首页 > 最新文献

2020 18th International Conference on Emerging eLearning Technologies and Applications (ICETA)最新文献

英文 中文
Teaching Course on Algorithms and Data Structures during the Coronavirus Pandemic 新冠肺炎疫情期间算法与数据结构教学课程
Michal Varga, M. Kvassay, Marek Kvet
At the beginning of spring 2020, the life in Slovakia and in other European countries has slowed down due to coronavirus disease 2019 caused by SARS-CoV-2. Slovakia and many other countries have tried to stop or slow down the spread of the coronavirus by minimizing face-to-face interactions between people. This has resulted in reduction of public transport, closing churches, shops, restaurants, and a lot of other services, including education. During the second half of March 2020, most education institutions, including universities, were closed to the public. Students and teachers could not visit them, and the process of education had to move from a classical physical space to a virtual space. Traditional face-to-face education supported by online learning had to be replaced by distance learning very quickly. However, most of the education institutions in Slovakia were not be prepared for this since distance learning had not been actively used by them before. Also universities, which provide education that requires much more self-study than in case of primary and secondary schools, challenged to problems how the distance learning should be realized in such a short term. In this paper, we present how some of the challenges and issues related to fast transformation of face-to-face education to education based on distance learning were solved by us within a course on algorithms and data structures taught at the Faculty of Management Science and Informatics of University of Zilina. Results presented in the paper indicate that a course requiring active participation of a student in the learning process by solving real world problems can be taught effectively using distance learning and the quality of education and knowledge grasped by students do not suffer from absence of face-to-face lectures and practical classes.
2020年春季伊始,由于SARS-CoV-2引起的2019冠状病毒病,斯洛伐克和其他欧洲国家的生活放缓。斯洛伐克和许多其他国家试图通过尽量减少人与人之间的面对面互动来阻止或减缓冠状病毒的传播。这导致公共交通减少,教堂、商店、餐馆和许多其他服务关闭,包括教育。2020年3月下半月,包括大学在内的大多数教育机构对公众关闭。学生和老师不能参观,教育的过程不得不从经典的物理空间转移到虚拟空间。由在线学习支持的传统面对面教育必须很快被远程学习所取代。但是,斯洛伐克的大多数教育机构没有为此做好准备,因为它们以前没有积极利用远程学习。此外,大学提供的教育比小学和中学需要更多的自学,挑战的问题是如何在这么短的时间内实现远程学习。在本文中,我们介绍了我们如何在淄博大学管理科学与信息学院的算法和数据结构课程中解决了与面对面教育到基于远程学习的教育的快速转变相关的一些挑战和问题。本文的研究结果表明,通过解决现实世界的问题,要求学生积极参与学习过程的课程可以通过远程学习有效地教授,并且学生掌握的教育质量和知识不会因为缺乏面对面的讲座和实践课程而受到影响。
{"title":"Teaching Course on Algorithms and Data Structures during the Coronavirus Pandemic","authors":"Michal Varga, M. Kvassay, Marek Kvet","doi":"10.1109/ICETA51985.2020.9379156","DOIUrl":"https://doi.org/10.1109/ICETA51985.2020.9379156","url":null,"abstract":"At the beginning of spring 2020, the life in Slovakia and in other European countries has slowed down due to coronavirus disease 2019 caused by SARS-CoV-2. Slovakia and many other countries have tried to stop or slow down the spread of the coronavirus by minimizing face-to-face interactions between people. This has resulted in reduction of public transport, closing churches, shops, restaurants, and a lot of other services, including education. During the second half of March 2020, most education institutions, including universities, were closed to the public. Students and teachers could not visit them, and the process of education had to move from a classical physical space to a virtual space. Traditional face-to-face education supported by online learning had to be replaced by distance learning very quickly. However, most of the education institutions in Slovakia were not be prepared for this since distance learning had not been actively used by them before. Also universities, which provide education that requires much more self-study than in case of primary and secondary schools, challenged to problems how the distance learning should be realized in such a short term. In this paper, we present how some of the challenges and issues related to fast transformation of face-to-face education to education based on distance learning were solved by us within a course on algorithms and data structures taught at the Faculty of Management Science and Informatics of University of Zilina. Results presented in the paper indicate that a course requiring active participation of a student in the learning process by solving real world problems can be taught effectively using distance learning and the quality of education and knowledge grasped by students do not suffer from absence of face-to-face lectures and practical classes.","PeriodicalId":149716,"journal":{"name":"2020 18th International Conference on Emerging eLearning Technologies and Applications (ICETA)","volume":"80 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132424446","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
