检索结果-内蒙古大学图书馆

Learning the continuous-time optimal decision law from discrete-time rewards

National Science Open 2024年第5期3卷 130-147页

作者： Ci Chen Lihua Xie Kan Xie Frank Leroy Lewis Yilu Liu Shengli Xie School of Automation Guangdong University of TechnologyGuangdong Key Laboratory of IoT Information TechnologyGuangzhou 510006China Key Laboratory of Intelligent Information Processing and System Integration of IoT Ministry of EducationGuangzhou 510006China School of Electrical and Electronic Engineering Nanyang Technological UniversitySingapore 639798Singapore 111 Center for Intelligent Batch Manufacturing Based on IoT Technology Guangzhou 510006China UTA Research Institute the University of Texas at ArlingtonFort Worth 76118USA Department of Electrical Engineering and Computer Science University of TennesseeKnoxville 37996USA Oak Ridge National Laboratory Oak Ridge 37830USA Guangdong-HongKong-Macao Joint Laboratory for Smart Discrete Manufacturing Guangzhou 510006China

The concept of reward is fundamental in reinforcement learning with a wide range of applications in natural and social *** an interpretable reward for decision-making that largely shapes the system's behavior has always been a challenge in reinforcement *** this work,we explore a discrete-time reward for reinforcement learning in continuous time and action spaces that represent many phenomena captured by applying physical *** find that the discrete-time reward leads to the extraction of the unique continuous-time decision law and improved computational efficiency by dropping the integrator operator that appears in classical results with integral *** apply this finding to solve output-feedback design problems in power *** results reveal that our approach removes an intermediate stage of identifying dynamical *** work suggests that the discrete-time reward is efficient in search of the desired decision law,which provides a computational tool to understand and modify the behavior of large-scale engineering systems using the optimal learned decision.

关键词： continuous-time state and action decision law learning discrete-time reward dynamical systems reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Investigation the Performance Effect of QOS in MPLS-TE Network

Investigation the Performance Effect of QOS in MPLS-TE Netwo...

引用

Signal, Control and Communication (SCC), International Conference on

作者： Kenz A. Bozed Ahlam Mohammed Elbeskri Jazia R. Ali Zreg Amer R. Zerek Department of Computer System Design Faculty of Information Technology Benghazi University Benghazi Libya Higher institute of Technical Water Affairs Sabratha Libya Sabratha University College of Science Sabratha Libya Electrical and Electronic Eng. Department Faculty of Engineering Zawia University Zawia Libya

ISBN: (数字)9781665402705

ISBN: (纸本)9781665402712

Due to the need for different communication types (Voice, video, and data) over the network, vendors improving enterprise networks for this purpose to minimize delays in order to support the better result, some applications like voice considered real-time applications which suffer from delay, jitter and packet losses, This paper discusses comparison of QoS performance between three QoS algorithms (PQ, FIFO, and WFQ), when using MPLS-TE technology considering the VoIP QoS parameters (end to end delay, jitter, and packet loss, as simulation done by OPNET modeler 14.5.

关键词： Packet loss Quality of service Switches Jitter Streaming media Data models Routing protocols

来源：评论

学校读者我要写书评

暂无评论

Transverse Patterns and Dual-Frequency Lasing in a Low-Noise Nonplanar-Ring Orbital-Angular-Momentum Oscillator

引用

Physical Review Applied 2020年第2期13卷 024067-024067页

作者： Yaqin Cao Ping Liu Cuifang Hou Yanne K. Chembo Zehuang Lu Guoping Lin MOE Key Laboratory of Fundamental Physical Quantities Measurement Hubei Key Laboratory of Gravitation and Quantum Physics PGMF and School of Physics Huazhong University of Science and Technology Wuhan 430074 China Institute for Research in Electronics and Applied Physics (IREAP) and Department of Electrical and Computer Engineering University of Maryland College Park Maryland 20742 USA Ministry of Industry and Information Technology Key Lab of Micro-Nano Optoelectronic Information System School of Science Harbin Institute of Technology Shenzhen 518055 China

Monolithic optical cavities employing total internal reflections are appealing compact platforms for a wide range of applications from fundamental physics to industry applications. We characterize the transverse patterns of a millimeter-size monolithic nonplanar ring vortex laser pumped by a Gaussian beam. Vortex beams carrying orbital angular momentum (OAM) up to 30 together with vortex crystals and petal patterns are observed. The rigid nature of the monolithic cavity brings along its low-noise lasing performance for these beams. A frequency noise floor as low as 0.1Hz/Hz1/2 corresponding to sub-Hz instantaneous linewidth is measured. Furthermore, we demonstrate low-noise dual-frequency lasing with phase noise as low as −118dBc/Hz at 10-kHz offset for the beatnote at 8.2 GHz. We expect that such versatile and compact OAM laser sources can facilitate multiple applications including optical communications, optical tweezers, and laser metrology such as dual-frequency Doppler lidar.

