检索结果-南通市图书馆

Towards sustainable adversarial training with successive perturbation generation

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Information Technology & Electronic Engineering 2024年第4期25卷 527-539页

作者： Wei LIN Lichuan LIAO college of Computer Science and Mathematics Fujian University of TechnologyFuzhou 350118China college of Economics and Management Xi’an University of TechnologyXi’an 710048China Fujian Provincial Key Laboratory of big data Mining and Applications Fujian University of TechnologyFuzhou 350118China

Adversarial training with online-generated adversarial examples has achieved promising performance in defending adversarial attacks and improving robustness of convolutional neural network ***,most existing adversarial training methods are dedicated to finding strong adversarial examples for forcing the model to learn the adversarial data distribution,which inevitably imposes a large computational overhead and results in a decrease in the generalization performance on clean *** this paper,we show that progressively enhancing the adversarial strength of adversarial examples across training epochs can effectively improve the model robustness,and appropriate model shifting can preserve the generalization performance of models in conjunction with negligible computational *** this end,we propose a successive perturbation generation scheme for adversarial training(SPGAT),which progressively strengthens the adversarial examples by adding the perturbations on adversarial examples transferred from the previous epoch and shifts models across the epochs to improve the efficiency of adversarial *** proposed SPGAT is both efficient and effective;e.g.,the computation time of our method is 900 min as against the 4100 min duration observed in the case of standard adversarial training,and the performance boost is more than 7%and 3%in terms of adversarial accuracy and clean accuracy,*** extensively evaluate the SPGAT on various datasets,including small-scale MNIST,middle-scale CIFAR-10,and large-scale *** experimental results show that our method is more efficient while performing favorably against state-of-the-art methods.

关键词： Adversarial training Adversarial attack Stochastic weight average Machine learning Model generalization

Classification of Sailboat Tell Tail Based on Deep Learning

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Ocean University of China 2024年第3期23卷 710-720页

作者： CHANG Xiaofeng YU Jintao GAO Ying DING Hongchen LIU Yulong YU Huaming Department of Physical Education Ocean University of ChinaQingdao 266100China college of big data Qingdao University of Science and TechnologyQingdao 266061China college of Oceanic and Atmospheric Sciences Ocean University of ChinaQingdao 266100China

The tell tail is usually placed on the triangular sail to display the running state of the air flow on the sail *** is of great significance to make accurate judgement on the drift of the tell tail of the sailboat during sailing for the best sailing *** it is difficult for sailors to keep an eye for a long time on the tell sail for accurate judging its changes,affected by strong sunlight and visual *** this case,we adopt computer vision technology in hope of helping the sailors judge the changes of the tell tail in ease with *** paper proposes for the first time a method to classify sailboat tell tails based on deep learning and an expert guidance system,supported by a sailboat tell tail classification data set on the expert guidance system of interpreting the tell tails states in different sea wind conditions,including the feature extraction *** the expression capabilities that vary with the computational features in different visual tasks,the paper focuses on five tell tail computing features,which are recoded by an automatic encoder and classified by a SVM *** experimental samples were randomly divided into five groups,and four groups were selected from each group as the training set to train the *** remaining one group was used as the test set for *** highest resolution value of the ResNet network was 80.26%.To achieve better operational results on the basis of deep computing features obtained through the ResNet network in the *** method can be used to assist the sailors in making better judgement about the tell tail changes during sailing.

关键词： tell tail sailboat classification deep learning

Production of higher excited quarkonium pair at the super Z factory

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Chinese Physics C 2024年第7期48卷 45-54页

作者：廖其力蒋军 Chongqing college of Mobile Telecommunications Chongqing 401520China Chongqing Key Laboratory of Public big data Security Technology Chongqing 401520China School of Physics Shandong UniversityJinan 250100China

The heavy constituent quark pair of the heavy quarkonium is produced perturbatively and subsequently undergoes hadronization into the bound state *** production of the heavy quarkonium is essential to testing our understanding of quantum chromodynamics(QCD)in both perturbative and non-perturbative *** electron-positron collider will provide a suitable platform for the precise study of the heavy *** higher excited heavy quarkonium may contribute significantly to the ground states,which should be considered for sound *** study the production rates of the higher excited states quarkonium pair in■at the future Z factory under the non-relativistic QCD(NRQCD)framework,where the■represents the color-singlet states■The differential angle distribution of cross sections■is *** also discuss the uncertainties of cross sections caused by the varying quark masses and the renormalization scaleμ.We show that significant numbers of events for pairs of higher excited state quarkonia can be generated at the super Z factory.

