Pub Date : 2020-07-01DOI: 10.1109/YEF-ECE49388.2020.9171814
Mohamed Tanta, Luis A. M. Barros, J. G. Pinto, A. Martins, J. Afonso
The Modular Multilevel Converter (MMC) has become the most preferable multilevel converter topology for medium and high-power systems, due to the MMC’s high reliability and redundancy. This paper focuses on MMC applications in electrified railway traction grids, namely, applications of rail static frequency converters and rail power conditioners. These applications provide a higher railway traction grid capacity and improve the power quality of the three-phase power grid. Simulation results of a case study are presented to show the features when using the MMC in electrified railway grids.
{"title":"Modular Multilevel Converter in Electrified Railway Systems: Applications of Rail Static Frequency Converters and Rail Power Conditioners","authors":"Mohamed Tanta, Luis A. M. Barros, J. G. Pinto, A. Martins, J. Afonso","doi":"10.1109/YEF-ECE49388.2020.9171814","DOIUrl":"https://doi.org/10.1109/YEF-ECE49388.2020.9171814","url":null,"abstract":"The Modular Multilevel Converter (MMC) has become the most preferable multilevel converter topology for medium and high-power systems, due to the MMC’s high reliability and redundancy. This paper focuses on MMC applications in electrified railway traction grids, namely, applications of rail static frequency converters and rail power conditioners. These applications provide a higher railway traction grid capacity and improve the power quality of the three-phase power grid. Simulation results of a case study are presented to show the features when using the MMC in electrified railway grids.","PeriodicalId":331206,"journal":{"name":"2020 International Young Engineers Forum (YEF-ECE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123713472","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 : 2020-07-01DOI: 10.1109/YEF-ECE49388.2020.9171807
Xavier Godinho, Hermano Bernardo, F. Oliveira, J. Sousa
Forecasting heating and cooling energy demand in buildings plays a critical role in supporting building management and operation. Thus, analysing the energy consumption pattern of a building could help in the design of potential energy savings and also in operation fault detection, while contributing to provide proper indoor environmental conditions to the building’s occupants.This paper aims at presenting the main results of a study consisting in forecasting the hourly heating and cooling demand of an office building located in Lisbon, Portugal, using machine learning models and analysing the influence of exogenous variables on those predictions. In order to forecast the heating and cooling demand of the considered building, some traditional models, such as linear and polynomial regression, were considered, as well as artificial neural networks and support vector regression, oriented to machine learning. The input parameters considered in the development of those models were the hourly heating and cooling energy historical records, the occupancy, solar gains through glazing and the outside dry-bulb temperature.The models developed were validated using the mean absolute error (MAE) and the root mean squared error (RMSE), used to compare the values obtained from machine learning models with data obtained through a building energy simulation performed on an adequately calibrated model.The proposed exploratory analysis is integrated in a research project focused on applying machine learning methodologies to support energy forecasting in buildings. Hence, the research line proposed in this article corresponds to a preliminary project task associated with feature selection/extraction and evaluation of potential use of machine learning methods.
