Geochemical maps are of great value in mineral exploration.Integrated geochemical anomaly maps provide comprehensive information about mapping assemblages of element concentrations to possible types of mineralization/...Geochemical maps are of great value in mineral exploration.Integrated geochemical anomaly maps provide comprehensive information about mapping assemblages of element concentrations to possible types of mineralization/ore,but vary depending on expert's knowledge and experience.This paper aims to test the capability of deep neural networks to delineate integrated anomaly based on a case study of the Zhaojikou Pb-Zn deposit,Southeast China.Three hundred fifty two samples were collected,and each sample consisted of 26 variables covering elemental composition,geological,and tectonic information.At first,generative adversarial networks were adopted for data augmentation.Then,DNN was trained on sets of synthetic and real data to identify an integrated anomaly.Finally,the results of DNN analyses were visualized in probability maps and compared with traditional anomaly maps to check its performance.Results showed that the average accuracy of the validation set was 94.76%.The probability maps showed that newly-identified integrated anomalous areas had a probability of above 75%in the northeast zones.It also showed that DNN models that used big data not only successfully recognized the anomalous areas identified on traditional geochemical element maps,but also discovered new anomalous areas,not picked up by the elemental anomaly maps previously.展开更多
The novel Coronavirus disease 2019(COVID-19)pandemic has begun in China and is still affecting thousands of patient livesworldwide daily.AlthoughChest X-ray and Computed Tomography are the gold standardmedical imaging...The novel Coronavirus disease 2019(COVID-19)pandemic has begun in China and is still affecting thousands of patient livesworldwide daily.AlthoughChest X-ray and Computed Tomography are the gold standardmedical imaging modalities for diagnosing potentially infected COVID-19 cases,applying Ultrasound(US)imaging technique to accomplish this crucial diagnosing task has attracted many physicians recently.In this article,we propose two modified deep learning classifiers to identify COVID-19 and pneumonia diseases in US images,based on generative adversarial neural networks(GANs).The proposed image classifiers are a semi-supervised GAN and a modifiedGANwith auxiliary classifier.Each one includes a modified discriminator to identify the class of the US image using semi-supervised learning technique,keeping its main function of defining the“realness”of tested images.Extensive tests have been successfully conducted on public dataset of US images acquired with a convex US probe.This study demonstrated the feasibility of using chest US images with two GAN classifiers as a new radiological tool for clinical check of COVID-19 patients.The results of our proposed GAN models showed that high accuracy values above 91.0%were obtained under different sizes of limited training data,outperforming other deep learning-based methods,such as transfer learning models in the recent studies.Consequently,the clinical implementation of our computer-aided diagnosis of US-COVID-19 is the future work of this study.展开更多
Efficiently tracking and imaging interested moving targets is crucial across various applications,from autonomous systems to surveillance.However,persistent challenges remain in various fields,including environmental ...Efficiently tracking and imaging interested moving targets is crucial across various applications,from autonomous systems to surveillance.However,persistent challenges remain in various fields,including environmental intricacies,limitations in perceptual technologies,and privacy considerations.We present a teacher-student learning model,the generative adversarial network(GAN)-guided diffractive neural network(DNN),which performs visual tracking and imaging of the interested moving target.The GAN,as a teacher model,empowers efficient acquisition of the skill to differentiate the specific target of interest in the domains of visual tracking and imaging.The DNN-based student model learns to master the skill to differentiate the interested target from the GAN.The process of obtaining a GAN-guided DNN starts with capturing moving objects effectively using an event camera with high temporal resolution and low latency.Then,the generative power of GAN is utilized to generate data with position-tracking capability for the interested moving target,subsequently serving as labels to the training of the DNN.The DNN learns to image the target during training while retaining the target’s positional information.Our experimental demonstration highlights the efficacy of the GAN-guided DNN in visual tracking and imaging of the interested moving target.We expect the GAN-guided DNN can significantly enhance autonomous systems and surveillance.展开更多
In recent years,landslide susceptibility mapping has substantially improved with advances in machine learning.However,there are still challenges remain in landslide mapping due to the availability of limited inventory...In recent years,landslide susceptibility mapping has substantially improved with advances in machine learning.However,there are still challenges remain in landslide mapping due to the availability of limited inventory data.In this paper,a novel method that improves the performance of machine learning techniques is presented.The proposed method creates synthetic inventory data using Generative Adversarial Networks(GANs)for improving the prediction of landslides.In this research,landslide inventory data of 156 landslide locations were identified in Cameron Highlands,Malaysia,taken from previous projects the authors worked on.Elevation,slope,aspect,plan curvature,profile curvature,total curvature,lithology,land use and land cover(LULC),distance to the road,distance to the river,stream power index(SPI),sediment transport index(STI),terrain roughness index(TRI),topographic wetness index(TWI)and vegetation density are geo-environmental factors considered in this study based on suggestions from previous works on Cameron Highlands.To show the capability of GANs in improving landslide prediction models,this study tests the proposed GAN model with benchmark models namely Artificial Neural Network(ANN),Support Vector Machine(SVM),Decision Trees(DT),Random Forest(RF)and Bagging ensemble models with ANN and SVM models.These models were validated using the area under the receiver operating characteristic curve(AUROC).The DT,RF,SVM,ANN and Bagging ensemble could achieve the AUROC values of(0.90,0.94,0.86,0.69 and 0.82)for the training;and the AUROC of(0.76,0.81,0.85,0.72 and 0.75)for the test,subsequently.When using additional samples,the same models achieved the AUROC values of(0.92,0.94,0.88,0.75 and 0.84)for the training and(0.78,0.82,0.82,0.78 and 0.80)for the test,respectively.Using the additional samples improved the test accuracy of all the models except SVM.As a result,in data-scarce environments,this research showed that utilizing GANs to generate supplementary samples is promising because it can improve the predictive capability of common landslide prediction models.展开更多
