检索结果-内蒙古大学图书馆

2020 Moscow Workshop on Electronic and Networking Technologies, MWENT 2020

作者： Zhmud, Vadim A. Stukach, Oleg V. Dimitrov, Lubomir V. Roth, Hubert Novosibirsk State Technical University Novosibirsk Russia Vice-Rector of Technical University of Sofia Sofia Bulgaria University of Siegen Dept. of Automatic Control Engineering Siegen Germany

ISBN: (纸本)9781728125718

The controller design for a high-order object prone to oscillations under sufficient of interest in automation and robotics is being solved. For the first time, the square root in the error growth detector used as a component for the cost function calculating unit is proposed. Justification for this proposal is given, and the effectiveness of such modification of the cost function is demonstrated on example of object. Software SimInTech was used for some calculations. It was shown that strong procedures of optimization are wide necessary for controller design. © 2020 IEEE.

关键词： Feedback

来源：评论

学校读者我要写书评

暂无评论

Using AoI forecasts in communicating and robust distributed model-predictive control

arXiv

引用

arXiv 2021年

作者： Hahn, Jannik Schoeffauer, Richard Wunder, Gerhard Stursberg, Olaf Control and System Theory Dept. of Electrical Engineering and Computer Science University of Kassel Germany Heisenberg CIT Group Free University of Berlin Dept. of Mathematics and Computer Science Germany

In order to enhance the performance of cyber-physical systems, this paper proposes the integrated design of distributed controllers for distributed plants and the control of the communication network. Conventional design methods use static interfaces between both entities and therefore rely on worst-case estimations of communication delay, often leading to conservative behavior of the overall system. By contrast, the present approach establishes a robust distributed model-predictive control scheme, in which the local subsystem controllers operate under the assumption of a variable communication schedule that is predicted by a network controller. Using appropriate models for the communication network, the network controller applies a predictive network policy for scheduling the communication among the subsystem controllers across the network. Given the resulting time-varying predictions of the age of information, the paper shows under which conditions the subsystem controllers can robustly stabilize the distributed system. To illustrate the approach, the paper also reports on the application to a vehicle platooning scenario. © 2021, CC BY.

关键词： Networked control systems

来源：评论

学校读者我要写书评

暂无评论

Assessment of Integrating Evacuated Tube-Based Domestic Electric/Solar Water Heater with an Aluminum Reflector for Managing Electrical Consumption

SSRN

引用

SSRN 2023年

作者： Sabry, Ahmad H. Al-Dujaili, Ayad Q. Oleiwi, Bushra Kadhim Alkubaisi, Yaser Mahmood Humaidi, Amjad J. Electrical Engineering Technical College Middle Technical University Baghdad Iraq Department of Control and Systems Engineering University of Technology-Iraq Baghdad Iraq Department of Computer Engineering Al-Nahrain University Al Jadriyah Bridge Baghdad64074 Iraq Department of Sustainability Management Dubai Academic Health Corporation Dubai4545 United Arab Emirates Control and Systems Eng. Dept. University of Technology Baghdad Iraq

Most places in the world have seen rapid increases in the need for power. It is essential to look for alternatives and energy-saving technologies because traditional fossil fuel power plants emit pollution in addition to the electricity they produce. This work considers a multi-generational heating system with the hybrid Electric/Solar Water Heaters (ESWHs) to replace electric water heaters (EWH)by combining the ESWH with an Aluminum reflector. This work experimental discusses the performance of the ESWH and the influence of placing a reflector plate underneath the evacuated tubes in Baghdad-Iraq. A test procedure to heat the water to a specified heating temperature over the whole day period was conducted to analyze the daily power consumption profile of the system. Four operational scenarios have been conducted including the mode;the ESWH as a solar water heater, ESWH as an electric water heater, ESWH without a reflector, and ESWH with a reflector plate. The experimental analysis confirmed that the presented multi-generational heating configuration could contribute to energy sustainably. The developed multi-generational heating system achieved an improvement in annual energy consumption of 15.4% over the hybrid electric/solar water heater and 46.2% over the traditional electrical water heater. © 2023, The Authors. All rights reserved.

