检索结果-内蒙古大学图书馆

2nd International Scientific Conference on Metrological Support of Innovative Technologies, ICMSIT II-2021

作者： Lantsov, V.N. Computer Engineering and System Control Department Vladimir State University Named after Alexander and Nikolay Stoletovs Gorky Str. 87 Vladimir600000 Russia

Tensor decomposition methods are widely used for solving high-dimensional and multi-dimensional problems. These approaches have a huge potential for reducing computational costs in the simulation of electronic circuits and in the CAD systems for electronics. Simulation of modern radio-frequency (RF) circuits, especially for RF integrated circuits, is one of the areas of extensive scientific research and development. The main problem of analysis methods for circuit design of RF electronics is the significant computational costs associated with the high dimensions to be solved. This paper shows that the computational costs of circuit design are largely determined by the costs of solving a system of linear algebraic equations (SLAE). The problems of the solving of SLAE are indicated in the paper. Further development of methods for solving and reducing computational costs requires the use of new approaches, one of which is proposed in this paper. The article presents the developed algorithm for converting a second-order matrix into a higher-order tensor. In this paper algorithms and software tools for tensor decompositions, as well as methods for solving SLAE in the representation of equations in tensor format are investigated. The results of numerical experiments and the results of comparison with traditional methods are presented. © Published under licence by IOP Publishing Ltd.

关键词： Cost reduction

来源：评论

学校读者我要写书评

暂无评论

Intelligent trust path search 13

Intelligent trust path search

引用

13th International Congress on Image and Signal Processing, BioMedical engineering and Informatics, CISP-BMEI 2020

作者： Che, Jiaying Tong, Xiangrong Kong, Ru Yantai University School Computer and Control Engineering Yantai264005 China

ISBN: (纸本)9780738105451

In internet age, the interaction among people becomes more and more frequent. Therefore, the trust relationships between people are becoming more and more important. So it has become one of the hot spots in the research of multi-agent systems and trust path search. Trust network is established based on the transitivity of trust, and it is useful to use the network to evaluate the trust between two indirectly connected users on the reliable path. Aggregating trust of all possible trust paths can improve the accuracy of trust inference, so it is necessary to extend the problem of finding a single path to multiple trust paths. This paper mainly summarizes the study of trust path search and comprises four parts: the basic study of trust and trust network;some kinds of heuristic search algorithms including unidirectional and bidirectional searching for the shortest path, single-agent and multi-agent searching for multiple paths;the researches on path search based on trust;and the future directions of trust path search. © 2020 IEEE.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Adaptability Evaluation of Energy Storage Working Conditions in Different Application Scenarios 4

Adaptability Evaluation of Energy Storage Working Conditions...

引用

4th International Conference on Energy, Electrical and Power engineering, CEEPE 2021

作者： Li, Yuxing Lu, Yu Li, Hao Wang, Dong Mu, Zhiguo Han, Xiaojuan State Grid Jilin Province Economic Research Institute Changchun China North China Electric Power University School of Control and Computer Engineering Beijing China

ISBN: (纸本)9781665433631

Aiming at the lack of standard evaluation system for the planning of energy storage power stations under multiple application scenarios of renewable energy connected to the grid, this paper proposes a planning method of energy storage power stations under multiple application scenarios based on objective weighting method. According to the characteristic and cost technology indicators of different energy storage batteries, an evaluation system of the selection for energy storage batteries under multiple application scenarios based on multi-objective and multi-attribute is established, and the weight and adaptability index \chi of various energy storage batteries are calculated by the CRITIC method. The validity and correctness of the proposed method are verified by a simulation example, and Lithium-titanate battery (LTB) is currently the most suitable energy storage system for power smoothing and tracking planned output applications. The method proposed in this paper provides a theoretical basis for the planning of energy storage power stations under multiple application scenarios. © 2021 IEEE.

关键词： Lithium compounds

来源：评论

学校读者我要写书评

暂无评论

Multi-Level Single Event Effect-hardened Design for SRAM-FPGA-Based System

Multi-Level Single Event Effect-hardened Design for SRAM-FPG...

引用

International Conference on Reliability, Maintainability and Safety,ICRMS

作者： Wenbin Zhang Peng Li Peng Guo Yifan Chen Technology and Engineering Center for Space Utilization Chinese Academy of Sciences Beijing P.R. China School of Control and Computer Engineering North China Electric Power University Beijing P.R. China

ISBN: (数字)9798350329988

ISBN: (纸本)9798350329995

Commercial off-the-shelf (COTS) static random-access memory (SRAM) based Field-programmable gate arrays (FPGAs) technology has been widely used within the space industry due to its cost-effectiveness and high-performance attributes. However, its original design primarily caters to benign operating environments. The deleterious impact of space radiation, particularly the single-event effect (SEE), poses a significant threat to the operational reliability of SRAM-FPGA devices in space applications. In order to fortify these devices against the challenges of the space radiation environment and ensure the utmost system reliability, this paper initiates by providing an overview of the SEE-related issues pertaining to SRAM-FPGA and offers insights into general hardening design solutions. Subsequently, this paper introduces a comprehensive multilevel SEE hardening design strategy, encompassing component selection, as well as hardware and software hardening methods at the board-level. Furthermore, it delves into system-level design protective measures. A real-world case study is presented to exemplify the practical implementation of these hardening techniques that enhance system reliability.