Vulkan in C# for Multi-Platform Real- Time Graphics Vulkan在c#中用于多平台实时图形
Dávid Szabó, Z. Illés
Nowadays almost every computer device contains a graphics processor. Large desktop PCs have dedicated graphics cards, laptops and even mobiles have integrated graphics units inside the CPU. To use and program these graphics units we need special libraries, the Graphics APIs. Usually these APIs are made in C or C++ to ensure low-level capabilities and high performance. In the meantime, the .NET supported C# language evolved greatly in the past years. C# is now a fast, powerful and multi-platform language. [1] The main goal of our research is the merging of these two worlds: We're examining the possibilities of the real-time graphical programming in .NET C# using the modern Vulkan graphics API. This paper presents methods of creating multi-platform real-time graphical libraries using Vulkan in .NET C#. We provide solutions for rendering onto common .NET UI frameworks with Vulkan and techniques for dealing with the low-level memory management required by the API. Furthermore, we determine the functional and performance differences between multiple runtimes and compilers.
现在几乎每台计算机设备都包含一个图形处理器。大型台式电脑有专用的显卡,笔记本电脑甚至手机都在CPU内集成了图形单元。为了使用和编程这些图形单元,我们需要特殊的库,即图形api。通常,这些api是用C或c++编写的,以确保低级功能和高性能。与此同时,. net支持的c#语言在过去的几年里有了很大的发展。c#现在是一种快速、强大和多平台的语言。[1]我们研究的主要目标是合并这两个世界:我们正在研究使用现代Vulkan图形API在。net c#中进行实时图形编程的可能性。本文介绍了在。net c#中使用Vulkan创建多平台实时图形库的方法。我们提供了使用Vulkan在通用。net UI框架上进行渲染的解决方案,以及处理API所需的低级内存管理的技术。此外,我们还确定了多个运行时和编译器之间的功能和性能差异。
{"title":"Vulkan in C# for Multi-Platform Real- Time Graphics","authors":"Dávid Szabó, Z. Illés","doi":"10.1109/ICETA51985.2020.9379169","DOIUrl":"https://doi.org/10.1109/ICETA51985.2020.9379169","url":null,"abstract":"Nowadays almost every computer device contains a graphics processor. Large desktop PCs have dedicated graphics cards, laptops and even mobiles have integrated graphics units inside the CPU. To use and program these graphics units we need special libraries, the Graphics APIs. Usually these APIs are made in C or C++ to ensure low-level capabilities and high performance. In the meantime, the .NET supported C# language evolved greatly in the past years. C# is now a fast, powerful and multi-platform language. [1] The main goal of our research is the merging of these two worlds: We're examining the possibilities of the real-time graphical programming in .NET C# using the modern Vulkan graphics API. This paper presents methods of creating multi-platform real-time graphical libraries using Vulkan in .NET C#. We provide solutions for rendering onto common .NET UI frameworks with Vulkan and techniques for dealing with the low-level memory management required by the API. Furthermore, we determine the functional and performance differences between multiple runtimes and compilers.","PeriodicalId":149716,"journal":{"name":"2020 18th International Conference on Emerging eLearning Technologies and Applications (ICETA)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132080978","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
Analysis of Network Traffic in CLOUD Environment 云环境下的网络流量分析
M. Hasin, B. Madoš, J. Palša, Alla Janitor
The article focuses on the research and design of the infrastructure used for data collection from the network traffic of the CLOUD platform. The aim was to identify the structure of network traffic that occurs in the CLOUD platform. From the mentioned data it is possible to evaluate network security of the protocols used in communication and subsequently compare the obtained data with the security standards introduced in the experimental platform. When implementing the measurement, the NetFlow protocol was used, enabling data collection directly on virtual machines located in the CLOUD platform. The measured data was then stored in the non-relational database Elasticsearch. The selected database is intended for the analysis of a large amount of data. The most important part is the creation of an interactive web environment in order to interpret the measured data in a user-friendly form. The next step in the processing of measured data involves the application of artificial intelligence methods to evaluate and predict the existence of potential security problems.
