首页 > 最新文献

2021 IEEE 19th World Symposium on Applied Machine Intelligence and Informatics (SAMI)最新文献

英文 中文
Representation of Dense Volume Datasets Using Pointerless Sparse Voxel Octrees With Variable and Fixed-Length Encoding 用可变和固定长度编码的无指针稀疏体素八叉树表示密集体数据集
Pub Date : 2021-01-21 DOI: 10.1109/SAMI50585.2021.9378675
B. Madoš, N. Ádám, Martin Stancel
The paper deals with the problematics of the dense volume datasets representation, in which voxels are formed as multi-bit scalar values, and is oriented to the use of hierarchical data structures, not only as the medium for encoding and storing of volume datasets, but also for their lossless compression. The main contribution of the paper is in the design of the hierarchical data structure, that allows carving out of subtrees, that are homogenously filled not only by the symbol 0 or symbol 1, but any binary representation of voxel value from defined set of values. Designed data structure provides the possibility of fixed-length and also variable-length (Huffman) encoding of voxel values in leaf node level of the data structure and also in the non-leaf nodes. Results of tests, performed on medical volume datasets that were obtained by various non-invasive imaging techniques, including Computed Tomography and Magnetic Resonance Imaging, along with conclusions that were made, based on the test results, take place in the second part of the paper.
本文讨论了密集体数据集表示的问题,其中体素被形成为多位标量值,并面向分层数据结构的使用,不仅作为编码和存储体数据集的介质,而且还用于无损压缩。本文的主要贡献在于分层数据结构的设计,该结构允许雕刻出子树,这些子树不仅由符号0或符号1均匀填充,而且由定义值集的体素值的任何二进制表示填充。设计的数据结构提供了在数据结构的叶节点级别和非叶节点级别对体素值进行定长和变长(Huffman)编码的可能性。通过各种非侵入性成像技术(包括计算机断层扫描和磁共振成像)获得的医学体积数据集进行的测试结果,以及根据测试结果得出的结论,将在本文的第二部分中介绍。
{"title":"Representation of Dense Volume Datasets Using Pointerless Sparse Voxel Octrees With Variable and Fixed-Length Encoding","authors":"B. Madoš, N. Ádám, Martin Stancel","doi":"10.1109/SAMI50585.2021.9378675","DOIUrl":"https://doi.org/10.1109/SAMI50585.2021.9378675","url":null,"abstract":"The paper deals with the problematics of the dense volume datasets representation, in which voxels are formed as multi-bit scalar values, and is oriented to the use of hierarchical data structures, not only as the medium for encoding and storing of volume datasets, but also for their lossless compression. The main contribution of the paper is in the design of the hierarchical data structure, that allows carving out of subtrees, that are homogenously filled not only by the symbol 0 or symbol 1, but any binary representation of voxel value from defined set of values. Designed data structure provides the possibility of fixed-length and also variable-length (Huffman) encoding of voxel values in leaf node level of the data structure and also in the non-leaf nodes. Results of tests, performed on medical volume datasets that were obtained by various non-invasive imaging techniques, including Computed Tomography and Magnetic Resonance Imaging, along with conclusions that were made, based on the test results, take place in the second part of the paper.","PeriodicalId":402414,"journal":{"name":"2021 IEEE 19th World Symposium on Applied Machine Intelligence and Informatics (SAMI)","volume":"120 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116639244","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: 2
Pilot study: Measurement of mechanical load using a glass-coated microwire for implantology applications 试点研究:测量机械负荷使用玻璃涂层微丝种植应用
Pub Date : 2021-01-21 DOI: 10.1109/SAMI50585.2021.9378681
M. Kohan, R. Varga, R. Hudák, M. Schnitzer, Norbert Ferenčík, Gabriela Dancáková, S. Lancoš
The aim of the pilot study was to determine the mechanical load using a glass-coated microwire on 3 experimental samples at different positions of the microwire (vertical, horizontal, diagonal position) for possible application in the field of implantology. The production of experimental samples was created by additive technology from a flexible material. The mechanical load ranged from F = 40 N to F = 50 N and was measured by a force sensor. A frequency generator (GW instek GFG-3015) and an oscilloscope (Tektronix TDS 2001C) were used to generate and detect the signal. The switching field of the microwire was excited and sensed through 0.4 mm diameter (excitation coil) and 0.056 mm (sense coil) coils. The results of the study indicate a relationship between the switching field of the microwire and the mechanical load, and it was shown that in experimental samples 1 and 2 a decrease in the switching field of the microwire was detected as a result of poor fixation or bending of the microwire. Experimental sample 3 showed the best switching field values. However, by solving the fixation of the microwire into the implemented object, this type of microsensor makes a suitable candidate in the field of implantology.
