We present a method for solving partial differential equations using artificial neural networks and an adaptive collocation strategy.In this procedure,a coarse grid of training points is used at the initial training s...We present a method for solving partial differential equations using artificial neural networks and an adaptive collocation strategy.In this procedure,a coarse grid of training points is used at the initial training stages,while more points are added at later stages based on the value of the residual at a larger set of evaluation points.This method increases the robustness of the neural network approximation and can result in significant computational savings,particularly when the solution is non-smooth.Numerical results are presented for benchmark problems for scalar-valued PDEs,namely Poisson and Helmholtz equations,as well as for an inverse acoustics problem.展开更多
In this paper,a deep collocation method(DCM)for thin plate bending problems is proposed.This method takes advantage of computational graphs and backpropagation algorithms involved in deep learning.Besides,the proposed...In this paper,a deep collocation method(DCM)for thin plate bending problems is proposed.This method takes advantage of computational graphs and backpropagation algorithms involved in deep learning.Besides,the proposed DCM is based on a feedforward deep neural network(DNN)and differs from most previous applications of deep learning for mechanical problems.First,batches of randomly distributed collocation points are initially generated inside the domain and along the boundaries.A loss function is built with the aim that the governing partial differential equations(PDEs)of Kirchhoff plate bending problems,and the boundary/initial conditions are minimised at those collocation points.A combination of optimizers is adopted in the backpropagation process to minimize the loss function so as to obtain the optimal hyperparameters.In Kirchhoff plate bending problems,the C^1 continuity requirement poses significant difficulties in traditional mesh-based methods.This can be solved by the proposed DCM,which uses a deep neural network to approximate the continuous transversal deflection,and is proved to be suitable to the bending analysis of Kirchhoff plate of various geometries.展开更多
The leakage of medical audio data in telemedicine seriously violates the privacy of patients.In order to avoid the leakage of patient information in telemedicine,a two-stage reversible robust audio watermarking algori...The leakage of medical audio data in telemedicine seriously violates the privacy of patients.In order to avoid the leakage of patient information in telemedicine,a two-stage reversible robust audio watermarking algorithm is proposed to protect medical audio data.The scheme decomposes the medical audio into two independent embedding domains,embeds the robust watermark and the reversible watermark into the two domains respectively.In order to ensure the audio quality,the Hurst exponent is used to find a suitable position for watermark embedding.Due to the independence of the two embedding domains,the embedding of the second-stage reversible watermark will not affect the first-stage watermark,so the robustness of the first-stage watermark can be well maintained.In the second stage,the correlation between the sampling points in the medical audio is used to modify the hidden bits of the histogram to reduce the modification of the medical audio and reduce the distortion caused by reversible embedding.Simulation experiments show that this scheme has strong robustness against signal processing operations such as MP3 compression of 48 db,additive white Gaussian noise(AWGN)of 20 db,low-pass filtering,resampling,re-quantization and other attacks,and has good imperceptibility.展开更多
A novel nonlocal operator theory based on the variational principle is proposed for the solution of partial differential equations.Common differential operators as well as the variational forms are defined within the ...A novel nonlocal operator theory based on the variational principle is proposed for the solution of partial differential equations.Common differential operators as well as the variational forms are defined within the context of nonlocal operators.The present nonlocal formulation allows the assembling of the tangent stiffness matrix with ease and simplicity,which is necessary for the eigenvalue analysis such as the waveguide problem.The present formulation is applied to solve the differential electromagnetic vector wave equations based on electric fields.The governing equations are converted into nonlocal integral form.An hourglass energy functional is introduced for the elimination of zeroenergy modes.Finally,the proposed method is validated by testing three classical benchmark problems.展开更多
Deep Learning(DL)is such a powerful tool that we have seen tremendous success in areas such as Computer Vision,Speech Recognition,and Natural Language Processing.Since Automated Modulation Classification(AMC)is an imp...Deep Learning(DL)is such a powerful tool that we have seen tremendous success in areas such as Computer Vision,Speech Recognition,and Natural Language Processing.Since Automated Modulation Classification(AMC)is an important part in Cognitive Radio Networks,we try to explore its potential in solving signal modulation recognition problem.It cannot be overlooked that DL model is a complex model,thus making them prone to over-fitting.DL model requires many training data to combat with over-fitting,but adding high quality labels to training data manually is not always cheap and accessible,especially in real-time system,which may counter unprecedented data in dataset.Semi-supervised Learning is a way to exploit unlabeled data effectively to reduce over-fitting in DL.In this paper,we extend Generative Adversarial Networks(GANs)to the semi-supervised learning will show it is a method can be used to create a more dataefficient classifier.展开更多
The virus SARS-CoV2,which causes the Coronavirus disease COVID-19 has become a pandemic and has spread to every inhabited continent.Given the increasing caseload,there is an urgent need to augment clinical skills in o...The virus SARS-CoV2,which causes the Coronavirus disease COVID-19 has become a pandemic and has spread to every inhabited continent.Given the increasing caseload,there is an urgent need to augment clinical skills in order to identify from among the many mild cases the few that will progress to critical illness.We present a first step towards building an artificial intelligence(AI)framework,with predictive analytics(PA)capabilities applied to real patient data,to provide rapid clinical decision-making support.COVID-19 has presented a pressing need as a)clinicians are still developing clinical acumen given the disease’s novelty,and b)resource limitations in a rapidly expanding pandemic require difficult decisions relating to resource allocation.The objectives of this research are:(1)to algorithmically identify the combinations of clinical characteristics of COVID-19 that predict outcomes,and(2)to develop a tool with AI capabilities that will predict patients at risk for more severe illness on initial presentation.The predictive models learn from historical data to help predict specifically who will develop acute respiratory distress syndrome(ARDS),a severe outcome in COVID-19.Our experimental results based on two hospitals in Wenzhou,Zhejang,China identify features most predictive of ARDS in COVID-19 initial presentation which would not have stood out to clinicians.A mild increase in elevated alanine aminotransferase(ALT)(a liver enzyme)),a presence of myalgias(body aches),and an increase in hemoglobin,in this order,are the clinical features,on presentation,that are the most predictive.Those two centers’COVID-19 case series symptoms on initial presentation can help predict severe outcomes.Predictive models that learned from historical data of patients from two Chinese hospitals achieved 70%to 80%accuracy in predicting severe cases.展开更多
