Prediction of Uncertainty Estimation and Confidence Calibration Using Fully Convolutional Neural Network

Convolution neural networks(CNNs)have proven to be effective clinical imagingmethods.This study highlighted some of the key issues within these systems.It is difficult to train these systems in a limited clinical image databases,and many publications present strategies including such learning algorithm.Furthermore,these patterns are known formaking a highly reliable prognosis.In addition,normalization of volume and losses of dice have been used effectively to accelerate and stabilize the training.Furthermore,these systems are improperly regulated,resulting in more confident ratings for correct and incorrect classification,which are inaccurate and difficult to understand.This study examines the risk assessment of Fully Convolutional Neural Networks(FCNNs)for clinical image segmentation.Essential contributions have been made to this planned work:1)dice loss and cross-entropy loss are compared on the basis of segment quality and uncertain assessment of FCNNs;2)proposal for a group model for assurance measurement of full convolutional neural networks trained with dice loss and group normalization;And 3)the ability of the measured FCNs to evaluate the segment quality of the structures and to identify test examples outside the distribution.To evaluate the study’s contributions,it conducted a series of tests in three clinical image division applications such as heart,brain and prostate.The findings of the study provide significant insights into the predictive ambiguity assessment and a practical strategies for outside-distribution identification and reliable measurement in the clinical image segmentation.The approaches presented in this research significantly enhance the reliability and accuracy rating of CNNbased clinical imaging methods.

Intelligent Detection Model Based on a Fully Convolutional Neural Network for Pavement Cracks

The crack is a common pavement failure problem.A lack of periodic maintenance will result in extending the cracks and damage the pavement,which will affect the normal use of the road.Therefore,it is significant to establish an efficient intelligent identification model for pavement cracks.The neural network is a method of simulating animal nervous systems using gradient descent to predict results by learning a weight matrix.It has been widely used in geotechnical engineering,computer vision,medicine,and other fields.However,there are three major problems in the application of neural networks to crack identification.There are too few layers,extracted crack features are not complete,and the method lacks the efficiency to calculate the whole picture.In this study,a fully convolutional neural network based on ResNet-101 is used to establish an intelligent identification model of pavement crack regions.This method,using a convolutional layer instead of a fully connected layer,realizes full convolution and accelerates calculation.The region proposals come from the feature map at the end of the base network,which avoids multiple computations of the same picture.Online hard example mining and data-augmentation techniques are adopted to improve the model’s recognition accuracy.We trained and tested Concrete Crack Images for Classification(CCIC),which is a public dataset collected using smartphones,and the Crack Image Database(CIDB),which was automatically collected using vehicle-mounted charge-coupled device cameras,with identification accuracy reaching 91.4%and 86.4%,respectively.The proposed model has a higher recognition accuracy and recall rate than Faster RCNN and different depth models,and can extract more complete and accurate crack features in CIDB.We also analyzed translation processing,fuzzy,scaling,and distorted images.The proposed model shows a strong robustness and stability,and can automatically identify image cracks of different forms.It has broad application prospects in practical engineering problems.

Reconstructing the 3D digital core with a fully convolutional neural network

In this paper, the complete process of constructing 3D digital core by fullconvolutional neural network is described carefully. A large number of sandstone computedtomography (CT) images are used as training input for a fully convolutional neural networkmodel. This model is used to reconstruct the three-dimensional (3D) digital core of Bereasandstone based on a small number of CT images. The Hamming distance together with theMinkowski functions for porosity, average volume specifi c surface area, average curvature,and connectivity of both the real core and the digital reconstruction are used to evaluate theaccuracy of the proposed method. The results show that the reconstruction achieved relativeerrors of 6.26%, 1.40%, 6.06%, and 4.91% for the four Minkowski functions and a Hammingdistance of 0.04479. This demonstrates that the proposed method can not only reconstructthe physical properties of real sandstone but can also restore the real characteristics of poredistribution in sandstone, is the ability to which is a new way to characterize the internalmicrostructure of rocks.

