检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2025年第1期6卷 144-158页

作者： Zhang, Dengyong He, Ruiyi Liao, Xin Li, Feng Chen, Jiaxin Yang, Gaobo Changsha University of Science and Technology Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation the School of Computer and Communication Engineering Changsha410114 China Hunan University Changsha410082 China

Deepfake detection has gained increasing research attention in media forensics, and a variety of works have been produced. However, subtle artifacts might be eliminated by compression, and the convolutional neural networks (CNNs)-based detectors are invalidated for fake face images with compression. In this work, we propose a two-stream network for deepfake detection. We observed that high-frequency noise features and spatial features are inherently complementary to each other. Thus, both spatial features and high-frequency noise features are exploited for face forgery detection. Specifically, we design a double-frequency transformer module (DFTM) to guide the learning of spatial features from local artifact regions. To effectively fuse spatial features and high-frequency noise features, a dual-domain attention fusion module (DDAFM) is designed. We also introduce a local relationship constraint loss, which requires only image-level labels, for model training. We evaluate the proposed approach on five large-scale benchmark datasets, and extensive experimental results demonstrate the proposed approach outperforms most SOTA works. © 2024 IEEE.

关键词： Frequency domain analysis

来源：评论

学校读者我要写书评

暂无评论

Graph convolutional networks-based method for uncertainty quantification of building design loads

引用

Building Simulation 2025年第2期18卷 321-337页

作者： Jie Lu Zeyu Zheng Chaobo Zhang Yang Zhao Chenxin Feng Ruchi Choudhary Institute of Refrigeration and Cryogenics Zhejiang UniversityHangzhouChina Energy Efficient Cities Initiative Department of EngineeringUniversity of CambridgeCambridgeUK Department of Energy Engineering Zhejiang UniversityHangzhouChina Department of the Built Environment Eindhoven University of TechnologyEindhoventhe Netherlands Key Laboratory of Clean Energy and Carbon Neutrality of Zhejiang Province Jiaxing Research InstituteZhejiang UniversityJiaxingChina Data-centric Engineering The Alan Turing InstituteLondonUK

Uncertainty quantification of building design loads is essential to efficient and reliable building energy planning in the design *** data-driven methods struggle to generalize across buildings with diverse shapes due to limitations in representing complex geometric *** tackle this issue,a graph convolutional networks(GCN)-based uncertainty quantification method is *** graph-based approach is introduced to represent building shapes by dividing them into blocks and defining their spatial relationships through nodes and *** method effectively captures complex building characteristics,enhancing the generalization *** approach leveraging GCN could estimate design loads by understanding the impact of diverse uncertain ***,a class activation map is formulated to identify key uncertain factors,guiding the selection of important design parameters during the building design *** effectiveness of this method is evaluated through comparison with four widely-used data-driven *** indicate that the mean absolute percentage errors(MAPE)for statistical indicators of uncertainty quantification are under 6.0%and 4.0%for cooling loads and heating loads,*** proposed method is demonstrated to quantify uncertainty in building design loads with outstanding generalization *** regard to time costs,the computation time of the proposed method is reduced from 331 hours to 30 seconds for a twenty-floor building compared to a conventional physics-based method.

关键词： building design loads uncertainty quantification data-driven model graph convolutional networks Monte Carlo simulation

来源：评论

学校读者我要写书评

暂无评论

HTOTP: Honey Time-Based One-Time Passwords

引用

IEEE Transactions on Information Forensics and Security 2025年 20卷 4438-4453页

作者： Ding, Zixuan Wang, Ding Nankai University College of Cryptology and Cyber Science Key Laboratory of Data and Intelligent System Security Ministry of Education Tianjin300350 China Chinese Academy of Sciences Key Laboratory of Cyberspace Security Defense Institute of Information Engineering Beijing100085 China