{"title":"Forecasting Heating and Cooling Energy Demand in an Office Building using Machine Learning Methods","authors":"Xavier Godinho, Hermano Bernardo, F. Oliveira, J. Sousa","doi":"10.1109/YEF-ECE49388.2020.9171807","DOIUrl":"https://doi.org/10.1109/YEF-ECE49388.2020.9171807","url":null,"abstract":"Forecasting heating and cooling energy demand in buildings plays a critical role in supporting building management and operation. Thus, analysing the energy consumption pattern of a building could help in the design of potential energy savings and also in operation fault detection, while contributing to provide proper indoor environmental conditions to the building’s occupants.This paper aims at presenting the main results of a study consisting in forecasting the hourly heating and cooling demand of an office building located in Lisbon, Portugal, using machine learning models and analysing the influence of exogenous variables on those predictions. In order to forecast the heating and cooling demand of the considered building, some traditional models, such as linear and polynomial regression, were considered, as well as artificial neural networks and support vector regression, oriented to machine learning. The input parameters considered in the development of those models were the hourly heating and cooling energy historical records, the occupancy, solar gains through glazing and the outside dry-bulb temperature.The models developed were validated using the mean absolute error (MAE) and the root mean squared error (RMSE), used to compare the values obtained from machine learning models with data obtained through a building energy simulation performed on an adequately calibrated model.The proposed exploratory analysis is integrated in a research project focused on applying machine learning methodologies to support energy forecasting in buildings. Hence, the research line proposed in this article corresponds to a preliminary project task associated with feature selection/extraction and evaluation of potential use of machine learning methods.","PeriodicalId":331206,"journal":{"name":"2020 International Young Engineers Forum (YEF-ECE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129463758","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 : 2020-07-01DOI: 10.1109/YEF-ECE49388.2020.9171811
Carlos García, Rui Tavares, A. Mora, J. Fonseca, Henrique Oliveira, L. Oliveira
Land Use/Land Cover classification algorithms have been extensively studied and implemented in Central Processing Units (CPU) and Graphics Processing Units (GPU) based platforms. In this work we present a detailed study of Land Use/Land Cover classification performance in terms of accuracy and computational speed on an Field-Programmable Gate Array (FPGA). Two classification algorithms, Decision Tree and Minimum Distance, are studied to distinguish two categories (i.e. water or no-water). Both algorithms will be performed on FPGA and CPU to confirm the advantages of a parallel approach. Due to the pre-processing techniques used, both implementation on FPGA and CPU shared the same accuracy results, only differing in processing time. The results showed 98.97Decision Tree, and a speed up factor of 4 times FPGA over CPU for the Minimum Distance Classifier. The main goal of this case study is to generate maps that help firefighters in wildfires to locate water areas to refill water tanks. Final results conclude that the output of the classifier can better identify water resources than the ground truth Land Use/Land Cover map (COS) provided by Direção Geral do Território (DGT) Portugal.
{"title":"FPGA-based Satellite Image Classification for Water Bodies Detection","authors":"Carlos García, Rui Tavares, A. Mora, J. Fonseca, Henrique Oliveira, L. Oliveira","doi":"10.1109/YEF-ECE49388.2020.9171811","DOIUrl":"https://doi.org/10.1109/YEF-ECE49388.2020.9171811","url":null,"abstract":"Land Use/Land Cover classification algorithms have been extensively studied and implemented in Central Processing Units (CPU) and Graphics Processing Units (GPU) based platforms. In this work we present a detailed study of Land Use/Land Cover classification performance in terms of accuracy and computational speed on an Field-Programmable Gate Array (FPGA). Two classification algorithms, Decision Tree and Minimum Distance, are studied to distinguish two categories (i.e. water or no-water). Both algorithms will be performed on FPGA and CPU to confirm the advantages of a parallel approach. Due to the pre-processing techniques used, both implementation on FPGA and CPU shared the same accuracy results, only differing in processing time. The results showed 98.97Decision Tree, and a speed up factor of 4 times FPGA over CPU for the Minimum Distance Classifier. The main goal of this case study is to generate maps that help firefighters in wildfires to locate water areas to refill water tanks. Final results conclude that the output of the classifier can better identify water resources than the ground truth Land Use/Land Cover map (COS) provided by Direção Geral do Território (DGT) Portugal.","PeriodicalId":331206,"journal":{"name":"2020 International Young Engineers Forum (YEF-ECE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124745517","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 : 2020-07-01DOI: 10.1109/YEF-ECE49388.2020.9171812
Christoph Fischer, Maximilian Berndt, Dennis Krummacker, J. Zemitis, Daniel Fraunholz, H. Schotten
Networks of industrial plants are engineered manually as of today. This covers the configuration of a network as well as the cabling and the design of the network topology itself. Hereby, usually multiple subnetworks using different transmission technologies are involved. In our proposed solution the process of deriving a feasible network topology from communication demands for a given set of interacting distributed applications is automated. This describes a Constraint Satisfaction Problem (CSP) of which this paper approaches a solution with a Genetic Algorithm (GA). The strategy is generating an own search space for a solution, extending it iteratively based on knowledge ascertained in previous iterations and finally selecting the best solution. Presented is the description of an algorithm, an encoding format for network topologies as well as a methodology for evaluating solutions. This evaluation includes Key Performance Indicators and how to describe and measure them, e.g. to calculate a fitness score based on the number of hops. Additionally, an explicit feasibility check is introduced to prevent the selection of solutions, that might have a high fitness score but are unable to serve the use case requirements, e.g. due to an incomplete interconnection graph. Finally, an evaluation of the developed algorithm in terms of quality of a found solution and performance of execution is shown.
