Pub Date : 2024-03-20DOI: 10.1109/TLA.2024.10534300
Leandro Leysdian Oro Carralero;Edemar de Oliveira Prado;André Pires Nóbrega Tahim;Fabiano Fragoso Costa;José Renes Pinheiro
This paper presents a comprehensive methodology for the selection of power semiconductor devices in a standalone photovoltaic (PV)-battery system (SPBS) based on power loss analysis. The SPBS configuration is modeled analytically, and the waveforms for the system are obtained in a Hardware-In-the-Loop (HIL) and by simulation environment using Matlab. The study focuses on identifying the most cost-effective power semiconductor devices by assessing power loss at three distinct operating points. The algorithm evaluates losses in each component, facilitating the selection of optimal devices for enhanced system performance. The evaluation is performed for different operational modes, incorporating worst-case scenarios for current and voltage, providing a robust analysis of system behavior. By emphasizing the importance of power loss analysis in isolated PV systems, this research contributes to the advancement of energy efficiency in SPBS. The proposed methodology enables the identification of power semiconductor devices experiencing the highest losses, aiding in the selection of components that minimize overall losses and maximize energy utilization from PV panels and batteries.
{"title":"Selection of Power Semiconductor Devices for a Standalone System based on Power Loss Analysis","authors":"Leandro Leysdian Oro Carralero;Edemar de Oliveira Prado;André Pires Nóbrega Tahim;Fabiano Fragoso Costa;José Renes Pinheiro","doi":"10.1109/TLA.2024.10534300","DOIUrl":"https://doi.org/10.1109/TLA.2024.10534300","url":null,"abstract":"This paper presents a comprehensive methodology for the selection of power semiconductor devices in a standalone photovoltaic (PV)-battery system (SPBS) based on power loss analysis. The SPBS configuration is modeled analytically, and the waveforms for the system are obtained in a Hardware-In-the-Loop (HIL) and by simulation environment using Matlab. The study focuses on identifying the most cost-effective power semiconductor devices by assessing power loss at three distinct operating points. The algorithm evaluates losses in each component, facilitating the selection of optimal devices for enhanced system performance. The evaluation is performed for different operational modes, incorporating worst-case scenarios for current and voltage, providing a robust analysis of system behavior. By emphasizing the importance of power loss analysis in isolated PV systems, this research contributes to the advancement of energy efficiency in SPBS. The proposed methodology enables the identification of power semiconductor devices experiencing the highest losses, aiding in the selection of components that minimize overall losses and maximize energy utilization from PV panels and batteries.","PeriodicalId":55024,"journal":{"name":"IEEE Latin America Transactions","volume":"22 6","pages":"519-527"},"PeriodicalIF":1.3,"publicationDate":"2024-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10534300","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141073599","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-20DOI: 10.1109/TLA.2024.10534303
{"title":"Table of Contents June 2024","authors":"","doi":"10.1109/TLA.2024.10534303","DOIUrl":"https://doi.org/10.1109/TLA.2024.10534303","url":null,"abstract":"","PeriodicalId":55024,"journal":{"name":"IEEE Latin America Transactions","volume":"22 6","pages":"442-442"},"PeriodicalIF":1.3,"publicationDate":"2024-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10534303","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141073635","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-20DOI: 10.1109/TLA.2024.10534305
Ademir Luiz do Prado;Waldemar Volanski;Liana Signorini;Mauren Isfer Anghebem;Glaucio Valdameri;Vivian Rotuno Moure;Fabiane Gomes de Moraes Rego;Geraldo Picheth
Coronavirus disease 2019 (COVID-19) is a respiratory infection caused by the Severe Acute Respiratory Syndrome Coronavirus (SARS-CoV-2). In the current scenario of COVID-19, more than 6 million people have died worldwide, and near seven hundred thousand only in Brazil alone. The objective this work is designer a database using MySQL to develop a system for geolocating COVID-19 affected individuals and their close contacts. Patient addresses registered in the laboratory database were used to search for coordinate (latitude and longitude) using the OpenStreetMap Application Programming Interface. The user interface was developed in PHP using HTML, JavaScript, CSS, and AJAX. A dashboard displaying the geolocation information of selected patients was presented on the screen for public health agents. A system called G-CoV.2 was developed. The makers produced by G-CoV.2 had 100% accuracy when manually compared with the same patient address records. G-CoV.2 can be used as a computational system to aid health managers in identifying regions with the most people infected by COVID-19 or other pathological processes. The submitted work can meet the third goal of sustainable development of the United Nations for Latin America, ensuring a healthy life and thus promoting well-being for all people, at all ages. One of the ways is through the monitoring of COVID-19 and other pathologies as a preventive measure, applying the system developed G-CoV.2 that was the subject of the writing of the article, which may reduce the mortality rate at all ages, with the premise of ending epidemics of serious and communicable diseases, directing health managers to increase investment in health in critical areas, as well as creating actions in favor of prevention and promotion of the population's health.
