检索结果-内蒙古大学图书馆

Belief Combination of Classifiers for Incomplete Data

IEEE/CAA Journal of Automatica Sinica 2022年第4期9卷 652-667页

作者： Zuowei Zhang Songtao Ye Yiru Zhang Weiping Ding Hao Wang IEEE the Research Center for Optical Fiber Sensing Zhejiang Laboratory the School of Automation Northwestern Polytechnical University the School of Cyber Engineering Xidian University the Department of Computer Science CY Cergy Paris Université the School of Information Science and Technology Nantong University the School with of Cyber Engineering Xidian University the Department of Computer Science Norwegian University of Science and Technology

Data with missing values,or incomplete information,brings some challenges to the development of classification,as the incompleteness may significantly affect the performance of *** this paper,we handle missing values in both training and test sets with uncertainty and imprecision reasoning by proposing a new belief combination of classifier(BCC)method based on the evidence *** proposed BCC method aims to improve the classification performance of incomplete data by characterizing the uncertainty and imprecision brought by *** BCC,different attributes are regarded as independent sources,and the collection of each attribute is considered as a ***,multiple classifiers are trained with each subset independently and allow each observed attribute to provide a sub-classification result for the query ***,these sub-classification results with different weights(discounting factors)are used to provide supplementary information to jointly determine the final classes of query *** weights consist of two aspects:global and *** global weight calculated by an optimization function is employed to represent the reliability of each classifier,and the local weight obtained by mining attribute distribution characteristics is used to quantify the importance of observed attributes to the pattern *** comparative experiments including seven methods on twelve datasets are executed,demonstrating the out-performance of BCC over all baseline methods in terms of accuracy,precision,recall,F1 measure,with pertinent computational costs.

关键词： Classifier fusion classification evidence theory incomplete data missing values

来源：评论

学校读者我要写书评

暂无评论

LKAW: A Robust Watermarking Method Based on Large Kernel Convolution and Adaptive Weight Assignment

引用

computers, Materials & Continua 2023年第4期75卷 1-17页

作者： Xiaorui Zhang Rui Jiang Wei Sun Aiguo Song Xindong Wei Ruohan Meng Engineering Research Center of Digital Forensics Ministry of EducationJiangsu Engineering Center of Network MonitoringSchool of Computer and SoftwareNanjing University of Information Science&TechnologyNanjing210044China Wuxi Research Institute Nanjing University of Information Science&TechnologyWuxi214100China Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology(CICAEET) Nanjing University of Information Science&TechnologyNanjing210044China School of Automation Nanjing University of Information Science&TechnologyNanjing210044China School of Instrument Science and Engineering Southeast UniversityNanjing211189China School of Teacher Education Nanjing University of Information Science&TechnologyNanjing210044China School of Computer Science Engineering Nanyang Technological UniversitySingapore

Robust watermarking requires finding invariant features under multiple attacks to ensure correct *** learning has extremely powerful in extracting features,and watermarking algorithms based on deep learning have attracted widespread *** existing methods use 3×3 small kernel convolution to extract image features and embed the ***,the effective perception fields for small kernel convolution are extremely confined,so the pixels that each watermarking can affect are restricted,thus limiting the performance of the *** address these problems,we propose a watermarking network based on large kernel convolution and adaptive weight assignment for loss *** uses large-kernel depth-wise convolution to extract features for learning large-scale image information and subsequently projects the watermarking into a highdimensional space by 1×1 convolution to achieve adaptability in the channel ***,the modification of the embedded watermarking on the cover image is extended to more *** the magnitude and convergence rates of each loss function are different,an adaptive loss weight assignment strategy is proposed to make theweights participate in the network training together and adjust theweight ***,a high-frequency wavelet loss is proposed,by which the watermarking is restricted to only the low-frequency wavelet sub-bands,thereby enhancing the robustness of watermarking against image *** experimental results show that the peak signal-to-noise ratio(PSNR)of the encoded image reaches 40.12,the structural similarity(SSIM)reaches 0.9721,and the watermarking has good robustness against various types of noise.

关键词： Robust watermarking large kernel convolution adaptive loss weights high-frequency wavelet loss deep learning

来源：评论

学校读者我要写书评

暂无评论

C2FNet: Coarse-to-Fine Keypoint Localization Network for Monocular 6D Object Pose Estimation

C2FNet: Coarse-to-Fine Keypoint Localization Network for Mon...