关键词： Angular momentum of light Optical quantum information processing Optical sources & detectors Optical vortices Photonics Solid state lasers Spatial profiles of optical beams Cavity resonators

来源：评论

学校读者我要写书评

暂无评论

Cloud-Based IoT Solutions for Smart Grids: Advancing Smart Technologies in Energy Management

Cloud-Based IoT Solutions for Smart Grids: Advancing Smart T...

引用

International Conference on Electrical Power and Energy systems (ICEPES)

作者： Franciskus Antonius Alijoyo Deepak A. Vidhate Chamandeep Kaur V Nivedan V. Kanpur Rani A. Balakumar School of Business and Information Technology STMIK LIKMI Bandung Indonesia Department of Information Technology Dr. Vithalrao Vikhe Patil College of Engineering Ahmednagar Maharashtra India Department of Computer Science Jazan University Jazan Saudi Arabia Department of Electronics and Communication System Sri Ramakrishna College of Arts & Science Coimbatore India Hindustan Institute of Technology and Science Chennai India Department of ECE K.Ramakrishnan College of Engineering Trichy India

ISBN: (数字)9798350390728

ISBN: (纸本)9798350390735

The incorporation of Internet of Things (IoT) cloud computing solutions with smart grids signifies a significant advancement in energy management. Traditional methods, though beneficial, often lack scalability and real-time capabilities, limiting their effectiveness in managing the complexity of modern energy systems. In this paper, a novel approach cloud-based IoT technologies to address these shortcomings and enhance smart grid functionalities. Existing energy management methods heavily rely on localized monitoring and control systems, constraining scalability and real-time responsiveness. Additionally, these methods struggle to handle the immense data generated by IoT devices dispersed throughout the grid. The proposed approach tackles these challenges by utilizing cloud computing to store, process, and analyze IoT sensor data in real-time. The novelty of this method lies in seamlessly integrating cloud-based platforms with IoT devices across the smart grid. Through utilising cloud resources, the limitations of traditional approaches are overcome, enabling scalable, real-time oversight and management of grid assets. The methodology involves deploying IoT sensors across the grid to compile information about energy usage, generation, and distribution, which is then transmitted to cloud servers for analysis and decision-making. Through simulations and real-world experiments, the effectiveness of this approach in optimizing grid performance, improving reliability, and facilitating demand-response programs is demonstrated. The results exhibit significant enhancements in grid efficiency and resilience, showcasing the potential of cloud-based IoT solutions to transform energy management in smart grids. Overall, this proposed method presents a promising pathway towards establishing more efficient, sustainable, and resilient energy infrastructure for the future.

关键词： Cloud computing Scalability Transforms Real-time systems Smart grids Internet of Things Servers

来源：评论

学校读者我要写书评

暂无评论

The Weapon Target Assignment in Adversarial Environments 1

引用

2nd International Conference on Cognitive Computation and systems, ICCCS 2023

作者： Gao, Rui Zheng, Shaoqiu Wang, Kai Zhang, Longlong Zhu, Zhiyuan Yuan, Xiaohu College of Electronic and Information Engineering Southwest University Chongqing400715 China Key Lab of Information System Requirement Nanjing Research Institute of Electronics Engineering Nanjing210007 China Department of Computer Science and Technology Tsinghua University Beijing100084 China

ISBN: (数字)9789819708857

ISBN: (纸本)9789819708840

In context of the current weapon target assignment (WTA) problem, consideration of target capability is often disregarded. To address this issue, we propose an optimized model for weapon target assignment in complex environments. Our model provides a comprehensive description and conducts a detailed analysis of constraints and objective functions in the context of adversarial weapon target assignment (AWTA). To efficiently tackle the assignment problem, we employ the multi-particle swarm optimization algorithm (MOPSO). During the optimization process, we incorporate learning factors and inertia weights to update particle positions, seamlessly implementing the model with a set of adjustable parameters. Experimental results demonstrate that our model effectively captures the concept of adversarial scenarios. Furthermore, by utilizing the MOPSO optimization algorithm, we achieve a superior Pareto front even for small-scale adversarial scenarios, successfully resolving the adversarial WTA problem. Our research contributes an effective optimization approach to address the weapon task assignment problem and offers valuable inspiration for future investigations into multi-objective research. In conclusion, our study reveals the potential of multi-objective optimization research in the context of weapon target assignment. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

