检索结果-内蒙古大学图书馆

2023 IEEE International Conference on Metaverse Computing, Networking and Applications, MetaCom 2023

作者： Zhang, Chuan Wang, Weijie Zhang, Weiting Nie, Jiangtian Liang, Jinwen Zhu, Liehuang Beijing Institute of Technology School of Cyberspace Science and Technology Beijing China Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies Guangdong China Beijing Institute of Technology School of Computer Science & Technology Beijing China Beijing Jiaotong University School of Electronic and Information Engineering Beijing China Nanyang Technological University School of Computer Science and Engineering Singapore Hong Kong Polytechnic University Department of Computing Hong Kong

ISBN: (纸本)9798350333336

Cross-Chain is an emerging technology to enable transaction circulation across different blockchain systems, breaking down transaction isolation among decentralized ecosystems. Existing cross-chain solutions are often constructed based on centralized trusted third parties, which introduce additional threats to users' identities due to potentially compromised risks on the centralized third parties. To exclude the single-point compromised risk in centralized systems, this paper focuses on a fully decentralized scenario and develops a distributed cross-chain transaction scheme, which enables cross-chain transaction exchanges while ensuring the unlinkability between payees and payers. Specifically, we first propose a cross-chain cryptocurrency exchange scheme by leveraging Ethereum's smart contracts, which achieves transaction exchanges in decentralized settings. Then, we leverage zero-knowledge succinct non-interactive argument of knowledge (i.e., zk-SNARKs) to explore a privacy-preserving method for cross-chain transactions in account-model blockchain systems, such that the unlinkability between payees and payers and the privacy of cross-chain participants can be guaranteed. Security analysis and experimental evaluations demonstrate that the proposed scheme achieves the security goal at acceptable costs. © 2023 IEEE.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

Intrusion Detection Systems Based on Machine Learning Approaches: A Systematic Review

Intrusion Detection Systems Based on Machine Learning Approa...

引用

2023 International Conference on science, engineering and Business for Sustainable Development Goals, SEB-SDG 2023

作者： Ogundokun, Roseline Oluwaseun Basil, Ugochukwu Babatunde, Akinbowale Nathaniel Abdulahi, Abdul Rahman Tosho Adenike, Ajiboye Raimot Adebiyi, Ayodele Ariyo Kaunas University of Technology Department of Multimedia Engineering Lithuania Landmark University Sdg 11. Sustainable Cities and Communities Omu Aran Nigeria Landmark University Department of Computer Science Omu Aran Nigeria Kwara State University Department of Computer Science Malete Nigeria Institute of Information and Communication Technology Department of Computer Science Kwara State Polytechnic Nigeria Institute of Applied Sciences Department of Statistics Kwara State Polytechnic Nigeria Landmark University Omu-Aran Department of Computer Science Omu Aran Nigeria Landmark University Omu Aran Sdg 3. Good Health and Wellbeing Nigeria

ISBN: (纸本)9798350324785

The proliferation of Internet use poses certain security problems for networks. Intrusion detection (ID) in cybersecurity technology is to recognize unexpected entry to or assaults on secured networked computers. In the research, many machine learning (ML) and deep learning (DL) algorithms have been used to tackle intrusion detection systems (IDS). Nevertheless, few publications examine and explain the present state of employing ML approaches to tackle ID issues. This systematic review (SR) analyzes 11 papers published between 2016 and 2021 that focused on developing single, hybrid, and ensemble classifiers. Similar research is evaluated based on their classifier designs, the datasets they used, and their conceptual frameworks. Recent accomplishments and limits in developing IDS systems using ML are presented and analyzed. In addition, many prospective study possibilities are offered. © 2023 IEEE.

关键词： Intrusion detection

来源：评论

学校读者我要写书评

暂无评论

Active and Visual Methods for Teaching Nonrectangular Reinforced Concrete Beams

Active and Visual Methods for Teaching Nonrectangular Reinfo...

引用

Best Practices and Lessons Learned for Teaching Concrete Materials and Reinforced Concrete 2021

作者： Carroll, J. Chris Behrouzi, Anahid A. Meyer, Karl F. The Department of Civil Computer and Electrical Engineering The School of Science and Engineering Saint Louis University United States California Polytechnic State University United States The Georgia Institute of Technology United States The Department of Civil and Mechanical Engineering The United States Military Academy United States

