检索结果-内蒙古大学图书馆

A Decentralized Communication Framework Based on Dual-Level Recurrence for Multiagent Reinforcement Learning

IEEE Transactions on Cognitive and Developmental Systems 2024年第2期16卷 640-649页

作者： Li, Xuesi Li, Jingchen Shi, Haobin Hwang, Kao-Shing Northwestern Polytechnical University School of Computer Science and Engineering Xi'an710129 China National Sun Yat-sen University Department of Electrical Engineering Kaohsiung804 Taiwan

Designing communication channels for multiagent is a feasible method to conduct decentralized learning, especially in partially observable environments or large-scale multiagent systems. In this work, a communication model with dual-level recurrence is developed to provide a more efficient communication mechanism for the multiagent reinforcement learning field. The communications are conducted by a gated-attention-based recurrent network, in which the historical states are taken into account and regarded as the second-level recurrence. We separate communication messages from memories in the recurrent model so that the proposed communication flow can adapt changeable communication objects in the case of limited communication, and the communication results are fair to every agent. We provide a sufficient discussion about our method in both partially observable and fully observable environments. The results of several experiments suggest our method outperforms the existing decentralized communication frameworks and the corresponding centralized training method. © 2016 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Towards a lightweight security framework using blockchain and machine learning

引用

Blockchain(Research and Applications) 2024年第1期5卷 107-118页

作者： Shereen Ismail Muhammad Nouman Diana W.Dawoud Hassan Reza School of Electrical Engineering and Computer Science University of North DakotaND 58202USA Department of Computer Science COMSATS University IslamabadIslamabad 44000Pakistan College of Engineering and Information Technology University of DubaiDubaiUnited Arab Emirates

Cyber-attacks pose a significant challenge to the security of Internet of Things(IoT)sensor networks,necessitating the development of robust countermeasures tailored to their unique characteristics and *** prevention and detection techniques have been proposed to mitigate these *** this paper,we propose an integrated security framework using blockchain and Machine Learning(ML)to protect IoT sensor *** framework consists of two modules:a blockchain prevention module and an ML detection *** blockchain prevention module has two lightweight mechanisms:identity management and trust *** management employs a lightweight Smart Contract(SC)to manage node registration and authentication,ensuring that unauthorized entities are prohibited from engaging in any tasks,while trust management uses a lightweight SC that is responsible for maintaining trust and credibility between sensor nodes throughout the network’s lifetime and tracking historical node *** and transaction validation are achieved through a Verifiable Byzantine Fault Tolerance(VBFT)mechanism to ensure network reliability and *** ML detection module utilizes the Light Gradient Boosting Machine(LightGBM)algorithm to classify malicious nodes and notify the blockchain network if it must make decisions to mitigate their *** investigate the performance of several off-the-shelf ML algorithms,including Logistic Regression,Complement Naive Bayes,Nearest Centroid,and Stacking,using the WSN-DS *** is selected following a detailed comparative analysis conducted using accuracy,precision,recall,F1-score,processing time,training time,prediction time,computational complexity,and Matthews Correlation Coefficient(MCC)evaluation metrics.

关键词： Blockchain Machine learning IoT Security Integration Smart contracts

来源：评论

学校读者我要写书评

暂无评论

PIDSNeRF: pose interpolation depth supervision neural radiance fields for view synthesis from challenging input

引用

Multimedia Tools and Applications 2024年 1-21页

作者： Wang, Jianxin Shao, Haijian Deng, Xing Jiang, Yingtao School of Computer Jiangsu University of Science and Technology Jiangsu Zhenjiang212003 China Department of Electrical and Computer Engineering University of Nevada Las VegasNV89154 United States