{"title":"G-CoV.2: A computational system for geolocation of patients diagnosed with COVID-19","authors":"Ademir Luiz do Prado;Waldemar Volanski;Liana Signorini;Mauren Isfer Anghebem;Glaucio Valdameri;Vivian Rotuno Moure;Fabiane Gomes de Moraes Rego;Geraldo Picheth","doi":"10.1109/TLA.2024.10534305","DOIUrl":"https://doi.org/10.1109/TLA.2024.10534305","url":null,"abstract":"Coronavirus disease 2019 (COVID-19) is a respiratory infection caused by the Severe Acute Respiratory Syndrome Coronavirus (SARS-CoV-2). In the current scenario of COVID-19, more than 6 million people have died worldwide, and near seven hundred thousand only in Brazil alone. The objective this work is designer a database using MySQL to develop a system for geolocating COVID-19 affected individuals and their close contacts. Patient addresses registered in the laboratory database were used to search for coordinate (latitude and longitude) using the OpenStreetMap Application Programming Interface. The user interface was developed in PHP using HTML, JavaScript, CSS, and AJAX. A dashboard displaying the geolocation information of selected patients was presented on the screen for public health agents. A system called G-CoV.2 was developed. The makers produced by G-CoV.2 had 100% accuracy when manually compared with the same patient address records. G-CoV.2 can be used as a computational system to aid health managers in identifying regions with the most people infected by COVID-19 or other pathological processes. The submitted work can meet the third goal of sustainable development of the United Nations for Latin America, ensuring a healthy life and thus promoting well-being for all people, at all ages. One of the ways is through the monitoring of COVID-19 and other pathologies as a preventive measure, applying the system developed G-CoV.2 that was the subject of the writing of the article, which may reduce the mortality rate at all ages, with the premise of ending epidemics of serious and communicable diseases, directing health managers to increase investment in health in critical areas, as well as creating actions in favor of prevention and promotion of the population's health.","PeriodicalId":55024,"journal":{"name":"IEEE Latin America Transactions","volume":"22 6","pages":"460-467"},"PeriodicalIF":1.3,"publicationDate":"2024-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10534305","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141073595","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-20DOI: 10.1109/TLA.2024.10534307
Alejandro Lopez-Telgie;Mario Quappe-Gutierrez;Walter Abrahão Dos Santos
This study presents an automated tool designed for the classification and analysis of Earth Observation CubeSats, with focus in the low Earth orbit (LEO) region (200-1,000 km altitude). Leveraging an integration of data from different reputable databases, the tool provides a detailed data repository which facilitates analysis of CubeSat deployment trends, configurations, and operational orbits, aiding in mission design. A key finding from our analysis is the pronounced concentration of CubeSats in certain LEO regions: Sun-Synchronus and ISS, with the United States as a leading contributor in CubeSat deployments. Moreover, the tool offers a comprehensive estimation of lifecycle costs associated with CubeSat missions, highlighting a trend of decreasing costs among major CubeSat developers such as Planet and Spire. This cost reduction trend is attributed to economies of scale, implementation of ground segment infrastructure, and vertical integration in the development of the satellites. By providing a detailed dataset, and classification of CubeSats, along with an analysis of cost trends, this research contributes valuable insights for the planning and cost optimization of future space missions. The findings underscore the growing commercial viability and strategic importance of CubeSats in the evolving landscape of Earth observation and new space.
