检索结果-南通市图书馆

Granger causal representation learning for groups of time series

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

science China(Information sciences) 2024年第5期67卷 56-68页

作者： Ruichu CAI Yunjin WU Xiaokai HUANG Wei CHEN Tom Z.J.FU Zhifeng HAO School of computer science Guangdong University of Technology Peng Cheng Laboratory College of science Shantou University

Discovering causality from multivariate time series is an important but challenging *** existing methods focus on estimating the Granger causal structures among multivariate time series,while ignoring the prior knowledge of these time series, e.g., the group of the time series. Focusing on discovering the Granger causal structures among groups of time series, we propose a Granger causal representation learning method to solve this problem. First, we use the multiset canonical correlation analysis method to learn the Granger causal representation of each group of time series. Then, we model the Granger causal relationships among the learned Granger causal representations using a recurrent neural network with temporal information. Finally, we formulate the above two stages into one unified optimization problem, which is efficiently solved using the augmented Lagrangian method. We conduct extensive experiments on synthetic and real-world datasets to validate the correctness and effectiveness of the proposed method.

关键词： Granger causal discovery Granger causal representation learning time series data recurrent neural network multiset canonical correlation analysis

The Effect of Key Nodes on theMalware Dynamics in the Industrial Control Network

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 329-349页

作者： Qiang Fu JunWang Changfu Si Jiawei Liu College of computer science and technology Shenyang University of Chemical TechnologyShenyang110142China College of computer science and Engineering Northeastern UniversityShenyang110169China

As industrialization and informatization becomemore deeply intertwined,industrial control networks have entered an era of *** connection between industrial control networks and the external internet is becoming increasingly close,which leads to frequent security *** paper proposes a model for the industrial control *** includes a malware containment strategy that integrates intrusion detection,quarantine,and ***,the role of keynodes in the spreadofmalware is studied,a comparisonexperiment is conducted to validate the impact of the containment *** addition,the dynamic behavior of the model is analyzed,the basic reproduction number is computed,and the disease-free and endemic equilibrium of the model is also obtained by the basic reproduction ***,through simulation experiments,the effectiveness of the containment strategy is validated,the influence of the relevant parameters is analyzed,and the containment strategy is *** otherwords,selective immunity to key nodes can effectively suppress the spread ofmalware andmaintain the stability of industrial control *** earlier the immunization of key nodes,the *** the time exceeds the threshold,immunizing key nodes is almost *** analysis provides a better way to contain the malware in the industrial control network.

关键词： Key nodes dynamic model industrial control network simulation

Efficient Untargeted White-Box Adversarial Attacks Based on Simple Initialization

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 2024年第04期33卷 979-988页

作者： Yunyi ZHOU Haichang GAO Jianping HE Shudong ZHANG Zihui WU School of computer science and technology Xidian University

Adversarial examples(AEs) are an additive amalgamation of clean examples and artificially malicious perturbations. Attackers often leverage random noise and multiple random restarts to initialize perturbation starting points, thereby increasing the diversity of AEs. Given the non-convex nature of the loss function, employing randomness to augment the attack's success rate may lead to considerable computational overhead. To overcome this challenge,we introduce the one-hot mean square error loss to guide the initialization. This loss is combined with the strongest first-order attack, the projected gradient descent, alongside a dynamic attack step size adjustment strategy to form a comprehensive attack process. Through experimental validation, we demonstrate that our method outperforms baseline attacks in constrained attack budget scenarios and regular experimental settings. This establishes it as a reliable measure for assessing the robustness of deep learning models. We explore the broader application of this initialization strategy in enhancing the defense impact of few-shot classification models. We aspire to provide valuable insights for the community in designing attack and defense mechanisms.

关键词： Deep learning Additives Perturbation methods Noise Mean square error methods Robustness Glass box

Meta label associated loss for fine-grained visual recognition

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

science China(Information sciences) 2024年第6期67卷 230-247页

作者： Yanchao LI Fu XIAO Hao LI Qun LI Shui YU School of computer science Nanjing University of Posts and Telecommunications School of Network Engineering Zhoukou Normal University School of computer science University of Technology Sydney

Recently, intensive attempts have been made to design robust models for fine-grained visual recognition, most notably are the impressive gains for training with noisy labels by incorporating a reweighting strategy into a meta-learning framework. However, it is limited to up or downweighting the contribution of an instance for label reweighting approaches in the learning process. To solve this issue, a novel noise-tolerant method with auxiliary web data is proposed. Specifically, first, the associations made from embeddings of well-labeled data with those of web data and back at the same class are measured. Next, its association probability is employed as a weighting fusion strategy into angular margin-based loss, which makes the trained model robust to noisy datasets. To reduce the influence of the gap between the well-labeled and noisy web data, a bridge schema is proposed via the corresponding loss that encourages the learned embeddings to be coherent. Lastly, the formulation is encapsulated into the meta-learning framework, which can reduce the overfitting of models and learn the network parameters to be noise-tolerant. Extensive experiments are performed on benchmark datasets, and the results clearly show the superiority of the proposed method over existing state-of-the-art approaches.

