Pub Date : 2017-11-01DOI: 10.1109/ROPEC.2017.8261672
Carolina Maldonado-Mendez, Ana Luisa Solís, H. Rios-Figueroa, A. Marín-Hernández
In this paper we are interesting in knowing which features provide useful information for detecting a fall and how the set of selected characteristics impact the accuracy of detection. For this purpose two sets of features are used. The first one describes the shape of the detected person, and the second one, the change of the shape over the time. All of features are extracted from a cloud of points of a detected person by the Kinect device. To determinate a fallen pose, a generative model is used. Two experiments are carried out to analyze the effect of using two different subset of features, one of them selected by a Genetic Algorithm and the second by Principal Component Analysis (PCA). The obtained results suggest that the success of detection of fall depends on the selected features, and the genetic algorithm is a good technique to select them, when compared with PCA.
{"title":"Human fallen pose detection by using feature selection and a generative model","authors":"Carolina Maldonado-Mendez, Ana Luisa Solís, H. Rios-Figueroa, A. Marín-Hernández","doi":"10.1109/ROPEC.2017.8261672","DOIUrl":"https://doi.org/10.1109/ROPEC.2017.8261672","url":null,"abstract":"In this paper we are interesting in knowing which features provide useful information for detecting a fall and how the set of selected characteristics impact the accuracy of detection. For this purpose two sets of features are used. The first one describes the shape of the detected person, and the second one, the change of the shape over the time. All of features are extracted from a cloud of points of a detected person by the Kinect device. To determinate a fallen pose, a generative model is used. Two experiments are carried out to analyze the effect of using two different subset of features, one of them selected by a Genetic Algorithm and the second by Principal Component Analysis (PCA). The obtained results suggest that the success of detection of fall depends on the selected features, and the genetic algorithm is a good technique to select them, when compared with PCA.","PeriodicalId":260469,"journal":{"name":"2017 IEEE International Autumn Meeting on Power, Electronics and Computing (ROPEC)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130994392","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 : 2017-11-01DOI: 10.1109/ROPEC.2017.8261587
Sohail Khan, R. Escarela-Perez, J. C. Olivares-Galvan, V. M. Jimenez-Mondragon, F. Espino-cortes
The modern world is moving towards the smart grids and increased use of electronic loads. The realization of smart grid technology is the increased use of distributed energy resources, introducing new intelligent, communication and control systems that are mostly electronic circuits. The issues associated with this technology are bi-directional flow of power flow, increased harmonic emissions, direct current offsets and unbalances, voltage variation and switching transients. The increased usage of electronic loads at distribution level are generating harmonics, which in turn increases power losses in the transformers and cause pre-mature damage. These loads mostly inject the odd harmonics in the distribution system, resulting in the temperature rise of the transformer. It causes accelerated aging of transformer thereby called the attention of manufacturers and researchers to develop the procedures for enhancing the system reliability. In the literature, several methods have been proposed for calculating losses and derating the transformer such as experimental, IEEE recommended, analytical and Finite Element Method (FEM). This paper reviews the finite element analysis of distribution transformer under harmonics condition. The losses associated with harmonics, modeling and derating of transformer are the topics included in this paper. It is found that the main focus is paid on derating and losses calculation of the transformer for a percentage of harmonic contents.