Multi-principal element alloys(MPEAs),inclusive of high entropy alloys(HEAs),continue to attract significant research attention owing to their potentially desirable properties.Although MPEAs remain under extensive res...Multi-principal element alloys(MPEAs),inclusive of high entropy alloys(HEAs),continue to attract significant research attention owing to their potentially desirable properties.Although MPEAs remain under extensive research,traditional(i.e.empirical)alloy production and testing are both costly and timeconsuming,partly due to the inefficiency of the early discovery process which involves experiments on a large number of alloy compositions.It is intuitive to apply machine learning in the discovery of this novel class of materials,of which only a small number of potential alloys have been probed to date.In this work,a proof-of-concept is proposed,combining generative adversarial networks(GANs)with discriminative neural networks(NNs),to accelerate the exploration of novel MPEAs.By applying the GAN model herein,it was possible to directly generate novel compositions for MPEAs,and to predict their phases.To verify the predictability of the model,alloys designed by the model are presented and a candidate produced-as validation.This suggests that the model herein offers an approach that can significantly enhance the capacity and efficiency of development of novel MPEAs.展开更多
Digital watermark embeds information bits into digital cover such as images and videos to prove the creator’s ownership of his work.In this paper,we propose a robust image watermark algorithm based on a generative ad...Digital watermark embeds information bits into digital cover such as images and videos to prove the creator’s ownership of his work.In this paper,we propose a robust image watermark algorithm based on a generative adversarial network.This model includes two modules,generator and adversary.Generator is mainly used to generate images embedded with watermark,and decode the image damaged by noise to obtain the watermark.Adversary is used to discriminate whether the image is embedded with watermark and damage the image by noise.Based on the model Hidden(hiding data with deep networks),we add a high-pass filter in front of the discriminator,making the watermark tend to be embedded in the mid-frequency region of the image.Since the human visual system pays more attention to the central area of the image,we give a higher weight to the image center region,and a lower weight to the edge region when calculating the loss between cover and embedded image.The watermarked image obtained by this scheme has a better visual performance.Experimental results show that the proposed architecture is more robust against noise interference compared with the state-of-art schemes.展开更多
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...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.展开更多
Autism Spectrum Disorder(ASD)requires a precise diagnosis in order to be managed and rehabilitated.Non-invasive neuroimaging methods are disease markers that can be used to help diagnose ASD.The majority of available ...Autism Spectrum Disorder(ASD)requires a precise diagnosis in order to be managed and rehabilitated.Non-invasive neuroimaging methods are disease markers that can be used to help diagnose ASD.The majority of available techniques in the literature use functional magnetic resonance imaging(fMRI)to detect ASD with a small dataset,resulting in high accuracy but low generality.Traditional supervised machine learning classification algorithms such as support vector machines function well with unstructured and semi structured data such as text,images,and videos,but their performance and robustness are restricted by the size of the accompanying training data.Deep learning on the other hand creates an artificial neural network that can learn and make intelligent judgments on its own by layering algorithms.It takes use of plentiful low-cost computing and many approaches are focused with very big datasets that are concerned with creating far larger and more sophisticated neural networks.Generative modelling,also known as Generative Adversarial Networks(GANs),is an unsupervised deep learning task that entails automatically discovering and learning regularities or patterns in input data in order for the model to generate or output new examples that could have been drawn from the original dataset.GANs are an exciting and rapidly changingfield that delivers on the promise of generative models in terms of their ability to generate realistic examples across a range of problem domains,most notably in image-to-image translation tasks and hasn't been explored much for Autism spectrum disorder prediction in the past.In this paper,we present a novel conditional generative adversarial network,or cGAN for short,which is a form of GAN that uses a generator model to conditionally generate images.In terms of prediction and accuracy,they outperform the standard GAN.The pro-posed model is 74%more accurate than the traditional methods and takes only around 10 min for training even with a huge dataset.展开更多
Generative adversarial networks(GANs)are paid more attention to dealing with the end-to-end speech enhancement in recent years.Various GANbased enhancement methods are presented to improve the quality of reconstructed...Generative adversarial networks(GANs)are paid more attention to dealing with the end-to-end speech enhancement in recent years.Various GANbased enhancement methods are presented to improve the quality of reconstructed speech.However,the performance of these GAN-based methods is worse than those of masking-based methods.To tackle this problem,we propose speech enhancement method with a residual dense generative adversarial network(RDGAN)contributing to map the log-power spectrum(LPS)of degraded speech to the clean one.In detail,a residual dense block(RDB)architecture is designed to better estimate the LPS of clean speech,which can extract rich local features of LPS through densely connected convolution layers.Meanwhile,sequential RDB connections are incorporated on various scales of LPS.It significantly increases the feature learning flexibility and robustness in the time-frequency domain.Simulations show that the proposed method achieves attractive speech enhancement performance in various acoustic environments.Specifically,in the untrained acoustic test with limited priors,e.g.,unmatched signal-to-noise ratio(SNR)and unmatched noise category,RDGAN can still outperform the existing GAN-based methods and masking-based method in the measures of PESQ and other evaluation indexes.It indicates that our method is more generalized in untrained conditions.展开更多
Haze is a very common phenomenon that degrades or reduces visibility. It causes various problems where high-quality images are required such as traffic and security monitoring. So haze removal from scenes is an immedi...Haze is a very common phenomenon that degrades or reduces visibility. It causes various problems where high-quality images are required such as traffic and security monitoring. So haze removal from scenes is an immediate demand for clear vision. Recently, in addition to the conventional dehazing mechanisms, different types of deep generative adversarial networks (GAN) are applied to suppress the noise and improve the dehazing performance. But it is unclear how these algorithms would perform on hazy images acquired “in the wild” and how we could gauge the progress in the field. To bridge this gap, this presents a comprehensive study on three single image dehazing state-of-the-art GAN models, such as AOD-Net, cGAN, and DHSGAN. We have experimented using benchmark dataset consisting of both synthetic and real-world hazy images. The obtained results are evaluated both quantitatively and qualitatively. Among these techniques, the DHSGAN gives the best performance.展开更多
