检索结果-内蒙古大学图书馆

An improved super-resolution with manifold learning and histogram matching

International Conference on Biometrics, ICB 2006

作者： Chan, Tak Ming Zhang, Junping Shanghai Key Laboratory of Intelligent Information Processing Department of Computer Science and Engineering Fudan University 200433 China Key Laboratory of Complex Systems and Intelligence Science Institute of Automation Chinese Academy of Sciences Beijing 100080 China

ISBN: (纸本)3540311114

Biometric Person Authentication such as face, fingerprint, palmprint and signature depends on the quality of image processing. When it needs to be done under a low-resolution image, the accuracy will be impaired. So how to recover the lost information from down-sampled images is important for both authentication and preprocessing. Based on Super-Resolution through Neighbor Embedding algorithm and histogram matching, we propose an improved super-resolution approach to choose more reasonable training images. First, the training image are selected by histogram matching. Second, neighbor embedding algorithm is employed to recover the high-resolution image. Experiments in several images show that our improved super-resolution approach is promising for potential applications such as low-resolution mobile phone or CCTV (Closed Circuit Television) image person authentication. © Springer-Verlag Berlin Heidelberg 2005.

关键词： Pattern matching

来源：评论

学校读者我要写书评

暂无评论

Energy-Efficient Wireless Federated Learning: A Secrecy Oriented design via Sequential Artificial Jamming

引用

IEEE Transactions on Vehicular Technology 2023年第5期72卷 6412-6427页

作者： Wang, Tianshun Huang, Ning Wu, Yuan Quek, Tony Q. S. University of Macau State Key Laboratory of Internet of Things for Smart City 999078 China University of Macau Department of Computer and Information Science 999078 China University of Macau State Key Lab of Internet of Things for Smart City The Department of Computer and Information Science 999078 China Zhuhai UM Science and Technology Research Institute Zhuhai519031 China Singapore University of Technology and Design Information Systems Technology and Design Pillar 487372 Singapore National Cheng Kung University Tainan701 Taiwan

Wireless federated learning (FL) is envisioned as a promising paradigm of distributed learning in wireless networks without disclosing users' data privacy. However, radio channel leads to a potential risk of eavesdropping attack when sending the trained model data in wireless networks. To address this eavesdropping attack, in this work, we propose an energy-efficient wireless FL by using artificial jamming. Specifically, the group of wireless devices (WDs) adopt the time division multiple access (TDMA) approach to send their locally trained models to the FL server for model aggregation subject to the eavesdropping attack of a malicious node. When one of the WDs sends its local model, all the other WDs send the artificial jamming signals to interfere with the eavesdropper, which helps increase the secrecy throughput of the targeted WD for uploading its local model. Different from many existing studies using stochastic gradient descent (SGD), we adopt the stochastic average gradient (SAG) method in the local training to improve the convergence of FL and derive the corresponding lower bound of the FL convergence rate via SAG. Furthermore, we formulate an optimization problem that aims at minimizing the energy consumption of the WDs by jointly optimizing different WDs' local training time, their uploading transmission time in TDMA and the transmit-powers for providing artificial jamming, as well as the FL configurations of the local/global iterations. We also propose an efficient algorithm for solving this non-convex optimization problem. Numerical results are illustrated to validate the advantages of our design of wireless FL and the corresponding algorithms. In particular, the results demonstrate that our secrecy oriented energy-efficient FL can significantly outperform the other heuristic FL schemes. © 1967-2012 IEEE.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

UAV-Assisted Dynamic Avatar Task Migration for Vehicular Metaverse Services: A Multi-Agent Deep Reinforcement Learning Approach

引用

IEEE/CAA Journal of Automatica Sinica 2024年第2期11卷 430-445页

作者： Jiawen Kang Junlong Chen Minrui Xu Zehui Xiong Yutao Jiao Luchao Han Dusit Niyato Yongju Tong Shengli Xie IEEE School of Automation Guangdong University of TechnologyGuangzhou 510006China 111 Center for Intelligent Batch Manufacturing based on IoT Technology Guangzhou 510006China Key Laboratory of Intelligent Information Processing and System Integration of IoT Ministry of EducationGuangzhou 510006China School of Computer Science and Engineering Nanyang Technological UniversitySingaporeSingapore Pillar of Information Systems Technology and Design Singapore University of Technology and DesignSingaporeSingapore College of Communication Engineering Army Engineering University of PLANanjing 210007China National Natural Science Foundation of China Beijing 100085China Key Laboratory of Intelligent Detection and IoT in Manufacturing Ministry of EducationGuangzhou 510006China Guangdong Key Laboratory of IoT Information Technology Guangzhou 510006China

