检索结果-内蒙古大学图书馆

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Feng, Chen Liu, Ziquan Zhi, Zhuo Bogunovic, Ilija Gerner-Beuerle, Carsten Rodrigues, Miguel Department of Electronic and Electrical Engineering University College London United Kingdom School of Electronic Engineering and Computer Science Queen Mary University of London United Kingdom Faculty of Laws University College London United Kingdom AI Centre Department of Electronic and Electrical Engineering University College London United Kingdom

ISBN: (纸本)157735897X

It is widely known that state-of-the-art machine learning models, including vision and language models, can be seriously compromised by adversarial perturbations. It is therefore increasingly relevant to develop capabilities to certify their performance in the presence of the most effective adversarial attacks. Our paper offers a new approach to certify the performance of machine learning models in the presence of adversarial attacks with population level risk guarantees. In particular, we introduce the notion of (α, ζ)-safe machine learning model. We propose a hypothesis testing procedure, based on the availability of a calibration set, to derive statistical guarantees providing that the probability of declaring that the adversarial (population) risk of a machine learning model is less than α (i.e. the model is safe), while the model is in fact unsafe (i.e. the model adversarial population risk is higher than α), is less than ζ. We also propose Bayesian optimization algorithms to determine efficiently whether a machine learning model is (α, ζ)-safe in the presence of an adversarial attack, along with statistical guarantees. We apply our framework to a range of machine learning models - including various sizes of vision Transformer (ViT) and ResNet models - impaired by a variety of adversarial attacks, such as PGDAttack, MomentumAttack, GenAttack and BanditAttack, to illustrate the operation of our approach. Importantly, we show that ViT’s are generally more robust to adversarial attacks than ResNets, and large models are generally more robust than smaller models. Our approach goes beyond existing empirical adversarial risk-based certification guarantees. It formulates rigorous (and provable) performance guarantees that can be used to satisfy regulatory requirements mandating the use of state-of-the-art technical tools. © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

OpenAI-Powered NLP for SQL Generation: Enhancing Database Access for Non-Technical Users

OpenAI-Powered NLP for SQL Generation: Enhancing Database Ac...

引用

International ECTI Northern Section Conference on electrical, Electronics, computer and Telecommunications engineering (ECTI-NCON)

作者： Yuenyong Nilsiam Piyaphiphat Khammaw Siranee Nuchitprasitchai Department of Electrical and Computer Engineering Faculty of Engineering King Mongkut’s University of Technology North Bangkok Bangkok Thailand Department of Information Technology Faculty of Information Technology and Digital Innovation King Mongkut’s University of Technology North Bangkok Bangkok Thailand

ISBN: (数字)9798331543273

ISBN: (纸本)9798331543280

Database accessibility can be challenging for users without technical expertise, particularly when generating SQL queries to retrieve information. This study addresses this gap by developing an OpenAI-powered system designed to automate SQL command generation, enabling non-expert users to interact with databases using natural language. Implemented as a web application, the system was evaluated by expert users, assessing both performance in query accuracy and user satisfaction. Results indicate high usability and satisfaction scores, with the system effectively enhancing accessibility to database functions, thus providing a user-friendly solution for database management.

关键词： Structured Query Language Accuracy Translation Databases Decision making Data structures User experience Systems support Usability Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

A Unified Framework for Guiding Generative AI with Wireless Perception in Resource Constrained Mobile Edge Networks

arXiv

引用

arXiv 2023年

作者： Wang, Jiacheng Du, Hongyang Niyato, Dusit Kang, Jiawen Xiong, Zehui Rajan, Deepu Mao, Shiwen Shen, Xuemin The School of Computer Science and Engineering Nanyang Technological University Singapore The School of Automation Guangdong University of Technology China The Pillar of Information Systems Technology and Design Singapore University of Technology and Design Singapore The Department of Electrical and Computer Engineering Auburn University Auburn United States The Department of Electrical and Computer Engineering University of Waterloo Canada

