检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Liu, Peng Li, Kailai Hendeby, Gustaf Gustafsson, Fredrik Division of Automatic Control Department of Electrical Engineering Linköping University Linköping Sweden Bernoulli Institute for Mathematics Computer Science and Artificial Intelligence University of Groningen Groningen Netherlands

This letter proposes a new method for joint state and parameter estimation in uncertain dynamical systems. We exploit the partial errors-in-variables (PEIV) principle and formulate a regression problem in the sense of weighted total least squares, where the uncertainty in the parameter prior is explicitly considered. Based thereon, the PEIV regression can be solved iteratively through the Kalman smoothing and the regularized least squares for estimating the state and the parameter, respectively. The simulations demonstrate improved accuracy of the proposed method compared to existing approaches, including the joint maximum a posterior-maximum likelihood, the expectation maximisation, and the augmented state extended Kalman smoother. Copyright © 2024, The Authors. All rights reserved.

关键词： Errors

来源：评论

学校读者我要写书评

暂无评论

Saving 100x storage: prototype replay for reconstructing training sample distribution in class-incremental semantic segmentation 23

Saving 100x storage: prototype replay for reconstructing tra...

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Jinpeng Chen Runmin Cong Yuxuan Luo Horace Ho Shing Ip Sam Kwong Department of Computer Science City University of Hong Kong Hong Kong School of Control Science and Engineering Shandong University Jinan Shandong China Lingnan University Hong Kong

Existing class-incremental semantic segmentation (CISS) methods mainly tackle catastrophic forgetting and background shift, but often overlook another crucial issue. In CISS, each step focuses on different foreground classes, and the training set for a single step only includes images containing pixels of the current foreground classes, excluding images without them. This leads to an overrepresentation of these foreground classes in the single-step training set, causing the classification biased towards these classes. To address this issue, we present STAR, which preserves the main characteristics of each past class by storing a compact prototype and necessary statistical data, and aligns the class distribution of single-step training samples with the complete dataset by replaying these prototypes and repeating background pixels with appropriate frequency. Compared to the previous works that replay raw images, our method saves over 100 times the storage while achieving better performance. Moreover, STAR incorporates an old-class features maintaining (OCFM) loss, keeping old-class features unchanged while preserving sufficient plasticity for learning new classes. Furthermore, a similarity-aware discriminative (SAD) loss is employed to specifically enhance the feature diversity between similar old-new class pairs. Experiments on two public datasets, Pascal VOC 2012 and ADE20K, reveal that our model surpasses all previous state-of-the-art methods. The official code is available at https://***/jinpeng0528/STAR.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Federated Cubic Regularized Newton Learning with Sparsification-amplified Differential Privacy

arXiv

引用

arXiv 2024年

作者： Huo, Wei Liu, Changxin Ding, Kemi Johansson, Karl Henrik Shi, Ling Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Sweden Digital Futures StockholmSE-10044 Sweden School of System Design and Intelligent Manufacturing Southern University of Science and Technology Shenzhen518055 China

This paper investigates the use of the cubic-regularized Newton method within a federated learning framework while addressing two major concerns that commonly arise in federated learning: privacy leakage and communication bottleneck. We introduce a federated learning algorithm called Differentially Private Federated Cubic Regularized Newton (DP-FCRN). By leveraging second-order techniques, our algorithm achieves lower iteration complexity compared to first-order methods. We also incorporate noise perturbation during local computations to ensure privacy. Furthermore, we employ sparsification in uplink transmission, which not only reduces the communication costs but also amplifies the privacy guarantee. Specifically, this approach reduces the necessary noise intensity without compromising privacy protection. We analyze the convergence properties of our algorithm and establish the privacy guarantee. Finally, we validate the effectiveness of the proposed algorithm through experiments on a benchmark dataset. © 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

Robust Event-Triggered control of Nonlinear Systems Under a Global Sector-Bound Condition

