检索结果-南通市图书馆

GrCol-PPFL:User-Based Group Collaborative Federated Learning Privacy Protection Framework

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2023年第1期74卷 1923-1939页

作者： Jieren Cheng Zhenhao Liu Yiming shi Ping Luo Victor s.sheng school of Compute science and Technology Hainan UniversityHaikou570228China Hainan Blockchain Technology Engineering Research Center Hainan UniversityHaikou570228China Department of Computer science Texas Tech University TX79409USA

With the increasing number of smart devices and the development of machine learning technology,the value of users’personal data is becoming more and more *** on the premise of protecting users’personal privacy data,federated learning(FL)uses data stored on edge devices to realize training tasks by contributing training model parameters without revealing the original ***,since FL can still leak the user’s original data by exchanging gradient *** existing privacy protection strategy will increase the uplink time due to encryption *** is a huge challenge in terms of *** there are a large number of devices,the privacy protection cost of the system is *** on these issues,we propose a privacy-preserving scheme of user-based group collaborative federated learning(GrCol-PPFL).Our scheme primarily divides participants into several groups and each group communicates in a chained transmission *** groups work in parallel at the same *** server distributes a random parameter with the same dimension as the model parameter for each participant as a mask for the model *** use the public datasets of modified national institute of standards and technology database(MNIsT)to test the model *** experimental results show that GrCol-PPFL not only ensures the accuracy of themodel,but also ensures the security of the user’s original data when users collude with each ***,through numerical experiments,we show that by changing the number of groups,we can find the optimal number of groups that reduces the uplink consumption time.

关键词： Federated learning privacy protection uplink consumption time

Few-shot Object Detection Based on the Transformer and High-Resolution Network

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2023年第2期74卷 3439-3454页

作者： Dengyong Zhang Huaijian Pu Feng Li Xiangling Ding Victor s.sheng Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation Changsha University of Science and TechnologyChangsha410114China school of Computer and Communication Engineering Changsha University of Science and TechnologyChangsha410114China school of Computer science and Engineering Hunan University of Science and TechnologyXiangtan411004China Department of Computer science Texas Tech UniversityLubbock79409TXUSA

Now object detection based on deep learning tries different *** uses fewer data training networks to achieve the effect of large dataset ***,the existing methods usually do not achieve the balance between network parameters and training *** makes the information provided by a small amount of picture data insufficient to optimize model parameters,resulting in unsatisfactory detection *** improve the accuracy of few shot object detection,this paper proposes a network based on the transformer and high-resolution feature extraction(THR).High-resolution feature extractionmaintains the resolution representation of the *** and spatial attention are used to make the network focus on features that are more useful to the *** addition,the recently popular transformer is used to fuse the features of the existing *** compensates for the previous network failure by making full use of existing object *** on the Pascal VOC and Ms-COCO datasets prove that the THR network has achieved better results than previous mainstream few shot object detection.

关键词： Object detection few shot object detection transformer high-resolution

A survey on Image semantic segmentation Using Deep Learning Techniques

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2023年第1期74卷 1941-1957页

作者： Jieren Cheng Hua Li Dengbo Li shuai Hua Victor s.sheng school of Computer science and Technology Hainan UniversityHaikou570228China school of Cyberspace security(school of Cryptology) Hainan UniversityHaikou570228China Hainan Blockchain Technology Engineering Research Center Hainan UniversityHaikou570228China Department of Computer science Texas Tech University TX 79409USA

Image semantic segmentation is an important branch of computer vision of a wide variety of practical applications such as medical image analysis,autonomous driving,virtual or augmented reality,*** recent years,due to the remarkable performance of transformer and multilayer perceptron(MLP)in computer vision,which is equivalent to convolutional neural network(CNN),there has been a substantial amount of image semantic segmentation works aimed at developing different types of deep learning *** survey aims to provide a comprehensive overview of deep learning methods in the field of general image semantic ***,the commonly used image segmentation datasets are ***,extensive pioneering works are deeply studied from multiple perspectives(e.g.,network structures,feature fusion methods,attention mechanisms),and are divided into four categories according to different network architectures:CNN-based architectures,transformer-based architectures,MLP-based architectures,and ***,this paper presents some common evaluation metrics and compares the respective advantages and limitations of popular techniques both in terms of architectural design and their experimental value on the most widely used ***,possible future research directions and challenges are discussed for the reference of other researchers.

