检索结果-内蒙古大学图书馆

IEEE Transactions on Instrumentation and Measurement 2025年 74卷

作者： Michał Kozioł Tomasz Boczar Daniel Jancarczyk Marcin Bernaś Faculty of Electrical Engineering Automatic Control and Informatics Opole University of Technology Opole Poland Department of Computer Science and Automatics University of Bielsko-Biala Bielsko-Biala 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. This 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 (ML) 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.

关键词： Stimulated emission Optical variables measurement Optical fibers Optical sensors Optical fiber sensors Partial discharges Electrical engineering Signal processing algorithms Optical films Discharges (electric)

Hyperbolic embedding model for a class of microrna-disease networks

学校读者我要写书评

暂无评论

UPB Scientific Bulletin, Series A: Applied Mathematics and Physics 2020年第1期82卷 219-230页

作者： Angelescu, Radu Dobrescu, Radu Department of Automatic Control and Industrial Informatics Faculty of Auto matic Control and Computer Science University "Politehnica" of Bucharest Romania

The main goal of this paper is to study the embedding of networks in a form that can be used in differential programming. We prove that certain networks have better embeddings in an appropriate metric space and provide a numerically stable embedding solution. We generate embeddings for the disease-microRNA network. © 2020, Politechnica University of Bucharest. All rights reserved.

关键词： RNA

A Unified Formulation of Geometry-aware Discrete Dynamic Movement Primitives

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Abu-Dakka, Fares J. Saveriano, Matteo Kyrki, Ville Electronic and Computer Science Department Faculty of Engineering Mondragon Unibertsitatea Arrasate20500 Spain Automatic Control Lab Department of Industrial Engineering University of Trento Trento Italy Intelligent Robotics Group Department of Electrical Engineering and Automation Aalto University Aalto Finland

Learning from demonstration (LfD) is considered as an efficient way to transfer skills from humans to robots. Traditionally, LfD has been used to transfer Cartesian and joint positions and forces from human demonstrations. The traditional approach works well for some robotic tasks, but for many tasks of interest, it is necessary to learn skills such as orientation, impedance, and/or manipulability that have specific geometric characteristics. An effective encoding of such skills can be only achieved if the underlying geometric structure of the skill manifold is considered and the constrains arising from this structure are fulfilled during both learning and execution. However, typical learned skill models such as dynamic movement primitives (DMPs) are limited to Euclidean data and fail in correctly embedding quantities with geometric constraints. In this paper, we propose a novel and mathematically principled framework that uses concepts from Riemannian geometry to allow DMPs to properly embed geometric constrains. The resulting DMP formulation can deal with data sampled from any Riemannian manifold including, but not limited to, unit quaternions and symmetric and positive definite matrices. The proposed approach has been extensively evaluated both on simulated data and real robot experiments. The performed evaluation demonstrates that beneficial properties of DMPs, such as convergence to a given goal and the possibility to change the goal during operation, apply also to the proposed formulation. © 2022, CC BY-NC-ND.

关键词： Demonstrations

Policy and Value Deep RL for Temporal Language-Agnostic Street Image Captioning 3

学校读者我要写书评

暂无评论

Policy and Value Deep RL for Temporal Language-Agnostic Stre...

3rd IEEE Eurasia Conference on Biomedical Engineering, Healthcare and Sustainability, ECBIOS 2021

作者： Chan, Christopher Chun Ki Chen, Chih-Cheng Delaney, Steven Yang, Cheng-Fu Department of Information Management Chaoyang University of Technology Taichung Taiwan Department of Automatic Control Engineering Feng Chia University Taichung40724 Taiwan Department of Aeronautical Engineering Chaoyang University of Technology Taichung Taiwan Department of Computer Science Ryerson University Canada Department of Chemical and Materials Engineering National University of Kaohsiung Kaohsiung Taiwan