The emergence of adversarial examples has revealed the inadequacies in the robustness of image classification models based on Convolutional Neural Networks (CNNs). Particularly in recent years, the discovery of natura...The emergence of adversarial examples has revealed the inadequacies in the robustness of image classification models based on Convolutional Neural Networks (CNNs). Particularly in recent years, the discovery of natural adversarial examples has posed significant challenges, as traditional defense methods against adversarial attacks have proven to be largely ineffective against these natural adversarial examples. This paper explores defenses against these natural adversarial examples from three perspectives: adversarial examples, model architecture, and dataset. First, it employs Class Activation Mapping (CAM) to visualize how models classify natural adversarial examples, identifying several typical attack patterns. Next, various common CNN models are analyzed to evaluate their susceptibility to these attacks, revealing that different architectures exhibit varying defensive capabilities. The study finds that as the depth of a network increases, its defenses against natural adversarial examples strengthen. Lastly, Finally, the impact of dataset class distribution on the defense capability of models is examined, focusing on two aspects: the number of classes in the training set and the number of predicted classes. This study investigates how these factors influence the model’s ability to defend against natural adversarial examples. Results indicate that reducing the number of training classes enhances the model’s defense against natural adversarial examples. Additionally, under a fixed number of training classes, some CNN models show an optimal range of predicted classes for achieving the best defense performance against these adversarial examples.展开更多
Graph Neural Networks(GNNs)have demonstrated outstanding capabilities in processing graph-structured data and are increasingly being integrated into large-scale pre-trained models,such as Large Language Models(LLMs),t...Graph Neural Networks(GNNs)have demonstrated outstanding capabilities in processing graph-structured data and are increasingly being integrated into large-scale pre-trained models,such as Large Language Models(LLMs),to enhance structural reasoning,knowledge retrieval,and memory management.The expansion of their application scope imposes higher requirements on the robustness of GNNs.However,as GNNs are applied to more dynamic and heterogeneous environments,they become increasingly vulnerable to real-world perturbations.In particular,graph data frequently encounters joint adversarial perturbations that simultaneously affect both structures and features,which are significantly more challenging than isolated attacks.These disruptions,caused by incomplete data,malicious attacks,or inherent noise,pose substantial threats to the stable and reliable performance of traditional GNN models.To address this issue,this study proposes the Dual-Shield Graph Neural Network(DSGNN),a defense model that simultaneously mitigates structural and feature perturbations.DSGNN utilizes two parallel GNN channels to independently process structural noise and feature noise,and introduces an adaptive fusion mechanism that integrates information from both pathways to generate robust node representations.Theoretical analysis demonstrates that DSGNN achieves a tighter robustness boundary under joint perturbations compared to conventional single-channel methods.Experimental evaluations across Cora,CiteSeer,and Industry datasets show that DSGNN achieves the highest average classification accuracy under various adversarial settings,reaching 81.24%,71.94%,and 81.66%,respectively,outperforming GNNGuard,GCN-Jaccard,GCN-SVD,RGCN,and NoisyGNN.These results underscore the importance of multi-view perturbation decoupling in constructing resilient GNN models for real-world applications.展开更多
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 tem...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.展开更多
In this paper,a communication model in cognitive radios is developed and uses machine learning to learn the dynamics of jamming attacks in cognitive radios.It is designed further to make their transmission decision th...In this paper,a communication model in cognitive radios is developed and uses machine learning to learn the dynamics of jamming attacks in cognitive radios.It is designed further to make their transmission decision that automati-cally adapts to the transmission dynamics to mitigate the launched jamming attacks.The generative adversarial learning neural network(GALNN)or genera-tive dynamic neural network(GDNN)automatically learns with the synthesized training data(training)with a generator and discriminator type neural networks that encompass minimax game theory.The elimination of the jamming attack is carried out with the assistance of the defense strategies and with an increased detection rate in the generative adversarial network(GAN).The GDNN with game theory is designed to validate the channel condition with the cross entropy loss function and back-propagation algorithm,which improves the communica-tion reliability in the network.The simulation is conducted in NS2.34 tool against several performance metrics to reduce the misdetection rate and false alarm rates.The results show that the GDNN obtains an increased rate of successful transmis-sion by taking optimal actions to act as a defense mechanism to mislead the jam-mer,where the jammer makes high misclassification errors on transmission dynamics.展开更多
With the rapid developments of artificial intelligence(AI)and deep learning(DL)techniques,it is critical to ensure the security and robustness of the deployed algorithms.Recently,the security vulnerability of DL algor...With the rapid developments of artificial intelligence(AI)and deep learning(DL)techniques,it is critical to ensure the security and robustness of the deployed algorithms.Recently,the security vulnerability of DL algorithms to adversarial samples has been widely recognized.The fabricated samples can lead to various misbehaviors of the DL models while being perceived as benign by humans.Successful implementations of adversarial attacks in real physical-world scenarios further demonstrate their practicality.Hence,adversarial attack and defense techniques have attracted increasing attention from both machine learning and security communities and have become a hot research topic in recent years.In this paper,we first introduce the theoretical foundations,algorithms,and applications of adversarial attack techniques.We then describe a few research efforts on the defense techniques,which cover the broad frontier in the field.Several open problems and challenges are subsequently discussed,which we hope will provoke further research efforts in this critical area.展开更多