With the significant advancements in artificial intelligence (AI) technologies and powerful computational capabilities, generative AI (GAI) has become a pivotal digital content generation technique for offering superior digital services. However, directing GAI towards desired outputs still suffer the inherent instability of the AI model. In this paper, we design a novel framework that utilizes wireless perception to guide GAI (WiPe-GAI) for providing digital content generation service, i.e., AI-generated content (AIGC), in resource-constrained mobile edge networks. Specifically, we first propose a new sequential multi-scale perception (SMSP) algorithm to predict user skeleton based on the channel state information (CSI) extracted from wireless signals. This prediction then guides GAI to provide users with AIGC, such as virtual character generation. To ensure the efficient operation of the proposed framework in resource constrained networks, we further design a pricing-based incentive mechanism and introduce a diffusion model based approach to generate an optimal pricing strategy for the service provisioning. The strategy maximizes the user’s utility while enhancing the participation of the virtual service provider (VSP) in AIGC provision. The experimental results demonstrate the effectiveness of the designed framework in terms of skeleton prediction and optimal pricing strategy generation comparing with other existing solutions. © 2023, CC BY.

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

A Hybrid-Logic Scheme for High-Performance and Low-Power Decoders in 7nm Process

A Hybrid-Logic Scheme for High-Performance and Low-Power Dec...

引用

International Conference on Solid-State and Integrated Circuit Technology

作者： Donghao Xia Yuejun Zhang Mengfan Xu Liang Wen Yiting Guo Faculty of Electrical Engineering and Computer Science Ningbo University Zhejiang China Department of Electronic Technology China Coast Guard Academy Ningbo China

ISBN: (数字)9798350361834

ISBN: (纸本)9798350361841

Advancing memory circuitry has heightened the performance criteria for memory in diverse chip applications. Decoders, serving as peripheral circuits to memory devices, have be a prominent area of academic interest. The new NAND/NOR gate circuits are proposed using pass-transistor logic (PTL) and transmission gate logic (TGL). The two hybrid-logic design schemes of high-performance and low-power (HPLP) and HPLP inverting (HPLPI) utilizing PTL and TGL gate in combination with static CMOS logic for decoders are proposed, while achieving fewer transistors, faster speed, lower power dissipation as compared to conventional circuits. Experiments are conducted in TSMC 7nm FinFET process for hybrid-logic decoders. The simulation results indicate that, in comparison to conventional decoders, the proposed hybrid-logic 3–8 decoder demonstrates improvements, with the HPLP design reducing delay by over 19% and power by over 71%, and the HPLPI design reducing delay by over 17% and power by over 48%.

关键词： Performance evaluation Simulation Voltage Logic gates FinFETs Decoding Delays Power dissipation Transistors Logic

来源：评论

学校读者我要写书评

暂无评论

Reliability calculations based on an enhanced transformer life expectancy model

引用

Ain Shams engineering Journal 2022年第4期13卷

作者： Ibrahim, K. Sharkawy, R.M. Temraz, H.K. Salama, M.M.A. Electrical and Control Engineering Department Arab Academy for Science and Technology Cairo Egypt Electrical Power and Machines Engineering Department Faculty of Engineering-Ain Shams University Cairo Egypt Electrical and Computer Engineering Department University of Waterloo Waterloo Canada

In this paper, The IEEE thermal ageing model is utilized to build an enhanced Transformer Life Expectancy (TLE) model. The enhanced model is developed relying on the current transformer Health Index (HI) in addition to the loading conditions. A direct correlation between the IEEE and the (HI) ageing factors is identified and projected. The model is capable of integrating factors affecting transformers. Transformer faults and maintenance are amongst factors taken into consideration to improve the model. The reliability calculations are applied for assessing the transformers as well as the distribution network. The calculated transformer (HI) score with the aid of historical failure rate are utilized during the calculation of the distribution network reliability. An application on a simple network connectivity including transformers and loads is demonstrated to verify the strategy effectiveness. The results of this research are the basis for an enhancement for the smart grids performance estimation. © 2021 THE AUTHORS