本文重点研究和设计了用于云平台网络流量数据采集的基础设施。目的是确定发生在云平台上的网络流量的结构。根据上述数据,可以评估通信中使用的协议的网络安全性,并随后将获得的数据与实验平台中引入的安全标准进行比较。在实施测量时,使用了NetFlow协议,可以直接在位于CLOUD平台的虚拟机上收集数据。测量的数据随后存储在非关系数据库Elasticsearch中。所选择的数据库用于分析大量数据。最重要的部分是创建一个交互式网络环境,以便以用户友好的形式解释测量数据。测量数据处理的下一步涉及应用人工智能方法来评估和预测潜在安全问题的存在。
{"title":"Analysis of Network Traffic in CLOUD Environment","authors":"M. Hasin, B. Madoš, J. Palša, Alla Janitor","doi":"10.1109/ICETA51985.2020.9379153","DOIUrl":"https://doi.org/10.1109/ICETA51985.2020.9379153","url":null,"abstract":"The article focuses on the research and design of the infrastructure used for data collection from the network traffic of the CLOUD platform. The aim was to identify the structure of network traffic that occurs in the CLOUD platform. From the mentioned data it is possible to evaluate network security of the protocols used in communication and subsequently compare the obtained data with the security standards introduced in the experimental platform. When implementing the measurement, the NetFlow protocol was used, enabling data collection directly on virtual machines located in the CLOUD platform. The measured data was then stored in the non-relational database Elasticsearch. The selected database is intended for the analysis of a large amount of data. The most important part is the creation of an interactive web environment in order to interpret the measured data in a user-friendly form. The next step in the processing of measured data involves the application of artificial intelligence methods to evaluate and predict the existence of potential security problems.","PeriodicalId":149716,"journal":{"name":"2020 18th International Conference on Emerging eLearning Technologies and Applications (ICETA)","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116333822","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Editor of the Monte Carlo Method for Special Purpose 编辑蒙特卡罗方法的特殊用途
Veronika Stoffová, R. Horváth
The contribution describes an interactive computer implementation of the Monte Carlo method for particular purposes - to diagnose the foot condition according to the footprint of a person, to recognise the flat foot. Monte Carlo method, with a combination of computer graphics and numerical mathematics, allows us to calculate an unknown area where a direct analytical solution does not exist, or we do not know it. It is widely used, for example, in quickly finding approximate results of various calculations, such as calculating a definite integral, determining the probabilities of events in individual events, empirically determining the value, cost estimates in certain situations, and so on. It is an empirical-numerical method based on the use of values of random variables and probability theory. Our goal was to implement a general-purpose interactive software that will allow by the Monte Carlo method to determine the content of any irregular area in the form of a digital image. The presented software is implemented in Java using the programming framework GRobot. The graphic user interface is characteristic of this framework and is suitable for this type of applications. The Monte Carlo method forms a thematic unit of the subject of modelling and simulation at universities. It is often also the topic of students' semester, competition, and final theses. The beginnings of the editor described here also goes back to the semester, later diploma thesis of a student of computer science teacher programme at the Faculty of Education of the Trnava University in Trnava. The mentioned projects were developed under the guidance and significant help of the authors of this article.