Recently,many researchers have concentrated on using neural networks to learn features for Distant Supervised Relation Extraction(DSRE).These approaches generally use a softmax classifier with cross-entropy loss,which...Recently,many researchers have concentrated on using neural networks to learn features for Distant Supervised Relation Extraction(DSRE).These approaches generally use a softmax classifier with cross-entropy loss,which inevitably brings the noise of artificial class NA into classification process.To address the shortcoming,the classifier with ranking loss is employed to DSRE.Uniformly randomly selecting a relation or heuristically selecting the highest score among all incorrect relations are two common methods for generating a negative class in the ranking loss function.However,the majority of the generated negative class can be easily discriminated from positive class and will contribute little towards the training.Inspired by Generative Adversarial Networks(GANs),we use a neural network as the negative class generator to assist the training of our desired model,which acts as the discriminator in GANs.Through the alternating optimization of generator and discriminator,the generator is learning to produce more and more discriminable negative classes and the discriminator has to become better as well.This framework is independent of the concrete form of generator and discriminator.In this paper,we use a two layers fully-connected neural network as the generator and the Piecewise Convolutional Neural Networks(PCNNs)as the discriminator.Experiment results show that our proposed GAN-based method is effective and performs better than state-of-the-art methods.展开更多
Blind image quality assessment(BIQA)is of fundamental importance in low-level computer vision community.Increasing interest has been drawn in exploiting deep neural networks for BIQA.Despite of the notable success ach...Blind image quality assessment(BIQA)is of fundamental importance in low-level computer vision community.Increasing interest has been drawn in exploiting deep neural networks for BIQA.Despite of the notable success achieved,there is a broad consensus that training deep convolutional neural networks(DCNN)heavily relies on massive annotated data.Unfortunately,BIQA is typically a small sample problem,resulting the generalization ability of BIQA severely restricted.In order to improve the accuracy and generalization ability of BIQA metrics,this work proposed a totally opinion-unaware BIQA in which no subjective annotations are involved in the training stage.Multiple full-reference image quality assessment(FR-IQA)metrics are employed to label the distorted image as a substitution of subjective quality annotation.A deep neural network(DNN)is trained to blindly predict the multiple FR-IQA score in absence of corresponding pristine image.In the end,a selfsupervised FR-IQA score aggregator implemented by adversarial auto-encoder pools the predictions of multiple FR-IQA scores into the final quality predicting score.Even though none of subjective scores are involved in the training stage,experimental results indicate that our proposed full reference induced BIQA framework is as competitive as state-of-the-art BIQA metrics.展开更多
These days,deep learning and computer vision are much-growing fields in this modern world of information technology.Deep learning algorithms and computer vision have achieved great success in different applications li...These days,deep learning and computer vision are much-growing fields in this modern world of information technology.Deep learning algorithms and computer vision have achieved great success in different applications like image classification,speech recognition,self-driving vehicles,disease diagnostics,and many more.Despite success in various applications,it is found that these learning algorithms face severe threats due to adversarial attacks.Adversarial examples are inputs like images in the computer vision field,which are intentionally slightly changed or perturbed.These changes are humanly imperceptible.But are misclassified by a model with high probability and severely affects the performance or prediction.In this scenario,we present a deep image restoration model that restores adversarial examples so that the target model is classified correctly again.We proved that our defense method against adversarial attacks based on a deep image restoration model is simple and state-of-the-art by providing strong experimental results evidence.We have used MNIST and CIFAR10 datasets for experiments and analysis of our defense method.In the end,we have compared our method to other state-ofthe-art defense methods and proved that our results are better than other rival methods.展开更多
Image classifiers that based on Deep Neural Networks(DNNs)have been proved to be easily fooled by well-designed perturbations.Previous defense methods have the limitations of requiring expensive computation or reducin...Image classifiers that based on Deep Neural Networks(DNNs)have been proved to be easily fooled by well-designed perturbations.Previous defense methods have the limitations of requiring expensive computation or reducing the accuracy of the image classifiers.In this paper,we propose a novel defense method which based on perceptual hash.Our main goal is to destroy the process of perturbations generation by comparing the similarities of images thus achieve the purpose of defense.To verify our idea,we defended against two main attack methods(a white-box attack and a black-box attack)in different DNN-based image classifiers and show that,after using our defense method,the attack-success-rate for all DNN-based image classifiers decreases significantly.More specifically,for the white-box attack,the attack-success-rate is reduced by an average of 36.3%.For the black-box attack,the average attack-success-rate of targeted attack and non-targeted attack has been reduced by 72.8%and 76.7%respectively.The proposed method is a simple and effective defense method and provides a new way to defend against adversarial samples.展开更多
基金supported by NFSC Funds(Grant Nos.41902071 and 42011530173)the Doctoral Research Start-up Fund,East China University of Technology(DHBK2019313)。
文摘Geochemical maps are of great value in mineral exploration.Integrated geochemical anomaly maps provide comprehensive information about mapping assemblages of element concentrations to possible types of mineralization/ore,but vary depending on expert's knowledge and experience.This paper aims to test the capability of deep neural networks to delineate integrated anomaly based on a case study of the Zhaojikou Pb-Zn deposit,Southeast China.Three hundred fifty two samples were collected,and each sample consisted of 26 variables covering elemental composition,geological,and tectonic information.At first,generative adversarial networks were adopted for data augmentation.Then,DNN was trained on sets of synthetic and real data to identify an integrated anomaly.Finally,the results of DNN analyses were visualized in probability maps and compared with traditional anomaly maps to check its performance.Results showed that the average accuracy of the validation set was 94.76%.The probability maps showed that newly-identified integrated anomalous areas had a probability of above 75%in the northeast zones.It also showed that DNN models that used big data not only successfully recognized the anomalous areas identified on traditional geochemical element maps,but also discovered new anomalous areas,not picked up by the elemental anomaly maps previously.