One-Time Passwords (OTPs) play a crucial role in Two-Factor Authentication (2FA) and Multi-Factor Authentication (MFA) by adding an additional layer of security. OTPs effectively reduce the risk of static passwords being intercepted and reused. Nevertheless, both academic schemes and industrial solutions face security threats stemming from server/device compromises and OTP factor forgery. Chain-based asymmetric OTP schemes are a promising approach to addressing the problem of server compromise but still face threats from device compromise and pre-generated chain leakage. We emphasize that since devices directly store the OTP seed, OTP authentication is essentially equivalent to verifying device possession. This means that in existing OTP schemes, OTP forgery and device compromise remain prevalent and difficult to overcome. In this work, we propose a brand new scheme to address OTP factor forgery and server/device compromises. For the first time, our scheme constructs a tightly coupled architecture between the password factor and the OTP factor. The OTP seed is derived from a password and a device-stored salt, preventing OTP seed extraction and OTP forgery even in the event of a device compromise. Through the integration of "honeywords" with the tightly coupled OTP architecture, the server stores decoy OTP seeds generated by decoy passwords, providing resistance against server compromises and partial password guessing from devices. We conduct a comprehensive evaluation of our OTP schemes. The computational overhead is correlated with the number of honeywords, and with the recommended set size of 20, the total verification overhead is approximately 0.24~ms . Additionally, we propose formal security properties and application metrics, and rigorously prove our scheme’s resistance against server/device compromise attacks and guessing attacks. Our scheme is the first to achieve comprehensive OTP security with low overhead. © 2005-2012 IEEE.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

A Method for Fast Feature Selection Utilizing Cross-Similarity within the Context of Fuzzy Relations

引用

Computers, Materials & Continua 2025年第4期83卷 1195-1218页

作者： Wenchang Yu Xiaoqin Ma Zheqing Zhang Qinli Zhang School of Big Data and Artificial Intelligence Chizhou UniversityChizhou247000China Anhui Education Big Data Intelligent Perception and Application Engineering Research Center Anhui Provincial Joint Construction Key Laboratory of Intelligent Education Equipment and TechnologyChizhou247000China

Feature selection methods rooted in rough sets confront two notable limitations:their high computa-tional complexity and sensitivity to noise,rendering them impractical for managing large-scale and noisy *** primary issue stems from these methods’undue reliance on all *** overcome these challenges,we introduce the concept of cross-similarity grounded in a robust fuzzy relation and design a rapid and robust feature selection ***,we construct a robust fuzzy relation by introducing a truncation ***,based on this fuzzy relation,we propose the concept of cross-similarity,which emphasizes the sample-to-sample similarity relations that uniquely determine feature importance,rather than considering all such relations *** studying the manifestations and properties of cross-similarity across different fuzzy granularities,we propose a forward greedy feature selection algorithm that leverages cross-similarity as the foundation for information *** algorithm significantly reduces the time complexity from O(m2n2)to O(mn2).Experimental findings reveal that the average runtime of five state-of-the-art comparison algorithms is roughly 3.7 times longer than our algorithm,while our algorithm achieves an average accuracy that surpasses those of the five comparison algorithms by approximately 3.52%.This underscores the effectiveness of our *** paper paves the way for applying feature selection algorithms grounded in fuzzy rough sets to large-scale gene datasets.

关键词： Fuzzy rough sets feature selection cross-similarity fuzzy relations

来源：评论

学校读者我要写书评

暂无评论

Dramatic improvement of formability in Mg-3Al-1Sn-0.5Ca-0.1Sm alloy via Mn microalloying combined with high temperature rolling

引用

Journal of Magnesium and Alloys 2025年第4期13卷 1630-1645页

作者： Wang, Shi-Chao Chen, Si-Yu Jin, Zhong-Zheng Ma, Xiao Jia, Hai-Long Zhu, Jia-Ning Li, Chun-Yuan Zha, Min Wang, Hui-Yuan State Key Laboratory of Superhard Materials Jilin University Changchun130012 China Key Laboratory of UV-Emitting Materials and Technology of Ministry of Education Northeast Normal University Changchun130024 China Department of Materials Science and Engineering Delft University of Technology Netherlands Key Laboratory of Automobile Materials of Ministry of Education & School of Materials Science and Engineering Nanling Campus Jilin University No. 5988 Renmin Street Changchun130025 China International Center of Future Science Jilin University Changchun130012 China

