Pub Date : 2021-11-24DOI: 10.1109/urucon53396.2021.9647375
Sergio Pulido-Castro, Nubia Palacios-Quecan, Michelle P. Ballen-Cardenas, S. Cancino-Suarez, Alejandra Rizo-Arevalo, J. M. López
The creation of algorithms that predict emotional recognition is a subject that has been of particular interest by researchers around the world for the last few years, as many computer vision-based systems make use of this information to get an approximation of the emotional state of an individual. This study aims to develop a real-time emotional recognition algorithm based on the facial expression. Our main contributions are the following: This algorithm was tested in a computational tool designed to stimulate the imitation and recognition of emotions of children with Autism Spectrum Disorder based on their facial expressions. By designing an ensemble of machine learning models which separates emotions into different sets, we are able to improve the recognition accuracy. Additionally, the selection of relevant features greatly reduces the execution time of the algorithm, making it feasible for real-time recognition. Testing of different label combinations is yet to be performed in order to further improve the recognition accuracy.
{"title":"Ensemble of Machine Learning Models for an Improved Facial Emotion Recognition","authors":"Sergio Pulido-Castro, Nubia Palacios-Quecan, Michelle P. Ballen-Cardenas, S. Cancino-Suarez, Alejandra Rizo-Arevalo, J. M. López","doi":"10.1109/urucon53396.2021.9647375","DOIUrl":"https://doi.org/10.1109/urucon53396.2021.9647375","url":null,"abstract":"The creation of algorithms that predict emotional recognition is a subject that has been of particular interest by researchers around the world for the last few years, as many computer vision-based systems make use of this information to get an approximation of the emotional state of an individual. This study aims to develop a real-time emotional recognition algorithm based on the facial expression. Our main contributions are the following: This algorithm was tested in a computational tool designed to stimulate the imitation and recognition of emotions of children with Autism Spectrum Disorder based on their facial expressions. By designing an ensemble of machine learning models which separates emotions into different sets, we are able to improve the recognition accuracy. Additionally, the selection of relevant features greatly reduces the execution time of the algorithm, making it feasible for real-time recognition. Testing of different label combinations is yet to be performed in order to further improve the recognition accuracy.","PeriodicalId":337257,"journal":{"name":"2021 IEEE URUCON","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127164419","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 : 2021-11-24DOI: 10.1109/urucon53396.2021.9647211
Samuel T. da S. Maraschin, Paulo R. da S. Pereira, C. Cima, Luíse C. Dalló, P. S. Lora, Celso Peter
Polymerase chain reaction (PCR) is a procedure employed by clinical and research laboratories to amplify segments of DNA. The technique uses the thermal cycling of genetic material to produce a substantial amount of DNA from a small initial sample. The amplification of specific segments of DNA helps identify viruses and gene mutations, and also plays a role in diagnosis methods. The whole procedure may take several hours to be completed using conventional benchtop thermal cyclers. In order to reduce process time and equipment cost, we propose the development of a microfluidic device as an alternative to the thermal cyclers currently available in the market. The paper describes the steps and processes required for creating PCR microfluidic thermal cyclers. The main results of the development are the thermal modeling and the prototype fabrication of the new device.
{"title":"Modeling and Prototyping of a Microfluidic Device for DNA Amplification","authors":"Samuel T. da S. Maraschin, Paulo R. da S. Pereira, C. Cima, Luíse C. Dalló, P. S. Lora, Celso Peter","doi":"10.1109/urucon53396.2021.9647211","DOIUrl":"https://doi.org/10.1109/urucon53396.2021.9647211","url":null,"abstract":"Polymerase chain reaction (PCR) is a procedure employed by clinical and research laboratories to amplify segments of DNA. The technique uses the thermal cycling of genetic material to produce a substantial amount of DNA from a small initial sample. The amplification of specific segments of DNA helps identify viruses and gene mutations, and also plays a role in diagnosis methods. The whole procedure may take several hours to be completed using conventional benchtop thermal cyclers. In order to reduce process time and equipment cost, we propose the development of a microfluidic device as an alternative to the thermal cyclers currently available in the market. The paper describes the steps and processes required for creating PCR microfluidic thermal cyclers. The main results of the development are the thermal modeling and the prototype fabrication of the new device.","PeriodicalId":337257,"journal":{"name":"2021 IEEE URUCON","volume":"352 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127233689","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 : 2021-11-24DOI: 10.1109/urucon53396.2021.9647310
F. Blasina, Andrés Echarri, Gabriel Farber, Federico Molina, Sofia Machin, Nicolás Pérez
Hail characterization is necessary for generating models to protect people and their goods. Designing an electronic characterization system requires reproducing hail events. The objective of this article is to present a design proposal of a device for hail simulation based on the theory of energy matching. The simulator uses steel balls in place of hailstones. It can be loaded with up to 14 balls of sizes between 0.5 cm to 3.0 cm, which can be either dropped one by one or in pairs. If dropped in pairs, the distance between them can be regulated, as well as the delay. In this paper, the importance of having such a device is explained and several experiments to be conducted by using it in order to design a hail sensor are described.