Distributed denial-of-service(DDoS)is a rapidly growing problem with the fast development of the Internet.There are multitude DDoS detection approaches,however,three major problems about DDoS attack detection appear i...Distributed denial-of-service(DDoS)is a rapidly growing problem with the fast development of the Internet.There are multitude DDoS detection approaches,however,three major problems about DDoS attack detection appear in the big data environment.Firstly,to shorten the respond time of the DDoS attack detector;secondly,to reduce the required compute resources;lastly,to achieve a high detection rate with low false alarm rate.In the paper,we propose an abnormal network flow feature sequence prediction approach which could fit to be used as a DDoS attack detector in the big data environment and solve aforementioned problems.We define a network flow abnormal index as PDRA with the percentage of old IP addresses,the increment of the new IP addresses,the ratio of new IP addresses to the old IP addresses and average accessing rate of each new IP address.We design an IP address database using sequential storage model which has a constant time complexity.The autoregressive integrated moving average(ARIMA)trending prediction module will be started if and only if the number of continuous PDRA sequence value,which all exceed an PDRA abnormal threshold(PAT),reaches a certain preset threshold.And then calculate the probability that is the percentage of forecasting PDRA sequence value which exceed the PAT.Finally we identify the DDoS attack based on the abnormal probability of the forecasting PDRA sequence.Both theorem and experiment show that the method we proposed can effectively reduce the compute resources consumption,identify DDoS attack at its initial stage with higher detection rate and lower false alarm rate.展开更多
Vehicle re-identification(ReID)aims to retrieve the target vehicle in an extensive image gallery through its appearances from various views in the cross-camera scenario.It has gradually become a core technology of int...Vehicle re-identification(ReID)aims to retrieve the target vehicle in an extensive image gallery through its appearances from various views in the cross-camera scenario.It has gradually become a core technology of intelligent transportation system.Most existing vehicle re-identification models adopt the joint learning of global and local features.However,they directly use the extracted global features,resulting in insufficient feature expression.Moreover,local features are primarily obtained through advanced annotation and complex attention mechanisms,which require additional costs.To solve this issue,a multi-feature learning model with enhanced local attention for vehicle re-identification(MFELA)is proposed in this paper.The model consists of global and local branches.The global branch utilizes both middle and highlevel semantic features of ResNet50 to enhance the global representation capability.In addition,multi-scale pooling operations are used to obtain multiscale information.While the local branch utilizes the proposed Region Batch Dropblock(RBD),which encourages the model to learn discriminative features for different local regions and simultaneously drops corresponding same areas randomly in a batch during training to enhance the attention to local regions.Then features from both branches are combined to provide a more comprehensive and distinctive feature representation.Extensive experiments on VeRi-776 and VehicleID datasets prove that our method has excellent performance.展开更多
Due to the slow processing speed of text topic clustering in stand-alone architecture under the background of big data,this paper takes news text as the research object and proposes LDA text topic clustering algorithm...Due to the slow processing speed of text topic clustering in stand-alone architecture under the background of big data,this paper takes news text as the research object and proposes LDA text topic clustering algorithm based on Spark big data platform.Since the TF-IDF(term frequency-inverse document frequency)algorithm under Spark is irreversible to word mapping,the mapped words indexes cannot be traced back to the original words.In this paper,an optimized method is proposed that TF-IDF under Spark to ensure the text words can be restored.Firstly,the text feature is extracted by the TF-IDF algorithm combined CountVectorizer proposed in this paper,and then the features are inputted to the LDA(Latent Dirichlet Allocation)topic model for training.Finally,the text topic clustering is obtained.Experimental results show that for large data samples,the processing speed of LDA topic model clustering has been improved based Spark.At the same time,compared with the LDA topic model based on word frequency input,the model proposed in this paper has a reduction of perplexity.展开更多
Currently,some photorealistic computer graphics are very similar to photographic images.Photorealistic computer generated graphics can be forged as photographic images,causing serious security problems.The aim of this...Currently,some photorealistic computer graphics are very similar to photographic images.Photorealistic computer generated graphics can be forged as photographic images,causing serious security problems.The aim of this work is to use a deep neural network to detect photographic images(PI)versus computer generated graphics(CG).In existing approaches,image feature classification is computationally intensive and fails to achieve realtime analysis.This paper presents an effective approach to automatically identify PI and CG based on deep convolutional neural networks(DCNNs).Compared with some existing methods,the proposed method achieves real-time forensic tasks by deepening the network structure.Experimental results show that this approach can effectively identify PI and CG with average detection accuracy of 98%.展开更多
Wireless Sensor Networks(WSNs)are large-scale and high-density networks that typically have coverage area overlap.In addition,a random deployment of sensor nodes cannot fully guarantee coverage of the sensing area,whi...Wireless Sensor Networks(WSNs)are large-scale and high-density networks that typically have coverage area overlap.In addition,a random deployment of sensor nodes cannot fully guarantee coverage of the sensing area,which leads to coverage holes in WSNs.Thus,coverage control plays an important role in WSNs.To alleviate unnecessary energy wastage and improve network performance,we consider both energy efficiency and coverage rate for WSNs.In this paper,we present a novel coverage control algorithm based on Particle Swarm Optimization(PSO).Firstly,the sensor nodes are randomly deployed in a target area and remain static after deployment.Then,the whole network is partitioned into grids,and we calculate each grid’s coverage rate and energy consumption.Finally,each sensor nodes’sensing radius is adjusted according to the coverage rate and energy consumption of each grid.Simulation results show that our algorithm can effectively improve coverage rate and reduce energy consumption.展开更多