Rolled Mg-Al-Sn series alloys generally possess limited formability due to the formation of strong basal texture. Texture weakening is an effective way to enhance formability, but usually accompanied with decreasing strength. In this work, synergistic enhancement of strength and formability is achieved in a Mg-3Al-1Sn-0.5Ca-0.1Sm (ATXS3110) alloy by 0.2 wt.% Mn addition combined with high temperature rolling, exhibiting a high index Erichsen (I.E.) value of ∼8.1 mm and near-isotropic mechanical properties. On one hand, after Mn addition, the grain refinement from ∼7.6 µm to ∼4.1 µm results in suppression of extension twinning, thereby preventing the development of strong basal texture upon stretch forming. On the other hand, trace Mn addition narrows the grain size distribution and promotes the formation of uniform fine grains, which induces homogeneous deformation during stretch forming. Moreover, grain refinement and high-density nano-sized precipitates caused by trace Mn addition increase the strength. This work may provide insights into designing low-cost Mg-Al-Sn series alloys with superior comprehensive mechanical properties for further structural applications. © 2024

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

TCMS: A Multi-Sequence Log Parsing Method Based on Token Conversion

引用

IEEE Transactions on Dependable and Secure Computing 2025年第3期22卷 3028-3045页

作者： Wei, Mingkuan Wen, Jigang He, Shiming Xie, Kun Liang, Wei Xie, Gaogang Li, Kenli Zhu, Ziyu Hunan University Ministry of Education Key Laboratory of "Fusion Computing of Supercomputing and Artificial Intelligence" College of Computer Science and Electronics Engineering Changsha410012 China Hunan University of Science and Technology School of Computer Science and Engineering Xiangtan411201 China Changsha University of Science and Technology School of Computer and Communication Engineering Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation Changsha410114 China Beijing100045 China Columbia University Electrical Engineering New YorkNY10027 United States

Detailed system operations are recorded in logs. To ensure system reliability, developers can detect system anomalies through log anomaly detection. Log parsing, which converts semi-structured log messages into structured data, is a crucial step in log anomaly detection and advanced program analysis and verification. Despite the availability of various log parsing tools, they generally suffer from low parsing accuracy and slow efficiency due to the ignorance of variable characteristics and the use of costly pairwise comparison methods. In this paper, we propose a TCMS framework to parse logs, consisting of two main technologies. First, by studying 16 public log datasets, we find that most log variable tokens are structured variable tokens. Based on this discovery, we propose a token conversion algorithm to improve parsing accuracy. This algorithm converts the changed parts in structured variable tokens into wildcards (‘’), preventing these tokens from being directly identified as constant tokens. Second, to improve efficiency, we propose the LogMLCS algorithm, which intelligently constructs a graph to facilitate the extraction of common parts from multiple log messages at once, instead of using pairwise comparisons. Comprehensive experiments conducted on 16 log datasets reveal that our TCMS outperforms seven other parsing methods, achieving the highest parsing accuracy at the fastest speed. Furthermore, experimental results from running a log anomaly detection algorithm in conjunction with different log parsing methods demonstrate that TCMS significantly boosts detection accuracy. For instance, on the OpenStack dataset, our TCMS-facilitated log anomaly detection algorithm achieves a perfect F1-score, precision, and recall of 100% each, surpassing the best peer method by 32.2, 0.8, and 19.5 percentage points, respectively. © 2004-2012 IEEE.

关键词： Accuracy Anomaly Detection Clustering Algorithms Peer To Peer Computing Electronic Mail Source Coding Particle Separators Codes Tokenization Itemsets Log Parsing Log Analysis Token Conversion Log MLCS Log Parsing Pairwise Comparisons Low Accuracy Public datasets Anomaly Detection Common Part Multiple Messages Long Short Term Memory Point Source Target Domain Logarithm Of The Number Captive Animals Multi Objective Optimization Problem Regular Expressions Biological Sequences Rule Based Methods Point In The Graph Kinds Of datasets Template Generation Number Of Templates Similar Template Parse Tree Syntax Errors Harmonic Average Of Precision Log Length Earliest Methods Common Subsequence Precision And Recall Leaf Node Part Of The Message

来源：评论

学校读者我要写书评

暂无评论

AMSCF-Net: An adaptive multi-scale cost fusion stereo network for high-quality disparity estimation