Automated Delineation of Smallholder Farm Fields Using Fully Convolutional Networks and Generative Adversarial Networks

Accurate boundaries of smallholder farm fields are important and indispensable geo-information that benefits farmers,managers,and policymakers in terms of better managing and utilizing their agricultural resources.Due to their small size,irregular shape,and the use of mixed-cropping techniques,the farm fields of smallholder can be difficult to delineate automatically.In recent years,numerous studies on field contour extraction using a deep Convolutional Neural Network(CNN)have been proposed.However,there is a relative shortage of labeled data for filed boundaries,thus affecting the training effect of CNN.Traditional methods mostly use image flipping,and random rotation for data augmentation.In this paper,we propose to apply Generative Adversarial Network(GAN)for the data augmentation of farm fields label to increase the diversity of samples.Specifically,we propose an automated method featured by Fully Convolutional Neural networks(FCN)in combination with GAN to improve the delineation accuracy of smallholder farms from Very High Resolution(VHR)images.We first investigate four State-Of-The-Art(SOTA)FCN architectures,i.e.,U-Net,PSPNet,SegNet and OCRNet,to find the optimal architecture in the contour detection task of smallholder farm fields.Second,we apply the identified optimal FCN architecture in combination with Contour GAN and pixel2pixel GAN to improve the accuracy of contour detection.We test our method on the study area in the Sudano-Sahelian savanna region of northern Nigeria.The best combination achieved F1 scores of 0.686 on Test Set 1(TS1),0.684 on Test Set 2(TS2),and 0.691 on Test Set 3(TS3).Results indicate that our architecture adapts to a variety of advanced networks and proves its effectiveness in this task.The conceptual,theoretical,and experimental knowledge from this study is expected to seed many GAN-based farm delineation methods in the future.

基于FCNN和ICAE的SAR图像目标识别方法

近年来,基于卷积神经网络(Convolutional Neural Network, CNN)的合成孔径雷达(Synthetic Aperture Radar, SAR)图像目标识别得到深入研究。全卷积神经网络(Fully Convolutional Neural Network, FCNN)是CNN结构上的改进,它比CNN能获得更高的识别率,但在训练过程中仍需要大量的带标签训练样本。该文提出一种基于FCNN和改进的卷积自编码器(Improved Convolutional Auto-Encoder, ICAE)的SAR图像目标识别方法,即先用ICAE无监督训练方式获得的编码器网络参数初始化FCNN的部分参数,后用带标签训练样本对FCNN进行训练。基于MSTAR数据集的十类目标分类实验结果表明,在不扩充带标签训练样本的情况下,该方法不仅能获得98.14%的平均正确识别率,而且具有较强的抗噪声能力。

How to accurately extract large-scale urban land?Establishment of an improved fully convolutional neural network model

Realizing accurate perception of urban boundary changes is conducive to the formulation of regional development planning and researches of urban sustainable development.In this paper,an improved fully convolution neural network was provided for perceiving large-scale urban change,by modifying network structure and updating network strategy to extract richer feature information,and to meet the requirement of urban construction land extraction under the background of large-scale low-resolution image.This paper takes the Yangtze River Economic Belt of China as an empirical object to verify the practicability of the network,the results show the extraction results of the improved fully convolutional neural network model reached a precision of kappa coefficient of 0.88,which is better than traditional fully convolutional neural networks,it performs well in the construction land extraction at the scale of small and medium-sized cities.