贡献描述了蒙特卡罗方法的交互式计算机实现,用于特定目的-根据人的足迹诊断足部状况,识别平足。蒙特卡罗方法结合了计算机图形学和数值数学,使我们能够计算不存在直接解析解的未知区域,或者我们不知道它。它被广泛使用,例如,快速找到各种计算的近似结果,如计算定积分,确定单个事件中事件的概率,经验地确定值,在某些情况下的成本估算等。它是一种基于随机变量值和概率论的经验数值方法。我们的目标是实现一个通用的交互式软件,该软件将允许通过蒙特卡罗方法以数字图像的形式确定任何不规则区域的内容。本软件采用Java语言,使用编程框架GRobot实现。图形用户界面是该框架的特点,适合这类应用程序。蒙特卡罗方法构成了大学建模与仿真学科的一个专题单元。这通常也是学生学期、比赛和毕业论文的主题。这里所描述的编辑的开始也可以追溯到特尔纳瓦特尔纳瓦大学教育学院计算机科学教师课程的一名学生的毕业论文。上述项目是在本文作者的指导和大力帮助下开发的。
{"title":"Editor of the Monte Carlo Method for Special Purpose","authors":"Veronika Stoffová, R. Horváth","doi":"10.1109/ICETA51985.2020.9379210","DOIUrl":"https://doi.org/10.1109/ICETA51985.2020.9379210","url":null,"abstract":"The contribution describes an interactive computer implementation of the Monte Carlo method for particular purposes - to diagnose the foot condition according to the footprint of a person, to recognise the flat foot. Monte Carlo method, with a combination of computer graphics and numerical mathematics, allows us to calculate an unknown area where a direct analytical solution does not exist, or we do not know it. It is widely used, for example, in quickly finding approximate results of various calculations, such as calculating a definite integral, determining the probabilities of events in individual events, empirically determining the value, cost estimates in certain situations, and so on. It is an empirical-numerical method based on the use of values of random variables and probability theory. Our goal was to implement a general-purpose interactive software that will allow by the Monte Carlo method to determine the content of any irregular area in the form of a digital image. The presented software is implemented in Java using the programming framework GRobot. The graphic user interface is characteristic of this framework and is suitable for this type of applications. The Monte Carlo method forms a thematic unit of the subject of modelling and simulation at universities. It is often also the topic of students' semester, competition, and final theses. The beginnings of the editor described here also goes back to the semester, later diploma thesis of a student of computer science teacher programme at the Faculty of Education of the Trnava University in Trnava. The mentioned projects were developed under the guidance and significant help of the authors of this article.","PeriodicalId":149716,"journal":{"name":"2020 18th International Conference on Emerging eLearning Technologies and Applications (ICETA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134439045","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Energy Harvesting for Wireless Embedded Systems 无线嵌入式系统的能量收集
V. Kunštár, T. Krajcovic
This paper discusses the selection of equipment for collecting energy from the environment. Different types of energy cell are compared from different perspectives, the performance and efficiency of the devices are analyzed. In general, we focus on the most well-known types of devices, such as photovoltaic panels. The reason for choosing these devices is their frequent use. We try to find the most suitable type of photoelectric panel for WESPEH.
本文讨论了从环境中收集能源的设备选择问题。从不同的角度对不同类型的能量电池进行了比较,分析了器件的性能和效率。一般来说,我们专注于最知名的设备类型,例如光伏板。选择这些设备的原因是它们的频繁使用。我们试图找到最适合WESPEH的光电面板类型。
{"title":"Energy Harvesting for Wireless Embedded Systems","authors":"V. Kunštár, T. Krajcovic","doi":"10.1109/ICETA51985.2020.9379270","DOIUrl":"https://doi.org/10.1109/ICETA51985.2020.9379270","url":null,"abstract":"This paper discusses the selection of equipment for collecting energy from the environment. Different types of energy cell are compared from different perspectives, the performance and efficiency of the devices are analyzed. In general, we focus on the most well-known types of devices, such as photovoltaic panels. The reason for choosing these devices is their frequent use. We try to find the most suitable type of photoelectric panel for WESPEH.","PeriodicalId":149716,"journal":{"name":"2020 18th International Conference on Emerging eLearning Technologies and Applications (ICETA)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133935196","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Web Application for Graph Visualization Purposes 用于图形可视化目的的Web应用程序
A. Dudáš, J. Janky, J. Škrinárová
Graphs are one of several abstract topics presented in teaching of computer science at university. Graphs are part of various subjects such as optimization, compilers, networks, etc. Main objective of this paper is to present online application aimed at graph visualization. Implemented tool can be also used as a translator between various formats of graph description - adjacency matrix, graph6 format and diagram of graph. The greatest emphasis was placed on functionalities which are lacking in other online tools for similar purposes - mainly method of graphical representation of graph, possibility of various forms of input for graphical representation and possibility of multiple graphs on the input for simultaneous visualization of set of graphs. Presented application is first part of Moodle course project which is focused on graphs and parallel computing.