Recently, Neural Radiance Fields(NeRF) have shown remarkable performance in the task of novel view synthesis through multi-view. The present study introduces an advanced optimization framework, termed Pose Interpolation Depth Supervision Neural Radiance Fields (PIDSNeRF), designed to address the challenges encountered by NeRF in novel view synthesis. These challenges manifest as artifacts, texture details loss, and geometric inconsistencies, particularly in scenes characterized by different lighting conditions, Textureless regions, and sparse images as inputs. The principle of PIDSNeRF involves interpolating virtual camera positions in the 3D space domain based on known cameras, Subsequently, the sparse point clouds formed during camera pose estimation is re-projected onto these virtual poses, employing an inverse angle weighting strategy, thereby generating depth-supervised rays. Furthermore, we propose a depth diffusion method that spreads depth-supervised rays along the pixel plane, forming Gaussian functions with different variances based on the diffusion distances. Finally, depth supervision during volume rendering is achieved by optimizing the Kullback-Leibler(KL) divergence between the weight distribution of sampled points along each ray and the probability density function of the corresponding Gaussian function along that ray. The above process enables a more comprehensive optimization of multi-resolution grid features that align with the sampled points along the rays. The experiments on the DTU, LLFF, and DL3DV-10K datasets demonstrate, PIDSNeRF can synthesize complete novel views within minutes, and the various metrics of the synthesized images achieve the best performance. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Probability density function

来源：评论

学校读者我要写书评

暂无评论

Heat Transfer Area Optimization for Heat Exchanger System

引用

computer Modeling in engineering & sciences 2025年第4期143卷 335-349页

作者： Yu-Cheng Liao Fu-I Chou Po-Yuan Yang Jyh-Horng Chou Department of Electrical Engineering National Kaohsiung University of Science and TechnologyKaohsiung807Taiwan Department of Intelligent Robotics National Pingtung UniversityPingtung900Taiwan Department of Mechanical and Computer-Aided Engineering Feng Chia UniversityTaichung407Taiwan

This paper presents an allowable-tolerance-based group search optimization(AT-GSO),which combines the robust GSO(R-GSO)and the external quality design planning of the Taguchi ***-GSO algorithm is used to optimize the heat transfer area of the heat exchanger *** R-GSO algorithm integrates the GSO algorithm with the Taguchi method,utilizing the Taguchi method to determine the optimal producer in each iteration of the GSO algorithm to strengthen the robustness of the search process and the ability to find the global *** conventional parameter design optimization,it is typically assumed that the designed parameters can be applied accurately and consistently throughout ***,for systems that are sensitive to changes in design parameters,even minor inaccuracies can substantially reduce overall system ***,the permissible variations of the design parameters are considered in the tolerance-optimized design to ensure the robustness of the *** optimized design of the heat exchanger system assumes that the system’s operating temperature parameters are ***,fixing the systemoperating temperature parameters at a constant value is *** paper assumes that the system operating temperature parameters have an uncertainty error when optimizing the heat transfer area of the heat exchanger *** results show that the AT-GSO algorithm optimizes the heat exchanger system and finds the optimal operating temperature in the absence of tolerance and under three tolerance conditions.

关键词： Heat exchanger system allowable tolerance-based group search optimization Taguchi method tolerance design

来源：评论

学校读者我要写书评

暂无评论

RMR-Efficient Detectable Objects for Persistent Memory and Their Applications 28

RMR-Efficient Detectable Objects for Persistent Memory and T...

引用

28th International Conference on Principles of Distributed Systems, OPODIS 2024

作者： Dhoked, Sahil Fahmy, Ahmed Golab, Wojciech Mittal, Neeraj Department of Computer Science The University of Texas DallasTX United States Department of Electrical and Computer Engineering University of Waterloo Canada

ISBN: (纸本)9783959773607

We describe a novel construction of arbitrary read-modify-write (RMW) primitives in a persistent shared memory model with process failures. Our construction uses blocking synchronization, in the form of recoverable mutual exclusion (RME), and is optimal in terms of the widely studied remote memory reference (RMR) complexity measure. The implemented objects tolerate either system-wide or independent process crashes, depending on the RME lock used, and also provide detectability for resolving the outcome of operations interrupted by failures. We prove that our construction is RMR-optimal using a reduction back to the RME problem. Our proof technique introduces a novel algorithmic style that enables solving challenging synchronization problems using a common execution path for both the system-wide and independent failure models, which previously required separate analyses, and relies only on a suitable implementation of the detectable base objects in each model to achieve RMR efficiency. Experiments demonstrate that our construction outperforms prior wait-free and lock-free algorithms on a multiprocessor with Intel Optane persistent memory. © Sahil Dhoked, Ahmed Fahmy, Wojciech Golab, and Neeraj Mittal.

