检索结果-内蒙古大学图书馆

International Conference on Multisensor Fusion and Integration for Intelligent systems (MFI)

作者： Xingyu Liu Esa Apriaskar Lyudmila Mihaylova Department of Automatic Control and Systems Engineering University of Sheffield Sheffield United Kingdom Department of Electrical Engineering Faculty of Engineering Universitas Negeri Semarang Semarang Indonesia

ISBN: (数字)9798350368031

ISBN: (纸本)9798350368048

The introduction of autonomous vehicles (AVs) presents a novel approach to regulating and optimising traffic flow through the automated control of AVs. In this context, the AV is defined as the actuator and an optimal control policy is desired to make control decisions. Deep Reinforcement Learning (DRL) is a novel method which aims to maximize the cumulative rewards given by the predefined reward function by making sequential decisions in a stochastic environment. In light of the above, we propose a DRL-based vehicular control method to train an optimal policy for the control of AV in a model-free fashion, and consequently improve the traffic efficiency with the obtained control policy. A single-lane circular road environment with both AV and human-driven vehicles is selected to serve as the mixed autonomy traffic system in the Simulation of Urban MObility (SUMO) [1] traffic simulator, and the Proximal Policy Optimization (PPO) algorithm is applied for the policy improvement. Simulation results demonstrate that our strategy is effective in mitigating the unstable stop-and-go waves, increasing 67.7% of the average driving speed and reducing 19.3% of the average energy consumption in a closed-ring road environment.

关键词： Roads Simulation Heuristic algorithms Stochastic processes Optimal control Deep reinforcement learning Fuels Intelligent systems Traffic congestion Optimization

来源：评论

学校读者我要写书评

暂无评论

A deep learning architecture for audience interest prediction of news topic on social media 24

A deep learning architecture for audience interest predictio...

引用

Advances in Database Technology - 24th International Conference on Extending Database Technology, EDBT 2021

作者： Truică, Ciprian-Octavian Apostol, Elena-Simona Stefu, Teodor Karras, Panagiotis Faculty of Automatic Control and Computers University Politehnica of Bucharest Bucharest Romania Department Computer Science Aarhus University Aarhus Denmark

ISBN: (纸本)9783893180844

Personalized social media offer communication opportunities that mass media could not afford, yet also raise novel challenges. A prime challenge arising from this shift in digital communication is to detect topics and events of interest. In this paper, we propose and deploy a novel Deep Learning architecture that predicts if a news topic becomes viral by analyzing social media diffusion and audience interest in current news events. The proposed solution: (i) analyzes news articles, (ii) extracts associated topics and events, (iii) matches the topics and events to filter and extract developing topics, (iv) extracts current events from Twitter and matches them to the filtered news topics, and (v) predicts audience interest in news topics using Twitter likes and retweets. We employ several feature engineering techniques to improve prediction by integrating user metadata into the training set. In our experiments, we correlate two datasets collected over several months in the same time period. The first dataset contains news articles collected from different news venues, while the second one contains tweets regarding the news. The experimental results from our real-world deployment prove that the proposed system achieves high accuracy when integrating influencers metadata and the day of the week. Thus, proving that the news topics virality prediction is improved under the assumptions that spreaders and the day of the week play a huge role in information diffusion. © 2021 Copyright held by the owner/author(s).

关键词： Metadata

来源：评论

学校读者我要写书评

暂无评论

Vibration Mitigation of Hybrid Oscillating Water Column-Floating Offshore Wind Turbine Using ANFIS-Based Airflow control 16th

Vibration Mitigation of Hybrid Oscillating Water Column-Floa...