An epidemic is a quick and widespread disease that threatens many lives and damages the economy.The epidemic lifetime should be accurate so that timely and remedial steps are determined.These include the closing of bo...An epidemic is a quick and widespread disease that threatens many lives and damages the economy.The epidemic lifetime should be accurate so that timely and remedial steps are determined.These include the closing of borders schools,suspension of community and commuting services.The forecast of an outbreak effectively is a very necessary but difficult task.A predictive model that provides the best possible forecast is a great challenge for machine learning with only a few samples of training available.This work proposes and examines a prediction model based on a deep extreme learning machine(DELM).This methodology is used to carry out an experiment based on the recent Wuhan coronavirus outbreak.An optimized prediction model that has been developed,namely DELM,is demonstrated to be able to make a prediction that is fairly best.The results show that the new methodology is useful in developing an appropriate forecast when the samples are far from abundant during the critical period of the disease.During the investigation,it is shown that the proposed approach has the highest accuracy rate of 97.59%with 70%of training,30%of test and validation.Simulation results validate the prediction effectiveness of the proposed scheme.展开更多
Image recognition has always been a hot research topic in the scientific community and industry.The emergence of convolutional neural networks(CNN)has made this technology turned into research focus on the field of co...Image recognition has always been a hot research topic in the scientific community and industry.The emergence of convolutional neural networks(CNN)has made this technology turned into research focus on the field of computer vision,especially in image recognition.But it makes the recognition result largely dependent on the number and quality of training samples.Recently,DCGAN has become a frontier method for generating images,sounds,and videos.In this paper,DCGAN is used to generate sample that is difficult to collect and proposed an efficient design method of generating model.We combine DCGAN with CNN for the second time.Use DCGAN to generate samples and training in image recognition model,which based by CNN.This method can enhance the classification model and effectively improve the accuracy of image recognition.In the experiment,we used the radar profile as dataset for 4 categories and achieved satisfactory classification performance.This paper applies image recognition technology to the meteorological field.展开更多
This paper aims to perform a comparison of deterministic and stochastic models.The stochastic modelling is a more realistic way to study the dynamics of gonorrhoea infection as compared to its corresponding determinis...This paper aims to perform a comparison of deterministic and stochastic models.The stochastic modelling is a more realistic way to study the dynamics of gonorrhoea infection as compared to its corresponding deterministic model.Also,the deterministic solution is itself mean of the stochastic solution of the model.For numerical analysis,first,we developed some explicit stochastic methods,but unfortunately,they do not remain consistent in certain situations.Then we proposed an implicitly driven explicit method for stochastic heavy alcohol epidemic model.The proposed method is independent of the choice of parameters and behaves well in all scenarios.So,some theorems and simulations are presented in support of the article.展开更多
Supply chain 4.0 refers to the fourth industrial revolution’s supply chain management systems,which integrate the supply chain’s manufacturing operations,information technology,and telecommunication processes.Althou...Supply chain 4.0 refers to the fourth industrial revolution’s supply chain management systems,which integrate the supply chain’s manufacturing operations,information technology,and telecommunication processes.Although supply chain 4.0 aims to improve supply chains’production systems and profitability,it is subject to different operational and disruptive risks.Operational risks are a big challenge in the cycle of supply chain 4.0 for controlling the demand and supply operations to produce and deliver products across IT systems.This paper proposes a voting classifier to identify the operational risks in the supply chain 4.0 based on a Sine Cosine Dynamic Group(SCDG)algorithm.Exploration and exploitation mechanisms of the basic Sine Cosine Algorithm(CSA)are adjusted and controlled by two groups of agents that can be changed dynamically during the iterations.External and internal features were collected and analyzed from different data sources of service level agreements and transaction data from various KSA firms to validate the proposed algorithm’s efficiency.A balanced accuracy of 0.989 and a Mean Square Error(MSE)of 0.0476 were achieved compared with other optimization-based classifier techniques.A one-way analysis of variance(ANOVA)and Wilcoxon rank-sum tests were performed to show the superiority of the proposed SCDG algorithm.Thus,the experimental results indicate the effectiveness of the proposed SCDG algorithm-based voting classifier.展开更多
With the increasing application of surveillance cameras,vehicle re-identication(Re-ID)has attracted more attention in the eld of public security.Vehicle Re-ID meets challenge attributable to the large intra-class diff...With the increasing application of surveillance cameras,vehicle re-identication(Re-ID)has attracted more attention in the eld of public security.Vehicle Re-ID meets challenge attributable to the large intra-class differences caused by different views of vehicles in the traveling process and obvious inter-class similarities caused by similar appearances.Plentiful existing methods focus on local attributes by marking local locations.However,these methods require additional annotations,resulting in complex algorithms and insufferable computation time.To cope with these challenges,this paper proposes a vehicle Re-ID model based on optimized DenseNet121 with joint loss.This model applies the SE block to automatically obtain the importance of each channel feature and assign the corresponding weight to it,then features are transferred to the deep layer by adjusting the corresponding weights,which reduces the transmission of redundant information in the process of feature reuse in DenseNet121.At the same time,the proposed model leverages the complementary expression advantages of middle features of the CNN to enhance the feature expression ability.Additionally,a joint loss with focal loss and triplet loss is proposed in vehicle Re-ID to enhance the model’s ability to discriminate difcult-to-separate samples by enlarging the weight of the difcult-to-separate samples during the training process.Experimental results on the VeRi-776 dataset show that mAP and Rank-1 reach 75.5%and 94.8%,respectively.Besides,Rank-1 on small,medium and large sub-datasets of Vehicle ID dataset reach 81.3%,78.9%,and 76.5%,respectively,which surpasses most existing vehicle Re-ID methods.展开更多