关键词： Energy conservation

来源：评论

学校读者我要写书评

暂无评论

Beyond bandit feedback in online multiclass classification 21

Beyond bandit feedback in online multiclass classification

引用

Proceedings of the 35th International Conference on Neural Information Processing Systems

作者： Dirk van der Hoeven Federico Fusco Nicolò Cesa-Bianchi Dept. of Computer Science Università degli Studi di Milano Italy Dept. of Computer Control and Management Engineering Sapienza Università di Roma Italy DSRC & Dept. of Computer Science Università degli Studi di Milano Italy

ISBN: (纸本)9781713845393

We study the problem of online multiclass classification in a setting where the learner's feedback is determined by an arbitrary directed graph. While including bandit feedback as a special case, feedback graphs allow a much richer set of applications, including filtering and label efficient classification. We introduce GAP-PLETRON, the first online multiclass algorithm that works with arbitrary feedback graphs. For this new algorithm, we prove surrogate regret bounds that hold, both in expectation and with high probability, for a large class of surrogate losses. Our bounds are of order $B\sqrt{\rho KT}$, where B is the diameter of the prediction space, K is the number of classes, T is the time horizon, and ρ is the domination number (a graph-theoretic parameter affecting the amount of exploration). In the full information case, we show that GAPPLETRON achieves a constant surrogate regret of order B2K. We also prove a general lower bound of order max {B2K, √T} showing that our upper bounds are not significantly improvable. Experiments on synthetic data show that for various feedback graphs our algorithm is competitive against known baselines.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Beyond bandit feedback in online multiclass classification

arXiv

引用

arXiv 2021年

作者： van der Hoeven, Dirk Fusco, Federico Cesa-Bianchi, Nicolò Dept. of Computer Science Università degli Studi di Milano Italy Dept. of Computer Control and Management Engineering Sapienza Università di Roma Italy DSRC Dept. of Computer Science Università degli Studi di Milano Italy

We study the problem of online multiclass classification in a setting where the learner’s feedback is determined by an arbitrary directed graph. While including bandit feedback as a special case, feedback graphs allow a much richer set of applications, including filtering and label efficient classification. We introduce Gappletron, the first online multiclass algorithm that works with arbitrary feedback graphs. For this new algorithm, we prove surrogate regret bounds that hold, both in expectation and with high probability, for a large class of surrogate losses. Our bounds are of order B√ρKT, where B is the diameter of the prediction space, K is the number of classes, T is the time horizon, and ρ is the domination number (a graph-theoretic parameter affecting the amount of exploration). In the full information case, we show that Gappletron achieves a constant surrogate regret of order B2K. We also prove a general lower bound of order max {B2K, √T} showing that our upper bounds are not significantly improvable. Experiments on synthetic data show that for various feedback graphs our algorithm is competitive against known baselines. Copyright © 2021, The Authors. All rights reserved.

关键词： Directed graphs

来源：评论

学校读者我要写书评

暂无评论

Decentralized Federated Learning for Nonintrusive Load Monitoring in Smart Energy Communities

Decentralized Federated Learning for Nonintrusive Load Monit...

