检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Truica, Ciprian-Octavian Apostol, Elena-Simona Marogel, Marius Paschke, Adrian Computer Science and Engineering Department Faculty of Automatic Control and Computers National University of Science and Technology Politehnica Bucharest Splaiul Independentei 313 Bucharest060042 Romania Academy of Romanian Scientists Ilfov 3 Bucharest050044 Romania Department of Mathematics and Computer Science Freie Universität Berlin Arnimallee 14 Berlin14195 Germany Fraunhofer Institute for Open Communication Systems Kaiserin-Augusta-Allee 31 Berlin10589 Germany

In today’s digital age, fake news has become a major problem that has serious consequences, ranging from social unrest to political upheaval. To address this issue, new methods for detecting and mitigating fake news are required. In this work, we propose to incorporate contextual and network-aware features into the detection process. This involves analyzing not only the content of a news article but also the context in which it was shared and the network of users who shared it, i.e., the information diffusion. Thus, we propose GETAE, Graph Information Enhanced Deep Neural Network Ensemble ArchitecturE for Fake News Detection, a novel ensemble architecture that uses textual content together with the social interactions to improve fake news detection. GETAE contains two Branches: the Text Branch and the Propagation Branch. The Text Branch uses Word and Transformer Embeddings and a Deep Neural Network based on feed-forward and bidirectional Recurrent Neural Networks ([Bi]RNN) for learning novel contextual features and creating a novel Text Content Embedding. The Propagation Branch considers the information propagation within the graph network and proposes a Deep Learning architecture that employs Node Embeddings to create novel Propagation Embedding. GETAE Ensemble combines the two novel embeddings, i.e., Text Content Embedding and Propagation Embedding, to create a novel Propagation-Enhanced Content Embedding which is afterward used for classification. The experimental results obtained on two real-world publicly available datasets, i.e., Twitter15 and Twitter16, prove that using this approach improves fake news detection and outperforms state-of-the-art models. © 2024, CC BY-NC-ND.

关键词： Graph embeddings

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

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

引用

Federated Conference on computer science and Information Systems (FedCSIS)

作者： Przemysław Głomb Michał Cholewa Paweł Foszner Jakub Bularz Institute of Theoretical and Applied Informatics Polish Academy of Sciences Gliwice Poland Department of Computer Graphics Vision and Digital Systems Faculty of Automatic Control Electronics and Computer Science Silesian University of Technology Gliwice Poland AIUT Sp. z o.o. ul Gliwice Poland

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.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Pilots' Perceived Workload and Flight Performance while Interacting with Touchscreen Inceptor during Instrument Landings

Pilots' Perceived Workload and Flight Performance while Inte...

引用

Conference on Digital Avionics Systems (DASC)

作者： Jingyi Zhang Wojciech Tomasz Korek Wen-Chin Li Safety and Accident Investigation Centre School of Aerospace Transport and Manufacturing Cranfield University Cranfield United Kingdom Dynamics Simulation and Control Group School of Aerospace Transport and Manufacturing Cranfield University Cranfield United Kingdom Faculty of Automatic Control Electronics and Computer Science Silesian University of Technology Gliwice Poland

In this study, to dig into the further potential application of the touchscreen in flight operation, an integrated touchscreen system as the aircraft control inceptor was innovatively proposed. The touchscreen inceptor is integrated into the middle of the primary flight display allowing pilots to control the aircraft's movement horizontally (roll) and vertically (pitch) with their fingers. Fifty-six participants (23 pilots and 33 non-pilots) joined the Future Systems Simulator trail to perform instrument landings using the touchscreen and sidestick in conditions without and with simulated turbulence in vertical and horizontal channels. The heart rate variability reflecting the perceived workload was measured using the Inner Balance device. The flight data related to the flight path, touchdown location, and landing load were collected and calculated as the performance score. The three-way analysis of variance was applied to compare the perceived workload and flight performance between touchscreen and sidestick controllers in different disturbance conditions among pilots and nonpilots. The data analysis results indicated that in the scenario of landing with the disturbance, participants' heart rate variability was improved while interacting with the touchscreen inceptor compared to the sidestick. The flight performance of nonpilots while performing landing tasks with sidestick was significantly lower than pilots. Nevertheless, no significant difference in flight performance was found between nonpilots and pilots when using the touchscreen inceptor. The empirical study indicated that the touchscreen could provide a more intuitive interaction of a ‘point-where-you-want-to-go' control technique without the additional input device of sidestick to reduce the mental workload and cognitive stress. Furthermore, there is an evident decrease in performance score with the touchscreen inceptor compared to traditional sidestick due to the unfamiliarity of the touchscreen interacti