初步研究的目的是在不同位置(垂直、水平、对角线位置)对3个实验样品使用玻璃包覆微丝确定机械载荷,以便在种植领域中应用。实验样品的生产是由一种柔性材料的添加剂技术创造的。机械载荷范围从F = 40 N到F = 50 N,由力传感器测量。频率发生器(GW instek GFG-3015)和示波器(Tektronix TDS 2001C)用于产生和检测信号。通过直径为0.4 mm的励磁线圈和直径为0.056 mm的感测线圈对微导线的开关场进行激励和感测。研究结果表明,微丝的开关场与机械载荷之间存在一定的关系,并且在实验样品1和2中,由于微丝固定不良或弯曲导致微丝的开关场减小。实验样品3显示出最佳的开关场值。然而,通过解决将微丝固定到被实施对象中的问题,这种类型的微传感器成为种植领域的合适候选者。
{"title":"Pilot study: Measurement of mechanical load using a glass-coated microwire for implantology applications","authors":"M. Kohan, R. Varga, R. Hudák, M. Schnitzer, Norbert Ferenčík, Gabriela Dancáková, S. Lancoš","doi":"10.1109/SAMI50585.2021.9378681","DOIUrl":"https://doi.org/10.1109/SAMI50585.2021.9378681","url":null,"abstract":"The aim of the pilot study was to determine the mechanical load using a glass-coated microwire on 3 experimental samples at different positions of the microwire (vertical, horizontal, diagonal position) for possible application in the field of implantology. The production of experimental samples was created by additive technology from a flexible material. The mechanical load ranged from F = 40 N to F = 50 N and was measured by a force sensor. A frequency generator (GW instek GFG-3015) and an oscilloscope (Tektronix TDS 2001C) were used to generate and detect the signal. The switching field of the microwire was excited and sensed through 0.4 mm diameter (excitation coil) and 0.056 mm (sense coil) coils. The results of the study indicate a relationship between the switching field of the microwire and the mechanical load, and it was shown that in experimental samples 1 and 2 a decrease in the switching field of the microwire was detected as a result of poor fixation or bending of the microwire. Experimental sample 3 showed the best switching field values. However, by solving the fixation of the microwire into the implemented object, this type of microsensor makes a suitable candidate in the field of implantology.","PeriodicalId":402414,"journal":{"name":"2021 IEEE 19th World Symposium on Applied Machine Intelligence and Informatics (SAMI)","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117265948","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
Petri net implementation in programmable logic controllers: methodology for development and validation 可编程逻辑控制器中的Petri网实现:开发和验证的方法学
Pub Date : 2021-01-21 DOI: 10.1109/SAMI50585.2021.9378673
Igor Azkarate Fernández, Juan Carlos Mugarza Cortabarría, Luka Eciolaza Echeverría
Lead times are key to good market positioning of providers of automated solutions based on a programmable logic controller (PLC). Testing control software against a digital twin (DT) of the process, any programming errors that may have incurred are detected before commissioning, which reduces project duration. This work raises the possibility of reducing that probability of error when programming discrete event dynamic systems (DEDS), by implementing a Petri net (PN) managing algorithm. A framework is presented which combines the use of this algorithm, by means of pre-incidence and post-incidence matrices and initial marking vector of a net, with code validation through emulation. A use case is brought forward in which the control program of a sequential process with parallel operations is implemented, with both virtual (VC) and real commissioning.