关键词： Thermal aging

来源：评论

学校读者我要写书评

暂无评论

A Door Detection System for Convenience Stores in Taiwan

A Door Detection System for Convenience Stores in Taiwan

引用

2021 International Conference on computer System, Information Technology, and electrical engineering, COSITE 2021

作者： Thaipisutikul, Tipajin Prompol, Kanatip Lin, Chih-Yang Chang, Wen-Thong Muchtar, Kahlil Mahidol University Faculty of Information and Communication Technology Thailand Yuan Ze Universit College of Electrical and Communication Engineering Department of Electrical Engineering Taiwan Asia University Dept. of Computer Science and Information Engineering Taichung Taiwan Universitas Syiah Kuala Department of Electrical and Computer Engineering Aceh Indonesia

ISBN: (纸本)9781665425094

A door is a very substantial element since it enables a person to enter a target place. Though detecting a doorway is an easy task for a regular person, it is challenging for robots or visually impaired people. Although most existing deep learning object detection models have shown promising results, they have a limitation in distinguishing between glass doors and glass walls in a convenience store. To address this issue, we propose an effective door detection system for convenience stores in Taiwan. Our system consists of two main models: 1) the object detection and 2) the door bounding box models. The former model uses the re-train YOLOv4 as the main building box. The latter model uses a fully connected neural network as the main building box. In particular, we utilize the surrounding objects in the scene to improve the performance and robustness of convenient glass door entrance detection. The experimental results demonstrate that our proposed method not only achieves the quantitative accuracy result up to 93% but also provides decent qualitative results. © 2021 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Investigation of the Accuracy of Thermographic Inspections of Photovoltaic Modules 29

Investigation of the Accuracy of Thermographic Inspections o...

引用

29th IEEE International Symposium for Design and Technology in Electronic Packaging, SIITME 2023

作者： Evstatiev, Boris Valov, Nikolay Gabrovska-Evstatieva, Katerina Mladenova, Tsvetelina Mihailov, Nicolay University of Ruse 'Angel Kanchev' Department of Electronics Ruse Bulgaria University of Ruse 'Angel Kanchev' Department of Automation and Mechatronics Ruse Bulgaria University of Ruse 'Angel Kanchev' Department of Computer Science Ruse Bulgaria University of Ruse 'Angel Kanchev' Department of Computing Ruse Bulgaria University of Ruse 'Angel Kanchev' Department of Electrical Power Engineering Ruse Bulgaria

ISBN: (纸本)9798350344110

Remote inspections of photovoltaic installations are an important factor for taking timely measures to increase their efficiency and reduce degradation. This study deals with the accuracy and uncertainty of thermal measurements of PV cells. An experiment is organized in order to compare the measured temperatures with means of contact sensor and contactless infrared cameras from different distance. The obtained results indicate significant difference in the measured peak temperatures with the different means. Furthermore, the temperature gradient of an affected cell depends strongly on the soiling area and could surpass 40°C, which is a precondition for significant errors in the measured temperatures, i.e. it creates a significant uncertainty. Another important observation is that for the investigated polycrystalline module no hotspot was created if 6% or less of a cell's area is covered. © 2023 IEEE.

关键词： Cells

来源：评论

学校读者我要写书评

暂无评论

Joint Optimization of Microphone Array Geometry and Region-of-Interest Beamforming with Sparse Circular Sector Arrays

Joint Optimization of Microphone Array Geometry and Region-o...

