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。

Hyperparameter Tuning for Deep Neural Networks Based Optimization Algorithm

For training the present Neural Network(NN)models,the standard technique is to utilize decaying Learning Rates(LR).While the majority of these techniques commence with a large LR,they will decay multiple times over time.Decaying has been proved to enhance generalization as well as optimization.Other parameters,such as the network’s size,the number of hidden layers,drop-outs to avoid overfitting,batch size,and so on,are solely based on heuristics.This work has proposed Adaptive Teaching Learning Based(ATLB)Heuristic to identify the optimal hyperparameters for diverse networks.Here we consider three architec-tures Recurrent Neural Networks(RNN),Long Short Term Memory(LSTM),Bidirectional Long Short Term Memory(BiLSTM)of Deep Neural Networks for classification.The evaluation of the proposed ATLB is done through the various learning rate schedulers Cyclical Learning Rate(CLR),Hyperbolic Tangent Decay(HTD),and Toggle between Hyperbolic Tangent Decay and Triangular mode with Restarts(T-HTR)techniques.Experimental results have shown the performance improvement on the 20Newsgroup,Reuters Newswire and IMDB dataset.

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。

Novel model of a AlGaN/GaN high electron mobility transistor based on an artificial neural network

In this paper we present a novel approach to modeling AlGaN/GaN high electron mobility transistor （HEMT） with an artificial neural network （ANN）. The AlGaN/GaN HEMT device structure and its fabrication process are described. The circuit-based Neuro-space mapping （neuro-SM） technique is studied in detail. The EEHEMT model is implemented according to the measurement results of the designed device, which serves as a coarse model. An ANN is proposed to model AIGaN/CaN HEMT based on the coarse model. Its optimization is performed. The simulation results from the model are compared with the measurement results. It is shown that the simulation results obtained from the ANN model of A1GaN/GaN HEMT are more accurate than those obtained from the EEHEMT model.

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.

ECGAN:Translate Real World to Cartoon Style Using Enhanced Cartoon Generative Adversarial Network

Visual illustration transformation from real-world to cartoon images is one of the famous and challenging tasks in computer vision.Image-to-image translation from real-world to cartoon domains poses issues such as a lack of paired training samples,lack of good image translation,low feature extraction from the previous domain images,and lack of high-quality image translation from the traditional generator algorithms.To solve the above-mentioned issues,paired independent model,high-quality dataset,Bayesian-based feature extractor,and an improved generator must be proposed.In this study,we propose a high-quality dataset to reduce the effect of paired training samples on the model’s performance.We use a Bayesian Very Deep Convolutional Network(VGG)-based feature extractor to improve the performance of the standard feature extractor because Bayesian inference regu-larizes weights well.The generator from the Cartoon Generative Adversarial Network(GAN)is modified by introducing a depthwise convolution layer and channel attention mechanism to improve the performance of the original generator.We have used the Fréchet inception distance(FID)score and user preference score to evaluate the performance of the model.The FID scores obtained for the generated cartoon and real-world images are 107 and 76 for the TCC style,and 137 and 57 for the Hayao style,respectively.User preference score is also calculated to evaluate the quality of generated images and our proposed model acquired a high preference score compared to other models.We achieved stunning results in producing high-quality cartoon images,demonstrating the proposed model’s effectiveness in transferring style between authentic images and cartoon images.

Genetics Based Compact Fuzzy System for Visual Sensor Network

As a component of Wireless Sensor Network(WSN),Visual-WSN(VWSN)utilizes cameras to obtain relevant data including visual recordings and static images.Data from the camera is sent to energy efficient sink to extract key-information out of it.VWSN applications range from health care monitoring to military surveillance.In a network with VWSN,there are multiple challenges to move high volume data from a source location to a target and the key challenges include energy,memory and I/O resources.In this case,Mobile Sinks(MS)can be employed for data collection which not only collects information from particular chosen nodes called Cluster Head(CH),it also collects data from nearby nodes as well.The innovation of our work is to intelligently decide on a particular node as CH whose selection criteria would directly have an impact on QoS parameters of the system.However,making an appropriate choice during CH selection is a daunting task as the dynamic and mobile nature of MSs has to be taken into account.We propose Genetic Machine Learning based Fuzzy system for clustering which has the potential to simulate human cognitive behavior to observe,learn and understand things from manual perspective.Proposed architecture is designed based on Mamdani’s fuzzy model.Following parameters are derived based on the model residual energy,node centrality,distance between the sink and current position,node centrality,node density,node history,and mobility of sink as input variables for decision making in CH selection.The inputs received have a direct impact on the Fuzzy logic rules mechanism which in turn affects the accuracy of VWSN.The proposed work creates a mechanism to learn the fuzzy rules using Genetic Algorithm(GA)and to optimize the fuzzy rules base in order to eliminate irrelevant and repetitive rules.Genetic algorithmbased machine learning optimizes the interpretability aspect of fuzzy system.Simulation results are obtained using MATLAB.The result shows that the classification accuracy increase along with minimizing fuzzy rules count and thus it can be inferred that the suggested methodology has a better protracted lifetime in contrast with Low Energy Adaptive Clustering Hierarchy(LEACH)and LEACHExpected Residual Energy(LEACH-ERE).

