检索结果-内蒙古大学图书馆

Optimization of Methodology for Identifying Partial Discharges in Insulating Liquids through Optical Radiation Analysis Using Machine Learning

引用

IEEE Transactions on Instrumentation and Measurement 2025年 74卷

作者： Koziol, Michal Boczar, Tomasz Jancarczyk, Daniel Bernas, Marcin Opole University of Technology Faculty of Electrical Engineering Automatic Control and Informatics Opole45-758 Poland University of Bielsko-Biala Department of Computer Science and Automatics Bielsko-Biala43-309 Poland

The emission of optical radiation is associated with electrical discharges in high-voltage power systems. Detecting, measuring, and analyzing this radiation can enable the identification of the type of electrical discharge and the determination of its source. The article presents the results of measurements and analysis of optical spectra in the context of their application for recognizing different forms of electrical discharges in selected insulating liquids. Optical radiation in the ultraviolet, visible light, and near-infrared range, emitted by electrical discharges in insulating liquids commonly used in electrical engineering, such as mineral oil, natural ester, and synthetic ester, was analyzed. As part of the research, an innovative methodology for measuring and analyzing optical radiation emitted by electrical discharges was proposed, utilizing machine learning tools for precise analysis and interpretation of measurement data. The research results enrich current knowledge with new parameters and measurement indicators, representing another stage in the development of diagnostic methods that can be used to build expert systems and new diagnostic techniques for high-voltage insulation systems. © 1963-2012 IEEE.

关键词： Electric insulation

来源：评论

学校读者我要写书评

暂无评论

Algorithm for Planning, Generating and Simulating Trajectories for a Group of Drones

Algorithm for Planning, Generating and Simulating Trajectori...

引用

Mechatronics Systems and Materials (MSM)

作者： Patryk Szywalski Andrzej Waindok Faculty of Electrical Engineering Automatic Control and Informatics Opole University of Technology Opole Poland

ISBN: (数字)9781728169569

ISBN: (纸本)9781728169576

The methodology of generating trajectories for a group of drones (Unmanned Aircraft System - UAS) was presented in the paper. The software enables flight planning for up to several thousand Unmanned Aerial Vehicles (UAV). The algorithm chooses the i-th UAV's position (Di) in pair with the target position Pj in order to obtain minimum value of the sum of all pair distances DiPj. The system can work in real time even for a large groups of UAV's, which is very difficult using standard gradient methods, especially for low computing resources.

关键词： Trajectory Classification algorithms Drones Electrical engineering Aircraft Memory management

来源：评论

学校读者我要写书评

暂无评论

The Impact of Recommendation Systems on Opinion Dynamics: Microscopic Versus Macroscopic Effects

The Impact of Recommendation Systems on Opinion Dynamics: Mi...

引用

IEEE Conference on Decision and control

作者： Nicolas Lanzetti Florian Dörfler Nicolò Pagan Department of Electrical Engineering and Information Technology Automatic Control Laboratory ETH Zürich Zürich Switzerland Department of Informatics Social Computing Group University of Zürich Zürich Switzerland

Recommendation systems are widely used in web services, such as social networks and e-commerce platforms, to serve personalized content to the users and, thus, enhance their experience. While personalization assists users in navigating through the available options, there have been growing concerns regarding its repercussions on the users and their opinions. Examples of negative impacts include the emergence of filter bubbles and the amplification of users' confirmation bias, which can cause opinion polarization and radicalization. In this paper, we study the impact of recommendation systems on users, both from a microscopic (i.e., at the level of individual users) and a macroscopic (i.e., at the level of a homogenous population) perspective. Specifically, we build on recent work on the interactions between opinion dynamics and recommendation systems to propose a model for this closed loop, which we then study both analytically and numerically. Among others, our analysis reveals that shifts in the opinions of individual users do not always align with shifts in the opinion distribution of the population. In particular, even in settings where the opinion distribution appears unaltered (e.g., measured via surveys across the population), the opinion of individual users might be significantly distorted by the recommendation system.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Continual Learning of a Time Series Model Using a Mixture of HMMs with Application to the IoT Fuel Sensor Verification 18

Continual Learning of a Time Series Model Using a Mixture of...

引用

18th Conference on Computer Science and Intelligence Systems, FedCSIS 2023

作者： Glomb, Przemyslaw Cholewa, Michal Foszner, Pawel Bularz, Jakub Institute of Theoretical and Applied Informatics Polish Academy of Sciences Batycka 5 Gliwice44-100 Poland Department of Computer Graphics Vision and Digital Systems Faculty of Automatic Control Electronics and Computer Science Silesian University of Technology Akademicka 2A Gliwice44-100 Poland Aiut Sp. Z O.o. ul. Wyczókowskiego 113 Gliwice44-109 Poland

