{"title":"Edge computing implementation of safety monitoring system in frame of IIoT","authors":"Martin Muzelak, T. Skovranek","doi":"10.1109/iccc54292.2022.9805918","DOIUrl":"https://doi.org/10.1109/iccc54292.2022.9805918","url":null,"abstract":"Intelligent automation of manufacturing processes is one of the topics of the fourth industrial revolution - Industry 4.0. Edge Computing, Cloud Computing and inference of machine learning algorithms on equipments in the frame of Industrial Internet of Things is therefore of high interest. In this paper the implementation of a machine learning algorithm in the form of neural network is used for detection of wearing protective equipment in production environment. Furthermore, the edge computing technology is used for deployment of the proposed application on the edge device using video data from the Closed-Circuit Television system. The Edge device is communicating with the Cloud, where streaming platforms are running, taking necessary safety precautions to prevent accidents at work and also record these situations for reporting purposes.","PeriodicalId":167963,"journal":{"name":"2022 23rd International Carpathian Control Conference (ICCC)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133157002","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":"DC Motor Control based on Integral Reinforcement Learning","authors":"Gheorghe Bujgoi, D. Sendrescu","doi":"10.1109/iccc54292.2022.9805935","DOIUrl":"https://doi.org/10.1109/iccc54292.2022.9805935","url":null,"abstract":"The paper presents the control of a DC motor using a machine learning technique known as integral reinforcement learning. The integral reinforcement learning control method belongs to the category of intelligent control systems. The main advantage of the integral reinforcement learning method is that it addresses continuous systems while most reinforcement learning methods are developed for discrete systems. The control system is based on a classic structure in reinforcement learning of critical – actor type. The critic is represented by a neural network that evaluates the efficiency of the actions generated by the actor (the correspondent of the controller in conventional control systems). Critic tuning (neural network training) is done online using the technique known as Temporal Difference Learning. The presented technique is tested and analysed both by simulation and implementation on an experimental platform.","PeriodicalId":167963,"journal":{"name":"2022 23rd International Carpathian Control Conference (ICCC)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131332941","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":"Robotic Plugging of CCS Type 2 Connector","authors":"J. Cernohorsky, Lukáš Krčmář, Pavel Jandura","doi":"10.1109/ICCC54292.2022.9805867","DOIUrl":"https://doi.org/10.1109/ICCC54292.2022.9805867","url":null,"abstract":"The fully autonomous vehicles have another advantage for their user, they can refuel/recharge itself. The high power charging system require a robust conductive connection between the charging station and vehicle. The high power charging CCS Type 2 cable assembly uses large cross-section conductors and a liquid cooling system which makes the manipulation less comfortable, particularly for disabled people. In this article, we present a method for connecting the CCS Type 2 plug to the inlet of a mobile platform using a 2D camera and the force torque sensor. Finally, alternative approach to this method is presented.","PeriodicalId":167963,"journal":{"name":"2022 23rd International Carpathian Control Conference (ICCC)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133850941","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":"Embedded Control System for an Aircraft High Bypass Turbofan with Coolant Injection into the Compressor","authors":"A. Tudosie","doi":"10.1109/ICCC54292.2022.9805913","DOIUrl":"https://doi.org/10.1109/ICCC54292.2022.9805913","url":null,"abstract":"The author has studied a control system for an aircraft high-bypass turbofan. Engine’s basic control systems (for the fuel flow rate and for the exhaust nozzle opening) are completed by the coolant injection flow rate controller. Most important turbofan’s performance is the total thrust, so as main outputs were considered engine’s spools’ rotational speeds (which are measurable parameters and are proportional to engine’s thrust), to describe the turbofan as controlled object; meanwhile, the combustor’s temperature, as secondary output was also considered. One has chosen the architectures of all involved controllers and has created a convenient embedded control architecture, given that the turbofan has a single input – its power lever position. Starting from controllers’ mathematical models, one has built the embedded control system block diagram with transfer functions; it was the base for the performed Simulink-Matlab simulations. Simulation conclusions about embedded system quality (the behavior of system’s main output parameters) are revealed, as well as some observation concerning engine’s optimal control architecture.","PeriodicalId":167963,"journal":{"name":"2022 23rd International Carpathian Control Conference (ICCC)","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114371527","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":"Adapted Path-relinking Based Search for Non-dominated Set of Emergency Medical System Designs","authors":"Marek