{"title":"Spark-Based Digital Factory Design","authors":"István Pölöskei","doi":"10.2478/aei-2022-0008","DOIUrl":"https://doi.org/10.2478/aei-2022-0008","url":null,"abstract":"Abstract Big data processing often uses the paradigm of parallelism by computing directly on top of the distributed data storage. The existing big data workflows unify the data processing practices to utilize the cloud’s native computational potentials to offer advanced machine learning and BI capabilities. Spark is an open-source massively parallel in-memory data processing framework, the current state-of-the-art. The primary approach is to break down the job into granular-level executed tasks, enabling parallelization. In the discussed case study, through IoT – cloud solutions, the plant data can be converted into an analyzable form to let the farther machine learning modules produce added value. To maximize the efficiency of the processing and accumulation, cloud-based components are introduced. Based on the data insights, the appropriate operative actions can be taken. The cost and performance optimization methods were also discussed in the study. Through achieving higher degree of digitalization, the control over the production increased.","PeriodicalId":31657,"journal":{"name":"Acta Electrotechnica et Informatica","volume":"22 1","pages":"19 - 26"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42854433","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}
P. Šatala, Juliana Ivančáková, David Trella, P. Butka, F. Babič
{"title":"Analysis of Reactions of Mobile Phone Users","authors":"P. Šatala, Juliana Ivančáková, David Trella, P. Butka, F. Babič","doi":"10.2478/aei-2022-0006","DOIUrl":"https://doi.org/10.2478/aei-2022-0006","url":null,"abstract":"Abstract In this work, we analyze the aspects of user reactions during their work with a mobile phone. We tried to find the most crucial positions within the mobile screen, which provide essential information and stimulus. One of the main factors is to know which part of the screen is the first interest of the user and which part the user reacts to the fastest. Sixty-four persons participated in an experiment. We used the gamification approach to motivate users for the best results and created a game. Users competed with each other during the game, and they tried to react to the new point of the screen as soon as possible. The experiment showed that about a quarter of the screen below the centre was an area where users react the fastest. There were interesting differences between men and women and signs of background impact.","PeriodicalId":31657,"journal":{"name":"Acta Electrotechnica et Informatica","volume":"22 1","pages":"3 - 7"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45954621","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}
Diana Klimonová, Viera Anderková, F. Babič, L. Majnarić
{"title":"Decision Support System Improving the Interpretability of Generated Tree-Based Models","authors":"Diana Klimonová, Viera Anderková, F. Babič, L. Majnarić","doi":"10.2478/aei-2022-0009","DOIUrl":"https://doi.org/10.2478/aei-2022-0009","url":null,"abstract":"Abstract A decision tree represents one of the most used data analysis methods for classification tasks. The generated decision models can be visualized as a graph, but this visualization is quite complicated for a domain expert to understand in large or heterogeneous data. Our previous experience with medical data analytics related to the classification of patients with Metabolic Syndrome, Mild Cognitive Impairment, heart disease, or Frailty motivated us to evaluate the potential of new visualizations for this decision model in the medical domain. We managed a user study to design and implement a decision support system containing selected methods to improve the interpretability of the generated tree-based decision model. We hypothesized that this approach would result in more effective communication between data analysts and medical experts, reduce necessary time and energy and bring more comprehensive results. For this purpose, we selected two model-agnostic methods, LIME and SHAP, and one new interactive visualization called Sunburst. We used two data samples for design and evaluation: the publicly available heart disease dataset and the Metabolic Syndrome dataset the participating medical expert provided. We will use the collected feedback and experience for further improvements, like more evaluation metrics related to the usability of the decision models.","PeriodicalId":31657,"journal":{"name":"Acta Electrotechnica et Informatica","volume":"22 1","pages":"27 - 33"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46969707","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}