{"title":"Industrial Network Topology Generation with Genetic Algorithms","authors":"Christoph Fischer, Maximilian Berndt, Dennis Krummacker, J. Zemitis, Daniel Fraunholz, H. Schotten","doi":"10.1109/YEF-ECE49388.2020.9171812","DOIUrl":"https://doi.org/10.1109/YEF-ECE49388.2020.9171812","url":null,"abstract":"Networks of industrial plants are engineered manually as of today. This covers the configuration of a network as well as the cabling and the design of the network topology itself. Hereby, usually multiple subnetworks using different transmission technologies are involved. In our proposed solution the process of deriving a feasible network topology from communication demands for a given set of interacting distributed applications is automated. This describes a Constraint Satisfaction Problem (CSP) of which this paper approaches a solution with a Genetic Algorithm (GA). The strategy is generating an own search space for a solution, extending it iteratively based on knowledge ascertained in previous iterations and finally selecting the best solution. Presented is the description of an algorithm, an encoding format for network topologies as well as a methodology for evaluating solutions. This evaluation includes Key Performance Indicators and how to describe and measure them, e.g. to calculate a fitness score based on the number of hops. Additionally, an explicit feasibility check is introduced to prevent the selection of solutions, that might have a high fitness score but are unable to serve the use case requirements, e.g. due to an incomplete interconnection graph. Finally, an evaluation of the developed algorithm in terms of quality of a found solution and performance of execution is shown.","PeriodicalId":331206,"journal":{"name":"2020 International Young Engineers Forum (YEF-ECE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129153733","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 : 2020-07-01DOI: 10.1109/YEF-ECE49388.2020.9171809
Vítor Monteiro, T. Sousa, J. Afonso, Vítor Monteiro, J. Afonso
The paradigm of smart grids has been continuously addressing new challenges in terms of power electronics converters, for instance, to deal with technologies like renewables, electric mobility, energy storage, and hybrid power grids. Allied with this context, a novel topology of modular multilevel bidirectional (MMB) non-isolated dc-dc converter is proposed in this paper. Taking into consideration the nature of the proposed MMB dc-dc converter, it is appropriated to operate as back-end converter linked to front-end ac-dc converters based on cascade structures, i.e., with more than one dc-link. As unique features, the proposed MMB dc-dc converter can operate with five-voltage levels, allowing to reduce the voltage stress in each semiconductor, and it is controlled based on the interleaved principle of operation, although it is not an interleaved converter. A dedicated pulse-width modulation, as well as voltage and current control strategies, are proposed and clearly explained along the paper. The claimed distinctive features of the proposed MMB dc-dc converter are supported by analytic description and by computer simulation validation, considering steady-state and transient-state operations in relevant conditions of the dc interfaces.