ISBN: (纸本)9788396744784

This paper presents an application of a mixture of Hidden Markov Models (HMMs) as a tool for verification of IoT fuel sensors. The IoT fuel sensors report the level of fuel in tanks of a petrol station, and are a key component for monitoring system reliability (billing), safety (fuel/oil leak detection) and security (theft prevention). We propose an algorithm for learning a mixture of HMMs based on a continual learning principle, i.e. it adapts the model while monitoring a sensor over time, signalling unexpected or anomalous sensor reports. We have tested the proposed approach on a real-life data of 15 fuel tanks being monitored with the FuelPrime system, where it has shown a very good performance (average area under ROC curve of 0.94) of detecting anomalies in the sensor data. Additionally we show that the proposed method can be used for trend monitoring and present qualitative analysis of the short and long term learning performance. The proposed method has promising performance score, the resulting model has a high degree of explainability, limited memory and computation requirements and can be easily generalized to other domains of sensor verification. © 2023 Polish Information Processing Society.

关键词： Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

The Impact of Recommendation Systems on Opinion Dynamics: Microscopic versus Macroscopic Effects

arXiv

引用

arXiv 2023年

作者： Lanzetti, Nicolas Dörfler, Florian Pagan, Nicolò The Automatic Control Laboratory Department of Electrical Engineering and Information Technology ETH Zürich Zürich8003 Switzerland The Social Computing Group Department of Informatics University of Zürich Zürich8003 Switzerland

Recommendation systems are widely used in web services, such as social networks and e-commerce platforms, to serve personalized content to the users and, thus, enhance their experience. While personalization assists users in navigating through the available options, there have been growing concerns regarding its repercussions on the users and their opinions. Examples of negative impacts include the emergence of filter bubbles and the amplification of users’ confirmation bias, which can cause opinion polarization and radicalization. In this paper, we study the impact of recommendation systems on users, both from a microscopic (i.e., at the level of individual users) and a macroscopic (i.e., at the level of a homogenous population) perspective. Specifically, we build on recent work on the interactions between opinion dynamics and recommendation systems to propose a model for this closed loop, which we then study both analytically and numerically. Among others, our analysis reveals that shifts in the opinions of individual users do not always align with shifts in the opinion distribution of the population. In particular, even in settings where the opinion distribution appears unaltered (e.g., measured via surveys across the population), the opinion of individual users might be significantly distorted by the recommendation system. © 2023, CC BY.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Investigating Large Language Models for ComplexWord Identification in Multilingual and Multidomain Setups

arXiv

引用

arXiv 2024年

作者： Smǎdu, Rǎzvan-Alexandru Ion, David-Gabriel Cercel, Dumitru-Clementin Pop, Florin Cercel, Mihaela-Claudia National University of Science and Technology POLITEHNICA Bucharest Faculty of Automatic Control and Computers Bucharest Romania National Institute for Research & Development in Informatics ICI Bucharest Bucharest Romania Academy of Romanian Scientists Bucharest Romania Paris 1 Pantheon-Sorbonne University Paris France University of Bucharest Bucharest Romania

Complex Word Identification (CWI) is an essential step in the lexical simplification task and has recently become a task on its own. Some variations of this binary classification task have emerged, such as lexical complexity prediction (LCP) and complexity evaluation of multi-word expressions (MWE). Large language models (LLMs) recently became popular in the Natural Language Processing community because of their versatility and capability to solve unseen tasks in zero/few-shot settings. Our work investigates LLM usage, specifically open-source models such as Llama 2, Llama 3, and Vicuna v1.5, and closed-source, such as ChatGPT-3.5- turbo and GPT-4o, in the CWI, LCP, and MWE settings. We evaluate zero-shot, few-shot, and fine-tuning settings and show that LLMs struggle in certain conditions or achieve comparable results against existing methods. In addition, we provide some views on meta-learning combined with prompt learning. In the end, we conclude that the current state of LLMs cannot or barely outperform existing methods, which are usually much smaller. © 2024, CC BY-SA.

关键词： Open systems

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of Adaptive NMPC in industrial applications: case study

Design and Implementation of Adaptive NMPC in industrial app...

引用

International Carpathian control Conference (ICCC)

作者： Stepan Ozana Filip Krupa Jakub Nemcik Gergely Takacs Jakub Mozaryn Petr Beremlijski Abhaya Singh Aleksandra Kawala-Sterniuk Department of Cybernetics and Biomedical Engineering VSB-Technical University of Ostrava Ostrava Czech Republic Institute of Automation Measurement and Applied Informatics Slovak University of Technology in Bratislava Bratislava Slovak Republic Institute of Automatic Control and Robotics Warsaw University of Technology Warsaw Poland Department of Applied Mathematics VSB-Technical University of Ostrava Ostrava Czech Republic Department of engineering University of Sannio Sannio Italy Department of Electrical Power and Renewable Energy Opole University of Technology Opole Poland