The controller is indispensable in software-defined networking(SDN).With several features,controllers monitor the network and respond promptly to dynamic changes.Their performance affects the quality-of-service(QoS)in...The controller is indispensable in software-defined networking(SDN).With several features,controllers monitor the network and respond promptly to dynamic changes.Their performance affects the quality-of-service(QoS)in SDN.Every controller supports a set of features.However,the support of the features may be more prominent in one controller.Moreover,a single controller leads to performance,single-point-of-failure(SPOF),and scalability problems.To overcome this,a controller with an optimum feature set must be available for SDN.Furthermore,a cluster of optimum feature set controllers will overcome an SPOF and improve the QoS in SDN.Herein,leveraging an analytical network process(ANP),we rank SDN controllers regarding their supporting features and create a hierarchical control plane based cluster(HCPC)of the highly ranked controller computed using the ANP,evaluating their performance for the OS3E topology.The results demonstrated in Mininet reveal that a HCPC environment with an optimum controller achieves an improved QoS.Moreover,the experimental results validated in Mininet show that our proposed approach surpasses the existing distributed controller clustering(DCC)schemes in terms of several performance metrics i.e.,delay,jitter,throughput,load balancing,scalability and CPU(central processing unit)utilization.展开更多
Advanced cloud computing technology provides cost saving and flexibility of services for users.With the explosion of multimedia data,more and more data owners would outsource their personal multimedia data on the clou...Advanced cloud computing technology provides cost saving and flexibility of services for users.With the explosion of multimedia data,more and more data owners would outsource their personal multimedia data on the cloud.In the meantime,some computationally expensive tasks are also undertaken by cloud servers.However,the outsourced multimedia data and its applications may reveal the data owner’s private information because the data owners lose the control of their data.Recently,this thought has aroused new research interest on privacy-preserving reversible data hiding over outsourced multimedia data.In this paper,two reversible data hiding schemes are proposed for encrypted image data in cloud computing:reversible data hiding by homomorphic encryption and reversible data hiding in encrypted domain.The former is that additional bits are extracted after decryption and the latter is that extracted before decryption.Meanwhile,a combined scheme is also designed.This paper proposes the privacy-preserving outsourcing scheme of reversible data hiding over encrypted image data in cloud computing,which not only ensures multimedia data security without relying on the trustworthiness of cloud servers,but also guarantees that reversible data hiding can be operated over encrypted images at the different stages.Theoretical analysis confirms the correctness of the proposed encryption model and justifies the security of the proposed scheme.The computation cost of the proposed scheme is acceptable and adjusts to different security levels.展开更多
Nowadays,the amount of wed data is increasing at a rapid speed,which presents a serious challenge to the web monitoring.Text sentiment analysis,an important research topic in the area of natural language processing,is...Nowadays,the amount of wed data is increasing at a rapid speed,which presents a serious challenge to the web monitoring.Text sentiment analysis,an important research topic in the area of natural language processing,is a crucial task in the web monitoring area.The accuracy of traditional text sentiment analysis methods might be degraded in dealing with mass data.Deep learning is a hot research topic of the artificial intelligence in the recent years.By now,several research groups have studied the sentiment analysis of English texts using deep learning methods.In contrary,relatively few works have so far considered the Chinese text sentiment analysis toward this direction.In this paper,a method for analyzing the Chinese text sentiment is proposed based on the convolutional neural network(CNN)in deep learning in order to improve the analysis accuracy.The feature values of the CNN after the training process are nonuniformly distributed.In order to overcome this problem,a method for normalizing the feature values is proposed.Moreover,the dimensions of the text features are optimized through simulations.Finally,a method for updating the learning rate in the training process of the CNN is presented in order to achieve better performances.Experiment results on the typical datasets indicate that the accuracy of the proposed method can be improved compared with that of the traditional supervised machine learning methods,e.g.,the support vector machine method.展开更多
Text classification has always been an increasingly crucial topic in natural language processing.Traditional text classification methods based on machine learning have many disadvantages such as dimension explosion,da...Text classification has always been an increasingly crucial topic in natural language processing.Traditional text classification methods based on machine learning have many disadvantages such as dimension explosion,data sparsity,limited generalization ability and so on.Based on deep learning text classification,this paper presents an extensive study on the text classification models including Convolutional Neural Network-Based(CNN-Based),Recurrent Neural Network-Based(RNN-based),Attention Mechanisms-Based and so on.Many studies have proved that text classification methods based on deep learning outperform the traditional methods when processing large-scale and complex datasets.The main reasons are text classification methods based on deep learning can avoid cumbersome feature extraction process and have higher prediction accuracy for a large set of unstructured data.In this paper,we also summarize the shortcomings of traditional text classification methods and introduce the text classification process based on deep learning including text preprocessing,distributed representation of text,text classification model construction based on deep learning and performance evaluation.展开更多
文摘We present a method for solving partial differential equations using artificial neural networks and an adaptive collocation strategy.In this procedure,a coarse grid of training points is used at the initial training stages,while more points are added at later stages based on the value of the residual at a larger set of evaluation points.This method increases the robustness of the neural network approximation and can result in significant computational savings,particularly when the solution is non-smooth.Numerical results are presented for benchmark problems for scalar-valued PDEs,namely Poisson and Helmholtz equations,as well as for an inverse acoustics problem.