Kvet, J. Janáček","doi":"10.1109/ICCC54292.2022.9805968","DOIUrl":"https://doi.org/10.1109/ICCC54292.2022.9805968","url":null,"abstract":"The path-relinking method has proved to be a very powerful tool, when searching for a good solution in the set of feasible solutions of a zero-one programming problem with one min-sum objective function. Nevertheless, designing of an emergency medical system includes making decisions on a balance between conflicting criteria, which reflect requirements of efficiency on one hand and requirements of fair access to minorities on the other hand. This decision-making process needs a series of non-dominated solutions, which enables to reduce the range of solutions for final implementation. This paper is focused on the path-relinking method exploitation to find a good approximation of the Pareto front of the emergency medical system designs. As the path-relinking method itself is able to inspect only one short path in the surface of a unit hypercube, the method must be embedded into a more sophisticated searching process. We present here a learning algorithm, which adaptively choices pair of input solutions for a single path-relinking method run. The learning algorithm also sets weights of the conflicting criteria to define composed objective function used in the control process of the path-relinking method. The complete searching process was tested on several real-sized benchmarks and the resulting sets of non-dominated solutions are compared to the exact Pareto fronts. The obtained results are reported in details in a computational study at the end of the paper.","PeriodicalId":167963,"journal":{"name":"2022 23rd International Carpathian Control Conference (ICCC)","volume":"154 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115756429","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}
Mihajasoa Léa Fanomezana, Andrianjaka Miary Rapatsalahy, N. Razafindrakoto, C. Bǎdicǎ
{"title":"Proposed Methodology for Designing a Microservice Architecture","authors":"Mihajasoa Léa Fanomezana, Andrianjaka Miary Rapatsalahy, N. Razafindrakoto, C. Bǎdicǎ","doi":"10.1109/iccc54292.2022.9805930","DOIUrl":"https://doi.org/10.1109/iccc54292.2022.9805930","url":null,"abstract":"The changing needs of the enterprise require the manageability of its information system. Therefore, it is crucial to absorb these changes by orienting the design of the information system towards a modern architecture that decomposes the monolithic application into autonomous services. This paper proposes an enterprise architecture methodological framework to design the so-called microservice architecture known as MSA. Our approach is to describe the similarities between the MSA style of architecture and the service-oriented architecture known as SOA, the latter having a rich research literature focused on exploiting the methodology for designing services in a service architecture. The result of the comparative study indicates that the ideology for designing a SOA is identical as MSA which ultimately relies on decomposing applications into smaller components with a smaller and more manageable footprint. Thus, we conclude that it is preferable to use the adapted enterprise architecture methodology for SOA to design MSA.","PeriodicalId":167963,"journal":{"name":"2022 23rd International Carpathian Control Conference (ICCC)","volume":"242 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121292287","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}
Bogdan Popa, C. Ionete, A. Lorincz, Laviniu Aurelian Badulescu
{"title":"Possibilities for fast Generation of Fractal Images and Various Fields of Applicability","authors":"Bogdan Popa, C. Ionete, A. Lorincz, Laviniu Aurelian Badulescu","doi":"10.1109/iccc54292.2022.9805946","DOIUrl":"https://doi.org/10.1109/iccc54292.2022.9805946","url":null,"abstract":"The results of this paper consist of testing and performing comparisons for some fractals set generation applications, such as Mandelbrot sets. The fractal generation part represents an area of analysis and illustration of the modalities of parallel calculation. This method implies a very high degree of accuracy, respecting the selected fractal generation mathematical model, and does not represent a specialized method for a certain type of image. This fractal study is exemplified by the Mandelbrot set because it represents a method that reveals its usefulness in various applications in different fields. During the study, was discovered different types of images that can hardly be obtained by other methods and can be compared, in terms of complexity, only with some natural ones, extremely beautiful. The complexity and infinity of these images create a new field of research for the future.This paper aims to present an interesting way to design sets of fractals, considering different methods, starting from the contribution of parallel programming in contrast to sequential programming, to highlight the modern methods of accelerating the computation time. Starting from the generation of fractal images, they are used in several other image compression applications, to analyze the results of some natural resources with examples in the paper.","PeriodicalId":167963,"journal":{"name":"2022 23rd International Carpathian Control Conference (ICCC)","volume":"108 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116004481","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}
M. Laciak, J. Kačur, P. Flegner, M. Durdán, Marcela Pavlíčková, J. Terpák