引用

Guidance, Navigation and control 2022年第2期2卷 59-79页

作者： Pengpeng Zhang Tengfei Liu Zhong-Ping Jiang Department of Control Science&Engineering Frontiers Science Center for Intelligent Autonomous SystemsTongji UniversityShanghai 201804P.R.China State Key Laboratory of Synthetical Automation for Process Industries Northeastern UniversityShenyang 110819P.R.China Department of Electrical and Computer Engineering New York University370 Jay StreetBrooklynNY 11201USA

This paper studies an event-tniggered control problem for nonlinear systems subject to both external disturbancoes and dy namic *** is assumed that the system satisfies a global sector bound *** avold infnitely fast samplng,a novel eventriggred sampling mechanism is propoeed,which use8 not only the measuned system state but also an estimation of the inluence of the *** the propoeed design,the intersampling intervals an be lower bounded by a poeitive constant,and it is independent of botb external disturbances and dynamie ***,the doeedl loop event-tniggered system i proved to be input-torstate stable with repect to the extemal *** smalgain techmigues are;used for the stability analysis of the dloeeil-bop system.

关键词： Event-triggered control external disturbance dynamic uncertainty input-to-state stability

来源：评论

学校读者我要写书评

暂无评论

An Efficient Hybrid Red Panda Optimization-Similarity-Navigated Graph Neural Network with Blockchain Technology for Shared Electric Vehicle Charging

An Efficient Hybrid Red Panda Optimization-Similarity-Naviga...

引用

Sustainable Expert Systems (ICSES), International Conference on

作者： Sammy. F Rajeshwari S Prashanth G K Babu Thirumalaimuthu Hemant Singh Pokhariya Natrayan L Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Vaddeswaram Andhra Pradesh India Department of Mathematics Bangalore Institute of Technology Bengaluru Karnataka India Department of MCA Siddaganga Institute Technology Tumkur Karnataka India Department of Instrumentation and Control Engineering St. Joseph's College of Engineering Chennai Tamil Nandu India Department of Computer Science & Engineering Graphic Era Deemed to be University Dehradun Uttarakhand India Department of Mechanical Engineering Saveetha School of EngineeringSIMATS Chennai Tamil Nadu India

ISBN: (数字)9798331540364

ISBN: (纸本)9798331540371

Blockchain technology for shared electric vehicle (EV) charging makes use of a distributed ledger in handling different transactions which promotes authenticity in charging. However, this technology can be non-scalable at times which slows down the transaction rates as the scale increases in an organization and may also demand high computational as well as energy requirements which increases the inefficiency of the total system, the operating expenses of EV charging station, costs of energy utilized for charging, cost of maintenance and cost of station infrastructure may prove to be a weakness, impacting the feasibility of infrastructure deployment and upkeep expenses of the charging stations. To overcome these drawbacks, this paper proposes a hybrid method for blockchain technology with shared EV charging. The proposed approach combines the use of the Red Panda Optimization (RPO) with Similarity-Navigated Graph Neural Network (SNGNN). Hence, it is named as hybrid RPO-SNGNN approach. Reducing the operating cost of EV charging position and maximizes the security efficiency is the main aim of the proposed approach. To optimize scheduling and resource allocation by finding efficient paths by RPO and predict future demand and user behaviour patterns by SNGNN. By then, the proposed model has been put into practice on the MATLAB work platform and contrasted with other existing methods. The proposed technique outperforms all existing techniques, including Fuzzy-based Cross Hierarchical Reinforcement Q Learning (FCHRQL), Non-Dominated Sorting Genetic Algorithm-Long Short-Term Memory Network (NSGA-II-LSTMN), and Ant Colony Optimization-Proximal Policy Optimization (ACO-PPO). The proposed method shows the operating cost of $550 and the security rate is 97%. From the result, the proposed approach operating cost is low and the security rate is high when compared to the existing approaches.

关键词： Costs Q-learning Electric vehicle charging Graph neural networks Scheduling Blockchains Security Resource management Optimization Sorting

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Temporal-Magnitude Based Sampling for Event-Based control

A Hybrid Temporal-Magnitude Based Sampling for Event-Based C...