图是大学计算机科学教学中出现的几个抽象主题之一。图是各种主题的一部分,如优化、编译器、网络等。本文的主要目的是介绍一种面向图形可视化的在线应用程序。所实现的工具还可以作为各种图形描述格式-邻接矩阵,graph6格式和图的图之间的转换器。最大的重点是放在其他在线工具所缺乏的功能上,用于类似的目的-主要是图形表示的图形方法,图形表示的各种形式的输入的可能性,以及同时可视化一组图形的输入上的多个图形的可能性。该应用程序是Moodle课程项目的第一部分,该项目侧重于图形和并行计算。
{"title":"Web Application for Graph Visualization Purposes","authors":"A. Dudáš, J. Janky, J. Škrinárová","doi":"10.1109/ICETA51985.2020.9379200","DOIUrl":"https://doi.org/10.1109/ICETA51985.2020.9379200","url":null,"abstract":"Graphs are one of several abstract topics presented in teaching of computer science at university. Graphs are part of various subjects such as optimization, compilers, networks, etc. Main objective of this paper is to present online application aimed at graph visualization. Implemented tool can be also used as a translator between various formats of graph description - adjacency matrix, graph6 format and diagram of graph. The greatest emphasis was placed on functionalities which are lacking in other online tools for similar purposes - mainly method of graphical representation of graph, possibility of various forms of input for graphical representation and possibility of multiple graphs on the input for simultaneous visualization of set of graphs. Presented application is first part of Moodle course project which is focused on graphs and parallel computing.","PeriodicalId":149716,"journal":{"name":"2020 18th International Conference on Emerging eLearning Technologies and Applications (ICETA)","volume":"96 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134162557","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
Annotated dataset for the fake news classification in Slovak language 斯洛伐克语假新闻分类的标注数据集
M. Sarnovský, V. Maslej-Krešňáková, Nikola Hrabovska
Fake news detection currently presents an active field of research. Detection methods based on natural language processing and machine learning are being developed to automatically identify the possible misinformation contained within the news articles. To successfully train these models, annotated data are needed. In English language, multiple human-annotated datasets already are available and are being widely used in the research. The main objective of the work presented in this paper, was to create similar dataset consisting of articles in Slovak language. We collected the data from the various local news portals including reputable publishers as well as suspicious conspiratory portals. To obtain the annotations, we used crowdsourcing approach. Annotated dataset was used in preliminary experiments, in which neural network classifier was trained and evaluated.