关键词： Deep learning semantic segmentation CNN MLP transformer

Interpreting Randomly Wired Graph Models for Chinese NER

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computer Modeling in Engineering & sciences 2023年第1期134卷 747-761页

作者： Jie Chen Jiabao Xu Xuefeng Xi Zhiming Cui Victor s.sheng The school of Electronic and Information Engineering SuzhouUniversity of Science and TechnologySuzhouChina The school of Computer science Texas Tech UniversityTexasUSA

Interpreting deep neural networks is of great importance to understand and verify deep models for natural language processing(NLP)***,most existing approaches only focus on improving the performance of models but ignore their *** this work,we propose a Randomly Wired Graph Neural Network(RWGNN)by using graph to model the structure of Neural Network,which could solve two major problems(word-boundary ambiguity and polysemy)of ***,we develop a pipeline to explain the RWGNNby using saliency Map and Adversarial *** results demonstrate that our approach can identify meaningful and reasonable interpretations for hidden states of RWGNN.

关键词： Named entity recognition graph neural network saliency map random graph network interpretation

A New Method of Image Restoration Technology Based on WGAN

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computer systems science & Engineering 2022年第5期41卷 689-698页

作者： Wei Fang Enming Gu Weinan Yi Weiqing Wang Victor s.sheng school of Computer&software Engineering Research Center of Digital ForensicsMininstry of EducationNanjing University of Information Science&TechnologyNanjing210044China Provincial Key Laboratory for Computer Information Processing Technology Soochow UniversitySuzhou215325China Texas Tech University USA

With the development of image restoration technology based on deep learning,more complex problems are being solved,especially in image semantic inpainting based on ***,image semantic inpainting techniques are becoming more ***,due to the limitations of memory,the instability of training,and the lack of sample diversity,the results of image restoration are still encountering difficult problems,such as repairing the content of glitches which cannot be well integrated with the original ***,we propose an image inpainting network based on Wasserstein generative adversarial network(WGAN)*** the corresponding technology having been adjusted and improved,we attempted to use the Adam algorithm to replace the traditional stochastic gradient descent,and another algorithm to optimize the training used in recent *** evaluated our algorithm on the ImageNet *** obtained high-quality restoration results,indicating that our algorithm improves the clarity and consistency of the image.

关键词： Image restoration WGAN DCGAN context semantic

An Improved BPNN Prediction Method Based on Multi-strategy sparrow search Algorithm

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2023年第2期74卷 2789-2802页

作者： Xiangyan Tang Dengfang Feng KeQiu Li Jingxin Liu Jinyang song Victor s.sheng College of Intelligence and Computing Tianjin UniversityTianjin300350China school of Computer science and Technology Hainan UniversityHaikou570228China school of Cyberspace security(school of Cryptology) Hainan UniversityHaikou570228China Department of Computer science Texas Tech University TX 79409USA

Data prediction can improve the science of decision-making by making predictions about what happens in daily life based on natural law *** propagation(BP)neural network is a widely used prediction *** reduce its probability of falling into local optimum and improve the prediction accuracy,we propose an improved BP neural network prediction method based on a multi-strategy sparrow search algorithm(MssA).The weights and thresholds of the BP neural network are optimized using the sparrow search algorithm(ssA).Three strategies are designed to improve the ssA to enhance its optimization-seeking ability,leading to the MssA-BP prediction *** MssA algorithm was tested with nine different types of benchmark functions to verify the optimization performance of the *** different datasets were selected for comparison experiments on three groups of *** the same conditions,the mean absolute error(MAE),root mean square error(RMsE),andmean absolute percentage error(MAPE)of the prediction results of MssA-BPwere significantly reduced,and the convergence speed was significantly ***-BP can effectively improve the prediction accuracy and has certain application value.

