Data-augmented landslide displacement prediction using generative adversarial network

Landslides are destructive natural disasters that cause catastrophic damage and loss of life worldwide.Accurately predicting landslide displacement enables effective early warning and risk management.However,the limited availability of on-site measurement data has been a substantial obstacle in developing data-driven models,such as state-of-the-art machine learning(ML)models.To address these challenges,this study proposes a data augmentation framework that uses generative adversarial networks(GANs),a recent advance in generative artificial intelligence(AI),to improve the accuracy of landslide displacement prediction.The framework provides effective data augmentation to enhance limited datasets.A recurrent GAN model,RGAN-LS,is proposed,specifically designed to generate realistic synthetic multivariate time series that mimics the characteristics of real landslide on-site measurement data.A customized moment-matching loss is incorporated in addition to the adversarial loss in GAN during the training of RGAN-LS to capture the temporal dynamics and correlations in real time series data.Then,the synthetic data generated by RGAN-LS is used to enhance the training of long short-term memory(LSTM)networks and particle swarm optimization-support vector machine(PSO-SVM)models for landslide displacement prediction tasks.Results on two landslides in the Three Gorges Reservoir(TGR)region show a significant improvement in LSTM model prediction performance when trained on augmented data.For instance,in the case of the Baishuihe landslide,the average root mean square error(RMSE)increases by 16.11%,and the mean absolute error(MAE)by 17.59%.More importantly,the model’s responsiveness during mutational stages is enhanced for early warning purposes.However,the results have shown that the static PSO-SVM model only sees marginal gains compared to recurrent models such as LSTM.Further analysis indicates that an optimal synthetic-to-real data ratio(50%on the illustration cases)maximizes the improvements.This also demonstrates the robustness and effectiveness of supplementing training data for dynamic models to obtain better results.By using the powerful generative AI approach,RGAN-LS can generate high-fidelity synthetic landslide data.This is critical for improving the performance of advanced ML models in predicting landslide displacement,particularly when there are limited training data.Additionally,this approach has the potential to expand the use of generative AI in geohazard risk management and other research areas.

Free form deformation and symmetry constraint‐based multimodal brain image registration using generative adversarial nets

Multi‐modal brain image registration has been widely applied to functional localisation,neurosurgery and computational anatomy.The existing registration methods based on the dense deformation fields involve too many parameters,which is not conducive to the exploration of correct spatial correspondence between the float and reference images.Meanwhile,the unidirectional registration may involve the deformation folding,which will result in the change of topology during registration.To address these issues,this work has presented an unsupervised image registration method using the free form deformation(FFD)and the symmetry constraint‐based generative adversarial networks(FSGAN).The FSGAN utilises the principle component analysis network‐based structural representations of the reference and float images as the inputs and uses the generator to learn the FFD model parameters,thereby producing two deformation fields.Meanwhile,the FSGAN uses two discriminators to decide whether the bilateral registration have been realised simultaneously.Besides,the symmetry constraint is utilised to construct the loss function,thereby avoiding the deformation folding.Experiments on BrainWeb,high grade gliomas,IXI and LPBA40 show that compared with state‐of‐the‐art methods,the FSGAN provides superior performance in terms of visual comparisons and such quantitative indexes as dice value,target registration error and computational efficiency.

基于GAN和MS-ResNet的房颤自动检测模型

房颤是一种常见的心律失常疾病,针对现有研究工作大多依赖于单尺度信号段而忽略了不同尺度下潜在的互补信息和数据不平衡问题导致诊断性能下降的问题,提出了一种新颖的基于生成对抗网络(generative adversarial network, GAN)和多尺度残差网络(multiscale residual net, MS-ResNet)的房颤自动检测模型,该网络使用GAN合成具有高形态相似性的单导联心电数据来解决数据的隐私和不平衡问题。同时,设计了MS-ResNet特征提取策略,从不同尺度提取不同大小信号段的特征,从而有效地捕捉P波消失和RR间期不规则特征。该模型联合这两种策略不仅为房颤自动检测生成高质量心电图(electrocardiogram,ECG)数据,还可以利用多尺度网格提取不同波之间的时序特征。在PhysioNet Challenge2017公开ECG数据集上以及平衡后的数据集上评估了MS-ResNet的性能,并将其与现有的房颤分类模型进行了比较。实验结果表明,MS-ResNet在平衡后的数据集上平均F1值和精确率分别达到0.914 1和91.56%,与不平衡数据集相比,F1提高了4.5%,精确率提高了3.5%。