引用

Mediterranean Conference on control and Automation (MED)

作者： Alessandro Giuseppi Sabato Manfredi Danilo Menegatti Antonio Pietrabissa Cecilia Poli Dept. of Computer Control and Management Engineering (DIAG) University of Rome "La Sapienza" Rome Italy Dept. of Electrical Engineering and Information Technology University of Naples "Federico II" Naples Italy National Centre for Innovative Technologies in Public Health (TISP) Istituto Superiore di Sanit&#x00E0 Rome Italy

ISBN: (数字)9781665406734

ISBN: (纸本)9781665406741

Federated Learning is a distributed learning solution for machine learning problems without the need of collecting the available data in a single centralized data centre. With the standard FL approaches, model training is performed locally and a centralized server collects and elaborates the trainable parameters of the local models: even if data are not shared, the presence of the centralized server still rises trust and security issues. In this work, we introduce the Decentralized Federated Learning (DECFEDAVG) algorithm, which aims at achieving complete decentralization by the lack of a coordination server, and compare its performance against the original federated learning algorithm Federated Averaging (FEDAVG) over the Nonintrusive Load Monitoring problem.

关键词： Training Load monitoring Distance learning Distributed databases Machine learning Collaborative work Data models

来源：评论

学校读者我要写书评

暂无评论

Exploiting Prediction Error Inconsistencies through LSTM-based Classifiers to Detect Deepfake Videos 20

Exploiting Prediction Error Inconsistencies through LSTM-bas...

引用

8th ACM Workshop on Information Hiding and Multimedia Security, IH and MMSec 2020

作者： Amerini, Irene Caldelli, Roberto Dept. of Computer Control and Management Engineering Sapienza University of Rome Rome Italy Parma Italy Mercatorum University Rome Italy

ISBN: (纸本)9781450370509

The ability of artificial intelligence techniques to build synthesized brand new videos or to alter the facial expression of already existing ones has been efficiently demonstrated in the literature. The identification of such new threat generally known as Deepfake, but consisting of different techniques, is fundamental in multimedia forensics. In fact this kind of manipulated information could undermine and easily distort the public opinion on a certain person or about a specific event. Thus, in this paper, a new technique able to distinguish synthetic generated portrait videos from natural ones is introduced by exploiting inconsistencies due to the prediction error in the re-encoding phase. In particular, features based on inter-frame prediction error have been investigated jointly with a Long Short-Term Memory (LSTM) model network able to learn the temporal correlation among consecutive frames. Preliminary results have demonstrated that such sequence-based approach, used to distinguish between original and manipulated videos, highlights promising performances. © 2020 ACM.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Enabling Smart Agriculture in Nigeria: Application of Digital-Twin Technology 1

Enabling Smart Agriculture in Nigeria: Application of Digita...

引用

1st International Conference on Multidisciplinary engineering and Applied Science, ICMEAS 2021

作者： Elijah, Olakunle Rahim, Sharul Kamal A. Emmanuel, Abioye Abiodun Salihu, Yahaya Otuoze Usman, Zubair Gatugel Jimoh, Adinoyi Momoh Wireless Communication Center School of Electrical Engineering University of Technology Malaysia Johor Bahru Malaysia School of Electrical Engineering University of Technology Malaysia Control and Mechatronics Engr. Dept. Johor Bahru Malaysia Kaduna Polytechnic Computer Engineering Department Kaduna Nigeria Saudi Telecommunication Company Riyadh Saudi Arabia

ISBN: (纸本)9781665434935

The digital twin (DT) is an emerging technology and one of the industry 4.0 technologies. The research in the application of DT in agriculture is currently attracting research interest. In this paper, we provide an overview of DT and discuss possible areas in which it can enable smart agriculture in Nigeria. The benefits and challenges of deploying the DT are also presented. Finally, methods that can be adopted in the application of DT towards solving the problems facing Nigeria's agriculture sector are proposed. © 2021 IEEE.