引用

International Workshop on Acoustic Signal Enhancement (IWAENC)

作者： Gal Itzhak Simon Doclo Israel Cohen Faculty of Electrical & Computer Engineering Technion–Israel Institute of Technology Department of Medical Physics and Acoustics Carl Von Ossietzky Universität Oldenburg

ISBN: (数字)9798350361858

ISBN: (纸本)9798350361865

This paper focuses on two key aspects: region-of-interest beamforming and optimal sparse circular sector array design. The aim is to address the problem of the unknown direction of arrival within a given region of interest while optimizing the array geometry layout and beamformer taps. This is done while meeting the maximum broadband array directivity criterion. To ensure that the desired signal is not distorted, we apply appropriate optimization constraints while maintaining a sufficiently high white noise gain. Our proposed approach outperforms a recently suggested approach in terms of the directivity factor, especially when the direction of arrival of the desired source significantly deviates from its nominal value.

关键词： Geometry Direction-of-arrival estimation Acoustic distortion Array signal processing Layout White noise Acoustic arrays Microphone arrays Broadband communication Optimization

来源：评论

学校读者我要写书评

暂无评论

Towards Accurate Discretization of Arbitrary Right-Hand Side Excitations on Multiply-Connected Geometries 22

Towards Accurate Discretization of Arbitrary Right-Hand Side...

引用

22nd International Conference on Electromagnetics in Advanced Applications, ICEAA 2021

作者： Hofmann, Bernd Eibert, Thomas F. Andriulli, Francesco P. Adrian, Simon B. Technical University of Munich Chair of High-Frequency Engineering Department of Electrical and Computer Engineering Munich80290 Germany Politecnico di Torino Department of Electronics and Telecommunications Turin10129 Italy University of Rostock Institute of General Electrical Engineering Faculty of Computer Science and Electrical Engineering Rostock18059 Germany

ISBN: (纸本)9781665413862

For the computation of the field scattered by an object, integral equation formulations such as the electric field integral equation (EFIE), the magnetic field integral equation (MFIE), and the combined field integral equation (CFIE) are well-established techniques. They are flexible, accurate, and computationally efficient. They suffer, however, from different issues when the frequency becomes low: The EFIE and the CFIE become ill-conditioned. Furthermore, for the MFIE significant round-off errors prevent an accurate solution. As a remedy, a quasi¬Helmholtz decomposition of the surface current density into a loop-star or a loop-tree basis can be leveraged [1]. Even more suitable are quasi-Helmholtz projectors derived from the loop-star basis [2]. They avoid the introduction of a dense-discretization breakdown such that in combination with Calderon preconditioning a stable system matrix is obtained. © 2021 IEEE.

关键词： Stars

来源：评论

学校读者我要写书评

暂无评论

Control-oriented modeling and passivity analysis of thermal dynamics in a multi-producer district heating system

引用

IFAC-PapersOnLine 2023年第1期56卷 175-180页

作者： Saeed Ahmed Juan E. Machado Michele Cucuzzella Jacquelien M.A. Scherpen Jan C. Willems Center for Systems and Control ENTEG Faculty of Science and Engineering University of Groningen 9747 AG Groningen The Netherlands Department of Electrical Computer and Biomedical Engineering University of Pavia Italy

Climate change and geopolitics have led to the conception of plans for reducing greenhouse gas emissions and improving the sustainability of existing fossil-based energy systems. In this respect, district heating has been identified as an indispensable player for its potential to integrate seamlessly environmentally-friendly heat sources. To improve the efficiency of these district heating systems, optimal operation schemes can be devised and enforced through control systems. To this end, we present a control-oriented nonlinear ODE-based model of temperature dynamics in a multi-producer district heating system. The model features a modular design and comprises the thermal dynamics of heat exchangers of producers and consumers interconnected by a distribution network of meshed topology. Then, we establish passivity properties and zero-state detectability for the modeled temperature dynamics that could be exploited for controller design and solving constrained optimization problems.

关键词： District heating thermal dynamics Krasovskii passivity shifted passivity zero-state detectability

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：