关键词： Prediction parrow search algorithm back propagation neural network

Air Pollution Prediction Via Graph Attention Network and Gated Recurrent Unit

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2022年第10期73卷 673-687页

作者： shun Wang Lin Qiao Wei Fang Guodong Jing Victor s.sheng Yong Zhang Beijing Key Laboratory of Multimedia and Intelligent software Technology Beijing Artificial Intelligence Institutethe Faculty of Information TechnologyBeijing University of TechnologyBeijing100124China Beijing Meteorological Observatory Beijing100089China Nanjing University of Information science&Technology Nanjing210044China China Meteorological Administration Training Centre Beijing100081China Texas Tech University LubbockTX79409United States

PM2.5 concentration prediction is of great significance to environmental protection and human *** accurate prediction of PM2.5 concentration has become an important research ***,PM2.5 pollutants can spread in the earth’s atmosphere,causing mutual influence between different *** effectively capture the air pollution relationship between cities,this paper proposes a novel spatiotemporal model combining graph attention neural network(GAT)and gated recurrent unit(GRU),named GAT-GRU for PM2.5 concentration ***,GAT is used to learn the spatial dependence of PM2.5 concentration data in different cities,and GRU is to extract the temporal dependence of the long-term data *** proposed model integrates the learned spatio-temporal dependencies to capture long-term complex spatio-temporal *** that air pollution is related to the meteorological conditions of the city,the knowledge acquired from meteorological data is used in the model to enhance PM2.5 prediction *** input of the GAT-GRU model consists of PM2.5 concentration data and meteorological *** order to verify the effectiveness of the proposed GAT-GRU prediction model,this paper designs experiments on real-world datasets compared with other *** results prove that our model achieves excellent performance in PM2.5 concentration prediction.

关键词： Air pollution prediction deep learning spatiotemporal data modeling graph attention network

Gate-Attention and Dual-End Enhancement Mechanism for Multi-Label Text Classification

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2023年第11期77卷 1779-1793页

作者： Jieren Cheng Xiaolong Chen Wenghang Xu shuai Hua Zhu Tang Victor s.sheng school of Computer science and Technology Hainan UniversityHaikou570228China Hainan Blockchain Technology Engineering Research Center Hainan UniversityHaikou570228China school of Cyberspace security Hainan UniversityHaikou570228China Department of Computer science Texas Tech UniversityLubbock79409USA

In the realm of Multi-Label Text Classification(MLTC),the dual challenges of extracting rich semantic features from text and discerning inter-label relationships have spurred innovative *** studies in semantic feature extraction have turned to external knowledge to augment the model’s grasp of textual content,often overlooking intrinsic textual cues such as label statistical *** contrast,these endogenous insights naturally align with the classification *** our paper,to complement this focus on intrinsic knowledge,we introduce a novel Gate-Attention *** mechanism adeptly integrates statistical features from the text itself into the semantic fabric,enhancing the model’s capacity to understand and represent the ***,to address the intricate task of mining label correlations,we propose a Dual-end enhancement *** mechanism effectively mitigates the challenges of information loss and erroneous transmission inherent in traditional long short term memory *** conducted an extensive battery of experiments on the AAPD and RCV1-2 *** experiments serve the dual purpose of confirming the efficacy of both the Gate-Attention mechanism and the Dual-end enhancement *** final model unequivocally outperforms the baseline model,attesting to its *** findings emphatically underscore the imperativeness of taking into account not just external knowledge but also the inherent intricacies of textual data when crafting potent MLTC models.

关键词： Multi-label text classification feature extraction label distribution information sequence generation

Image Inpainting Detection Based on High-Pass Filter Attention Network

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computer systems science & Engineering 2022年第12期43卷 1145-1154页

作者： Can Xiao Feng Li Dengyong Zhang Pu Huang Xiangling Ding Victor s.sheng Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation Changsha University of Science and TechnologyChangsha410114China school of Computer and Communication Engineering Changsha University of Science and TechnologyChangsha410114China school of Computer science and Engineering Hunan University of Science and TechnologyXiangtan411004China Department of Computer science Texas Tech UniversityLubbock79409USA

Image inpainting based on deep learning has been greatly *** original purpose of image inpainting was to repair some broken photos, suchas inpainting artifacts. However, it may also be used for malicious operations,such as destroying evidence. Therefore, detection and localization of imageinpainting operations are essential. Recent research shows that high-pass filteringfull convolutional network (HPFCN) is applied to image inpainting detection andachieves good results. However, those methods did not consider the spatial location and channel information of the feature map. To solve these shortcomings, weintroduce the squeezed excitation blocks (sE) and propose a high-pass filter attention full convolutional network (HPACN). In feature extraction, we apply concurrent spatial and channel attention (scsE) to enhance feature extraction and obtainmore information. Channel attention (csE) is introduced in upsampling toenhance detection and localization. The experimental results show that the proposed method can achieve improvement on ImageNet.

关键词： Image inpainting detection spatial attention channel attention full convolutional network high-pass filter