检索结果-内蒙古大学图书馆

Federated Cubic Regularized Newton Learning with Sparsification-amplified Differential Privacy

学校读者我要写书评

暂无评论

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

Minimal control Placement of Turing's Model Using Symmetries

学校读者我要写书评

暂无评论

Minimal Control Placement of Turing's Model Using Symmetries

IEEE Conference on Decision and control

作者： Yuexin Cao Yibei Li Zhixin Liu Lirong Zheng Xiaoming Hu Department of Mathematics KTH Royal Institute of Technology Sweden School of Electrical and Electronic Engineering Nanyang Technological University Singapore Key Laboratory of Systems and Control Academy of Mathematics and Systems Science Chinese Academy of Sciences China School of Information Science and Technology Fudan University China

In this paper, the minimal control placement prob-lem for Turing's reaction-diffusion model is studied. Turing's model describes the process of morphogens diffusing and reacting with each other and is considered as one of the most fundamental models to explain pattern formation in a devel-oping embryo. controlling pattern formation artificially has gained increasing attention in the field of development biology, which motivates us to investigate this problem mathematically. In this work, the two-dimensional Turing's reaction-diffusion model is discretized into square grids. The minimal control placement problem for the diffusion system is investigated first. The symmetric control sets are defined based on the symmetry of the network structure. A necessary condition is provided to guarantee controllability. Under certain circumstances, we prove that this condition is also sufficient. Then we show that the necessary condition can also be applied to the reaction-diffusion system by means of suitable extension of the symmetric control sets. Under similar circumstances, a sufficient condition is given to place the minimal control for the reaction-diffusion system.

关键词：

PredRecon: A Prediction-boosted Planning Framework for Fast and High-quality Autonomous Aerial Reconstruction

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Feng, Chen Li, Haojia Gao, Fei Zhou, Boyu Shen, Shaojie School of Artificial Intelligence Sun Yat-Sen University Zhuhai China Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Hong Kong State Key Laboratory of Industrail Control Technology Institute of Cyber-Systems and Control Zhejiang University Hangzhou China Huzhou Institute Zhejiang University Huzhou China

Autonomous UAV path planning for 3D reconstruction has been actively studied in various applications for high-quality 3D models. However, most existing works have adopted explore-then-exploit, prior-based or exploration-based strategies, demonstrating inefficiency with repeated flight and low autonomy. In this paper, we propose PredRecon, a prediction-boosted planning framework that can autonomously generate paths for high 3D reconstruction quality. We obtain inspiration from humans can roughly infer the complete construction structure from partial observation. Hence, we devise a surface prediction module (SPM) to predict the coarse complete surfaces of the target from the current partial reconstruction. Then, the uncovered surfaces are produced by online volumetric mapping waiting for observation by UAV. Lastly, a hierarchical planner plans motions for 3D reconstruction, which sequentially finds efficient global coverage paths, plans local paths for maximizing the performance of Multi-View Stereo (MVS), and generates smooth trajectories for image-pose pairs acquisition. We conduct benchmarks in the realistic simulator, which validates the performance of PredRecon compared with the classical and state-of-the-art methods. The open-source code is released at https://***/HKUST-Aerial-Robotics/PredRecon. Copyright © 2023, The Authors. All rights reserved.

关键词： Forecasting

AutoTrans: A Complete Planning and control Framework for Autonomous UAV Payload Transportation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Li, Haojia Wang, Haokun Feng, Chen Gao, Fei Zhou, Boyu Shen, Shaojie School of Artificial Intelligence Sun Yat-Sen University Zhuhai China Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and Control Zhejiang University Hangzhou China Huzhou Institute Zhejiang University Huzhou China

The robotics community is increasingly interested in autonomous aerial transportation. Unmanned aerial vehicles with suspended payloads have advantages over other systems, including mechanical simplicity and agility, but pose great challenges in planning and control. To realize fully autonomous aerial transportation, this paper presents a systematic solution to address these difficulties. First, we present a real-time planning method that generates smooth trajectories considering the time-varying shape and non-linear dynamics of the system, ensuring whole-body safety and dynamic feasibility. Additionally, an adaptive NMPC with a hierarchical disturbance compensation strategy is designed to overcome unknown external perturbations and inaccurate model parameters. Extensive experiments show that our method is capable of generating high-quality trajectories online, even in highly constrained environments, and tracking aggressive flight trajectories accurately, even under significant uncertainty. We plan to release our code to benefit the community. © 2023, CC BY-NC-ND.