ISBN: (纸本)9781641952361

Nonrectangular cross sections are a common occurrence in reinforced concrete design typically taking the form of flanged beam sections, circular columns, and square or rectangular columns subject to biaxial bending. Instructors typically introduce the theory behind nonrectangular beams using two-dimensional sketches of flanged sections. Students can struggle to visualize the examples when presented in two dimensions;deciphering the multiple resultant compressive forces and their corresponding moment arms are particularly difficult. This paper presents an overview of nonrectangular beam theory and select active learning methods along with three specific examples used by the authors to teach nonrectangular beams in an undergraduate reinforced concrete design course. The first method is a simple problem-based learning example to dissuade students from "plug and chug" calculations using improper equations;the second method illustrates three cases for a traditional flanged T-beam section using physical three-dimensional models;and the third method uses virtual three-dimensional models to derive the depth of the equivalent stress block and corresponding nominal flexural strength for various cross sections. Each description provides the reader with the best practices to implement the respective technique. Lastly, the authors provide some lessons learned from their past implementations. The overall goal is to provide educators with examples to simplify the presentation of nonrectangular beams theory. © 2023 American Concrete institute. All rights reserved.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

What Improves the Generalization of Graph Transformers? A Theoretical Dive into the Self-attention and Positional Encoding 41

What Improves the Generalization of Graph Transformers? A Th...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Li, Hongkang Wang, Meng Ma, Tengfei Liu, Sijia Zhang, Zaixi Chen, Pin-Yu Department of Electrical Computer and System Engineering Rensselaer Polytechnic Institute TroyNY United States Department of Biomedical Informatics Stony Brook University Stony BrookNY United States Department of Computer Science and Engineering Michigan State University East LansingMI United States MIT-IBM Watson AI Lab IBM Research MA United States Department of Computer Science and Engineering University of Science and Technology of China Anhui Hefei China IBM Thomas J. Watson Research Center Yorktown HeightsNY United States

Graph Transformers, which incorporate self-attention and positional encoding, have recently emerged as a powerful architecture for various graph learning tasks. Despite their impressive performance, the complex non-convex interactions across layers and the recursive graph structure have made it challenging to establish a theoretical foundation for learning and generalization. This study introduces the first theoretical investigation of a shallow Graph Transformer for semi-supervised node classification, comprising a self-attention layer with relative positional encoding and a two-layer perceptron. Focusing on a graph data model with discriminative nodes that determine node labels and non-discriminative nodes that are class-irrelevant, we characterize the sample complexity required to achieve a desirable generalization error by training with stochastic gradient descent (SGD). This paper provides the quantitative characterization of the sample complexity and number of iterations for convergence dependent on the fraction of discriminative nodes, the dominant patterns, and the initial model errors. Furthermore, we demonstrate that self-attention and positional encoding enhance generalization by making the attention map sparse and promoting the core neighborhood during training, which explains the superior feature representation of Graph Transformers. Our theoretical results are supported by empirical experiments on synthetic and real-world benchmarks. Copyright 2024 by the author(s)

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

DeepRiceTransfer: Exploiting CNN Transfer Learning for Effective Rice Variety Classification

DeepRiceTransfer: Exploiting CNN Transfer Learning for Effec...

引用

Social and Sustainable Innovations in Technology and engineering (SASI-ITE), International Conference on

作者： P Kanaga Priya P Kirupa P Thilakaveni K Nisha Devi M Mahabooba S Jayachitra Department of Computer Science and Engineering KPR Institute of Engineering and Technology Coimbatore India Department of Computer Science and Engineering SNS College of Engineering Coimbatore India Department of Computer Engineering PSG Polytechnic College Coimbatore India Department of Artificial Intelligence and Data Science Bannari Amman Institute of Technology Erode India Department of Computer Science and Engineering Nehru Institute of Engineering and Technology Coimbatore India Department of Electronics and Communication Engineering PSNA College of Engineering and Technology Dindigul India

ISBN: (数字)9798350360790

ISBN: (纸本)9798350360806

Abstract- The proposed DeepRiceTransfer (DRT) model gives a thorough examination of the accurate categorization of rice types. The research aimed at reworking the accuracy and effectiveness of rice variety types. Convolutional Neural Networks (CNNs) and transfer learning are utilized by the version to strategically capitalize on previous facts from several datasets. The proposed methodology used many extraordinary neural network architectures, along with the DeepRiceTransfer Convolutional Neural community (CNN) for the rice image dataset, to achieve the correct type of results. To enhance the model’s overall performance, we especially used transfer learning methods with the MobileNet, ResNet50, and VGG16 architectures. Numerous statistical criteria, which include accuracy, precision, F1 score, and support, have been used to evaluate the class consequences. With accuracy scores of 98.44% for the DRT model,98.94% for CNN with transfer learning using MobileNet, 79.79% for ResNet50, and 99.47% for VGG16 architectures, the models showed impressive success in classifying rice varieties. The models confirmed impressive achievement in classifying rice types effects spotlight CNN models’ effectiveness in efficaciously classifying rice sorts consistent with their distinctive trends, especially those who use DRT and switch getting to know with MobileNet, ResNet50, and VGG16 architectures. The models’ elevated accuracy charges spotlight their capacity for real-time implementations in the rice range category and first-class assessment.