假新闻检测目前是一个活跃的研究领域。基于自然语言处理和机器学习的检测方法正在开发中,以自动识别新闻文章中可能包含的错误信息。为了成功地训练这些模型,需要带注释的数据。在英语语言中,已有多个人工注释的数据集可供使用,并在研究中广泛使用。本文提出的工作的主要目标是创建由斯洛伐克语文章组成的类似数据集。我们从各个地方的新闻门户网站收集数据,包括有信誉的出版商和可疑的阴谋门户网站。为了获得注释,我们使用了众包的方法。初步实验采用带注释的数据集,对神经网络分类器进行训练和评价。
{"title":"Annotated dataset for the fake news classification in Slovak language","authors":"M. Sarnovský, V. Maslej-Krešňáková, Nikola Hrabovska","doi":"10.1109/ICETA51985.2020.9379254","DOIUrl":"https://doi.org/10.1109/ICETA51985.2020.9379254","url":null,"abstract":"Fake news detection currently presents an active field of research. Detection methods based on natural language processing and machine learning are being developed to automatically identify the possible misinformation contained within the news articles. To successfully train these models, annotated data are needed. In English language, multiple human-annotated datasets already are available and are being widely used in the research. The main objective of the work presented in this paper, was to create similar dataset consisting of articles in Slovak language. We collected the data from the various local news portals including reputable publishers as well as suspicious conspiratory portals. To obtain the annotations, we used crowdsourcing approach. Annotated dataset was used in preliminary experiments, in which neural network classifier was trained and evaluated.","PeriodicalId":149716,"journal":{"name":"2020 18th International Conference on Emerging eLearning Technologies and Applications (ICETA)","volume":"9 42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116571102","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 4
PCA Tail as the Anomaly Indicator PCA Tail作为异常指标
O. Škvarek, M. Klimo, Jaroslav Kopčan
Nowadays, tools based on machine learning becomes an integral part of education. Propper application of these tools brings benefits, but misuse can be dangerous. The pattern recognition system always indicates the class most similar to the submitted pattern based on the features extracted from the training set. Designers optimise recognisers for specific training set classes. Still, users may not be familiar with its preparation methodology, and thus, they may apply the recognition system to samples incompatible to the training set (outliers, novelties, anomalies). This paper analyses a tail remaining after linear principal component analysis as an anomaly indicator. A nonlinear approach based on generative adversarial networks (GAN) is also presented. In addition to the result of the recognition, the user also gets a level of its credibility categorised into three classes: accept, do not decide, reject. For example, Fashion-MNIST queries were submitted to the recogniser trained on the MNIST database. The proposed linear misuse detector refused all of them; the neural network-based detector failed in 4.81 % of queries. For a more detailed analysis, MNIST samples corrupted by Gaussian noise were admitted presented to the misuse detector trained on the noiseless MNIST dataset. The experiments revealed a sharp border between acceptance and non-acceptance (no decision or rejection) decisions.
如今,基于机器学习的工具已成为教育不可或缺的一部分。适当地应用这些工具会带来好处,但滥用可能是危险的。模式识别系统总是根据从训练集中提取的特征来指出与提交的模式最相似的类。设计师为特定的训练集类优化识别器。尽管如此,用户可能不熟悉它的准备方法,因此,他们可能会将识别系统应用于与训练集不兼容的样本(异常值、新奇、异常)。本文分析了线性主成分分析后的尾余量作为异常指标。提出了一种基于生成对抗网络(GAN)的非线性方法。除了识别结果之外,用户还会得到一个可信度等级,分为三类:接受、不决定、拒绝。例如,Fashion-MNIST查询被提交给在MNIST数据库上训练的识别器。提出的线性误用检测器拒绝了所有这些;基于神经网络的检测器在4.81%的查询中失败。为了进行更详细的分析,被高斯噪声损坏的MNIST样本被允许提交给在无噪声MNIST数据集上训练的误用检测器。实验揭示了接受和不接受(没有决定或拒绝)决定之间的明显界限。
{"title":"PCA Tail as the Anomaly Indicator","authors":"O. Škvarek, M. Klimo, Jaroslav Kopčan","doi":"10.1109/ICETA51985.2020.9379267","DOIUrl":"https://doi.org/10.1109/ICETA51985.2020.9379267","url":null,"abstract":"Nowadays, tools based on machine learning becomes an integral part of education. Propper application of these tools brings benefits, but misuse can be dangerous. The pattern recognition system always indicates the class most similar to the submitted pattern based on the features extracted from the training set. Designers optimise recognisers for specific training set classes. Still, users may not be familiar with its preparation methodology, and thus, they may apply the recognition system to samples incompatible to the training set (outliers, novelties, anomalies). This paper analyses a tail remaining after linear principal component analysis as an anomaly indicator. A nonlinear approach based on generative adversarial networks (GAN) is also presented. In addition to the result of the recognition, the user also gets a level of its credibility categorised into three classes: accept, do not decide, reject. For example, Fashion-MNIST queries were submitted to the recogniser trained on the MNIST database. The proposed linear misuse detector refused all of them; the neural network-based detector failed in 4.81 % of queries. For a more detailed analysis, MNIST samples corrupted by Gaussian noise were admitted presented to the misuse detector trained on the noiseless MNIST dataset. The experiments revealed a sharp border between acceptance and non-acceptance (no decision or rejection) decisions.","PeriodicalId":149716,"journal":{"name":"2020 18th International Conference on Emerging eLearning Technologies and Applications (ICETA)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115365120","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
Wrist Rehabilitation in Carpal Tunnel Syndrome by Gaming using EMG Controller 肌电控制游戏对腕管综合征腕关节康复的影响
P. Lukács, E. Pietriková
Technological progress brings many significant benefits to our lives, but also new obstacles that we must face. Increasingly widespread sedentary jobs and computer work contribute to various health problems, such as carpal tunnel syndrome. This disease can be relatively successfully treated or prevented through rehabilitation exercises. However, patients often find these exercises boring and they are not determined to perform them precisely. The aim of this paper is to develop a rehabilitation game application providing more entertaining form of exercise and motivate them to regular rehabilitation.