{"title":"Why and How to Construct a Device for Hail Simulation","authors":"F. Blasina, Andrés Echarri, Gabriel Farber, Federico Molina, Sofia Machin, Nicolás Pérez","doi":"10.1109/urucon53396.2021.9647310","DOIUrl":"https://doi.org/10.1109/urucon53396.2021.9647310","url":null,"abstract":"Hail characterization is necessary for generating models to protect people and their goods. Designing an electronic characterization system requires reproducing hail events. The objective of this article is to present a design proposal of a device for hail simulation based on the theory of energy matching. The simulator uses steel balls in place of hailstones. It can be loaded with up to 14 balls of sizes between 0.5 cm to 3.0 cm, which can be either dropped one by one or in pairs. If dropped in pairs, the distance between them can be regulated, as well as the delay. In this paper, the importance of having such a device is explained and several experiments to be conducted by using it in order to design a hail sensor are described.","PeriodicalId":337257,"journal":{"name":"2021 IEEE URUCON","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125485518","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 : 2021-11-24DOI: 10.1109/urucon53396.2021.9647176
Andres Rojas, G. Dolecek
This paper presents a fingerprint recognition system based on Wavelet transform, multiple domain feature extraction, and Ensemble Subspace Discriminant Classifier. The main contribution of this work is the computation of a set of features that can be used for the classification of fingerprints, and the implementation of an ensemble of discriminant classifiers. First, the review of previous works is presented. Next, a detailed description of the proposed method is elaborated. Finally, it is shown that the proposed system provides the highest accuracy (97.5%) in comparison with other works proposed in the literature using a different type of classifier such as the ensemble subspace discriminant.
{"title":"Fingerprint Recognition Based on Wavelet Transform and Ensemble Subspace Classifier","authors":"Andres Rojas, G. Dolecek","doi":"10.1109/urucon53396.2021.9647176","DOIUrl":"https://doi.org/10.1109/urucon53396.2021.9647176","url":null,"abstract":"This paper presents a fingerprint recognition system based on Wavelet transform, multiple domain feature extraction, and Ensemble Subspace Discriminant Classifier. The main contribution of this work is the computation of a set of features that can be used for the classification of fingerprints, and the implementation of an ensemble of discriminant classifiers. First, the review of previous works is presented. Next, a detailed description of the proposed method is elaborated. Finally, it is shown that the proposed system provides the highest accuracy (97.5%) in comparison with other works proposed in the literature using a different type of classifier such as the ensemble subspace discriminant.","PeriodicalId":337257,"journal":{"name":"2021 IEEE URUCON","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114955797","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 : 2021-11-24DOI: 10.1109/urucon53396.2021.9647309
R. Molina-Robles, R. García-Ramírez, A. Chacón-Rodríguez, R. Rímolo-Donadío, A. Arnaud
To date, I2C is a protocol that has a lot of use on microcontroller applications. Implementing the hardware for a I2C controller affects directly chip size, cost and time development in VLSI projects. To save on these aspects, we have used hardware emulation by software to recreate the I2C behavior through GPIO ports in a RISC-V microcontroller of our own. This paper proposes a flexible and practical low-level algorithm that replaces a physical I2C controller, to be able connect an I2C peripheral device to its driver code inside the microcontroller using GPIO ports as channels. An explanation of the application is described, along with the code structure and the logic behind the algorithm. At the end, this paper presents results with a brief analysis of its benefits and future improvements.