基于深度全卷积神经弹性网络WCGAN-GP模型的语音增强研究

Wasserstein距离生成对抗网络(Wasserstein Generative Adversal Network,WGAN)模型^([1])在语音增强中运用广泛,但存在梯度易爆炸、性能不稳定等问题。引入梯度惩罚(Gradient Penalty,GP)和弹性网络条件约束,并将生成器和判别器优化成深度全卷积神经网络(Deep Fully Convolutional Neural Networks,DFCNN)结构,提出一种基于DFCNN的弹性网络条件梯度惩罚(Wasserstein Conditional Generative Adversal Network Gradient Penalty,WCGAN-GP)模型。改进后的模型可以达到真实Lipschitz限制条件,提高了可控性、稳定性和特征提取能力,能更快优化训练。实验将改进后的模型与WGAN对不同噪声条件下的语音进行增强,结果证实了改进后的模型在语音增强方面的优越性。

基于RIS的元素分组面状全连接网络

针对神经网络全连接层在训练中参数量多、所占内存多、易产生过拟合问题,从智能超表面(reconfigurable intelligence surface,RIS)结构特征出发,提出了一种基于RIS的元素分组面状全连接神经网络(RIS-based element grouping areal fully connected neural network,RGFCNN)。借鉴RIS的结构特征,在传统全连接神经网络上进行优化。设计了透射面注意力机制用于数据有效特征提取,相比于传统的全连接网络,该网络没有对数据进行一维排列,而是提出了一种运用于神经网络构建的元素分组策略,直接对二维面状数据进行分组全连接处理,各组处理输出进行数据串联。实验结果表明:在公开的具有IQ数据特征的通信信号数据集上,RGFCNN在信噪比大于0 dB时具有更好的识别精度,而训练参数是原来的大约1/6。

图像分割算法在医学图像中的应用综述

医学图像分割是计算机辅助诊断领域的一项关键技术,其主要任务是将特定的器官、组织或异常区域从图像中准确地识别出来。但是医学图像的质量易受到其复杂纹理和成像设备限制(如噪声和边界不清晰)的影响,故传统的医学图像分割方法已难以满足现实临床需求。随着深度学习技术的进步,基于这一领域的算法已经取得了显著的进展。本文首先回顾了七种传统的医学图像分割策略,并重点介绍了两种当前主流的深度学习方法:全卷积神经网络和U-Net,最后文章探讨了目前深度学习技术所面临的挑战及其可能的解决策略。

Automatic Detection of Lung Nodules Using 3D Deep Convolutional Neural Networks

Lung cancer is the leading cause of cancer deaths worldwide. Accurate early diagnosis is critical in increasing the 5-year survival rate of lung cancer, so the efficient and accurate detection of lung nodules,the potential precursors to lung cancer, is paramount. In this paper, a computer-aided lung nodule detection system using 3D deep convolutional neural networks(CNNs) is developed. The first multi-scale 11-layer 3D fully convolutional neural network(FCN) is used for screening all lung nodule candidates. Considering relative small sizes of lung nodules and limited memory, the input of the FCN consists of 3D image patches rather than of whole images. The candidates are further classified in the second CNN to get the final result. The proposed method achieves high performance in the LUNA16 challenge and demonstrates the effectiveness of using 3D deep CNNs for lung nodule detection.

FCNN深度学习模型及其在动物语音识别中的应用

为解决使用语音信号准确识别动物以保护和研究野生动物的问题,提出一种全连接算法与稀疏连接算法相结合的全卷积神经网络(FCNN:Fully Convolutional Neural Network),用于语音的自动识别。利用全连接算法提取更多的组合特征,稀疏连接算法筛选重要特征可加快收敛速度。同时给出了具体的模型结构及算法流程,并进行了动物语音识别实验。实验结果表明,该全卷积神经网络深度学习算法是一种语音自动识别的有效方法,解决了蛙声识别问题,为动物语音识别提供参考。

Marine aquaculture mapping using GF-1 WFV satellite images and full resolution cascade convolutional neural network

Growing demand for seafood and reduced fishery harvests have raised intensive farming of marine aquaculture in coastal regions,which may cause severe coastal water problems without adequate environmental management.Effective mapping of mariculture areas is essential for the protection of coastal environments.However,due to the limited spatial coverage and complex structures,it is still challenging for traditional methods to accurately extract mariculture areas from medium spatial resolution(MSR)images.To solve this problem,we propose to use the full resolution cascade convolutional neural network(FRCNet),which maintains effective features over the whole training process,to identify mariculture areas from MSR images.Specifically,the FRCNet uses a sequential full resolution neural network as the first-level subnetwork,and gradually aggregates higher-level subnetworks in a cascade way.Meanwhile,we perform a repeated fusion strategy so that features can receive information from different subnetworks simultaneously,leading to rich and representative features.As a result,FRCNet can effectively recognize different kinds of mariculture areas from MSR images.Results show that FRCNet obtained better performance than other classical and recently proposed methods.Our developed methods can provide valuable datasets for large-scale and intelligent modeling of the marine aquaculture management and coastal zone planning.

