检索结果-内蒙古大学图书馆

International Conference on Parallel and Distributed Systems (ICPADS)

作者： Ronghuan Zhang Jing Zhao Ming Li Qingzhi Zou Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China School of Intelligence and Information Engineering Shandong University of Traditional Chinese Medicine Jinan China

ISBN: (数字)9798331515966

ISBN: (纸本)9798331515973

Extracting buildings from remote sensing images using deep learning techniques is a widely applied and crucial task. Convolutional Neural Networks (CNNs) adopt hierarchical feature representation, showcasing powerful capabilities in extracting local information but facing challenges in capturing global features. Transformers can address this limitation, but they perform poorly in extracting local features and significantly increase memory requirements and computational complexity. To overcome these challenges, we propose a method for building extraction from remote sensing images called LGDB-Net (Local-Global Dual-Branch Network), employing a dual-branch approach. Firstly, inspired by Swin Transformer, we designed GB-Former(Global Branch-Former) as the backbone network to model global information. We use a linear multi-head self-attention mechanism to reduce time and memory complexity while maintaining a large global receptive field. Additionally, we replace the traditional multi-layer perceptron with a convolution-enhanced multi-layer perceptron to improve channel feature representation, reduce model parameters, and enhance segmentation performance. Secondly, we use multiple Depth-wise Conv3×3 + LN (Layer Normalization) + GeLU (Gaussian Error Linear Unit) modules as the auxiliary branch for local detailed feature extraction. Finally, we adopt a multi-scale feature fusion strategy to integrate feature information from both branches. We conduct a series of experiments on three datasets: WHU, Massachusetts, and Inria. The experimental results demonstrate that the proposed method not only effectively improves segmentation accuracy with lower building omission and commission rates but also significantly reduces model parameters and computational complexity.

关键词： Accuracy Computational modeling Memory management Neural networks Feature extraction Transformers Sensors Data mining Computational complexity Remote sensing

来源：评论

学校读者我要写书评

暂无评论

FedCache: A Knowledge Cache-driven Federated Learning Architecture for Personalized Edge Intelligence

TechRxiv

引用

TechRxiv 2024年

作者： Wu, Zhiyuan Sun, Sheng Wang, Yuwei Liu, Min Xu, Ke Wang, Wen Jiang, Xuefeng Gao, Bo Lu, Jinda Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Zhongguancun Laboratory Beijing China Department of Computer Science and Technology Tsinghua University Beijing China School of Computer and Information Technology The Engineering Research Center of Network Management Technology for High-Speed Railway Ministry of Education Beijing Jiaotong University Beijing China School of Information Science and Technology University of Science and Technology of China Hefei China

Edge Intelligence (EI) allows Artificial Intelligence (AI) applications to run at the edge, where data analysis and decision-making can be performed in real-time and close to data sources. To protect data privacy and unify data silos distributed among end devices in EI, Federated Learning (FL) is proposed for collaborative training of shared AI models across multiple devices without compromising data privacy. However, the prevailing FL approaches cannot guarantee model generalization and adaptation on heterogeneous clients. Recently, Personalized Federated Learning (PFL) has drawn growing awareness in EI, as it enables a productive balance between local-specific training requirements inherent in devices and global-generalized optimization objectives for satisfactory performance. However, most existing PFL methods are based on the Parameters Interaction-based Architecture (PIA) represented by FedAvg, which suffers from unaffordable communication burdens due to large-scale parameters transmission between devices and the edge server. In contrast, Logits Interaction-based Architecture (LIA) allows to update model parameters with logits transfer and gains the advantages of communication lightweight and heterogeneous on-device model allowance compared to PIA. Nevertheless, previous LIA methods attempt to achieve satisfactory performance either relying on unrealistic public datasets or increasing communication overhead for additional information transmission other than logits. To tackle this dilemma, we propose a knowledge cache-driven PFL architecture, named FedCache, which reserves a knowledge cache on the server for fetching personalized knowledge from the samples with similar hashes to each given on-device sample. During the training phase, ensemble distillation is applied to on-device models for constructive optimization with personalized knowledge transferred from the server-side knowledge cache. Empirical experiments on four datasets demonstrate that FedCache achiev

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

AOCC-FL: Federated Learning with Aligned Overlapping via Calibrated Compensation

AOCC-FL: Federated Learning with Aligned Overlapping via Cal...