Avatars, as promising digital representations and service assistants of users in Metaverses, can enable drivers and passengers to immerse themselves in 3D virtual services and spaces of UAV-assisted vehicular Metaverses. However, avatar tasks include a multitude of human-to-avatar and avatar-to-avatar interactive applications, e.g., augmented reality navigation,which consumes intensive computing resources. It is inefficient and impractical for vehicles to process avatar tasks locally. Fortunately, migrating avatar tasks to the nearest roadside units(RSU)or unmanned aerial vehicles(UAV) for execution is a promising solution to decrease computation overhead and reduce task processing latency, while the high mobility of vehicles brings challenges for vehicles to independently perform avatar migration decisions depending on current and future vehicle status. To address these challenges, in this paper, we propose a novel avatar task migration system based on multi-agent deep reinforcement learning(MADRL) to execute immersive vehicular avatar tasks dynamically. Specifically, we first formulate the problem of avatar task migration from vehicles to RSUs/UAVs as a partially observable Markov decision process that can be solved by MADRL algorithms. We then design the multi-agent proximal policy optimization(MAPPO) approach as the MADRL algorithm for the avatar task migration problem. To overcome slow convergence resulting from the curse of dimensionality and non-stationary issues caused by shared parameters in MAPPO, we further propose a transformer-based MAPPO approach via sequential decision-making models for the efficient representation of relationships among agents. Finally, to motivate terrestrial or non-terrestrial edge servers(e.g., RSUs or UAVs) to share computation resources and ensure traceability of the sharing records, we apply smart contracts and blockchain technologies to achieve secure sharing management. Numerical results demonstrate that the proposed approach

关键词： Avatar blockchain metaverses multi-agent deep reinforcement learning transformer UAVs

来源：评论

学校读者我要写书评

暂无评论

Wireless Federated Learning With Hybrid Local and Centralized Training: A Latency Minimization design

引用

IEEE Journal on Selected Topics in Signal Processing 2023年第1期17卷 248-263页

作者： Huang, Ning Dai, Minghui Wu, Yuan Quek, Tony Q. S. Shen, Xuemin State Key Lab of Internet of Things for Smart City China University of Macau Department of Computer and Information Science China University of Macau State Key Laboratory of Internet of Things for Smart City The Department of Computer and Information Science China Zhuhai Um Science and Technology Research Institute Zhuhai519031 China Singapore University of Technology and Design Information Systems Technology and Design Pillar 487372 Singapore National Cheng Kung University Taiwan University of Waterloo Department of Electrical and Computer Engineering WaterlooONN2L 3G1 Canada

Wireless federated learning (FL) is a collaborative machine learning (ML) framework in which wireless client-devices independently train their ML models and send the locally trained models to the FL server for aggregation. In this paper, we consider the coexistence of privacy-sensitive client-devices and privacy-insensitive yet computing-resource constrained client-devices, and propose an FL framework with a hybrid centralized training and local training. Specifically, the privacy-sensitive client-devices perform local ML model training and send their local models to the FL server. Each privacy-insensitive client-device can have two options, i.e., (i) conducting a local training and then sending its local model to the FL server, and (ii) directly sending its local data to the FL server for the centralized training. The FL server, after collecting the data from the privacy-insensitive client-devices (which choose to upload the local data), conducts a centralized training with the received datasets. The global model is then generated by aggregating (i) the local models uploaded by the client-devices and (ii) the model trained by the FL server centrally. Focusing on this hybrid FL framework, we firstly analyze its convergence feature with respect to the client-devices' selections of local training or centralized training. We then formulate a joint optimization of client-devices' selections of the local training or centralized training, the FL training configuration (i.e., the number of the local iterations and the number of the global iterations), and the bandwidth allocations to the client-devices, with the objective of minimizing the overall latency for reaching the FL convergence. Despite the non-convexity of the joint optimization problem, we identify its layered structure and propose an efficient algorithm to solve it. Numerical results demonstrate the advantage of our proposed FL framework with the hybrid local and centralized training as well as our proposed alg

关键词： information management

来源：评论

学校读者我要写书评

暂无评论

Z-tiles: Building blocks for modular, pressure-sensing floorspaces

Z-tiles: Building blocks for modular, pressure-sensing floor...

