Pub Date : 2017-08-01DOI: 10.1109/INTERCON.2017.8079699
J. Reategui, R. Callupe
Although superficial electromyographic signals are the most common input signal for machine learning algorithms in hand gesture recognition and finger force estimation applications, there are only a few commercially available systems for superficial EMG acquisition. This work proposes a cheap and easy to fabricate, dry superficial electrodes array. This system uses multiple active differential sensors integrated in a small double layer PCBs, each one uses two small rectangle areas of the bottom layer as conductive layer for signal acquisition. With a differential gain of 60dB between 23 and 3000Hz and a common mode rejection ration of −60dB at 60Hz. Design criteria and simulations are presented.
{"title":"Surface EMG multichannel array using active dry sensors for forearm signal extraction","authors":"J. Reategui, R. Callupe","doi":"10.1109/INTERCON.2017.8079699","DOIUrl":"https://doi.org/10.1109/INTERCON.2017.8079699","url":null,"abstract":"Although superficial electromyographic signals are the most common input signal for machine learning algorithms in hand gesture recognition and finger force estimation applications, there are only a few commercially available systems for superficial EMG acquisition. This work proposes a cheap and easy to fabricate, dry superficial electrodes array. This system uses multiple active differential sensors integrated in a small double layer PCBs, each one uses two small rectangle areas of the bottom layer as conductive layer for signal acquisition. With a differential gain of 60dB between 23 and 3000Hz and a common mode rejection ration of −60dB at 60Hz. Design criteria and simulations are presented.","PeriodicalId":229086,"journal":{"name":"2017 IEEE XXIV International Conference on Electronics, Electrical Engineering and Computing (INTERCON)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114734487","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 : 2017-08-01DOI: 10.1109/INTERCON.2017.8079680
D. L. Oliveira, Orlando Verducci, L. Faria, T. Curtinhas
Digital circuit design may demand critical requirements, such as power consumption, robustness, performance, etc., while being implemented in VLSI (Very Large Scale Integration). The asynchronous paradigm presents interesting features that serve as an alternative to these critical requirements. An important class of the asynchronous paradigm is the one called QDI (Quasi Delay Insensitive) circuits that can also be used for critical requirements design. QDI circuits are interesting for these applications because they are robust to certain kinds of faults, to noise and to temperature and supply voltage variations, having also low electromagnetic emissions. An interesting style of QDI circuits is the NCL (Κ Convention Logic) circuits because they accept conventional Boolean functions and can achieve great optimization. This paper presents an architecture based on basic QDI gates for the synthesis of NCL gates focusing on VLSI that uses only standard libraries and FPGA (Field Programmable Gate Array).
{"title":"A novel Κ convention logic (NCL) gates architecture based on basic gates","authors":"D. L. Oliveira, Orlando Verducci, L. Faria, T. Curtinhas","doi":"10.1109/INTERCON.2017.8079680","DOIUrl":"https://doi.org/10.1109/INTERCON.2017.8079680","url":null,"abstract":"Digital circuit design may demand critical requirements, such as power consumption, robustness, performance, etc., while being implemented in VLSI (Very Large Scale Integration). The asynchronous paradigm presents interesting features that serve as an alternative to these critical requirements. An important class of the asynchronous paradigm is the one called QDI (Quasi Delay Insensitive) circuits that can also be used for critical requirements design. QDI circuits are interesting for these applications because they are robust to certain kinds of faults, to noise and to temperature and supply voltage variations, having also low electromagnetic emissions. An interesting style of QDI circuits is the NCL (Κ Convention Logic) circuits because they accept conventional Boolean functions and can achieve great optimization. This paper presents an architecture based on basic QDI gates for the synthesis of NCL gates focusing on VLSI that uses only standard libraries and FPGA (Field Programmable Gate Array).","PeriodicalId":229086,"journal":{"name":"2017 IEEE XXIV International Conference on Electronics, Electrical Engineering and Computing (INTERCON)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126879081","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 : 2017-08-01DOI: 10.1109/INTERCON.2017.8079686
Jeanfranco D. Farfan-Escobedo, Lauro Enciso-Rodas, John E. Vargas-Muñoz
Building recognition from images is a challenging task since pictures can be taken from different angles and under different illumination conditions. Most of the building recognition methods use local and global handcrafted image features and do not consider the rejection scenario, where the method have to be capable of identifying if a given image does not belong to any of the classes of interest. We propose a method based on convolutional neural networks that obtain effective feature vectors to perform accurate classification of buildings. Additionally, we analyze and propose methods for the problem of classification with rejection.