MACDCGAN的发电机轴承故障诊断方法

在实际工况中,发电机中传感器采集到的故障样本数据有限,使用基于深度学习的方法进行故障诊断存在过拟合问题导致模型泛化能力较差以及诊断精度不高。为了解决这个问题,采用样本扩充的思路,提出了一种改进的辅助分类器条件深度卷积生成对抗网络(MACDCGAN)的故障诊断方法。通过对采集的一维时序信号进行小波变换增强特征,构建简化结构参数的条件深度卷积生成对抗网络模型生成样本,并在模型中采用Wasserstein距离优化损失函数解决训练过程中存在模式崩塌和梯度消失的缺点;通过添加一个独立的分类器来改进分类模型的兼容性,并在分类器中引入学习率衰减算法增加模型稳定性。试验结果表明,该方法可以有效地提高故障诊断的精度,并且验证了所提模型具有良好的泛化性能。

基于图像小波域自适应干扰的GAN生成人脸反取证

针对现有生成对抗网络(GAN)生成人脸反取证方法攻击迁移性不强的问题,提出了一个基于图像小波域自适应干扰的GAN生成人脸反取证方法以提升攻击迁移性.该方法通过对GAN生成人脸图像的小波域信息(即图像经过小波分解后的频率分量)施加扰动以实现其对取证模型的抵抗,并且分别在空域和频域上基于最小可觉察误差(JND)设计自适应扰动阈值,对图像不同像素点位置设置不同的扰动强度,从而增强扰动的人眼不可感知性.此外,还设计了一种数据增强方式对反取证人脸进行数据分布多样性扩充,以进一步提升攻击迁移性.实验结果表明,与6种基线方法相比,所提方法生成的反取证人脸在保证扰动对人眼不可感知前提下具有更强的攻击迁移性.

基于Transformer和GAN的对抗样本生成算法

对抗攻击与防御是计算机安全领域的一个热门研究方向。针对现有基于梯度的对抗样本生成方法可视质量差、基于优化的方法生成效率低的问题,提出基于Transformer和生成对抗网络(GAN)的对抗样本生成算法Trans-GAN。首先利用Transformer强大的视觉表征能力,将其作为重构网络,用于接收干净图像并生成攻击噪声;其次将Transformer重构网络作为生成器,与基于深度卷积网络的鉴别器相结合组成GAN网络架构,提高生成图像的真实性并保证训练的稳定性,同时提出改进的注意力机制Targeted Self-Attention,在训练网络时引入目标标签作为先验知识,指导网络模型学习生成具有特定攻击目标的对抗扰动;最后利用跳转连接将对抗噪声施加在干净样本上,形成对抗样本,攻击目标分类网络。实验结果表明:Trans-GAN算法针对MNIST数据集中2种模型的攻击成功率都达到99.9%以上,针对CIFAR10数据集中2种模型的攻击成功率分别达到96.36%和98.47%,优于目前先进的基于生成式的对抗样本生成方法;相比快速梯度符号法和投影梯度下降法,Trans-GAN算法生成的对抗噪声扰动量更小,形成的对抗样本更加自然,满足人类视觉不易分辨的要求。

基于改进MMD-GAN的可再生能源随机场景生成

针对可再生能源出力不确定性的准确表征问题,提出了一种基于改进的最大均值差异生成对抗网络(maximum mean discrepancy generative adversarial networks,MMD-GAN)的可再生能源随机场景生成方法。首先,阐述了GAN及MMD-GAN的基本原理,提出了MMD-GAN的改进方案,即在MMD-GAN的基础上改进鉴别器损失函数,并采用谱归一化和有界高斯核提升生成器和鉴别器的训练稳定性。然后,设计了基于改进MMD-GAN的可再生能源随机场景生成流程。最后,分析了所提方法在可再生能源随机场景生成中的效果,比较了改进MMD-GAN方法与MMD-GAN方法及典型GAN方法的性能差异。结果表明,改进MMD-GAN方法在生成分布和真实分布的Wasserstein距离上较对比方法降低超过50%,生成的场景精度得到有效提升。

融合门控变换机制和GAN的低光照图像增强方法

针对低光照图像增强过程中存在的配对图像数据依赖、细节损失严重和噪声放大问题,提出结合门控通道变换机制和生成对抗网络(GAN)的低光照图像增强方法AGR-GAN,该方法可以在没有低/正常光图像对的情况下进行训练。首先,设计特征提取网络,该网络由多个基于门控通道变换单元的多尺度卷积残差模块构成,以提取输入图像的全局上下文特征和多尺度局部特征信息;然后,在特征融合网络中,采用卷积残差结构将提取的深浅层特征进行充分融合,再引入横向跳跃连接结构,最大程度保留细节特征信息,获得最终的增强图像;最后,引入联合损失函数指导网络训练过程,抑制图像噪声,使增强图像色彩更自然匀称。实验结果表明,该方法在主观视觉分析和客观指标评价方面相较其他算法均具有显著优势,其能有效提高低光照图像的亮度和对比度,减弱图像噪声,增强后的图像更清晰且色彩更真实,峰值信噪比、结构相似度和无参考图像质量评价指标平均可达16.48 dB、0.93和3.37。

