检索结果-内蒙古大学图书馆

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Bi, Jing Yue, Caiheng Yuan, Haitao Zhai, Jiahui Zhang, Jia Zhou, MengChu Beijing University of Technology College of Computer Beijing100124 China Beihang University School of Automation Science and Electrical Engineering Beijing100191 China Southern Methodist University Dept. of Computer Science DallasTX75275 United States New Jersey Institute of Technology Dept. of Electrical and Computer Engineering NewarkNJ07102 United States

ISBN: (纸本)9781665410205

Multi-objective optimization algorithms are essential for addressing real-world challenges characterized by conflicting objectives. Although conventional algorithms are effective in exploring solution spaces and generating non-dominated solutions, solution quality and dynamic adaptability of true Pareto fronts need to be improved. This work proposes a multi-objective algorithm that integrates Non-dominated sorting genetic algorithm II (NSGA-II) and Multi-Objective Reinforcement Learning (N-MORL). N-MORL consists of two parts including upstream and downstream components. In the upstream component, this work improves the Variance-stabilized Multi-objective Proximal Policy Optimization (VMPPO) for enhanced convergence stability by adjusting its iteration mechanism. Additionally, this work optimizes variance networks and action sampling to balance exploration and exploitation, which improves experience sampling efficiency. This work adopts high-quality solution sets yielded by MORL as the initial solution set for downstream NSGA-II, guiding the exploration space and increasing the solution number. High-quality initial solutions significantly accelerate the iterative convergence speed of N-MORL. N-MORL provides the quality and the number of solutions, better covering or approaching the true Pareto front. Experimental results with five benchmark multi-objective functions demonstrate that N-MORL outperforms the other three multi-objective evolutionary algorithms regarding high-quality solutions with the same iterations. © 2024 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Generalized Zero-Shot Learning via Implicit Attribute Composition

Generalized Zero-Shot Learning via Implicit Attribute Compos...

引用

2023 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2023

作者： Zhou, Lei Liu, Yang Li, Qiang School of Computer Science and Artificial Intelligence Wuhan University of Technology Wuhan China College of Computer Science and Technology Zhejiang University Hangzhou China Institute of Automation Chinese Academy of Sciences State Key Laboratory for Management and Control of Complex Systems Beijing China

ISBN: (纸本)9798350337020

Zero-shot learning (ZSL) is an important but challenging task in computer vision that aims to identify unseen classes without matching training samples. Current cutting-edge ZSL methods based on locality focus on acquiring the explicit locality of distinguishing characteristics, which could face a lack of adequate supervision at the class attribute level. This paper introduces a novel approach called IAC, which aims to learn Implicit Attribute Composition for ZSL. This method is more comprehensive compared to attribute localization that solely focuses on class-level attribute supervision. IAC utilizes subspace representations that efficiently capture the inherent structure of high-dimensional image features. Then, we learn implicit attribute composition through subspace representation learning. The superiority of the proposed IAC compared to the state-of-the-art is demonstrated through sufficient experiments conducted on three commonly used ZSL datasets, CUB, SUN, and AwA2. © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A federated learning attack method based on edge collaboration via cloud

A federated learning attack method based on edge collaborati...

引用

作者： Yang, Jie Baker, Thar Gill, Sukhpal Singh Yang, Xiaochuan Han, Weifeng Li, Yuanzhang School of Cyberspace Science and Technology Beijing Institute of Technology Beijing China Department of Computer Science College of Computing and Informatics University of Sharjah Sharjah United Arab Emirates School of Electronic Engineering and Computer Science Queen Mary University of London London United Kingdom School of Computer Science Beijing Institute of Technology Beijing China School of Mechanical Manufacturing and Automation Engineer of China Railway Tunnel Bureau Group Co. Ltd Henan Zhengzhou China