{"title":"Finite element analysis of distribution transformer under harmonics condition: A review","authors":"Sohail Khan, R. Escarela-Perez, J. C. Olivares-Galvan, V. M. Jimenez-Mondragon, F. Espino-cortes","doi":"10.1109/ROPEC.2017.8261587","DOIUrl":"https://doi.org/10.1109/ROPEC.2017.8261587","url":null,"abstract":"The modern world is moving towards the smart grids and increased use of electronic loads. The realization of smart grid technology is the increased use of distributed energy resources, introducing new intelligent, communication and control systems that are mostly electronic circuits. The issues associated with this technology are bi-directional flow of power flow, increased harmonic emissions, direct current offsets and unbalances, voltage variation and switching transients. The increased usage of electronic loads at distribution level are generating harmonics, which in turn increases power losses in the transformers and cause pre-mature damage. These loads mostly inject the odd harmonics in the distribution system, resulting in the temperature rise of the transformer. It causes accelerated aging of transformer thereby called the attention of manufacturers and researchers to develop the procedures for enhancing the system reliability. In the literature, several methods have been proposed for calculating losses and derating the transformer such as experimental, IEEE recommended, analytical and Finite Element Method (FEM). This paper reviews the finite element analysis of distribution transformer under harmonics condition. The losses associated with harmonics, modeling and derating of transformer are the topics included in this paper. It is found that the main focus is paid on derating and losses calculation of the transformer for a percentage of harmonic contents.","PeriodicalId":260469,"journal":{"name":"2017 IEEE International Autumn Meeting on Power, Electronics and Computing (ROPEC)","volume":"139 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128475885","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 : 2017-11-01DOI: 10.1109/ROPEC.2017.8261637
Miguel A. Vega-Sánchez, Paulina D. Castañeda-Jiménez, R. Peña-Gallardo, Antonio Ruiz-Alonso, J. Morales-Saldaña, E. Palacios-Hernandez
This paper presents a study of the complementarity of wind and solar resources over Mexico for electricity generation. A dataset was generated using high-resolution wind and solar resource maps provided by the SIGER project to assess the possibility of a combined used of these renewable energy sources. Using image processing techniques, the values of average monthly wind speed and solar irradiation were obtained, and then the average energy production was calculated. In order to obtain new maps that show the degree of correlation between the wind and solar resources the Pearson correlation coefficient was applied. The obtained results show a good degree of complementarity between both energy sources, in specific places of the country in the different seasons of the year. The obtained maps can be useful in projects related to the installation of hybrid renewable energy generation systems that have wind turbines and photovoltaic cells.
{"title":"Evaluation of complementarity of wind and solar energy resources over Mexico using an image processing approach","authors":"Miguel A. Vega-Sánchez, Paulina D. Castañeda-Jiménez, R. Peña-Gallardo, Antonio Ruiz-Alonso, J. Morales-Saldaña, E. Palacios-Hernandez","doi":"10.1109/ROPEC.2017.8261637","DOIUrl":"https://doi.org/10.1109/ROPEC.2017.8261637","url":null,"abstract":"This paper presents a study of the complementarity of wind and solar resources over Mexico for electricity generation. A dataset was generated using high-resolution wind and solar resource maps provided by the SIGER project to assess the possibility of a combined used of these renewable energy sources. Using image processing techniques, the values of average monthly wind speed and solar irradiation were obtained, and then the average energy production was calculated. In order to obtain new maps that show the degree of correlation between the wind and solar resources the Pearson correlation coefficient was applied. The obtained results show a good degree of complementarity between both energy sources, in specific places of the country in the different seasons of the year. The obtained maps can be useful in projects related to the installation of hybrid renewable energy generation systems that have wind turbines and photovoltaic cells.","PeriodicalId":260469,"journal":{"name":"2017 IEEE International Autumn Meeting on Power, Electronics and Computing (ROPEC)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128185709","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 : 2017-11-01DOI: 10.1109/ROPEC.2017.8261650
J. M. Sosa, E. D. Silva-Vera, G. Vázquez, G. Escobar, P. Martinez‐Rodriguez
In this paper the experimental validation of the open-loop operation for a buck converter with an LCLC filter at the output is addressed. This DC-DC buck converter has a significant reduction of output switching ripples and an increase of power density compared to the buck conventional topology. Moreover as passive components are less demanding, the implementation may be performed by using film capacitors. Hence the converter mean time failures can be made higher than for the conventional buck converter. These features can be applied in efficient renewable electric energy systems, in sensitive power sources and in sensitive loads. In this paper it is shown that by adequately selecting the passive elements, the open-loop oscillating behaviors may be highly alleviated which makes of the converter a suitable solution. Experimental results are presented to show the performance of the converter.
