Pub Date : 2022-11-09DOI: 10.1109/CONCAPAN48024.2022.9997734
Luis Felipe Gaitán Cubides, Juan David Gomez Ariza, Luis Alberto Zapata Giraldo, J. Serna, Jorge Sánchez
Some towns in Colombia that are not connected to the National Interconnected System, supply their energy needs from Diesel Generation and Solar-Diesel Hybrid systems. These populations do not have uninterrupted electric energy service, reason why, in case of a transient failure in the distribution network, a great number of users may lose the electric supply, due to the performance of the protections. In this work, the implementation of reclosers in the electrical distribution system is proposed with the objective that these devices allow the disconnection of only the faulted parts of the circuit in a coordinated manner with the fuse tripping. The overcurrent functions criteria of the recloser are adjusted and a Recloser - Fuse coordination scheme with defined time characteristics in the first actuation cycle is proposed.
{"title":"Recloser - Fuse Coordination in the Distribution System of a Non-Interconnected Zone","authors":"Luis Felipe Gaitán Cubides, Juan David Gomez Ariza, Luis Alberto Zapata Giraldo, J. Serna, Jorge Sánchez","doi":"10.1109/CONCAPAN48024.2022.9997734","DOIUrl":"https://doi.org/10.1109/CONCAPAN48024.2022.9997734","url":null,"abstract":"Some towns in Colombia that are not connected to the National Interconnected System, supply their energy needs from Diesel Generation and Solar-Diesel Hybrid systems. These populations do not have uninterrupted electric energy service, reason why, in case of a transient failure in the distribution network, a great number of users may lose the electric supply, due to the performance of the protections. In this work, the implementation of reclosers in the electrical distribution system is proposed with the objective that these devices allow the disconnection of only the faulted parts of the circuit in a coordinated manner with the fuse tripping. The overcurrent functions criteria of the recloser are adjusted and a Recloser - Fuse coordination scheme with defined time characteristics in the first actuation cycle is proposed.","PeriodicalId":138415,"journal":{"name":"2022 IEEE 40th Central America and Panama Convention (CONCAPAN)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121892598","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 : 2022-11-09DOI: 10.1109/CONCAPAN48024.2022.9997787
Cristian Rodriguez, Jorge Piñeros, A. Prieto, Miguel Oliva
Recently a commission of scientists and environmentalists from the European Union have declared an ambitious plan to mitigate global warming by requiring a reduction of greenhouse gas (GHG) emissions of at least 55% by 2030. The aim is to achieve climate neutrality by 2050 and avoid severe consequences of climate change [1]. Energy sustainability is now a key global imperative, and EconiQ™ transformers are suitable as a solution. Hitachi Energy is delivering to support sustainable development in power grids. The four cornerstones of the framework are carbon footprint reduction, protection of local ecosystems, improved safety, and responsible use of resources. These cornerstones are based on transparency throughout the value chain and product lifecycle, co-creation with our customers, the joint application of advanced technologies and solutions, and Hitachi Energy’s sustainability strategy for the coming years. In more detail, the application of optimal design evaluation methodologies that minimize energy consumption for operation, considering the application of high-performance and environmentally friendly materials, applying more robust technologies that minimize the severity of catastrophic events, and a detailed analysis/evaluation process provide the applicable context for EconiQ™ transformers showing some cases for a local market. This framework shows the structure and wants to provide feedback/sensitization on a suitable scenario for the conception, acquisition, and management of assets that aim at mitigating the emission of carbon polluting gases and other gases with highly damaging footprints and seek a better sustainability of the electricity sector.