引用

ISPRS Journal of Photogrammetry and Remote Sensing 2025年 226卷 76-101页

作者： Tian, Mao Fan, Jiajin Zhang, Qinghua Chen, Chi Yang, Bisheng College of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing400065 China State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing Wuhan University Wuhan430079 China Key Laboratory of Tourism Multisource Data Perception and Decision Ministry of Culture and Tourism China

Accurate and complete reconstruction of the high-quality three-dimensional (3D) geometric information from stereo images has been one of the challenging tasks in the fields of photogrammetry and computer vision. Although tremendous efforts have been made in stereo matching by utilizing convolutional neural network (CNN)-based deep learning architectures, the matching ambiguities in the case of occlusions, disparity discontinuities, and poor and repetitive texture areas remain to be explored. In this paper, to address these issues, we propose a novel end-to-end disparity estimation network named AMSCF-Net, which consists of two main components: the context and geometry adaptive attention weight generation (CGA-AWG) subnetwork for yielding robust multi-scale attention weights, and the adaptive multi-scale cost volume fusion (AMS-CVF) subnetwork to enhance the feature representation of the cost volumes for accurate disparity map prediction. Firstly, the multi-scale feature maps are obtained from the stereo images by employing a weight-sharing hierarchical feature extraction subnetwork. Secondly, the CGA-AWG subnetwork is adopted to produce accurate and robust multi-scale attention weights. Thirdly, the adaptive multi-scale cost volume fusion (AMS-CVF) subnetwork is introduced to boost the robustness of the fused cost volume in the poor and repetitive texture areas, while simultaneously preserving the details of the scene's geometric structure in the rich texture regions. Finally, the context and geometry adaptive disparity map prediction (CGA-DMP) subnetwork is applied to further refine the cost volumes for high-accuracy disparity map reconstruction. Three publicly available benchmark datasets, i.e., the KITTI 2015, US3D, and Vaihingen stereo datasets, were used to evaluate the performance of AMSCF-Net. The comprehensive experiments demonstrate that AMSCF-Net achieves state-of-the-art disparity prediction results on all datasets in terms of the ("D1-bg", "D1-fg", "D1-a

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Byzantine-robust distributed support vector machine

引用

Science china Mathematics 2025年第3期68卷 707-728页

作者： Xiaozhou Wang Weidong Liu Xiaojun Mao School of Statistics East China Normal UniversityShanghai 200062China Key Laboratory of Advanced Theory and Application in Statistics and Data Science(Ministry of Education) East China Normal UniversityShanghai 200062China School of Mathematical Sciences Shanghai Jiao Tong UniversityShanghai 200240China Key Laboratory of Artificial Intelligence(Ministry of Education) Shanghai Jiao Tong UniversityShanghai 200240China Key Laboratory of Scientific and Engineering Computing(Ministry of Education) Shanghai Jiao Tong UniversityShanghai 200240China

The development of information technology brings diversification of data sources and large-scale data sets and calls for the exploration of distributed learning algorithms. In distributed systems, some local machines may behave abnormally and send arbitrary information to the central machine(known as Byzantine failures), which can invalidate the distributed algorithms based on the assumption of faultless systems. This paper studies Byzantine-robust distributed algorithms for support vector machines(SVMs) in the context of binary classification. Despite a vast literature on Byzantine problems, much less is known about the theoretical properties of Byzantine-robust SVMs due to their unique challenges. In this paper, we propose two distributed gradient descent algorithms for SVMs. The median and trimmed mean operations in aggregation can effectively defend against Byzantine failures. Theoretically, we show the convergence of the proposed estimators and provide the statistical error rates. After a certain number of iterations, our estimators achieve near-optimal rates. Simulation studies and real data analysis are conducted to demonstrate the performance of the proposed Byzantine-robust distributed algorithms.