交货时间是基于可编程逻辑控制器(PLC)的自动化解决方案供应商良好市场定位的关键。针对过程的数字孪生(DT)测试控制软件,在调试之前检测到可能发生的任何编程错误,从而缩短了项目持续时间。这项工作通过实现Petri网(PN)管理算法,提高了在编程离散事件动态系统(DEDS)时减少错误概率的可能性。提出了一个框架,将该算法的使用结合起来,通过事前关联矩阵和事后关联矩阵以及网络的初始标记向量,并通过仿真验证代码。提出了一个用例,实现了具有并行操作的顺序过程的控制程序,并进行了虚拟调试和实际调试。
{"title":"Petri net implementation in programmable logic controllers: methodology for development and validation","authors":"Igor Azkarate Fernández, Juan Carlos Mugarza Cortabarría, Luka Eciolaza Echeverría","doi":"10.1109/SAMI50585.2021.9378673","DOIUrl":"https://doi.org/10.1109/SAMI50585.2021.9378673","url":null,"abstract":"Lead times are key to good market positioning of providers of automated solutions based on a programmable logic controller (PLC). Testing control software against a digital twin (DT) of the process, any programming errors that may have incurred are detected before commissioning, which reduces project duration. This work raises the possibility of reducing that probability of error when programming discrete event dynamic systems (DEDS), by implementing a Petri net (PN) managing algorithm. A framework is presented which combines the use of this algorithm, by means of pre-incidence and post-incidence matrices and initial marking vector of a net, with code validation through emulation. A use case is brought forward in which the control program of a sequential process with parallel operations is implemented, with both virtual (VC) and real commissioning.","PeriodicalId":402414,"journal":{"name":"2021 IEEE 19th World Symposium on Applied Machine Intelligence and Informatics (SAMI)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125991040","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
Measuring the morpho-syntactic ambiguity using the edit distance functions 使用编辑距离函数测量词法歧义
Pub Date : 2021-01-21 DOI: 10.1109/SAMI50585.2021.9378613
P. Bednar
This paper presents the application of edit distance functions for the measuring of morphological ambiguity and similarity between the natural languages. We propose sequence and tree edit distance functions for the Universal dependencies framework, which compare both morphological and syntactical annotations of the words in the sentences. The experiments were performed with the Slovak as a reference language and set of Slavic languages for comparison.
本文介绍了编辑距离函数在自然语言形态歧义和相似度度量中的应用。我们提出了通用依赖关系框架的序列和树编辑距离函数,用于比较句子中单词的形态和句法注释。实验是用斯洛伐克语作为参考语言和一组斯拉夫语言进行比较的。
{"title":"Measuring the morpho-syntactic ambiguity using the edit distance functions","authors":"P. Bednar","doi":"10.1109/SAMI50585.2021.9378613","DOIUrl":"https://doi.org/10.1109/SAMI50585.2021.9378613","url":null,"abstract":"This paper presents the application of edit distance functions for the measuring of morphological ambiguity and similarity between the natural languages. We propose sequence and tree edit distance functions for the Universal dependencies framework, which compare both morphological and syntactical annotations of the words in the sentences. The experiments were performed with the Slovak as a reference language and set of Slavic languages for comparison.","PeriodicalId":402414,"journal":{"name":"2021 IEEE 19th World Symposium on Applied Machine Intelligence and Informatics (SAMI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128862127","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
Influence of Heat Treatment on Dental Prostheses Produced by Additive Technology 热处理对增材工艺生产义齿的影响
Pub Date : 2021-01-21 DOI: 10.1109/SAMI50585.2021.9378627
V. Rajt’úková, Ľuboš Chromý, A. Balogová, G. Izaríková, Andrea Sinčák Konečná, R. Hudák