文摘The novel Coronavirus disease 2019(COVID-19)pandemic has begun in China and is still affecting thousands of patient livesworldwide daily.AlthoughChest X-ray and Computed Tomography are the gold standardmedical imaging modalities for diagnosing potentially infected COVID-19 cases,applying Ultrasound(US)imaging technique to accomplish this crucial diagnosing task has attracted many physicians recently.In this article,we propose two modified deep learning classifiers to identify COVID-19 and pneumonia diseases in US images,based on generative adversarial neural networks(GANs).The proposed image classifiers are a semi-supervised GAN and a modifiedGANwith auxiliary classifier.Each one includes a modified discriminator to identify the class of the US image using semi-supervised learning technique,keeping its main function of defining the“realness”of tested images.Extensive tests have been successfully conducted on public dataset of US images acquired with a convex US probe.This study demonstrated the feasibility of using chest US images with two GAN classifiers as a new radiological tool for clinical check of COVID-19 patients.The results of our proposed GAN models showed that high accuracy values above 91.0%were obtained under different sizes of limited training data,outperforming other deep learning-based methods,such as transfer learning models in the recent studies.Consequently,the clinical implementation of our computer-aided diagnosis of US-COVID-19 is the future work of this study.
基金supported by the National Natural Science Foundation of China(Grant Nos.62422509 and 62405188)the Shanghai Natural Science Foundation(Grant No.23ZR1443700)+3 种基金the Shuguang Program of Shanghai Education Development Foundation and Shanghai Municipal Education Commission(Grant No.23SG41)the Young Elite Scientist Sponsorship Program by CAST(Grant No.20220042)the Science and Technology Commission of Shanghai Municipality(Grant No.21DZ1100500)the Shanghai Municipal Science and Technology Major Project,and the Shanghai Frontiers Science Center Program(2021-2025 No.20).
文摘Efficiently tracking and imaging interested moving targets is crucial across various applications,from autonomous systems to surveillance.However,persistent challenges remain in various fields,including environmental intricacies,limitations in perceptual technologies,and privacy considerations.We present a teacher-student learning model,the generative adversarial network(GAN)-guided diffractive neural network(DNN),which performs visual tracking and imaging of the interested moving target.The GAN,as a teacher model,empowers efficient acquisition of the skill to differentiate the specific target of interest in the domains of visual tracking and imaging.The DNN-based student model learns to master the skill to differentiate the interested target from the GAN.The process of obtaining a GAN-guided DNN starts with capturing moving objects effectively using an event camera with high temporal resolution and low latency.Then,the generative power of GAN is utilized to generate data with position-tracking capability for the interested moving target,subsequently serving as labels to the training of the DNN.The DNN learns to image the target during training while retaining the target’s positional information.Our experimental demonstration highlights the efficacy of the GAN-guided DNN in visual tracking and imaging of the interested moving target.We expect the GAN-guided DNN can significantly enhance autonomous systems and surveillance.
基金This research is funded by the Centre for Advanced Modeling and Geospatial Information Systems(CAMGIS),Faculty of Engineering and Information Technology,the University of Technology Sydney,Australia.
文摘In recent years,landslide susceptibility mapping has substantially improved with advances in machine learning.However,there are still challenges remain in landslide mapping due to the availability of limited inventory data.In this paper,a novel method that improves the performance of machine learning techniques is presented.The proposed method creates synthetic inventory data using Generative Adversarial Networks(GANs)for improving the prediction of landslides.In this research,landslide inventory data of 156 landslide locations were identified in Cameron Highlands,Malaysia,taken from previous projects the authors worked on.Elevation,slope,aspect,plan curvature,profile curvature,total curvature,lithology,land use and land cover(LULC),distance to the road,distance to the river,stream power index(SPI),sediment transport index(STI),terrain roughness index(TRI),topographic wetness index(TWI)and vegetation density are geo-environmental factors considered in this study based on suggestions from previous works on Cameron Highlands.To show the capability of GANs in improving landslide prediction models,this study tests the proposed GAN model with benchmark models namely Artificial Neural Network(ANN),Support Vector Machine(SVM),Decision Trees(DT),Random Forest(RF)and Bagging ensemble models with ANN and SVM models.These models were validated using the area under the receiver operating characteristic curve(AUROC).The DT,RF,SVM,ANN and Bagging ensemble could achieve the AUROC values of(0.90,0.94,0.86,0.69 and 0.82)for the training;and the AUROC of(0.76,0.81,0.85,0.72 and 0.75)for the test,subsequently.When using additional samples,the same models achieved the AUROC values of(0.92,0.94,0.88,0.75 and 0.84)for the training and(0.78,0.82,0.82,0.78 and 0.80)for the test,respectively.Using the additional samples improved the test accuracy of all the models except SVM.As a result,in data-scarce environments,this research showed that utilizing GANs to generate supplementary samples is promising because it can improve the predictive capability of common landslide prediction models.
