{"title":"Switching control of a rotary inverted pendulum","authors":"Boglárka Sütö, Z. Lendek","doi":"10.1109/ICSTCC55426.2022.9931817","DOIUrl":"https://doi.org/10.1109/ICSTCC55426.2022.9931817","url":null,"abstract":"In this paper we consider the problem of swinging-up and stabilization of a rotary inverted pendulum. We design switching controllers and analyse whether the performance can be improved using more controllers. We optimize both the control gains and the switching points. All the controllers are tested experimentally on a rotary inverted pendulum. Our results indicate that having a large number of switching controllers does not necessarily lead to a performance increase.","PeriodicalId":220845,"journal":{"name":"2022 26th International Conference on System Theory, Control and Computing (ICSTCC)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116150288","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}
Roxana-Maria Motorga, V. Muresan, M. Abrudean, H. Valean, I. Clitan, M. Ungureșan
{"title":"Adaptive control for the 13C isotope separation process","authors":"Roxana-Maria Motorga, V. Muresan, M. Abrudean, H. Valean, I. Clitan, M. Ungureșan","doi":"10.1109/ICSTCC55426.2022.9931901","DOIUrl":"https://doi.org/10.1109/ICSTCC55426.2022.9931901","url":null,"abstract":"In this paper a solution required in order to control the 13C isotope concentration inside and at the output of the separation column is presented. The classical control strategies, namely the PI and the PID controllers tunned using the Ziegler-Nichols method, were approached. The system performances were improved using an adaptive mechanism to compute their optimal parameters and a comparison between the results obtained between those methods is presented. The chemical exchange process between the carbamate and the carbon dioxide taking place, it results the enriched 13C isotope. This process is a distributed parameters one, depending on the time constant and on the position in the column's height, and it can be simulated after determining an analytical solution when the process is working in the transitory regime. The control strategies require the implementation of the process modelling – it is desired to reach the 13C isotope concentration by using an optimal amount of monoethanolamine solution, the input flow. The adaptive mechanism consists of a PI controller which determines the proper time constants of the two controllers so the control of the 13C isotope concentration is possible in any point of height in the separation column, improving the performances of the system by reducing the settling time – if the concentration suffers variations at certain moments of time, the adaptive mechanism is also capable of settling with the new requirements.","PeriodicalId":220845,"journal":{"name":"2022 26th International Conference on System Theory, Control and Computing (ICSTCC)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128023449","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":"Improving the Accuracy of Object Detection Models using Patch Splitting","authors":"A. Florea, C. Oara","doi":"10.1109/ICSTCC55426.2022.9931855","DOIUrl":"https://doi.org/10.1109/ICSTCC55426.2022.9931855","url":null,"abstract":"The classification and afterwards also the localization of objects in images were among the initial breakthroughs that stimulated research into artificial neural networks. Improving the detection accuracy along with other metrics has been a continuous research objective and analysis subject. One particular issue during the training of such models is the varying resolution of input images and it's effects on the training/detection results as most models accept arbitrary resolutions and resize them internally to a specific resolution. This article examines the benefits of automatically splitting images into patches before the detection stage and afterwards joining the patches along with the detection results into the original image. An accuracy test is conducted in a real environment.","PeriodicalId":220845,"journal":{"name":"2022 26th International Conference on System Theory, Control and Computing (ICSTCC)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126725549","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":"Social Medical Network","authors":"L. Stanescu, Raluca Stanescu","doi":"10.1109/ICSTCC55426.2022.9931896","DOIUrl":"https://doi.org/10.1109/ICSTCC55426.2022.9931896","url":null,"abstract":"The article presents a prototype social media network dedicated to the medical staff of Romania, from the architectural and functional points of view. The medical social media network is implemented as a web application for the time being, followed by the future implementation of a mobile application as well. This network allows for the medical staff in Romania to register, log in and virtually connect, with the purpose of sharing special medical cases or getting advised opinions for setting diagnostics. Any doctor in Romania will be able to create an account, add their information about their medical department/specialty in which they activate, their former studies, obtained diplomas/specializations, former or current occupied positions, resume etc. They will have the possibility to create posts, in the form of text, accompanied by medical images if needed. Oher users will be able to comment on the added posts. Each post or comment is considered a document, stored in the database. One of the most useful functionalities of the web application is the possibility of search - simple, based on the name of a doctor; or advanced - which implies searching in posts and comments using information retrieval algorithms. The web application is based on a MongoDB database, using MongoDB Atlas search, that is an embedded full-text search, build on Apache Lucene. The medical social media network is now in the testing phase, being utilized by a group of doctors from a private clinic in Romania. The feedback gathered from this usage is taken into consideration to improve and further develop the application.","PeriodicalId":220845,"journal":{"name":"2022 26th International Conference on System Theory, Control and Computing (ICSTCC)","volume":"145 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115406675","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}
Daniel Băncilă, D. Popescu, Ştefan Colbu, Adrien Megard, Matthieu Blanchard