残差网络在图像分类上的轻量化研究

卷积神经网络由于其出色的性能,在计算机视觉领域被广泛使用。但是由于卷积神经网络其自身特性所限制,常常出现训练所需数据量大、模型训练困难等问题。为了达到模型轻量化的目的,文章改进了网络的基本模块,并将卷积核进行分解,使用卷积层代替全连接层,以达到减少参数量。实验证明所提出的模型分类正确率为90.5%,而且提出的模型在与ResNet18分类正确率相差无几的情况下,大幅度减少参数量和计算量,具有一定的应用价值。

基于全卷积残差收缩网络的地震波阻抗反演

卷积神经网络对地震波阻抗反演已经能取得不错的效果,但反演精度、抗噪声性能有待提高,针对此问题,本文提出了一种基于带逐通道阈值的全卷积残差收缩网络(FCRSN-CW)的地震波阻抗反演方法。该方法首先在残差网络的结构上加入了“注意力机制”和“软阈值化”构成反演网络,然后用波阻抗数据通过正演计算得到合成地震数据集,接着用该数据集训练全卷积残差收缩网络,最后将地震数据输入到训练好的网络中,直接得到反演结果。理论模型反演结果表明,该网络能准确地反演出波阻抗,具有良好的学习能力和抗噪声性能。实测数据反演结果表明,该方法能有效解决地震波阻抗反演问题。

基于软硬协作决策的半监督珊瑚礁底质分类方法

珊瑚礁底质分类对海洋资源开发和海洋生态环境保护起到至关重要的作用。目前,深度学习语义分割方法在遥感图像分类领域应用广泛,但在底质分类方面的研究较少。由于基于全监督深度学习的方法中逐像素标注标签的成本较高,不适用于大规模、高频次的底质分类工作,基于半监督的深度学习方法能够有效利用已标注标签为无标签数据产生伪标签,从而有效降低人工成本,然而现有半监督方法的性能易受伪标签噪声的干扰。针对以上问题,本文提出了一种基于软硬协作决策的半监督底质分类方法。首先,利用多模型联合决策生成高质量的伪标签;然后,提出了一种能够顾及伪标签像素置信度的损失函数来指导模型进行训练;最后,采用软硬协作的决策方式得到精确的底质分类结果。在美属维尔京群岛圣克罗伊岛北部的巴克岛礁和夏威夷群岛的中途岛东南约400km处的珍珠与爱马仕环礁的浅层底栖生物栖息地地图数据集上评估了本文方法的精度,实验结果表明,本文提出的方法与全监督学习方法精度相当,比主流的语义分割方法精度平均高3.08%,能够有效服务于珊瑚礁底质调查工作。

遥感自动提取技术在房屋抗震调查中的应用

房屋抗震能力调查对于全面摸清地震灾害风险底数,预测地震灾害损失具有十分重要的意义。传统实地调查方法难以大范围开展,而依靠经验估计和人工解译的遥感房屋抗震能力评价的效率仍有待提高。针对此问题,文章以深度学习遥感目标识别算法为基础,提出了多尺度聚合的房屋自动提取方法,并将该方法应用于湖北省房屋抗震能力遥感初判,自动提取房屋建筑共计1 060万余栋,并对其抗震能力进行了分类判别。经与试点县实地调查结果对比,文章方法房屋提取误差总体在10%以内,房屋抗震能力判别准确度在72.3%~90.9%之间。实验结果表明文章方法可为全国自然灾害风险普查工程房屋调查工作提供技术支持。