关键词： Trajectories

PredRecon: A Prediction-boosted Planning Framework for Fast and High-quality Autonomous Aerial Reconstruction

学校读者我要写书评

暂无评论

PredRecon: A Prediction-boosted Planning Framework for Fast ...

IEEE International Conference on Robotics and Automation (ICRA)

作者： Chen Feng Haojia Li Fei Gao Boyu Zhou Shaojie Shen Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Hong Kong China State Key Laboratory of Industrail Control Technology Institute of Cyber-Systems and Control Zhejiang University Hangzhou China Huzhou Institute Zhejiang University Huzhou China School of Artificial Intelligence Sun Yat-Sen University Zhuhai China

关键词：

One RING to Rule Them All: Radon Sinogram for Place Recognition, Orientation and Translation Estimation

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Lu, Sha Xu, Xuecheng Yin, Huan Chen, Zexi Xiong, Rong Wang, Yue State Key Laboratory of Industrial Control and Technology Institute of Cyber-Systems and Control Zhejiang University Hangzhou310058 China Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Clear Water Bay Hong Kong

LiDAR-based global localization is a fundamental problem for mobile robots. It consists of two stages, place recognition and pose estimation, which yields the current orientation and translation, using only the current scan as query and a database of map scans. Inspired by the definition of a recognized place, we consider that a good global localization solution should keep the pose estimation accuracy with a lower place density. Following this idea, we propose a novel framework towards sparse place-based global localization, which utilizes a unified and learning-free representation, Radon sinogram (RING), for all sub-tasks. Based on the theoretical derivation, a translation invariant descriptor and an orientation invariant metric are proposed for place recognition, achieving certifiable robustness against arbitrary orientation and large translation between query and map scan. In addition, we also utilize the property of RING to propose a global convergent solver for both orientation and translation estimation, arriving at global localization. Evaluation of the proposed RING based framework validates the feasibility and demonstrates a superior performance even under a lower place density. Copyright © 2022, The Authors. All rights reserved.

关键词： Radon

Multi-view Unsupervised Representation Learning via Integration of Fuzzy Rules and Graph-Based Adaptive Regularization

学校读者我要写书评

暂无评论

IEEE Transactions on Fuzzy systems 2025年

作者： Zhu, Yi Li, Dong Xi, Chao Pedrycz, Witold Macau University of Science and Technology School of Computer Science and Engineering China East China University of Technology School of Mechanical and Electronic Engineering Nanchang330013 China Gliwice Department of Measurement and Control Systems Gliwice44-100 Poland University of Alberta Department of Electrical and Computer Engineering EdmontonABT6G 2R3 Canada Istinye University Research Center of Performance and Productivity Analysis Istanbul34010 Turkey

With the rapid advancement of data acquisition technologies, multiview data have been widely applied in fields such as social networks, computer vision, and natural language processing. Multiview data typically contain information arising from different views or sensors, offering more perspectives for observation. The multiview nature also brings challenges, such as high dimensionality, noise, heterogeneity, and redundancy. Particularly, in scenarios with limited labeled data, traditional single-view learning methods often struggle to handle these complex issues. To address this, this article proposes an unsupervised multiview learning framework that integrates Takagi–Sugeno–Kang fuzzy systems and graph-based adaptive regularization (MvTSK-GAR) to handle the heterogeneity and redundancy in multiview data effectively. Specifically, this article first captures the uncertainty in multiview data through fuzzy rules and models the structural relationships between the data using graph-based adaptive regularization. The framework does not rely on a large amount of labeled data. Instead, it integrates complementary information coming from different views to automatically mine latent patterns, thus generating more accurate and stable data representations. Experimental results demonstrate that the proposed framework performs well in various real-world applications, particularly excelling in high-dimensional data processing and noise reduction. Good performance in multiple publicly available datasets validates the effectiveness of our approach. Thecode is available at https://***/r/MvTSK-GAR-E3FB/***. © 1993-2012 IEEE.

