检索结果-南通市图书馆

Fairness in machine learning: definition, testing,debugging, and application

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2024年第9期67卷 41-61页

作者： Xuanqi GAO Chao SHEN Weipeng JIANG Chenhao LIN Qian LI Qian WANG Qi LI Xiaohong GUAN Faculty of electronic and Information engineering Xi'an Jiaotong University School of Cyber Science and engineering Wuhan University Institute for Network Sciences and Cyberspace Tsinghua University

In recent years, artificial intelligence technology has been widely used in many fields, such as computer vision, natural language processing and autonomous driving. Machine learning algorithms, as the core technique of AI, have significantly facilitated people's lives. However, underlying fairness issues in machine learning systems can pose risks to individual fairness and social security. Studying fairness definitions, sources of problems, and testing and debugging methods of fairness can help ensure the fairness of machine learning systems and promote the wide application of artificial intelligence technology in various fields. This paper introduces relevant definitions of machine learning fairness and analyzes the sources of fairness problems. Besides, it provides guidance on fairness testing and debugging methods and summarizes popular datasets. This paper also discusses the technical advancements in machine learning fairness and highlights future challenges in this area.

关键词： artificial intelligence security machine learning security machine learning fairness model testing model debugging

Time domain characteristic analysis of non-coupled PCNN

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Optoelectronics Letters 2024年第11期20卷 689-696页

作者： DENG Xiangyu YU Haiyue HUANG Xikai College of Physics and electronic engineering Northwest Normal University

Pulse-coupled neural network(PCNN) is a multi-parameter artificial neural network, and the characteristics of PCNN can be fully explored by analyzing different simplified networks.

关键词： A

同方期刊数据库

Poles Extraction Based LiDAR Localization for Autonomous Robot Systems

在线全文

学校读者我要写书评

暂无评论

Journal of Systems Science & Complexity 2024年第4期37卷 1413-1424页

作者： HONG Xin DONG Yi College of electronic and Information engineering Tongji UniversityShanghai 201800China

With the development of intelligent technology,the problem of Li DAR-based localization has played an increasingly important role in the localization of robots in unmanned *** the dense point clouds from the environment requires a large amount of memory,specific and stable structural features,such as pole-like objects in the environment,can serve as the ideal landmarks for localization in unmanned systems,which can effectively reduce the memory usage and mitigate the effects of dynamic environment *** this paper,the authors propose a pole-like objects extraction approach and then,it is applied into the localization system of mobile *** the same experimental conditions,the proposed method can extract more pole-like objects and achieve better long-term localization accuracy than some existing methods in different urban environmental datasets.

关键词： Pole-like landmark extraction robot localization

维普期刊数据库

An Algorithm of Deformation Image Correction Based on Spatial Mapping

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of electronics 2024年第5期33卷 1326-1336页

作者： Xiangyu DENG Aijia ZHANG Jinhong YE College of Physics and electronic engineering Northwest Normal University

The original image undergoes geometric deformation in terms of position, shape, size, and orientation due to the shooting angle or capturing process during image acquisition. This leads to inconveniences and significant challenges in various image processing fields such as image fusion, denoising, recognition, and segmentation. To enhance the processing ability and recognition accuracy of deformation images, an adaptive algorithm for correcting image deformities is proposed for quadrilaterals and triangles. Firstly, the deformation image undergoes preprocessing, and the contour of the image edge is extracted. Then, discrete points on the image edge are identified to accurately locate the edges. Finally, the deformation of the quadrilateral or triangle is transformed into a standard rectangular or equilateral triangular image using the proposed three-dimensional homography transformation algorithm. This effectively completes the conversion from an irregular image to a regular image in an adaptive manner. Numerous experiments demonstrate that the proposed algorithm surpasses traditional methods like Hough transform and Radon *** improves the effectiveness of correcting deformation in images, effectively addresses the issue of geometric deformation, and provides a new technical method for processing deformation images.

关键词： Image preprocessing Image vertex positioning Three-dimensional space Homography transformation Image correction Image preprocessing Image vertex positioning Three-dimensional space Homography transformation Image correction DISTORTION

同方期刊数据库

Triad-displaced ULAs configuration for non-circular sources with larger continuous virtual aperture and enhanced degrees of freedom

在线全文

学校读者我要写书评

暂无评论

Journal of Systems engineering and electronics 2024年第1期35卷 81-93页

作者： SHAIKH Abdul Hayee DANG Xiaoyu HUANG Daqing College of electronic and Information engineering Nanjing University of Aeronautics and AstronauticsNanjing 211106China

Non-uniform linear array(NULA)configurations are well renowned due to their structural ability for providing increased degrees of freedom(DOF)and wider array aperture than uniform linear arrays(ULAs).These characteristics play a significant role in improving the direction-of-arrival(DOA)estimation ***,most of the existing NULA geometries are primarily applicable to circular sources(CSs),while they limitedly improve the DOF and continuous virtual aperture for noncircular sources(NCSs).Toward this purpose,we present a triaddisplaced ULAs(Tdis-ULAs)configuration for *** TdisULAs structure generally consists of three ULAs,which are appropriately *** proposed antenna array approach fully exploits the non-circular characteristics of the *** the same number of elements,the Tdis-ULAs design achieves more DOF and larger hole-free co-array aperture than its sparse array ***,the number of uniform DOF,optimal distribution of elements among the ULAs,and precise element positions are uniquely determined by the closed-form ***,the proposed array also produces a filled resulting *** simulations are conducted to show the performance advantages of the proposed Tdis-ULAs configuration over its counterpart designs.