{"title":"Measurement of Particulate Matter: Principles and Options of Measurement at Present","authors":"S. Kirešová, M. Guzan","doi":"10.2478/aei-2022-0007","DOIUrl":"https://doi.org/10.2478/aei-2022-0007","url":null,"abstract":"Abstract This paper serves as an overview of the research on particulate matter. This includes the sources of particulate matter, the composition of particles and, most importantly, negative impact on human health. The paper also deals with the methods, and instruments of measurement of particulate matter. Future development of measuring particulate matter is proposed, such as implementing Internet of Things and wireless sensor network technologies as well as performing the analysis of the measured data to find how other measured quantities affect the concentration of particulate matter.","PeriodicalId":31657,"journal":{"name":"Acta Electrotechnica et Informatica","volume":"22 1","pages":"8 - 18"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44721258","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}
Matej Hires, P. Bugata, Matej Gazda, D. Hresko, R. Kanász, L. Vavrek, P. Drotár
{"title":"Brief Overview of Neural Networks for Medical Applications","authors":"Matej Hires, P. Bugata, Matej Gazda, D. Hresko, R. Kanász, L. Vavrek, P. Drotár","doi":"10.2478/aei-2022-0010","DOIUrl":"https://doi.org/10.2478/aei-2022-0010","url":null,"abstract":"Abstract Neural networks experienced great deal of success in many domains of machine intelligence. In tasks such as object detection, speech recognition or natural language processing is performance of neural networks close to that of human. This allows penetration of neural networks in many domains. The medicine is one of the domains that can successfully harvest methodological advances in neural networks. Medical personnel has to deal with huge amount of data that are used for patients’ diagnosis, monitoring and treatment. Application of neural networks in diagnosis and decision support systems have proven to add more objectivity to diagnosis, allow for quicker and more accurate decision and provide more personalized treatment. In this brief review we describe several main architectures of neural networks together with their applications. We provide description of convolutional neural networks, auto-encoders and recurrent neural networks together with their applications such as medical image segmentation, processing of electrocardiogram for arrhythmia detection and many others.","PeriodicalId":31657,"journal":{"name":"Acta Electrotechnica et Informatica","volume":"22 1","pages":"34 - 44"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45312103","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}
{"title":"Impact of Virtual Assistant on Programming Novices’ Performance, Behavior and Motivation","authors":"M. Binas, E. Pietriková","doi":"10.2478/aei-2022-0005","DOIUrl":"https://doi.org/10.2478/aei-2022-0005","url":null,"abstract":"Abstract In the following study, we deal with data-driven support for novice programmers – students, working in large groups. We introduce a virtual assistant, which aims to simplify communication and feedback, sending reports and advice during the programming course. We experiment with 134 students during one semester period, and we try to understand how the virtual assistant affects novices – students. In the introduction, we state 3 hypotheses, focusing on performance, behavior, and motivation. The experiment evaluation relies on data collected throughout the semester. The results reveal the impact of the virtual assistant on novice programmers in 2 of the studied aspects – performance and motivation. This can be perceived as potential towards efficient support in programming education, especially in large groups. We also believe the study is contributional to the areas of learning analytics and program comprehension.","PeriodicalId":31657,"journal":{"name":"Acta Electrotechnica et Informatica","volume":"22 1","pages":"30 - 36"},"PeriodicalIF":0.0,"publicationDate":"2022-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48094822","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}
{"title":"Hints on the Multicore CPU Design for Personal Computers","authors":"Ecem Iren, Halil Can Akince, A. Kantarci","doi":"10.2478/aei-2022-0002","DOIUrl":"https://doi.org/10.2478/aei-2022-0002","url":null,"abstract":"Abstract Abstract - Multi-core processors are created by combining multiple units, each called the core, containing the processing unit, registers and a cache. This study provides a detailed analysis on the performances of multicore CPUs for personal computers. We parallelized some cryptographic algorithms with OpenMP tool and tested one 2-core and one 4-core CPU with two cryptographic software one of which imposes high data load and the other one high work load. In the light of the experiments that stress the CPUs from these two different aspects, we present our hints and suggestions for designing multicore chips for the usage in personal computers.","PeriodicalId":31657,"journal":{"name":"Acta Electrotechnica et Informatica","volume":"22 1","pages":"8 - 17"},"PeriodicalIF":0.0,"publicationDate":"2022-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48048535","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}