文摘In this paper,a deep collocation method(DCM)for thin plate bending problems is proposed.This method takes advantage of computational graphs and backpropagation algorithms involved in deep learning.Besides,the proposed DCM is based on a feedforward deep neural network(DNN)and differs from most previous applications of deep learning for mechanical problems.First,batches of randomly distributed collocation points are initially generated inside the domain and along the boundaries.A loss function is built with the aim that the governing partial differential equations(PDEs)of Kirchhoff plate bending problems,and the boundary/initial conditions are minimised at those collocation points.A combination of optimizers is adopted in the backpropagation process to minimize the loss function so as to obtain the optimal hyperparameters.In Kirchhoff plate bending problems,the C^1 continuity requirement poses significant difficulties in traditional mesh-based methods.This can be solved by the proposed DCM,which uses a deep neural network to approximate the continuous transversal deflection,and is proved to be suitable to the bending analysis of Kirchhoff plate of various geometries.
基金This work was supported,in part,by the Natural Science Foundation of Jiangsu Province under Grant Numbers BK20201136,BK20191401in part,by the National Nature Science Foundation of China under Grant Numbers 61502240,61502096,61304205,61773219in part,by the Priority Academic Program Development of Jiangsu Higher Education Institutions(PAPD)fund.Conflicts of Interest:The aut。
文摘The leakage of medical audio data in telemedicine seriously violates the privacy of patients.In order to avoid the leakage of patient information in telemedicine,a two-stage reversible robust audio watermarking algorithm is proposed to protect medical audio data.The scheme decomposes the medical audio into two independent embedding domains,embeds the robust watermark and the reversible watermark into the two domains respectively.In order to ensure the audio quality,the Hurst exponent is used to find a suitable position for watermark embedding.Due to the independence of the two embedding domains,the embedding of the second-stage reversible watermark will not affect the first-stage watermark,so the robustness of the first-stage watermark can be well maintained.In the second stage,the correlation between the sampling points in the medical audio is used to modify the hidden bits of the histogram to reduce the modification of the medical audio and reduce the distortion caused by reversible embedding.Simulation experiments show that this scheme has strong robustness against signal processing operations such as MP3 compression of 48 db,additive white Gaussian noise(AWGN)of 20 db,low-pass filtering,resampling,re-quantization and other attacks,and has good imperceptibility.
文摘A novel nonlocal operator theory based on the variational principle is proposed for the solution of partial differential equations.Common differential operators as well as the variational forms are defined within the context of nonlocal operators.The present nonlocal formulation allows the assembling of the tangent stiffness matrix with ease and simplicity,which is necessary for the eigenvalue analysis such as the waveguide problem.The present formulation is applied to solve the differential electromagnetic vector wave equations based on electric fields.The governing equations are converted into nonlocal integral form.An hourglass energy functional is introduced for the elimination of zeroenergy modes.Finally,the proposed method is validated by testing three classical benchmark problems.
基金This work is supported by the National Natural Science Foundation of China(Nos.61771154,61603239,61772454,6171101570).
文摘Deep Learning(DL)is such a powerful tool that we have seen tremendous success in areas such as Computer Vision,Speech Recognition,and Natural Language Processing.Since Automated Modulation Classification(AMC)is an important part in Cognitive Radio Networks,we try to explore its potential in solving signal modulation recognition problem.It cannot be overlooked that DL model is a complex model,thus making them prone to over-fitting.DL model requires many training data to combat with over-fitting,but adding high quality labels to training data manually is not always cheap and accessible,especially in real-time system,which may counter unprecedented data in dataset.Semi-supervised Learning is a way to exploit unlabeled data effectively to reduce over-fitting in DL.In this paper,we extend Generative Adversarial Networks(GANs)to the semi-supervised learning will show it is a method can be used to create a more dataefficient classifier.
文摘The virus SARS-CoV2,which causes the Coronavirus disease COVID-19 has become a pandemic and has spread to every inhabited continent.Given the increasing caseload,there is an urgent need to augment clinical skills in order to identify from among the many mild cases the few that will progress to critical illness.We present a first step towards building an artificial intelligence(AI)framework,with predictive analytics(PA)capabilities applied to real patient data,to provide rapid clinical decision-making support.COVID-19 has presented a pressing need as a)clinicians are still developing clinical acumen given the disease’s novelty,and b)resource limitations in a rapidly expanding pandemic require difficult decisions relating to resource allocation.The objectives of this research are:(1)to algorithmically identify the combinations of clinical characteristics of COVID-19 that predict outcomes,and(2)to develop a tool with AI capabilities that will predict patients at risk for more severe illness on initial presentation.The predictive models learn from historical data to help predict specifically who will develop acute respiratory distress syndrome(ARDS),a severe outcome in COVID-19.Our experimental results based on two hospitals in Wenzhou,Zhejang,China identify features most predictive of ARDS in COVID-19 initial presentation which would not have stood out to clinicians.A mild increase in elevated alanine aminotransferase(ALT)(a liver enzyme)),a presence of myalgias(body aches),and an increase in hemoglobin,in this order,are the clinical features,on presentation,that are the most predictive.Those two centers’COVID-19 case series symptoms on initial presentation can help predict severe outcomes.Predictive models that learned from historical data of patients from two Chinese hospitals achieved 70%to 80%accuracy in predicting severe cases.