文摘Multi-principal element alloys(MPEAs),inclusive of high entropy alloys(HEAs),continue to attract significant research attention owing to their potentially desirable properties.Although MPEAs remain under extensive research,traditional(i.e.empirical)alloy production and testing are both costly and timeconsuming,partly due to the inefficiency of the early discovery process which involves experiments on a large number of alloy compositions.It is intuitive to apply machine learning in the discovery of this novel class of materials,of which only a small number of potential alloys have been probed to date.In this work,a proof-of-concept is proposed,combining generative adversarial networks(GANs)with discriminative neural networks(NNs),to accelerate the exploration of novel MPEAs.By applying the GAN model herein,it was possible to directly generate novel compositions for MPEAs,and to predict their phases.To verify the predictability of the model,alloys designed by the model are presented and a candidate produced-as validation.This suggests that the model herein offers an approach that can significantly enhance the capacity and efficiency of development of novel MPEAs.
基金supported by the National Natural Science Foundation of China under Grants 62072295,61525203,U1636206,U1936214Natural Science Foundation of Shanghai under Grant 19ZR1419000。
文摘Digital watermark embeds information bits into digital cover such as images and videos to prove the creator’s ownership of his work.In this paper,we propose a robust image watermark algorithm based on a generative adversarial network.This model includes two modules,generator and adversary.Generator is mainly used to generate images embedded with watermark,and decode the image damaged by noise to obtain the watermark.Adversary is used to discriminate whether the image is embedded with watermark and damage the image by noise.Based on the model Hidden(hiding data with deep networks),we add a high-pass filter in front of the discriminator,making the watermark tend to be embedded in the mid-frequency region of the image.Since the human visual system pays more attention to the central area of the image,we give a higher weight to the image center region,and a lower weight to the edge region when calculating the loss between cover and embedded image.The watermarked image obtained by this scheme has a better visual performance.Experimental results show that the proposed architecture is more robust against noise interference compared with the state-of-art schemes.
基金Foundation of Anhui Province Key Laboratory of Physical Geographic Environment(No.2022PGE012)
文摘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.
文摘Autism Spectrum Disorder(ASD)requires a precise diagnosis in order to be managed and rehabilitated.Non-invasive neuroimaging methods are disease markers that can be used to help diagnose ASD.The majority of available techniques in the literature use functional magnetic resonance imaging(fMRI)to detect ASD with a small dataset,resulting in high accuracy but low generality.Traditional supervised machine learning classification algorithms such as support vector machines function well with unstructured and semi structured data such as text,images,and videos,but their performance and robustness are restricted by the size of the accompanying training data.Deep learning on the other hand creates an artificial neural network that can learn and make intelligent judgments on its own by layering algorithms.It takes use of plentiful low-cost computing and many approaches are focused with very big datasets that are concerned with creating far larger and more sophisticated neural networks.Generative modelling,also known as Generative Adversarial Networks(GANs),is an unsupervised deep learning task that entails automatically discovering and learning regularities or patterns in input data in order for the model to generate or output new examples that could have been drawn from the original dataset.GANs are an exciting and rapidly changingfield that delivers on the promise of generative models in terms of their ability to generate realistic examples across a range of problem domains,most notably in image-to-image translation tasks and hasn't been explored much for Autism spectrum disorder prediction in the past.In this paper,we present a novel conditional generative adversarial network,or cGAN for short,which is a form of GAN that uses a generator model to conditionally generate images.In terms of prediction and accuracy,they outperform the standard GAN.The pro-posed model is 74%more accurate than the traditional methods and takes only around 10 min for training even with a huge dataset.
基金This work is supported by the National Key Research and Development Program of China under Grant 2020YFC2004003 and Grant 2020YFC2004002the National Nature Science Foundation of China(NSFC)under Grant No.61571106。
文摘Generative adversarial networks(GANs)are paid more attention to dealing with the end-to-end speech enhancement in recent years.Various GANbased enhancement methods are presented to improve the quality of reconstructed speech.However,the performance of these GAN-based methods is worse than those of masking-based methods.To tackle this problem,we propose speech enhancement method with a residual dense generative adversarial network(RDGAN)contributing to map the log-power spectrum(LPS)of degraded speech to the clean one.In detail,a residual dense block(RDB)architecture is designed to better estimate the LPS of clean speech,which can extract rich local features of LPS through densely connected convolution layers.Meanwhile,sequential RDB connections are incorporated on various scales of LPS.It significantly increases the feature learning flexibility and robustness in the time-frequency domain.Simulations show that the proposed method achieves attractive speech enhancement performance in various acoustic environments.Specifically,in the untrained acoustic test with limited priors,e.g.,unmatched signal-to-noise ratio(SNR)and unmatched noise category,RDGAN can still outperform the existing GAN-based methods and masking-based method in the measures of PESQ and other evaluation indexes.It indicates that our method is more generalized in untrained conditions.