Federated learning (FL) is widely used in edge-cloud collaborative training due to its distributed architecture and privacy-preserving properties without sharing local data. FLTrust, the most state-of-the-art FL defense method, is a federated learning defense system with trust guidance. However, we found that FLTrust is not very robust. Therefore, in the edge collaboration scenario, we mainly study the poisoning attack on the FLTrust defense system. Due to the aggregation rule, FLTrust, with trust guidance, the model updates of participants with a significant deviation from the root gradient direction will be eliminated, which makes the poisoning effect on the global model not obvious. To solve this problem, under the premise of not being deleted by the FLTrust aggregation rules, we construct malicious model updates that deviate from the trust gradient to the greatest extent to achieve model poisoning attacks. First, we utilize the rotation of high-dimensional vectors around axes to construct malicious vectors with fixed orientations. Second, the malicious vector is constructed by the gradient inversion method to achieve an efficient and fast attack. Finally, a method of optimizing random noise is used to construct a malicious vector with a fixed direction. Experimental results show that our attack method reduces the model accuracy by 20%, severely undermining the usability of the model. Attacks are also successful hundreds of times faster than the FLTrust adaptive attack method. © 2022 John Wiley & Sons Ltd.

关键词： Vectors

来源：评论

学校读者我要写书评

暂无评论

Shifting Spotlight for Co-supervision: A Simple yet Efficient Single-branch Network to See Through Camouflage

Shifting Spotlight for Co-supervision: A Simple yet Efficien...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Hu, Yang Zhang, Jinxia Zhang, Kaihua Yuan, Yin Huang, Jiale Zhan, Zechao Wang, Xin Key Laboratory of Measurement and Control of CSE School of Automation Southeast University China School of Computer Science Nanjing University of Information Science and Technology China Advanced Ocean Institute of Southeast University China Alibaba Group China

ISBN: (纸本)9798350368741

Camouflaged object detection (COD) remains a challenging task in computer vision. Existing methods often resort to additional branches for edge supervision, incurring substantial computational costs. To address this, we propose the Co-Supervised Spotlight Shifting Network (CS3Net), a compact single-branch framework inspired by how shifting light source exposes camouflage. Our spotlight shifting strategy replaces multi-branch designs by generating supervisory signals that highlight boundary cues. Within CS3Net, a Projection Aware Attention (PAA) module is devised to strengthen feature extraction, while the Extended Neighbor Connection Decoder (ENCD) enhances final predictions. Extensive experiments on public datasets demonstrate that CS3Net not only achieves superior performance, but also reduces Multiply-Accumulate operations (MACs) by 32.13% compared to state-of-the-art COD methods, striking an optimal balance between efficiency and effectiveness. © 2025 IEEE.

关键词： Camouflaged Object Detection Efficient Network Design Network Co-supervision

来源：评论

学校读者我要写书评

暂无评论

Multi-resolution Small Sample Face Recognition Based on Coupled Dictionary Learning 8

Multi-resolution Small Sample Face Recognition Based on Coup...

引用

8th IEEE International Conference on computer and Communications, ICCC 2022

作者： Fan, Xiaojin Zou, Weidong Wang, Changzhi School of Computer Science and Technology Beijing Institute of Technology Beijing China School of Automation Beijing Institute of Technology Beijing China Fudan University Department of Electronic Engineering Shanghai China

ISBN: (纸本)9781665450515

Multi-resolution small sample face recognition has always been a challenge in the field of face recognition. This paper proposes a multi-resolution small sample face recognition method based on coupled dictionary learning (MCDL). To expose the relationship between the representation coefficients corresponding to dictionary atoms and samples at different resolutions, MCDL introduces an analysis dictionary and jointly learns it with the synthesis dictionary. Besides, various coding coefficients are applied to each sample with varied resolutions throughout the multi-dictionary learning process so that the learnt dictionary is more realistic. Furthermore, we introduce the fractional norm into the model to remove the redundant information. Experimental results show that MCDL achieves good results and its recognition rate is higher than that of many algorithms. © 2022 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Trust-Region Based Stochastic Variational Inference for Distributed and Asynchronous Networks