关键词： Radiation hardening (electronics) Prevention and mitigation Design methodology Space radiation Reliability engineering Software Hardware Reliability Integrated circuit reliability Field programmable gate arrays

来源：评论

学校读者我要写书评

暂无评论

Neuro-symbolic Empowered Denoising Diffusion Probabilistic Models for Real-time Anomaly Detection in Industry 4.0

arXiv

引用

arXiv 2023年

作者： Capogrosso, Luigi Mascolini, Alessio Girella, Federico Skenderi, Geri Gaiardelli, Sebastiano Dall’Ora, Nicola Ponzio, Francesco Fraccaroli, Enrico Di Cataldo, Santa Vinco, Sara Macii, Enrico Fummi, Franco Cristani, Marco Dept. of Engineering for Innovation Medicine University of Verona Italy Dept. of Control and Computer Engineering Polytechnic of Turin Italy Dept. of Regional and Urban Studies and Planning Polytechnic of Turin Italy Dept. of Computer Science University of North Carolina Chapel Hill United States

Industry 4.0 involves the integration of digital technologies, such as IoT, Big Data, and AI, into manufacturing and industrial processes to increase efficiency and productivity. As these technologies become more interconnected and interdependent, Industry 4.0 systems become more complex, which brings the difficulty of identifying and stopping anomalies that may cause disturbances in the manufacturing process. This paper aims to propose a diffusion-based model for real-time anomaly prediction in Industry 4.0 processes. Using a neuro-symbolic approach, we integrate industrial ontologies in the model, thereby adding formal knowledge on smart manufacturing. Finally, we propose a simple yet effective way of distilling diffusion models through Random Fourier Features for deployment on an embedded system for direct integration into the manufacturing process. To the best of our knowledge, this approach has never been explored before. © 2023, CC BY.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Locally Differentially Private Online Federated Learning With Correlated Noise

arXiv

引用

arXiv 2024年

作者： Zhang, Jiaojiao Zhu, Linglingzhi Fay, Dominik Johansson, Mikael Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology StockholmSE-100 44 Sweden H. Milton Stewart School of Industrial and Systems Engineering Georgia Institute of Technology AtlantaGA United States

We introduce a locally differentially private (LDP) algorithm for online federated learning that employs temporally correlated noise to improve utility while preserving privacy. To address challenges posed by the correlated noise and local updates with streaming non-IID data, we develop a perturbed iterate analysis that controls the impact of the noise on the utility. Moreover, we demonstrate how the drift errors from local updates can be effectively managed for several classes of nonconvex loss functions. Subject to an (ϵ,δ)-LDP budget, we establish a dynamic regret bound that quantifies the impact of key parameters and the intensity of changes in the dynamic environment on the learning performance. Numerical experiments confirm the efficacy of the proposed algorithm. © 2024, CC BY.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Enhancing 6G-Satellite Network Integration with Artificial Intelligence: A Future Communication Paradigm

Enhancing 6G-Satellite Network Integration with Artificial I...

引用

Learning and Technology Conference (L&T)

作者： Ibrahim Salah Aziza I. Hussein Mostafa Wageh Lotfy Mohamed Mourad Mabrook Control and Computer Department College of Engineering Almaaqal University Basrah Iraq College of Engineering Energy and Technology Research Center Effat University Saudi Arabia Dept. of Process Control Technology Faculty of Technology and Education Beni-Suef University Beni-Suef Egypt Space Communication Dept. Faculty of Navigation Science & Space Technology Beni-Suef University Beni-Suef Egypt

ISBN: (数字)9798331532215

ISBN: (纸本)9798331532222

The integration of 6G networks and satellite communications is set to revolutionize global connectivity, offering seamless coverage across terrestrial and non-terrestrial environments. Artificial Intelligence (AI) is essential for improving this integration, addressing challenges such as dynamic resource management, latency reduction, and network optimization. AI techniques like machine learning, deep learning, and reinforcement learning offer innovative solutions to handle the complexities of 6G-satellite networks. These advancements promise to significantly improve network efficiency, enhance data transmission reliability, and ensure seamless connectivity across different areas. Potential use cases include smart cities, autonomous vehicles, and Internet of Things (IoT) applications, where AI-driven 6G-satellite integration will be crucial. The proposed AI-enhanced 6G-satellite framework not only addresses current challenges but also lays the groundwork for a resilient, scalable, and globally interconnected communication infrastructure, offering a promising future.