引用

Conference on Human Factors in Computing systems, CHI EA 2004

作者： Richardson, Bruce Leydon, Krispin Fernström, Mikael Paradiso, Joseph A. Interaction Design Centre Department of Computer Science and Information Systems University of Limerick Limerick Ireland MIT Media Laboratory 77 Massachusetts Avenue Cambridge MA 02142 United States

ISBN: (纸本)1581137036

A new interactive floorspace has been developed which uses modular nodes connected together to create a pressure-sensitive area of varying size and shape, giving it the potential to be integrated into an interactive environment. The floorspace uses an array of force-sensitive resistors on each node to detect pressure, and that pressure information is output by way of a self-organised network formed by the floor nodes. This paper describes the pressure sensing and network systems, suggests potential applications of the floorspace, and introduces the further research on in-network data aggregation being carried out using the system's framework. © 2004 ACM.

关键词： Building materials

来源：评论

学校读者我要写书评

暂无评论

Dual-Objective Mixed Integer Linear Program and Memetic Algorithm for an Industrial Group Scheduling Problem

引用

IEEE/CAA Journal of Automatica Sinica 2021年第6期8卷 1199-1209页

作者： Ziyan Zhao Shixin Liu MengChu Zhou Abdullah Abusorrah State Key Laboratory of Synthetical Automation for Process Industries and the College of Information Science and Engineering Northeastern UniversityShenyang 110819China Department of Electrical and Computer Engineering New Jersey Institute of TechnologyNewark NJ 07102 USA Center of Research Excellence in Renewable Energy and Power Systems King Abdulaziz UniversityJeddah 21481Saudi Arabia Department of Electrical and Computer Engineering Faculty of Engineeringand Center of Research Excellence in Renewable Energy and Power SystemsKing Abdulaziz UniversityJeddah 21481Saudi Arabia

Group scheduling problems have attracted much attention owing to their many practical *** work proposes a new bi-objective serial-batch group scheduling problem considering the constraints of sequence-dependent setup time,release time,and due *** is originated from an important industrial process,i.e.,wire rod and bar rolling process in steel production *** objective functions,i.e.,the number of late jobs and total setup time,are minimized.A mixed integer linear program is established to describe the *** obtain its Pareto solutions,we present a memetic algorithm that integrates a population-based nondominated sorting genetic algorithm II and two single-solution-based improvement methods,i.e.,an insertion-based local search and an iterated greedy *** computational results on extensive industrial data with the scale of a one-week schedule show that the proposed algorithm has great performance in solving the concerned problem and outperforms its *** high accuracy and efficiency imply its great potential to be applied to solve industrial-size group scheduling problems.

关键词： Insertion-based local search iterated greedy algorithm machine learning memetic algorithm nondominated sorting genetic algorithm II(NSGA-II) production scheduling

来源：评论

学校读者我要写书评

暂无评论

Learning Attentions: Residual Attentional Siamese Network for High Performance Online Visual Tracking 31

Learning Attentions: Residual Attentional Siamese Network fo...

引用

31st IEEE/CVF Conference on computer Vision and Pattern Recognition (CVPR)

作者： Wang, Qiang Teng, Zhu Xing, Junliang Gao, Jin Hu, Weiming Maybank, Stephen University of Chinese Academy of Sciences Beijing China School of Computer and Information Technology Beijing Jiaotong University Beijing China National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing China Department of Computer Science and Information Systems Birkbeck College University of London UK

ISBN: (纸本)9781538664209

Offline training for object tracking has recently shown great potentials in balancing tracking accuracy and speed. However, it is still difficult to adapt an offline trained model to a target tracked online. This work presents a Residual Attentional Siamese Network (RASNet) for high performance object tracking. The RASNet model reformulates the correlation filter within a Siamese tracking framework, and introduces different kinds of the attention mechanisms to adapt the model without updating the model online. In particular, by exploiting the offline trained general attention, the target adapted residual attention, and the channel favored feature attention, the RASNet not only mitigates the over-fitting problem in deep network training, but also enhances its discriminative capacity and adaptability due to the separation of representation learning and discriminator learning. The proposed deep architecture is trained from end to end and takes full advantage of the rich spatial temporal information to achieve robust visual tracking. Experimental results on two latest benchmarks, OTB-2015 and VOT2017, show that the RASNet tracker has the state-of-the-art tracking accuracy while runs at more than 80 frames per second.