Using GAN Neural Networks for Super-Resolution Reconstruction of Temperature Fields

A Generative Adversarial Neural(GAN)network is designed based on deep learning for the Super-Resolution(SR)reconstruction task of temperaturefields(comparable to downscaling in the meteorologicalfield),which is limited by the small number of ground stations and the sparse distribution of observations,resulting in a lack offineness of data.To improve the network’s generalization performance,the residual structure,and batch normalization are used.Applying the nearest interpolation method to avoid over-smoothing of the climate element values instead of the conventional Bicubic interpolation in the computer visionfield.Sub-pixel convolution is used instead of transposed convolution or interpolation methods for up-sampling to speed up network inference.The experimental dataset is the European Centre for Medium-Range Weather Forecasts Reanalysis v5(ERA5)with a bidirectional resolution of 0:1°×0:1°.On the other hand,the task aims to scale up the size by a factor of 8,which is rare compared to conventional methods.The comparison methods include traditional interpolation methods and a more widely used GAN-based network such as the SRGAN.Thefinal experimental results show that the proposed scheme advances the performance of Root Mean Square Error(RMSE)by 37.25%,the Peak Signal-to-noise Ratio(PNSR)by 14.4%,and the Structural Similarity(SSIM)by 10.3%compared to the Bicubic Interpolation.For the traditional SRGAN network,a relatively obvious performance improvement is observed by experimental demonstration.Meanwhile,the GAN network can converge stably and reach the approximate Nash equilibrium for various initialization parameters to empirically illustrate the effectiveness of the method in the temperature fields.

Honey Badger Algorithm Based Clustering with Routing Protocol for Wireless Sensor Networks

Wireless sensor network(WSN)includes a set of self-organizing and homogenous nodes employed for data collection and tracking applications.It comprises a massive set of nodes with restricted energy and processing abilities.Energy dissipation is a major concern involved in the design of WSN.Clustering and routing protocols are considered effective ways to reduce the quantity of energy dissipation using metaheuristic algorithms.In order to design an energy aware cluster-based route planning scheme,this study introduces a novel Honey Badger Based Clustering with African Vulture Optimization based Routing(HBAC-AVOR)protocol for WSN.The presented HBAC-AVOR model mainly aims to cluster the nodes in WSN effectually and organize the routes in an energy-efficient way.The presented HBAC-AVOR model follows a two stage process.At the initial stage,the HBAC technique is exploited to choose an opti-mal set of cluster heads(CHs)utilizing afitness function involving many input parameters.Next,the AVOR approach was executed for determining the optimal routes to BS and thereby lengthens the lifetime of WSN.A detailed simulation analysis was executed to highlight the increased outcomes of the HBAC-AVOR protocol.On comparing with existing techniques,the HBAC-AVOR model has outperformed existing techniques with maximum lifetime.

Lateral interaction by Laplacian‐based graph smoothing for deep neural networks

Lateral interaction in the biological brain is a key mechanism that underlies higher cognitive functions.Linear self‐organising map(SOM)introduces lateral interaction in a general form in which signals of any modality can be used.Some approaches directly incorporate SOM learning rules into neural networks,but incur complex operations and poor extendibility.The efficient way to implement lateral interaction in deep neural networks is not well established.The use of Laplacian Matrix‐based Smoothing(LS)regularisation is proposed for implementing lateral interaction in a concise form.The authors’derivation and experiments show that lateral interaction implemented by SOM model is a special case of LS‐regulated k‐means,and they both show the topology‐preserving capability.The authors also verify that LS‐regularisation can be used in conjunction with the end‐to‐end training paradigm in deep auto‐encoders.Additionally,the benefits of LS‐regularisation in relaxing the requirement of parameter initialisation in various models and improving the classification performance of prototype classifiers are evaluated.Furthermore,the topologically ordered structure introduced by LS‐regularisation in feature extractor can improve the generalisation performance on classification tasks.Overall,LS‐regularisation is an effective and efficient way to implement lateral interaction and can be easily extended to different models.

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.