{"title":"An Automated Data-Gathering Tool for Earth Observation CubeSats Classification","authors":"Alejandro Lopez-Telgie;Mario Quappe-Gutierrez;Walter Abrahão Dos Santos","doi":"10.1109/TLA.2024.10534307","DOIUrl":"https://doi.org/10.1109/TLA.2024.10534307","url":null,"abstract":"This study presents an automated tool designed for the classification and analysis of Earth Observation CubeSats, with focus in the low Earth orbit (LEO) region (200-1,000 km altitude). Leveraging an integration of data from different reputable databases, the tool provides a detailed data repository which facilitates analysis of CubeSat deployment trends, configurations, and operational orbits, aiding in mission design. A key finding from our analysis is the pronounced concentration of CubeSats in certain LEO regions: Sun-Synchronus and ISS, with the United States as a leading contributor in CubeSat deployments. Moreover, the tool offers a comprehensive estimation of lifecycle costs associated with CubeSat missions, highlighting a trend of decreasing costs among major CubeSat developers such as Planet and Spire. This cost reduction trend is attributed to economies of scale, implementation of ground segment infrastructure, and vertical integration in the development of the satellites. By providing a detailed dataset, and classification of CubeSats, along with an analysis of cost trends, this research contributes valuable insights for the planning and cost optimization of future space missions. The findings underscore the growing commercial viability and strategic importance of CubeSats in the evolving landscape of Earth observation and new space.","PeriodicalId":55024,"journal":{"name":"IEEE Latin America Transactions","volume":"22 6","pages":"451-459"},"PeriodicalIF":1.3,"publicationDate":"2024-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10534307","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141073636","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-20DOI: 10.1109/TLA.2024.10534308
Juan Sebastian Arboleda Arroyave;Jorge Wilson González Sanchez;Idi Amin Isaac Millan
This paper addresses a proposal for the optimization and automation of the methodology of selectivity analysis in protection relays by fault sweeps, to improve selectivity and evaluate the operation times and coordination margins in a complex network composed by a large amount of overcurrent units. Through the operating times of the protection devices, it can be quickly identified the lack of coordination that may occur in the relays of the network for several topological conditions. The coordination times are obtained by a set of injected failures in the assets delimited by the scope of the selectivity study, and through an automatic systemic analysis it is sought to generate a diagnosis of the most critical points in which there is no correct selectivity within protection functions. The automation strategy of this work is designed and evaluated in DIgSILENT PowerFactory and Python computational tools. Through the scripting and automation module, a Python script is executed in the PowerFactory environment, and in this way the protection relays and the measurement transformers are modeled by assigning their respective settings and directionality. Finally, an analysis is carried out with criteria of the good setting of protection devices created by experts in the field, and a calculation file is generated with the optimized operating times of the protection devices and an analysis of selectivity between the overcurrent functions of the system.
{"title":"Automation of Methodology for Analysis of Overcurrent Protection Functions in Electrical Power Systems","authors":"Juan Sebastian Arboleda Arroyave;Jorge Wilson González Sanchez;Idi Amin Isaac Millan","doi":"10.1109/TLA.2024.10534308","DOIUrl":"https://doi.org/10.1109/TLA.2024.10534308","url":null,"abstract":"This paper addresses a proposal for the optimization and automation of the methodology of selectivity analysis in protection relays by fault sweeps, to improve selectivity and evaluate the operation times and coordination margins in a complex network composed by a large amount of overcurrent units. Through the operating times of the protection devices, it can be quickly identified the lack of coordination that may occur in the relays of the network for several topological conditions. The coordination times are obtained by a set of injected failures in the assets delimited by the scope of the selectivity study, and through an automatic systemic analysis it is sought to generate a diagnosis of the most critical points in which there is no correct selectivity within protection functions. The automation strategy of this work is designed and evaluated in DIgSILENT PowerFactory and Python computational tools. Through the scripting and automation module, a Python script is executed in the PowerFactory environment, and in this way the protection relays and the measurement transformers are modeled by assigning their respective settings and directionality. Finally, an analysis is carried out with criteria of the good setting of protection devices created by experts in the field, and a calculation file is generated with the optimized operating times of the protection devices and an analysis of selectivity between the overcurrent functions of the system.","PeriodicalId":55024,"journal":{"name":"IEEE Latin America Transactions","volume":"22 6","pages":"494-501"},"PeriodicalIF":1.3,"publicationDate":"2024-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10534308","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141073632","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-20DOI: 10.1109/TLA.2024.10534301
Victor Flores;Nicolas Henríquez;Edgardo Ortiz;Rafael Martinez;Claudio Leiva
In the copper mining industry, Data Science (DS) techniques and Machine Learning (ML) methods are contributing to improve the prediction of results in industrial processes. In this paper, an experience of applying both DS techniques and a ML algorithm, using historical data from the flotation process is described. These data were collected using a prototype of flotation equipment developed at the Universidad Catolica del Norte, in Antofagasta, Chile. To achieve the result an Extraction, Transformation and Load (ETL) process was made. Also, for both, improving the understanding of domain dynamics and selecting the most relevant predictive variables in the flotation process, a Random Forest (FR) model was developed. The combination of these previous results made it possible to generate recommendations on the management of predictor variables to improve copper recovery in the context of the flotation equipment prototype. In this document, the methodological details are presented, and the process used to obtain the aforementioned results is described. As progress was made through 2 iterations, the quality of the results obtained with the predictive model, generated by RF, was improving. At the end of the process, an accuracy of 94,44% was achieved, with an accuracy in each of the classes greater than 90%. These results demonstrate the effectiveness and outstanding performance of the predictive model. These values are highly competitive when compared to those obtained in other similar studies in the context of Industry 4.0.