{"title":"Towards accurate building recognition using convolutional neural networks","authors":"Jeanfranco D. Farfan-Escobedo, Lauro Enciso-Rodas, John E. Vargas-Muñoz","doi":"10.1109/INTERCON.2017.8079686","DOIUrl":"https://doi.org/10.1109/INTERCON.2017.8079686","url":null,"abstract":"Building recognition from images is a challenging task since pictures can be taken from different angles and under different illumination conditions. Most of the building recognition methods use local and global handcrafted image features and do not consider the rejection scenario, where the method have to be capable of identifying if a given image does not belong to any of the classes of interest. We propose a method based on convolutional neural networks that obtain effective feature vectors to perform accurate classification of buildings. Additionally, we analyze and propose methods for the problem of classification with rejection.","PeriodicalId":229086,"journal":{"name":"2017 IEEE XXIV International Conference on Electronics, Electrical Engineering and Computing (INTERCON)","volume":"96 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121721515","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 : 2017-08-01DOI: 10.1109/INTERCON.2017.8079646
M. Dominguez, Sergio Nesmachnow, José-Isidro Hernández-Vega
This article presents the simulation genetic algorithms with multi-agent system application to solve problems of collaboration and coordination, with the goal of minimizing the travel time of a fleet of drones. The experimental analysis compares the travel time of a deterministic algorithm versus a probabilistic algorithm in a multi-agent system with BDI architecture. The results show that the genetic algorithm delivers significant improvements in travel time, exceeding the deterministic algorithm by up to 35% on average. This article also discusses the feasibility of combining genetic algorithms and multi-agent systems for solving people search and rescue problems.
{"title":"Planning a drone fleet using artificial intelligence for search and rescue missions","authors":"M. Dominguez, Sergio Nesmachnow, José-Isidro Hernández-Vega","doi":"10.1109/INTERCON.2017.8079646","DOIUrl":"https://doi.org/10.1109/INTERCON.2017.8079646","url":null,"abstract":"This article presents the simulation genetic algorithms with multi-agent system application to solve problems of collaboration and coordination, with the goal of minimizing the travel time of a fleet of drones. The experimental analysis compares the travel time of a deterministic algorithm versus a probabilistic algorithm in a multi-agent system with BDI architecture. The results show that the genetic algorithm delivers significant improvements in travel time, exceeding the deterministic algorithm by up to 35% on average. This article also discusses the feasibility of combining genetic algorithms and multi-agent systems for solving people search and rescue problems.","PeriodicalId":229086,"journal":{"name":"2017 IEEE XXIV International Conference on Electronics, Electrical Engineering and Computing (INTERCON)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129597972","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 : 2017-08-01DOI: 10.1109/INTERCON.2017.8079709
Jeanette Quiñones Ccorimanya, L. Ling
We present a traffic control scheme in transmission queues of LTE systems in the downlink direction, based on traffic policing algorithms known as leaky bucket regulators with flows holding fractal and multifractal characteristics. The proposed control scheme aims at regulating the input traffic flows rate within an established profile. The simulation results have shown that the proposed control approach guarantees the efficient use of available LTE system resources.
{"title":"Traffic control in the transmission queue of LTE system downlink based on policing algorithms","authors":"Jeanette Quiñones Ccorimanya, L. Ling","doi":"10.1109/INTERCON.2017.8079709","DOIUrl":"https://doi.org/10.1109/INTERCON.2017.8079709","url":null,"abstract":"We present a traffic control scheme in transmission queues of LTE systems in the downlink direction, based on traffic policing algorithms known as leaky bucket regulators with flows holding fractal and multifractal characteristics. The proposed control scheme aims at regulating the input traffic flows rate within an established profile. The simulation results have shown that the proposed control approach guarantees the efficient use of available LTE system resources.","PeriodicalId":229086,"journal":{"name":"2017 IEEE XXIV International Conference on Electronics, Electrical Engineering and Computing (INTERCON)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122656163","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 : 2017-08-01DOI: 10.1109/INTERCON.2017.8079658
Luis Camacho Caballero, Carlos Saito, Reynaldo Baquerizo Micheline, J. A. Paredes
Wildlife inventories contribute to gauging the value of biodiversity in the Amazon rainforest. However, few studies have been made about this subject, mainly because of the lack of appropriate technology. In this paper, the design of hardware and software of a low-cost long-lasting time flight drone is proposed with the purpose of serving as a data mule to export data from an isolated wireless multimedia sensor network located in a remote nature reservation.