Sathasivam Purushothamans, Gunasekaran Mohanavel, K. Kalaichelvi
{"title":"An Enhanced Accident Detection and Recovery System Using MEMS Technology","authors":"Sathasivam Purushothamans, Gunasekaran Mohanavel, K. Kalaichelvi","doi":"10.2478/aei-2022-0001","DOIUrl":"https://doi.org/10.2478/aei-2022-0001","url":null,"abstract":"Abstract This is an intention to implement an innovative solution for this problem by developing an automatic accident detection system and recovery analysis play an important role. By using this mobile (SMS) and also with the help of embedded technology we can solve this problem. An accelerometer can be used in a car alarm application; Dangerous driving can be detected with an accelerometer. The vibration sensor detects the accident. The MEMS sensor detects a rollover and alerts the driver. A major accident can be detected using accelerometer readings. According to this idea, when a car is involved in an accident, the vehicle number and contact information for the people involved are promptly recorded and will be transferred to police control room or a rescue team by using GSM MODEM. As a result, using GPS, the cops can quickly determine where the communication originated. One more advances of this modern technology were for an uncertain situation many of vehicles that have center locking system, Due this technology people faces many problem due to automatic locking system. There is no option to open the lock in the case; our work will provide a suitable solution for this so it is useful for implementing this project in useful way to reduce the human death ratio by accidents.","PeriodicalId":31657,"journal":{"name":"Acta Electrotechnica et Informatica","volume":" ","pages":"3 - 7"},"PeriodicalIF":0.0,"publicationDate":"2022-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46834862","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}
{"title":"Sensorless Control of PMSM in Low Speed Region Using HF Pulse Signal Injection Method","authors":"Viktor Petro, Karol Kyslan","doi":"10.2478/aei-2022-0003","DOIUrl":"https://doi.org/10.2478/aei-2022-0003","url":null,"abstract":"Abstract The sensorless control of the permanent magnet synchronous motor (PMSM) has attracted wide attention due to its economic and safety benefits. A fast and high-precision rotor-position estimation is necessary for the implementation of sensorless control. In low-speed region, high frequency (HF) signal injection methods are mostly adopted. They suffer to bandwidth deterioration as some digital filters must be included in the current feedback loop or the speed observation signal processing. The HF signal injection method based on the injection of voltage pulses is presented in this paper together with its implementation in MATLAB/Simulink. The method is based on the injection of voltage pulses where injection itself is separated from the motor control algorithm. The simulation results show that the proposed method has good dynamic performance for the sensorless control of PMSM.","PeriodicalId":31657,"journal":{"name":"Acta Electrotechnica et Informatica","volume":" ","pages":"18 - 23"},"PeriodicalIF":0.0,"publicationDate":"2022-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45123934","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}
{"title":"Measurement of Leakage Current in Wet and Polluted Conditions Using Different Sensing Electrodes","authors":"Ľuboš Šárpataky, B. Dolník","doi":"10.2478/aei-2022-0004","DOIUrl":"https://doi.org/10.2478/aei-2022-0004","url":null,"abstract":"Abstract Insulators, as the main insulating element of transmission lines, are exposed to various stresses, which affect the operation and thus the reliability of electricity supply. To improve the reliability of insulators, it is necessary to monitor their condition. Thanks to the development of computer technology, it is possible to process a large amount of data, which popularizes the possibility of diagnostics online. Factors that affect reliability, failure rate, and losses the most, are pollution and humidity. Our research is focused on monitoring and evaluating the applicability of various sensing electrodes for measuring leakage current on glass insulators. Relative humidity and pollution levels changes can give us a clear view of the used measuring method and how different sensing electrodes can affect the value of leakage current.","PeriodicalId":31657,"journal":{"name":"Acta Electrotechnica et Informatica","volume":"22 1","pages":"24 - 29"},"PeriodicalIF":0.0,"publicationDate":"2022-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46746707","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}