{"title":"Sustainability in transformers: A key concept in a more sustainable power grid","authors":"Cristian Rodriguez, Jorge Piñeros, A. Prieto, Miguel Oliva","doi":"10.1109/CONCAPAN48024.2022.9997787","DOIUrl":"https://doi.org/10.1109/CONCAPAN48024.2022.9997787","url":null,"abstract":"Recently a commission of scientists and environmentalists from the European Union have declared an ambitious plan to mitigate global warming by requiring a reduction of greenhouse gas (GHG) emissions of at least 55% by 2030. The aim is to achieve climate neutrality by 2050 and avoid severe consequences of climate change [1]. Energy sustainability is now a key global imperative, and EconiQ™ transformers are suitable as a solution. Hitachi Energy is delivering to support sustainable development in power grids. The four cornerstones of the framework are carbon footprint reduction, protection of local ecosystems, improved safety, and responsible use of resources. These cornerstones are based on transparency throughout the value chain and product lifecycle, co-creation with our customers, the joint application of advanced technologies and solutions, and Hitachi Energy’s sustainability strategy for the coming years. In more detail, the application of optimal design evaluation methodologies that minimize energy consumption for operation, considering the application of high-performance and environmentally friendly materials, applying more robust technologies that minimize the severity of catastrophic events, and a detailed analysis/evaluation process provide the applicable context for EconiQ™ transformers showing some cases for a local market. This framework shows the structure and wants to provide feedback/sensitization on a suitable scenario for the conception, acquisition, and management of assets that aim at mitigating the emission of carbon polluting gases and other gases with highly damaging footprints and seek a better sustainability of the electricity sector.","PeriodicalId":138415,"journal":{"name":"2022 IEEE 40th Central America and Panama Convention (CONCAPAN)","volume":"23 24","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120862132","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 : 2022-11-09DOI: 10.1109/CONCAPAN48024.2022.9997771
Erick Blanco, R. Alvarez, César Echeverría, Rudy Merlos
This article presents a methodology for the practical estimation of the usable wind resource in a site of interest for the assembly of low power wind turbines.The methodology includes the use of historical information in a time range of two years to compare it with the values of databases in the same period of time that a commercial software tool has and validate them through measurements of the resource in a site under study in that same time window to corroborate that the data provided by the software tool are consistent with those measured. Having verified the above, it is guaranteed that we can use the software tools to estimate practically the wind resource and the usable power in places of interest, since throughout the article it is shown that the measured and historical data are very close, therefore, for low power applications, it is a practical way to estimate the wind resource at any point of interest in El Salvador or the Central American region.
{"title":"Methodology for Practical Estimation of the Wind Resource for Low Power Applications","authors":"Erick Blanco, R. Alvarez, César Echeverría, Rudy Merlos","doi":"10.1109/CONCAPAN48024.2022.9997771","DOIUrl":"https://doi.org/10.1109/CONCAPAN48024.2022.9997771","url":null,"abstract":"This article presents a methodology for the practical estimation of the usable wind resource in a site of interest for the assembly of low power wind turbines.The methodology includes the use of historical information in a time range of two years to compare it with the values of databases in the same period of time that a commercial software tool has and validate them through measurements of the resource in a site under study in that same time window to corroborate that the data provided by the software tool are consistent with those measured. Having verified the above, it is guaranteed that we can use the software tools to estimate practically the wind resource and the usable power in places of interest, since throughout the article it is shown that the measured and historical data are very close, therefore, for low power applications, it is a practical way to estimate the wind resource at any point of interest in El Salvador or the Central American region.","PeriodicalId":138415,"journal":{"name":"2022 IEEE 40th Central America and Panama Convention (CONCAPAN)","volume":"112 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124132076","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 : 2022-11-09DOI: 10.1109/concapan48024.2022.9997754
{"title":"CONCAPAN 2022 Cover Page","authors":"","doi":"10.1109/concapan48024.2022.9997754","DOIUrl":"https://doi.org/10.1109/concapan48024.2022.9997754","url":null,"abstract":"","PeriodicalId":138415,"journal":{"name":"2022 IEEE 40th Central America and Panama Convention (CONCAPAN)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124793337","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 : 2022-11-09DOI: 10.1109/concapan48024.2022.9997608
Eduardo Flores-Morán, Wendy Yánez-Pazmiño, Luis Espín-Pazmiño, Ivette Carrera-Manosalvas, Julio Barzola-Monteses
Direct current (DC) drivers have been widely implemented in a variety of systems due to their simple and affordable configuration and capability for variable speed control. DC drivers position control are modeled as third order systems, which demand considerable effort in terms of control action. More recent attention has focused on the development of controllers based on artificial intelligence. However, the computational resource is significant. To determine the effectiveness of a specific controller, it is necessary to examine the parameters of rising time (tr), settling time (ts), overshoot percentage (Mp%) and steady state error (ESS). Thus, the main contribution in this paper is to provide a comprehensive study of two strategies, Model Predictive Control (MPC) and Genetic Algorithm (GA). MPC applies a set of rules to the model in order to forecast the upcoming behavior of a system across a defined horizon. The latter is a solver that imitates the natural evolution of Darwin’s law to tune PID controller. MPC provides a suitable response in terms of toque load disturbance and overshoot percentage.
