检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Heo, DongNyeong Lee, Doyoung Kim, Hee-Gon Park, Suhyun Choi, Heeyoul Dept. of Information and Communication Engineering Handong Global University Pohang Korea Republic of Dept. of Computer Science and Engineering Pohang University of Science and Technology Pohang Korea Republic of

In the management of computer network systems, the service function chaining (SFC) modules play an important role by generating efficient paths for network traffic through physical servers with virtualized network functions (VNF). To provide the highest quality of services, the SFC module should generate a valid path quickly even in various network topology situations including dynamic VNF resources, various requests, and changes of topologies. The previous supervised learning method demonstrated that the network features can be represented by graph neural networks (GNNs) for the SFC task. However, the performance was limited to only the fixed topology with labeled data. In this paper, we apply reinforcement learning methods for training models on various network topologies with unlabeled data. In the experiments, compared to the previous supervised learning method, the proposed methods demonstrated remarkable flexibility in new topologies without re-designing and re-training, while preserving a similar level of performance. Copyright © 2020, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Statistical Analysis of Lightning-Induced Voltages in the Case of Lossy Ground 19

Statistical Analysis of Lightning-Induced Voltages in the Ca...

引用

19th IEEE International Conference on Environment and Electrical engineering and 2019 IEEE Industrial and Commercial Power Systems Europe, EEEIC/I and CPS Europe 2019

作者： Andreotti, Amedeo Masone, Adriano Mottola, Fabio Proto, Daniela Rakov, Vladimir A. Dept. of Electrical Engineering and Information Technology University of Naples Federico II Naples Italy Dept. of Electrical and Computer Engineering University of Florida GainesvilleFL United States

ISBN: (纸本)9781728106526

In this paper, statistical analysis of lightning-induced voltages on distribution lines accounting for lossy ground is proposed. The analysis is performed by means of a Monte Carlo-based probabilistic approach. It aims at deducing parametric distributions that best fit the probability density functions of the induced voltages. A lightning model based on step-function channel-base current is employed. © 2019 IEEE.

关键词： Statistical methods

来源：评论

学校读者我要写书评

暂无评论

On robust precoder design for energy-efficient MIMO-cognitive relay networks

On robust precoder design for energy-efficient MIMO-cognitiv...

引用

2019 IEEE Conference on information and Communication technology, CICT 2019

作者： Maurya, Shikha Bansal, Matadeen PDPM-Indian Institute of Information Technology Design and Manufacturing Dept. of Electronics and Communication Engineering Jabalpur India

ISBN: (纸本)9781728153988

This paper considers the robust relay precoder design problem for multi-input multi-output cognitive relay networks (MIMO-CRNs), where a pair of secondary user (SU) communicates using an amplify-and-forward (AF) half-duplex (HD) relay in the presence of a primary user (PU). The channel state information (CSI) of the relay-PU channel at the relay node is assumed to be imperfect. The channel imperfection is considered in the form of channel uncertainties, which is modelled by using the ellipsoidal model. Taking into account the imperfect CSI, we design the robust relay precoder to maximize the energy efficiency (EE) of the SU subject to the interference and transmit power constraints. An efficient solution, based on the constraint relaxation and the fractional programming theory, is proposed to tackle the robust precoding problem. Numerical results demonstrate that the proposed robust relay precoder scheme maximizes the EE of the SU while securing the transmission of the PU by satisfying the interference constraint for different channel uncertainties. © 2019 IEEE.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

An approach to linear active disturbance rejection controller design with a linear quadratic regulator for a non-minimum phase system 38

An approach to linear active disturbance rejection controlle...

引用

38th Chinese control Conference, CCC 2019

作者： Tanaka, Ryo Koga, Tetsunori Dept. of Control and Information Systems Engineering Kurume College 1-1-1 Komorino Kurume Fukuoka830-8555 Japan

ISBN: (纸本)9789881563972

This study proposes an approach to determining the controller gain based on the linear quadratic regulator (LQR) method for a non-minimum phase plant. The extended state observer is designed based on the conventional pole placement method to prevent the observer from being unstable. The control law is determined based on the LQR method in terms of fast responses of the plant outputs and the magnitude of its inputs. The stability of the whole closed-loop control system is evaluated using the Routh-Hurwitz stability criterion. The effectiveness of the proposed method is confirmed by performing numerical simulations and comparing their results with those of the conventional I-PD control. In addition, a superior robustness of the plant with a modeling error is achieved compared with that of the fundamental I-PD control system. Finally, the proposed LADRC with an LQR is confirmed to demonstrate a performance that is approximately the same as that of the conventional LADRC. © 2019 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Observers Stability criteria Mathematical model Bandwidth Regulators

来源：评论

学校读者我要写书评

暂无评论

General-Purpose Intelligent Management System of Logistics Fleet

General-Purpose Intelligent Management System of Logistics F...