技术进步给我们的生活带来了许多显著的好处,但也给我们带来了必须面对的新障碍。越来越普遍的久坐不动的工作和电脑工作会导致各种健康问题,比如腕管综合症。这种疾病可以通过康复训练相对成功地治疗或预防。然而,患者经常发现这些练习很无聊,他们不确定要精确地执行它们。本文的目的是开发一个康复游戏应用程序,提供更有趣的运动形式,并激励他们定期康复。
{"title":"Wrist Rehabilitation in Carpal Tunnel Syndrome by Gaming using EMG Controller","authors":"P. Lukács, E. Pietriková","doi":"10.1109/ICETA51985.2020.9379203","DOIUrl":"https://doi.org/10.1109/ICETA51985.2020.9379203","url":null,"abstract":"Technological progress brings many significant benefits to our lives, but also new obstacles that we must face. Increasingly widespread sedentary jobs and computer work contribute to various health problems, such as carpal tunnel syndrome. This disease can be relatively successfully treated or prevented through rehabilitation exercises. However, patients often find these exercises boring and they are not determined to perform them precisely. The aim of this paper is to develop a rehabilitation game application providing more entertaining form of exercise and motivate them to regular rehabilitation.","PeriodicalId":149716,"journal":{"name":"2020 18th International Conference on Emerging eLearning Technologies and Applications (ICETA)","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131465093","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
Colors Perception in Object Detectors 物体检测器中的颜色感知
L. Vokorokos, Michal Hulic, Martin Stancel, Martin Knut
Detecting objects in computer vision have become very popular these days, especially in self-driving vehicles and autonomous cars. We are proposing a method to enhance this experience by detecting colors, which could also lead in the color perception by robotic systems in the future. First, there are technologies used described in the first section of the paper and then the algorithm itself is introduced with several conducted experiments.
如今,用计算机视觉检测物体已经变得非常流行,尤其是在自动驾驶汽车和自动驾驶汽车中。我们提出了一种通过检测颜色来增强这种体验的方法,这也可能在未来引领机器人系统的颜色感知。首先,本文第一部分描述了使用的技术,然后通过几个实验介绍了算法本身。
{"title":"Colors Perception in Object Detectors","authors":"L. Vokorokos, Michal Hulic, Martin Stancel, Martin Knut","doi":"10.1109/ICETA51985.2020.9379256","DOIUrl":"https://doi.org/10.1109/ICETA51985.2020.9379256","url":null,"abstract":"Detecting objects in computer vision have become very popular these days, especially in self-driving vehicles and autonomous cars. We are proposing a method to enhance this experience by detecting colors, which could also lead in the color perception by robotic systems in the future. First, there are technologies used described in the first section of the paper and then the algorithm itself is introduced with several conducted experiments.","PeriodicalId":149716,"journal":{"name":"2020 18th International Conference on Emerging eLearning Technologies and Applications (ICETA)","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128624413","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
期刊
2020 18th International Conference on Emerging eLearning Technologies and Applications (ICETA)
全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1