{"title":"Random forest for generating recommendations for predicting copper recovery by flotation","authors":"Victor Flores;Nicolas Henríquez;Edgardo Ortiz;Rafael Martinez;Claudio Leiva","doi":"10.1109/TLA.2024.10534301","DOIUrl":"https://doi.org/10.1109/TLA.2024.10534301","url":null,"abstract":"In the copper mining industry, Data Science (DS) techniques and Machine Learning (ML) methods are contributing to improve the prediction of results in industrial processes. In this paper, an experience of applying both DS techniques and a ML algorithm, using historical data from the flotation process is described. These data were collected using a prototype of flotation equipment developed at the Universidad Catolica del Norte, in Antofagasta, Chile. To achieve the result an Extraction, Transformation and Load (ETL) process was made. Also, for both, improving the understanding of domain dynamics and selecting the most relevant predictive variables in the flotation process, a Random Forest (FR) model was developed. The combination of these previous results made it possible to generate recommendations on the management of predictor variables to improve copper recovery in the context of the flotation equipment prototype. In this document, the methodological details are presented, and the process used to obtain the aforementioned results is described. As progress was made through 2 iterations, the quality of the results obtained with the predictive model, generated by RF, was improving. At the end of the process, an accuracy of 94,44% was achieved, with an accuracy in each of the classes greater than 90%. These results demonstrate the effectiveness and outstanding performance of the predictive model. These values are highly competitive when compared to those obtained in other similar studies in the context of Industry 4.0.","PeriodicalId":55024,"journal":{"name":"IEEE Latin America Transactions","volume":"22 6","pages":"443-450"},"PeriodicalIF":1.3,"publicationDate":"2024-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10534301","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141073598","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-20DOI: 10.1109/TLA.2024.10534304
Jhandry R. Lapo;Oscar M. Cumbicus-Pineda
Waste management in the recycling business is a time-consuming and labor-intensive process. In this context, the need to improve accuracy and reduce the time associated with this process is highlighted. In order to improve the classification of recyclable solid waste and streamline the waste management process, the creation of a convolutional neural network (CNN) model using PyTorch was proposed. The MLOps methodology was implemented in the development of the proposed model. In the first phase, an interview was conducted to analyze the waste sorting process in the company GIRA. In the second phase, the Taco Trash Dataset was reclassified, a CNN architecture based on RetinaNet was designed and the model was trained with hyper parameters based on related works. The third phase, the model was evaluated by testing and A/B testing. The model demonstrated high accuracy in waste detection and classification. It successfully identified materials such as paper, cardboard, PET bottles, hard plastic containers, flexible plastics, cans, glass, Tetra Pak containers, Flex foam and PET bottle caps. The loss was minimal, reaching 0.02120%, equivalent to 97% accuracy, and 80% accuracy in a real environment based on the Technology Acceptance Model (TAM). It is concluded that the implementation of a sorting and waste detection model optimizes the time and improves the accuracy of the sorting process.