引用

2019 International Conference on Intelligent Computing and Its Emerging Applications, ICEA 2019

作者： Wu, Hsin-Te Hu, Wu-Chih Jiang, Bing-Wei Dept. of Computer Science and Information Engineering National Penghu University of Science and Technology Penghu County Taiwan

ISBN: (纸本)9781728131597

This study proposes an 'General-Purpose Intelligent Management System of Logistics Fleet' aimed at providing an easy-to-install and financially affordable system that can service small and medium logistic businesses while also resolving common issues they encounter. The proposed system boasts the following features: (1) logistic vehicle safety detection, which ensures vehicle safety, (2) transparency of the logistic vehicle's traveling route and work progress, so that both the logistic enterprise and the merchandise shipper can easily track deliveries, (3) merchandise-related temperature and humidity monitoring, to prevent goods from being damaged, (4) integration of beacon technology with GPS for monitoring of delivery processes, and (5) charts and graphs analysis that can help businesses improve their strategies. With the aforementioned features, the proposed system can achieve the goal of realizing a comprehensive intelligent logistics system that safeguards vehicle safety. Additionally, the system is available via rental, reducing establishment costs for small and medium logistic businesses. The system is also easy to install - it does not require damage to the vehicle body, nor does it require installation of signal cable;all in all, it promotes the system's mobility. © 2019 IEEE.

关键词： Vehicle safety

来源：评论

学校读者我要写书评

暂无评论

Identifiability issues in estimating the impact of interventions on Covid-19 spread

引用

IFAC-PapersOnLine 2020年第5期53卷 829-832页

作者： Fredrik Gustafsson Joakim Jaldén Bo Bernhardsson Kristian Soltesz Linköping University Div. of Automatic Control Linköping Sweden. KTH Royal Institute of Technology Div. Division of Information Science and Engineering Stockholm Sweden. Lund University Dept. Automatic Control Lund Sweden.

The Covid-19 pandemic has spawned numerous dynamic modeling attempts aimed at estimation, prediction, and ultimately control. The predictive power of these attempts has varied, and there remains a lack of consensus regarding the mechanisms of virus spread and the effectiveness of various non-pharmaceutical interventions that have been enforced regionally as well as nationally. Setting out in data available in the spring of 2020, and with a now-famous model by Imperial College researchers as example, we employ an information-theoretical approach to shed light on why the predictive power of early modeling approaches have remained disappointingly poor.

关键词： Bayesian methods Covid-19 Epidemiology Identifiability Sensitivity

来源：评论

学校读者我要写书评

暂无评论

Virtual Cluster Head Based PSO and Fuzzy Logic Approach for WSN to Extend Network Lifetime

Virtual Cluster Head Based PSO and Fuzzy Logic Approach for ...

引用

2020 International Conference on Computing and information technology, ICCIT 2020

作者： Manikandan, V. Mavaluru, DInesh Gobinathan, K. Rajanarayanan, S. Jenifer, M. Rohini, R. Lebanese French University Department of Computer Networking Erbil Kurdistan Region Iraq Saudi Electronic University College of Computing and Informatics Department of Information Technology Saudi Arabia Gnanamani Collge of Technology Department of CSE Namakkal India Arba Minch University Dept. of Business Administration and Information System Ethiopia Arba Minch University Arba Minch Institute of Technology Faculty of Computing and Software Engineering Ethiopia Vivekanandha College of Engineering for Women Department of CSE Namakkal India

ISBN: (纸本)9781728126807

In recent times, Wireless Sensor Networks (WSNs) are broadly utilized in targeted monitoring applications. Traditional target coverage techniques usually consider that environment is known completely and every target is covered by single sensor. However those algorithms are inflexible when the sensor is about to die, that is, lack of energy and therefore target has to be covered with more than a sensor which is termed as n coverage crisis. In general, n coverage problem is energy and time consuming process, as well sensor organization is needed all the time. To resolve this crisis, this work anticipates a n coverage model with VCH-PSO (Virtual Cluster Head based Particle Swarm Optimization and EFLM (Energy management based Fuzzy logic Model) to enlarge the lifetime of WSN. During the search of optimal area coverage, diverse factors like node position, energy consumption, and coverage range of sensors are considered significantly. Simulation was carried out in MATLAB environment and compared with prevailing techniques. The proposed model shows better trade off in terms of network lifetime and time needed for switching between various coverage regions. © 2020 IEEE.