关键词： Byzantine robustness convergence distributed learning support vector machine

来源：评论

学校读者我要写书评

暂无评论

Rapid preparation of graphene-skinned glass fiber fabric based on propane as carbon source

引用

Nano Research 2025年第3期18卷 1-8页

作者： Longfei Liu Jianjian Shi Wenjuan Li Kangyi Zheng Hao Yuan Fushun Liang Ruojuan Liu Yuyao Yang Fan Yang Shuting Cheng Wenjing Jiang Qingxu Su Jingnan Wang Yuejie Zhao Mengxiong Liu Ce Tu Mengwei Li Xiaobai Wang Xiaoli Sun Yue Qi Zhongfan Liu Academy for Advanced Interdisciplinary Research North University of ChinaTaiyuan 030051China Beijing Graphene Institute(BGI) Beijing 100095China School of Electronic Engineering Chengdu Technological UniversityChengdu 611730China Centre for Nanochemistry Beijing Science and Engineering Centre for NanocarbonsBeijing National Laboratory for Molecular SciencesCollege of Chemistry and Molecular EngineeringPeking UniversityBeijing 100871China College of Energy Soochow Institute for Energy and Materials Innovations(SIEMIS)Jiangsu Provincial Key Laboratory for Advanced Carbon Materials and Wearable Energy TechnologiesSoochow UniversitySuzhou 215006China School of Population and Health Renmin University of ChinaBeijing 100872China Department of Chemistry School of Light Industry Science and EngineeringBeijing Technology and Business UniversityBeijing 100048China

Direct chemical vapor deposition(CVD)growth of graphene on dielectric/insulating materials promises transfer-free applications of ***,growing graphene on non-catalytic substrates faces significant challenges,particularly due to its limited growth rate,restricting large-scale production and potential ***,we develop graphene-skinned glass fiber fabric(GGFF)by growing graphene CVD on commercial glass fiber fabric(GFF).This study utilizes propane as a carbon source to prepare GGFF *** active carbon source(C2H)derived from propane plays a significant role in facilitating the rapid growth of graphene *** accelerated growth rates(~50 times faster),and reduced growth temperature(~100℃ lower)compared to the conventional carbon source ***,propane consistently maintains a higher graphene growth rate than methane at equivalent growth *** lightweight flexibility,excellent thermal radiation properties,and energy efficiency of GGFF make it an outstanding material for infrared radiation drying.

关键词： chemical vapor deposition graphene propane rapid preparation

来源：评论

学校读者我要写书评

暂无评论

Laplacian Sparse Dynamic Slow Feature Analysis for Process Monitoring and Fault Isolation

引用

IEEE Sensors Journal 2025年第9期25卷 15653-15667页

作者： Wu, Ping Xue, Yikai Ni, Yuxuan Pan, Haipeng Zhang, Xi He, Yuchen Gao, Jinfeng Zhejiang Sci-Tech University School of Information Science and Engineering Hangzhou310018 China China Jiliang University Key Laboratory of Intelligent Manufacturing Quality Big Data Tracing and Analysis of Zhejiang Province Hangzhou314423 China

The process monitoring and fault isolation are essential for ensuring operational safety and maintaining product quality in the industrial processes. This study introduces a novel approach to process monitoring and fault isolation based on the Laplacian sparse dynamic slow feature analysis (LSDSFA). To simultaneously account for sparsity, dynamics, and global structural information, a new optimization framework for LSDSFA is proposed. This framework incorporates the n l1 norm and a Laplacian graph into dynamic slow feature analysis (SFA), with enhancements to process variable representation. The optimization problem is addressed using the alternating direction method of multipliers (ADMMs). The proposed method decomposes the process variable space into latent and residual subspaces. In addition, three monitoring statistics are developed to facilitate effective process monitoring, while fault isolation is achieved through a two-level contribution plot. Specifically, the intrinsic structure of the process data is captured by employing a graph Laplacian operator to explore intervariable correlations. Simultaneously, the incorporation of the graph Laplacian operator and l1 norm into dynamic SFA (DSFA) reduces variable redundancy, thereby exploiting the intrinsic structure of the process data more effectively and improving interpretability through the sparsity. Experimental evaluations conducted on the widely adopted Tennessee Eastman Process (TEP) benchmark and a real-world blast furnace ironmaking process (BFIP) demonstrate the superior performance of the proposed LSDSFA-based method in comparison with related techniques. © 2001-2012 IEEE.

关键词： Blast furnaces

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：