文摘Haze is a very common phenomenon that degrades or reduces visibility. It causes various problems where high-quality images are required such as traffic and security monitoring. So haze removal from scenes is an immediate demand for clear vision. Recently, in addition to the conventional dehazing mechanisms, different types of deep generative adversarial networks (GAN) are applied to suppress the noise and improve the dehazing performance. But it is unclear how these algorithms would perform on hazy images acquired “in the wild” and how we could gauge the progress in the field. To bridge this gap, this presents a comprehensive study on three single image dehazing state-of-the-art GAN models, such as AOD-Net, cGAN, and DHSGAN. We have experimented using benchmark dataset consisting of both synthetic and real-world hazy images. The obtained results are evaluated both quantitatively and qualitatively. Among these techniques, the DHSGAN gives the best performance.
文摘The emergence of adversarial examples has revealed the inadequacies in the robustness of image classification models based on Convolutional Neural Networks (CNNs). Particularly in recent years, the discovery of natural adversarial examples has posed significant challenges, as traditional defense methods against adversarial attacks have proven to be largely ineffective against these natural adversarial examples. This paper explores defenses against these natural adversarial examples from three perspectives: adversarial examples, model architecture, and dataset. First, it employs Class Activation Mapping (CAM) to visualize how models classify natural adversarial examples, identifying several typical attack patterns. Next, various common CNN models are analyzed to evaluate their susceptibility to these attacks, revealing that different architectures exhibit varying defensive capabilities. The study finds that as the depth of a network increases, its defenses against natural adversarial examples strengthen. Lastly, Finally, the impact of dataset class distribution on the defense capability of models is examined, focusing on two aspects: the number of classes in the training set and the number of predicted classes. This study investigates how these factors influence the model’s ability to defend against natural adversarial examples. Results indicate that reducing the number of training classes enhances the model’s defense against natural adversarial examples. Additionally, under a fixed number of training classes, some CNN models show an optimal range of predicted classes for achieving the best defense performance against these adversarial examples.
基金funded by the Key Research and Development Program of Zhejiang Province No.2023C01141the Science and Technology Innovation Community Project of the Yangtze River Delta No.23002410100suported by the Open Research Fund of the State Key Laboratory of Blockchain and Data Security,Zhejiang University.
文摘Graph Neural Networks(GNNs)have demonstrated outstanding capabilities in processing graph-structured data and are increasingly being integrated into large-scale pre-trained models,such as Large Language Models(LLMs),to enhance structural reasoning,knowledge retrieval,and memory management.The expansion of their application scope imposes higher requirements on the robustness of GNNs.However,as GNNs are applied to more dynamic and heterogeneous environments,they become increasingly vulnerable to real-world perturbations.In particular,graph data frequently encounters joint adversarial perturbations that simultaneously affect both structures and features,which are significantly more challenging than isolated attacks.These disruptions,caused by incomplete data,malicious attacks,or inherent noise,pose substantial threats to the stable and reliable performance of traditional GNN models.To address this issue,this study proposes the Dual-Shield Graph Neural Network(DSGNN),a defense model that simultaneously mitigates structural and feature perturbations.DSGNN utilizes two parallel GNN channels to independently process structural noise and feature noise,and introduces an adaptive fusion mechanism that integrates information from both pathways to generate robust node representations.Theoretical analysis demonstrates that DSGNN achieves a tighter robustness boundary under joint perturbations compared to conventional single-channel methods.Experimental evaluations across Cora,CiteSeer,and Industry datasets show that DSGNN achieves the highest average classification accuracy under various adversarial settings,reaching 81.24%,71.94%,and 81.66%,respectively,outperforming GNNGuard,GCN-Jaccard,GCN-SVD,RGCN,and NoisyGNN.These results underscore the importance of multi-view perturbation decoupling in constructing resilient GNN models for real-world applications.
基金supported by the General Program of the National Natural Science Foundation of China(Grant No.61977029).
文摘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.
文摘In this paper,a communication model in cognitive radios is developed and uses machine learning to learn the dynamics of jamming attacks in cognitive radios.It is designed further to make their transmission decision that automati-cally adapts to the transmission dynamics to mitigate the launched jamming attacks.The generative adversarial learning neural network(GALNN)or genera-tive dynamic neural network(GDNN)automatically learns with the synthesized training data(training)with a generator and discriminator type neural networks that encompass minimax game theory.The elimination of the jamming attack is carried out with the assistance of the defense strategies and with an increased detection rate in the generative adversarial network(GAN).The GDNN with game theory is designed to validate the channel condition with the cross entropy loss function and back-propagation algorithm,which improves the communica-tion reliability in the network.The simulation is conducted in NS2.34 tool against several performance metrics to reduce the misdetection rate and false alarm rates.The results show that the GDNN obtains an increased rate of successful transmis-sion by taking optimal actions to act as a defense mechanism to mislead the jam-mer,where the jammer makes high misclassification errors on transmission dynamics.
基金supported by the National Key Research and Development Program of China[grant number 2020YFA0608000]the National Natural Science Foundation of China[grant number 42075141]+2 种基金the Meteorological Joint Funds of the National Natural Science Foundation of China[grant number U2142211]the Key Project Fund of the Shanghai 2020“Science and Technology Innovation Action Plan”for Social Development[grant number 20dz1200702]the first batch of Model Interdisciplinary Joint Research Projects of Tongji University in 2021[grant number YB-21-202110].
基金Ant Financial,Zhejiang University Financial Technology Research Center.