关键词： Training Technological innovation Accuracy Scalability Transfer learning Switches User interfaces

来源：评论

学校读者我要写书评

暂无评论

Development of a Sociocyberphysical Systems Cyber Threats Classifier 7

Development of a Sociocyberphysical Systems Cyber Threats Cl...

引用

7th International Symposium on Multidisciplinary Studies and Innovative Technologies, ISMSIT 2023

作者： Yevseiev, Serhii Murr, Pierre Milevskyi, Stanislav Korol, Olha Melnyk, Marharyta National Technical University 'Kharkiv Polytechnic Institute' Cybersecurity Department Kharkiv Ukraine International University of Science and Technology in Kuwait Computer Engineering Department Kuwait Kuwait National Technical University 'Kharkiv Polytechnic Institute' Cybersecurity Department Kharkiv Ukraine Set University Department of Cyber Security and Information Protection Kyiv Ukraine

ISBN: (纸本)9798350342154

The emergence of transformations of cyber-physical systems based on integration with elements of smart technologies and Internet of things predetermined the formation of socio-cyber-physical systems, which, on the one hand, expands the range of services based on the use of the advantages of social networks, on the other hand, forms the integration of targeted attacks with threats based on social engineering methods. The proposed universal classifier of cyber threats allows to take into account the possibilities of integration, as well as signs of synergy and hybridity of modern target threats. This approach increases the level of objectivity of the possible impact on the infrastructure elements of socio-cyber-physical systems by modern mechanisms of cyber-physical threats with their possible integration with threats based on social engineering methods, increases the level of security based on the timely formation of preventive measures for building multi-contour security systems, and carrying out measures to increase the level of knowledge of employees, companies, organizations, etc. © 2023 IEEE.

关键词： Cyber Physical System

来源：评论

学校读者我要写书评

暂无评论

Enhanced Multidimensional Harmonic Retrieval in MIMO Wireless Channel Sounding

引用

IEEE Internet of Things Journal 2025年第11期12卷 16243-16255页

作者： Zhang, Yanming Xu, Wenchao Jin, A-Long Tang, Tianquan Li, Min Ma, Peifeng Jiang, Lijun Gao, Steven The Chinese University of Hong Kong Department of Electronic Engineering Hong Kong Hong Kong The Hong Kong Polytechnic University Department of Computing Hong Kong Hong Kong Xi'an Jiaotong-Liverpool University Department of Communications and Networking Suzhou China HKU Zhejiang Institute of Research and Innovation Lab for Aerodynamics and Acoustics Hangzhou China Tianjin University School of Microelectronics Tianjin China The Chinese University of Hong Kong Institute of Space and Earth Information Science Department of Geography and Resource Management Hong Kong Hong Kong Missouri University of Science and Technology Department of Electrical and Computer Engineering RollaMO United States

This paper introduces a recursive parallel dynamic mode decomposition (RPDMD) scheme tailored for multidimensional harmonic retrieval (MHR), specifically applied to MIMO wireless channel sounding. The RPDMD algorithm is devised to address the complexities inherent in multidimensional scenarios, leveraging the dynamic mode decomposition (DMD) framework within a recursive parallel structure. Initially, the observed tensorial multidimensional harmonic data is transformed into a two-dimensional matrix format along the r-th dimension. Subsequently, DMD dissects this matrix data into eigenvalues and their associated modes. The real and imaginary components of the DMD eigenvalues yield damping factors and frequencies in the r-th dimension, respectively. Furthermore, recursive DMD is employed to scrutinize each mode independently for parameter retrieval across the remaining dimensions, enabling parallel analysis. Ultimately, this high-dimensional correlated decomposition scheme delivers paired damping factors and frequencies for all tones. Notably, the proposed approach can ascertain the number of tones in undamped sinusoidal signals, making it particularly suitable for MHR even without prior knowledge of the source count. Numerical experiments demonstrate the accuracy and robustness of the RPDMD scheme, with comparative analysis indicating that RPDMD outperforms similar methods, achieving optimal results with minimal mean square error in high signal-to-noise ratio scenarios. This work presents an effective data-driven solution for the MHR problem in MIMO wireless channel sounding. © 2014 IEEE.