{"title":"Low-level algorithm for a software-emulated I2C I/O module in general purpose RISC-V based microcontrollers","authors":"R. Molina-Robles, R. García-Ramírez, A. Chacón-Rodríguez, R. Rímolo-Donadío, A. Arnaud","doi":"10.1109/urucon53396.2021.9647309","DOIUrl":"https://doi.org/10.1109/urucon53396.2021.9647309","url":null,"abstract":"To date, I2C is a protocol that has a lot of use on microcontroller applications. Implementing the hardware for a I2C controller affects directly chip size, cost and time development in VLSI projects. To save on these aspects, we have used hardware emulation by software to recreate the I2C behavior through GPIO ports in a RISC-V microcontroller of our own. This paper proposes a flexible and practical low-level algorithm that replaces a physical I2C controller, to be able connect an I2C peripheral device to its driver code inside the microcontroller using GPIO ports as channels. An explanation of the application is described, along with the code structure and the logic behind the algorithm. At the end, this paper presents results with a brief analysis of its benefits and future improvements.","PeriodicalId":337257,"journal":{"name":"2021 IEEE URUCON","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115173024","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 : 2021-11-24DOI: 10.1109/urucon53396.2021.9647336
Alejandro Bellati, Nicolas Perez Blengio, Fabian Cancela, P. Monzón, Nicolás Pérez
The Furuta inverted pendulum is a benchmark for nonlinear underactuated control system. For our control lab, we developed an Arduino-based Furuta pendulum that can be integrated in real-time with the Simulink environment to design and test different controllers. This brief article presents some details of the model process of the pendulum and the development of a supervisory control scheme, that includes swing-up the pendulum from the down-right position and control it at the up-right position.
{"title":"Modeling and control of a Furuta pendulum","authors":"Alejandro Bellati, Nicolas Perez Blengio, Fabian Cancela, P. Monzón, Nicolás Pérez","doi":"10.1109/urucon53396.2021.9647336","DOIUrl":"https://doi.org/10.1109/urucon53396.2021.9647336","url":null,"abstract":"The Furuta inverted pendulum is a benchmark for nonlinear underactuated control system. For our control lab, we developed an Arduino-based Furuta pendulum that can be integrated in real-time with the Simulink environment to design and test different controllers. This brief article presents some details of the model process of the pendulum and the development of a supervisory control scheme, that includes swing-up the pendulum from the down-right position and control it at the up-right position.","PeriodicalId":337257,"journal":{"name":"2021 IEEE URUCON","volume":"103 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116046791","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 : 2021-11-24DOI: 10.1109/urucon53396.2021.9647345
Jonathan Layedra, Maximiliano Martínez, P. Mercado
This article presents a Levelized Cost of Storage (LCOS) analysis for lithium batteries in different applications. A battery degradation model is incorporated into the analysis, which estimates the reduction in economic income due to the decrease in energy capacity. Another factor considered is the residual value attributed to the batteries, once they have completed their first stage of degradation and can be reused in second life applications. The Present Value of Throughput (PVT) metric is used to estimate the health factor of repurposed batteries and then calculate an attractive and reasonable selling price. All the analysis are made for the year 2020, and based on studies of the evolution of technology costs, the LCOS is projected for the year 2030. The results show that the most significant component of LCOS for all applications is investment, due to the high cost of this type of storage technology. Even for the year 2030, the LCOS is significantly reduced, capital expenditures continue to predominate, while the residual value represents an important role in the economic income at the end of the project life.
本文介绍了锂电池在不同应用中的平准化存储成本(LCOS)分析。在分析中引入了电池退化模型，该模型估计了由于能量容量下降而导致的经济收入减少。另一个考虑的因素是电池的剩余价值，一旦它们完成了第一阶段的降解，就可以在第二次使用中重复使用。利用产量现值(Present Value of Throughput, PVT)指标估算再利用电池的健康系数，进而计算出具有吸引力且合理的销售价格。所有的分析都是针对2020年进行的，并基于对技术成本演变的研究，预测了2030年的LCOS。结果表明，由于这种存储技术的高成本，LCOS在所有应用中最重要的组成部分是投资。即使到2030年，LCOS也会显著减少，资本支出继续占主导地位，而剩余价值在项目生命周期结束时的经济收入中发挥着重要作用。
{"title":"Levelized Cost of Storage for Lithium Batteries, Considering Degradation and Residual Value","authors":"Jonathan Layedra, Maximiliano Martínez, P. Mercado","doi":"10.1109/urucon53396.2021.9647345","DOIUrl":"https://doi.org/10.1109/urucon53396.2021.9647345","url":null,"abstract":"This article presents a Levelized Cost of Storage (LCOS) analysis for lithium batteries in different applications. A battery degradation model is incorporated into the analysis, which estimates the reduction in economic income due to the decrease in energy capacity. Another factor considered is the residual value attributed to the batteries, once they have completed their first stage of degradation and can be reused in second life applications. The Present Value of Throughput (PVT) metric is used to estimate the health factor of repurposed batteries and then calculate an attractive and reasonable selling price. All the analysis are made for the year 2020, and based on studies of the evolution of technology costs, the LCOS is projected for the year 2030. The results show that the most significant component of LCOS for all applications is investment, due to the high cost of this type of storage technology. Even for the year 2030, the LCOS is significantly reduced, capital expenditures continue to predominate, while the residual value represents an important role in the economic income at the end of the project life.","PeriodicalId":337257,"journal":{"name":"2021 IEEE URUCON","volume":"1247 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122697896","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 : 2021-11-24DOI: 10.1109/urucon53396.2021.9647089
Lenin Aucatoma, I. de la Torre, Fausto Lopez, Verônica Soria
This paper presents the effects that occur on the reflection coefficient, VSWR, dimensions and bandwidth of a half-wave dipole antenna when the resonant frequencies vary. To achieve the objectives for reflection coefficient (less than - 10dB) and VSWR (between 1 and 1.5), it was necessary adjust the antenna dimensions, highlighting the most important gaps in length of poles and length of substrate, obtaining gaps varying from 2000% to 8000% respectfully to the mathematical models. Finally, with a test in substrate, we found that using a different material than air, we achieved an increase of bandwidth for each model in each frequency, this increase was three times superior in comparison with the antennas that used air as substrate.
