Pub Date : 2018-10-01DOI: 10.1109/ICA-ACCA.2018.8609757
D. Aldana, Yamisleydi Salgueiro, C. Bellinger, M. Rivera, C. Astudillo
The non-intrusive monitoring of electrical systems has gained relevance, during the last years, due to its lower costs and space requirements. Machine learning techniques have proved their ability to predict the parameters under monitoring and consequently improve the performance of power electronics systems. The present work seeks to determine the combination of machine learning techniques and dimensionality reduction that efficiently predicts the inductance value for a Voltage Source Inverter’s Modulate Model Predictive Control (VSI_M2PC). The problem, modeled as a classification one with three classes, has a high dimensionality 5000 attributes. Consequently, its reduction is needed to make it tractable at the cost of slightly sacrificing the accuracy of the model. Seven machine learning methods Support Vector Machine, K-Nearest Neighbours, Naïve Bayes, Linear Discriminant Analysis, Classification and Regression Trees, C4.5 and Random Fores. Additionally, the strategies for dimensions reduction Correlation Elimination, Principal Component Analysis, and Boruta were experimentally studied on VSI_M2PC Matlab simulations. It was found that Random Forest combined with the Boruta provided the best results regarding classification efficiency.
{"title":"Performance Assessment of Classification Methods for the Inductance within a VSI","authors":"D. Aldana, Yamisleydi Salgueiro, C. Bellinger, M. Rivera, C. Astudillo","doi":"10.1109/ICA-ACCA.2018.8609757","DOIUrl":"https://doi.org/10.1109/ICA-ACCA.2018.8609757","url":null,"abstract":"The non-intrusive monitoring of electrical systems has gained relevance, during the last years, due to its lower costs and space requirements. Machine learning techniques have proved their ability to predict the parameters under monitoring and consequently improve the performance of power electronics systems. The present work seeks to determine the combination of machine learning techniques and dimensionality reduction that efficiently predicts the inductance value for a Voltage Source Inverter’s Modulate Model Predictive Control (VSI_M2PC). The problem, modeled as a classification one with three classes, has a high dimensionality 5000 attributes. Consequently, its reduction is needed to make it tractable at the cost of slightly sacrificing the accuracy of the model. Seven machine learning methods Support Vector Machine, K-Nearest Neighbours, Naïve Bayes, Linear Discriminant Analysis, Classification and Regression Trees, C4.5 and Random Fores. Additionally, the strategies for dimensions reduction Correlation Elimination, Principal Component Analysis, and Boruta were experimentally studied on VSI_M2PC Matlab simulations. It was found that Random Forest combined with the Boruta provided the best results regarding classification efficiency.","PeriodicalId":176587,"journal":{"name":"2018 IEEE International Conference on Automation/XXIII Congress of the Chilean Association of Automatic Control (ICA-ACCA)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133280998","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}
Pub Date : 2018-10-01DOI: 10.1109/ICA-ACCA.2018.8609794
M. Sarbanzadeh, M. Hosseinzadeh, E. Sarebanzadeh, Marco Rivera
Predictive control is a new control strategy that has been applied to control power electronics applications, in the last decades. Many researches are working on the improvement of this control method such as reduction of computations cost, increasing accuracy, etc. This paper introduces some of the most challenges and trends through an overview on papers that were published recently.
{"title":"Recent Predictive Control Strategies Applied to Flying Capacitor Multilevel Inverters","authors":"M. Sarbanzadeh, M. Hosseinzadeh, E. Sarebanzadeh, Marco Rivera","doi":"10.1109/ICA-ACCA.2018.8609794","DOIUrl":"https://doi.org/10.1109/ICA-ACCA.2018.8609794","url":null,"abstract":"Predictive control is a new control strategy that has been applied to control power electronics applications, in the last decades. Many researches are working on the improvement of this control method such as reduction of computations cost, increasing accuracy, etc. This paper introduces some of the most challenges and trends through an overview on papers that were published recently.","PeriodicalId":176587,"journal":{"name":"2018 IEEE International Conference on Automation/XXIII Congress of the Chilean Association of Automatic Control (ICA-ACCA)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133107713","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}
Pub Date : 2018-10-01DOI: 10.1109/ICA-ACCA.2018.8609730
K. Gularte, Leonardo N. C. Rêgo, J. Vargas
This paper proposes a scheme for secure telecommunication based on the synchronization of an under-actuated chaotic Lorenz system, Lyapunov analysis and analog electronics. Unlike most of the schemes usually found in the literature, the proposed scheme only requires that the control signal act in one of the state equations of the slave system. The proposed scheme has the advantages of being robust against disturbances (internal and external) and simple, which is important, since it leads to important cost reductions when implemented using analog electronics. To validate the robustness and simplicity of the proposed scheme, computational simulations using MATLAB / SIMULINK and Multisim were performed.