{"title":"Experimental validation for an open-loop LCLC output filter buck converter","authors":"J. M. Sosa, E. D. Silva-Vera, G. Vázquez, G. Escobar, P. Martinez‐Rodriguez","doi":"10.1109/ROPEC.2017.8261650","DOIUrl":"https://doi.org/10.1109/ROPEC.2017.8261650","url":null,"abstract":"In this paper the experimental validation of the open-loop operation for a buck converter with an LCLC filter at the output is addressed. This DC-DC buck converter has a significant reduction of output switching ripples and an increase of power density compared to the buck conventional topology. Moreover as passive components are less demanding, the implementation may be performed by using film capacitors. Hence the converter mean time failures can be made higher than for the conventional buck converter. These features can be applied in efficient renewable electric energy systems, in sensitive power sources and in sensitive loads. In this paper it is shown that by adequately selecting the passive elements, the open-loop oscillating behaviors may be highly alleviated which makes of the converter a suitable solution. Experimental results are presented to show the performance of the converter.","PeriodicalId":260469,"journal":{"name":"2017 IEEE International Autumn Meeting on Power, Electronics and Computing (ROPEC)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116883797","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 : 2017-11-01DOI: 10.1109/ROPEC.2017.8261661
C. Caballero, Rafael Rodríguez Ponce, F. Muñoz
In this paper, design considerations for a low cost, site-specific solar simulator with only white LED emitters as light source are presented, harnessing the low dependence of crystalline solar cells on spectral distribution, which allows a low complexity design. Although several solar-based energy harvesting systems have been reported on different publications, the evaluation of their performance has been accomplished under different outdoor conditions that largely affect the results, making difficult to reproduce results, achieve an objective comparison and predict minimum conditions for reliable operation under different operation scenarios. As an alternative for controlled indoor testing, the use of solar simulators is proposed; nevertheless, typical commercial solar simulators are costly, complex and mainly designed for testing photovoltaic devices under simulated and ideal clear-sky standards, such as AM 1.5G, which differs from real-life outdoor conditions, since solar irradiance is highly dependent on weather conditions and geographical location: The proposed design is aimed for testing devices under controlled and close to real conditions.
{"title":"Design of a LED-based solar simulator for energy harvesting applications","authors":"C. Caballero, Rafael Rodríguez Ponce, F. Muñoz","doi":"10.1109/ROPEC.2017.8261661","DOIUrl":"https://doi.org/10.1109/ROPEC.2017.8261661","url":null,"abstract":"In this paper, design considerations for a low cost, site-specific solar simulator with only white LED emitters as light source are presented, harnessing the low dependence of crystalline solar cells on spectral distribution, which allows a low complexity design. Although several solar-based energy harvesting systems have been reported on different publications, the evaluation of their performance has been accomplished under different outdoor conditions that largely affect the results, making difficult to reproduce results, achieve an objective comparison and predict minimum conditions for reliable operation under different operation scenarios. As an alternative for controlled indoor testing, the use of solar simulators is proposed; nevertheless, typical commercial solar simulators are costly, complex and mainly designed for testing photovoltaic devices under simulated and ideal clear-sky standards, such as AM 1.5G, which differs from real-life outdoor conditions, since solar irradiance is highly dependent on weather conditions and geographical location: The proposed design is aimed for testing devices under controlled and close to real conditions.","PeriodicalId":260469,"journal":{"name":"2017 IEEE International Autumn Meeting on Power, Electronics and Computing (ROPEC)","volume":"143 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115905572","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 : 2017-11-01DOI: 10.1109/ROPEC.2017.8261607
A. Camarena-Ibarrola, F. Luque, Edgar Chávez
Identifying a speaker in a noisy environment is still a challenging problem. In spite of the impressive efficacy of deep architectures, the solution obtained is an obscure mapping, a black box. For transparent classifiers, the standard feature are the Mel-Frequency Cepstral Coefficients (MFCC). In this paper we build entropy vectors out of the first sixteen critical bands according to Bark's scale as features. The classifier consists in finding the closest vector sequences of the query in the database, counting the hits as in a k-nn classifier. In one case we use the MFCC (the state of the art) and in the other case we use the described entropy vectors. For the text-independent, we used gaped vector sequences which are discussed below in the paper. For text-dependent speaker identification we obtained 80% true positives @10% false positives, while the MFCC have about 60% true positives at the same false positive rate. This is also about the same for the text-independent case. In general we obtained more area under the respective ROC curves.