Heat treatment process represents an important part of metal-ceramic dental prostheses production process. The presented paper deals with the influence of heat treatment on the geometry of dental prostheses manufactured using SLM additive technology. Dental prostheses (crowns, two-unit bridges, thee-unit bridges) made from cobalt-chromium alloy on the device Mlab cusing R (Concept Laser, USA) via SLM technology. to-piece batch from each type of prostheses were produced. Subsequently, the pre- and post-heat treatment change in prosthesis geometry compared against the original.stl model was examined using GOM Inspect software (GOM, Germany). Crowns and two-unit bridges did not meet the normality requirement, therefore a non-parametric t-test (Wilcoxon test) was applied for variation comparison. Three-unit bridges met the normality criterion, therefore a parametric t-test was used to identify statistically relevant variations in dependent samples. Based on the results, we may conclude that the crowns and two-unit bridges manufactured via SLM technology do not change their geometry prior to or following the heat treatment. Three-unit bridges undergo geometry changes, therefore the heat treatment must be performed before the bridges are removed from a manufacturing platform.
热处理工艺是金属陶瓷口腔修复体生产工艺的重要组成部分。本文讨论了热处理对用SLM增材制造的义齿几何形状的影响。通过SLM技术,在Mlab设备上使用R (Concept Laser, USA)由钴铬合金制成的牙修复体(牙冠、二单元桥、三单元桥)。对每种类型的假体进行批量生产。随后,与原始假体相比,热处理前后假体几何形状发生了变化。采用GOM Inspect软件(德国GOM)对stl模型进行检验。冠和双单元桥不符合正态性要求,因此采用非参数t检验(Wilcoxon检验)进行变异比较。三单元桥符合正态性标准,因此使用参数t检验来识别依赖样本中统计相关的变化。根据结果,我们可以得出结论,通过SLM技术制造的冠和双单元桥在热处理前后不会改变其几何形状。三单元桥经历几何变化,因此必须在桥从制造平台移除之前进行热处理。
{"title":"Influence of Heat Treatment on Dental Prostheses Produced by Additive Technology","authors":"V. Rajt’úková, Ľuboš Chromý, A. Balogová, G. Izaríková, Andrea Sinčák Konečná, R. Hudák","doi":"10.1109/SAMI50585.2021.9378627","DOIUrl":"https://doi.org/10.1109/SAMI50585.2021.9378627","url":null,"abstract":"Heat treatment process represents an important part of metal-ceramic dental prostheses production process. The presented paper deals with the influence of heat treatment on the geometry of dental prostheses manufactured using SLM additive technology. Dental prostheses (crowns, two-unit bridges, thee-unit bridges) made from cobalt-chromium alloy on the device Mlab cusing R (Concept Laser, USA) via SLM technology. to-piece batch from each type of prostheses were produced. Subsequently, the pre- and post-heat treatment change in prosthesis geometry compared against the original.stl model was examined using GOM Inspect software (GOM, Germany). Crowns and two-unit bridges did not meet the normality requirement, therefore a non-parametric t-test (Wilcoxon test) was applied for variation comparison. Three-unit bridges met the normality criterion, therefore a parametric t-test was used to identify statistically relevant variations in dependent samples. Based on the results, we may conclude that the crowns and two-unit bridges manufactured via SLM technology do not change their geometry prior to or following the heat treatment. Three-unit bridges undergo geometry changes, therefore the heat treatment must be performed before the bridges are removed from a manufacturing platform.","PeriodicalId":402414,"journal":{"name":"2021 IEEE 19th World Symposium on Applied Machine Intelligence and Informatics (SAMI)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122643557","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
Multi-degree-of-freedom joint nonlinear motion control with considering the friction effect 考虑摩擦效应的多自由度关节非线性运动控制
Pub Date : 2021-01-21 DOI: 10.1109/SAMI50585.2021.9378674
Jiashuai Yang, Guoyuan Zhang, Liewen Wang, Jietian Wang, Hao Wang