基金This work was supported by the National Natural Science Foundation of China[No.61762033,61363071,61702539]The National Natural Science Foundation of Hainan[No.617048,2018CXTD333]+1 种基金Hainan University Doctor Start Fund Project[No.kyqd1328]Hainan University Youth Fund Project[No.qnjj1444].
文摘Distributed denial-of-service(DDoS)is a rapidly growing problem with the fast development of the Internet.There are multitude DDoS detection approaches,however,three major problems about DDoS attack detection appear in the big data environment.Firstly,to shorten the respond time of the DDoS attack detector;secondly,to reduce the required compute resources;lastly,to achieve a high detection rate with low false alarm rate.In the paper,we propose an abnormal network flow feature sequence prediction approach which could fit to be used as a DDoS attack detector in the big data environment and solve aforementioned problems.We define a network flow abnormal index as PDRA with the percentage of old IP addresses,the increment of the new IP addresses,the ratio of new IP addresses to the old IP addresses and average accessing rate of each new IP address.We design an IP address database using sequential storage model which has a constant time complexity.The autoregressive integrated moving average(ARIMA)trending prediction module will be started if and only if the number of continuous PDRA sequence value,which all exceed an PDRA abnormal threshold(PAT),reaches a certain preset threshold.And then calculate the probability that is the percentage of forecasting PDRA sequence value which exceed the PAT.Finally we identify the DDoS attack based on the abnormal probability of the forecasting PDRA sequence.Both theorem and experiment show that the method we proposed can effectively reduce the compute resources consumption,identify DDoS attack at its initial stage with higher detection rate and lower false alarm rate.
基金This work was supported,in part,by the National Nature Science Foundation of China under Grant Numbers 61502240,61502096,61304205,61773219in part,by the Natural Science Foundation of Jiangsu Province under grant numbers BK20201136,BK20191401+1 种基金in part,by the Postgraduate Research&Practice Innovation Program of Jiangsu Province under Grant Numbers SJCX21_0363in part,by the Priority Academic Program Development of Jiangsu Higher Education Institutions(PAPD)fund.
文摘Vehicle re-identification(ReID)aims to retrieve the target vehicle in an extensive image gallery through its appearances from various views in the cross-camera scenario.It has gradually become a core technology of intelligent transportation system.Most existing vehicle re-identification models adopt the joint learning of global and local features.However,they directly use the extracted global features,resulting in insufficient feature expression.Moreover,local features are primarily obtained through advanced annotation and complex attention mechanisms,which require additional costs.To solve this issue,a multi-feature learning model with enhanced local attention for vehicle re-identification(MFELA)is proposed in this paper.The model consists of global and local branches.The global branch utilizes both middle and highlevel semantic features of ResNet50 to enhance the global representation capability.In addition,multi-scale pooling operations are used to obtain multiscale information.While the local branch utilizes the proposed Region Batch Dropblock(RBD),which encourages the model to learn discriminative features for different local regions and simultaneously drops corresponding same areas randomly in a batch during training to enhance the attention to local regions.Then features from both branches are combined to provide a more comprehensive and distinctive feature representation.Extensive experiments on VeRi-776 and VehicleID datasets prove that our method has excellent performance.
基金This work is supported by the Science Research Projects of Hunan Provincial Education Department(Nos.18A174,18C0262)the National Natural Science Foundation of China(No.61772561)+2 种基金the Key Research&Development Plan of Hunan Province(Nos.2018NK2012,2019SK2022)the Degree&Postgraduate Education Reform Project of Hunan Province(No.209)the Postgraduate Education and Teaching Reform Project of Central South Forestry University(No.2019JG013).
文摘Due to the slow processing speed of text topic clustering in stand-alone architecture under the background of big data,this paper takes news text as the research object and proposes LDA text topic clustering algorithm based on Spark big data platform.Since the TF-IDF(term frequency-inverse document frequency)algorithm under Spark is irreversible to word mapping,the mapped words indexes cannot be traced back to the original words.In this paper,an optimized method is proposed that TF-IDF under Spark to ensure the text words can be restored.Firstly,the text feature is extracted by the TF-IDF algorithm combined CountVectorizer proposed in this paper,and then the features are inputted to the LDA(Latent Dirichlet Allocation)topic model for training.Finally,the text topic clustering is obtained.Experimental results show that for large data samples,the processing speed of LDA topic model clustering has been improved based Spark.At the same time,compared with the LDA topic model based on word frequency input,the model proposed in this paper has a reduction of perplexity.
基金This work is supported,in part,by the National Natural Science Foundation of China under grant numbers U1536206,U1405254,61772283,61602253,61672294,61502242In part,by the Jiangsu Basic Research Programs-Natural Science Foundation under grant numbers BK20150925 and BK20151530+1 种基金In part,by the Priority Academic Program Development of Jiangsu Higher Education Institutions(PAPD)fundIn part,by the Collaborative Innovation Center of Atmospheric Environment and Equipment Technology(CICAEET)fund,China.
文摘Currently,some photorealistic computer graphics are very similar to photographic images.Photorealistic computer generated graphics can be forged as photographic images,causing serious security problems.The aim of this work is to use a deep neural network to detect photographic images(PI)versus computer generated graphics(CG).In existing approaches,image feature classification is computationally intensive and fails to achieve realtime analysis.This paper presents an effective approach to automatically identify PI and CG based on deep convolutional neural networks(DCNNs).Compared with some existing methods,the proposed method achieves real-time forensic tasks by deepening the network structure.Experimental results show that this approach can effectively identify PI and CG with average detection accuracy of 98%.
基金This research work was supported by the National Natural Science Foundation of China(61772454,61811530332).Professor Gwang-jun Kim is the corresponding author.
