Leopoldo Yoshioka - Academia.edu (original) (raw)
Papers by Leopoldo Yoshioka
Proceedings of the L Brasilian Congress of Engineering Education
TThis work presents an educational experience related to Innovation. It presents a model of disci... more TThis work presents an educational experience related to Innovation. It presents a model of discipline that acts both in the conceptualization and in the realization of Innovation in Engineering.
2022 International Joint Conference on Neural Networks (IJCNN)
EQUATIONS, 2021
Technological evolutions at Intelligent Transport Systems (ITS) is allowing that ubiquitous socie... more Technological evolutions at Intelligent Transport Systems (ITS) is allowing that ubiquitous society use the ITS facilities to conducting their activities. At this scenario the paper presents a study case in order to use ITS technologies applied to conduct his activities, mainly for bus tracking. The study case presented in this paper uses the concept of IoT (Internet of Things) to make the inspection of trucks; all study case considers the use of existing ITS infrastructure, as well as the deployment of new infrastructure. In order to implement the IoT, the study case use the RFID (Radio Frequency Identification) technologies associated with sensors installed at vehicle in order to identify the vehicle when it pass through a portal and the associated information, if available, as: temperature, average velocity, doors and others relevant information. The advantage of IoT is the ability to identify the vehicles and other information without disrupting the normal flow.
This is a dataset of vehicle's binary images obtained with an optical barrier. The main goal ... more This is a dataset of vehicle's binary images obtained with an optical barrier. The main goal off this dataset is to train and test a vehicle classification method. Categories are defined according to the number of axles and the presence of double wheel or not. (See the vehicle_categories.png) This dataset is composed by 3 folders. Train: Images used to train a CNN. (Over 1000 images/cat) Total of 11232 images. Experiment1: Images used to validate.5389 images. Experiment2: Field test. Four days off images. 196018 images. Train and Experiment1 are selected images from the same lane, in different periods over 3 months. Experiment2 has images from several different lanes, and 3 different toll stations. We do not delete any image in this set.
2020 International Conference on Electrical, Communication, and Computer Engineering (ICECCE), 2020
The concept of Smart Cities is a trend in large cities. Intelligent Transportation Systems) plays... more The concept of Smart Cities is a trend in large cities. Intelligent Transportation Systems) plays an essential role in providing accurate information on bus travel times. It improves the planning of passengers and the agency responsible for public transport. The purpose of this paper is to create a new methodology to predict the travel times of buses based on open data collected in real-time. We constructed a dataset from Sao Paulo City bus fleet location data, real-time traffic data, and traffic forecast from Google Maps. In the following, we trained an Artificial Neural Network (ANN). In the ANN training process, we alternated the dataset and its hyperparameters to find out the combination that provides the lower prediction error. The mean absolute percentage error found was 8.97%, using all data sets except weather data. We showed that our method could provide an accurate bus travel time prediction from web data collected in real-time.
International experience shows that several organizations have used traffic data and events occur... more International experience shows that several organizations have used traffic data and events occurred on roadways to build quality indicators. This paper explores methods that allow estimating traffic conditions at a given moment or over a given period of time. Traffic data were collected using Module of Intelligent Transport System (MITS), and were processed by means of Artificial Intelligence (AI) techniques based on Highway Capacity Manual (HCM) methodology. Part of these data were used to train the Artificial Neural Network (ANN) and another part were used to compare with that estimated by ANN. Experimental results show that ANN has estimated the level of service (LOS) of traffic with less than 3% error. This method can help the highway users decide the best window time for your displacement.
The development of mobile phone technology, beginning in the introduction of the first cellular s... more The development of mobile phone technology, beginning in the introduction of the first cellular systems in the mid-eighties, caused a rupture in the telecommunications industry service model. To fill the gaps created by the technological breakthrough in the service availability architecture, which arose in the transition from first generation (analog) to the second (digital) and the popularization of Internet access, the 3GPP (an ITU-T group) has developed a model that resulted in an architecture called IMS -IP Multimedia Subsystem. The IMS architecture was initially developed in order to meet the needs of 3GPP in the context of cellular systems and became the basis of the session control architecture for third-generation networks (3G) and their evolution (4G and beyond), where the focus is no longer the increase in capacity or bandwidth, but the interoperability between heterogeneous access networks, such as LTE and WiMAX, enhanced services control and service quality. Based on the...