关键词： Fuzzy logic

来源：评论

学校读者我要写书评

暂无评论

Improved shuffled frog Leaping Algorithm for Path Planning of multiple Mobile-Robot 2

Improved shuffled frog Leaping Algorithm for Path Planning o...

引用

2nd International Conference on Innovations in Electronics, Signal Processing and Communication, IESC 2019

作者： Paikray, H.K. Das, P.K. Panda, S. Balabantaray, B.K. VSSUT Dept. of Computer Applications BurlaOdisha India VSSUT Dept. of Information Technology BurlaOdisha India NIT Dept. of Computer Science and Engineering Meghalaya India

ISBN: (纸本)9781728107448

Improved shuffled frog leaping algorithm (ISFLA) has been proposed in this paper for multi-robot path planning in a clutter environment. Basic SFLA algorithm has been improved in the local search process by adding the weight and acceleration factor in the original version of SFLA to avoid the local optima and premature convergence. ISFLA technique has been embedded into the multi-robot system in a dynamic framework for generating optimal trajectory path by determining an optimal subsequent position for each robot from their existing position. Fitness function have been formulated by considering the different constraints and then, it optimized through ISFLA for generating optimal trajectory smooth path by avoiding the obstacles present in the environment. Finally, the simulation and experiment have been carried out to validate the performance of the proposed algorithm. The results obtained through ISFLA, SFLA and IGSA in terms of runtime, path deviation, the path travelled and energy utilized during travel shows ISFLA has outperformed its competitors. © 2019 IEEE.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Privacy-preserving training of tree ensembles over continuous data

arXiv

引用

arXiv 2021年

作者： Adams, Samuel Choudhary, Chaitali de Cock, Martine Dowsley, Rafael Melanson, David Nascimento, Anderson C.A. Railsback, Davis Shen, Jianwei School of Engineering and Technology University of Washington Tacoma TacomaWA98402 United States Dept. of Applied Mathematics Computer Science and Statistics Ghent University Faculty of Information Technology Monash University Clayton Australia Department of Computer Science University of Arizona

Most existing Secure Multi-Party Computation (MPC) protocols for privacy-preserving training of decision trees over distributed data assume that the features are categorical. In real-life applications, features are often numerical. The standard "in the clear" algorithm to grow decision trees on data with continuous values requires sorting of training examples for each feature in the quest for an optimal cut-point in the range of feature values in each node. Sorting is an expensive operation in MPC, hence finding secure protocols that avoid such an expensive step is a relevant problem in privacy-preserving machine learning. In this paper we propose three more efficient alternatives for secure training of decision tree based models on data with continuous features, namely: (1) secure discretization of the data, followed by secure training of a decision tree over the discretized data;(2) secure discretization of the data, followed by secure training of a random forest over the discretized data;and (3) secure training of extremely randomized trees ("extra-trees") on the original data. Approaches (2) and (3) both involve randomizing feature choices. In addition, in approach (3) cut-points are chosen randomly as well, thereby alleviating the need to sort or to discretize the data up front. We implemented all proposed solutions in the semi-honest setting with additive secret sharing based MPC. In addition to mathematically proving that all proposed approaches are correct and secure, we experimentally evaluated and compared them in terms of classification accuracy and runtime. We privately train tree ensembles over data sets with 1000s of instances or features in a few minutes, with accuracies that are at par with those obtained in the clear. This makes our solution orders of magnitude more efficient than the existing approaches, which are based on oblivious sorting. Copyright © 2021, The Authors. All rights reserved.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Model-based electron density profile estimation and control, applied to ITER

arXiv

引用

arXiv 2021年

作者： Bosman, Thomas van Berkel, M. de Baar, M.R. DIFFER - Dutch Institute for Fundamental Energy Research PO Box 6336 Eindhoven5600HH Netherlands Eindhoven University of Technology Dept. of Mechanical Engineering Control Systems Technology Group PO Box 513 Eindhoven5600MB Netherlands

In contemporary magnetic confinement devices, the density distribution is sensed with interferometers and actuated with feedback controlled gas injection and open-loop pellet injection. This is at variance with the density control for ITER and DEMO, that will depend mainly on pellet injection as an actuator in feed-back control. This paper presents recent developments in state estimation and control of the electron density profile for ITER using relevant sensors and actuators. As a first step, Thomson scattering is included in an existing dynamic state observer. Second, model predictive control is developed as a strategy to regulate the density profile while avoiding limits associated with the total density (Greenwald limit) or gradients in the density distribution (e.g. neoclassical impurity transport). Simulations show that high quality density profile estimation can be achieved with Thomson Scattering and that the controller is capable of regulating the distribution as desired. Copyright © 2021, The Authors. All rights reserved.

关键词： Light scattering

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：