关键词： Z boson decays pair of higher excited quarkonia NRQCD D0I:10.1088/1674-1137/ad3c2e

Image Recognition Model of Fraudulent Websites Based on Image Leader Decision and Inception-V3 Transfer Learning

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

China Communications 2024年第1期21卷 215-227页

作者： Shengli Zhou Cheng Xu Rui Xu Weijie Ding Chao Chen Xiaoyang Xu Information Department of Zhejiang Police college Hangzhou 310053China Hangzhou Dianzi University Hangzhou 310018China big data Laboratory of Zhejiang Police college Hangzhou 310053China Hangzhou Public Security Bureau Hangzhou 310002China

The fraudulent website image is a vital information carrier for telecom *** efficient and precise recognition of fraudulent website images is critical to combating and dealing with fraudulent *** research on image recognition of fraudulent websites is mainly carried out at the level of image feature extraction and similarity study,which have such disadvantages as difficulty in obtaining image data,insufficient image analysis,and single identification *** study develops a model based on the entropy method for image leader decision and Inception-v3 transfer learning to address these *** data processing part of the model uses a breadth search crawler to capture the image ***,the information in the images is evaluated with the entropy method,image weights are assigned,and the image leader is *** model training and prediction,the transfer learning of the Inception-v3 model is introduced into image recognition of fraudulent *** selected image leaders to train the model,multiple types of fraudulent websites are identified with high *** experiment proves that this model has a superior accuracy in recognizing images on fraudulent websites compared to other current models.

关键词： fraudulent website image leaders telecom fraud transfer learning

Leveraging the Empirical Wavelet Transform in Combination with Convolutional LSTM Neural Networks to Enhance the Accuracy of Polar Motion Prediction

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Research in Astronomy and Astrophysics 2024年第9期 216-226页

作者： Xu-Qiao Wang Lan Du Zhong-Kai Zhang Ze-Jun Liu Hao Xiang college of Geospatial Information Information Engineering University Henan Industrial Technology Academy of Spatio-Temporal big data

High-precision polar motion prediction is of great significance for deep space exploration and satellite *** motion is affected by a variety of excitation factors, and nonlinear prediction methods are more suitable for polar motion prediction. In order to explore the effect of deep learning in polar motion prediction. This paper proposes a combined model based on empirical wavelet transform(EWT), Convolutional Neural Networks(CNN)and Long Short Term Memory(LSTM). By training and forecasting EOP 20C04 data, the effectiveness of the algorithm is verified, and the performance of two forecasting strategies in deep learning for polar motion prediction is explored. The results indicate that recursive multi-step prediction performs better than direct multi-step prediction for short-term forecasts within 15 days, while direct multi-step prediction is more suitable for medium and long-term forecasts. In the 365 days forecast, the mean absolute error of EWT-CNN-LSTM in the X direction and Y direction is 18.25 mas and 15.78 mas, respectively, which is 23.5% and 16.2% higher than the accuracy of Bulletin A. The results show that the algorithm has a good effect in medium and long term polar motion prediction.

关键词：

An Innovative K-Anonymity Privacy-Preserving Algorithm to Improve data Availability in the Context of big data

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第4期79卷 1561-1579页

作者： Linlin Yuan Tiantian Zhang Yuling Chen Yuxiang Yang Huang Li State Key Laboratory of Public big data College of Computer Science and TechnologyGuizhou UniversityGuiyang550025China college of Information Engineering Guizhou Open UniversityGuiyang550025China Guizhou Academy of Tobacco Science Guiyang550025China

The development of technologies such as big data and blockchain has brought convenience to life,but at the same time,privacy and security issues are becoming more and more *** K-anonymity algorithm is an effective and low computational complexity privacy-preserving algorithm that can safeguard users’privacy by anonymizing big ***,the algorithm currently suffers from the problem of focusing only on improving user privacy while ignoring data *** addition,ignoring the impact of quasi-identified attributes on sensitive attributes causes the usability of the processed data on statistical analysis to be *** on this,we propose a new K-anonymity algorithm to solve the privacy security problem in the context of big data,while guaranteeing improved data ***,we construct a new information loss function based on the information quantity *** that different quasi-identification attributes have different impacts on sensitive attributes,we set weights for each quasi-identification attribute when designing the information loss *** addition,to reduce information loss,we improve K-anonymity in two ***,we make the loss of information smaller than in the original table while guaranteeing privacy based on common artificial intelligence algorithms,i.e.,greedy algorithm and 2-means clustering *** addition,we improve the 2-means clustering algorithm by designing a mean-center method to select the initial center of ***,we design the K-anonymity algorithm of this scheme based on the constructed information loss function,the improved 2-means clustering algorithm,and the greedy algorithm,which reduces the information ***,we experimentally demonstrate the effectiveness of the algorithm in improving the effect of 2-means clustering and reducing information loss.