关键词： Synchronization

来源：评论

学校读者我要写书评

暂无评论

Defocus blur detection using novel local directional mean patterns(LDMP)and segmentation via KNN matting

引用

Frontiers of computer science 2022年第2期16卷 110-122页

作者： Awais KHAN Aun IRTAZA Ali JAVED Tahira NAZIR Hafiz MALIK Khalid Mahmood MALIK Muhammad Ammar KHAN Department of Computer Science University of Engineering and TechnologyTaxila 47050Pakistan Department of Electrical and Computer Engineering University of MichiganDearbornMI 48128USA Department of Software Engineering University of Engineering and TechnologyTaxila 47050Pakistan Department of Computer Science and Engineering Oakland UniversityMI 48309USA

Detection and segmentation of defocus blur is a challenging task in digital imaging applications as the blurry images comprise of blur and sharp regions that wrap significant information and require effective methods for information *** defocus blur detection and segmentation methods have several limitations i.e.,discriminating sharp smooth and blurred smooth regions,low recognition rate in noisy images,and high computational cost without having any prior knowledge of images i.e.,blur degree and camera ***,there exists a dire need to develop an effective method for defocus blur detection,and segmentation robust to the above-mentioned *** paper presents a novel features descriptor local directional mean patterns(LDMP)for defocus blur detection and employ KNN matting over the detected LDMP-Trimap for the robust segmentation of sharp and blur *** argue/hypothesize that most of the image fields located in blurry regions have significantly less specific local patterns than those in the sharp regions,therefore,proposed LDMP features descriptor should reliably detect the defocus blurred *** fusion of LDMP features with KNN matting provides superior performance in terms of obtaining high-quality segmented regions in the ***,the proposed LDMP features descriptor is robust to noise and successfully detects defocus blur in high-dense noisy *** results on Shi and Zhao datasets demonstrate the effectiveness of the proposed method in terms of defocus blur *** and comparative analysis signify that our method achieves superior segmentation performance and low computational cost of 15 seconds.

关键词： defocus blur detection local directional mean patterns image matting sharpness metrics blur segmentation

来源：评论

学校读者我要写书评

暂无评论

Entanglement-Controlled Quantum Federated Learning

引用

IEEE Internet of Things Journal 2025年第11期12卷 18318-18330页

作者： Park, Soohyun Lee, Hyunsoo Jung, Soyi Park, Jihong Bennis, Mehdi Kim, Joongheon Sookmyung Women’s University Division of Computer Science Seoul04310 Korea Republic of Korea University Department of Electrical and Computer Engineering Seoul02841 Korea Republic of Ajou University Department of Electrical and Computer Engineering Suwon16499 Korea Republic of Pillar Tampines Singapore University of Oulu Centre for Wireless Communications Oulu90014 Finland

According to the advances in quantum computing and distributed learning, quantum federated learning (QFL) has recently become an emerging field of study. In QFL, each quantum computer or device locally trains its quantum neural network (QNN) with trainable gates, and communicates only these gate parameters over classical channels, without costly quantum communications. To successfully opeate QFL under various and dynamic channel conditions in Internet of Things (IoT) environments, this article develops a novel depth-controllable architecture of entangled slimmable QNNs (eSQNNs), and thus, proposes an entangled slimmable QFL (eSQFL) that communicates the superposition-coded parameters of eSQNNs. Even though the proposed eSQNN-based eSQFL is superior, training the depth-controllable eSQNN architecture is challenging due to high-entanglement entropy and interdepth interference. Therefore, the proposed method in this article mitigates the interference using entanglement controlled universal (CU) gates and an inplace fidelity distillation (IPFD) regularizer penalizing interdepth quantum state differences, respectively. Furthermore, the proposed method optimizes the superposition coding power allocation by deriving and minimizing the convergence bound of eSQFL. The novelty of this work is evaluated via extensive simulations in terms of prediction accuracy, fidelity, and entropy compared to Vanilla QFL as well as under different channel conditions and various data distributions. © 2014 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

LRS: Enhancing Adversarial Transferability through Lipschitz Regularized Surrogate 38

LRS: Enhancing Adversarial Transferability through Lipschitz...