文摘With the rapid developments of artificial intelligence(AI)and deep learning(DL)techniques,it is critical to ensure the security and robustness of the deployed algorithms.Recently,the security vulnerability of DL algorithms to adversarial samples has been widely recognized.The fabricated samples can lead to various misbehaviors of the DL models while being perceived as benign by humans.Successful implementations of adversarial attacks in real physical-world scenarios further demonstrate their practicality.Hence,adversarial attack and defense techniques have attracted increasing attention from both machine learning and security communities and have become a hot research topic in recent years.In this paper,we first introduce the theoretical foundations,algorithms,and applications of adversarial attack techniques.We then describe a few research efforts on the defense techniques,which cover the broad frontier in the field.Several open problems and challenges are subsequently discussed,which we hope will provoke further research efforts in this critical area.
基金This research work is supported by the National Natural Science Foundation of China(NO.61772454,6171101570,61602059)Hunan Provincial Natural Science Foundation of China(No.2017JJ3334)+1 种基金the Research Foundation of Education Bureau of Hunan Province,China(No.16C0045)the Open Project Program of the National Laboratory of Pattern Recognition(NLPR).Professor Jin Wang is the corresponding author.
文摘Recently,many researchers have concentrated on using neural networks to learn features for Distant Supervised Relation Extraction(DSRE).These approaches generally use a softmax classifier with cross-entropy loss,which inevitably brings the noise of artificial class NA into classification process.To address the shortcoming,the classifier with ranking loss is employed to DSRE.Uniformly randomly selecting a relation or heuristically selecting the highest score among all incorrect relations are two common methods for generating a negative class in the ranking loss function.However,the majority of the generated negative class can be easily discriminated from positive class and will contribute little towards the training.Inspired by Generative Adversarial Networks(GANs),we use a neural network as the negative class generator to assist the training of our desired model,which acts as the discriminator in GANs.Through the alternating optimization of generator and discriminator,the generator is learning to produce more and more discriminable negative classes and the discriminator has to become better as well.This framework is independent of the concrete form of generator and discriminator.In this paper,we use a two layers fully-connected neural network as the generator and the Piecewise Convolutional Neural Networks(PCNNs)as the discriminator.Experiment results show that our proposed GAN-based method is effective and performs better than state-of-the-art methods.
基金supported by the Public Welfare Technology Application Research Project of Zhejiang Province,China(No.LGF21F010001)the Key Research and Development Program of Zhejiang Province,China(Grant No.2019C01002)the Key Research and Development Program of Zhejiang Province,China(Grant No.2021C03138)。
文摘Blind image quality assessment(BIQA)is of fundamental importance in low-level computer vision community.Increasing interest has been drawn in exploiting deep neural networks for BIQA.Despite of the notable success achieved,there is a broad consensus that training deep convolutional neural networks(DCNN)heavily relies on massive annotated data.Unfortunately,BIQA is typically a small sample problem,resulting the generalization ability of BIQA severely restricted.In order to improve the accuracy and generalization ability of BIQA metrics,this work proposed a totally opinion-unaware BIQA in which no subjective annotations are involved in the training stage.Multiple full-reference image quality assessment(FR-IQA)metrics are employed to label the distorted image as a substitution of subjective quality annotation.A deep neural network(DNN)is trained to blindly predict the multiple FR-IQA score in absence of corresponding pristine image.In the end,a selfsupervised FR-IQA score aggregator implemented by adversarial auto-encoder pools the predictions of multiple FR-IQA scores into the final quality predicting score.Even though none of subjective scores are involved in the training stage,experimental results indicate that our proposed full reference induced BIQA framework is as competitive as state-of-the-art BIQA metrics.
文摘These days,deep learning and computer vision are much-growing fields in this modern world of information technology.Deep learning algorithms and computer vision have achieved great success in different applications like image classification,speech recognition,self-driving vehicles,disease diagnostics,and many more.Despite success in various applications,it is found that these learning algorithms face severe threats due to adversarial attacks.Adversarial examples are inputs like images in the computer vision field,which are intentionally slightly changed or perturbed.These changes are humanly imperceptible.But are misclassified by a model with high probability and severely affects the performance or prediction.In this scenario,we present a deep image restoration model that restores adversarial examples so that the target model is classified correctly again.We proved that our defense method against adversarial attacks based on a deep image restoration model is simple and state-of-the-art by providing strong experimental results evidence.We have used MNIST and CIFAR10 datasets for experiments and analysis of our defense method.In the end,we have compared our method to other state-ofthe-art defense methods and proved that our results are better than other rival methods.
基金The work is supported by the National Key Research Development Program of China(2016QY01W0200)the National Natural Science Foundation of China NSFC(U1636101,U1736211,U1636219).
文摘Image classifiers that based on Deep Neural Networks(DNNs)have been proved to be easily fooled by well-designed perturbations.Previous defense methods have the limitations of requiring expensive computation or reducing the accuracy of the image classifiers.In this paper,we propose a novel defense method which based on perceptual hash.Our main goal is to destroy the process of perturbations generation by comparing the similarities of images thus achieve the purpose of defense.To verify our idea,we defended against two main attack methods(a white-box attack and a black-box attack)in different DNN-based image classifiers and show that,after using our defense method,the attack-success-rate for all DNN-based image classifiers decreases significantly.More specifically,for the white-box attack,the attack-success-rate is reduced by an average of 36.3%.For the black-box attack,the average attack-success-rate of targeted attack and non-targeted attack has been reduced by 72.8%and 76.7%respectively.The proposed method is a simple and effective defense method and provides a new way to defend against adversarial samples.