{"title":"Speaker identification through spectral entropy analysis","authors":"A. Camarena-Ibarrola, F. Luque, Edgar Chávez","doi":"10.1109/ROPEC.2017.8261607","DOIUrl":"https://doi.org/10.1109/ROPEC.2017.8261607","url":null,"abstract":"Identifying a speaker in a noisy environment is still a challenging problem. In spite of the impressive efficacy of deep architectures, the solution obtained is an obscure mapping, a black box. For transparent classifiers, the standard feature are the Mel-Frequency Cepstral Coefficients (MFCC). In this paper we build entropy vectors out of the first sixteen critical bands according to Bark's scale as features. The classifier consists in finding the closest vector sequences of the query in the database, counting the hits as in a k-nn classifier. In one case we use the MFCC (the state of the art) and in the other case we use the described entropy vectors. For the text-independent, we used gaped vector sequences which are discussed below in the paper. For text-dependent speaker identification we obtained 80% true positives @10% false positives, while the MFCC have about 60% true positives at the same false positive rate. This is also about the same for the text-independent case. In general we obtained more area under the respective ROC curves.","PeriodicalId":260469,"journal":{"name":"2017 IEEE International Autumn Meeting on Power, Electronics and Computing (ROPEC)","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123215442","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 : 2017-11-01DOI: 10.1109/ROPEC.2017.8261628
Ismael Molina-Moreno, A. Medina, R. Cisneros-Magaña, O. Anaya‐Lara
Power quality deals with waveform of sine voltage. Good power quality is supplied by utilities when a perfect sine waveform is delivered. However, several adverse phenomena negatively affect the power quality, e.g. harmonic currents injected to the network. Hence, voltage and current waveforms are distorted. In order to obtain the harmonic content in voltage and current waveforms, they are captured using data acquisition systems. Unfortunately, data can be contaminated by noise. This paper analyzes how affects this noise to determine the harmonic content by an algorithm designed for this purpose such as the Fast Fourier Transform, among others, and proposes an algorithm based on moving average filter to mitigate these adverse effects. The proposed method has been tested using the modified IEEE 14 bus test system. The results show that the harmonic content obtained from low noisy voltage and current waveforms present a considerable error in harmonics of low magnitude; hence, a procedure is necessary to mitigate the noise in contaminated measurements, before they are used to obtain the harmonic content or to assess the time domain state estimation. The results suggest that by using the proposed method, the noise in measurements can be mitigated to low values, thus improving the accuracy of the harmonic content estimation.