Friction effect between joints needs to be considered in the fast changeover process of the dulcimer robot which is oriented to precise position control. A complete nonlinear dynamic equation with coulomb friction model for a six-degree-of-freedom robot is proposed. Based on Solidworks and Matlab SimMechanics dynamics model, the transformation and simulation of the above dynamic equations are completed, and the joint motion parameter recognition for the end positions is obtained. The results show that with and without considering the friction, the maximum difference on the moment response of joints of the robot is 7%. In order to precisely control the movement of each joint, a track tracking method combining traditional PID control and adaptive fuzzy PID control is proposed, and the angular difference of each joint track can keep within the range below 0.08 rad. The research process and results provide a theoretical reference for improving the high-speed position accuracy and evaluating the response characteristics of the multi -degree-of-freedom dulcimer robot, and have important engineering reference for ensuring the accurate acquisition of the multi-degree-of-freedom robot's motion.
扬琴机器人以精确的位置控制为导向,在快速转换过程中需要考虑关节间的摩擦效应。提出了六自由度机器人具有库仑摩擦模型的完全非线性动力学方程。基于Solidworks和Matlab SimMechanics动力学模型,完成了上述动力学方程的变换和仿真,得到了末端位置的关节运动参数识别。结果表明,考虑摩擦和不考虑摩擦时,机器人关节力矩响应的最大差异为7%。为了精确控制各关节的运动,提出了一种传统PID控制与自适应模糊PID控制相结合的轨迹跟踪方法,使各关节的轨迹角差保持在0.08 rad以内。研究过程和结果为提高多自由度扬琴机器人的高速定位精度和评价其响应特性提供了理论参考。对保证多自由度机器人运动的准确采集具有重要的工程参考意义。
{"title":"Multi-degree-of-freedom joint nonlinear motion control with considering the friction effect","authors":"Jiashuai Yang, Guoyuan Zhang, Liewen Wang, Jietian Wang, Hao Wang","doi":"10.1109/SAMI50585.2021.9378674","DOIUrl":"https://doi.org/10.1109/SAMI50585.2021.9378674","url":null,"abstract":"Friction effect between joints needs to be considered in the fast changeover process of the dulcimer robot which is oriented to precise position control. A complete nonlinear dynamic equation with coulomb friction model for a six-degree-of-freedom robot is proposed. Based on Solidworks and Matlab SimMechanics dynamics model, the transformation and simulation of the above dynamic equations are completed, and the joint motion parameter recognition for the end positions is obtained. The results show that with and without considering the friction, the maximum difference on the moment response of joints of the robot is 7%. In order to precisely control the movement of each joint, a track tracking method combining traditional PID control and adaptive fuzzy PID control is proposed, and the angular difference of each joint track can keep within the range below 0.08 rad. The research process and results provide a theoretical reference for improving the high-speed position accuracy and evaluating the response characteristics of the multi -degree-of-freedom dulcimer robot, and have important engineering reference for ensuring the accurate acquisition of the multi-degree-of-freedom robot's motion.","PeriodicalId":402414,"journal":{"name":"2021 IEEE 19th World Symposium on Applied Machine Intelligence and Informatics (SAMI)","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131179821","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: 2
Algorithms of Machine Learning in Recognition of Trolls in Online Space 网络空间巨魔识别中的机器学习算法
Pub Date : 2021-01-21 DOI: 10.1109/SAMI50585.2021.9378699
K. Machová, Michal Porezaný, Miroslava Hresková
The Internet is becoming more and more accessible and widespread. With a growing user base, we also encounter more often the anti-social behavior of users. One of these forms of behavior is a trollism. The problem of troll's comments regulation becomes more and more important. One of possible solutions is a recognition of trolls by machine learning models. The work deals with the behavior of trolls on the Internet, the possibilities of the trollism detection and types of data, which can be used to it. The proposed approach is based on the use of Support Vectors Machine, Multinomial Naïve Bayes, and Logistic Regression. The best results were achieved by Multinomial Naïve Bayes model up to 0,92 of Recall.