Although Intelligent Transportation Systems – ITS applications are quite advanced for metro-rail,... more Although Intelligent Transportation Systems – ITS applications are quite advanced for metro-rail, aviation and road modes of transportation, for BRT corridors there is a need of deepening the concepts in terms of the reference architecture, service group (domains ) and well established ITS functionalities. This paper focuses on determining how ITS systems can support the implementation of BRT corridors. It contains the definition of the main players directly involved or benefited by ITS. A proposal is also made for a Public Urban Transportation ITS architecture to be applied on BRT corridors. To do so, it was adopted a systematic identification process for ITS functionalities and its classification into groups of services. This approach can be used as a reference to improve ITS functionalities in future BRT corridors projects. Key-Words: Intelligent Transportation Systems, Public Urban Transportation, Bus Rapid Transit, ITS4BRT Architecture, BRT, ITS.
In order to implement the Internet of things, the case study uses the technologies associated wit... more In order to implement the Internet of things, the case study uses the technologies associated with sensors installed in the vehicle in order to identify the vehicle when it passes through a portal and the associated information available as RFID (Radio Frequency Identification): temperature, average speed, doors and other relevant information. The paper presents a case study in order to use ITS technologies applied to conduct activities, mainly for the bus tracking. The case study is proposed with this paper, using the concept of IoT (Internet of Things) is the inspection of trucks.
Smarter cities provide sustainable economic growth and prosperity to their citizens. Their leader... more Smarter cities provide sustainable economic growth and prosperity to their citizens. Their leaders should have the tools to analyze municipality data from its environment to support best decisions, anticipating problems to resolve them proactively and to coordinate resources to operate effectively. For this reason, smart cities become sensitive, when instrumented with technological framework to collect environmental information. Providing a comprehensive view of the city requires a large number of sensors, in addition to a constant increase in order to follow the growth of the city. However, if the sensors are hosted on public transportation vehicles, the route is verified to cover the main populated areas, with a dynamic principle of growth, which adapts to the development of the city. Taking advantage of these principles, this paper proposes the best placement for the components of sensor network for environmental monitoring, which is maintained by the information from the sensors...
Technological evolutions at Intelligent Transport Systems (ITS) is allowing that ubiquitous socie... more Technological evolutions at Intelligent Transport Systems (ITS) is allowing that ubiquitous society use the ITS facilities to conducting their activities. At this scenario the paper presents a study case that is being developed to SEFAZ (Treasury Department) of São Paulo state in order to use ITS technologies applied to conduct his activities, mainly for tax inspection. The study case presented in this paper uses the Optical Character Recognition to identify and monitor the vehicles that does not pay the IPVA (motor vehicle tax), all study case considers the use of existing ITS infrastructure, as well as the deployment of new infrastructure. The advantage of OCR is the ability to identify vehicles without disrupting the normal flow or even cause a decrease in speed and to be non-intrusive in perspective of vehicles owners. Key-Words: ITS, OCR, Inspection, Goods, Trucks, Tax.
The aim of intelligent transport system (ITS) is to enhance the urban mobility in relation to saf... more The aim of intelligent transport system (ITS) is to enhance the urban mobility in relation to safety, usability, mobility, quality and productivity through the use of information and communication technology (ICT), and one of the main problems is to ensure that the elements of ITS such as cars, buses sensors, actuators, traffic lights, among others are exchanging data with each other, due to the size of this environment, the communication infrastructure between transport management system (TMS) and ITS elements and between ITS elements are extremely important In this context, this paper proposes the use of communication technologies considered for the smart grid, that is the Power Line Communication (PLC) system which consists of data communication through the grid which is available in large urban centers, and may even share with the existing network of smart grid. Key-Words: ITS, Smart Grid, Infrastructure, PLC, Sensors Network, Transport Management System
The use of embedded hardware and software are growing in the automotive applications. However, th... more The use of embedded hardware and software are growing in the automotive applications. However, the development effort required is increasing at the same time that schedule is becoming tight. In this paper we present a methodology for the development of embedded systems suited to the dynamics of the automotive sector. We propose a development framework that adds the concepts of component-base software engineering, reusable hardware platforms and pair-wise testing techniques. The effectiveness was evaluated through a case study of developing a telematic module. Development cycle of automotive embedded system can be accelerated by using framework.