{"title":"On the design of an UAV-based store and forward transport network for wildlife inventory in the western Amazon rainforest","authors":"Luis Camacho Caballero, Carlos Saito, Reynaldo Baquerizo Micheline, J. A. Paredes","doi":"10.1109/INTERCON.2017.8079658","DOIUrl":"https://doi.org/10.1109/INTERCON.2017.8079658","url":null,"abstract":"Wildlife inventories contribute to gauging the value of biodiversity in the Amazon rainforest. However, few studies have been made about this subject, mainly because of the lack of appropriate technology. In this paper, the design of hardware and software of a low-cost long-lasting time flight drone is proposed with the purpose of serving as a data mule to export data from an isolated wireless multimedia sensor network located in a remote nature reservation.","PeriodicalId":229086,"journal":{"name":"2017 IEEE XXIV International Conference on Electronics, Electrical Engineering and Computing (INTERCON)","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125397544","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 : 2017-08-01DOI: 10.1109/INTERCON.2017.8079706
P. E. Vintimilla-Tapia, J. Bravo-Torres, Pablo L. Gallegos-Segovia, E. F. Ordóñez-Morales, M. López-Nores, Y. Blanco-Fernández
Internet, combined with the technologies of communication and information (ICT), is changing the society. Most aspects of the life of each individual have been influenced by this technological revolution. Education is not indifferent to this reality, since a number of tools and applications have been created which seek to improve the learning process. However, these educational technologies do not adapt to the way each student likes to learn. To solve this problem, this paper implements OPPIA, a multi-model educational platform, which offers three models: self-learning, tutoring learning and collaborative learning. Each student can choose the way they want to learn to obtain learning resources that reinforce their knowledge. At the end, he/she makes an assessment, which corroborates if the necessary knowledge about a certain subject was obtained.
{"title":"OPPIA: A multi-model platform for e-learning","authors":"P. E. Vintimilla-Tapia, J. Bravo-Torres, Pablo L. Gallegos-Segovia, E. F. Ordóñez-Morales, M. López-Nores, Y. Blanco-Fernández","doi":"10.1109/INTERCON.2017.8079706","DOIUrl":"https://doi.org/10.1109/INTERCON.2017.8079706","url":null,"abstract":"Internet, combined with the technologies of communication and information (ICT), is changing the society. Most aspects of the life of each individual have been influenced by this technological revolution. Education is not indifferent to this reality, since a number of tools and applications have been created which seek to improve the learning process. However, these educational technologies do not adapt to the way each student likes to learn. To solve this problem, this paper implements OPPIA, a multi-model educational platform, which offers three models: self-learning, tutoring learning and collaborative learning. Each student can choose the way they want to learn to obtain learning resources that reinforce their knowledge. At the end, he/she makes an assessment, which corroborates if the necessary knowledge about a certain subject was obtained.","PeriodicalId":229086,"journal":{"name":"2017 IEEE XXIV International Conference on Electronics, Electrical Engineering and Computing (INTERCON)","volume":"156 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129180643","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 : 2017-08-01DOI: 10.1109/INTERCON.2017.8079674
Wilson F. Cueva, F. Muñoz, G. Vásquez, G. Delgado.
In the last decades, skin cancer increased its incidence becoming a public health problem. Technological advances have allowed the development of applications that help the early detection of melanoma. In this context, an image processing was developed to obtain Asymmetry, Border, Color, and Diameter (ABCD of melanoma). Using neural networks to perform a classification of the different kinds of moles. As a result, this algorithm developed after an analysis of 200 images was obtained a performance of 97.51%.
{"title":"Detection of skin cancer ”Melanoma” through computer vision","authors":"Wilson F. Cueva, F. Muñoz, G. Vásquez, G. Delgado.","doi":"10.1109/INTERCON.2017.8079674","DOIUrl":"https://doi.org/10.1109/INTERCON.2017.8079674","url":null,"abstract":"In the last decades, skin cancer increased its incidence becoming a public health problem. Technological advances have allowed the development of applications that help the early detection of melanoma. In this context, an image processing was developed to obtain Asymmetry, Border, Color, and Diameter (ABCD of melanoma). Using neural networks to perform a classification of the different kinds of moles. As a result, this algorithm developed after an analysis of 200 images was obtained a performance of 97.51%.","PeriodicalId":229086,"journal":{"name":"2017 IEEE XXIV International Conference on Electronics, Electrical Engineering and Computing (INTERCON)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121995995","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 : 2017-08-01DOI: 10.1109/INTERCON.2017.8079675
D. L. Oliveira, T. Curtinhas, L. Faria, Orlando Verducci
Asynchronous controllers based on Asynchronous Finite State Machines (AFSM) are widely used in the control unit design of asynchronous systems. These systems can be implemented in Field Programmable Gate Arrays (FPGAs), which are a low cost design alternative. Different styles have been proposed to implement AFSMs, but all of them have limitations when implemented in FPGAs. Therefore, this paper proposes a novel architecture for AFSMs in the local clock style. AFSMs are described in the extended burst-mode (XBM) specification. The existence of a local clock reduces the requirements of asynchronous logic, but the timing requirements may require the insertion of delays, which makes FPGA implementation difficult and leads to degradation of performance and reliability. The novel proposed local clock architecture is robust to setup and hold time violations, so they are free of timing analysis and do not need to introduce any kind of delays. The proposed architecture was applied to thirteen benchmarks and when compared to the local clock architecture of SICARELO tool, focused on FPGAs, it did not need to introduce any delays, whereas SICARELO had to introduce delays in all thirteen benchmarks of up to 4.9ns and there was an average reduction of 30% at the time of latency.