{"title":"Model Predictive Control and Genetic Algorithm PID for DC Motor position.","authors":"Eduardo Flores-Morán, Wendy Yánez-Pazmiño, Luis Espín-Pazmiño, Ivette Carrera-Manosalvas, Julio Barzola-Monteses","doi":"10.1109/concapan48024.2022.9997608","DOIUrl":"https://doi.org/10.1109/concapan48024.2022.9997608","url":null,"abstract":"Direct current (DC) drivers have been widely implemented in a variety of systems due to their simple and affordable configuration and capability for variable speed control. DC drivers position control are modeled as third order systems, which demand considerable effort in terms of control action. More recent attention has focused on the development of controllers based on artificial intelligence. However, the computational resource is significant. To determine the effectiveness of a specific controller, it is necessary to examine the parameters of rising time (tr), settling time (ts), overshoot percentage (Mp%) and steady state error (ESS). Thus, the main contribution in this paper is to provide a comprehensive study of two strategies, Model Predictive Control (MPC) and Genetic Algorithm (GA). MPC applies a set of rules to the model in order to forecast the upcoming behavior of a system across a defined horizon. The latter is a solver that imitates the natural evolution of Darwin’s law to tune PID controller. MPC provides a suitable response in terms of toque load disturbance and overshoot percentage.","PeriodicalId":138415,"journal":{"name":"2022 IEEE 40th Central America and Panama Convention (CONCAPAN)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125067106","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 : 2022-11-09DOI: 10.1109/CONCAPAN48024.2022.9997653
J. Clímaco, Telma Chávez, Arturo Escalante
In the interaction with computer systems, the trend is moving toward the use of virtual computer assistants that will allow users to request information and interact with computers as it was communicating with another human. This article summarizes the work around the design, analysis, and development of a conversational bot using Artificial Intelligence with RASA framework, that implements natural language processing NLP. The bot named ChatO intends to provide weather information and the impacts related in a simple code, allowing the population of El Salvador to be informed and take actions that aim the reduction of negative impacts due to the occurrence of natural hazards.
{"title":"Conversational AI to improve local environmental risk management","authors":"J. Clímaco, Telma Chávez, Arturo Escalante","doi":"10.1109/CONCAPAN48024.2022.9997653","DOIUrl":"https://doi.org/10.1109/CONCAPAN48024.2022.9997653","url":null,"abstract":"In the interaction with computer systems, the trend is moving toward the use of virtual computer assistants that will allow users to request information and interact with computers as it was communicating with another human. This article summarizes the work around the design, analysis, and development of a conversational bot using Artificial Intelligence with RASA framework, that implements natural language processing NLP. The bot named ChatO intends to provide weather information and the impacts related in a simple code, allowing the population of El Salvador to be informed and take actions that aim the reduction of negative impacts due to the occurrence of natural hazards.","PeriodicalId":138415,"journal":{"name":"2022 IEEE 40th Central America and Panama Convention (CONCAPAN)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128428522","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 : 2022-11-09DOI: 10.1109/CONCAPAN48024.2022.9997703
Sarah Castelar, Leonardo A. Banegas, David A. Mendoza, Jean Carlo Soto, Kenny Davila
A new L200 banknote arrived to commemorate the bicentennial of Honduras. This made necessary to update automated methods for banknote image classification. The goal of this work was to develop algorithms that take centered images of banknotes and determine their denominations and visible sides. Two classification methods are presented. The first one uses local descriptors such as ORB or SIFT to match keypoints between the input image and templates to create feature vectors, and the images are then classified using Support Vector Machines or Random Forests. The second method is a Convolutional Neural Network (CNN) called LempiraNet, where transfer learning was used to deal with the limited data available. In both methods, image preprocessing can be used to locate the banknote to make its classification easier. To evaluate the effectiveness of these methods, two sets of 412 and 265 images were used for training and testing respectively. Multiple configurations were considered per method, and each one was evaluated in terms of recall, precision, F1 and run time. It was found that both methods reached at least 98% F1 score when using image preprocessing for locating the banknote in the input image. Also, it is observed that SIFT has better performance than ORB. In terms of run time, LempiraNet was at least 20 times faster than the other method, making it usable in real applications.