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。

Geographic Drone-based Route Optimization Approach for Emergency Area Ad-Hoc Network

Wireless sensor Mobile ad hoc networks have excellent potential in moving and monitoring disaster area networks on real-time basis.The recent challenges faced in Mobile Ad Hoc Networks(MANETs)include scalability,localization,heterogeneous network,self-organization,and self-sufficient operation.In this background,the current study focuses on specially-designed communication link establishment for high connection stability of wireless mobile sensor networks,especially in disaster area network.Existing protocols focus on location-dependent communications and use networks based on typically-used Internet Protocol(IP)architecture.However,IP-based communications have a few limitations such as inefficient bandwidth utilization,high processing,less transfer speeds,and excessive memory intake.To overcome these challenges,the number of neighbors(Node Density)is minimized and high Mobility Nodes(Node Speed)are avoided.The proposed Geographic Drone Based Route Optimization(GDRO)method reduces the entire overhead to a considerable level in an efficient manner and significantly improves the overall performance by identifying the disaster region.This drone communicates with anchor node periodically and shares the information to it so as to introduce a drone-based disaster network in an area.Geographic routing is a promising approach to enhance the routing efficiency in MANET.This algorithm helps in reaching the anchor(target)node with the help of Geographical Graph-Based Mapping(GGM).Global Positioning System(GPS)is enabled on mobile network of the anchor node which regularly broadcasts its location information that helps in finding the location.In first step,the node searches for local and remote anticipated Expected Transmission Count(ETX),thereby calculating the estimated distance.Received Signal Strength Indicator(RSSI)results are stored in the local memory of the node.Then,the node calculates the least remote anticipated ETX,Link Loss Rate,and information to the new location.Freeway Heuristic algorithm improves the data speed,efficiency and determines the path and optimization problem.In comparison with other models,the proposed method yielded an efficient communication,increased the throughput,and reduced the end-to-end delay,energy consumption and packet loss performance in disaster area networks.

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。

结合多注意力及IE-GAN的面部属性编辑方法

面部属性编辑主要有两个目的:①将图像从源域转换到目标域,对指定的目标属性(如性别、年龄、发色等)进行修改;②只改变与目标属性相关的人脸区域,保留目标属性之外其他属性的细节。而现有的人脸属性编辑方法不可避免地会对与目标属性无关区域进行更改。因此,提出一种基于IE-GAN和多注意力机制的面部属性编辑方法MAIE-GAN,引入补充注意连接(Complementary attention connection,CAC)的概念连接编解码器,解决了由直接跳跃连接引起的信息冗余问题,将自注意力机制作为生成器中卷积层的补充,使其能更好定位目标属性,限定属性变换区域,此外,还利用互补注意特征的概念,实现目标属性无关区域的更好保留。通过与现有方法的对比分析表明,该方法在属性定位和图像质量方面优于现有的方法。

Unsupervised multi-modal image translation based on the squeeze-and-excitation mechanism and feature attention module

The unsupervised multi-modal image translation is an emerging domain of computer vision whose goal is to transform an image from the source domain into many diverse styles in the target domain.However,the multi-generator mechanism is employed among the advanced approaches available to model different domain mappings,which results in inefficient training of neural networks and pattern collapse,leading to inefficient generation of image diversity.To address this issue,this paper introduces a multi-modal unsupervised image translation framework that uses a generator to perform multi-modal image translation.Specifically,firstly,the domain code is introduced in this paper to explicitly control the different generation tasks.Secondly,this paper brings in the squeeze-and-excitation(SE)mechanism and feature attention(FA)module.Finally,the model integrates multiple optimization objectives to ensure efficient multi-modal translation.This paper performs qualitative and quantitative experiments on multiple non-paired benchmark image translation datasets while demonstrating the benefits of the proposed method over existing technologies.Overall,experimental results have shown that the proposed method is versatile and scalable.

Mechanism of Gan Dou Ling in improving liver fibrosis in Wilson disease based on network pharmacology and experimental verification

Objective:To explore and verify the mechanism of Gan Dou Ling in improving liver fibrosis in Wilson disease(WD)by network pharmacology and copper loaded mice experiments.Methods:The main chemical components and corresponding gene targets of each drug in Gan Dou Ling were obtained by using TCMSP database.The database of gene mutation and disease related gene was searched through the GeneCards database,DrugBank database,PharmGKB database and the DisGeNET database.After the intersection of drug and disease target genes.The STRING website was used to analyze the protein-protein interaction degree of target genes,and import the data to Cytoscape software 38.2 to analyze protein interaction network.The GO databases and KEGG databases were obtained in R language for enrichment analysis.On this basis,Masson staining were used to observe the degree of liver fibrosis in copper loaded mouse model,and the results of network pharmacological analysis were verified by Western Blot(WB).Results:A total of 108 drug disease intersection genes were analyzed by network pharmacology.Through PPI network analysis,JUN was found to be the key genes.The enrichment analysis of KEGG pathway showed that MAPK signal pathway was the important potential target pathways.Animal experiments showed that Gan Dou Ling could reduce liver fibrosis and inhibit the phosphorylation of P38,JNK and C-JUN in copper loaded mice.Conclusion:Gan Dou Ling may achieve the effect of treating WD liver fibrosis by inhibiting P38/JNK signaling pathway.