关键词： Target tracking Correlation Feature extraction Training Adaptation models Visualization Object tracking

来源：评论

学校读者我要写书评

暂无评论

Equivalence knowledge cumularspharolith and multiple approximate reasoning in R-logic ℂR

Equivalence knowledge cumularspharolith and multiple approxi...

引用

2009 WRI World Congress on computer science and information Engineering, CSIE 2009

作者： Yalin, Zheng Guang, Yang Research Center of Intelligent Information Technology Department of Computer Science and Technology Dongguan University of Science and Technology Dongguan 523808 China State Key Laboratory for Intelligent Technology and Systems Department of Automation Tsinghua University Beijing 100084 China

ISBN: (纸本)9780769535074

By casting off the direct restriction of topological structure, this paper presents another matching scheme between the input A* and the knowledge A → B based on the equivalence relation on formulae set F(S) and the corresponding equivalence classification F(S)/R = {[A]R |A ∈ F(S)} therefore, obtains another algorithm of approximate reasoning - the IV-type R-algorithm. The paper presents the IV-type R-algorithm for the simple approximate reasoning model and the multiple approximate reasoning model in the frame of R-logic ℂR. © 2008 IEEE.

关键词： Knowledge based systems

来源：评论

学校读者我要写书评

暂无评论

Hybridization of Harmony Search with Nelder-Mead Algorithm for Combined Heat and Power Economic Dispatch Problem 36

Hybridization of Harmony Search with Nelder-Mead Algorithm f...

引用

第36届中国控制会议

作者： Zhi-Yong Feng Huiru Guo Zhen-Tao Liu Li Xu Jinhua She Hubei Key Laboratory of Advanced Technology of Automotive Parts Wuhan University of Technology School of Automation China University of Geosciences Department of Electronics and Information Systems Akita Prefectural University School of Computer Science Tokyo University of Technology

ISBN: (纸本)9781538629185

A new hybridized algorithm is developed to solve the combined heat and power economic dispatch(CHPED) *** to the non-convexity of the CHPED problem, the global optimum is difficult to achieve. The presented approach combines the algorithms of harmony search(HS) and Nelder-Mead(NM), and the hybridized algorithm is called the NM-HS algorithm. The hybridized NM-HS algorithm improves the efficiency of the two original algorithms, and also the robustness. Two benchmark examples demonstrate the good performance of the NM-HS algorithm. The solutions obtained is better than, or at least is the same as, other methods.

关键词： Economic dispatch Combined heat and power Harmony search Nelder-Mead Hybridized algorithm

来源：评论

学校读者我要写书评

暂无评论

Geometrical probability covering algorithm

Geometrical probability covering algorithm

引用

2nd International Conference on Fuzzy systems and Knowledge Discovery, FSKD 2005

作者： Zhang, Junping Li, Stan Z. Wang, Jue Shanghai Key Laboratory of Intelligent Information Processing Department of Computer Science and Engineering Fudan University Shanghai 200433 China Key Laboratory of Complex Systems and Intelligence Science Institute of Automation Chinese Academy of Sciences Beijing 100080 China National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing 100080 China

ISBN: (纸本)9783540283126

In this paper, we propose a novel classification algorithm, called geometrical probability covering (GPC) algorithm, to improve classification ability. On the basis of geometrical properties of data, the proposed algorithm first forms extended prototypes through computing means of any two prototypes in the same class. Then Gaussian kernel is employed for covering the geometrical structure of data and used as a local probability measurement. By computing the sum of the probabilities that a new sample to be classified to the set of prototypes and extended prototypes, the classified criterion based on the global probability measurement is achieved. The proposed GPC algorithm is simple but powerful, especially, when training samples are sparse and small size. Experiments on several databases show that the proposed algorithm is promising. Also, we explore other potential applications such as outlier removal with the proposed GPC algorithm. © Springer-Verlag Berlin Heidelberg 2005.

关键词： algorithms

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：