关键词：

来源：评论

学校读者我要写书评

暂无评论

The OPS-SAT benchmark for detecting anomalies in satellite telemetry

arXiv

引用

arXiv 2024年

作者： Ruszczak, Bogdan Kotowski, Krzysztof Evans, David Nalepa, Jakub Faculty of Electrical Engineering Automatic Control and Informatics Department of Informatics Opole University of Technology Prószkowska Str. 76 Opole45-758 Poland Faculty of Automatic Control Electronics and Computer Science Department of Algorithmics and Software Silesian University of Technology Akademicka Str. 16 Gliwice44-100 Poland KP Labs Bojkowska Str. 37J Gliwice44-100 Poland European Space Agency ESOC Robert-Bosch-Str. 5 Darmstadt64293 Germany

Detecting anomalous events in satellite telemetry is a critical task in space operations. This task, however, is extremely time-consuming, error-prone and human dependent, thus automated data-driven anomaly detection algorithms have been emerging at a steady pace. However, there are no publicly available datasets of real satellite telemetry accompanied with the ground-truth annotations that could be used to train and verify anomaly detection supervised models. In this article, we address this research gap and introduce the AI-ready benchmark dataset (OPSSAT-AD) containing the telemetry data acquired on board OPS-SAT—a CubeSat mission which has been operated by the European Space Agency which has come to an end during the night of 22–23 May 2024 (CEST). The dataset is accompanied with the baseline results obtained using 30 supervised and unsupervised classic and deep machine learning algorithms for anomaly detection. They were trained and validated using the training-test dataset split introduced in this work, and we present a suggested set of quality metrics which should be always calculated to confront the new algorithms for anomaly detection while exploiting OPSSAT-AD. We believe that this work may become an important step toward building a fair, reproducible and objective validation procedure that can be used to quantify the capabilities of the emerging anomaly detection techniques in an unbiased and fully transparent way. © 2024, CC BY.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Setting up a Distributed control System Laboratory 11

Setting up a Distributed Control System Laboratory

引用

11th International Conference and Exposition on Electrical And Power Engineering, EPE 2020

作者： Postovei, Danut Adrian Bulac, Constantin Tristiu, Ion Camachi, Balduino University Politehnica of Bucharest Faculty of Power Engineering Bucharest Romania University Politehnica of Bucharest Faculty of Automatic Control and Computer Science Bucharest Romania

ISBN: (纸本)9781728181264

This paper presents a practical laboratory for student education purpose in Distributed control Systems, with focus on applications for high voltage transmission substations. The monitoring, control and protection part is realized with a software platform and IED devices manufactured by AREVA TD France, while the primary equipment, like circuit breakers and disconnectors are simulated with latched relays. The system architecture and communication network are reproducing a real one usually used in transmission substations. The implementation of this laboratory, both through specific laboratory works and experiments, makes the theoretical part to be supported by a practical experience, resulting in future graduates with added value in the electric power industry. © 2020 IEEE.