{"title":"A Novel Topology of Modular Multilevel Bidirectional Non-Isolated dc-dc Converter","authors":"Vítor Monteiro, T. Sousa, J. Afonso, Vítor Monteiro, J. Afonso","doi":"10.1109/YEF-ECE49388.2020.9171809","DOIUrl":"https://doi.org/10.1109/YEF-ECE49388.2020.9171809","url":null,"abstract":"The paradigm of smart grids has been continuously addressing new challenges in terms of power electronics converters, for instance, to deal with technologies like renewables, electric mobility, energy storage, and hybrid power grids. Allied with this context, a novel topology of modular multilevel bidirectional (MMB) non-isolated dc-dc converter is proposed in this paper. Taking into consideration the nature of the proposed MMB dc-dc converter, it is appropriated to operate as back-end converter linked to front-end ac-dc converters based on cascade structures, i.e., with more than one dc-link. As unique features, the proposed MMB dc-dc converter can operate with five-voltage levels, allowing to reduce the voltage stress in each semiconductor, and it is controlled based on the interleaved principle of operation, although it is not an interleaved converter. A dedicated pulse-width modulation, as well as voltage and current control strategies, are proposed and clearly explained along the paper. The claimed distinctive features of the proposed MMB dc-dc converter are supported by analytic description and by computer simulation validation, considering steady-state and transient-state operations in relevant conditions of the dc interfaces.","PeriodicalId":331206,"journal":{"name":"2020 International Young Engineers Forum (YEF-ECE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129791395","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 : 2020-07-01DOI: 10.1109/YEF-ECE49388.2020.9171815
B. Capitão, J. Lagarto, R. Pereira, P. Almeida, P. Fonte
Demand response actions allow to support an adequate domestic load management, considering consumer preferences. In order to develop a hardware tool based on Arduino used to support consumers load management and decisions, an optimization mathematical model is developed and detailed in this paper. In the developed mathematical model, household appliances and electric vehicle are considered as controllable loads. The existence of a storage system based on batteries is considered as well as energy provided by the power grid and solar panel self-generation. The model is implemented using optimization software GAMS (General Algebraic Modeling System) as a Mixed Integer Programming (MIP) problem, where its outputs are used as inputs applied to the hardware used as interface between the optimization mathematical model and controllable loads.
{"title":"Demand Response Model for Hardware Implementation","authors":"B. Capitão, J. Lagarto, R. Pereira, P. Almeida, P. Fonte","doi":"10.1109/YEF-ECE49388.2020.9171815","DOIUrl":"https://doi.org/10.1109/YEF-ECE49388.2020.9171815","url":null,"abstract":"Demand response actions allow to support an adequate domestic load management, considering consumer preferences. In order to develop a hardware tool based on Arduino used to support consumers load management and decisions, an optimization mathematical model is developed and detailed in this paper. In the developed mathematical model, household appliances and electric vehicle are considered as controllable loads. The existence of a storage system based on batteries is considered as well as energy provided by the power grid and solar panel self-generation. The model is implemented using optimization software GAMS (General Algebraic Modeling System) as a Mixed Integer Programming (MIP) problem, where its outputs are used as inputs applied to the hardware used as interface between the optimization mathematical model and controllable loads.","PeriodicalId":331206,"journal":{"name":"2020 International Young Engineers Forum (YEF-ECE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122609681","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 : 2020-07-01DOI: 10.1109/YEF-ECE49388.2020.9171808
V. Anes, A. Abreu, Ricardo Santos
Agile is a successful project management mindset developed by the software industry which recently has been extrapolated for other industries. This mindset has been promoting the use and development of several tools that aim to minimize risks associated to the project output, i.e., in Agile the user requirements are the major priority and the risk associated to these requirements is strongly mitigated using tools like Scrum or Kanban. However, risk analysis in Agile projects has an implicit nature without well-defined and systematic methods. This feature was inherited from the software industry where this implicit approach works well, but for industries different from those that develop software it creates serious drawbacks. In fact, the risk associated to the project itself, or in other words, the risk associated to the Agile team capability to implement and manage a given project is not explicitly analyzed in Agile methods. Moreover, the Agile risk mitigation approach do not consider this important point of view in risk management. In this sense, important risk factors have been omitted, risk factors such as scope creep, unrealistic expectations, lack of cooperation, or lack of communication are some of these factors that have been overlooked despite their strong impact on Agile projects. This paper proposes a new approach to perform risk assessment and management of Agile projects. The approach comprises a set of qualitative risk tools inline with the Agile way of doing things, i.e., the proposed model does not jeopardize the flexibility found in Agile methods so appreciated by Agile team members, but at the same time, the proposed model introduces a systematic way of risk analysis which absence in Agile projects has been criticize in literature.