关键词： Blockchain big data K-anonymity 2-means clustering greedy algorithm mean-center method

Nonlinear Registration of Brain Magnetic Resonance Images with Cross Constraints of Intensity and Structure

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 2024年第5期79卷 2295-2313页

作者： Han Zhou HongtaoXu Xinyue Chang Wei Zhang Heng Dong Digital Fujian Research Institute of big data forAgriculture and Forestry Fujian Agriculture and Forestry UniversityFuzhou350002China college of Computer and Information Science Fujian Agriculture and Forestry UniversityFuzhou350002China

Many deep learning-based registration methods rely on a single-stream encoder-decoder network for computing deformation fields between 3D ***,these methods often lack constraint information and overlook semantic consistency,limiting their *** address these issues,we present a novel approach for medical image registration called theDual-VoxelMorph,featuring a dual-channel cross-constraint *** innovative network utilizes both intensity and segmentation images,which share identical semantic information and feature *** encoder-decoder structures calculate deformation fields for intensity and segmentation images,as generated by the dual-channel cross-constraint *** design facilitates bidirectional communication between grayscale and segmentation information,enabling the model to better learn the corresponding grayscale and segmentation details of the same anatomical *** ensure semantic and directional consistency,we introduce constraints and apply the cosine similarity function to enhance semantic *** on four public datasets demonstrates superior performance compared to the baselinemethod,achieving Dice scores of 79.9%,64.5%,69.9%,and 63.5%for OASIS-1,OASIS-3,LPBA40,and ADNI,respectively.

关键词： Medical image registration cross constraint semantic consistency directional consistency dual-channel

Economic Development and Social Integration of Migrants in China

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

China & World Economy 2024年第1期32卷 1-20页

作者： Guangjun Shen Chuanchuan Zhang Lingnan college Sun Yat-sen UniversityChina School of Economics and Institute for Fiscal big data and Policy Zhejiang UniversityChina

Migrants often face challenges in social *** a nationally representative sample of migrant workers and employing the epidemiological approach,this paper examines the determinants of social *** finds that,conditional on a set of individual features,the migrants from less-developed provinces have greater difficulty in integrating into local *** results still demonstrate robustness across alternative variables,samples,and various *** analysis shows that educational and employment factors account for over 40 percent of the variance in social integration levels,suggesting their significant ***,the analysis suggests that native bias against migrants,along with misunderstandings between them,may account for part of the remaining variation in social integration ***,the ability to speak local dialects has been identified as a crucial factor that can significantly improve migrants'subjective experience of integrating into a new *** identifying one specific cause of social integration,this paper provides information to individuals and governments and assists them to improve social integration.

关键词： economic development epidemiologic approach migrant social integration

Recommendation System Based on Perceptron and Graph Convolution 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 2024年第6期79卷 3939-3954页

作者： Zuozheng Lian Yongchao Yin Haizhen Wang college of Computer and Control Engineering Qiqihar UniversityQiqihar161006China Heilongjiang Key Laboratory of big data Network Security Detection and Analysis Qiqihar UniversityQiqihar161006China

The relationship between users and items,which cannot be recovered by traditional techniques,can be extracted by the recommendation algorithm based on the graph convolution *** current simple linear combination of these algorithms may not be sufficient to extract the complex structure of user interaction *** paper presents a new approach to address such issues,utilizing the graph convolution network to extract association *** proposed approach mainly includes three modules:Embedding layer,forward propagation layer,and score prediction *** embedding layer models users and items according to their interaction information and generates initial feature vectors as input for the forward propagation *** forward propagation layer designs two parallel graph convolution networks with self-connections,which extract higher-order association relevance from users and items separately by multi-layer graph ***,the forward propagation layer integrates the attention factor to assign different weights among the hop neighbors of the graph convolution network fusion,capturing more comprehensive association relevance between users and items as input for the score prediction *** score prediction layer introduces MLP(multi-layer perceptron)to conduct non-linear feature interaction between users and items,***,the prediction score of users to items is *** recall rate and normalized discounted cumulative gain were used as evaluation *** proposed approach effectively integrates higher-order information in user entries,and experimental analysis demonstrates its superiority over the existing algorithms.

关键词： Recommendation system graph convolution network attention mechanism multi-layer perceptron