关键词： Unsupervised learning

Modelling and Optimal Design of Hybrid Power System Photovoltaic/Solid Oxide Fuel Cell for a Mediterranean City

学校读者我要写书评

暂无评论

Energy engineering 2021年第6期118卷 1767-1781页

作者： Bachir Melzi Nesrine Kefif Mamdouh El Haj Assad Haleh Delnava Abdulkadir Hamid School of Materials Sciences and Engineering Wuhan University of TechnologyWuhanChina Power and Control Department Electronic and Electrical Engineering InstituteM’hamed Bougara UniversityBoumerdesAlgeria Sustainable and Renewable Energy Engineering Department University of SharjahSharjahUnited Arab Emirates Institute of Manufacturing Information and Systems National Cheng Kung UniversityTainanTaiwan Electrical Engineering Department University of SharjahSharjahUnited Arab Emirates

This work presents a hybrid power system consisting of photovoltaic and solid oxide fuel cell(PV-SOFC)for electricity production and hydrogen *** simulation of this hybrid system is adjusted for Bou-Zedjar city in north *** software was used for this simulation to calculate the power output and the total net present *** method used depends on the annual average monthly values of clearness index and radiation for which the energy contributions are determined for each component of PV/SOFC hybrid *** economic study is more important criterion in the proposed hybrid system,and the results show that the cost is very suitable for the use of this hybrid system,which ensures that the area is fed continuously with the sufficient energy for the load which assumed to be 500 kW in the peak *** optimized results of the present study show that the photovoltaic is capable of generating 8733 kW electricity while the SOFC produces 500 kW *** electrolyzer is capable of producing 238750 kg of hydrogen which is used as fuel in the SOFC to compensate the energy lack in nights and during peak season.

关键词： Energy storage PV/SOFC hybrid systems hydrogen production energy and economic optimization

Robust co-design framework for buildings operated by predictive control

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Falugi, P. O’Dwyer, E. Zagorowska, M.A. Kerrigan, E.C. Nie, Y. Strbac, G. Shah, N. Engineering and Construction Department University of East London London United Kingdom Department of Chemical Engineering Imperial College London London United Kingdom Mechanical Engineering Department Delft University of Technology Delft Netherlands Department of Aeronautics Imperial College London London United Kingdom Department of Electrical and Electronic Engineering Imperial College London London United Kingdom Department of Automatic Control and Systems Engineering University of Sheffield United Kingdom

Cost-effective decarbonisation of the built environment is a stepping stone to achieving net-zero carbon emissions since buildings are globally responsible for more than a quarter of global energy-related CO2 emissions. Improving energy utilization and decreasing costs naturally requires considering multiple domain-specific performance criteria. The resulting problem is often computationally infeasible. The paper proposes an approach based on decomposition and selection of significant operating conditions to achieve a formulation with reduced computational complexity. We present a robust framework to optimise the physical design, the controller, and the operation of residential buildings in an integrated fashion, considering external weather conditions and time-varying electricity prices. The framework explicitly includes operational constraints and increases the utilization of the energy generated by intermittent resources. A case study illustrates the potential of co-design in enhancing the reliability, flexibility and self-sufficiency of a system operating under different conditions. Specifically, numerical results demonstrate reductions in costs up to 30% compared to a deterministic formulation. Furthermore, the proposed approach achieves a computational time reduction at least 10 times lower compared to the original problem with a deterioration in the performance of only 0.6%. © 2024, CC BY.

关键词： Zero-carbon