{"title":"Detection of recyclable solid waste using convolutional neural networks and PyTorch","authors":"Jhandry R. Lapo;Oscar M. Cumbicus-Pineda","doi":"10.1109/TLA.2024.10534304","DOIUrl":"https://doi.org/10.1109/TLA.2024.10534304","url":null,"abstract":"Waste management in the recycling business is a time-consuming and labor-intensive process. In this context, the need to improve accuracy and reduce the time associated with this process is highlighted. In order to improve the classification of recyclable solid waste and streamline the waste management process, the creation of a convolutional neural network (CNN) model using PyTorch was proposed. The MLOps methodology was implemented in the development of the proposed model. In the first phase, an interview was conducted to analyze the waste sorting process in the company GIRA. In the second phase, the Taco Trash Dataset was reclassified, a CNN architecture based on RetinaNet was designed and the model was trained with hyper parameters based on related works. The third phase, the model was evaluated by testing and A/B testing. The model demonstrated high accuracy in waste detection and classification. It successfully identified materials such as paper, cardboard, PET bottles, hard plastic containers, flexible plastics, cans, glass, Tetra Pak containers, Flex foam and PET bottle caps. The loss was minimal, reaching 0.02120%, equivalent to 97% accuracy, and 80% accuracy in a real environment based on the Technology Acceptance Model (TAM). It is concluded that the implementation of a sorting and waste detection model optimizes the time and improves the accuracy of the sorting process.","PeriodicalId":55024,"journal":{"name":"IEEE Latin America Transactions","volume":"22 6","pages":"475-483"},"PeriodicalIF":1.3,"publicationDate":"2024-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10534304","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141073563","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-20DOI: 10.1109/TLA.2024.10534309
Leonardo Daniel Estrada Moreno;Rosa María Valdovinos Rosas;Lourdes Loza Hernandez;Roberto Alejo
The global emergency of COVID-19 caused by the SARS-CoV-2 virus at the end of 2019, was without a doubt a critical and historical point for society in general; for instance, the effective development of vaccines, as well as the efficient distribution of them; They were an unprecedented challenge to slow down the spread or mitigate its impact on societies around the world. This article specifies three bio-inspired metaheuristic algorithms (genetic algorithm, particle swarm optimization algorithm, and artificial bee colony algorithm) that were used in the context of the capacitated vehicle routing problem to generate vaccine distribution routes, specifically, COVID-19 vaccine for over 18 years old the first and the second doses applications in Mexico, particularly in the State of Mexico. The quality of the solutions obtained by these algorithms is compared, as a result of the performance of the particle swarm optimization (PSO) algorithm being superior in solution quality.
{"title":"COVID-19 Vaccines distribution routes with bioinspired metaheuristic algorithms: Resoluteness","authors":"Leonardo Daniel Estrada Moreno;Rosa María Valdovinos Rosas;Lourdes Loza Hernandez;Roberto Alejo","doi":"10.1109/TLA.2024.10534309","DOIUrl":"https://doi.org/10.1109/TLA.2024.10534309","url":null,"abstract":"The global emergency of COVID-19 caused by the SARS-CoV-2 virus at the end of 2019, was without a doubt a critical and historical point for society in general; for instance, the effective development of vaccines, as well as the efficient distribution of them; They were an unprecedented challenge to slow down the spread or mitigate its impact on societies around the world. This article specifies three bio-inspired metaheuristic algorithms (genetic algorithm, particle swarm optimization algorithm, and artificial bee colony algorithm) that were used in the context of the capacitated vehicle routing problem to generate vaccine distribution routes, specifically, COVID-19 vaccine for over 18 years old the first and the second doses applications in Mexico, particularly in the State of Mexico. The quality of the solutions obtained by these algorithms is compared, as a result of the performance of the particle swarm optimization (PSO) algorithm being superior in solution quality.","PeriodicalId":55024,"journal":{"name":"IEEE Latin America Transactions","volume":"22 6","pages":"484-493"},"PeriodicalIF":1.3,"publicationDate":"2024-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10534309","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141073637","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-20DOI: 10.1109/TLA.2024.10534306
Ingo Pastl;Danilo Araújo
Netheradays planning of metropolitan areas considers to improve quality of life of their inhabitants and urbanmobility is one of the main concerns. Studies point out that investments in public transportation and other modes are aimedat the overall improvement of mobility. However, there is a gap in proper tools for optimizing public transport networks.In fact, network optimization is an NP-Hard problem and there are usually many conflicting objectives that need to beoptimized simultaneously. This paper proposes the use of manyobjective evolutionary algorithms to address the problem ofpublic transport networks optimization, focusing on metropolitan bus lines. The proposal consists in optimizing the position of bus stops and consequently obtaining new routes that pass through these stops in order to minimize the average travel time, the time spent between origin / destination and the variance of distance between the stops. To evaluate our proposal, a simulator was used to simulate the behavior of different passenger profiles in an urban area and the results were compared between the lines obtained by the optimization process and existing bus lines in the city of Sao Paulo. According to our results, optimized bus routes have mean travel time 22% less than the existing route and the time spent between origin/destination has decreased up to 18%.