{"title":"Noise mitigation in voltage and current waveforms in harmonic distortion estimation","authors":"Ismael Molina-Moreno, A. Medina, R. Cisneros-Magaña, O. Anaya‐Lara","doi":"10.1109/ROPEC.2017.8261628","DOIUrl":"https://doi.org/10.1109/ROPEC.2017.8261628","url":null,"abstract":"Power quality deals with waveform of sine voltage. Good power quality is supplied by utilities when a perfect sine waveform is delivered. However, several adverse phenomena negatively affect the power quality, e.g. harmonic currents injected to the network. Hence, voltage and current waveforms are distorted. In order to obtain the harmonic content in voltage and current waveforms, they are captured using data acquisition systems. Unfortunately, data can be contaminated by noise. This paper analyzes how affects this noise to determine the harmonic content by an algorithm designed for this purpose such as the Fast Fourier Transform, among others, and proposes an algorithm based on moving average filter to mitigate these adverse effects. The proposed method has been tested using the modified IEEE 14 bus test system. The results show that the harmonic content obtained from low noisy voltage and current waveforms present a considerable error in harmonics of low magnitude; hence, a procedure is necessary to mitigate the noise in contaminated measurements, before they are used to obtain the harmonic content or to assess the time domain state estimation. The results suggest that by using the proposed method, the noise in measurements can be mitigated to low values, thus improving the accuracy of the harmonic content estimation.","PeriodicalId":260469,"journal":{"name":"2017 IEEE International Autumn Meeting on Power, Electronics and Computing (ROPEC)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130095786","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 : 2017-11-01DOI: 10.1109/ROPEC.2017.8261652
Abimael Rangel-Damián, E. Melgoza-Vázquez, H. Ruiz-Paredes
Fault location in electric distribution systems has been a subject of interest for a long time, due to its relevance for improving service continuity and reducing response time when a power interruption occurs. In many cases, electric companies invest heavily to modernize distribution systems, including substations and networks, either by replacing obsolete electrical equipment or by adding modern equipment. The information that this new technology can provide through communication channels to the Control Center in the company's SCADA (Supervisory Control and Data Acquisition) can be used along with fault localization methods to provide a fault distance estimation which can be useful for maintenance personnel to locate and repair the problem faster. This paper shows a study case prepared using the IEEE 34 node test feeder to reveal how the information available in the electrical equipment, such as voltage and current measurements, can be introduced in an impedance-based algorithm for fault location, improving performance if we consider equipment not only at the substation but along the mainline of the feeder.
{"title":"Application of fault location methods in distribution circuits with SCADA","authors":"Abimael Rangel-Damián, E. Melgoza-Vázquez, H. Ruiz-Paredes","doi":"10.1109/ROPEC.2017.8261652","DOIUrl":"https://doi.org/10.1109/ROPEC.2017.8261652","url":null,"abstract":"Fault location in electric distribution systems has been a subject of interest for a long time, due to its relevance for improving service continuity and reducing response time when a power interruption occurs. In many cases, electric companies invest heavily to modernize distribution systems, including substations and networks, either by replacing obsolete electrical equipment or by adding modern equipment. The information that this new technology can provide through communication channels to the Control Center in the company's SCADA (Supervisory Control and Data Acquisition) can be used along with fault localization methods to provide a fault distance estimation which can be useful for maintenance personnel to locate and repair the problem faster. This paper shows a study case prepared using the IEEE 34 node test feeder to reveal how the information available in the electrical equipment, such as voltage and current measurements, can be introduced in an impedance-based algorithm for fault location, improving performance if we consider equipment not only at the substation but along the mainline of the feeder.","PeriodicalId":260469,"journal":{"name":"2017 IEEE International Autumn Meeting on Power, Electronics and Computing (ROPEC)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127960330","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 : 2017-11-01DOI: 10.1109/ROPEC.2017.8261597
E. Bernal-Merchán, P. Suquilanda-Cuesta, C. Espinoza-Fajardo, A. León-Pesántez, Y. Robles-Bykbaev, V. Robles-Bykbaev, D. Quisi-Peralta
Language constitutes one of the most important mainstays in cognitive, social and psychological development of children. However, nowadays an important percentage of children without disabilities present communication disorders such as dyslalia, speech disorders, dysglosia, among many others. Likewise, in developing countries it is difficult to provide personalized rehabilitation services for those children due the lack of personnel, large number of students per classroom or lack of technologies to support activities in the schools or at home. For these reasons, in this paper we present an intelligent system to support the rehabilitation and development language skills in children from 4 to 5 years. Our approach relies on data mining techniques (clustering) and ludic activities. The system was validated with 60 children and 25 students of initial education career. The results are encouraging given that show a high interest for using the application in both side, teachers and children.