{"title":"The Analysis of the Influence of Input Parameters on the Accuracy of Temperature Model in the Steelmaking Process","authors":"M. Laciak, J. Kačur, P. Flegner, M. Durdán, Marcela Pavlíčková, J. Terpák","doi":"10.1109/ICCC54292.2022.9805906","DOIUrl":"https://doi.org/10.1109/ICCC54292.2022.9805906","url":null,"abstract":"The steel production process in the converter is one of the important processes within the metallurgical technological chain. The most important quality parameters of this process are the chemical composition of the steel and the temperature of the steel, which is important in terms of further processing of the steel. In addition to the steelmaking process itself, the steel temperature is also affected by input parameters such as, e.g., temperature, weight, and the composition of pig iron, weight, the composition of steel scrap, amount of blown oxygen, etc. This paper analyses the effect of these parameters on steel temperature using a simulation model. The simulation model calculates the temperature of the melt during the steelmaking process, which increases through the heat released from the exothermic reactions of blown oxygen with metal impurities. This model was created by a deterministic approach and also includes the so-called heat losses, defined as other heat losses that cannot be unambiguously determined. The aim of the research was to increase the accuracy of the model by determining these heat losses.","PeriodicalId":167963,"journal":{"name":"2022 23rd International Carpathian Control Conference (ICCC)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131707455","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}
Mădălin Mămuleanu, C. Ionete, Anca Albița, D. Selișteanu
{"title":"Distributed Deep Learning Model for Predicting the Risk of Diabetes, Trained on Imbalanced Dataset","authors":"Mădălin Mămuleanu, C. Ionete, Anca Albița, D. Selișteanu","doi":"10.1109/ICCC54292.2022.9805989","DOIUrl":"https://doi.org/10.1109/ICCC54292.2022.9805989","url":null,"abstract":"When developing and training a deep learning model, usually the dataset is balanced and contains approximately the same number of samples for each class. However, in some fields, this is not always the case. In healthcare, a dataset can have imbalanced classes due to few investigations for a specific lesion, rare diseases or because the institution did not have enough patients in the study. Besides that, these datasets are usually distributed across many institutions (hospitals, healthcare centers) and trying to obtain a complete dataset is almost impossible, especially due to legal concerns. This paper proposes to train a deep learning model for predicting the risk of diabetes in a distributed way, called federated learning. Our assumptions are that the data is distributed across many entities and merging it is not possible. In federated learning, the deep learning model is trained across multiple entities. The training is coordinated by a server which, at the end of the training session, compiles a new model based on the results obtained by each entity. The dataset used in our paper is imbalanced, having only 268 positive cases from a total of 768 cases. Training a deep learning model on the dataset as it is can lead to a biased model. Hence, for solving this problem, oversampling techniques for balancing the dataset are applied.","PeriodicalId":167963,"journal":{"name":"2022 23rd International Carpathian Control Conference (ICCC)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127717435","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":"Adaptive Swap Algorithm for Pareto Front Approximation","authors":"J. Janáček, Marek Kvet","doi":"10.1109/iccc54292.2022.9805934","DOIUrl":"https://doi.org/10.1109/iccc54292.2022.9805934","url":null,"abstract":"Implementation of any public service system is matter of negotiation of the system founder and public representatives, who try to apply conflicting criteria to the final system design. Pareto front or its approximation can be a very useful tool for the negotiation, as the set of solutions represents the set of such designs, which cannot be improved in one of the criteria unless some of the others get worsened. Nevertheless, constitution of the exact Pareto front represents serious computational problem, with big expected consumption of computational time. This drawback evoked the idea to use a heuristic for constituting a good approximation of the Pareto front of the public service system designs. In this paper, a swap algorithm is used as the base searching method due to its excellent efficiency, when applied to p-location problems with one objective function. The algorithm was adjusted for bi-criteria p-location problems so that its local objective function was formulated as a convex combination of the conflicting criteria and, furthermore, a run of the algorithm was limited by a maximal permitted computational time. This parameterized algorithm was embedded into an adaptive process, which randomly sets the parameters and a starting solution to active values based on results of previous algorithm runs. The adaptive algorithm was tested on real-sized benchmarks derived from existing emergency medical systems and the obtained results were compared to the exact Pareto fronts.","PeriodicalId":167963,"journal":{"name":"2022 23rd International Carpathian Control Conference (ICCC)","volume":"2017 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130439165","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}