关键词： Laboratories

来源：评论

学校读者我要写书评

暂无评论

Development of Unmanned Cargo VTOL Aircraft 1

引用

59th Symposium on Engineering Modelling in Mechanics, 2020

作者： Czyba, Roman Gorol, Zbigniew Lemanowicz, Marcin Pawlak, Mariusz Sikora, Adam Faculty of Automatic Control Electronics and Computer Science Department of Automatic Control and Robotics Silesian University of Technology Akademicka Street 2A Gliwice44-100 Poland Faculty of Mechanical Engineering Department of Theoretical and Applied Mechanics Silesian University of Technology Akademicka Street 2A Gliwice44-100 Poland Faculty of Chemistry Department of Chemical Engineering and Process Design Silesian University of Technology Akademicka Street 2A Gliwice44-100 Poland

ISBN: (数字)9783030684556

ISBN: (纸本)9783030684549

The aim of the paper is to present a design cycle regarding to the construction of an unmanned cargo aircraft with own weight up to 25 kg, operating range of up to 100 km and AGL operating ceiling of up to 1 km. The task of the project team was to plan the design cycle, perform analytical calculations and CFD simulations, and finally to build an unmanned aircraft capable of lifting cargo. At the same time, a number of assumptions and technical regulations regarding constructions had to be met, which are specified in legal regulations regarding the given class of unmanned aerial vehicles. In order to achieve optimal UAV aerodynamic properties, including maximization of the payload while minimizing the own weight, aerodynamic calculations and CFD simulations were performed. © 2021, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Standard vs. non-standard cross-validation: evaluation of performance in a space with structured distribution of datapoints

引用

Procedia computer science 2021年 192卷 1245-1254页

作者： Grzegorz Baron Urszula Stańczyk Department of Graphics Computer Vision and Digital Systems Faculty of Automatic Control Electronics and Computer Science Silesian University of Technology Akademicka 2A 44-100 Gliwice Poland

Cross-validation is a popularly used approach to evaluation of performance for classifiers. It relies on random selection of independent samples for training and testing, and assumes that if any similarities among samples exist, they do not lead to known grouping of datapoints in the input space. If these conditions are violated, as it may happen for datasets with some structure of samples included, standard cross-validation can return biased results even for many folds. In the paper the research on cross-validation was reported for application to stylometric datasets, describing a task of authorship attribution. The comparison of standard and non-standard processing was presented. In the latter case, selected subsets of examples were swapped over between training and test sets several times. The experiments with three popular classifiers showed that standard cross-validation tended to give over-optimistic results, whereas non-standard processing was more guarded, and by that more reliable. To avoid high computational costs involved, evaluation based on averaged predictions for limited numbers of test sets can be considered as a reasonable compromise.

关键词： Cross-validation Fold Evaluation of Performance Classification Distribution Stylometry

来源：评论

学校读者我要写书评

暂无评论

Weighting factor for attributes based on reduct cardinality

引用

Procedia computer science 2021年 192卷 1255-1264页

作者： Urszula Stańczyk Department of Graphics Computer Vision and Digital Systems Faculty of Automatic Control Electronics and Computer Science Silesian University of Technology Akademicka 2A 44-100 Gliwice Poland

Estimation of attribute importance can be obtained by a mechanism that allows to assign some weight to variables. Weighting attributes can lead to their ordering, which, in turn, can be exploited for feature selection and reduction. Decision reducts constitute an example of a mechanism aiming at dimensionality reduction, embedded in rough set approach to data mining. The paper presents research works, where the process of weighting was driven by the proposed factor based on reducts, with varying their sets, and the results were analysed through the perspective of reduct cardinality, since it is typically considered as the most significant indicator of reduct quality. Constructed rankings of variables were used for inferring sets of decision rules from gradually decreasing numbers of features, and then the performance of the rule classifiers was tested. The experiments show that for the weighting factor to be useful for feature reduction, not only reduct cardinalities, but also the numbers of reducts found need to be taken into account.

关键词： Weighting Ranking Feature selection Rough set theory Decision reduct Reduct cardinality

来源：评论

学校读者我要写书评

暂无评论

Multi-loop Sliding-Mode control for a Battery Charger Using a Quadratic Buck Converter

Multi-loop Sliding-Mode Control for a Battery Charger Using ...