关键词： label associated loss weighting noisy samples fine-grained visual recognition noise-tolerant learning meta-learning

Starlet:Network defense resource allocation with multi-armed bandits for cloud-edge crowd sensing in IoT

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

Digital Communications and Networks 2024年第3期10卷 586-596页

作者： Hui Xia Ning Huang Xuecai Feng Rui Zhang Chao Liu College of computer science and technology Ocean University of ChinaQingdao266100China

The cloud platform has limited defense resources to fully protect the edge servers used to process crowd sensing data in Internet of *** guarantee the network's overall security,we present a network defense resource allocation with multi-armed bandits to maximize the network's overall ***,we propose the method for dynamic setting of node defense resource thresholds to obtain the defender(attacker)benefit function of edge servers(nodes)and ***,we design a defense resource sharing mechanism for neighboring nodes to obtain the defense capability of ***,we use the decomposability and Lipschitz conti-nuity of the defender's total expected utility to reduce the difference between the utility's discrete and continuous arms and analyze the difference ***,experimental results show that the method maximizes the defender's total expected utility and reduces the difference between the discrete and continuous arms of the utility.

关键词： Internet of things Defense resource sharing Multi-armed bandits Defense resource allocation

DIR:Dynamic Request Interleaving for Improving the Read Performance of Aged Solid-State Drives

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 computer science & technology 2024年第1期39卷 82-98页

作者：聂世强张驰伍卫国 Department of computer science and technology Xi'an Jiaotong UniversityShaanci 710049China

Triple-level cell(TLC)NAND flash is increasingly adopted to build solid-state drives(SSDs)for modern computer *** TLC NAND flash effectively improves storage density,it faces severe reliability issues;in partic-ular,the pages exhibit different raw bit error rates(RBERs).Integrating strong low-density parity-check(LDPC)code helps to improve reliability but suffers from prolonged and proportional read latency due to multiple read retries for worse *** straightforward idea is that dispersing page-size data across several pages in different types can achieve a low-er average RBER and reduce the read ***,directly implementing this simple idea into flash translation lay-er(FTL)induces the read amplification issue as one logic page residing in more than one physical page brings several read *** this paper,we propose the Dynamic Request Interleaving(DIR)technology for improving the performance of TLC NAND flash-based SSDs,in particular,the aged ones with large *** exploits the observation that the la-tency of an I/O request is determined,without considering the queuing time,by the access of the slowest device page,i.e.,the page that has the highest *** grouping consecutive logical pages that have high locality and interleaving their encoded data in different types of device pages that have different RBERs,DIR effectively reduces the number of read re-tries for LDPC with limited read *** meet the requirement of allocating hybrid page types for interleaved data,we also design a page-interleaving friendly page allocation scheme,which splits all the planes into multi-plane re-gions for storing the interleaved data and single-plane regions for storing the normal *** pages in the multi-plane re-gion can be read/written in parallel by the proposed multi-plane command and avoid the read amplification *** on the DIR scheme and the proposed page allocation scheme,we build DIR-enable FTL,which integrates the pro

关键词： triple-layer cell solid-state drive(TLC SSD) performance interleaving data unbalanced bit error rate

Predicting Age and Gender in Author Profiling: A Multi-Feature Exploration

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 3333-3353页

作者： Aiman Muhammad Arshad Bilal Khan Sadique Ahmad Muhammad Asim Department of computer science City University of Science and Information TechnologyPeshawar25000Pakistan EIAS:Data science and Blockchain Laboratory College of Computer and Information SciencesPrince Sultan UniversityRiyadh11586Saudi Arabia School of computer science and technology Guangdong University of TechnologyGuangzhou510006China