{"title":"Optimal control for solar tracking systems","authors":"Daniel Băncilă, D. Popescu, Ştefan Colbu, Adrien Megard, Matthieu Blanchard","doi":"10.1109/ICSTCC55426.2022.9931807","DOIUrl":"https://doi.org/10.1109/ICSTCC55426.2022.9931807","url":null,"abstract":"The efficiency of a photovoltaic system can be measured throughout the possibility of delivering maximum power to the end customer. The main objective of the current research is to propose an optimal solar tracking control system used to attain and to maintain the maximum specified power. A mathematical model for a variable oriented photovoltaic panel will be determined. Further, the electrical model of a real photovoltaic panel will be introduced in order to compute the associated maximum power setpoint. Afterward, for the defined model an optimal controller will be designed, in order to attain and to maintain the setpoint for the solar tracking system. The proposed approach will be validated through simulation, in MATLAB/Simulink.","PeriodicalId":220845,"journal":{"name":"2022 26th International Conference on System Theory, Control and Computing (ICSTCC)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131890982","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":"Global Trajectory Tracking Control of a Four-Link Robot Manipulator without Velocity Measurements","authors":"J. Khusanov, Zilola Yusupova, O. Peregudova","doi":"10.1109/ICSTCC55426.2022.9931803","DOIUrl":"https://doi.org/10.1109/ICSTCC55426.2022.9931803","url":null,"abstract":"This paper deals with the trajectory tracking control problem of a serial four-link manipulator in order to design a controller which globally stabilizes the desired motion of the robot without velocity measurements. We use the dynamic model of the manipulator described by Euler-Lagrange equations. The output position dynamic feedback controller has been proposed on the base of Lyapunov functions method. We exploit the periodicity property of the manipulator dynamic equations with respect to the rotational angles of the robot links. More precisely, we obtain the solution to the global trajectory tracking control problem in a cylindrical phase space. Global attractivity and uniform asymptotic stability properties of the closed-loop system are achieved. Simulation results are provided to show the quality of the controller.","PeriodicalId":220845,"journal":{"name":"2022 26th International Conference on System Theory, Control and Computing (ICSTCC)","volume":"323 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133424968","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":"Using Knowledge Transfer for Neural Network Architecture Optimization with Improved Training Efficiency","authors":"M. Gavrilescu, Florin Leon","doi":"10.1109/ICSTCC55426.2022.9931898","DOIUrl":"https://doi.org/10.1109/ICSTCC55426.2022.9931898","url":null,"abstract":"Neural networks have demonstrated their potential for solving a wide range of real-world problems. While capable of learning correlations and relationships among complex datasets, neural network training and validation are often tedious and time-consuming, especially for large, high-dimensional datasets, given that sufficient models should be run through the validation pipeline so as to adequately cover the hyperparameter space. In order to address this problem, we propose a weight adjustment method for improving training times when searching for the optimal neural network architecture by incorporating a knowledge transfer step into the corresponding pipeline. This involves learning weight features from a trained model and using them to improve the training times of a subsequent one. Considering a sequence of candidate neural networks with different hyperparameter values, each model, once trained, serves as a source of knowledge for the next one, resulting in improved overall training times. We test our approach on dataset of various sizes, where we obtain reduced total training times, especially when small learning rates are used for finely-tuned convergence.","PeriodicalId":220845,"journal":{"name":"2022 26th International Conference on System Theory, Control and Computing (ICSTCC)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133744635","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":"Automatic Load Estimation Solution for Adaptive Bang-Bang Control","authors":"A. Berciu, E. Dulf, C. Festila","doi":"10.1109/ICSTCC55426.2022.9931773","DOIUrl":"https://doi.org/10.1109/ICSTCC55426.2022.9931773","url":null,"abstract":"The “bang-bang” control method and its improvements from an adaptive actuation perspective have long been used in various industries. However, in order to obtain optimal results, the methods developed suppose accurate knowledge of the mass of the bale to be transported, being all the more effective the more rigorously the mass value is determined. This paper proposes an innovative solution using the adaptive “bang-bang” control method for which no prior knowledge of the object mass is required. The effectiveness of the proposal is proved by simulation results.","PeriodicalId":220845,"journal":{"name":"2022 26th International Conference on System Theory, Control and Computing (ICSTCC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130877525","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}
Mariana Mulinari Pinheiro Machado, A. Voda, G. Besançon, G. Becq, O. David, P. Kahane
{"title":"System-Identification-Based Automatic Brain Tissue Classification for Stereoelectroencephalography","authors":"Mariana Mulinari Pinheiro Machado, A. Voda, G. Besançon, G. Becq, O. David, P. Kahane","doi":"10.1109/ICSTCC55426.2022.9931852","DOIUrl":"https://doi.org/10.1109/ICSTCC55426.2022.9931852","url":null,"abstract":"In the cases of drug-resistant epilepsy, patients might undergo resective surgery of the epileptic zone (EZ). The success of the surgery depends on the correct identification of the EZ and the eloquent cortex to be avoided. In both cases, the correct classification of the tissue where the measuring contacts are inserted is needed during the stereoelectroencephalography (SEEG). Most of the tissue classification procedures rely on imaging. In this paper a system identification based automatic classifier is proposed using previously proposed non-parametric and parametric methods for single contact tissue classification. By combining both identification methods, poorly classified contacts can be eliminated, and overall contact classification can be improved, especially for the parametric classifier. The proposed method can be either used in combination with imaging methods, or it could be used to help select contacts to be recorded during SEEG Investigation.","PeriodicalId":220845,"journal":{"name":"2022 26th International Conference on System Theory, Control and Computing (ICSTCC)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132714379","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":"2020 24th International Conference on System Theory, Control and Computing (ICSTCC)","authors":"Ieee Staff","doi":"10.1109/icstcc39008.2016","DOIUrl":"https://doi.org/10.1109/icstcc39008.2016","url":null,"abstract":"","PeriodicalId":220845,"journal":{"name":"2022 26th International Conference on System Theory, Control and Computing (ICSTCC)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133705315","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}