{"title":"Scheme for Chaos-based Encryption and Lyapunov Analysis","authors":"K. Gularte, Leonardo N. C. Rêgo, J. Vargas","doi":"10.1109/ICA-ACCA.2018.8609730","DOIUrl":"https://doi.org/10.1109/ICA-ACCA.2018.8609730","url":null,"abstract":"This paper proposes a scheme for secure telecommunication based on the synchronization of an under-actuated chaotic Lorenz system, Lyapunov analysis and analog electronics. Unlike most of the schemes usually found in the literature, the proposed scheme only requires that the control signal act in one of the state equations of the slave system. The proposed scheme has the advantages of being robust against disturbances (internal and external) and simple, which is important, since it leads to important cost reductions when implemented using analog electronics. To validate the robustness and simplicity of the proposed scheme, computational simulations using MATLAB / SIMULINK and Multisim were performed.","PeriodicalId":176587,"journal":{"name":"2018 IEEE International Conference on Automation/XXIII Congress of the Chilean Association of Automatic Control (ICA-ACCA)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116942047","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}
Pub Date : 2018-10-01DOI: 10.1109/ICA-ACCA.2018.8609826
José A. Guzmán, Felipe Núñez
During the last decade, plenty of devices labeled as “smart” have appeared in the market with the promise of taking the relationship home-user to a new level. Unfortunately, most of these devices are not able to interact with one another and the “smart” solution reduces to the use of a phone app to control a particular device or process. Lately, new devices known as smart hubs have arisen as smart home enablers based on their ability to talk several communication protocols and incorporate devices from different vendors. However, hub-based solutions suffer from various drawbacks, notably the lack of scalability and the presence of a single point of failure. In this work, a multi agent approach is proposed to generate and operate home automation systems. The proposed approach distributes the intelligence among agents, which behave as finite state machines, achieving a scalable and robust architecture. A pilot implementation is presented as proof of concept.
{"title":"A Multi Interface Home Automation System with Distributed Intelligence","authors":"José A. Guzmán, Felipe Núñez","doi":"10.1109/ICA-ACCA.2018.8609826","DOIUrl":"https://doi.org/10.1109/ICA-ACCA.2018.8609826","url":null,"abstract":"During the last decade, plenty of devices labeled as “smart” have appeared in the market with the promise of taking the relationship home-user to a new level. Unfortunately, most of these devices are not able to interact with one another and the “smart” solution reduces to the use of a phone app to control a particular device or process. Lately, new devices known as smart hubs have arisen as smart home enablers based on their ability to talk several communication protocols and incorporate devices from different vendors. However, hub-based solutions suffer from various drawbacks, notably the lack of scalability and the presence of a single point of failure. In this work, a multi agent approach is proposed to generate and operate home automation systems. The proposed approach distributes the intelligence among agents, which behave as finite state machines, achieving a scalable and robust architecture. A pilot implementation is presented as proof of concept.","PeriodicalId":176587,"journal":{"name":"2018 IEEE International Conference on Automation/XXIII Congress of the Chilean Association of Automatic Control (ICA-ACCA)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123992641","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}
Pub Date : 2018-10-01DOI: 10.1109/ICA-ACCA.2018.8609731
Vanessa Lara, Héctor Vargas, Cristian Castro, J. Chacón, L. D. L. Torre
Theory and practice in control education come together into hands-on laboratories. Control laboratories are commonly composed by a set of didactical plants (typically plants of liquid level control in tanks, temperature control, speed and position control in motors, among others) on which students perform the practical experiences required by the teaching staff. However, given that these plants usually have a fixed structure (normally first or second order models), the creation of control learning activities for different type and order plants are not possible. In this context, this paper presents a flexible educational plant which has been designed as a set of electronic modules based on operational amplifiers which can be combined to create different transfer functions (or plants) and perform PID control on it. This plant is accompanied by a data acquisition system that allows sending and receiving signals to and from the modules and visualizing the results through a graphical user interface developed in LabVIEW. The application also includes an additional tool to compare simulated and real responses for analysis and validation purposes of the designed controllers.