Author Profiling (AP) is a subsection of digital forensics that focuses on the detection of the author’s personalinformation, such as age, gender, occupation, and education, based on various linguistic features, e.g., stylistic,semantic, and syntactic. The importance of AP lies in various fields, including forensics, security, medicine, andmarketing. In previous studies, many works have been done using different languages, e.g., English, Arabic, French,***, the research on RomanUrdu is not up to the ***, this study focuses on detecting the author’sage and gender based on Roman Urdu text messages. The dataset used in this study is Fire’18-MaponSMS. Thisstudy proposed an ensemble model based on AdaBoostM1 and Random Forest (AMBRF) for AP using multiplelinguistic features that are stylistic, character-based, word-based, and sentence-based. The proposed model iscontrasted with several of the well-known models fromthe literature, including J48-Decision Tree (J48),Na飗e Bays(NB), K Nearest Neighbor (KNN), and Composite Hypercube on Random Projection (CHIRP), NB-Updatable,RF, and AdaboostM1. The overall outcome shows the better performance of the proposed AdaboostM1 withRandom Forest (ABMRF) with an accuracy of 54.2857% for age prediction and 71.1429% for gender predictioncalculated on stylistic features. Regarding word-based features, age and gender were considered in 50.5714% and60%, respectively. On the other hand, KNN and CHIRP show the weakest performance using all the linguisticfeatures for age and gender prediction.

关键词： Digital forensics author profiling for security AdaBoostM1 random forest ensemble learning

Modified DS np Chart Using Generalized Multiple Dependent State Sampling under Time Truncated Life Test

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 2024年第3期138卷 2471-2495页

作者： Wimonmas Bamrungsetthapong Pramote Charongrattanasakul Division of Applied Statistics Department of Mathematics and Computer ScienceFaculty of Science and TechnologyRajamangala University of Technology ThanyaburiPathum Thani12110Thailand Division of Mathematics Department of Mathematics and Computer ScienceFaculty of Science and TechnologyRajamangala University of Technology KrungthepBangkok10120Thailand

This study presents the design of a modified attributed control chart based on a double sampling(DS)np chart applied in combination with generalized multiple dependent state(GMDS)sampling to monitor the mean life of the product based on the time truncated life test employing theWeibull *** control chart developed supports the examination of the mean lifespan variation for a particular product in the process of *** control limit levels are used:the warning control limit,inner control limit,and outer control ***,they enhance the capability for variation detection.A genetic algorithm can be used for optimization during the in-control process,whereby the optimal parameters can be established for the proposed control *** control chart performance is assessed using the average run length,while the influence of the model parameters upon the control chart solution is assessed via sensitivity analysis based on an orthogonal experimental design withmultiple linear regression.A comparative study was conducted based on the out-of-control average run length,in which the developed control chart offered greater sensitivity in the detection of process shifts while making use of smaller samples on average than is the case for existing control ***,to exhibit the utility of the developed control chart,this paper presents its application using simulated data with parameters drawn from the real set of data.

关键词： Modified DS np chart generalizedmultiple dependent state sampling time truncated life test Weibull distribution average run length average sample size

A Dual Discriminator Method for Generalized Zero-Shot 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

computers, Materials & Continua 2024年第4期79卷 1599-1612页

作者： Tianshu Wei Jinjie Huang School of computer science and technology Harbin University of Science and TechnologyHarbin150006China School of Automation Harbin University of Science and TechnologyHarbin150006China

Zero-shot learning enables the recognition of new class samples by migrating models learned from semanticfeatures and existing sample features to things that have never been seen before. The problems of consistencyof different types of features and domain shift problems are two of the critical issues in zero-shot learning. Toaddress both of these issues, this paper proposes a new modeling structure. The traditional approach mappedsemantic features and visual features into the same feature space;based on this, a dual discriminator approachis used in the proposed model. This dual discriminator approach can further enhance the consistency betweensemantic and visual features. At the same time, this approach can also align unseen class semantic features andtraining set samples, providing a portion of information about the unseen classes. In addition, a new feature fusionmethod is proposed in the model. This method is equivalent to adding perturbation to the seen class features,which can reduce the degree to which the classification results in the model are biased towards the seen *** the same time, this feature fusion method can provide part of the information of the unseen classes, improvingits classification accuracy in generalized zero-shot learning and reducing domain bias. The proposed method isvalidated and compared with othermethods on four datasets, and fromthe experimental results, it can be seen thatthe method proposed in this paper achieves promising results.

关键词： Generalized zero-shot learning modality consistent discriminator domain shift problem feature fusion