检索结果-南通市图书馆

Neighbor Library-Aware Graph Neural Network for Third Party Library Recommendation

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

清华大学学报:自然科学版(英文版) 2023年第4期28卷 769-785页

作者： Ying Jin Yi Zhang Yiwen Zhang school of artificial intelligence and Big data Hefei UniversityHefei 230601China school of Computer science and Technology Anhui UniversityHefei 230601China

Modern software development has moved toward agile growth and rapid delivery,where developers must meet the changing needs of users instantaneously.In such a situation,plug-and-play Third-Party Libraries(TPLs)introduce a considerable amount of convenience to developers.However,selecting the exact candidate that meets the project requirements from the countless TPLs is challenging for developers.Previous works have considered setting up a personalized recommender system to suggest TPLs for developers.Unfortunately,these approaches rarely consider the complex relationships between applications and TPLs,and are unsatisfactory in accuracy,training speed,and convergence speed.In this paper,we propose a new end-to-end recommendation model called Neighbor Library-Aware Graph Neural Network(NLA-GNN).Unlike previous works,we only initialize one type of node embedding,and construct and update all types of node representations using Graph Neural Networks(GNN).We use a simplified graph convolution operation to alternate the information propagation process to increase the training efficiency and eliminate the heterogeneity of the app-library bipartite graph,thus efficiently modeling the complex high-order relationships between the app and the library.Extensive experiments on large-scale real-world datasets demonstrate that NLA-GNN achieves consistent and remarkable improvements over state-of-the-art baselines for TPL recommendation tasks.

关键词： Third-Party Library(TPL) TPL recommendation Graph Neural Network(GNN) bipartite graph

Towards privacy-preserving dynamic deep packet inspection over outsourced

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

High-Confidence Computing

High-Confidence Computing 2022年第1期2卷 1-8页

作者： Chunxiao Li Yu Guo Xia Wang school of artificial intelligence Beijing Normal UniversityBeijingChina school of Statistics and data science Beijing University of TechnologyBeijingChina

The prosperity of network function virtualization(NFV)pushes forward the paradigm of migrating in-house middleboxes to third-party providers,i.e.,software(virtualized)middlebox services.A lot of enterprises have outsourced traffic processing such as deep packet inspection(DPI),traffic classification,and load balancing to middleboxes provided by cloud providers.However,if the traffic is forwarded to the cloud provider without careful processing,it will cause privacy leakage,as the cloud provider has all the rights to access the data.To solve the security issue,recent efforts are made to design secure middleboxes that can directly conduct network functions over encrypted traffic and middlebox rules.However,security concerns from dynamic operations like dynamic DPI and rule updates are still not yet fully addressed.In this paper,we propose a privacy-preserving dynamic DPI scheme with forward privacy for outsourced middleboxes.Our design can enable cloud side middlebox to conduct secure packet inspection over encrypted traffic data.Besides,the middlebox providers cannot analyze the relationship between the newly added rules and the previous data.Several recent papers have proven that it is a strong property that resist adaptive attacks.Furthermore,we design a general method to inspect stateful packets while still ensuring the state privacy protection.We formally define and prove the security of our design.Finally,we implement a system prototype and analyze the performance from experimental aspects.The evaluation results demonstrate our scheme is effective and efficient.

关键词： DPI outsourcing Network function virtualization Dynamic searchable symmetric encryption

Perturbations of Dirac operators,spectral Einstein functionals and the Noncommutative residue

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Acta Mathematica Sinica,English Series 2024年

作者： Sining WEI Yong Wang school of data science and artificial intelligence Dongbei University of Finance and Economics school of Mathematics and Statistics Northeast Normal University

In this paper, we introduce the spectral Einstein functional for perturbations of Dirac operators on manifolds with boundary. Furthermore, we provide the proof of the Dabrowski-SitarzZalecki type theorems associated with the spectral Einstein functionals for perturbations of Dirac operators, particularly in the cases of on 4-dimensional manifolds with boundary.

关键词：

Some convergence properties for weighted sums of martingale difference random vectors

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Acta Mathematica Sinica,English Series 2022年

作者： Yi WU Xue Jun WANG school of Big data and artificial intelligence Chizhou University school of Big data and Statistics Anhui University

Let{X, F;1≤i≤n, n≥1}be an array of Rmartingale difference random vectors and{A, 1≤i≤n, n≥1}be an array of m×d matrices of real numbers. In this paper, the Marcinkiewicz-Zygmund type weak law of large numbers for maximal weighted sums of martingale difference random vectors is obtained with not necessarily finite p-th （1

关键词：

Confidence-weighted mutual supervision on dual networks for unsupervised cross-modality image segmentation

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

science China(Information sciences) 2023年第11期66卷 54-68页

作者： Yajie CHEN Xin YANG Xiang BAI school of Electronic Information and Communications Huazhong University of Science and Technology school of artificial intelligence and Automation Huazhong University of Science and Technology

The unsupervised cross-modality image segmentation has gained much attention. Many methods attempt to align different modalities via adversarial learning. Recently, self-training with pseudo labels for the unsupervised target modality has also been widely used and achieved very promising results. The pseudo labels are usually obtained by selecting reliable predictions whose highest predicted probability is larger than an empirically set value. Such pseudo label generation inevitably has noise and training a segmentation model using incorrect pseudo labels could yield nontrivial errors for the target modality. In this paper, we propose a confidence-weighted mutual supervision on dual networks for unsupervised cross-modality image segmentation. Specifically, we independently initialize two networks with the same architecture, and propose a novel confidence-weighted Dice loss to mutually supervise the two networks using their predicted results for unlabeled data. In this way, we make full use of all predictions of unlabeled images and leverage the prediction confidence to alleviate the negative impact of noisy pseudo labels. Extensive experiments on three widely-used unsupervised cross-modality image segmentation datasets(i.e., MM-WHS 2017, Brats 2018, and Multi-organ segmentation) demonstrate that the proposed method achieves superior performance to some state-of-the-art methods.