互联网正变得越来越普及。随着用户基础的增长,我们也经常遇到用户的反社会行为。其中一种行为形式是巨魔行为。喷子评论的监管问题变得越来越重要。一个可能的解决方案是通过机器学习模型识别喷子。研究了网络喷子的行为、网络喷子检测的可能性和可用于网络喷子检测的数据类型。提出的方法是基于使用支持向量机,多项式Naïve贝叶斯和逻辑回归。多项式Naïve贝叶斯模型在召回率为0.92的情况下取得了最好的结果。
{"title":"Algorithms of Machine Learning in Recognition of Trolls in Online Space","authors":"K. Machová, Michal Porezaný, Miroslava Hresková","doi":"10.1109/SAMI50585.2021.9378699","DOIUrl":"https://doi.org/10.1109/SAMI50585.2021.9378699","url":null,"abstract":"The Internet is becoming more and more accessible and widespread. With a growing user base, we also encounter more often the anti-social behavior of users. One of these forms of behavior is a trollism. The problem of troll's comments regulation becomes more and more important. One of possible solutions is a recognition of trolls by machine learning models. The work deals with the behavior of trolls on the Internet, the possibilities of the trollism detection and types of data, which can be used to it. The proposed approach is based on the use of Support Vectors Machine, Multinomial Naïve Bayes, and Logistic Regression. The best results were achieved by Multinomial Naïve Bayes model up to 0,92 of Recall.","PeriodicalId":402414,"journal":{"name":"2021 IEEE 19th World Symposium on Applied Machine Intelligence and Informatics (SAMI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129785489","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
Predictive Analytics for Default of Credit Card Clients 信用卡客户端违约预测分析
Pub Date : 2021-01-21 DOI: 10.1109/SAMI50585.2021.9378671
Alžbeta Bačová, F. Babič
Predictive analytics has a significant potential to support different decision processes. We aimed to compare various machine learning algorithms for the selected task, which predicts credit card clients' default based on the free available data. We chose Random Forest, AdaBoost, XGBoost, and Gradient Boosting algorithm and applied them to a prepared data sample. We experimentally evaluated the classification models within metrics like accuracy, precision, recall, ROC, and AUC. The results show a very similar performance of the selected algorithms on this dataset. The Gradient boosting (0.7828) achieved the best performance within AUC, but the best precision for target class 1 reached the Bagging algorithm (0.72). The simple data processing brought only minimal improvements in individual metrics. Our results are comparable to the mentioned studies instead of MCC metrics that resulted in better value (0.4111) achieved by the Gradient Boosting model.