{"title":"Robust architecture for locally-clocked extended burst-mode circuits without timing assumption","authors":"D. L. Oliveira, T. Curtinhas, L. Faria, Orlando Verducci","doi":"10.1109/INTERCON.2017.8079675","DOIUrl":"https://doi.org/10.1109/INTERCON.2017.8079675","url":null,"abstract":"Asynchronous controllers based on Asynchronous Finite State Machines (AFSM) are widely used in the control unit design of asynchronous systems. These systems can be implemented in Field Programmable Gate Arrays (FPGAs), which are a low cost design alternative. Different styles have been proposed to implement AFSMs, but all of them have limitations when implemented in FPGAs. Therefore, this paper proposes a novel architecture for AFSMs in the local clock style. AFSMs are described in the extended burst-mode (XBM) specification. The existence of a local clock reduces the requirements of asynchronous logic, but the timing requirements may require the insertion of delays, which makes FPGA implementation difficult and leads to degradation of performance and reliability. The novel proposed local clock architecture is robust to setup and hold time violations, so they are free of timing analysis and do not need to introduce any kind of delays. The proposed architecture was applied to thirteen benchmarks and when compared to the local clock architecture of SICARELO tool, focused on FPGAs, it did not need to introduce any delays, whereas SICARELO had to introduce delays in all thirteen benchmarks of up to 4.9ns and there was an average reduction of 30% at the time of latency.","PeriodicalId":229086,"journal":{"name":"2017 IEEE XXIV International Conference on Electronics, Electrical Engineering and Computing (INTERCON)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117065764","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 : 2017-08-01DOI: 10.1109/INTERCON.2017.8079714
C. C. C. dos Santos, J. Ortiz, Jônatas P. Américo, K. S. C. Linares
Magnetic materials are broadly use in electrical engineering applications, due to its high permeability that allows increasing magnetic flux. Analyzing systems containing these magnetic cores is complex due to the nonlinear behavior of the magnetic material. This nonlinear behavior can be represented by the magnetization curve and by the hysteresis phenomenon curve. In this work, only magnetization curve is modelled and shows flow variations by varying the magnetic field. For higher values of magnetic field, there is not a present considerable variation of magnetic flux. At this stage, the magnetic material or the core reaches its saturation. In this work, simple mathematical models represent nonlinear behavior of magnetic material in order to be used in circuit simulation and inductor design. Linearized, polynomial and hyperbolic models are used. The linearized model approaches experimental BH curve for linear segments. The polynomial model approaches the curve by polynomial equation and the hyperbolic model approaches the curve using a hyperbolic equation. For models implementation is needed the experimental BH curve. An RL circuit is used. Equations of the electric circuit, magnetic flux and the material model are coupled and solved. To validate, simulation and experimental voltage and current are compared.
{"title":"Nonlinear modeling of magnetic materials for electromagnetic devices simulation","authors":"C. C. C. dos Santos, J. Ortiz, Jônatas P. Américo, K. S. C. Linares","doi":"10.1109/INTERCON.2017.8079714","DOIUrl":"https://doi.org/10.1109/INTERCON.2017.8079714","url":null,"abstract":"Magnetic materials are broadly use in electrical engineering applications, due to its high permeability that allows increasing magnetic flux. Analyzing systems containing these magnetic cores is complex due to the nonlinear behavior of the magnetic material. This nonlinear behavior can be represented by the magnetization curve and by the hysteresis phenomenon curve. In this work, only magnetization curve is modelled and shows flow variations by varying the magnetic field. For higher values of magnetic field, there is not a present considerable variation of magnetic flux. At this stage, the magnetic material or the core reaches its saturation. In this work, simple mathematical models represent nonlinear behavior of magnetic material in order to be used in circuit simulation and inductor design. Linearized, polynomial and hyperbolic models are used. The linearized model approaches experimental BH curve for linear segments. The polynomial model approaches the curve by polynomial equation and the hyperbolic model approaches the curve using a hyperbolic equation. For models implementation is needed the experimental BH curve. An RL circuit is used. Equations of the electric circuit, magnetic flux and the material model are coupled and solved. To validate, simulation and experimental voltage and current are compared.","PeriodicalId":229086,"journal":{"name":"2017 IEEE XXIV International Conference on Electronics, Electrical Engineering and Computing (INTERCON)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114253700","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：