基于有效注意力和GAN结合的脑卒中EEG增强算法

在基于脑电的卒中分类诊断任务中,以卷积神经网络为基础的深度模型得到广泛应用,但由于卒中类别病患样本数量少,导致数据集类别不平衡,降低了分类精度。现有的少数类数据增强方法大多采用生成对抗网络(GAN),生成效果一般,虽然可通过引入缩放点乘注意力改善样本生成质量,但存储及运算代价往往较大。针对此问题,构建一种基于线性有效注意力的渐进式数据增强算法LESA-CGAN。首先,算法采用双层自编码条件生成对抗网络架构,分别进行脑电标签特征提取及脑电样本生成,并使生成过程逐层精细化;其次,通过在编码部分引入线性有效自注意力(LESA)模块,加强脑电的标签隐层特征提取,并降低网络整体的运算复杂度。消融与对比实验结果表明,在合理的编码层数与生成数据比例下,LESA-CGAN与其他基准方法相比计算资源占用较少,且在样本生成质量指标上实现了10%的性能提升,各频段生成的脑电特征样本均更加自然,同时将病患分类的准确率和敏感度提高到了98.85%和98.79%。

A Generative Adversarial Nets Method for Monitoring Data Generation on Aircraft Engines

A sufficient sample size of monitoring data becomes a key factor for describing aircraft engines state.Generative adversarial nets(GAN)can be used to expand the sample size based on the existing state monitoring information.In the paper,a GAN model is introduced to design an algorithm for generating the monitoring data of aircraft engines.This feasibility of the method is illustrated by an example.The experimental results demonstrate that the probability density distribution of generated data after a large number of network training iterations is consistent with the probability density distribution of monitoring data.The proposed method also effectively demonstrates the generated monitoring data of aircraft engine are in a reasonable range.The method can effectively solve the problem of inaccurate performance degradation evaluation caused by the small amount of aero?engine condition monitoring data.

基于改进WGAN考虑特征分布相似性的小样本负荷预测方法

对于综合能源系统中新接入用户,其往往由于历史数据匮乏而难以建立精准的短期负荷预测模型.本文基于迁移学习理论,提出了一种基于改进Wasserstein生成对抗网络(WGAN)的小样本负荷预测方法.首先,本文采用最大信息系数法量化各影响特征与负荷的相关性强弱.接着,将源域特征序列进行分割,计算各分割子序列与目标域小样本的实序列编辑距离确定初始源域.然后,引入卷积神经网络和长短期记忆模型建立源域预测网络.通过WGAN对齐目标域和源域负荷特征的空间分布,并在最优传输代价函数中加入局部特征损失以提高训练的稳定性和快速性.最后,将对抗训练后网络用于目标域负荷预测.采用该方法对某地区小样本负荷进行实验,结果表明,本文所提算法与其他预测模型相比能达到更高精度.

基于Transformer-GAN的农产品包装版式布局智能设计方法

本研究提出一种基于Transformer-GAN的农产品包装版式布局智能设计方法,旨在解决现阶段的农产品包装主要依赖通版包装、缺乏产品特色等问题。首先,设计了内容感知模块,学习包装设计的内容特征;其次,提出一种设计序列模块,对包装布局信息进行序列化处理;最后,融合内容感知和布局信息,使模型学习图像的内容特征和布局特征,输出包装版式布局设计图。与先前的模型相比,本研究模型具有更好的设计性能和可解释性,同时创新性地将布局智能设计方法应用于包装设计领域。实验结果表明,设计序列模块提升了设计的有效性,序列化的布局特征相较于非序列化的特征更能生成优质的布局。该模型具有较强的可解释性,在农产品包装版式设计上具有良好的生成性能。

联合注意力和条件GAN的被遮挡人体姿态和体形估计方法

基于图像的人体姿态和体形估计常常因人体被遮挡而充满挑战.为此,提出一种基于单幅图像的姿态和体形估计方法.首先提出多尺度的注意力模块策略,输出具有丰富上下文信息的多尺度注意力特征,以有效地获得不受遮挡影响的全局的姿态和体形分布;然后提出基于热图的条件生成对抗网络策略,将由关节热图得到的姿态估计作为约束,实现网格精细调整;最后借助这2个策略得到的姿态和体形估计方法实现全局预测和局部细节求精的结合.在Ubuntu环境下,在3DPW,3DOH50K和Human3.6M公开数据集上的实验结果表明,与SMPLify,GraphCMR和SPIN等方法相比,所提方法在身体部分被遮挡时重建效果更好,并在ACK,AVE和PA-MPJPE等定量评价指标上取得了更好的结果.