{"title":"Automated Honduran Banknote Image Classification using Machine Learning","authors":"Sarah Castelar, Leonardo A. Banegas, David A. Mendoza, Jean Carlo Soto, Kenny Davila","doi":"10.1109/CONCAPAN48024.2022.9997703","DOIUrl":"https://doi.org/10.1109/CONCAPAN48024.2022.9997703","url":null,"abstract":"A new L200 banknote arrived to commemorate the bicentennial of Honduras. This made necessary to update automated methods for banknote image classification. The goal of this work was to develop algorithms that take centered images of banknotes and determine their denominations and visible sides. Two classification methods are presented. The first one uses local descriptors such as ORB or SIFT to match keypoints between the input image and templates to create feature vectors, and the images are then classified using Support Vector Machines or Random Forests. The second method is a Convolutional Neural Network (CNN) called LempiraNet, where transfer learning was used to deal with the limited data available. In both methods, image preprocessing can be used to locate the banknote to make its classification easier. To evaluate the effectiveness of these methods, two sets of 412 and 265 images were used for training and testing respectively. Multiple configurations were considered per method, and each one was evaluated in terms of recall, precision, F1 and run time. It was found that both methods reached at least 98% F1 score when using image preprocessing for locating the banknote in the input image. Also, it is observed that SIFT has better performance than ORB. In terms of run time, LempiraNet was at least 20 times faster than the other method, making it usable in real applications.","PeriodicalId":138415,"journal":{"name":"2022 IEEE 40th Central America and Panama Convention (CONCAPAN)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129912066","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 : 2022-11-09DOI: 10.1109/CONCAPAN48024.2022.9997770
Y. P. Caviativa, Fabian C. Castro, Valentin Guzman, F. Sanz
Due to the increasing advances of technologies in education and developments in computer science, teachers of different engineering careers face constant pedagogical challenges in curriculum planning. These innovative technologies require that students start with new expectations in terms of interaction and communication, teamwork, breaking knowledge gaps. One strategy is to dynamize this communication in short courses, looking for professionals at the forefront of changes in new technologies. The objective of this research was to determine collaborative learning within the significant construction of knowledge. An educational experience focused on collaborative learning is presented for the design, development and implementation of a text mining course. Five digital resources were created and used. In platform with interaccon in chat and forums where case studies are discussed to encourage interaction and communication against lived experiences, the type of study of this research is qualitative interpretive descriptive approach, line by line analysis. Positive results were obtained in the construction of meaningful knowledge. The trainees reported a decrease in the gap between theory and practice. Other findings showed that collaborative work improved collective intelligence. An emergent category ”reflective knowledge” was discovered was discovered that contributed to the characterization of collaborative learning.