ISBN: (纸本)9781728193045

Dashcams and street cameras capture a huge amount of street and traffic video data. Temporal image captioning for such video data has been approached with an encoder-decoder framework and achieved substantial success in captioning accuracy. Most recently, policy and value deep reinforcement learning (PVRL) emerged as an outperformer over other decision-making frameworks for image captioning. In this paper, we design a framework that utilizes PVRL on an in-house dataset containing temporal images of East Asia streets as a step towards designing a language-agnostic street image captioning framework that is capable of captioning temporal images of any street regardless of location. For language-invariance, the framework includes cross-modal retrieval at the character level so that similar words in different languages but in the same word-embedding space are grouped together. Our results show that PVRL can be applied successfully to temporal video captured the streets and achieve natural semantic captions;preliminary studies on our dataset suggest that the framework is capable of use in multi-language scenarios. © 2021 ECBIOS 2021. All rights reserved.

关键词： Deep learning

Hcare web application for ehealth monitoring system

学校读者我要写书评

暂无评论

UPB Scientific Bulletin, Series C: Electrical Engineering an...

UPB Scientific Bulletin, Series C: Electrical Engineering and computer science 2020年第4期82卷 29-40页

作者： Almalchy, Mohammed Tali Algayar, Sarmad Monadel Alsahlani, Ahmed Y. F. Popescu, Nirvana Dept. of Computer Science Faculty of Automatic Control and Computer Science University POLITEHNICA of Bucharest Romania Dept. of Computer Science Faculty of Mathematics and Computer Science University of Bucharest Romania

This work presents a design and implementation of an enhanced healthcare monitoring system based on the web application framework and the cloud platform using four vital signs such as blood pressure, SPO2, body temperature, and electrocardiogram ECG. Innovative ECG modules were utilized for automatic diagnose like ECG filtering module and the DCNN-based ECG classification module. The solution provides various functionalities and privileges for the users in order to facilitate the work of doctors or emergency staff to monitor patients in order to provide medical support in a timely manner. Also, it supports patients by providing them with medical assistance through the remote interaction with medical professionals taking into consideration the security and privacy of sensitive medical data. © 2020, Politechnica University of Bucharest. All rights reserved.

关键词： Electrocardiograms

Stability of Linear Systems under Extended Weakly-Hard Constraints

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Vreman, Nils Pazzaglia, Paolo Magron, Victor Wang, Jie Maggio, Martina The Department of Automatic Control Lund University Sweden The Department of Computer Science Saarland University Germany The Laboratory for Analysis and Architecture of Systems CNRS France The Academy of Mathematics and Systems Science CAS China

control systems can show robustness to many events, like disturbances and model inaccuracies. It is natural to speculate that they are also robust to sporadic deadline misses when implemented as digital tasks on an embedded platform. This paper proposes a comprehensive stability analysis for control systems subject to deadline misses, leveraging a new formulation to describe the patterns experienced by the control task under different handling strategies. Such analysis brings the assessment of control systems robustness to computational problems one step closer to the controller implementation. Copyright © 2021, The Authors. All rights reserved.

关键词： Networked control systems

Cybersecurity Threat Detection in the Behavior of IoT Devices: Analysis of Data Mining Competition Results

学校读者我要写书评

暂无评论

Cybersecurity Threat Detection in the Behavior of IoT Device...

Federated Conference on computer science and Information Systems (FedCSIS)

作者： Michał Czerwiński Marcin Michalak Piotr Biczyk Błażej Adamczyk Daniel Iwanicki Iwona Kostorz Maksym Brzęczek Andrzej Janusz Marek Hermansa Łukasz Wawrowski Artur Kozłowski QED Software Warsaw Poland Faculty of Mathematics University of Warsaw Warsaw Poland Łukasiewicz Research Network - Institute of Innovative Technologies EMAG Katowice Poland Department of Computer Networks and Systems Silesian<file://Silesian> University of Technology Gliwice Poland Faculty of Automatic Control Electronics and Computer Science Silesian<file://Silesian> University of Technology Gliwice Poland EFIGO sp. z o.o. Katowice Poland

The paper discusses a data science competition centered around the development of an anomaly detection system for IoT devices. The competition utilized a unique environment that allowed for the operation and monitoring of real IoT devices, including scheduling of attacks on these devices. The environment was used to collect the data, which included both normal and attack-induced behavior of IoT devices. The paper presents the background of the competition, the top models submitted, and the competition results. The paper also includes a discussion about restrictions related to the use of synthetic attack data as input for constructing anomaly detection systems.