文摘Wireless Sensor Networks(WSNs)are large-scale and high-density networks that typically have coverage area overlap.In addition,a random deployment of sensor nodes cannot fully guarantee coverage of the sensing area,which leads to coverage holes in WSNs.Thus,coverage control plays an important role in WSNs.To alleviate unnecessary energy wastage and improve network performance,we consider both energy efficiency and coverage rate for WSNs.In this paper,we present a novel coverage control algorithm based on Particle Swarm Optimization(PSO).Firstly,the sensor nodes are randomly deployed in a target area and remain static after deployment.Then,the whole network is partitioned into grids,and we calculate each grid’s coverage rate and energy consumption.Finally,each sensor nodes’sensing radius is adjusted according to the coverage rate and energy consumption of each grid.Simulation results show that our algorithm can effectively improve coverage rate and reduce energy consumption.
文摘An epidemic is a quick and widespread disease that threatens many lives and damages the economy.The epidemic lifetime should be accurate so that timely and remedial steps are determined.These include the closing of borders schools,suspension of community and commuting services.The forecast of an outbreak effectively is a very necessary but difficult task.A predictive model that provides the best possible forecast is a great challenge for machine learning with only a few samples of training available.This work proposes and examines a prediction model based on a deep extreme learning machine(DELM).This methodology is used to carry out an experiment based on the recent Wuhan coronavirus outbreak.An optimized prediction model that has been developed,namely DELM,is demonstrated to be able to make a prediction that is fairly best.The results show that the new methodology is useful in developing an appropriate forecast when the samples are far from abundant during the critical period of the disease.During the investigation,it is shown that the proposed approach has the highest accuracy rate of 97.59%with 70%of training,30%of test and validation.Simulation results validate the prediction effectiveness of the proposed scheme.
文摘Image recognition has always been a hot research topic in the scientific community and industry.The emergence of convolutional neural networks(CNN)has made this technology turned into research focus on the field of computer vision,especially in image recognition.But it makes the recognition result largely dependent on the number and quality of training samples.Recently,DCGAN has become a frontier method for generating images,sounds,and videos.In this paper,DCGAN is used to generate sample that is difficult to collect and proposed an efficient design method of generating model.We combine DCGAN with CNN for the second time.Use DCGAN to generate samples and training in image recognition model,which based by CNN.This method can enhance the classification model and effectively improve the accuracy of image recognition.In the experiment,we used the radar profile as dataset for 4 categories and achieved satisfactory classification performance.This paper applies image recognition technology to the meteorological field.
基金The first author also thanks Prince Sultan University for funding this work through research-group number RG-DES2017-01-17.
文摘This paper aims to perform a comparison of deterministic and stochastic models.The stochastic modelling is a more realistic way to study the dynamics of gonorrhoea infection as compared to its corresponding deterministic model.Also,the deterministic solution is itself mean of the stochastic solution of the model.For numerical analysis,first,we developed some explicit stochastic methods,but unfortunately,they do not remain consistent in certain situations.Then we proposed an implicitly driven explicit method for stochastic heavy alcohol epidemic model.The proposed method is independent of the choice of parameters and behaves well in all scenarios.So,some theorems and simulations are presented in support of the article.
文摘Supply chain 4.0 refers to the fourth industrial revolution’s supply chain management systems,which integrate the supply chain’s manufacturing operations,information technology,and telecommunication processes.Although supply chain 4.0 aims to improve supply chains’production systems and profitability,it is subject to different operational and disruptive risks.Operational risks are a big challenge in the cycle of supply chain 4.0 for controlling the demand and supply operations to produce and deliver products across IT systems.This paper proposes a voting classifier to identify the operational risks in the supply chain 4.0 based on a Sine Cosine Dynamic Group(SCDG)algorithm.Exploration and exploitation mechanisms of the basic Sine Cosine Algorithm(CSA)are adjusted and controlled by two groups of agents that can be changed dynamically during the iterations.External and internal features were collected and analyzed from different data sources of service level agreements and transaction data from various KSA firms to validate the proposed algorithm’s efficiency.A balanced accuracy of 0.989 and a Mean Square Error(MSE)of 0.0476 were achieved compared with other optimization-based classifier techniques.A one-way analysis of variance(ANOVA)and Wilcoxon rank-sum tests were performed to show the superiority of the proposed SCDG algorithm.Thus,the experimental results indicate the effectiveness of the proposed SCDG algorithm-based voting classifier.
基金supported,in part,by the National Nature Science Foundation of China under Grant Numbers 61502240,61502096,61304205,61773219in part,by the Natural Science Foundation of Jiangsu Province under Grant Numbers BK20201136,BK20191401in part,by the Priority Academic Program Development of Jiangsu Higher Education Institutions(PAPD)fund.
文摘With the increasing application of surveillance cameras,vehicle re-identication(Re-ID)has attracted more attention in the eld of public security.Vehicle Re-ID meets challenge attributable to the large intra-class differences caused by different views of vehicles in the traveling process and obvious inter-class similarities caused by similar appearances.Plentiful existing methods focus on local attributes by marking local locations.However,these methods require additional annotations,resulting in complex algorithms and insufferable computation time.To cope with these challenges,this paper proposes a vehicle Re-ID model based on optimized DenseNet121 with joint loss.This model applies the SE block to automatically obtain the importance of each channel feature and assign the corresponding weight to it,then features are transferred to the deep layer by adjusting the corresponding weights,which reduces the transmission of redundant information in the process of feature reuse in DenseNet121.At the same time,the proposed model leverages the complementary expression advantages of middle features of the CNN to enhance the feature expression ability.Additionally,a joint loss with focal loss and triplet loss is proposed in vehicle Re-ID to enhance the model’s ability to discriminate difcult-to-separate samples by enlarging the weight of the difcult-to-separate samples during the training process.Experimental results on the VeRi-776 dataset show that mAP and Rank-1 reach 75.5%and 94.8%,respectively.Besides,Rank-1 on small,medium and large sub-datasets of Vehicle ID dataset reach 81.3%,78.9%,and 76.5%,respectively,which surpasses most existing vehicle Re-ID methods.