{"title":"Design and development of a flexible control laboratory plant for educational purposes","authors":"Vanessa Lara, Héctor Vargas, Cristian Castro, J. Chacón, L. D. L. Torre","doi":"10.1109/ICA-ACCA.2018.8609731","DOIUrl":"https://doi.org/10.1109/ICA-ACCA.2018.8609731","url":null,"abstract":"Theory and practice in control education come together into hands-on laboratories. Control laboratories are commonly composed by a set of didactical plants (typically plants of liquid level control in tanks, temperature control, speed and position control in motors, among others) on which students perform the practical experiences required by the teaching staff. However, given that these plants usually have a fixed structure (normally first or second order models), the creation of control learning activities for different type and order plants are not possible. In this context, this paper presents a flexible educational plant which has been designed as a set of electronic modules based on operational amplifiers which can be combined to create different transfer functions (or plants) and perform PID control on it. This plant is accompanied by a data acquisition system that allows sending and receiving signals to and from the modules and visualizing the results through a graphical user interface developed in LabVIEW. The application also includes an additional tool to compare simulated and real responses for analysis and validation purposes of the designed controllers.","PeriodicalId":176587,"journal":{"name":"2018 IEEE International Conference on Automation/XXIII Congress of the Chilean Association of Automatic Control (ICA-ACCA)","volume":"96 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130519528","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}
Pub Date : 2018-10-01DOI: 10.1109/ICA-ACCA.2018.8609773
Gilberto de Melo, Sílvio L. Vieira, W. Calixto
This paper presents audio signal encoding and decoding using the theory of Conformal Mapping technique. This is used in majority with images, but in this study will be applied in audio signal. The propose methodology was develop four case study to demonstrate that Conformal Mapping is applicable in audio signals and evaluate this method with two metrics, shuffling and deviation. The experimental results demonstrate a efficient encoding using Conformal Mapping, with a big shuffling and low deviation.
{"title":"Conformal Mapping applied in coding and decoding of audio signal","authors":"Gilberto de Melo, Sílvio L. Vieira, W. Calixto","doi":"10.1109/ICA-ACCA.2018.8609773","DOIUrl":"https://doi.org/10.1109/ICA-ACCA.2018.8609773","url":null,"abstract":"This paper presents audio signal encoding and decoding using the theory of Conformal Mapping technique. This is used in majority with images, but in this study will be applied in audio signal. The propose methodology was develop four case study to demonstrate that Conformal Mapping is applicable in audio signals and evaluate this method with two metrics, shuffling and deviation. The experimental results demonstrate a efficient encoding using Conformal Mapping, with a big shuffling and low deviation.","PeriodicalId":176587,"journal":{"name":"2018 IEEE International Conference on Automation/XXIII Congress of the Chilean Association of Automatic Control (ICA-ACCA)","volume":"236 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123340992","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}
Pub Date : 2018-10-01DOI: 10.1109/ICA-ACCA.2018.8609848
J. P. Vásconez, Jaime Salvo, F. Auat
To date, human action recognition is still a challenging topic and has been addressed from many perspectives. Detection of human actions can be useful to obtain relevant information to improve complex processes, which is the case of agricultural applications. In this work, the detection of objects that can provide information for human action recognition based on semantic representations is studied. For this purpose, a convolutional neuronal network based on Single Shot MultiBox Detector meta-architecture and MobileNet feature extractor was implemented, which has been trained to detect nine classes of objects during the process of collecting avocados in a Chilean farm. We have found that such detected objects are related to seven possible actions that can be detected during avocado harvesting process. Such information could allow to directly detect certain actions in still images, or improve conventional action detection methods during the harvesting process. The results show that is possible to detect human actions during the process, obtaining action recognition performances from 41% to 80% depending on the task. This approach can help to obtain information about how to improve harvesting process and reduce human workload in near future, which may be an important contribution for the search of sustainable agricultural practices.
{"title":"Toward Semantic Action Recognition for Avocado Harvesting Process based on Single Shot MultiBox Detector","authors":"J. P. Vásconez, Jaime Salvo, F. Auat","doi":"10.1109/ICA-ACCA.2018.8609848","DOIUrl":"https://doi.org/10.1109/ICA-ACCA.2018.8609848","url":null,"abstract":"To date, human action recognition is still a challenging topic and has been addressed from many perspectives. Detection of human actions can be useful to obtain relevant information to improve complex processes, which is the case of agricultural applications. In this work, the detection of objects that can provide information for human action recognition based on semantic representations is studied. For this purpose, a convolutional neuronal network based on Single Shot MultiBox Detector meta-architecture and MobileNet feature extractor was implemented, which has been trained to detect nine classes of objects during the process of collecting avocados in a Chilean farm. We have found that such detected objects are related to seven possible actions that can be detected during avocado harvesting process. Such information could allow to directly detect certain actions in still images, or improve conventional action detection methods during the harvesting process. The results show that is possible to detect human actions during the process, obtaining action recognition performances from 41% to 80% depending on the task. This approach can help to obtain information about how to improve harvesting process and reduce human workload in near future, which may be an important contribution for the search of sustainable agricultural practices.","PeriodicalId":176587,"journal":{"name":"2018 IEEE International Conference on Automation/XXIII Congress of the Chilean Association of Automatic Control (ICA-ACCA)","volume":"147 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121324360","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}
Air pollution and air quality assessment is a serious problem for a big cities, considering the increasing of air contamination. In this work, an air quality assessment on three monitoring points located in three different districts from Lima city, Peru, was conducted. The method used in this study was the grey clustering method, which is based on the grey system theory. This method has advantages, as it considers the uncertainty into its analysis, and air quality assessment is a topic with high level of uncertainty. The results revealed that the three monitoring points presented a good air quality according to Peruvian law. This is due to the fact that the districts on which are locates the monitoring points are new relatively; in addition, the wind from ocean helps to disperse the air pollution. The results of this study could to help to local and central authorities to make the best decision on air quality assessment. In addition, government from Peru could use the method applied in this word as an alternative to assess the air quality from other points of country.