引用

IEEE Annual Southern Power Electronics Conference (SPEC)

作者： Oswaldo López-Santos F. Flores-Bahamonde C. A. Torres-Pinzón Reham Haroun Hugo Valderrama-Blavi Juan A. Garriga Luis Martínez-Salamero Group of Automatic Control and Industrial Electronics Rovira i Virgili University Tarragona Spain Energy Transformation Center Faculty of Enigineering Universidad Andres Bello Chile Faculty of Electronic Engineering Universidad Santo Tomás Colombia Department of Computer Science and Industrial Engineering University of Lleida Lleida Spain

In this paper, the quadratic buck converter (QBC) is proposed as competitive alternative to implement a battery charger. Since, QBC is a high order system, the required control is designed to follow the conventional constant-current constant-voltage regime by means of three loops. Namely, i) an inner-loop operating in sliding mode to control the current of the closest inductor to the input port providing the properly stability of the system, ii) a first outer loop designed to regulate the battery voltage providing the reference of the inner loop, and finally iii) a second outer loop to regulate the battery current modifying the reference of the voltage loop. Proportional Integral (PI) controllers are used in both outer loops. Simulation results are presented validating the theoretical study.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Bacteriostatic Coatings Formed on Real Titanium Dental Implant

SSRN

引用

SSRN 2023年

作者： Kazek-Kęsik, Alicja Maciak, Weronika Kosczielny, Joanna Krok-Borkowicz, Malgorzata Reczyńska-Kolman, Katarzyna Student, Sebastian Śmiga-Matuszowicz, Monika Pamula, Elżbieta Simka, Wojciech Silesian University of Technology Faculty of Chemistry B. Krzywoustego Str. 6 Gliwice44-100 Poland Silesian University of Technology Biotechnology Centre Krzywoustego Str. 8 Gliwice44-100 Poland AGH University of Science and Technology Faculty of Materials Science and Ceramics Mickiewicza Av. 30 Krakow30-059 Poland Silesian University of Technology Institute of Automatic Control Faculty of Automatic Control Electronics and Computer Science Akademicka Str. 16 Gliwice44-100 Poland Silesian University of Technology Faculty of Chemistry M. Strzody Str. 9 Gliwice44-100 Poland

Veterinary titanium (Ti) real dental implants were anodized in calcium hypophosphite solution to obtain a porous, bioactive layer. The anodized implant surface was covered by a poly(sebacic anhydride) (PSBA) layer with amoxicillin. SEM analysis showed an irregular distribution of the antibiotic on the surface. However, confocal microscopy images revealed the formation of a uniform polymer layer. The thickness of the oxide and polymer layers was similar, between 6-9 μm. PSBA is an easy, hydrolysable polymer. After the polymer with amoxicillin was immersed in phosphate buffered solution (PBS) solution for 1 h, more than 53% of hydrolysis products were detected by 1H NMR spectroscopy. After 9 days of polymer immersion, the hydrolysis product content was more than 67%. Drug release was analyzed using high-performance liquid chromatography (HPLC). After 1 h of implant immersion in PBS an average of 6.0 μg/mL of amoxicillin was released. Importantly, the released concentration of amoxicillin was enough to inhibit S. aureus (ATCC 25923) and S. epidermidis (ATCC 12228) growth and decrease their adhesion to the implant surface. This paper presents the cytocompatibility results of PSBA, amoxicillin, and extracts collected from the implants exposed to mouse fibroblast L929 and osteoblast-like MG-63 cells. PSBA concentrations up to 1% did not significantly affect cell viability. Amoxicillin concentrations up to 150 μl/mL were cytocompatible with both cells line. Cell viability was greater than 70% for both cell lines after 24 h of treatment with extracts from modified implants that were immersed in PBS for 72 h prior to viability experiments. This work presents a simple method to obtain a hybrid, bacteriostatic and biocompatible layer on long-term implant surfaces. These techniques may find application in the surface treatment of various Ti implants with a variety of shapes and sizes. © 2023, The Authors. All rights reserved.

关键词： Titanium

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：