This paper deals with the design and implementation of adaptive nonlinear predictive control (NMPC). The resulting control system is deployed on a softPLC embedded target in real-time via the REXYGEN control system. The paper describes functional prototype using softPLC hosting the NMPC algorithm applied for a nonlinear system consisting of three coupled tanks. The NMPC algorithm is solved via the receding horizon control method (RHC), formulated as a nonlinear programming problem (NLP) and numerically computed using the SOLNP solver. The adaptivity is provided by online identification via moving horizon estimation (MHE), keeping the model updated to avoid a model-plant mismatch. The methodology described in this paper can be easily transferred to a wider group of industrial nonlinear processes. Such created control unit can run in a standalone mode or can be connected to some exiting control system providing a necessary computational power and thus upgrading the quality of control significantly.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Cross-Lingual Meta-Learning Method Based on Domain Adaptation for Speech Emotion Recognition

arXiv

引用

arXiv 2024年

作者： Ion, David-Gabriel Smădu, Răzvan-Alexandru Cercel, Dumitru-Clementin Pop, Florin Cercel, Mihaela-Claudia Faculty of Automatic Control and Computers National University of Science and Technology POLITEHNICA Bucharest Bucharest Romania National Institute for Research and Development in Informatics - ICI Bucharest Bucharest Romania Academy of Romanian Scientists Bucharest Romania Paris 1 Panthéon-Sorbonne University Paris France University of Bucharest Bucharest Romania

Best-performing speech models are trained on large amounts of data in the language they are meant to work for. However, most languages have sparse data, making training models challenging. This shortage of data is even more prevalent in speech emotion recognition. Our work explores the model’s performance in limited data, specifically for speech emotion recognition. Meta-learning specializes in improving the few-shot learning. As a result, we employ meta-learning techniques on speech emotion recognition tasks, accent recognition, and person identification. To this end, we propose a series of improvements over the multistage meta-learning method. Unlike other works focusing on smaller models due to the high computational cost of meta-learning algorithms, we take a more practical approach. We incorporate a large pre-trained backbone and a prototypical network, making our methods more feasible and applicable. Our most notable contribution is an improved fine-tuning technique during meta-testing that significantly boosts the performance on out-of-distribution datasets. This result, together with incremental improvements from several other works, helped us achieve accuracy scores of 83.78% and 56.30% for Greek and Romanian speech emotion recognition datasets not included in the training or validation splits in the context of 4-way 5-shot learning. © 2024, CC BY-NC-SA.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Neural network developed for obstacle avoidance of the four wheeled electric vehicle

Neural network developed for obstacle avoidance of the four ...

引用

IEEE International Conference on Electronics, Circuits and Systems (ICECS)

作者： Grazia Lo Sciuto Paweł Kowol Paweł Nowak Wacław Banás Salvo Coco Giacomo Capizzi Department of Mechatronics Silesian University of Technology Gliwice Poland Department of Electrical Electronics and Informatics Engineering University of Catania Catania Italy Department of Automatic Control and Robotic Silesian University of Technology Gliwice Poland Department of Mathematics Applications and Methods for Artificial Intelligence Faculty of Applied Mathematics Silesian University of Technology Gliwice Poland

Several solutions have been proposed for vehicle navigation in unknown environments to ensure safer driving by avoiding obstacles and collisions. In this work, an electric vehicle equipped with Mecanum 4 omnidirectional holonomic wheels, analog joystick to control driving movement, LiDAR sensors and Wi-Fi able to detect obstacles is investigated based on neural network approach. By experimental tests conducted to avoid collisions by detecting the presence of obstacles, the relation between the resistance distance and speed is described by the artificial neural network.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Real-time testing of vision-based systems for AGVs with ArUco markers

Real-time testing of vision-based systems for AGVs with ArUc...

引用

IEEE International Conference on Big Data

作者： Katarzyna Filus Łukasz Sobczak Joanna Domańska Adam Domański Rafał Cupek Polish Academy of Sciences Institute of Theoretical and Applied Informatics Gliwice Poland Faculty of Automatic Control Electronics and Computer Science Silesian University of Technology Gliwice Poland

ISBN: (纸本)9781665480468

Automated Ground Vehicles (AGVs) use deep-learning-based vision systems to perceive the surrounding environment and extract relevant information about it. Although deep learning models offer high capabilities, they require large amounts of data to be properly trained and tested. Testing is especially important when off-the-shelf models are used by the AGVs - to examine whether they can meet the demands of complex environments such as the production halls of automated factories. One area of such perception algorithms is object recognition. To test such systems, we propose a solution based on ArUco fiducial markers used for automatic labeling of objects. Our solution can be used to test deep learning systems in real time directly on a robot. Our solution requires minimal interference with the environment and additional infrastructure - the desired objects only need to be marked with a marker printed on a home printer. Therefore, the presented testing procedure can be used for testing of AGVs in real-life environments during a real ride from an actual robot perspective. Data gathered during the online testing can be used for the offline comparison of the accuracy of different deep learning models. Although we focus on the online and offline testing in our study, we also incorporated a marker masking procedure. Therefore, the resulting datasets may also be used for training.

关键词： Deep learning Training Computational modeling Big Data Real-time systems Data models Object recognition

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：