关键词： Eigenvalues and eigenfunctions

来源：评论

学校读者我要写书评

暂无评论

A Provably Effective Method for Pruning Experts in Fine-tuned Sparse Mixture-of-Experts

arXiv

引用

arXiv 2024年

作者： Chowdhury, Mohammed Nowaz Rabbani Wang, Meng Maghraoui, Kaoutar El Wang, Naigang Chen, Pin-Yu Carothers, Christopher Department of Electrical Computer and Systems Engineering Rensselaer Polytechnic Institute NY United States IBM Research Yorktown HeightsNY United States Department of Computer Science Rensselaer Polytechnic Institute NY United States

The sparsely gated mixture of experts (MoE) architecture sends different inputs to different subnetworks (experts), through trainable routers. MoE reduces the training computation significantly for large models, but its deployment can be still memory/computation expensive for some downstream tasks. Model pruning is a popular approach to reduce inference computation, but its application in MoE architecture is largely unexplored. To the best of our knowledge, this paper provides the first provably efficient technique for pruning experts in fine-tuned MoE models. We theoretically prove that prioritizing the pruning of the experts with a smaller change of the router’s l2 norm from the pre-trained model guarantees the preservation of test accuracy, while significantly reducing the model size and the computational requirements. Although our theoretical analysis is centered on binary classification tasks on simplified MoE architecture, our expert pruning method is verified on large vision MoE models such as V-MoE and E3-MoE fine-tuned on benchmark datasets such as CIFAR-10, CIFAR-100, and ImageNet. Copyright © 2024, The Authors. All rights reserved.

关键词： Large datasets

来源：评论

学校读者我要写书评

暂无评论

SF-DQN: Provable Knowledge Transfer using Successor Feature for Deep Reinforcement Learning 41

SF-DQN: Provable Knowledge Transfer using Successor Feature ...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Zhang, Shuai Fernando, Heshan Devaka Liu, Miao Murugesan, Keerthiram Lu, Songtao Chen, Pin-Yu Chen, Tianyi Wang, Meng Department of Data Science New Jersey Institute of Technology NewarkNJ United States Department of Electrical Computer and Systems Engineering Rensselaer Polytechnic Institute TroyNY United States IBM Thomas J.Watson Research Center IBM Research Yorktown HeightsNY United States

This paper studies the transfer reinforcement learning (RL) problem where multiple RL problems have different reward functions but share the same underlying transition *** this setting, the Q-function of each RL problem (task) can be decomposed into a successor feature (SF) and a reward mapping: the former characterizes the transition dynamics, and the latter characterizes the task-specific reward *** Q-function decomposition, coupled with a policy improvement operator known as generalized policy improvement (GPI), reduces the sample complexity of finding the optimal Q-function, and thus the SF & GPI framework exhibits promising empirical performance compared to traditional RL methods like ***, its theoretical foundations remain largely unestablished, especially when learning the successor features using deep neural networks (SF-DQN).This paper studies the provable knowledge transfer using SFs-DQN in transfer RL *** establish the first convergence analysis with provable generalization guarantees for SF-DQN with *** theory reveals that SF-DQN with GPI outperforms conventional RL approaches, such as deep Q-network, in terms of both faster convergence rate and better *** experiments on real and synthetic RL tasks support the superior performance of SF-DQN & GPI, aligning with our theoretical findings. Copyright 2024 by the author(s)

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Reconfigurable Two-tap Microwave Photonic Filter based on A Dual-input Machzehnder Modulator 5

A Reconfigurable Two-tap Microwave Photonic Filter based on ...

引用

5th International Conference on Electronics and Communication, Network and computer Technology, ECNCT 2023

作者： Wang, Lin Chen, Bijuan Cao, Yuan Chen, Rongjun Zhaoqing University School of Electronic and Electrical Engineering Zhaoqing China Guangdong Institute of Modern Agricultural Equipment Guangzhou China Jinan University Institute of Photonics Technology Guangzhou China Guangdong Polytechnic Normal University Academy of Computer Science Guangzhou China

ISBN: (纸本)9798350328660

A novel reconfigurable two-tap microwave photonics filter with switchable positive and negative coefficient is proposed and experimentally demonstrated. The filter uses a dual-input modulator and an optical switching to adjust the filter coefficient. By controlling the two optical carriers into the same or different input ports of the modulator, a positive or negative two-tap microwave photonic filter can be achieved. Experimental results have shown that the reconfigurable microwave photonics filter can be switched between positive and negative coefficient. This innovative filter design has the advantages of simple configuration and arbitrary adjustable with a wideband operating range. © 2023 IEEE.

关键词： Microwave photonics

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：