New Approach for Efficient Malicious Multiparty Private Set Intersection

SSRN

引用

SSRN 2023年

作者： Lv, Siyi Wei, Yu Jia, Jingyu Li, Xinhao Liu, Zheli Chen, Xiaofeng Guo, Liang College of Cyber Science The College of Computer Science Key Laboratory of Data and Intelligent System Security Ministry of Education Nankai University Tianjin China Department of Computer Science Purdue University United States School of Cyber Engineering Xidian University Xi’an China Huawei Technology Co. Ltd Shenzhen China

The Multiparty Private Set Intersection (MPSI) protocol allows untrusted parties to compute the intersection of their sets without revealing any additional information. However, existing solutions face challenges in terms of security and efficiency. Some schemes are secure only against semi-honest adversaries and cannot effectively defend against malicious adversaries. Other schemes, while capable of withstanding malicious adversaries, exhibit efficiency problems, especially as the number of corrupt participants increases. A practical solution must maintain high security and efficiency, even when handling large-scale data and a majority of corrupted *** paper introduces a novel scheme named TH-PSI, built upon a new star-shaped topological network communication framework based on the trusted execution environment. TH-PSI has been rigorously proven to be secure within the standard UC framework against malicious adversaries. To demonstrate the efficiency of TH-PSI, we implement the TH-PSI scheme and tested it in both LAN and WAN settings, involving up to 30 participants and datasets as large as $2^{22}$. We compare TH-PSI with state-of-the-art schemes, ENOC21 and NTY21. Our experiments show that TH-PSI is an efficient solution capable of delivering results within a matter of seconds, even when dealing with data at the million-level and a majority of corrupted participants. © 2023, The Authors. All rights reserved.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Relation between EMG signal activation and time lags using feature analysis during dynamic contraction

Relation between EMG signal activation and time lags using f...

引用

International Conference of Advanced Informatics: Concept, Theory and Application (ICAICTA)

作者： Nizam Uddin Ahamed Omar Altwijri S. A. M Matiur Rahaman Nasim Ahmed Mahdi Alqahtani Kenneth Sundaraj Mechatronic Engineering University Malaysia Pahang Pekan Pahang Malaysia College of Computer Science and Information System Najran University Najran Saudi Arabia Biomedical Technology Department King Saud University Saudi Arabia School of Computer and Communication Engineering Universiti Malaysia Perlis Malaysia Universiti Teknikal Malaysia Melaka MALAYSIA

This study examined the effects of electromyographic (EMG) signals from Biceps Brachii (BB) muscle on the root mean square (RMS)-time relationships during dynamic contraction. Ten healthy and right hand dominated male subjects were volunteered for the experiments. The RMS features were extracted from the corresponding EMG signals (amplitude of the full wave EMG) for 10 seconds in 5 minutes intervals between each trial. Ten seconds (or 10000 ms) were divided into 4 time lags to identify the muscle activity and relationship between EMG and time using different statistical analysing techniques, such as mean, regression analysis, correlation, ANOVA, and coefficient of variation (CoV) for muscle activity variation. The results shows that large positive linear association between EMG and endurance time where the points are close to the linear trend line (R squared = 0.93 and F-ratio = 453.1). Signal steadiness is better during last time lags (1.66% during 7501-10000 ms) compared to initial time duration (10.35% during 0-2500 ms).