{"title":"Educational resources with digital content for pedagogical and research teaching in technologies of knowledge and learning","authors":"Y. P. Caviativa, Fabian C. Castro, Valentin Guzman, F. Sanz","doi":"10.1109/CONCAPAN48024.2022.9997770","DOIUrl":"https://doi.org/10.1109/CONCAPAN48024.2022.9997770","url":null,"abstract":"Due to the increasing advances of technologies in education and developments in computer science, teachers of different engineering careers face constant pedagogical challenges in curriculum planning. These innovative technologies require that students start with new expectations in terms of interaction and communication, teamwork, breaking knowledge gaps. One strategy is to dynamize this communication in short courses, looking for professionals at the forefront of changes in new technologies. The objective of this research was to determine collaborative learning within the significant construction of knowledge. An educational experience focused on collaborative learning is presented for the design, development and implementation of a text mining course. Five digital resources were created and used. In platform with interaccon in chat and forums where case studies are discussed to encourage interaction and communication against lived experiences, the type of study of this research is qualitative interpretive descriptive approach, line by line analysis. Positive results were obtained in the construction of meaningful knowledge. The trainees reported a decrease in the gap between theory and practice. Other findings showed that collaborative work improved collective intelligence. An emergent category ”reflective knowledge” was discovered was discovered that contributed to the characterization of collaborative learning.","PeriodicalId":138415,"journal":{"name":"2022 IEEE 40th Central America and Panama Convention (CONCAPAN)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130703809","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 : 2022-11-09DOI: 10.1109/CONCAPAN48024.2022.9997609
Juan-Daniel Páez-Carabajo, M. Huerta, D. Rivas-Lalaleo, G. Vayas, Roger Clotet-Martinez, J. Castillo-Velazquez
In recent years, the number of deaths due to environmental pollution has increased. The main air pollutants are carbon monoxide, carbon dioxide, and sulfur dioxide. These are produced by the consumption of fossil fuels in vehicles, industrial activity, and agricultural practices, among others. Various technologies have been used to detect carbon dioxide (CO2), including the Internet of Things (IoT). However, no studies have been carried out to visualize the impact of IoT on CO2 monitoring and which countries are focused on minimizing emissions. This work shows a bibliometric study for CO2 environmental sensing using IoT. SCOPUS was the selected database, and PRISMA was the methodology used. The first search returned 13.207 documents written between 2013 and 2022, after filtering selected keywords, selecting only English articles, and abstract review we selected finally 79 documents for the measurement of CO2 using IoT. The results of analyzing them, show that the Asian countries produces more than the western countries, where India and Indonesia are leading. Also is interesting to note that the USA and Latin America produced the same quantity of documents, where the four countries contributing to Latin America are Brazil, Mexico, Peru, and Ecuador. The main area of knowledge covered by the documents was Engineering with 25 percent followed by computer sciences, and 40 percent of documents were published by IEEE. Finally, the Latin American contributions to this field are outlined, verifying in detail the architectures for the proposed solutions with emphasis in sensors.
{"title":"Bibliometric study for CO2 measurement using IoT: Looking for the Latin American contributions","authors":"Juan-Daniel Páez-Carabajo, M. Huerta, D. Rivas-Lalaleo, G. Vayas, Roger Clotet-Martinez, J. Castillo-Velazquez","doi":"10.1109/CONCAPAN48024.2022.9997609","DOIUrl":"https://doi.org/10.1109/CONCAPAN48024.2022.9997609","url":null,"abstract":"In recent years, the number of deaths due to environmental pollution has increased. The main air pollutants are carbon monoxide, carbon dioxide, and sulfur dioxide. These are produced by the consumption of fossil fuels in vehicles, industrial activity, and agricultural practices, among others. Various technologies have been used to detect carbon dioxide (CO2), including the Internet of Things (IoT). However, no studies have been carried out to visualize the impact of IoT on CO2 monitoring and which countries are focused on minimizing emissions. This work shows a bibliometric study for CO2 environmental sensing using IoT. SCOPUS was the selected database, and PRISMA was the methodology used. The first search returned 13.207 documents written between 2013 and 2022, after filtering selected keywords, selecting only English articles, and abstract review we selected finally 79 documents for the measurement of CO2 using