引用

On-Line Conference (ONCON), Industrial Electronics Society Annual

作者： Oscar Miguel-Escrig José Sánchez-Moreno Julio-Ariel Romero-Pérez Sebastián Dormido-Bencomo Department of System Engineering and Design Universitat Jaume I Castelló de la Plana Spain Department of Computer Science and Automatic Control Universidad Nacional de Educación a Distancia (UNED) Madrid Spain

ISBN: (数字)9798331540319

ISBN: (纸本)9798331540326

In the current industrial environment, which is shifting towards an event-based control prone paradigm, sampling strategies in use must be revisited. Both temporal and magnitude dependent sampling strategies have been demonstrated to be suitable for control systems, reporting benefits in different categories. However, these sampling strategies also present some drawbacks, discussed in this contribution. Aiming to address some of these drawbacks, a new sampling strategy is proposed gathering characteristics of both predecessors.

关键词： Industrial electronics Transient response Quantization (signal) Event detection control systems Hybrid power systems Steady-state Data communication Guidelines

来源：评论

学校读者我要写书评

暂无评论

Error Dependent Sampling to Reduce Transient Events in Event Based control

Error Dependent Sampling to Reduce Transient Events in Event...

引用

On-Line Conference (ONCON), Industrial Electronics Society Annual

作者： Oscar Miguel-Escrig Julio-Ariel Romero-Pérez José Sánchez-Moreno Sebastián Dormido-Bencomo Department of System Engineering and Design Universitat Jaume I Castelló de la Plana Spain Department of Computer Science and Automatic Control Universidad Nacional de Educación a Distancia (UNED) Madrid Spain

ISBN: (数字)9798331540319

ISBN: (纸本)9798331540326

One of the objectives of event-based control is the reduction of generated events to perform an appropriate process control. Among the event generation techniques used to this end, those quantifying the error signal can be found more frequently for its simplicity of implementation. However, they entail a drawback in the form of trade-off between event generation and performance. Aiming to reduce the number of events, specifically in the transient response, without degrading the performance, an error dependent sampling scheme is studied in this work.

关键词： Industrial electronics Transient response Event detection Process control Robustness Regulation Generators Transient analysis

来源：评论

学校读者我要写书评

暂无评论

MULTIMODAL TRANSFORMER NETWORKS WITH LATENT INTERACTION FOR AUDIO-VISUAL EVENT LOCALIZATION

MULTIMODAL TRANSFORMER NETWORKS WITH LATENT INTERACTION FOR ...

引用

2021 IEEE International Conference on Multimedia and Expo, ICME 2021

作者： He, Yixuan Xu, Xing Liu, Xin Ou, Weihua Lu, Huimin Center for Future Media School of Computer Science and Engineering University of Electronic Science and Technology of China China Glasgow College University of Electronic Science and Technology of China China Department of Computer Science Huaqiao University China School of Big Data and Computer Science Guizhou Normal University China Department of Mechanical and Control Engineering Kyushu Institute of Technology Japan

ISBN: (纸本)9781665438643

The task of audio-visual event localization (AVEL) aims to localize a visible and audible event in a video. Previous methods first divide a video into segments and then fuse visual and acoustic features at the segment level via a co-attention mechanism. However, existing methods mostly model relations between individual visual and audio segments in a limitedly short period, which may not cover a longer video duration for better high-level event information modeling. In this paper, we proposed a novel model termed Multimodal Transformer Network with Latent Interaction (MTNLI) to tackle this problem. The proposed MTNLI model employs a multimodal Transformer structure to learn the cross-modality relationships between latent visual and audio summarizations in long segment sequences, which summarize the visual and audio segments into a small number of latent representations to avoid modeling uninformative individual visual-audio relations. The cross-modality information between the latent summarizations is propagated to fuse valuable information from both modalities, which can effectively handle large temporal inconsistent between vision and audio. Our MTNLI method achieves state-of-the-art performance on the benchmark AVE (Audio-Visual Event) dataset for the event localization task. © 2021 IEEE