关键词： 6G mobile communication Wireless communication Smart cities Resource management Reliability Internet of Things Stakeholders Artificial intelligence Vehicle dynamics Satellite communications

来源：评论

学校读者我要写书评

暂无评论

DEEPCON: Improving Distributed Deep Learning Model Consistency in Edge-Cloud Environments via Distillation

引用

IEEE Transactions on Cognitive Communications and Networking 2025年

作者： Qian, Bin Qian, Jiaxu Wen, Zhenyu Wu, Di He, Shibo Chen, Jiming Ranjan, Rajiv Zhejiang University State Key Laboratory of Industrial Control Technology Hangzhou China Zhejiang University of Technology Institute of Cyberspace Security College of Information Engineering Hangzhou China University of St Andrews School of Computer Science United Kingdom Newcastle University United Kingdom

In a typical distributed Deep Learning (DL) based application, models are configured differently to meet the requirements of resource constraints. For instance, a large ResNet56 model is deployed on the cloud server while a small lightweight MobileNet model is more suitable for the end-user device with fewer computation resources. However, the heterogeneity of the model architectures and configurations may bring a systemic problem -models may produce different outputs when given the same input. This inconsistency problem may cause severe system failure of prediction agreement inside the application. Current research has not studied the systemic design for efficiently detecting and reducing the inconsistency among models in distributed DL applications. With the increasing scale of distributed DL applications, the challenges of inconsistency mitigation should consider both algorithm and system design. To this end, we design and implement DEEPCON, an adaptive deployment system across the edge-cloud layer with over-the-air model updates. We implement ASRS sampling for efficiently sampling data to reveal the real data distribution as well as model prediction inconsistency. Then, we implement DMML-Par, an asynchronous parallel training algorithm for quickly updating the models and reducing inconsistency. implements over-the-air updates with a set of APIS to enable seamless inconsistency detection and reduction in such deep learning applications. Our experiment results on both vision and language tasks demonstrate that DMML could improve the model consistency up to 4%, 7%, and 13% at CIFAR10/100 and IMDB datasets without sacrificing the accuracy of individual models. We also show that the ASRS sampling can save 90% network bandwidth of data transmission and that DMML-Par is up to 60% faster compared to simple synchronous parallel training. 2015 IEEE.

关键词： Distributed cloud

来源：评论

学校读者我要写书评

暂无评论

Classification of skin lesions using morpho-granulometry features derived from color clusters

Classification of skin lesions using morpho-granulometry fea...

引用

International Conference on System Theory, control, and Computing (ICSTCC)

作者： Gigi Tăbăcaru Simona Moldovanu Marian Barbu Department of Automatic Control and Electrical Engineering Faculty of Automation Computers Electrical Engineering and Electronics "Dunarea de Jos" University of Galati Galati Romania Computer Science and Information Technology Faculty of Automation Computers Electrical Engineering and Electronics The Modelling & Simulation Laboratory "Dunarea de Jos" University of Galati Galati Romania

ISBN: (数字)9798350364293

ISBN: (纸本)9798350364309

The skin lesion can be thought of as a biological system, so the morpho-granulometry of significant color clusters found in skin lesions is one of the elements that reproduce in a natural way the structure of the lesion, this novelty is highlighted in this study. Important features of skin lesions can be modulated by fusing neural networks (NN) and machine learning (ML). By choosing the nevus and melanoma classes, the primary goal was accomplished, and three databases were used to test the methodology. The characteristics based on morpho-granulometry allowed for the identification of microstructure within the images, which can be very helpful in characterizing the biological system. Based on random forest (RF) and extreme gradient boosting (XGboost) classifiers, this work aimed to improve the classification performance of important feature selection. The selected features from three free image databases with three NNs were classified. In a binary classification of nevus vs. melanoma, the results showed that the pattern recognition neural network (PRNN), according to the PH2 database, provided an accuracy of 0.923 and an F1-score of 0.876. The classification is interpretable if it is not validated. In our study, the best results were verified with a logistic regression (LR) classifier.

关键词： Accuracy Recurrent neural networks Image color analysis Melanoma Biological systems Artificial neural networks Feature extraction Skin Lesions Classification tree analysis

来源：评论

学校读者我要写书评

暂无评论

Investigating Prediction Accuracy of Full Reference Objective Video Quality Measures through the ITS4S Dataset

Investigating Prediction Accuracy of Full Reference Objectiv...

引用

2020 Human Vision and Electronic Imaging Conference, HVEI 2020

作者： Tiotsop, Lohic Fotio Servetti, Antonio Masala, Enrico Control and Computer Engineering Department Politecnico di Torino Torino Italy

Large subjectively annotated datasets are crucial to the development and testing of objective video quality measures (VQMs). In this work we focus on the recently released ITS4S dataset. Relying on statistical tools, we show that the content of the dataset is rather heterogeneous from the point of view of quality assessment. Such diversity naturally makes the dataset a worthy asset to validate the accuracy of video quality metrics (VQMs). In particular we study the ability of VQMs to model the reduction or the increase of the visibility of distortion due to the spatial activity in the content. The study reveals that VQMs are likely to overestimate the perceived quality of processed video sequences whose source is characterized by few spatial details. We then propose an approach aiming at modeling the impact of spatial activity on distortion visibility when objectively assessing the visual quality of a content. The effectiveness of the proposal is validated on the ITS4S dataset as well as on the Netflix public dataset. © 2020 Society for Imaging Science and Technology. All rights reserved.

关键词： Visibility

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：