关键词： Electromyography Muscles Feature extraction Elbow Correlation Protocols Joints

来源：评论

学校读者我要写书评

暂无评论

PISTA-SENSE-ResNet for Parallel MRI Reconstruction

arXiv

引用

arXiv 2019年

作者： Lu, Tieyuan Zhang, Xinlin Huang, Yihui Yang, Yonggui Guo, Gang Bao, Lijun Huang, Feng Guo, Di Qu, Xiaobo Xiamen University Xiamen China Department of Radiology The Second Affiliated Hospital of Xiamen Medical College Xiamen China Neusoft Medical System Shanghai China Fujian Provincial University Key Laboratory of Internet of Things Application Technology School of Computer and Information Engineering Xiamen University of Technology Xiamen China

Magnetic resonance imaging has been widely applied in clinical diagnosis, however, is limited by its long data acquisition time. Although imaging can be accelerated by sparse sampling and parallel imaging, achieving promising reconstruction images with a fast reconstruction speed remains a challenge. Recently, deep learning approaches have attracted a lot of attention for its encouraging reconstruction results but without a proper interpretability. In this letter, to enable high-quality image reconstruction for the parallel magnetic resonance imaging, we design the network structure from the perspective of sparse iterative reconstruction and enhance it with the residual structure. The experimental results of a public knee dataset show that compared with the optimization-based method and the latest deep learning parallel imaging methods, the proposed network has less error in reconstruction and is more stable under different acceleration factors. Copyright © 2019, The Authors. All rights reserved.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

ESTIMATING LIVE FUEL MOISTURE IN SOUTHERN CALIFORNIA USING REMOTE SENSING VEGETATION WATER CONTENT PROXIES

ESTIMATING LIVE FUEL MOISTURE IN SOUTHERN CALIFORNIA USING R...

引用

IEEE International Geoscience and Remote Sensing Symposium

作者： Shenyue Jia Seung Hee Kim Son V. Nghiem Wonhee Cho Menas C. Kafatos Center of Excellence in Earth System Modeling and Observations (CEESMO) Chapman University Orange CA USA Jet Propulsion Laboratory California Institute of Technology Pasadena CA USA Department of Computer and Information Communication Korea Soongsil Cyber University Seoul Korea

Wildfires are a major ecological disturbance in Southern California and often lead to great destruction along the Wildland-Urban Interface. Live fuel moisture has been used as an important indicator of wildfire risk in measurements of vegetation water content. However, the limited field measurements of live fuel moisture in both time and space have affected the accuracy of wildfire risk estimations. Traditional estimation of live fuel moisture using remote sensing data was based on vegetation indices, indirect proxies of vegetation water content and subject to influence from weather conditions. In this study, we investigated the feasibility of estimating live fuel moisture using vegetation indices, Soil Moisture Active Passive L-band soil moisture data and the modeled vegetation water content using a nonlinear model based on VIs and the stem factor associated with remote sensing moisture data products. The stem factor describes the peak amount of water residing in stems of plants and varies by land cover. We also compared the outcomes from regression models and recurrent neural network using the same independent variables. We found the modeled vegetation water content outperformed vegetation indices and the L-band soil moisture observations, suggesting a nonlinear relationship between live fuel moisture and the remotely sensed vegetation signatures. We discuss our results which will improve the predictability of live fuel moisture.

关键词： Fires Vegetation mapping Moisture Remote sensing Estimation Fuels Soil moisture

来源：评论

学校读者我要写书评

暂无评论

Special session panel discussion: Methodological issues in the application of learning methods to climate modeling and earth sciences

Special session panel discussion: Methodological issues in t...

引用

International Joint Conference on Neural Networks, IJCNN 2005

作者： Cherkassky, Vladimir Krasnopolsky, Vladimir M. Solomatine, D.P. Valdés, Julio J. University of Minnesota Department of Electrical and Computer Engineering Minneapolis MN 55455 United States Earth System Science Interdisciplinary Center University of Maryland MD United States SAIC EMC/NCEP/NOAA MD United States UNESCO IHE Institute for Water Education P.O. Box 3015 2601 DA Delft Netherlands National Research Council Institute for Information Technology Ottawa Ont. K1AOR6 Canada

This special session has been motivated by the growing importance of data-driven modeling in Earth Sciences, Climate Modeling, Meteorological and Oceanographic Applications, Geophysical Data Processing, and Hydrology. Of particular interest are the methodological aspects of learning methods, with the clarification of the advantages and limitations of learning techniques in the context of specific applications. This panel will include informal presentations by the session co-chairs followed by questions and answers from the audience. Topics of discussion include the following: to identify major types of problems encountered in this field;how to estimate the quality of data-driven models;what are specific characteristics of data sets in Climate Modeling/ Earth Sciences that make them different from other applications;try to come to an agreement on possible benchmark data sets in this field. © 2005 IEEE.

关键词： Learning systems

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：