{"title":"Optimization of Public Transport Networks by Considering Alternative Positions for Network Stations","authors":"Ingo Pastl;Danilo Araújo","doi":"10.1109/TLA.2024.10534306","DOIUrl":"https://doi.org/10.1109/TLA.2024.10534306","url":null,"abstract":"Netheradays planning of metropolitan areas considers to improve quality of life of their inhabitants and urbanmobility is one of the main concerns. Studies point out that investments in public transportation and other modes are aimedat the overall improvement of mobility. However, there is a gap in proper tools for optimizing public transport networks.In fact, network optimization is an NP-Hard problem and there are usually many conflicting objectives that need to beoptimized simultaneously. This paper proposes the use of manyobjective evolutionary algorithms to address the problem ofpublic transport networks optimization, focusing on metropolitan bus lines. The proposal consists in optimizing the position of bus stops and consequently obtaining new routes that pass through these stops in order to minimize the average travel time, the time spent between origin / destination and the variance of distance between the stops. To evaluate our proposal, a simulator was used to simulate the behavior of different passenger profiles in an urban area and the results were compared between the lines obtained by the optimization process and existing bus lines in the city of Sao Paulo. According to our results, optimized bus routes have mean travel time 22% less than the existing route and the time spent between origin/destination has decreased up to 18%.","PeriodicalId":55024,"journal":{"name":"IEEE Latin America Transactions","volume":"22 6","pages":"468-474"},"PeriodicalIF":1.3,"publicationDate":"2024-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10534306","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141073596","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-18DOI: 10.1109/TLA.2024.10472963
ben liang;Jia Su;Kangkang Feng;Yongqiang Zhang;Weimin Hou
Due to unfavorable factors such as cluttered spatial and temporal distribution of multiple types of targets, occlusion of background objects of different shapes, and blurring of feature information by inclement weather, the low detection accuracy in complex traffic scenarios has been a troubling issue. Regarding the above-mentioned issues, the paper proposes a lightweight real-time detection network to augment multi-scale object perception capabilities in traffic scenarios while ensuring real-time detection speed. First, we construct a novel global feature extraction (GFE) structure by cascading orthogonal band convolution kernels that capture the global dependencies between pixels to improve feature discrimination. Then, an intra-layer multi-scale feature interaction (IMFI) module is proposed to reinforce the effective reuse and multi-level transfer of salient features. In addition, we build a multi-branch scale-aware aggregation (MSA) module that captures abundant context-associated features to improve the target decision-making capability and the self-adaptive capability of the model when dealing with diverse object scales. Experimental results demonstrate that the proposed approach attains a significant improvement of 5.6 percentage points in AP50 with fewer parameters and computational power compared to the baseline model, with an improved FPS of 73. Furthermore, our approach strikes the optimal speed-accuracy balance when compared against other excellent object detection algorithms of the same magnitude.
{"title":"Lightweight Real-Time Object Detection via Enhanced Global Perception and Intra-Layer Interaction for Complex Traffic Scenarios","authors":"ben liang;Jia Su;Kangkang Feng;Yongqiang Zhang;Weimin Hou","doi":"10.1109/TLA.2024.10472963","DOIUrl":"https://doi.org/10.1109/TLA.2024.10472963","url":null,"abstract":"Due to unfavorable factors such as cluttered spatial and temporal distribution of multiple types of targets, occlusion of background objects of different shapes, and blurring of feature information by inclement weather, the low detection accuracy in complex traffic scenarios has been a troubling issue. Regarding the above-mentioned issues, the paper proposes a lightweight real-time detection network to augment multi-scale object perception capabilities in traffic scenarios while ensuring real-time detection speed. First, we construct a novel global feature extraction (GFE) structure by cascading orthogonal band convolution kernels that capture the global dependencies between pixels to improve feature discrimination. Then, an intra-layer multi-scale feature interaction (IMFI) module is proposed to reinforce the effective reuse and multi-level transfer of salient features. In addition, we build a multi-branch scale-aware aggregation (MSA) module that captures abundant context-associated features to improve the target decision-making capability and the self-adaptive capability of the model when dealing with diverse object scales. Experimental results demonstrate that the proposed approach attains a significant improvement of 5.6 percentage points in AP50 with fewer parameters and computational power compared to the baseline model, with an improved FPS of 73. Furthermore, our approach strikes the optimal speed-accuracy balance when compared against other excellent object detection algorithms of the same magnitude.","PeriodicalId":55024,"journal":{"name":"IEEE Latin America Transactions","volume":"22 4","pages":"312-320"},"PeriodicalIF":1.3,"publicationDate":"2024-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10472963","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140161234","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","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：