether a patient is tested positive or negative for COVID-19 based on lung CT images. In this work, many different strategies are explored for the classification task. ResNet50 and VGG16 models are applied to classify CT lung images into COVID-19 positive or negative. Also, VGG16 and ReNet50 combined with U-Net, which is one of the most used architectures in deep learning for image segmentation, are employed to segment CT lung images before the classifying process to increase system performance. Moreover, the image size dependent normalization technique (ISDNT) and Wiener filter are utilized as the preprocessing techniques to enhance images and noise suppression. Additionally, transfer learning and data augmentation techniques are performed to solve the problem of COVID-19 CT lung images deficiency, therefore the over-fitting of deep models can be avoided. The proposed frameworks, which comprised of end-to-end, VGG16, ResNet50, and U-Net with VGG16 or ResNet50, are applied on the dataset that is sourced from COVID-19 lung CT images in Kaggle. The classification results show that using the preprocessed CT lung images as the input for U-Net hybrid with ResNet50 achieves the best performance. The proposed classification model achieves the 98.98% accuracy (ACC), 98.87% area under the ROC curve (AUC), 98.89% sensitivity (Se), 97.99 % precision (Pr), 97.88% F₁-score, and 1.8974-seconds computational time.     

一种引入聚焦机制的静态图像人体分割方法

针对静态图像中人体分割不能够聚焦所要分割区域,造成分割效果不佳的问题.通过对残差网络进行改进,使之能够适应人体分割这一任务,并在改进的残差网络中引入一种聚焦机制进行静态图像人体分割.根据静态图像人体分割问题,设计了具有聚焦机制的损失函数、辅助分割损失函数以及分割损失函数.另外,为了得到数据集的辅助分割类标、分割类标以及注意力聚焦图,提出了数据预处理算法.在Pascal-Person-Part数据集和LIP数据集上进行训练和测试,并将测试结果与SegNet,FCN-8s,DeepLabV2,Attention,LG-LSTM以及Attention+ SSL方法进行比较.通过比较像素精度、平均像素精度和IoU(Intersection over Union)指标,表明所提方法能够提高静态图像中人体分割的效果,验证了所提方法的可靠性.     

基于注意力机制的多方向文本检测

针对多方向排列的文本因其尺度变化大、复杂背景干扰而导致检测效果仍不甚理想的问题,本文提出了一种基于注意力机制的多方向文本检测方法。首先,考虑到自然场景下干扰信息多,构建文本特征提取网络(text feature information ResNet50,TF-ResNet),对图像中的文本特征信息进行提取;其次,在特征融合模型中加入文本注意模块(text attention module, TAM),抑制无关信息的同时突出显示文本信息,以增强文本特征之间的潜在联系;最后,采用渐进扩展模块,逐步融合扩展前部分得到的多个不同尺度的分割结果,以获得精确检测结果。本文方法在数据集CTW1500、ICDAR2015上进行实验验证和分析,其F值分别达到80.4%和83.0%,比次优方法分别提升了2.0%和2.4%,表明该方法在多方向文本检测上与其他方法相比具备一定的竞争力。     

Target Classification Method of Tactile Perception Data with Deep Learning

In order to improve the accuracy of manipulator operation, it is necessary to install a tactile sensor on the manipulator to obtain tactile information and accurately classify a target. However, with the increase in the uncertainty and complexity of tactile sensing data characteristics, and the continuous development of tactile sensors, typical machine-learning algorithms often cannot solve the problem of target classification of pure tactile data. Here, we propose a new model by combining a convolutional neural network and a residual network, named ResNet10-v1. We optimized the convolutional kernel, hyperparameters, and loss function of the model, and further improved the accuracy of target classification through the K-means clustering method. We verified the feasibility and effectiveness of the proposed method through a large number of experiments. We expect to further improve the generalization ability of this method and provide an important reference for the research in the field of tactile perception classification.     

基于可见光谱和改进注意力的农作物病害识别

基于可见光谱的农作物病害自动化识别和诊断是一个具有挑战性的研究领域,但现有基于卷积神经网络进行病害识别的研究往往利用深层网络牺牲模型参数量来提高对单一农作物病害识别的准确率,从而造成硬件资源的浪费.为提高农作物病害识别的准确率且避免深层网络的使用,该研究将注意力机制引入农作物病害识别领域,提出了一种基于可见光谱和改进注...     

基于卷积网络通道注意力的人脸表情识别

针对目前人脸表情识别(Facial Expression Recognition, FER)方法准确率低、模型大和识别时间长的问题,提出了一种基于卷积神经网络的通道注意力FER算法,在普通的卷积层中加入Xception网络中的可分离卷积网络,减少参数量和运算成本。在可分离卷积层的输出加入通道注意力Senet,实现对输出通道的权值按重要程度进行重新分配。引入Resnet网络中残差机制,减轻梯度消失现象。对设计的模型分别在CK+,RAF-DB数据集和FER2013数据集进行训练。实验结果显示,在CK+,RAF-DB数据集和FER2013数据集准确率分别提高至99.45%,78.10%和62.65%。模型参数量仅有1.8 MB,识别时间1.24 s。实现了更准、更快、更轻的FER。     

An Indoor Localization System Using Residual Learning with Channel State Information

With the increasing demand of location-based services, neural network (NN)-based intelligent indoor localization has attracted great interest due to its high localization accuracy. However, deep NNs are usually affected by degradation and gradient vanishing. To fill this gap, we propose a novel indoor localization system, including denoising NN and residual network (ResNet), to predict the location of moving object by the channel state information (CSI). In the ResNet, to prevent overfitting, we replace all the residual blocks by the stochastic residual blocks. Specially, we explore the long-range stochastic shortcut connection (LRSSC) to solve the degradation problem and gradient vanishing. To obtain a large receptive field without losing information, we leverage the dilated convolution at the rear of the ResNet. Experimental results are presented to confirm that our system outperforms state-of-the-art methods in a representative indoor environment.