引用

2023 China Automation Congress, CAC 2023

作者： Sun, Jiahao Ma, Xin Li, Yibin Center for Robotics School of Control Science and Engineering Shandong University China Engineering Research Center of Intelligent Unmanned System Ministry of Education Jinan China

ISBN: (纸本)9798350303759

Estimating the 6D object pose from a singular RGB image is a fundamental task in the field of computer vision. Recent studies have demonstrated that keypoint-based methods exhibit remarkable efficacy. Such methodologies initially identify keypoints and subsequently deduce the object's pose by addressing a Perspective-n-Point (PnP) problem. Nonetheless., the prevalent approach of directly regressing the 2D coordinates of keypoints renders these methods sensitive to occlusions. Instead., we inaugurate a coarse-to-fine keypoint localization network (C2FNet)., where we utilize the predicted keypoint offsets from the first stage as input to deformable convolutional networks (DCN) in the second stage., to further capture geometric features and enhance spatial relationships between keypoints., thus outputting accurate and robust keypoint coordinates. Experiments indicate that the proposed approach surpasses existing advanced methods in terms of performance on the LINEMOD and Occlusion LINEMOD datasets. © 2023 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

A Composite Decomposition Method for Large-Scale Global Optimization

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第12期5卷 6304-6319页

作者： Tian, Maojiang Chen, Minyang Du, Wei Tang, Yang Jin, Yaochu Yen, Gary G. Southern University of Science and Technology Department of Computer Science and Engineering Shenzhen518055 China East China University of Science and Technology Key Laboratory of Smart Manufacturing in Energy Chemical Process Ministry of Education Shanghai200237 China East China University of Science and Technology Engineering Research Center of Process System Engineering Ministry of Education Shanghai200237 China Westlake University School of Engineering Hangzhou310030 China Oklahoma State University School of Electrical and Computer Engineering StillwaterOK74048 United States

Cooperative coevolution (CC) algorithms, based on the divide-and-conquer strategy, have emerged as the predominant approach to solving large-scale global optimization (LSGO) problems. The efficiency and accuracy of the grouping stage significantly impact the performance of the optimization process. While the general separability grouping (GSG) method has overcome the limitation of previous differential grouping (DG) methods by enabling the decomposition of nonadditively separable functions, it suffers from high computational complexity. To address this challenge, this article proposes a composite separability grouping (CSG) method, seamlessly integrating DG and GSG into a problem decomposition framework to utilize the strengths of both approaches. CSG introduces a step-by-step decomposition framework that accurately decomposes various problem types using fewer computational resources. By sequentially identifying additively, multiplicatively and generally separable variables, CSG progressively groups nonseparable variables by recursively considering the interactions between each nonseparable variable and the formed nonseparable groups. Furthermore, to enhance the efficiency and accuracy of CSG, we introduce two innovative methods: a multiplicatively separable variable detection method and a nonseparable variable grouping method. These two methods are designed to effectively detect multiplicatively separable variables and efficiently group nonseparable variables, respectively. Extensive experimental results demonstrate that CSG achieves more accurate variable grouping with lower computational complexity compared to GSG and state-of-the-art DG-series designs. © 2024 IEEE.

关键词： Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

The propagation of Quasi-static region during granular impact

引用

Particuology 2023年第12期83卷 1-7页

作者： Moyu Yang Ran Li Yingnan Xiu Qiang Zeng Xiaoyan Ye Hui Yang School of Optical-Electrical and Computer Engineering University of Shanghai for Science and TechnologyShanghai200093China Center for Particle-Laden Turbulence Key Laboratory of Mechanics on Disaster and Environment in Western China attached to the Ministry of Education of ChinaDepartment of Mechanics and Engineering ScienceSchool of Civil Engineering and MechanicsLanzhou UniversityLanzhou730000China

In this paper,through experiments and DEM simulations,it is found that there is a ring-shaped region named Quasi-static Region between the particles expanding outward and the particles collapsing inward during the impact ***-static Region is always generated from the impact point at the same time,and then spreads out at a uniform *** the propagation of Quasi-static Region,the velocity of the particles in the particle extend region varies linearly in space and *** the change rate is only related to the properties of the particle *** simulation results show that the particle flow in Quasi-static Region is elastic-inertial flow,while the particle flow expanding outward and collapsing inward is inertial flow.