引用

IEEE Annual Joint Conference: INFOCOM, IEEE computer and Communications Societies

作者： Haozhao Wang Wenchao Xu Yunfeng Fan Ruixuan Li Pan Zhou School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China Department of Computing The Hong Kong Polytechnic University Hong Kong Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China

Federated Learning enables collaboratively model training among a number of distributed devices with the coordination of a centralized server, where each device alternatively performs local gradient computation and communication to the server. FL suffers from significant performance degradation due to the excessive communication delay between the server and devices, especially when the network bandwidth of these devices is limited, which is common in edge environments. Existing methods overlap the gradient computation and communication to hide the communication latency to accelerate the FL training. However, the overlapping can also lead to an inevitable gap between the local model in each device and the global model in the server that seriously restricts the convergence rate of learning process. To address this problem, we propose a new overlapping method for FL, AOCC-FL, which aligns the local model with the global model via calibrated compensation such that the communication delay can be hidden without deteriorating the convergence performance. Theoretically, we prove that AOCC-FL admits the same convergence rate as the non-overlapping method. On both simulated and testbed experiments, we show that AOCC-FL achieves a comparable convergence rate relative to the non-overlapping method while outperforming the state-of-the-art overlapping methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

JSRevealer: A Robust Malicious JavaScript Detector against Obfuscation

JSRevealer: A Robust Malicious JavaScript Detector against O...

引用

International Conference on Dependable Systems and Networks (DSN)

作者： Kunlun Ren Weizhong Qiang Yueming Wu Yi Zhou Deqing Zou Hai Jin National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China Jinyinhu Laboratory Wuhan China Nanyang Technological University Singapore National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China

Due to the convenience and popularity of Web applications, they have become a prime target for attackers. As the main programming language for Web applications, many methods have been proposed for detecting malicious JavaScript, among which static analysis-based methods play an important role because of their high effectiveness and efficiency. However, obfuscation techniques are commonly used in JavaScript, which makes the features extracted by static analysis contain many useless and disguised features, leading to many false positives and false negatives in detection results. In this paper, we propose a novel method to find out the essential features related to the semantics of JavaScript code. Specifically, we develop JS-Revealer, a robust, effective, scalable, and interpretable detector for malicious JavaScript. To test the capabilities of JSRevealer, we conduct comparative experiments with four other state-of-the-art malicious JavaScript detection tools. The experimental results show that JSRevealer has an average F1 of 84.8% on the data obfuscated by different obfuscators, which is 21.6%, 22.3%, 18.7%, and 22.9% higher than the tools CUJO, ZOZZLE, JAST, and JSTAP, respectively. Moreover, the detection results of JSRevealer can be interpreted, which can provide meaningful insights for further security research.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Entirety of Quantum Uncertainty and Its Experimental Verification

引用

Chinese Physics Letters 2021年第7期38卷 11-16页

作者： Jie Xie Li Zhou Aonan Zhang Huichao Xu Man-Hong Yung Ping Xu Nengkun Yu Lijian Zhang National Laboratory of Solid State Microstructures College of Engineering and Applied Sciences and School of PhysicsNanjing UniversityNanjing 210093China Collaborative Innovation Center of Advanced Microstructures Nanjing UniversityNanjing 210093China Department of Computer Science and Technology Tsinghua UniversityBeijing 100084China Shenzhen Institute for Quantum Science and Engineering and Department of Physics Southern University of Science and TechnologyShenzhen 518055China Shenzhen Key Laboratory of Quantum Science and Engineering Southern University of Science and TechnologyShenzhen 518055China Institute for Quantum Information&State Key Laboratory of High Performance Computing College of ComputerNational University of Defense TechnologyChangsha 410073China Centre for Quantum Software and Information School of SoftwareFaculty of Engineering and Information TechnologyUniversity of Technology SydneyNSWAustralia

As a foundation of quantum physics,uncertainty relations describe ultimate limit for the measurement uncertainty of incompatible ***,uncertainty relations are formulated by mathematical bounds for a specific *** we present a method for geometrically characterizing uncertainty relations as an entire area of variances of the observables,ranging over all possible input *** find that for the pair of position and momentum operators,Heisenberg's uncertainty principle points exactly to the attainable area of the variances of position and ***,for finite-dimensional systems,we prove that the corresponding area is necessarily semialgebraic;in other words,this set can be represented via finite polynomial equations and inequalities,or any finite union of such *** particular,we give the analytical characterization of the areas of variances of(a)a pair of one-qubit observables and(b)a pair of projective observables for arbitrary dimension,and give the first experimental observation of such areas in a photonic system.