基于完全残差的双分支去雨网络

针对使用深度学习的单幅图像去雨算法会导致细节信息丢失的问题,提出了一个双分支去雨网络,包括雨痕提取分支和细节恢复分支,通过补全细节使去雨图像更接近真实图像。雨痕提取分支的目的是完全提取出雨纹,通过构造特征金字塔来多尺度地学习雨纹信息,并在其中引入执行了全部身份映射的完全残差块来加强特征的重用和传播。为充分利用上下文信息,采用可变形卷积在动态扩大感受野的同时避免了网格伪影的产生,最后输入雨图去除雨痕便得到了初步去雨图。细节恢复分支需要产生细节特征图反馈给初步去雨图像来找回丢失的细节,使用轻量级的完全残差块捕捉特征信息,并用跳跃连接来连接完全残差块提供长距离的信息补偿。实验结果表明,该网络在合成数据集Rain100H中比较RESCAN、SPANet和JDNet等主流去雨方法,在PSNR和SSIM指标上分别至少提高了0.09 dB和0.02,在真实数据集和自制数据集中的去雨效果和细节保留程度均优于对比方法。

基于关键特征优化的电力系统短期负荷预测方法

短期电力负荷的准确预测是电力系统安全经济运行的重要条件。为了提高电力系统短期负荷预测的准确性,提出一种基于关键特征优化的电力系统短期负荷预测方法。首先,对影响电力系统短期负荷的气象特征、日类型特征和历史负荷特征的构建方法进行优化,为负荷预测模型提供更多先验知识;然后,考虑输入特征和输出预测向量的特点,构建结合卷积神经网络与全连接层的短期电力负荷预测模型;最后,通过算例验证基于关键特征优化的电力系统短期负荷预测方法在实际负荷预测任务中的效果。算例结果表明,对气象特征、日类型特征和历史负荷特征等关键特征的优化,均有利于提升电力系统短期负荷预测的准确性。

基于卷积神经网络的气体传感器阵列识别算法研究及应用

为解决混合气氛中气体浓度识别问题,常利用气体传感器阵列配合模式识别算法进行检测。设计了基于嵌入式处理器的传感器阵列,并利用识别算法对设备采集的混合气体进行分类识别及浓度预测。建立了以氨气、丙酮、甲醇气体为目标的混合气体数据集。使用最邻近分类算法(KNN)、三层全连接反向神经网络(BPNN)和三层卷积神经网络(CNN)分别对混合气体中的氨气、丙酮、甲醇气体进行识别分析。测试结果表明:改进的BPNN和CNN对测试数据集的分类识别率最高均可达100%,对混合气体的浓度预测均方差最低可达3.89和2.47,三层卷积层的CNN算法相对于BPNN和KNN在识别精度上提高明显。通过迁移学习思想,将该算法移植到树莓派中,并进行实际测试,实现了电子鼻应用。

基于改进RCF模型的转子表面缺陷检测

针对发动机转子表面存在磕划伤和凸起等弱对比度微小缺陷难以检测的问题,提出一种利用多方向照明结合卷积神经网络模型的发动机转子表面缺陷检测方法。首先,采用光度立体法获得增强图形凹凸性特征的曲率图和高度图,作为输入图像;其次,提出一种优化的更丰富的卷积特征网络(Richer Convolutional Features Network)模型,充分利用跳层连接将首阶段与后续阶段的侧输出特征融合,提高网络深层对精细尺度下信息的保留能力;通过通道及空间注意力机制对模型侧输出进行强化,增强有效特征并抑制干扰;优化损失函数,使数据集中无缺陷信息的图像样本也能够适用于网络模型的训练;最后,以人工标注的方式制作数据集并验证优化模型的有效性。试验结果表明,与经典的缺陷检测方法相比,全卷积网络对部分缺陷的区分能力较差,本文方法对转子的表面缺陷区域具有更好的检测效果,改进模型的像素准确率达94.31%,比RCF提高了0.87个百分点。