检索结果-内蒙古大学图书馆

16th International Conference on Electronics, Computers and Artificial Intelligence, ECAI 2024

作者： Mironela, Pirnau Iustin, Priescu Mihaela, Priescu Catalina Claudiu, Pirnau Daniel, Ghiculescu Liviu 'Titu Maiorescu' University Faculty of Informatics Department of Informatics Bucharest Romania National University of Science and Technology Politehnica Bucharest Faculty of Automatic Control and Computer Science Bucharest Romania National University of Science and Technology Politehnica Bucharest Faculty of Industrial Engineering and Robotics Manufacturing Engineering Department Bucharest Romania

ISBN: (纸本)9798350371154

This study proposes methods that can be used to examine and interpret comments that users have made after watching videos on YouTube on a particular topic. YouTube tutorials are very popular among young people. They have become an important pillar in informal education, thus contributing to the rapid acquisition of skills and knowledge. Under these circumstances, we were interested in analysing the YouTube videos comments, knowing that the platform has a continuous increase in popularity, which is also due to the opportunities of sharing them. Since ChatGPT-themed YouTube videos have seen a significant surge in popularity since 2022, we were interested to analyse some videos that approach the topics of 'ChatGPT, AI clone, AI robot and Deep Learning.' © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Real-time Pricing Mechanism for V2G Using Distributed Bilevel Optimization 63

Real-time Pricing Mechanism for V2G Using Distributed Bileve...

引用

63rd IEEE Conference on Decision and control, CDC 2024

作者： You, Jiawei Dai, Xinliang Jiang, Yuning Yin, Haoyu Shi, Yuanming Jones, Colin N. ShanghaiTech University School of Information Science and Technology China Epfl Switzerland Karlsruhe Institute of Technology Institute for Automation and Applied Informatics Germany Epfl Automatic Control Laboratory Switzerland Washington University in St. Louis Department of Electrical and Systems Engineering United States

ISBN: (纸本)9798350316339

This paper explores the impact of the burgeoning electric vehicle (EV) presence on distribution grid operations, highlighting the challenges they present to conventional pricing strategies due to their dual role as power consumers and suppliers, coupled with their energy storage capabilities. We propose an advanced real-time pricing model for the electricity market, employing a novel distributed bilevel optimization framework. This framework distinguishes between the distribution system operator (DSO) at the upper level and the EVs at the lower level, each aiming to optimize profit margins. The optimization includes power flow constraints at the upper level to ensure efficient operation within safe system limits, while model predictive control (MPC) is used to optimize lower-level EV responses. Additionally, we provide a rigorous convergence analysis of the proposed bilevel optimization method. Detailed convergence studies and simulation results demonstrate the effectiveness and superiority of the proposed algorithm. © 2024 IEEE.

关键词： Predictive control systems

来源：评论

学校读者我要写书评

暂无评论

control System of an Autonomous Object Tracking Robot 17

Control System of an Autonomous Object Tracking Robot

引用

17th International Conference on engineering of Modern Electric Systems, EMES 2023

作者： Barabas, Tiberiu Silaghi, Helga Spoiala, Dragos Gamcova, Maria University of Oradea Control Systems Engineering and Management Department Oradea Romania Technical University of Kosice Faculty of Electrical Engineering and Informatics Kosice Slovakia

ISBN: (纸本)9798350310634

This paper presents the control system of a mobile robot, capable of detecting, tracking and following an object of a certain color. The mobile robot was created for educational purposes, in the CIM laboratory of the University of Oradea. It is based on a crawler robot, controlled with a Raspberry Pi development system. This system controls the movements necessary for tracking the object: moving forward, backward, left turn or right turn. For detecting and locating the object, the robot is also equipped with a video camera connected to Raspberry Pi. The acquisition and processing of images in real time, provided by the camera, are performed with programming functions provided by the OpenCV (Open Source Computer Vision Library). These functions are implemented in a control program, written in Python language. In order to facilitate the tracking of the images obtained and processed during the movements, the robot has also been provided with a graphic display connected to the Raspberry Pi board. This paper also presents the implementation of a numerical control algorithm used for tracking the objects. © 2023 IEEE.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

Life Cycle Management in Oil&Gas Products Industry 17

Life Cycle Management in Oil&Gas Products Industry

引用

17th International Conference on engineering of Modern Electric Systems, EMES 2023

作者： Magdoiu, Liliana Doina Caciora, Simona Veronica Abrudan Pacala, Anca Gamcova, Maria University of Oradea Control Systems Engineering and Management Department Oradea Romania Technical University of Kosice Faculty of Electrical Engineering and Informatics Kosice Slovakia

ISBN: (纸本)9798350310634

The life cycle of a petroleum product reflects the evolution of its sales volume over time and represents the interval between its introduction on the market and its definitive disappearance from the commodity exchange arena. During the life cycle of a petroleum product, the company marketing it will keep on reformulating the adopted marketing strategies, as determined by variable conditions and new challenges on the side of the competition, along with the changes in customers' interests and their requirements in relation to the product;therefore, appropriate marketing strategies must be developed for each stage in the life cycle of the petroleum product in order to increase its marketing profitability, even though its existence is limited over time. © 2023 IEEE.