IoT. The results of analyzing them, show that the Asian countries produces more than the western countries, where India and Indonesia are leading. Also is interesting to note that the USA and Latin America produced the same quantity of documents, where the four countries contributing to Latin America are Brazil, Mexico, Peru, and Ecuador. The main area of knowledge covered by the documents was Engineering with 25 percent followed by computer sciences, and 40 percent of documents were published by IEEE. Finally, the Latin American contributions to this field are outlined, verifying in detail the architectures for the proposed solutions with emphasis in sensors.","PeriodicalId":138415,"journal":{"name":"2022 IEEE 40th Central America and Panama Convention (CONCAPAN)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131006439","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 : 2022-11-09DOI: 10.1109/CONCAPAN48024.2022.9997656
Christian Navarro-Castellanos, R. Orozco-Morales, Yakdiel Rodriguez-Gallo
In recent years new algorithms for image reconstruction in computed tomography have been proposed. The aim is to optimize Image Quality (IQ) and reduce the radiation dose applied to patients. This increase makes necessary the evaluation and standardization of objective quality metrics that allow to obtain a measure of existing differences in Hounsfield Unit (HU). This paper compares the performance of fifteen full reference (FR)-IQ metrics with the criteria of specialists. Images obtained from a phantom are modified, emulating the defects caused by factors such as noise, blurring and spatial resolution reduction due to the decrease of the projections used in the reconstruction. To measure the correlation between FR-IQ and the score assigned by the radiologists, Spearman’s nonparametric rank order correlation coefficient and Kendall’s rank order correlation coefficient were used. Cohen’s kappa was used to assess interobserver agreement. The Most Apparent Distortion (MAD), Structural Similarity Index (SSIM), Information Content Weighted SSIM (IW-SSIM), Feature Similarity Index Measure (FSIM), Information Content Weighted - Mean Square Error (IW-MSE), Information Content Weighted PSNR (IW-PSNR), Optimal Scale Selection Structural Similarity Index (OSS-SSIM), Riesz transform and Visual contrast sensitivity-based feature SIMilarity index (RVSIM), and Spectral Residual Based Similarity (SR-SIM) metrics were the best performing $(plt 0.001)$. The worst results were obtained by Noise Quality Measure (NQM) $(p=0.051)$ and Weighted Signal to Noise Ratio (WSNR) $(p=0.829)$. Results obtained show that a study using these objective quality metrics could dispense with expert judgment to evaluate the performance of the developed methods.
{"title":"Objective quality metrics for algorithm evaluation in Computed Tomography","authors":"Christian Navarro-Castellanos, R. Orozco-Morales, Yakdiel Rodriguez-Gallo","doi":"10.1109/CONCAPAN48024.2022.9997656","DOIUrl":"https://doi.org/10.1109/CONCAPAN48024.2022.9997656","url":null,"abstract":"In recent years new algorithms for image reconstruction in computed tomography have been proposed. The aim is to optimize Image Quality (IQ) and reduce the radiation dose applied to patients. This increase makes necessary the evaluation and standardization of objective quality metrics that allow to obtain a measure of existing differences in Hounsfield Unit (HU). This paper compares the performance of fifteen full reference (FR)-IQ metrics with the criteria of specialists. Images obtained from a phantom are modified, emulating the defects caused by factors such as noise, blurring and spatial resolution reduction due to the decrease of the projections used in the reconstruction. To measure the correlation between FR-IQ and the score assigned by the radiologists, Spearman’s nonparametric rank order correlation coefficient and Kendall’s rank order correlation coefficient were used. Cohen’s kappa was used to assess interobserver agreement. The Most Apparent Distortion (MAD), Structural Similarity Index (SSIM), Information Content Weighted SSIM (IW-SSIM), Feature Similarity Index Measure (FSIM), Information Content Weighted - Mean Square Error (IW-MSE), Information Content Weighted PSNR (IW-PSNR), Optimal Scale Selection Structural Similarity Index (OSS-SSIM), Riesz transform and Visual contrast sensitivity-based feature SIMilarity index (RVSIM), and Spectral Residual Based Similarity (SR-SIM) metrics were the best performing $(plt 0.001)$. The worst results were obtained by Noise Quality Measure (NQM) $(p=0.051)$ and Weighted Signal to Noise Ratio (WSNR) $(p=0.829)$. Results obtained show that a study using these objective quality metrics could dispense with expert judgment to evaluate the performance of the developed methods.","PeriodicalId":138415,"journal":{"name":"2022 IEEE 40th Central America and Panama Convention (CONCAPAN)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125419255","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：