引用

Journal of Systems Science & Complexity 2022年第6期35卷 2062-2076页

作者： FU Weiming QIN Jiahu LING Qing KANG Yu YE Baijia Department of Automation University of Science and Technology of ChinaHefei 230027China Institute of Artificial Intelligence Hefei Comprehensive National Science CenterHefei 230088China School of Computer Science and Engineering and Guangdong Province Key Laboratory of Computational ScienceSun Yat-Sen UniversityGuangzhou 510006China Institute of Advanced Technology University of Science and Technology of ChinaHefei 230027China

Stochastic variational inference is an efficient Bayesian inference technology for massive datasets,which approximates posteriors by using noisy gradient *** stochastic variational inference can only be performed in a centralized manner,which limits its applications in a wide range of situations where data is possessed by multiple ***,this paper develops a novel trust-region based stochastic variational inference algorithm for a general class of conjugate-exponential models over distributed and asynchronous networks,where the global parameters are diffused over the network by using the Metropolis rule and the local parameters are updated by using the trust-region ***,a simple rule is introduced to balance the transmission frequencies between neighboring nodes such that the proposed distributed algorithm can be performed in an asynchronous *** utility of the proposed algorithm is tested by fitting the Bernoulli model and the Gaussian model to different datasets on a synthetic network,and experimental results demonstrate its effectiveness and advantages over existing works.

关键词： Asynchronous networks Bayesian inference distributed algorithm stochastic variational inference trust-region method

来源：评论

学校读者我要写书评

暂无评论

Two-Stage Representation Refinement Based on Convex Combination for 3-D Human Poses Estimation

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第12期5卷 6500-6508页

作者： Chen, Luefeng Cao, Wei Zheng, Biao Wu, Min Pedrycz, Witold Hirota, Kaoru China University of Geosciences School of Automation Wuhan430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China Ministry of Education Engineering Research Center of Intelligent Technology for Geo-Exploration Wuhan430074 China University of Alberta Department of Electrical and Computer Engineering EdmontonABT6G 2R3 Canada Macau University of Science and Technology Institute of Systems Engineering Taipa999078 China Istinye University Research Center of Performance and Productivity Analysis Istanbul34010 Turkey Tokyo Institute of Technology Yokohama226-8502 Japan

In the human pose estimation task, on the one hand, 3-D pose always has difficulty in dividing different 2-D poses if the view is limited;on the other hand, it is hard to reduce the lifting ambiguity because of the lack of depth information, it is an important and challenging problem. Therefore, two-stage representation refinement based on the convex combination for 3-D human pose estimation is proposed, in which the two-stage method includes a dense-spatial-temporal convolutional network and a local-to-refine network. The former is applied to determine the features between each video frame;the latter is used to get the different scales of pose details. It aims to address the difficulty of estimating 3-D human pose from 2-D image sequences. In such a way, it can better use the relations between every frame in the sequence of the pose video to produce more accurate results. Finally, we combine the above network with a block called convex combination to help refine the 3-D pose location. We test the proposed approach on both Human3.6m and MPII datasets. The result confirms that our method can achieve better performance than improved CNN supervision, a simple yet effective baseline, and coarse-to-fine volumetric prediction. Besides, a robustness test experiment is carried out for the proposed method while the input is interrupted. The result verifies that our method shows better robustness. © 2024 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Integrating Machine Learning and Mathematical Optimization for Job Shop Scheduling

引用

IEEE Transactions on automation Science and Engineering 2024年第3期21卷 4829-4850页

作者： Liu, Anbang Luh, Peter B. Sun, Kailai Bragin, Mikhail A. Yan, Bing Department of Automation and BNRist Beijing100084 China University of Connecticut Department of Electrical and Computer Engineering StorrsCT06269 United States National Taiwan University Department of Electrical Engineering Taipei10617 Taiwan Tsinghua University Chaired Professors Group Center for Intelligent and Networked Systems Department of Automation Beijing100084 China Rochester Institute of Technology Department of Electrical and Microelectronic Engineering RochesterNY14623 United States