引用

38th AAAI Conference on Artificial Intelligence, AAAI 2024

作者： Wu, Tao Luo, Tie Wunsch, Donald C. Department of Computer Science Missouri University of Science and Technology United States Department of Electrical and Computer Engineering Missouri University of Science and Technology United States

ISBN: (纸本)1577358872

The transferability of adversarial examples is of central importance to transfer-based black-box adversarial attacks. Previous works for generating transferable adversarial examples focus on attacking given pretrained surrogate models while the connections between surrogate models and adversarial trasferability have been overlooked. In this paper, we propose Lipschitz Regularized Surrogate (LRS) for transfer-based black-box attacks, a novel approach that transforms surrogate models towards favorable adversarial transferability. Using such transformed surrogate models, any existing transfer-based black-box attack can run without any change, yet achieving much better performance. Specifically, we impose Lipschitz regularization on the loss landscape of surrogate models to enable a smoother and more controlled optimization process for generating more transferable adversarial examples. In addition, this paper also sheds light on the connection between the inner properties of surrogate models and adversarial transferability, where three factors are identified: smaller local Lipschitz constant, smoother loss landscape, and stronger adversarial robustness. We evaluate our proposed LRS approach by attacking state-of-the-art standard deep neural networks and defense models. The results demonstrate significant improvement on the attack success rates and transferability. Our code is available at https://***/TrustAIoT/LRS. Copyright © 2024, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Electricity demand forecasting at distribution and household levels using explainable causal graph neural network

引用

Energy and AI 2024年第2期16卷 385-395页

作者： Amir Miraki Pekka Parviainen Reza Arghandeh Department of Computer Science Electrical Engineering and Mathematical SciencesWestern Norway University of Applied SciencesBergenNorway Department of Informatics University of BergenBergenNorway

Forecasting electricity demand is an essential part of the smart grid to ensure a stable and reliable power grid. With the increasing integration of renewable energy resources into the grid, forecasting the demand for electricity is critical at all levels, from the distribution to the household. Most existing forecasting methods, however, can be considered black-box models as a result of deep digitalization enablers, such as deep neural networks, which remain difficult to interpret by humans. Moreover, capture of the inter-dependencies among variables presents a significant challenge for multivariate time series forecasting. In this paper we propose eXplainable Causal Graph Neural Network (X-CGNN) for multivariate electricity demand forecasting that overcomes these limitations. As part of this method, we have intrinsic and global explanations based on causal inferences as well as local explanations based on post-hoc analyses. We have performed extensive validation on two real-world electricity demand datasets from both the household and distribution levels to demonstrate that our proposed method achieves state-of-the-art performance.

关键词： Causal inference Electricity demand forecasting Explainable artificial intelligence(XAI) Graph neural network

来源：评论

学校读者我要写书评

暂无评论

Ant Colony Optimization-Based Path Planning for Autonomous Vehicle Navigation Systems 4

Ant Colony Optimization-Based Path Planning for Autonomous V...

引用

4th International Conference on electrical engineering and computer science, ICECOS 2024

作者： Sari, Desi Windi Dwijayanti, Suci Suprapto, Bhakti Yudho Universitas Sriwijaya Faculty of Engineering Department of Electrical Engineering Doctoral Program in Engineering Science Palembang Indonesia Universitas Sriwijaya Faculty of Engineering Department of Electrical Engineering Palembang Indonesia

ISBN: (纸本)9798350368253

A crucial aspect of autonomous vehicles is path planning, which involves using various algorithms to determine the most efficient routes. This study investigates the application of the Ant Colony Optimization (ACO) algorithm to create a system for identifying the shortest path. The process includes collecting coordinate data from specific test locations on the Universitas Sriwijaya Indralaya campus to generate a graph-based map for analysis. The study begins with gathering route data through the Google Maps application, which includes 182 routes. In simulation tests, the routes generated by ACO differ from those suggested by Google Maps;sometimes, the ACO route is longer and sometimes shorter, due to the probabilistic nature of the ACO algorithm in finding optimal routes. The average error compared to Google Maps is 11.7 meters. Additional tests introduce obstacles on the road, requiring the system to find alternative routes. For instance, the initial route from the auditorium to the Faculty of science and Math is 38-39-11-53-110-54-111 with a route length of 670 m. After adding a roadblock in front of the Faculty of engineering, the route changes to 38-39-116-40-70-69-56-111, with a route length of 730 meters. These tests demonstrate that the ACO algorithm effectively identifies the best routes for autonomous vehicles, both under normal conditions and when obstacles are present. © 2024 IEEE.

关键词： Ant colony optimization

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：