引用

16th APCA International Conference on automatic control and Soft Computing, controlO 2024

作者： M’zoughi, Fares Aboutalebi, Payam Ahmad, Irfan Rouch, Tahereh Bagheri Garrido, Izaskun Garrido, Aitor J. De La Sen, Manuel Automatic Control Group—ACG Institute of Research and Development of Processes—IIDP Department of Automatic Control and Systems Engineering Faculty of Engineering of Bilbao—EIB/BIE University of the Basque Country—UPV/EHU Po Rafael Moreno no. 3 Bilbao48013 Spain Automatic Control Group—ACG Institute of Research and Development of Processes IIDP Department of Electricity and Electronics Faculty of Science and Technology University of the Basque Country—UPV/EHU Bo Sarriena s/n Leioa48080 Spain

ISBN: (纸本)9783031817236

This paper introduces a novel approach to model and stabilize a Floating Offshore Wind Turbine (FOWT) by employing Oscillating Water Columns (OWC) as an active structural control system. The innovative concept involves designing a new floating barge-like platform with integrated OWCs on opposite sides of the platform to mitigate undesired oscillations of the system. These OWCs counteract the bending forces caused by wind on the tower and waves on the barge platform. To synchronize the opposing forces with the system’s tilting, a proposed Adaptive Neuro-Fuzzy Inference system-based airflow control strategy is employed. Through manipulation of the barge platform’s pitch angle, the ANFIS airflow control system adjusts the valves on either side, opening one and closing the other accordingly. Simulation results, compared with a standard FOWT demonstrate the effectiveness of the ANFIS airflow control. It is shown to be superior in reducing platform pitching and the fore-aft translation of the tower top. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Active Structural control Air Valve Airflow control ANFIS Barge Platform Floating Offshore Wind Turbine Oscillating Water Column

来源：评论

学校读者我要写书评

暂无评论

Optimized fine-tuned ensemble classifier using Bayesian optimization for the detection of ear diseases

引用

computers in Biology and Medicine 2025年 191卷 110092-110092页

作者： Elmorsy, Israa Moneir, Waleed Saleh, Ahmed I. Khalil, Abeer Twakol Electronics and Communications Engineering Department Faculty of Engineering Mansoura University Mansoura Egypt ORL Head and Neck Surgery Department Faculty of Medicine Mansoura University Mansoura Egypt Computers and Control System Engineering Department Faculty of Engineering Mansoura University Mansoura Egypt

External and middle ear diseases are common disorders, especially in children, and can be examined using a digital otoscope. Hearing loss can result from delayed diagnosis and treatment which is subjective and error-prone depending on the expertise of the otolaryngologist. For these reasons, deep learning-based automated diagnostic systems are highly needed. In this study, a novel weighted average voting ensemble classifier between MobileNet and DenseNet169 has been developed to diagnose and detect different ear conditions. Bayesian optimization was used to select hyperparameters that gave the best results during the training process. MobileNet and DenseNet169 were fine-tuned by updating the weights of all layers in addition to the newly added layers before fusing them into one ensemble classifier to improve the classification ability of the model and be more specific to our task. This study was performed on a public dataset consisting of 282 otoscopic images. All classes were considered except the Tympanostomy Tubes class for having only two samples. Consequently, the proposed model demonstrated promising results of 99.54 % accuracy and an AUC of 1. Grad-CAM++ saliency maps were employed to highlight the affected area and pertinent features of the otoscopic image. The proposed approach contributes to improving accuracy, decreasing the misdiagnosis rate, and developing an automatic ear disease classification tool. © 2025 Elsevier Ltd

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Solutions for Digital Interaction of a Resilient Energy Community in a Service-oriented Framework 12

Solutions for Digital Interaction of a Resilient Energy Comm...

引用

12th International Conference and Exposition on Electrical and Power engineering, EPE 2022

作者： Sanduleac, Mihai Ionescu, Constantin Mandis, Alexandru Gropa, Victor Efremov, Cristina Sanduleac, Vlad Department of Power Systems Faculty of Energy Engineering University Politehnica of Bucharest Bucharest Romania Dep. of Energy Generation and Use Faculty of Energy Engineering University Politehnica of Bucharest Bucharest Romania Faculty of Energetics and Electrical Engineering Technical University of Moldova Chisinau Moldova Department of Computer Science and Engineering Faculty of Automatic Control and Computers University Politehnica of Bucharest Romania