Feature-Based Augmentation in Sarcasm Detection Using Reverse Generative Adversarial Network

Sarcasm detection in text data is an increasingly vital area of research due to the prevalence of sarcastic content in online communication.This study addresses challenges associated with small datasets and class imbalances in sarcasm detection by employing comprehensive data pre-processing and Generative Adversial Network(GAN)based augmentation on diverse datasets,including iSarcasm,SemEval-18,and Ghosh.This research offers a novel pipeline for augmenting sarcasm data with Reverse Generative Adversarial Network(RGAN).The proposed RGAN method works by inverting labels between original and synthetic data during the training process.This inversion of labels provides feedback to the generator for generating high-quality data closely resembling the original distribution.Notably,the proposed RGAN model exhibits performance on par with standard GAN,showcasing its robust efficacy in augmenting text data.The exploration of various datasets highlights the nuanced impact of augmentation on model performance,with cautionary insights into maintaining a delicate balance between synthetic and original data.The methodological framework encompasses comprehensive data pre-processing and GAN-based augmentation,with a meticulous comparison against Natural Language Processing Augmentation(NLPAug)as an alternative augmentation technique.Overall,the F1-score of our proposed technique outperforms that of the synonym replacement augmentation technique using NLPAug.The increase in F1-score in experiments using RGAN ranged from 0.066%to 1.054%,and the use of standard GAN resulted in a 2.88%increase in F1-score.The proposed RGAN model outperformed the NLPAug method and demonstrated comparable performance to standard GAN,emphasizing its efficacy in text data augmentation.

Automated Video Generation of Moving Digits from Text Using Deep Deconvolutional Generative Adversarial Network

Generating realistic and synthetic video from text is a highly challenging task due to the multitude of issues involved,including digit deformation,noise interference between frames,blurred output,and the need for temporal coherence across frames.In this paper,we propose a novel approach for generating coherent videos of moving digits from textual input using a Deep Deconvolutional Generative Adversarial Network(DD-GAN).The DDGAN comprises a Deep Deconvolutional Neural Network(DDNN)as a Generator(G)and a modified Deep Convolutional Neural Network(DCNN)as a Discriminator(D)to ensure temporal coherence between adjacent frames.The proposed research involves several steps.First,the input text is fed into a Long Short Term Memory(LSTM)based text encoder and then smoothed using Conditioning Augmentation(CA)techniques to enhance the effectiveness of the Generator(G).Next,using a DDNN to generate video frames by incorporating enhanced text and random noise and modifying a DCNN to act as a Discriminator(D),effectively distinguishing between generated and real videos.This research evaluates the quality of the generated videos using standard metrics like Inception Score(IS),Fréchet Inception Distance(FID),Fréchet Inception Distance for video(FID2vid),and Generative Adversarial Metric(GAM),along with a human study based on realism,coherence,and relevance.By conducting experiments on Single-Digit Bouncing MNIST GIFs(SBMG),Two-Digit Bouncing MNIST GIFs(TBMG),and a custom dataset of essential mathematics videos with related text,this research demonstrates significant improvements in both metrics and human study results,confirming the effectiveness of DD-GAN.This research also took the exciting challenge of generating preschool math videos from text,handling complex structures,digits,and symbols,and achieving successful results.The proposed research demonstrates promising results for generating coherent videos from textual input.

A Sketch-Based Generation Model for Diverse Ceramic Tile Images Using Generative Adversarial Network