关键词： direction-of-arrival(DOA)estimation sparse array non-circular source(NCS) sum co-array difference co-array degrees of freedom(DOF)

维普期刊数据库

Design of Robust Var Reserve Contract for Enhancing Reactive Power Ancillary Service Market Efficiency

在线全文

学校读者我要写书评

暂无评论

CSEE Journal of Power and Energy Systems 2024年第2期10卷 767-771页

作者： Yunyang Zou Yan Xu School of Electrical and electronic engineering Nanyang Technological UniversitySingapore 639798Singapore

In a deregulated Var market, market power issue is more serious than in an energy market since reactive power cannot be transmitted over long distances. This letter designs a multi-timescale Var market framework, where market power that may arise in the hourly-ahead Var support service market due to system configuration deficiency and market structure flaws can be eliminated by day-ahead contract-based Var reserve service market. Settlement of day-ahead Var reserve contract is formulated as a two-stage robust optimization (TSRO) model considering worst case of uncertainty realization and potential market power that may arise in hourly-ahead market. TSRO with integer recourses is then solved by a new column and constraint generation algorithm. Results show a robust Var reserve contract can fully eliminate market power, and prevent suppliers from manipulating market prices.

关键词： Market efficiency market power reactive power ancillary service two-stage robust optimization Var reserve

Post-layout simulation driven analog circuit sizing

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2024年第4期67卷 289-300页

作者： Xiaohan GAO Haoyi ZHANG Siyuan YE Mingjie LIU David Z.PAN Linxiao SHEN Runsheng WANG Yibo LIN Ru HUANG School of Integrated Circuits Peking University School of Computer Science Peking University department of Electrical and Computer engineering University of Texas at Austin Institute of electronic Design Automation Peking University

Post-layout simulation provides accurate guidance for analog circuit design, but post-layout performance is hard to be directly optimized at early design stages. Prior work on analog circuit sizing often utilizes pre-layout simulation results as the optimization objective. In this work, we propose a post-layoutsimulation-driven(post-simulation-driven for short) analog circuit sizing framework that directly optimizes the post-layout simulation performance. The framework integrates automated layout generation into the optimization loop of transistor sizing and leverages a coupled Bayesian optimization algorithm to search for the best post-simulation performance. Experimental results demonstrate that our framework can achieve over 20% better post-layout performance in competitive time than manual design and the method that only considers pre-layout optimization.

关键词： analog EDA transistor sizing Bayesian optimization post-layout simulation

Optimal Bidding Strategies of Microgrid with Demand Side Management for Economic Emission Dispatch Incorporating Uncertainty and Outage of Renewable Energy Sources

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Energy engineering 2024年第4期121卷 849-867页

作者： Mousumi Basu Chitralekha Jena Baseem Khan Ahmed Ali department of Power engineering Jadavpur UniversityJadavpurIndia School of Electrical engineering KIIT UniversityBhubaneswarIndia department of Electrical and Computer engineering Hawassa UniversityHawassaEthiopia department of Electrical and electronic engineering Technology Faculty of Engineering and the Built EnvironmentUniversity of JohannesburgJohannesburgSouth Africa

In the restructured electricity market,microgrid(MG),with the incorporation of smart grid technologies,distributed energy resources(DERs),a pumped-storage-hydraulic(PSH)unit,and a demand response program(DRP),is a smarter and more reliable electricity *** consists of gas turbines and renewable energy sources such as photovoltaic systems and wind *** bidding strategies,prepared by MG operators,decrease the electricity cost and emissions from upstream grid and conventional and renewable energy sources(RES).But it is inefficient due to the very high sporadic characteristics of RES and the very high outage *** solve these issues,this study suggests non-dominated sorting genetic algorithm Ⅱ(NSGA-Ⅱ)for an optimal bidding strategy considering pumped hydroelectric energy storage and DRP based on outage conditions and uncertainties of renewable energy *** uncertainty related to solar and wind units is modeled using lognormal and Weibull probability ***-based DRP is used,especially considering the time of outages along with the time of peak loads and prices,to enhance the reliability of MG and reduce costs and emissions.

关键词： Micro-grid distributed energy resources demand response program uncertainty outage

MAUN:Memory-Augmented Deep Unfolding Network for Hyperspectral Image Reconstruction

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2024年第5期11卷 1139-1150页

作者： Qian Hu Jiayi Ma Yuan Gao Junjun Jiang Yixuan Yuan electronic Information School Wuhan UniversityWuhan 430072China School of Computer Science and Technology Harbin Institute of TechnologyHarbin 150001China department of electronic engineering Chinese University of Hong KongHong Kong 999077China

Spectral compressive imaging has emerged as a powerful technique to collect the 3D spectral information as 2D *** algorithm for restoring the original 3D hyperspectral images(HSIs)from compressive measurements is pivotal in the imaging *** approaches painstakingly designed networks to directly map compressive measurements to HSIs,resulting in the lack of interpretability without exploiting the imaging *** some recent works have introduced the deep unfolding framework for explainable reconstruction,the performance of these methods is still limited by the weak information transmission between iterative *** this paper,we propose a Memory-Augmented deep Unfolding Network,termed MAUN,for explainable and accurate HSI ***,MAUN implements a novel CNN scheme to facilitate a better extrapolation step of the fast iterative shrinkage-thresholding algorithm,introducing an extra momentum incorporation step for each iteration to alleviate the information ***,to exploit the high correlation of intermediate images from neighboring iterations,we customize a cross-stage transformer(CSFormer)as the deep denoiser to simultaneously capture self-similarity from both in-stage and cross-stage features,which is the first attempt to model the long-distance dependencies between iteration *** experiments demonstrate that the proposed MAUN is superior to other state-of-the-art methods both visually and *** code is publicly available at https://***/HuQ1an/MAUN.

关键词： Deep folding iteration

维普期刊数据库