{"title":"Air quality level assessment in Lima city using the grey clustering method","authors":"Alexi Delgado, Pamela Montellanos, Janfranco Llave","doi":"10.1109/ICA-ACCA.2018.8609699","DOIUrl":"https://doi.org/10.1109/ICA-ACCA.2018.8609699","url":null,"abstract":"Air pollution and air quality assessment is a serious problem for a big cities, considering the increasing of air contamination. In this work, an air quality assessment on three monitoring points located in three different districts from Lima city, Peru, was conducted. The method used in this study was the grey clustering method, which is based on the grey system theory. This method has advantages, as it considers the uncertainty into its analysis, and air quality assessment is a topic with high level of uncertainty. The results revealed that the three monitoring points presented a good air quality according to Peruvian law. This is due to the fact that the districts on which are locates the monitoring points are new relatively; in addition, the wind from ocean helps to disperse the air pollution. The results of this study could to help to local and central authorities to make the best decision on air quality assessment. In addition, government from Peru could use the method applied in this word as an alternative to assess the air quality from other points of country.","PeriodicalId":176587,"journal":{"name":"2018 IEEE International Conference on Automation/XXIII Congress of the Chilean Association of Automatic Control (ICA-ACCA)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121197415","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}
Pub Date : 2018-10-01DOI: 10.1109/ica-acca.2018.8609786
Daniel Castro-Contardo, M. Fernández-Fernández
In this document, the part I of the development of a continuous low-cost positive bi-pressure system as a respiratory support for patients with respiratory disorders while they sleep, such as sleep obstructive apnea-hypopnea, will be discussed. A description is given of the main requirements of this device, the features it must comply with and the components that comprise it.
{"title":"Design of a Continuous Positive Bi-Pressure System BPAP as Respiratory Support - Part I","authors":"Daniel Castro-Contardo, M. Fernández-Fernández","doi":"10.1109/ica-acca.2018.8609786","DOIUrl":"https://doi.org/10.1109/ica-acca.2018.8609786","url":null,"abstract":"In this document, the part I of the development of a continuous low-cost positive bi-pressure system as a respiratory support for patients with respiratory disorders while they sleep, such as sleep obstructive apnea-hypopnea, will be discussed. A description is given of the main requirements of this device, the features it must comply with and the components that comprise it.","PeriodicalId":176587,"journal":{"name":"2018 IEEE International Conference on Automation/XXIII Congress of the Chilean Association of Automatic Control (ICA-ACCA)","volume":"11 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116653385","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}
Pub Date : 2018-10-01DOI: 10.1109/ICA-ACCA.2018.8609814
S. Toledo, E. Maqueda, M. Rivera, T. Dragičević, R. Gregor
The classical model based predictive control leads to a variable switching frequency which could produce resonances in the input filter of the power converter, affecting the performance of the system. This paper proposes a fixed switching frequency model based predictive voltage control for UPS applications and a performance comparative between the proposed control and the variable switching frequency counterpart, showing the advantages and disadvantages among the two strategies.
{"title":"Predictive Voltage Control Techniques for AC UPS Applications","authors":"S. Toledo, E. Maqueda, M. Rivera, T. Dragičević, R. Gregor","doi":"10.1109/ICA-ACCA.2018.8609814","DOIUrl":"https://doi.org/10.1109/ICA-ACCA.2018.8609814","url":null,"abstract":"The classical model based predictive control leads to a variable switching frequency which could produce resonances in the input filter of the power converter, affecting the performance of the system. This paper proposes a fixed switching frequency model based predictive voltage control for UPS applications and a performance comparative between the proposed control and the variable switching frequency counterpart, showing the advantages and disadvantages among the two strategies.","PeriodicalId":176587,"journal":{"name":"2018 IEEE International Conference on Automation/XXIII Congress of the Chilean Association of Automatic Control (ICA-ACCA)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122672164","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：