Ceramic tiles are one of the most indispensable materials for interior decoration.The ceramic patterns can’t match the design requirements in terms of diversity and interactivity due to their natural textures.In this paper,we propose a sketch-based generation method for generating diverse ceramic tile images based on a hand-drawn sketches using Generative Adversarial Network(GAN).The generated tile images can be tailored to meet the specific needs of the user for the tile textures.The proposed method consists of four steps.Firstly,a dataset of ceramic tile images with diverse distributions is created and then pre-trained based on GAN.Secondly,for each ceramic tile image in the dataset,the corresponding sketch image is generated and then the mapping relationship between the images is trained based on a sketch extraction network using ResNet Block and jump connection to improve the quality of the generated sketches.Thirdly,the sketch style is redefined according to the characteristics of the ceramic tile images and then double cross-domain adversarial loss functions are employed to guide the ceramic tile generation network for fitting in the direction of the sketch style and to improve the training speed.Finally,we apply hidden space perturbation and interpolation for further enriching the output textures style and satisfying the concept of“one style with multiple faces”.We conduct the training process of the proposed generation network on 2583 ceramic tile images dataset.To measure the generative diversity and quality,we use Frechet Inception Distance(FID)and Blind/Referenceless Image Spatial Quality Evaluator(BRISQUE)metrics.The experimental results prove that the proposed model greatly enhances the generation results of the ceramic tile images,with FID of 32.47 and BRISQUE of 28.44.

面向舰船目标检测的SAR图像数据PCGAN生成方法

针对现有合成孔径雷达(SAR)图像数据生成方法大多无法同时生成舰船图像及其检测标签的问题,面向SAR舰船图像生成及目标检测任务,构建基于位置信息的条件生成对抗网络(PCGAN).首先,提出将舰船位置信息作为约束条件用于限制生成图像中舰船的位置,并将其作为舰船图像的检测标签;随后,引入Wasserstein距离稳定PCGAN的训练过程;最后,利用生成的SAR舰船图像及对应检测标签完成YOLOv3网络的端到端训练,实现舰船数据增强与目标检测的协同学习,进而获得更耦合目标检测实际应用的多样性数据.在HRSID(high resolution SAR image dataset)数据集上的实验结果表明,PCGAN方法能生成清晰、鲁棒的SAR舰船数据,舰船检测准确度最高提升1.01%,验证了所提出方法的有效性.

融合情感分析和GAN-TrellisNet的股价预测方法

将时序深度神经网络应用于股票价格预测,已成为量化金融领域的重要研究方向。时序神经网络具有很好的序列数据捕捉能力和学习记忆能力,在股票预测上有一定适用性。但是现有的模型大多存在预测准确度不高、模型结构复杂导致训练时间较长等问题.为了解决以上问题,提出了一种基于情感分析和GAN-TrellisNet的股价预测方法。提出了一个基于LSTM-CNN的情感分析模型,用于分析爬虫获取的主流金融论坛股票评论,并获得股票情感指数。为了提高预测准确度,将情感指数和百度搜索指数加入股票交易数据中作为训练集,提出了一个基于TrellisNet和CNN的改进型GAN股价预测模型,利用TrellisNet生成器的卷积特性来捕捉数据的局部特征,选取特征提取能力较强的CNN作为判别器来区别预测结果和真实股价。通过选取10只代表性股票和三种大盘指数的不同时段数据进行算法验证,结果表明,与ConvLSTM和GAN-LSTM预测模型相比,GAN-TrellisNet模型能有效缩短训练时间,提高预测准确率。

基于GAN改进的红外光与可见光图像融合算法研究

针对夜晚户外场景下,传统的单一鉴别器生成对抗网络(GAN)容易忽略红外光的亮度信息和边缘信息的问题,提出一种基于注意力机制与双鉴别器的红外光与可见光图像融合算法。首先,为了有针对性地获得红外光图像的目标信息和可见光图像的背景纹理信息,在生成器网络中引入通道注意力机制;其次,使用双鉴别器的生成对抗网络,并设计一种新的鉴别器输入,在提高训练稳定性的同时更好地保留源图像信息;最后,损失函数设置为对抗损失、结构相似性损失和梯度损失,以约束鉴别器使其生成细节信息丰富的融合图像。在TNO数据集上的实验结果表明,所提算法得到的融合图像梯度变化更明显、边缘更加清晰,更符合人眼视觉效果。

基于SA/WGAN的新能源场景生成方法

随着新能源渗透率逐年提高,其出力的随机性与波动特性难以准确预测,给电力系统的运行、规划和调度提出了严峻的挑战,因此新能源的不确定性建模受到越来越多的关注。为了更有效地获得新能源出力场景中的时序特征,提出了一种基于数据驱动的新能源场景生成方法,通过采用SA/WGAN模型,把自注意力机制和带有梯度惩罚的生成对抗网络判别器结合,构建基于两种模型结合的深度学习模型,有效突显新能源出力场景中时序特性,增强场景生成中非线性拟合能力。算例结果表明,所提模型的新能源生成场景相较于原始WGAN和WGAN-LSTM的场景生成结果,可以有效提高精准度,同时具备了WGAN-GP训练结果稳定和SA计算速度快的优势,更高效地生成与真实新能源场景分布接近的场景。