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Demand-Side Joint Electricity and Carbon Trading Mechanism

IEEE Transactions on Industrial Cyber-Physical Systems

引用

IEEE Transactions on Industrial Cyber-Physical Systems 2024年 2卷 14-25页

作者： Hua, Haochen Chen, Xingying Gan, Lei Sun, Jiaxiang Dong, Nanqing Liu, Di Qin, Zhaoming Li, Kang Hu, Shiyan College of Energy and Electrical Engineering Hohai University Nanjing211100 China Shanghai Artificial Intelligence Laboratory Shanghai200232 China Department of Automation Tsinghua University Beijing100084 China Automatic Control Laboratory at Ecole Polytechnique Fédérale de Lausanne Lausanne Switzerland School of Electronic and Electrical Engineering University of Leeds LeedsLS2 9JT United Kingdom School of Electronics and Computer Science University of Southampton SouthamptonSO17 1BJ United Kingdom

Decarbonization of the whole energy chain has been recognized as a measure to tackle the global challenge of climate change, and significant progress has already been made on the generation side to integrate renewable energy. However, the demand side is the single largest underlying factor in shaping decarbonization roadmap. Hence, the carbon emission cost should also be shared by the users according to their power consumption. In this paper, a joint electricity-carbon trading framework is designed to reduce the carbon emission through trading and demand response. A delayed carbon emission liability settlement for asynchronous markets is proposed to ameliorate the users' optimal decision from single-point optimization to interval-based optimization. To develop the optimal strategy of trading within the proposed mechanism, an improved proximal policy optimization (PPO) algorithm based on Monte Carlo reward sampling is applied. Simulation studies reveal that, compared with the market without carbon trading and users without delayed settlement, the proposed mechanism has achieved a carbon emission reduction by 40.7% and 12.7% respectively. Simulations also show the algorithm's training efficiency can be significantly improved with the proposed Monte Carlo sampling method. © 2023 IEEE.

关键词： Real time systems

来源：评论

学校读者我要写书评

暂无评论

Distributed Optimization with Finite Bit Adaptive Quantization for Efficient Communication and Precision Enhancement

Distributed Optimization with Finite Bit Adaptive Quantizati...

引用

IEEE Conference on Decision and control

作者： Apostolos I. Rikos Wei Jiang Themistoklis Charalambous Karl H. Johansson Artificial Intelligence Thrust of the Information Hub The Hong Kong University of Science and Technology (Guangzhou) Guangzhou China Department of Computer Science and Engineering The Hong Kong University of Science and Technology Clear Water Bay Hong Kong China Department of Electrical Engineering and Automation School of Electrical Engineering Aalto University Espoo Finland Department of Electrical and Computer Engineering School of Engineering University of Cyprus Nicosia Cyprus Division of Decision and Control Systems KTH Royal Institute of Technology SE-100 44 Stockholm Sweden

ISBN: (数字)9798350316339

ISBN: (纸本)9798350316346

In realistic distributed optimization scenarios, individual nodes possess only partial information and communicate over bandwidth constrained channels. For this reason, the development of efficient distributed algorithms is essential. In our paper we addresses the challenge of unconstrained distributed optimization. In our scenario each node’s local function exhibits strong convexity with Lipschitz continuous gradients. The exchange of information between nodes occurs through 3-bit bandwidth-limited channels (i.e., nodes exchange messages represented by a only 3 -bits). Our proposed algorithm respects the network’s bandwidth constraints by leveraging zoom-in and zoom-out operations to adjust quantizer parameters dynamically. We show that during our algorithm’s operation nodes are able to converge to the exact optimal solution. Furthermore, we show that our algorithm achieves a linear convergence rate to the optimal solution. We conclude the paper with simulations that highlight our algorithm’s unique characteristics.

关键词： Adaptation models Quantization (signal) Heuristic algorithms Bandwidth Distributed algorithms Optimization Convergence

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：