预测分析具有支持不同决策过程的巨大潜力。我们的目标是比较所选任务的各种机器学习算法,该算法根据免费可用数据预测信用卡客户的违约情况。我们选择了Random Forest, AdaBoost, XGBoost和Gradient Boosting算法,并将它们应用于准备好的数据样本。我们通过实验评估了分类模型的准确性、精密度、召回率、ROC和AUC等指标。结果表明,所选算法在该数据集上的性能非常相似。梯度增强算法(0.7828)在AUC范围内获得了最好的性能,但对于目标类别1的精度达到了Bagging算法(0.72)。简单的数据处理只带来了个别指标的最小改进。我们的结果与上述研究相媲美,而不是通过梯度增强模型获得更好的值(0.4111)的MCC指标。
{"title":"Predictive Analytics for Default of Credit Card Clients","authors":"Alžbeta Bačová, F. Babič","doi":"10.1109/SAMI50585.2021.9378671","DOIUrl":"https://doi.org/10.1109/SAMI50585.2021.9378671","url":null,"abstract":"Predictive analytics has a significant potential to support different decision processes. We aimed to compare various machine learning algorithms for the selected task, which predicts credit card clients' default based on the free available data. We chose Random Forest, AdaBoost, XGBoost, and Gradient Boosting algorithm and applied them to a prepared data sample. We experimentally evaluated the classification models within metrics like accuracy, precision, recall, ROC, and AUC. The results show a very similar performance of the selected algorithms on this dataset. The Gradient boosting (0.7828) achieved the best performance within AUC, but the best precision for target class 1 reached the Bagging algorithm (0.72). The simple data processing brought only minimal improvements in individual metrics. Our results are comparable to the mentioned studies instead of MCC metrics that resulted in better value (0.4111) achieved by the Gradient Boosting model.","PeriodicalId":402414,"journal":{"name":"2021 IEEE 19th World Symposium on Applied Machine Intelligence and Informatics (SAMI)","volume":"82 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130753602","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: 2
The Impact of Braille Systems on Advanced Mathematical Geometry 盲文系统对高等数学几何的影响
Pub Date : 2021-01-21 DOI: 10.1109/SAMI50585.2021.9378682
Ogbolu Melvin Omone, Zsíros Tímca, M. Kozlovszky
The invention of certain systems/tools for text transcription for people who are visually impaired or blind stands as a surge in technology and helps the people become independent, learned, and skillful. In the past decades, several systems/tools have evolved. However, each one of these systems/tools has advantages and disadvantages, limitations and strengths, and functional analysis accuracy. In this paper, the Braille system, the types of Braille, and tools which are applicable and most suitable with the Braille system for teaching mathematical geometry are explored. Thus, the Nemeth Braille code which stands out for teaching mathematical geometry is explicitly explained in this paper. The Nemeth Braille code is an advanced mathematical application of the Braille code which is used for teaching primitive and advanced mathematical geometry. This paper includes a review of the existing Nemeth Braille code and other Braille system. It introduces a software development that can be used for accessing and transcribing text documents containing ordinary mathematical geometry (which include shapes, formulas, functions, and equations) into Nemeth Braille code readable formats.
为视障人士或盲人提供文本转录的某些系统/工具的发明代表了技术的激增,并帮助人们变得独立,学习和熟练。在过去的几十年里,一些系统/工具已经发展。然而,这些系统/工具中的每一个都有优点和缺点,局限性和优点,以及功能分析的准确性。本文探讨了盲文系统、盲文的类型以及盲文系统在数学几何教学中最适用和最适合的工具。因此,本文明确阐述了在数学几何教学中脱颖而出的内梅特盲文编码。Nemeth盲文代码是盲文代码的高级数学应用,用于教学原始和高级数学几何。本文包括对现有的Nemeth盲文码和其他盲文系统的回顾。它介绍了一种软件开发,可用于访问和转录包含普通数学几何(包括形状、公式、函数和方程)的文本文档,并将其转换为Nemeth Braille代码可读格式。
{"title":"The Impact of Braille Systems on Advanced Mathematical Geometry","authors":"Ogbolu Melvin Omone, Zsíros Tímca, M. Kozlovszky","doi":"10.1109/SAMI50585.2021.9378682","DOIUrl":"https://doi.org/10.1109/SAMI50585.2021.9378682","url":null,"abstract":"The invention of certain systems/tools for text transcription for people who are visually impaired or blind stands as a surge in technology and helps the people become independent, learned, and skillful. In the past decades, several systems/tools have evolved. However, each one of these systems/tools has advantages and disadvantages, limitations and strengths, and functional analysis accuracy. In this paper, the Braille system, the types of Braille, and tools which are applicable and most suitable with the Braille system for teaching mathematical geometry are explored. Thus, the