ISBN: (数字)9781665489942

ISBN: (纸本)9781665489942

Energy communities are emerging entities which need their own Information and Communication system. Resilience is a key metric of such communities, and it has to be implemented for both energy supply versus public network outages and for its information system versus cyber-attacks, acting as cyber-citadels which have to resist external malicious attacks while having also digital interactions with external entities. The paper presents solutions for a resilient energy community with appropriate implementations of digital interaction for data exchange, in order to acquire external energy service for specialized companies and to deliver also information and communication-related services for external users. Principles of a Contractual Data Protection Regulation are presented, as an adaptation of data protection tailored for automated energy services and based on secure data exchange. The principles are verified in a demonstration project which has also external entities with digital interaction. © 20XX IEEE.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Tracking Trajectory by Using The Polynomial Method for ACC system Based on Smart Car Platform 17

Tracking Trajectory by Using The Polynomial Method for ACC S...

引用

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

作者： Luu, Duc Lich Hung, Nguyen Viet Lupu, Ciprian University of Science and Technology The University of Danang Faculty of Transportation Mechanical Engineering Da Nang550000 Viet Nam East Asia University of Technology Faculty of Information Technology Bac Ninh Viet Nam University Politehnica of Bucharest Department of Automatic Control and Systems Engineering Bucharest Romania

ISBN: (纸本)9798350310634

A well-known advanced driver assistance technology that can be employed for that is the Adaptive Cruise control system (ACC). Cars equipped with ACC system are to control the car speed to follow a driver's set speed closely when there is no leading car. When a slower leading car is present based on distance sensor, the ACC controlled car are able to keep desired distance with respect to the position and velocity of the car in front. This paper presents a design methodology of Adaptive Cruise control (ACC) system for two smart car platform consist of the leading smart car and a host smart car move on a single lane on a laboratory installation. RST algorithm in the multi algorithms structure is proposed to design in real-time architecture for ACC system. RST algorithm is one of the most effective solutions for the real-time control of nonlinear systems or working regimes. The results of the experiment have been conducted to illustrate the effectiveness of the proposed algorithm. © 2023 IEEE.

关键词： Adaptive cruise control

来源：评论

学校读者我要写书评

暂无评论

Utilizing Cloud Solutions for Object Recognition in the Context of Industrial Robotics Sorting Tasks

Utilizing Cloud Solutions for Object Recognition in the Cont...

引用

IEEE International Symposium on Innovations in Intelligent systems and Applications (INISTA)

作者： Ioana Livia Stefan Andrei Mateescu Ioana Miruna Vlasceanu Dragos Constantin Popescu Ioan Stefan Sacala Automatic Control and Systems Engineering Department Faculty of Automatic Control and Computers University POLITEHNICA of Bucharest Splaiul Independentei No. 313 Bucharest Romania Extreme Light Infrastructure (ELI-NP) & Horia Hulubei National Institute for R&D in Physics and Nuclear Engineering (IFIN-HH) Str. Reactorului No. 30 Măgurele Bucharest Romania

ISBN: (数字)9798350368130

ISBN: (纸本)9798350368147

The rapid advancements in sectors such as Internet of Things (IoT), Artificial Intelligence (AI), Machine Learning (ML), networking and cloud computing are opening the opportunity for integrating these techniques with robots from the manufacturing field, with the promising perspective of improved performance at reduced costs, inspiring the new field of cloud robotics. In this paper, we propose an architecture for integrating industrial robots with Cloud AI object recognition services. For our proposed solution, we explore the results obtained by simulating a sorting task in RobotStudio, communicating with Microsoft Azure Custom Vision API by sending the web service calls from a computer running a Python script. We present the cycle time added by the communication with the cloud service and test the robustness of the system by comparing the results obtained with four sets of images: unaltered, altered with gaussian noise, barrel distortion and both.

关键词： Histograms Technological innovation Service robots Web services Gaussian noise Distortion Object recognition

来源：评论

学校读者我要写书评

暂无评论

Reducing the energy consumption required for the disassembly process implemented on an assembly and disassembly line 24

Reducing the energy consumption required for the disassembly...