关键词： domain adaptation pseudo label mutual supervision cross-modality image segmentation

Perpendicular-Cutdepth:Perpendicular Direction Depth Cutting data Augmentation Method

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 927-941页

作者： Le Zou Linsong Hu Yifan Wang Zhize Wu Xiaofeng Wang Anhui Provincial Engineering Laboratory of Big data Technology Application forUrban Infrastructure School ofArtificial Intelligence and Big DataHefei UniversityHefei230601China Institute of Applied Optimization School of Artificial Intelligence and Big DataHefei UniversityHefei230601China

Depth estimation is an important task in computer vision.Collecting data at scale for monocular depth estimation is challenging,as this task requires simultaneously capturing RGB images and depth information.Therefore,data augmentation is crucial for this task.Existing data augmentationmethods often employ pixel-wise transformations,whichmay inadvertently disrupt edge features.In this paper,we propose a data augmentationmethod formonocular depth estimation,which we refer to as the Perpendicular-Cutdepth method.This method involves cutting realworld depth maps along perpendicular directions and pasting them onto input images,thereby diversifying the data without compromising edge features.To validate the effectiveness of the algorithm,we compared it with existing convolutional neural network(CNN)against the current mainstream data augmentation algorithms.Additionally,to verify the algorithm’s applicability to Transformer networks,we designed an encoder-decoder network structure based on Transformer to assess the generalization of our proposed algorithm.Experimental results demonstrate that,in the field of monocular depth estimation,our proposed method,Perpendicular-Cutdepth,outperforms traditional data augmentationmethods.On the indoor dataset NYU,our method increases accuracy from0.900 to 0.907 and reduces the error rate from0.357 to 0.351.On the outdoor dataset KITTI,our method improves accuracy from 0.9638 to 0.9642 and decreases the error rate from 0.060 to 0.0598.

关键词： Perpendicular depth estimation data augmentation

An Interactive Perception Method Based Collaborative Rating Prediction 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

Chinese Journal of Electronics 2023年第1期32卷 97-110页

作者： YAN Wenjie ZHANG Jiahao LI Ziqi school of artificial intelligence Hebei University of Technology

To solve the rating prediction problems of low accuracy and data sparsity on different datasets,we propose an interactive perception method based collaborative rating prediction algorithm named DCAE-MF,by fusing dual convolutional autoencoder(DCAE) and probability matrix factorization(PMF). Deep latent representations of users and items are captured simultaneously by DCAE and are deeply integrated with PMF to collaboratively make rating predictions based on the known rating history of users. A global multi-angle collaborative optimization learning method is developed to effectively optimize all the parameters of DCAE-MF. Extensive experiments are performed on seven real-world datasets to demonstrate the superiority of DCAE-MF on key rating accuracy metrics of the root mean squared error(RMSE) and mean absolute error(MAE).

关键词： Recommender systems Probabilistic matrix factorization Convolutional autoencoder Interactive perception Multi-angle optimization

A Novel Predictive Model for Edge Computing Resource Scheduling Based on Deep Neural Network

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Computer Modeling in Engineering & sciences 2024年第4期139卷 259-277页

作者： Ming Gao Weiwei Cai Yizhang Jiang Wenjun Hu Jian Yao Pengjiang Qian school of artificial intelligence and Computer science Jiangnan UniversityWuxi214122China The Center for Intelligent Systems and Applications Research School of Artificial Intelligence and Computer ScienceJiangnan UniversityWuxi214122China school of Information Engineering Huzhou UniversityHuzhou313000China

Currently,applications accessing remote computing resources through cloud data centers is the main mode of operation,but this mode of operation greatly increases communication latency and reduces overall quality of service(QoS)and quality of experience(QoE).Edge computing technology extends cloud service functionality to the edge of the mobile network,closer to the task execution end,and can effectivelymitigate the communication latency problem.However,the massive and heterogeneous nature of servers in edge computing systems brings new challenges to task scheduling and resource management,and the booming development of artificial neural networks provides us withmore powerfulmethods to alleviate this limitation.Therefore,in this paper,we proposed a time series forecasting model incorporating Conv1D,LSTM and GRU for edge computing device resource scheduling,trained and tested the forecasting model using a small self-built dataset,and achieved competitive experimental results.

关键词： Edge computing resource scheduling predictive models

The consistency of LSE estimators in partial linear regression models under mixing random errors

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Acta Mathematica Sinica,English Series 2022年

作者： Yun Bao YAO Yu Tan LYU Chao LU Wei WANG Xue Jun WANG school of Mathematical sciences Anhui University school of Big data and Statistics Anhui University school of Big data and artificial intelligence Chizhou University

In this paper,we consider the partial linear regression model y=xβ~*+g(t)+ε,i=1,2,...,n,where (x,t) are known fixed design points,g(·) is an unknown function,and β~*is an unknown parameter to be estimated,random errors εare (α,β)-mixing random variables.The p-th(p>1) mean consistency,strong consistency and complete consistency for least squares estimators ofβ~* and g(·) are investigated under some mild conditions.In addition,a numerical simulation is carried out to study the finite sample performance of the theoretical results.Finally,a real data analysis is provided to further verify the effect of the model.

关键词：