Nemeth Braille code which stands out for teaching mathematical geometry is explicitly explained in this paper. The Nemeth Braille code is an advanced mathematical application of the Braille code which is used for teaching primitive and advanced mathematical geometry. This paper includes a review of the existing Nemeth Braille code and other Braille system. It introduces a software development that can be used for accessing and transcribing text documents containing ordinary mathematical geometry (which include shapes, formulas, functions, and equations) into Nemeth Braille code readable formats.","PeriodicalId":402414,"journal":{"name":"2021 IEEE 19th World Symposium on Applied Machine Intelligence and Informatics (SAMI)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131087115","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
Using Digital Technologies in the Measurement of Health Outcomes 使用数字技术衡量健康结果
Pub Date : 2021-01-21 DOI: 10.1109/sami50585.2021.9378629
Z. Zrubka, M. Péntek
Digital technologies have pervaded medicine and healthcare systems and brought innovations with unprecedented speed, benefiting all stakeholders from patients to healthcare professionals, researchers and administrators. Health outcomes are defined as the measurable change in health as a result of interventions. The ultimate goal of medicine and health systems is to improve patients' health outcomes. Digital technologies have brought a revolution in the measurement of health outcomes from sensors and digital biomarkers recording physiological and behavioural data to the more precise measurement of patient reported outcomes and experiences - how themselves feel about the effect of health interventions or the participation in healthcare. From the analysis of big data to simple web surveys, the new possibilities and innovative solutions bring new insights but new methodological challenges and ethical dilemmas as well. This presentation will summarise why health outcomes matter to health economists and what are the contributions and ongoing research projects of the HECON - Health Economics Research Center in the measurement of health outcomes via digital technologies.
数字技术已经渗透到医学和医疗保健系统中,并以前所未有的速度带来了创新,使从患者到医疗保健专业人员、研究人员和管理人员的所有利益相关者受益。健康结果被定义为干预措施导致的可衡量的健康变化。医学和卫生系统的最终目标是改善患者的健康结果。数字技术带来了一场健康结果测量方面的革命,从记录生理和行为数据的传感器和数字生物标志物,到更精确地测量患者报告的结果和经历——他们自己对健康干预措施的影响或参与医疗保健的感受。从大数据分析到简单的网络调查,新的可能性和创新的解决方案带来了新的见解,但也带来了新的方法论挑战和道德困境。本演讲将总结为什么健康结果对健康经济学家很重要,以及HECON -卫生经济学研究中心在通过数字技术衡量健康结果方面的贡献和正在进行的研究项目。
{"title":"Using Digital Technologies in the Measurement of Health Outcomes","authors":"Z. Zrubka, M. Péntek","doi":"10.1109/sami50585.2021.9378629","DOIUrl":"https://doi.org/10.1109/sami50585.2021.9378629","url":null,"abstract":"Digital technologies have pervaded medicine and healthcare systems and brought innovations with unprecedented speed, benefiting all stakeholders from patients to healthcare professionals, researchers and administrators. Health outcomes are defined as the measurable change in health as a result of interventions. The ultimate goal of medicine and health systems is to improve patients' health outcomes. Digital technologies have brought a revolution in the measurement of health outcomes from sensors and digital biomarkers recording physiological and behavioural data to the more precise measurement of patient reported outcomes and experiences - how themselves feel about the effect of health interventions or the participation in healthcare. From the analysis of big data to simple web surveys, the new possibilities and innovative solutions bring new insights but new methodological challenges and ethical dilemmas as well. This presentation will summarise why health outcomes matter to health economists and what are the contributions and ongoing research projects of the HECON - Health Economics Research Center in the measurement of health outcomes via digital technologies.","PeriodicalId":402414,"journal":{"name":"2021 IEEE 19th World Symposium on Applied Machine Intelligence and Informatics (SAMI)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133402602","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
期刊
2021 IEEE 19th World Symposium on Applied Machine Intelligence and Informatics (SAMI)
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