关键词： observable union operators

来源：评论

学校读者我要写书评

暂无评论

MGRR-SQL: Multi-Granularity Relevant Retrieval-Based in-Context Learning Approach for Text-to-SQL Generation

MGRR-SQL: Multi-Granularity Relevant Retrieval-Based in-Cont...

引用

Advanced Algorithms and Control Engineering (ICAACE), International Conference on

作者： Yiming Zhan Zhao Li Tong Chen Shiwei Wu Yang Li Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China Shandong Evay Info Technology Co. Ltd. Jinan China School of Cyberspace Security (School of Cryptology) Hainan University Haikou China

ISBN: (数字)9798331535087

ISBN: (纸本)9798331535094

In-Context learning serves as a vital component for enhancing Text-to-SQL task performance. However, current in-context learning methodologies for Text-to-SQL applications fail to sufficiently bridge the significant cross-domain correlation gap that exists between few-shot examples and the intended query target. Our approach overcomes these challenges through a novel relevant retrieval-based in-context learning method, which operates across three distinct granularity levels: (1) semantic similarity retrieval for analogous questions, (2) query kernel entity matching for retrieving strongly relevant questions and (3) character-level similarity analysis for fine-grained question retrieval. Additionally, we introduce a novel Object-Relational Mapping (ORM)-based database prompt and a post cell value linking method that effectively describes the schema while avoiding error propagation common in traditional schema linking approaches. Our experimental evaluations conducted on the benchmark datasets BIRD and Spider reveal that our approach delivers strong performance, comparable to state-of-the-art methods.

关键词： Learning systems Structured Query Language Databases Large language models Computational modeling Semantics Benchmark testing Birds Business intelligence Standards

来源：评论

学校读者我要写书评

暂无评论

TarGF: learning target gradient field to rearrange objects without explicit goal specification 22

TarGF: learning target gradient field to rearrange objects w...

引用

Proceedings of the 36th International Conference on Neural Information Processing Systems

作者： Mingdong Wu Fangwei Zhong Yulong Xia Hao Dong Center on Frontiers of Computing Studies School of Computer Science Peking University and Beijing Institute for General Artificial Intelligence (BIGAI) School of Intelligence Science and Technology Peking University and Beijing Institute for General Artificial Intelligence (BIGAI) Center on Frontiers of Computing Studies School of Computer Science Peking University Center on Frontiers of Computing Studies School of Computer Science Peking University and Peng Cheng Laboratory

ISBN: (纸本)9781713871088

Object Rearrangement is to move objects from an initial state to a goal state. Here, we focus on a more practical setting in object rearrangement, i.e., rearranging objects from shuffled layouts to a normative target distribution without explicit goal specification. However, it remains challenging for AI agents, as it is hard to describe the target distribution (goal specification) for reward engineering or collect expert trajectories as demonstrations. Hence, it is infeasible to directly employ reinforcement learning or imitation learning algorithms to address the task. This paper aims to search for a policy only with a set of examples from a target distribution instead of a handcrafted reward function. We employ the score-matching objective to train a Target Gradient Field (TarGF), indicating a direction on each object to increase the likelihood of the target distribution. For object rearrangement, the TarGF can be used in two ways: 1) For model-based planning, we can cast the target gradient into a reference control and output actions with a distributed path planner; 2) For model-free reinforcement learning, the TarGF is not only used for estimating the likelihood-change as a reward but also provides suggested actions in residual policy learning. Experimental results in ball rearrangement and room rearrangement demonstrate that our method significantly outperforms the state-of-the-art methods in the quality of the terminal state, the efficiency of the control process, and scalability.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Unwritten Magic: Participatory Design of AI Dialogue to Empower Marginalized Voices 22

Unwritten Magic: Participatory Design of AI Dialogue to Empo...

引用

2nd ACM Conference on Information technology for Social Good, GoodIT 2022

作者： Buddemeyer, Amanda Nwogu, Jennifer Solyst, Jaemarie Walker, Erin Nkrumah, Tara Ogan, Amy Hatley, Leshell Stewart, Angela School of Computing and Information Learning Research and Development Center University of Pittsburgh United States Human Computer Interaction Institute Carnegie Mellon University United States Center for Gender Equity in Science and Technology Arizona State University United States Uplift Inc.