{"title":"Half-wave dipole antenna design comparison of 60, 67 y 74 GHz frequencies","authors":"Lenin Aucatoma, I. de la Torre, Fausto Lopez, Verônica Soria","doi":"10.1109/urucon53396.2021.9647089","DOIUrl":"https://doi.org/10.1109/urucon53396.2021.9647089","url":null,"abstract":"This paper presents the effects that occur on the reflection coefficient, VSWR, dimensions and bandwidth of a half-wave dipole antenna when the resonant frequencies vary. To achieve the objectives for reflection coefficient (less than - 10dB) and VSWR (between 1 and 1.5), it was necessary adjust the antenna dimensions, highlighting the most important gaps in length of poles and length of substrate, obtaining gaps varying from 2000% to 8000% respectfully to the mathematical models. Finally, with a test in substrate, we found that using a different material than air, we achieved an increase of bandwidth for each model in each frequency, this increase was three times superior in comparison with the antennas that used air as substrate.","PeriodicalId":337257,"journal":{"name":"2021 IEEE URUCON","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114430899","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 : 2021-11-24DOI: 10.1109/urucon53396.2021.9647053
R. S. F. Ferraz, R. S. F. Ferraz, Augusto C. Rueda-Medina, M. Paiva
The power flow and short-circuit algorithms are usually adopted in problems regarding the power system operation and planning. Thus, many authors have been using the Backward-Forward Sweep (BFS) method, due to its simplicity, low computational effort and high accuracy. However, in this method, it is necessary to order all the nodes by layers from the root node to the nodes which are further away from the substation, and this process may be substantially complex depending on the system dimension. Therefore, in this paper, a novel BFS approach was proposed, which uses graph theory to avoid the complex process mentioned before. Furthermore, the graph concepts were also adopted in order to assist in the short-circuit analysis, through the automated computation of the Thevenin equivalent impedance at the faulted node. These procedures were evaluated using the IEEE 13, 34, 37 and 123 node test feeders, and it can be generalized for feeders with higher dimensions. From the results, it is possible to conclude the low computational effort of the proposed method, preserving the high accuracy of the algorithms which achieve the power flow solution and short-circuit current.
{"title":"Power Flow and Fault analysis Using Graph Theory","authors":"R. S. F. Ferraz, R. S. F. Ferraz, Augusto C. Rueda-Medina, M. Paiva","doi":"10.1109/urucon53396.2021.9647053","DOIUrl":"https://doi.org/10.1109/urucon53396.2021.9647053","url":null,"abstract":"The power flow and short-circuit algorithms are usually adopted in problems regarding the power system operation and planning. Thus, many authors have been using the Backward-Forward Sweep (BFS) method, due to its simplicity, low computational effort and high accuracy. However, in this method, it is necessary to order all the nodes by layers from the root node to the nodes which are further away from the substation, and this process may be substantially complex depending on the system dimension. Therefore, in this paper, a novel BFS approach was proposed, which uses graph theory to avoid the complex process mentioned before. Furthermore, the graph concepts were also adopted in order to assist in the short-circuit analysis, through the automated computation of the Thevenin equivalent impedance at the faulted node. These procedures were evaluated using the IEEE 13, 34, 37 and 123 node test feeders, and it can be generalized for feeders with higher dimensions. From the results, it is possible to conclude the low computational effort of the proposed method, preserving the high accuracy of the algorithms which achieve the power flow solution and short-circuit current.","PeriodicalId":337257,"journal":{"name":"2021 IEEE URUCON","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129883226","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：