关键词： Life cycle

来源：评论

学校读者我要写书评

暂无评论

IMPACT OF THE VOLUME OF DEVELOPER HOUSING UNITS ON REAL ESTATE PRICES IN POLAND: CORRELATION AND COHERENCE ANALYSIS 38

IMPACT OF THE VOLUME OF DEVELOPER HOUSING UNITS ON REAL ESTA...

引用

38th ECMS International Conference on Modelling and Simulation, ECMS 2024

作者： Wotzka, Daria Mach, Lukasz Fracz, Pawel Chorkowy, Bartosz Stec, Marzena Dabrowski, Ireneusz faculty of Electrical Engineering Automatic Control and Informatics Opole University of Technology Poland Faculty of Economics University of Opole Poland Narodowy Bank Polski Regional Branch in Opole Poland Collegium of Management and Finance Warsaw School of Economics Poland

This article conducts a comprehensive correlation analysis to explore the relationship between the development volume by developers and average market prices in Poland's housing sector from 2010 to 2023, utilizing quarterly data on the number of apartments released and their average prices. It employs both linear and nonlinear correlation analysis alongside wavelet coherence analysis. Preliminary correlational analysis offered insights into the basic interdependency patterns, highlighting how developer-supplied apartment numbers impact average prices. Wavelet coherence analysis, a more sophisticated approach, decomposed the data across various frequencies to uncover complex, nonlinear relationship patterns potentially missed by conventional correlation methods. The findings of the study highlight significant connections between the variables that vary over time and space, emphasizing the complexity of the housing market and underscoring the necessity for thorough analysis. These results carry important implications for developers, investors, and housing policy formulation, contributing significantly to understanding Poland's residential real estate market dynamics and supporting further research and strategic real estate industry planning. ©ECMS Daniel Grzonka, Natalia Rylko, Grazyna Suchacka, Vladimir Mityushev (Editors) 2024.

关键词： Correlation methods

来源：评论

学校读者我要写书评

暂无评论

MTP-GO: Graph-Based Probabilistic Multi-Agent Trajectory Prediction with Neural ODEs

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2023年第9期8卷 4223-4236页

作者： Westny, Theodor Oskarsson, Joel Olofsson, Bjorn Frisk, Erik Linköping University Department of Computer and Information Science Linköping581 83 Sweden Lund University Department of Automatic Control Lund221 00 Sweden Linköping University Department of Electrical Engineering Linköping581 83 Sweden

Enabling resilient autonomous motion planning requires robust predictions of surrounding road users' future behavior. In response to this need and the associated challenges, we introduce our model titled MTP-GO. The model encodes the scene using temporal graph neural networks to produce the inputs to an underlying motion model. The motion model is implemented using neural ordinary differential equations where the state-transition functions are learned with the rest of the model. Multimodal probabilistic predictions are obtained by combining the concept of mixture density networks and Kalman filtering. The results illustrate the predictive capabilities of the proposed model across various data sets, outperforming several state-of-the-art methods on a number of metrics. © 2016 IEEE.

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

A nonsingular terminal sliding algorithm for swing and stance control of a prosthetic leg robot

引用

Applied Mathematical Modelling 2023年 113卷 13-29页

作者： Jafari, Maryam Mobayen, Saleh Bayat, Farhad Roth, Hubert Department of Electrical Engineering University of Zanjan Zanjan38791-45371 Iran Future Technology Research Center National Yunlin University of Science and Technology Yunlin Douliou64002 Taiwan Hubert Roth is with the Institute of Automatic Control Engineering University of Siegen Siegen Germany

The design of swing and stance control for path following of a prosthetic leg robot subject to uncertain dynamics and exterior disturbances is a serious issue, which affects the development of wearable robots. In wearable robots, parametric uncertainties and external disturbances are unavoidable problems. This problem is associated with practical engineering of wearable robots due to the actual swing and stance situations, where the combination of contact and tracking control objectives is highly complex. This paper proposes two novel finite-time controllers for a prosthetic leg robot with three degree-of-freedom. A prosthetic leg robot should emulate hip vertical displacement, thigh and knee angles according to human gaits in the presence of ground friction force and external disturbances. For the swing phase, a nonsingular fast terminal sliding mode control method is designed to track the reference trajectories fast and in the finite time without any non-singularity problem and chattering phenomenon. Moreover, the other designed controller can deal with input saturation by using a hyperbolic tangent function and an auxiliary system. For the stance phase, an impulse momentum sliding mode control scheme is introduced which allows the prosthetic leg robot to emulate the mechanics of human walking. Using the proposed controller, the robot imitates the patient momentum exchange and weight transfer in the stance phase. The proposed techniques cause the transition between contact and off-contact phases and contact phase itself. Finally, the simulation results verify the efficiency of the provided technique. In our future work, we will focus on employing this technique to a practical prosthesis legged robot. © 2022 Elsevier Inc.