{"title":"ISLanD: An informatics intelligent system to support the language development of children from 4 to 5 years","authors":"E. Bernal-Merchán, P. Suquilanda-Cuesta, C. Espinoza-Fajardo, A. León-Pesántez, Y. Robles-Bykbaev, V. Robles-Bykbaev, D. Quisi-Peralta","doi":"10.1109/ROPEC.2017.8261597","DOIUrl":"https://doi.org/10.1109/ROPEC.2017.8261597","url":null,"abstract":"Language constitutes one of the most important mainstays in cognitive, social and psychological development of children. However, nowadays an important percentage of children without disabilities present communication disorders such as dyslalia, speech disorders, dysglosia, among many others. Likewise, in developing countries it is difficult to provide personalized rehabilitation services for those children due the lack of personnel, large number of students per classroom or lack of technologies to support activities in the schools or at home. For these reasons, in this paper we present an intelligent system to support the rehabilitation and development language skills in children from 4 to 5 years. Our approach relies on data mining techniques (clustering) and ludic activities. The system was validated with 60 children and 25 students of initial education career. The results are encouraging given that show a high interest for using the application in both side, teachers and children.","PeriodicalId":260469,"journal":{"name":"2017 IEEE International Autumn Meeting on Power, Electronics and Computing (ROPEC)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124531969","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 : 2017-11-01DOI: 10.1109/ROPEC.2017.8261663
J. R. Velázquez-González, H. Peregrina-Barreto, J. Rangel-Magdaleno, J. Ramirez-San-Juan
Laser speckle contrast imaging (LSCI) is an optical technique capable for blood flow analyzing based on local speckle contrast. In general, a CCD camera combined with a simple optical arrangement allows to obtain blood flow information. Unfortunately, there are important limitations in the case of deep blood vessels (about 300μm). In this case, it is difficult to obtain blood vessel information since speckle patterns inside the images are sparse. In this work, we propose an iterative spatiotemporal anisotropic filtering approach which, aims to improve the performance under deep vessels images. This approach consists in two different filters combined with an iterative behavior and a post processing step. First, a temporal filter computes the contrast gradient (K) for all pixels within the input image. Then, contrast directions are computed. Finally, a spatiotemporal filter analyzes the blood flow behavior based on the contrast directions. Experimental results are encouraging, the proposed approach improves the performance under deep vessels, compared with previous work. Furthermore, these results (which were obtained at different samples) demonstrated that it is possible to improve the global performance by using an iterative behavior.
{"title":"Robust laser speckle contrast images suitable for blood vessel visualization","authors":"J. R. Velázquez-González, H. Peregrina-Barreto, J. Rangel-Magdaleno, J. Ramirez-San-Juan","doi":"10.1109/ROPEC.2017.8261663","DOIUrl":"https://doi.org/10.1109/ROPEC.2017.8261663","url":null,"abstract":"Laser speckle contrast imaging (LSCI) is an optical technique capable for blood flow analyzing based on local speckle contrast. In general, a CCD camera combined with a simple optical arrangement allows to obtain blood flow information. Unfortunately, there are important limitations in the case of deep blood vessels (about 300μm). In this case, it is difficult to obtain blood vessel information since speckle patterns inside the images are sparse. In this work, we propose an iterative spatiotemporal anisotropic filtering approach which, aims to improve the performance under deep vessels images. This approach consists in two different filters combined with an iterative behavior and a post processing step. First, a temporal filter computes the contrast gradient (K) for all pixels within the input image. Then, contrast directions are computed. Finally, a spatiotemporal filter analyzes the blood flow behavior based on the contrast directions. Experimental results are encouraging, the proposed approach improves the performance under deep vessels, compared with previous work. Furthermore, these results (which were obtained at different samples) demonstrated that it is possible to improve the global performance by using an iterative behavior.","PeriodicalId":260469,"journal":{"name":"2017 IEEE International Autumn Meeting on Power, Electronics and Computing (ROPEC)","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122953032","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：