关键词：

BDCP: An Improved Nested Named Entity Recognition Model Based on LSTM

学校读者我要写书评

暂无评论

BDCP: An Improved Nested Named Entity Recognition Model Base...

IEEE International Conference on Data science in Cyberspace (DSC)

作者： Ling Zhou Tianjiao Luan Na Yao Jianming Li Jie Ding School of Computer Science Guangzhou University Guangzhou China China Academy of Launch Vehicle Technology Beijing China Beijing Aerospace Automatic Control Institute Beijing China

ISBN: (纸本)9781665418164

In construction of knowledge graphs (KGs), named entity recognition (NER) is a sub-task to identify the boundaries of entities with special meaning and predict their categories in texts. The instance that an entity contains one or more entities is called nested entity. The current work on NER usually ignores the nested NER. We propose an improved model named Boundary Detection and Category Prediction (BDCP) for Nested NER. Our model uses LSTM to extract the contextual features of the sequence, and uses boundary detection unit to mark the boundaries of entities in the text. By introducing boundary detection unit, our model extracts the boundaries of entities and restrict the number of candidate entities. We also design a layer-by-layer decoding module by boundary detection unit for Nested NER. Experiments on Nested NER datasets named GENIA [1] demonstrate the effectiveness of our model on nested NER.

关键词： Knowledge engineering Text recognition Conferences Cyberspace Predictive models Data science Feature extraction

Efficient and Parallel Separable Dictionary Learning

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Rusu, Cristian Irofti, Paul Department of Automatic Control and Computers Faculty of Automatic Control and Computers University Politehnica Bucharest Bucharest Romania Department of Computer Science Faculty of Mathematics and Computer Science University of Bucharest Bucharest Romania

Separable, or Kronecker product, dictionaries provide natural decompositions for 2D signals, such as images. In this paper, we describe a highly parallelizable algorithm that learns such dictionaries which reaches sparse representations competitive with the previous state of the art dictionary learning algorithms from the literature but at a lower computational cost. We highlight the performance of the proposed method to sparsely represent image and hyperspectral data, and for image denoising. Copyright © 2020, The Authors. All rights reserved.

关键词： Image denoising

TextBenDS: A generic textual data benchmark for distributed systems

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Truicǎ, Ciprian-Octavian Apostol, Elena Darmont, Jérôme Assent, Ira Computer Science and Engineering Department Faculty of Automatic Control and Computers University Politehnica of Bucharest Bucharest Romania Department of Computer Science Aarhus University Aarhus Denmark Université de Lyon ERIC Lyon 2 EA 3083 France DIGIT Department of Computer Science Aarhus University Denmark

Extracting top-k keywords and documents using weighting schemes are popular techniques employed in text mining and machine learning for different analysis and retrieval tasks. The weights are usually computed in the data preprocessing step, as they are costly to update and keep track of all the modifications performed on the dataset. Furthermore, computation errors are introduced when analyzing only subsets of the dataset. Therefore, in a Big Data context, it is crucial to lower the runtime of computing weighting schemes, without hindering the analysis process and the accuracy of the machine learning algorithms. To address this requirement for the task of top-k keywords and documents, it is customary to design benchmarks that compare weighting schemes within various configurations of distributed frameworks and database management systems. Thus, we propose a generic document-oriented benchmark for storing textual data and constructing weighting schemes (TextBenDS). Our benchmark offers a generic data model designed with a multidimensional approach for storing text documents. We also propose using aggregation queries with various complexities and selectivities for constructing term weighting schemes, that are utilized in extracting top-k keywords and documents. We evaluate the computing performance of the queries on several distributed environments set within the Apache Hadoop ecosystem. Our experimental results provide interesting insights. As an example, MongoDB proves to have the best overall performance, while Spark's execution time remains almost the same, regardless of the weighting schemes. Copyright © 2021, The Authors. All rights reserved.

关键词： Machine learning