{"title":"A New Risk Assessment Approach for Agile Projects","authors":"V. Anes, A. Abreu, Ricardo Santos","doi":"10.1109/YEF-ECE49388.2020.9171808","DOIUrl":"https://doi.org/10.1109/YEF-ECE49388.2020.9171808","url":null,"abstract":"Agile is a successful project management mindset developed by the software industry which recently has been extrapolated for other industries. This mindset has been promoting the use and development of several tools that aim to minimize risks associated to the project output, i.e., in Agile the user requirements are the major priority and the risk associated to these requirements is strongly mitigated using tools like Scrum or Kanban. However, risk analysis in Agile projects has an implicit nature without well-defined and systematic methods. This feature was inherited from the software industry where this implicit approach works well, but for industries different from those that develop software it creates serious drawbacks. In fact, the risk associated to the project itself, or in other words, the risk associated to the Agile team capability to implement and manage a given project is not explicitly analyzed in Agile methods. Moreover, the Agile risk mitigation approach do not consider this important point of view in risk management. In this sense, important risk factors have been omitted, risk factors such as scope creep, unrealistic expectations, lack of cooperation, or lack of communication are some of these factors that have been overlooked despite their strong impact on Agile projects. This paper proposes a new approach to perform risk assessment and management of Agile projects. The approach comprises a set of qualitative risk tools inline with the Agile way of doing things, i.e., the proposed model does not jeopardize the flexibility found in Agile methods so appreciated by Agile team members, but at the same time, the proposed model introduces a systematic way of risk analysis which absence in Agile projects has been criticize in literature.","PeriodicalId":331206,"journal":{"name":"2020 International Young Engineers Forum (YEF-ECE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129908326","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 : 2020-07-01DOI: 10.1109/yef-ece49388.2020.9171804
{"title":"YEF-ECE 2020 Cover Page","authors":"","doi":"10.1109/yef-ece49388.2020.9171804","DOIUrl":"https://doi.org/10.1109/yef-ece49388.2020.9171804","url":null,"abstract":"","PeriodicalId":331206,"journal":{"name":"2020 International Young Engineers Forum (YEF-ECE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124001162","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 : 2020-07-01DOI: 10.1109/YEF-ECE49388.2020.9171802
Francisco Simoesõ, V. Pires, J. Murta-Pina
This paper assesses the possibility of using superconducting magnetic energy storage to improve the power quality of a grid, more specifically integrated into a current harmonic compensation device. Superconducting magnetic energy storage stores energy in the magnetic field of a lossless superconducting coil. They show a low energy density, but these devices are able to release high powers (in the MW range) within short times (ms up to a few seconds). Therefore, superconducting magnetic energy storage are foreseen for ”power” applications, as power quality improvement, rather than for bulk energy storage. In this way, they are also envisaged to compensate low-frequency harmonics generated by wind generators. Simulations show that a superconducting magnetic energy storage unit can be added in a voltage source converter based active filter to further contribute to mitigate current harmonics and decrease total harmonic distortion. Several simulation runs will be presented with the purpose of highlighting the main conclusions regarding this approach.