应用XCT断层扫描技术和GAN深度学习模型的多孔介质微观结构定量研究

物质在土壤中的迁移转化行为是研究地下水动力学的核心问题。定量化表征多孔介质拓扑结构并计算分析相关表面形态学参数,为研究复杂介质内物质运移微观机理提供了重要的数据基础和参数。应用微米级X射线计算机断层扫描(XCT)和图像处理技术,结合前沿的机器学习算法重建和定量分析多孔介质微观结构,可快速、批量创建高分辨率的复杂多孔介质研究样本。首先采用XCT技术,提取石英砂和散装土壤两类典型多孔介质的微观孔隙结构;而后基于生成对抗神经网络(GAN)模型重构复杂多孔介质的微观空间结构,与XCT扫描图像进行交叉验证;最后,计算获取Minkowski形态学参数,并基于多孔介质微观结构开展计算流体力学(CFD)数值模拟,计算石英砂和土壤多孔介质内的流动特征和渗透率。结果表明:1)GAN生成的合成数据与原始数据符合KS同分布,说明GAN能够成功合成与原始图像结构空间分布模式一致的图像;2)Minkowski宏观参数评价误差的较小,KS同分布结果表明,多孔介质样本的结构异质性会在一定程度上影响GAN模型的计算精度和效率;3)Open FOAM模拟计算得到的渗透率结果表明,GAN模型生成的多孔介质图像与原始图像具有一致的统计特征和物理性质。综上,综合运用前沿的XCT扫描、图像处理技术和机器学习算法,构建了土壤微观结构重建和定量分析模型,并结合多孔介质形态学和计算流体力学方法对模型进行了验证和分析。该研究为多孔介质微观结构研究提供了新技术和新方法,为进一步研究复杂多孔介质内溶质运移提供了科技支撑。

注意力融合双流特征的局部GAN生成人脸检测算法

为解决现有局部生成式对抗网络(GAN)生成人脸检测算法在检测经过后处理的图像时性能严重下降的问题,提出一种注意力融合双流特征的局部GAN生成人脸检测算法.该算法利用双流网络分别从RGB颜色空间和YCbCr颜色空间中提取鲁棒特征,并引入注意力特征融合模块在不同网络层上融合双流特征以获得更鲁棒的特征.同时采用多层次特征融合决策提高网络对局部生成区域特征的提取和辨别能力.实验结果表明,所提算法的鲁棒性优于现有算法,尤其是针对JPEG压缩和双边滤波后处理.在FFHQ+规则子集上与次优算法相比,该算法在3种强度的JPEG压缩和双边滤波上的平均准确率分别提高了1.88%和2.64%;在FFHQ+不规则子集上与次优算法相比,该算法在3种强度的JPEG压缩和双边滤波上的平均准确率分别提高了2.85%和1.60%.

DR-GAN:一种无监督学习的探地雷达杂波抑制方法

探地雷达(GPR)是一种基于电磁波的地下无损探测技术,广泛应用于市政工程、交通、军事等领域。在数据采集过程中,由于发射天线和接收天线之间的耦合、起伏地面的散射以及地下随机媒质的复杂性等原因,采集得到的GPR B-scan回波中通常存在杂波,杂波严重影响了地下目标的检测和特征提取。该文提出一种用于GPR B-scan图像杂波抑制的解纠缠表示生成对抗网络(DR-GAN),设计了目标特征编码器和杂波特征编码器用来提取GPR B-scan图像中的目标特征和杂波特征,设计了杂波抑制生成器用来获取杂波抑制后的GPR B-scan图像。与现有的基于监督学习的GPR杂波抑制方法相比,该方法在网络训练时不需要成对的匹配数据,可以更好地应用于实测GPR图像的杂波抑制。在仿真和实测GPR数据上的实验结果表明,DR-GAN这一无监督学习网络具有更好的杂波抑制性能。对石英砂中埋设的钢筋进行数据采集,运用DR-GAN对含杂波的实测数据进行处理,处理结果的改善系数(IF)指标较现有的鲁棒非负矩阵分解(RNMF)方法提高了17.85 dB。