关键词： Impact Quasi-staticregion Propagation Shearflow

来源：评论

学校读者我要写书评

暂无评论

DP-RAE: A Dual-Phase Merging Reversible Adversarial Example for Image Privacy Protection 24

DP-RAE: A Dual-Phase Merging Reversible Adversarial Example ...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Zhu, Jiajie Du, Xia Zhou, Jizhe Pun, Chi-Man Xu, Qizhen Liu, Xiaoyuan School of Computer and Information Engineering Xiamen University of Technology Xiamen China School of Computer Science Engineering Research Center of Machine Learning and Industry Intelligence Sichuan University Chengdu China Department of Computer and Information Science University of Macau China

ISBN: (纸本)9798400706868

In digital security, Reversible Adversarial Examples (RAE) blend adversarial attacks with Reversible Data Hiding (RDH) within images to thwart unauthorized access. Traditional RAE methods, however, compromise attack efficiency for the sake of perturbation concealment, diminishing the protective capacity of valuable perturbations and limiting applications to white-box scenarios. This paper proposes a novel Dual-Phase merging Reversible Adversarial Example (DP-RAE) generation framework, combining a heuristic black-box attack and RDH with Grayscale Invariance (RDH-GI) technology. This dual strategy not only evaluates and harnesses the adversarial potential of past perturbations more effectively but also guarantees flawless embedding of perturbation information and complete recovery of the original image. Experimental validation reveals our method's superiority, secured an impressive 96.9% success rate and 100% recovery rate in compromising black-box models. In particular, it achieved a 90% misdirection rate against commercial models under a constrained number of queries. This marks the first successful attempt at targeted black-box reversible adversarial attacks for commercial recognition models. This achievement highlights our framework's capability to enhance security measures without sacrificing attack performance. Moreover, our attack framework is flexible, allowing the interchangeable use of different attack and RDH modules to meet advanced technological requirements. © 2024 ACM.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

A Hybrid CNN-GRU model for Session-based Recommender Systems 9

A Hybrid CNN-GRU model for Session-based Recommender Systems

引用

9th International Conference on computer and Communications, ICCC 2023

作者： Tegene, Abebe Tamrat Liu, Qiao Gan, Yanglei Jimale, Elias Ayenew, Melak Leka, Habte University of Electronic Science and Technology of China School of Computer Science and Engineering Chengdu China Addis Ababa Science and Technology University Center of Excellence of Ai and Robotics Addis Ababa Ethiopia University of Electronic Science and Technology of China School of Information and Software Engineering Chengdu China

ISBN: (纸本)9798350317251

In many e-commerce recommendation systems, user profiles are mostly not available. In such cases, the recommendation task considers user behaviors like click sessions or browsing history. Traditional recommender methods often rely on users' past interactions for recommending user interests, which is difficult to apply to session-based recommender systems. However, these methods perform very poorly on this task. Recently, deep learning techniques such as recurrent neural networks (RNNs) and convolutional neural networks (CNNs) showed outstanding performance in session-based recommendation problems. In this paper, we propose a hybrid CNN and gated recurrent unit (GRU) model that exploits the advantages of both CNN and GRU in modeling the rigid order requirement for interactions inside sessions and modeling the sequential long-term dependencies in session data, respectively. Our proposed hybrid model has two architectures: the first part consists of the CNN layers that take input from Item ID to learn local features and relationships in sessions, and the second part is a GRU layer that takes the output from the CNN layer to learn the long-term dependencies in that session. This hybrid technique enables the architecture for modeling prominent features in the session to provide accurate recommendations. Extensive experiments over a real-world dataset demonstrate that the proposed hybrid model performs well and outperforms those GRU and CNN-based models in the state-of-the-art recommendation task on both metrics used. © 2023 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

LMCF-FS: A Novel Lightweight Malware Classification Framework Driven by Feature Selection 6th

LMCF-FS: A Novel Lightweight Malware Classification Framewor...

引用

6th International Conference on Machine Learning for Cyber Security, ML4CS 2024

作者： Yun, Cui Zhou, Lei Xing, Shuangshuang Yang, Ning Zhao, Pan Chen, Zhiguo School of Computer Jiangsu University of Science and Technology Zhenjiang212100 China Engineering Research Center of Digital Forensics Ministry of Education Nanjing University of Information Science and Technology Nanjing210044 China School of Computer Science and School of Cyber Science and Engineering Nanjing University of Information Science and Technology Nanjing210044 China