Job-shop scheduling is an important but difficult combinatorial optimization problem for low-volume and high-variety manufacturing, with solutions required to be obtained quickly at the beginning of each shift. In view of the increasing demand for customized products, problem sizes are growing. A promising direction is to take advantage of Machine Learning (ML). Direct learning to predict solutions for job-shop scheduling, however, suffers from major difficulties when problem scales are large. In this paper, a Deep Neural Network (DNN) is synergistically integrated within the decomposition and coordination framework of Surrogate Lagrangian Relaxation (SLR) to predict good-enough solutions for subproblems. Since a subproblem is associated with a single part, learning difficulties caused by large scales are overcome. Nevertheless, the learning still presents challenges. Because of the high-variety nature of parts, the DNN is desired to be able to generalize to solve all possible parts. To this end, our idea is to establish 'surrogate' part subproblems that are easier to learn, develop a DNN based on Pointer Network to learn to predict their solutions, and calculate the solutions of the original part subproblems based on the predictions. Moreover, a masking mechanism is developed such that all the predictions are feasible. Numerical results demonstrate that good-enough subproblem solutions are predicted in many iterations, and high-quality solutions of the overall problem are obtained in a computationally efficient manner. The performance of the method is further improved through continuous learning. Note to Practitioners - Scheduling is important for the planning and operation of job shops, and high-quality schedules need to be obtained quickly at the beginning of each shift. To take advantage of ML, in this paper, a DNN is integrated within our recent decomposition and coordination approach to learn to predict 'good-enough' solutions to part subproblems. To be able t

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Research on underground speech enhancement technology based on generative adversarial network

Research on underground speech enhancement technology based ...

引用

2022 IEEE International Conference on Signal Processing, Communications and Computing, ICSPCC 2022

作者： Zhang, Zhaozhao Liu, Zhongqi Chen, Xiaolin Sun, Kang Institute of Computer Science and Technology Xi'an University of Science and Technology Ccteg Changzhou Research Research Institute Xi'an China Automation Co. Ltd Changzhou China

ISBN: (数字)9781665469722

ISBN: (纸本)9781665469722

Because of the problems such as speech interaction and speech input difficulty caused by high noise intensity and unclear sources in underground mine, this paper proposes a speech enhancement system based on a Time-domain Generative Adversarial network, which is used in the front end of underground communication or speech recognition to improve the quality of speech information transmission and improve work efficiency. Aiming at the problems of ignoring the feature information between channels and training instability when extracting speech information in a time domain generative adversarial network, this paper introduces channel attention and Relativistic Average Generative Adversarial Network to optimize. The experimental results show that compared with other models, the proposed model can more effectively remove the downhole noise. © 2022 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

A Method of Extracting Corner Features from Laser Point Cloud Data

A Method of Extracting Corner Features from Laser Point Clou...

引用

2022 Chinese automation Congress, CAC 2022

作者： Dong, Shuzhou Li, Qian Gao, Han Kasimov, Farkhod Zhang, Dong Institute of Automation Qilu University of Technology Shandong Academy of Sciences Provincial Key Laboratory of Robot and Manufacturing Automation Technology Shandong China Jinan Lashan Aviation Technology Co.Ltd China Department of Computer Science-Automation and Management Tashkent chemical-technological institute Jinan250014 China

ISBN: (纸本)9781665465335

With the development of robot technology, the requirement of target recognition accuracy for depalletizing robot based on lidar is constantly improved. In order to solve the problems of large data acquisition error and low target recognition accuracy caused by environmental interference during lidar operation, a new corner feature extraction method is proposed in this paper. Firstly, based on the anomaly detection LOF algorithm, a data preprocessing method is designed to improve the accuracy of lidar data acquisition.;Then, the Douglas-Pucker algorithm is used for data segmentation to obtain the straight line segment features and corner features of the stacking object boundary. The corner features are further determined by re-judgment method to improve the accuracy of corner features. Finally, this paper designs a comparative experiment based on the data collected by lidar, and the experimental results verify the feasibility of the improved algorithm in this paper in terms of outlier removal and corner feature extraction. © 2022 IEEE.

关键词： Optical radar

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：