关键词： Agriculture

来源：评论

学校读者我要写书评

暂无评论

Improving super-resolution performance using meta-attention layers

arXiv

引用

arXiv 2021年

作者： Aquilina, Matthew Galea, Christian Abela, John Camilleri, Kenneth P. Farrugia, Reuben A. Dept. of Communications & Computer Engineering Faculty of ICT University of Malta UM Msida Malta Malta Deanery of Molecular Genetic & Population Health Sciences University of Edinburgh Scotland Edinburgh United Kingdom Dept. of Communications & Computer Engineering Faculty of ICT UM Dept. of Computer Information Systems Faculty of ICT UM Dept. of Systems & Control Engineering Faculty of Engineering UM

Convolutional Neural Networks (CNNs) have achieved impressive results across many super-resolution (SR) and image restoration tasks. While many such networks can upscale low-resolution (LR) images using just the raw pixel-level information, the ill-posed nature of SR can make it difficult to accurately super-resolve an image which has undergone multiple different degradations. Additional information (metadata) describing the degradation process (such as the blur kernel applied, compression level, etc.) can guide networks to super-resolve LR images with higher fidelity to the original source. Previous attempts at informing SR networks with degradation parameters have indeed been able to improve performance in a number of scenarios. However, due to the fully-convolutional nature of many SR networks, most of these metadata fusion methods either require a complete architectural change, or necessitate the addition of significant extra complexity. Thus, these approaches are difficult to introduce into arbitrary SR networks without considerable design alterations. In this paper, we introduce meta-attention, a simple mechanism which allows any SR CNN to exploit the information available in relevant degradation parameters. The mechanism functions by translating the metadata into a channel attention vector, which in turn selectively modulates the network’s feature maps. Incorporating meta-attention into SR networks is straightforward, as it requires no specific type of architecture to function correctly. Extensive testing has shown that meta-attention can consistently improve the pixel-level accuracy of state-of-the-art (SOTA) networks when provided with relevant degradation metadata. Despite average memory/runtime overheads of less than ≈2.6%/0.025 seconds for the datasets and models considered, meta-attention improves the performance for both PSNR and SSIM;for PSNR, the gain on blurred/downsampled (×4) images is of 0.2969 dB (on average) and 0.3320 dB for SOTA general and f

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Robust Interval Criterion for a Steady Value 30

Robust Interval Criterion for a Steady Value

引用

30th International Scientific Symposium Metrology and Metrology Assurance, MMA 2020

作者： Bekhtin, Y.S. Lupachev, A.A. Kyaw, N.M. Kovalenko, A.V. Petsinyarzh, A.R. National Research University Moscow Power Engineering Institute' Dept. of Diagnostics and Measurement Technologies Moscow Russia Moscow State Technical University Named after N. Bauman Dept. of Automatic Control Systems Moscow Russia

ISBN: (纸本)9781728197197

The work is a development of the interval criterion for determining the moment when the steady-state value of the transition signal occurs. These criteria are used in technologies related to testing complex objects under conditions of parametric uncertainty of its model. The transient signal is analyzed in on-line mode. Therefore, the accuracy of the decision about the time of the end of the tests determines the cost of conducting them. Such tests are characterized by significant dynamic errors that significantly exceed the allowed level. The reasons for this are the parametric uncertainty in the mathematical model of the object and the inability of the deterministic interval criterion to correctly issue a solution under these conditions. It was previously determined that the interval criterion is characterized by the presence of an asymptotic critical value of the criterion. Exceeding the object's real time constant over the critical value gives a false positive result. This situation is characterized by the fact that the desired moment is falsely determined significantly earlier than the optimal solution. You can avoid this situation if you set the criteria to the maximum constant of the object's time. However, this choice leads to significant time losses when analyzing the transition signal. The solution of the problem of guaranteed provision of a given level of dynamic error over the entire range of values of the object model parameter is possible using a robust algorithm. The basis for constructing a robust criterion is to control the duration of the observation interval. For this purpose, the current information about the analyzed signal is used. There are three ways to apply the current information. The first approach is based on the use of an extrapolated estimate of the established value. This allows you to determine the estimate of the current dynamic error and prevent a falsely positive decision of the criterion. The second approach is based on the analys

关键词： analysis of the transition process duration of the observation interval duration of the transition process dynamic error analysis false positive solution robust algorithm

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：