ISBN: (纸本)9789819645657

The rapid increase in the number of malware and its variants poses a significant threat to internet security. While existing machine learning-based malware classification methods can improve accuracy, they often require complex feature engineering. In contrast, converting executable files into images and classifying them using deep learning models can reduce the reliance on prior knowledge of malware features and simplify the feature processing. However, most studies have not adequately considered the impact of image pixel features and size on classification results. In addition, the model structure of deep learning classification methods based on pre-trained parameters and transfer learning is usually more complex, resulting in the classification model requiring more memory and time overhead. To solve the above problems, this paper proposes a novel lightweight malware classification framework LMCF-FS driven by feature selection. This framework uses a proposed new feature selection method based on pixel pair features to improve feature sparsity and optimize image texture features, thereby improving feature expression capabilities. At the same time, an interpolation algorithm is used to balance the image size. In addition, a new lightweight malware classification model ConvInceptionNet is built based on the Inception-C module to balance accuracy, computational cost, and number of parameters, thereby improving malware classification efficiency. Our proposed LMCF-FS framework achieves a classification accuracy of 99.12% on the Microsoft Malware Classification Challenge Dataset (BIG2015 Dataset), and it only takes 0.92 ms to predict a 224 × 224 malware image, verifying LMCF-FS effectiveness in dealing with malware classification. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Image texture

来源：评论

学校读者我要写书评

暂无评论

Rotor Angle Stability Prediction Using Temporal and Topological Embedding Deep Neural Network Based on Grid-informed Adjacency Matrix

引用

Journal of Modern Power Systems and Clean Energy 2024年第3期12卷 695-706页

作者： Peiyuan Sun Long Huo Xin Chen Siyuan Liang the School of Electrical Engineering Xi’an Jiaotong UniversityXi’an 710049China the School of Electrical Engineering and the Center of Nanomaterials for Renewable EnergyState Key Laboratory of Electrical Insulation and Power EquipmentXi’an Jiaotong UniversityXi’an 710049China the Department of Computer Science and Engineering The Chinese University of Hong KongShatin999077Hong KongChina

Rotor angle stability(RAS)prediction is critically essential for maintaining normal operation of the interconnected synchronous machines in power *** wide deployment of phasor measurement units(PMUs)promotes the development of data-driven methods for RAS *** paper proposes a temporal and topological embedding deep neural network(TTEDNN)model to accurately and efficiently predict RAS by extracting the temporal and topological features from the PMU *** grid-informed adjacency matrix incorporates the structural and electrical parameter information of the power *** the small-signal RAS with disturbance under initial operating conditions and the transient RAS with short circuits on transmission lines are *** studies of the IEEE 39-bus and IEEE 300-bus power systems are used to test the performance,scalability,and robustness against measurement uncertainties of the TTEDNN *** show that the TTEDNN model performs best among existing deep learning ***,the superior transfer learning ability from small-signal RAS conditions to transient RAS conditions has been proved.

关键词： Rotor angle stability prediction topological embedding deep learning graph convolution network

来源：评论

学校读者我要写书评

暂无评论

Reference Trustable Decoding: A Training-Free Augmentation Paradigm for Large Language Models 38

Reference Trustable Decoding: A Training-Free Augmentation P...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Shi, Luohe Yao, Yao Li, Zuchao Zhang, Lefei Zhao, Hai National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Wuhan430072 China Department of Computer Science and Engineering Shanghai Jiao Tong University China

Large language models (LLMs) have rapidly advanced and demonstrated impressive capabilities. In-Context Learning (ICL) and Parameter-Efficient Fine-Tuning (PEFT) are currently two mainstream methods for augmenting LLMs to downstream tasks. ICL typically constructs a few-shot learning scenario, either manually or by setting up a Retrieval-Augmented Generation (RAG) system, helping models quickly grasp domain knowledge or question-answering patterns without changing model parameters. However, this approach involves trade-offs, such as slower inference speed and increased space occupancy. PEFT assists the model in adapting to tasks through minimal parameter modifications, but the training process still demands high hardware requirements, even with a small number of parameters involved. To address these challenges, we propose Reference Trustable Decoding (RTD), a paradigm that allows models to quickly adapt to new tasks without fine-tuning, maintaining low inference costs. RTD constructs a reference datastore from the provided training examples and optimizes the LLM's final vocabulary distribution by flexibly selecting suitable references based on the input, resulting in more trustable responses and enabling the model to adapt to downstream tasks at a low cost. Experimental evaluations on various LLMs using different benchmarks demonstrate that RTD establishes a new paradigm for augmenting models to downstream tasks. Furthermore, our method exhibits strong orthogonality with traditional methods, allowing for concurrent usage. Our code can be found at https://***/ShiLuohe/ReferenceTrustableDecoding. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

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：