基金supported by the MSIT(Ministry of Science and ICT),Korea,under the ITRC(Information Technology Research Center)support program(IITP-2020-2018-0-01431)supervised by the IITP(Institute for Information&Communications Technology Planning&Evaluation).
文摘The controller is indispensable in software-defined networking(SDN).With several features,controllers monitor the network and respond promptly to dynamic changes.Their performance affects the quality-of-service(QoS)in SDN.Every controller supports a set of features.However,the support of the features may be more prominent in one controller.Moreover,a single controller leads to performance,single-point-of-failure(SPOF),and scalability problems.To overcome this,a controller with an optimum feature set must be available for SDN.Furthermore,a cluster of optimum feature set controllers will overcome an SPOF and improve the QoS in SDN.Herein,leveraging an analytical network process(ANP),we rank SDN controllers regarding their supporting features and create a hierarchical control plane based cluster(HCPC)of the highly ranked controller computed using the ANP,evaluating their performance for the OS3E topology.The results demonstrated in Mininet reveal that a HCPC environment with an optimum controller achieves an improved QoS.Moreover,the experimental results validated in Mininet show that our proposed approach surpasses the existing distributed controller clustering(DCC)schemes in terms of several performance metrics i.e.,delay,jitter,throughput,load balancing,scalability and CPU(central processing unit)utilization.
基金This work was supported by the National Natural Science Foundation of China(No.61702276)the Startup Foundation for Introducing Talent of Nanjing University of Information Science and Technology under Grant 2016r055 and the Priority Academic Program Development(PAPD)of Jiangsu Higher Education Institutions.The authors are grateful for the anonymous reviewers who made constructive comments and improvements.
文摘Advanced cloud computing technology provides cost saving and flexibility of services for users.With the explosion of multimedia data,more and more data owners would outsource their personal multimedia data on the cloud.In the meantime,some computationally expensive tasks are also undertaken by cloud servers.However,the outsourced multimedia data and its applications may reveal the data owner’s private information because the data owners lose the control of their data.Recently,this thought has aroused new research interest on privacy-preserving reversible data hiding over outsourced multimedia data.In this paper,two reversible data hiding schemes are proposed for encrypted image data in cloud computing:reversible data hiding by homomorphic encryption and reversible data hiding in encrypted domain.The former is that additional bits are extracted after decryption and the latter is that extracted before decryption.Meanwhile,a combined scheme is also designed.This paper proposes the privacy-preserving outsourcing scheme of reversible data hiding over encrypted image data in cloud computing,which not only ensures multimedia data security without relying on the trustworthiness of cloud servers,but also guarantees that reversible data hiding can be operated over encrypted images at the different stages.Theoretical analysis confirms the correctness of the proposed encryption model and justifies the security of the proposed scheme.The computation cost of the proposed scheme is acceptable and adjusts to different security levels.
文摘Nowadays,the amount of wed data is increasing at a rapid speed,which presents a serious challenge to the web monitoring.Text sentiment analysis,an important research topic in the area of natural language processing,is a crucial task in the web monitoring area.The accuracy of traditional text sentiment analysis methods might be degraded in dealing with mass data.Deep learning is a hot research topic of the artificial intelligence in the recent years.By now,several research groups have studied the sentiment analysis of English texts using deep learning methods.In contrary,relatively few works have so far considered the Chinese text sentiment analysis toward this direction.In this paper,a method for analyzing the Chinese text sentiment is proposed based on the convolutional neural network(CNN)in deep learning in order to improve the analysis accuracy.The feature values of the CNN after the training process are nonuniformly distributed.In order to overcome this problem,a method for normalizing the feature values is proposed.Moreover,the dimensions of the text features are optimized through simulations.Finally,a method for updating the learning rate in the training process of the CNN is presented in order to achieve better performances.Experiment results on the typical datasets indicate that the accuracy of the proposed method can be improved compared with that of the traditional supervised machine learning methods,e.g.,the support vector machine method.
基金This work supported in part by the National Natural Science Foundation of China under Grant 61872134,in part by the Natural Science Foundation of Hunan Province under Grant 2018JJ2062in part by Science and Technology Development Center of the Ministry of Education under Grant 2019J01020in part by the 2011 Collaborative Innovative Center for Development and Utilization of Finance and Economics Big Data Property,Universities of Hunan Province。
文摘Text classification has always been an increasingly crucial topic in natural language processing.Traditional text classification methods based on machine learning have many disadvantages such as dimension explosion,data sparsity,limited generalization ability and so on.Based on deep learning text classification,this paper presents an extensive study on the text classification models including Convolutional Neural Network-Based(CNN-Based),Recurrent Neural Network-Based(RNN-based),Attention Mechanisms-Based and so on.Many studies have proved that text classification methods based on deep learning outperform the traditional methods when processing large-scale and complex datasets.The main reasons are text classification methods based on deep learning can avoid cumbersome feature extraction process and have higher prediction accuracy for a large set of unstructured data.In this paper,we also summarize the shortcomings of traditional text classification methods and introduce the text classification process based on deep learning including text preprocessing,distributed representation of text,text classification model construction based on deep learning and performance evaluation.