关键词： Prosthetics

来源：评论

学校读者我要写书评

暂无评论

Anaerobic Digestion Processes controller Tuning Using Fictitious Reference Iterative Method 13th

Anaerobic Digestion Processes Controller Tuning Using Fictit...

引用

13th IFAC Symposium on Dynamics and control of Process Systems, including Biosystems, DYCOPS 2022

作者： Condrachi, Larisa Barbu, Marian Automatic Control and Electrical Engineering Department Dunarea de JosUniversity of Galati Galati Romania

In this paper, a new data-based procedure, Fictitious Reference Iterative Tuning, is proposed to control the anaerobic digestion process. In the first phase, the proposed approach uses input-output data from the anaerobic digestion process obtained by using a controller with initial parameters that ensure loop stability. In the second phase, the situation in which the input-output data are obtained in a closed-loop was also analyzed. Therefore, the Fictitious Reference Iterative Tuning method was used to obtain: a PI controller, which was tuned on the basis of an iterative, convergent and monotonous process and a PID controller, which was tuned on the basis of a divergent iterative process. The results obtained confirm the validity of the proposed Fictitious Reference Iterative Tuning method for the control of the anaerobic digestion process. © 2022 Elsevier B.V.. All rights reserved.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Out-of-distribution Object Detection through Bayesian Uncertainty Estimation 26

Out-of-distribution Object Detection through Bayesian Uncert...

引用

26th International Conference on Information Fusion, FUSION 2023

作者： Zhang, Tianhao Wang, Shenglin Bouaynaya, Nidhal Calinescu, Radu Mihaylova, Lyudmila The University of Sheffield Automatic Control and Systems Engineering United Kingdom Rowan University Department of Electrical and Computer Engineering United States University of York Department of Computer Science United Kingdom

ISBN: (纸本)9798890344854

The superior performance of object detectors is often established under the condition that the test samples are in the same distribution as the training data. However, in many practical applications, out-of-distribution (OOD) instances are inevitable and usually lead to uncertainty in the results. In this paper, we propose a novel, intuitive, and scalable probabilistic object detection method for OOD detection. Unlike other uncertainty-modeling methods that either require huge computational costs to infer the weight distributions or rely on model training through synthetic outlier data, our method is able to distinguish between in-distribution (ID) data and OOD data via weight parameter sampling from proposed Gaussian distributions based on pre-trained networks. We demonstrate that our Bayesian object detector can achieve satisfactory OOD identification performance by reducing the FPR95 score by up to 8.19% and increasing the AUROC score by up to 13.94% when trained on BDD100k and VOC datasets as the ID datasets and evaluated on COCO2017 dataset as the OOD dataset. © 2023 International Society of Information Fusion.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Influence of Histogram Equalization on Multi-Classification of Retinal Diseases in OCT B-scans

Influence of Histogram Equalization on Multi-Classification ...

引用

Signal Processing Algorithms, Architectures, Arrangements and Applications (SPA)

作者： Tomasz Marciniak Agnieszka Stankiewicz Department of Automatic Control Robotics and Electrical Engineering Institue of Automatic Control and Robotics Poznan University of Technology Poznan Poland

ISBN: (数字)9788362065486

ISBN: (纸本)9798350373806

The aim of this article is to analyze the impact of adaptive histogram equalization of the human eye OCT B-scans on the effectiveness of the classification of pathological changes. Tests were performed on two datasets. The first dataset contains 4 class B-scans (CNV, DME, DRUSEN, and NORMAL) taken with the use of Spectralis Heidelberg device, while the second dataset contains images from two devices (Spectralis Heidelberg OCT and Avanti Optovue OCT) and additionally contains the VMT (i.e., vitreomacular traction) class. The images were subjected to standard histogram equalization and contrast limited adaptive histogram equalization (CLAHE) with various parameters. The classification process was carried out using VGG16 artificial neural network. It can be observed that histogram equalization has no significant impact on improving classification performance.

关键词： Performance evaluation Histograms Pathology Optical coherence tomography Signal processing algorithms Artificial neural networks Adaptive equalizers Retina Standards Diseases

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：