ISBN: (纸本)9781450392846

Language is an act of identity, but AI has no identity other than that which its creators assign it. technology creators who do not fully consider how identity information is encoded in AI dialogue risk creating representational harms that negatively impact users' interactions with the technology, particularly young users from groups marginalized in STEM education. One solution is to engage young users in Participatory Design of dialogue, pushing power away from the researcher and toward the young users. This positions users as technology creators who understand AI language as a technosocial phenomenon and who have their own perspective about how identity is best portrayed in AI language. In this work in progress paper, we provide initial impressions from a Youth Advisory Group (YAG) with 12 middle-school-aged learners of color who are all female or non-binary. © 2022 Owner/Author.

关键词： Engineering education

来源：评论

学校读者我要写书评

暂无评论

Distributed private preserving learning based chaotic encryption framework for cognitive healthcare IoT systems

引用

Informatics in Medicine Unlocked 2024年 49卷

作者： Nabi, Shaik Abdul Kalpana, Ponugoti Chandra, N. Subhash Smitha, L. Naresh, K. Ezugwu, Absalom E. Abualigah, Laith Department of Computer Science and Engineering AVN Institute of Engineering and Technology Department of Computer Science and Engineering CVR College of Engineering Department of Information Technology G Narayanamma Institute of Technology and Science Department of Computer Science and Engineering TKR College of Engineering & Technology Unit for Data Science and Computing North-West University Computer Science Department Al Al-Bayt University MEU Research Unit Middle East University Applied Science Research Center Applied Science Private University Jadara Research Center Jadara University Artificial Intelligence and Sensing Technologies (AIST) Research Center University of Tabuk School of Engineering and Technology Sunway University Malaysia

In the field of cognitive healthcare Internet of Things (CH-IoT), there is a strong demand for reliable and minimally intrusive smart gadgets that consistently acquire, analyse, and obtain the confidential health details of the individual. In fact, CH-IoT is empowered with artificial intelligence (AI) to transmute a fewer operational inputs into actionable, intelligent actions through the digitization of medical healthcare data. However, these systems consume more network complexity, interaction, and overhead costs, while inducing a blend of susceptibility and confidentiality issues. In support of this complexity, these cognitive systems need centralised data collection and to be gathered and analysed, which affects scalability issues and adds fuel to privacy and security breaches. Even though it possesses greater intricacy in its potential application, a substantial factor is maintaining the private preservation of healthcare data against the growing attacks. Thus, this paper presents a distributed privacy-preserving, chaotic encryption-based framework that can be deployed for CH-IoT systems to safeguard sensitive data against message modification, denial of service (DoS), and man-in-the-middle attacks (MIM), guaranteeing privacy and data integrity. The proposed framework integrated the federated learning layered hybrid chaotic encryption strategies by investigating through examination the learning infrastructure of convolutional neural networks (CNN). In the examination, the complete framework was carried out in the Tensorflow Federated Learning Libraries (FLL), and numerous performance metrics such as accuracy, precision, recall, f1-score, transmission efficiency, and overhead ratio were measured and contrasted with the various existing frameworks. For the intensive analysis, formal and informal security experiments were also conducted by NIST (National Institute of science and technology). The analytical results illustrate the importance of the proposed framewor

关键词： Cognitive health care Distributed learning Federated learning libraries Internet of things NIST Privacy and security breaches

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-based Image Text Processing Research*

Deep Learning-based Image Text Processing Research*

引用

IEEE International Conference on Big Data Security on Cloud (BigDataSecurity), High Performance and Smart computing (HPSC) and Intelligent Data and Security (IDS)

作者： Huixuan Xiong Kai Jin Jingnian Liu Jiahong Cai Lijun Xiao School of Computer Science and Engineering Hunan University of Science and Technology Hunan Key Laboratory for Service Computing and Novel Software Technology Xiangtan China the College of Computer Science and Electronics Engineering Hunan University Changsha China Big Data Development and Research Center Guangzhou College of Technology and Business Guangzhou China

Deep learning is a powerful multi-layer architecture that has important applications in image processing and text classification. This paper first introduces the development of deep learning and two important algorithms of deep learning: convolutional neural networks and recurrent neural networks. The paper then introduces three applications of deep learning for image recognition, image detection, and image forensics, as well as three text classification methods based on convolutional neural networks, recurrent neural networks, and other text classification methods. Finally, the development trend of deep learning in the field of text and image processing and the difficulties to be further researched are summarised and prospected.

关键词： Deep learning Image forensics Recurrent neural networks Computational modeling Text categorization Feature extraction Data models

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：