引用

24th International Conference on control systems and Computer Science, CSCS 2023

作者： Marius-Adrian, Paun Elena, Dragomir Otilia Florin, Dragomir Stelian, Iliescu Sergiu Eugenia, Minca Octavian Gabriel, Duca Valentin, Gurgu Ion University 'Politehnica' of Bucharest Department of Automation and Industrial Informatics Bucharest Romania Valahia University of Targoviste Faculty of Electrical Engineering Electronics and Information Technology Targoviste Romania University 'Politehnica ' of Bucharest Faculty of Automatic Control and Computers Bucharest Romania University 'Dunarea de Jos ' of Galati Department of Automation and Electrical Engineering Galati Romania Institute of Multidisciplinary Research for Science and Technology Valahia University of Targoviste Targoviste Romania

ISBN: (纸本)9798350313390

This paper proposes a method to reduce the energy consumption of an industrial disassembly process implemented on a production line by using an energy-efficient secondary disassembly process. In the case of defective products, the flow directs the simple product with priority to be disassembled in workstation (WS) 7. Therefore, all defective products are redirected to WS7. The disassembly of all simple products in WS7 is problematic for two reasons: the power consumption of WS7 is high compared to the other workstations, additionally there is an increased possibility of bottlenecks in the production line due to the high disassembly time. The proposed solution to reduce the possibility of deadlock and reduce power consumption is to redirect the defective products to the flexible cell (FC). Handling robots located in neighboring stations will participate collaboratively in the disassembly process. The control structure ensures that the two robots 'meet' in the boundary plane of WS3 with WS4 and disassemble each component through collaborative tasks. Collaborative control of disassembly is thought of as a solution to the global 'fluidization' of production, removing the bottleneck, from the overall flow, but also as an ingenious solution to reduce energy consumption. © 2023 IEEE.

关键词： Assembly

来源：评论

学校读者我要写书评

暂无评论

Preventing Frequency Instability Using Large-Scale Photovoltaic Resources

Preventing Frequency Instability Using Large-Scale Photovolt...

引用

Technology and Energy Management (ICTEM), International Conference on

作者： Siavash Yari Hamid Khoshkhoo Kumars Rouzbehi S. M. Ale Emran Faculty of Electrical Engineering Sahand University of Technology Sahand Iran Department of System Engineering and Automatic Control University of Seville Seville Spain Faculty of Engineering University of Quebec at Chicoutimi (UQAC)

Various control methods have been presented to prevent the occurrence of instability in power systems, among which, it seems that methods based on the special protection system (SPS) are more effective and efficient than other ones. In this article, a SPS using the capabilities of large-scale photovoltaic power plants (LSPVPPs) is presented to prevent frequency increase and instability in power systems. According to the presented algorithm, when frequency increases, the proposed SPS uses the ability of photovoltaic power plants to quickly change their generation powers based on the operating point and frequency changes to prevent frequency instability. To confirm the proposal, LSPVPPs along with their controllers are modeled in the DSL environment of DIgSILENT PowerFactory software. The proposed SPS is implemented and tested on the IEEE 39-bus test system and the results of dynamic simulations show that this SPS prevents frequency instability in different conditions by taking timely measures.

关键词： Photovoltaic systems Time-frequency analysis Power system dynamics Software algorithms Power system stability Stability analysis Software

来源：评论

学校读者我要写书评

暂无评论

Fractional Order vs Integer Order Transfer Function Models of a Pendulum

Fractional Order vs Integer Order Transfer Function Models o...

引用

International Conference on Automation, AUTOMATION 2021

作者： Oprzędkiewicz, Krzysztof Rosól, Maciej Żegleń-Wlodarczyk, Jakub Department of Automatic Control and Robotics Faculty of Electrotechnics Automatic Control Informatics and Biomedical Engineering AGH University of Science and Technology al. A Mickiewicza 30 Krakow30-059 Poland

ISBN: (纸本)9783030748920

The paper presents the comparison of fractional order to integer order transfer function models of physical pendulum. The considered transfer functions describe the behaviour of the system around the lower, stable equilibrium point. Fractional order models are built using ORA approximation. Models were verified using real experimental data. Results of tests show that the fractional order transfer function can correctly describe the physical pendulum. Integer order models are a little bit more accurate, but they require more parameters to identify. © 2021, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Linear 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：