{"title":"Assessment of Using Superconducting Magnetic Energy Storage for Current Harmonic Compensation","authors":"Francisco Simoesõ, V. Pires, J. Murta-Pina","doi":"10.1109/YEF-ECE49388.2020.9171802","DOIUrl":"https://doi.org/10.1109/YEF-ECE49388.2020.9171802","url":null,"abstract":"This paper assesses the possibility of using superconducting magnetic energy storage to improve the power quality of a grid, more specifically integrated into a current harmonic compensation device. Superconducting magnetic energy storage stores energy in the magnetic field of a lossless superconducting coil. They show a low energy density, but these devices are able to release high powers (in the MW range) within short times (ms up to a few seconds). Therefore, superconducting magnetic energy storage are foreseen for ”power” applications, as power quality improvement, rather than for bulk energy storage. In this way, they are also envisaged to compensate low-frequency harmonics generated by wind generators. Simulations show that a superconducting magnetic energy storage unit can be added in a voltage source converter based active filter to further contribute to mitigate current harmonics and decrease total harmonic distortion. Several simulation runs will be presented with the purpose of highlighting the main conclusions regarding this approach.","PeriodicalId":331206,"journal":{"name":"2020 International Young Engineers Forum (YEF-ECE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114748541","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 : 2020-07-01DOI: 10.1109/YEF-ECE49388.2020.9171818
João E. Pereira-Pires, Valentine Aubard, João M. N. Silva, Rita Almeida Ribeiro, J. Pereira, J. Fonseca, M. Campagnolo, A. Mora
This last decade, large wildfires have increased in number, size and consequent damages in various countries worldwide. Since 2017, the large fire hazard is a major concern for Portugal. An important fuel break (FB) network is currently implemented in strategic areas by the Portuguese Institute of Nature and Forest Conservation (ICNF). The objective of reducing fuel loads on those thin strips is to reduce fire propagation and to improve firefighting conditions. The efficiency of FB depends on its periodic maintenance. The increasing quality and frequency of Earth Observation Satellite imagery nowadays allow the implementation of change detection methods to identify the occurrence of FB maintenance operations and help their necessary management. This article presents two approaches, a pixel-based and an object-based semi-automated supervised classification using monthly composites of Sentinel-2 imagery to achieve this detection. The pixel-based approach resource to the Maximum Entropy classifier while the object-based to an Artificial Neural Network. The overall accuracies range from 96.5% to 97.5%, which are promising results. Both methods can be combined for optimal detection over the whole territory.
{"title":"Pixel-based and object-based change detection methods for assessing fuel break maintenance","authors":"João E. Pereira-Pires, Valentine Aubard, João M. N. Silva, Rita Almeida Ribeiro, J. Pereira, J. Fonseca, M. Campagnolo, A. Mora","doi":"10.1109/YEF-ECE49388.2020.9171818","DOIUrl":"https://doi.org/10.1109/YEF-ECE49388.2020.9171818","url":null,"abstract":"This last decade, large wildfires have increased in number, size and consequent damages in various countries worldwide. Since 2017, the large fire hazard is a major concern for Portugal. An important fuel break (FB) network is currently implemented in strategic areas by the Portuguese Institute of Nature and Forest Conservation (ICNF). The objective of reducing fuel loads on those thin strips is to reduce fire propagation and to improve firefighting conditions. The efficiency of FB depends on its periodic maintenance. The increasing quality and frequency of Earth Observation Satellite imagery nowadays allow the implementation of change detection methods to identify the occurrence of FB maintenance operations and help their necessary management. This article presents two approaches, a pixel-based and an object-based semi-automated supervised classification using monthly composites of Sentinel-2 imagery to achieve this detection. The pixel-based approach resource to the Maximum Entropy classifier while the object-based to an Artificial Neural Network. The overall accuracies range from 96.5% to 97.5%, which are promising results. Both methods can be combined for optimal detection over the whole territory.","PeriodicalId":331206,"journal":{"name":"2020 International Young Engineers Forum (YEF-ECE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131271381","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：