In order to define a map of resources to users, operators, managers, equipment providers, applica... more In order to define a map of resources to users, operators, managers, equipment providers, application providers and other stakeholders, which can use as a guide for the implementation of its activities, it is used BRT, the Bus Rapid Transit (BRT) is an efficient transport system for cities that need to quickly expand your network of public transport, with a minimal investment compared to other systems. The BRT uses dedicated corridors to reduce user travel time, but these corridors should be within the existing road network, so it is necessary to implement automation systems that can coordinate BRT operations with other city transport modes. This automation system, known as ITS, has features that make this management, how to act at the traffic lights along the corridor in order to prioritize the passage of BRT, which also has other features in other areas that allow the proper functioning of the BRT. Key-Words: Map, BRT, ITS, Specification, Mobility, Transportation
2021 IEEE International Intelligent Transportation Systems Conference (ITSC), 2021
Automatic vehicle classification is one of the most critical subsystems in the Intelligent Transp... more Automatic vehicle classification is one of the most critical subsystems in the Intelligent Transport Systems, as it is responsible for the validation of vehicle categories in Electronic Toll Collection Systems. The accuracy of the classification in this kind of process needs to be high. Therefore, it is necessary to use several intrusive sensors in traffic lanes and sophisticated classification algorithms in practical applications. This article proposes a new classification method based on binary images of vehicle profiles extracted from a non-intrusive optical barrier sensor. We use an AlexNet convolutional neural network as a vehicle classification algorithm. The last layers of the network have been modified for the vehicle classification domain. In the training process, we use transfer learning and data augmentation techniques. The proposed method was tested using data collected at a toll plaza in the São Paulo State Highway, Brazil. The first experiment was carried out, with 11,233 images grouped in 11 categories, resulting in a classification accuracy of 98.02%. In the second experiment, we used 194,361 images collected over four days. We were able to evaluate the performance of the method in adverse conditions, specifically heavy rains. In this scenario, the proposed method reached an accuracy of 96.41%, which indicates that the replacement of a set of intrusive sensors with only an optical barrier can be a viable alternative for vehicle classification. Additionally, we become available all the images data used in this study in Mendeley's open repository.
It is important to bring to Urban Transportation, in specific of medium capacity, solutions that ... more It is important to bring to Urban Transportation, in specific of medium capacity, solutions that allow it to increase efficiency. This article shows functionalities associated to Intelligent Transportation Systems that can contribute to the increase in efficiency of Urban Collective Transportation. In particularly, the automation of a conventional bus by way of Autonomous Guidance Technology, which consists of magnetic sensing, computational intelligence and electro-mechanical actuator. The automation of the lateral guidance provides for docking maneuvers with better precision at the stops, in addition to allowing the vehicle to travel on narrow routes quickly and safely. One application of this technology is presented in Expresso Tiradentes bus corridor in São Paulo, where the achieved results demonstrate improvements in the efficiency of bus operations.
SAE Technical Paper Series, 2010
Proceedings of the L Brasilian Congress of Engineering Education
TThis work presents an educational experience related to Innovation. It presents a model of disci... more TThis work presents an educational experience related to Innovation. It presents a model of discipline that acts both in the conceptualization and in the realization of Innovation in Engineering.
2022 International Joint Conference on Neural Networks (IJCNN)
EQUATIONS, 2021
Technological evolutions at Intelligent Transport Systems (ITS) is allowing that ubiquitous socie... more Technological evolutions at Intelligent Transport Systems (ITS) is allowing that ubiquitous society use the ITS facilities to conducting their activities. At this scenario the paper presents a study case in order to use ITS technologies applied to conduct his activities, mainly for bus tracking. The study case presented in this paper uses the concept of IoT (Internet of Things) to make the inspection of trucks; all study case considers the use of existing ITS infrastructure, as well as the deployment of new infrastructure. In order to implement the IoT, the study case use the RFID (Radio Frequency Identification) technologies associated with sensors installed at vehicle in order to identify the vehicle when it pass through a portal and the associated information, if available, as: temperature, average velocity, doors and others relevant information. The advantage of IoT is the ability to identify the vehicles and other information without disrupting the normal flow.
This is a dataset of vehicle's binary images obtained with an optical barrier. The main goal ... more This is a dataset of vehicle's binary images obtained with an optical barrier. The main goal off this dataset is to train and test a vehicle classification method. Categories are defined according to the number of axles and the presence of double wheel or not. (See the vehicle_categories.png) This dataset is composed by 3 folders. Train: Images used to train a CNN. (Over 1000 images/cat) Total of 11232 images. Experiment1: Images used to validate.5389 images. Experiment2: Field test. Four days off images. 196018 images. Train and Experiment1 are selected images from the same lane, in different periods over 3 months. Experiment2 has images from several different lanes, and 3 different toll stations. We do not delete any image in this set.
2020 International Conference on Electrical, Communication, and Computer Engineering (ICECCE), 2020
The concept of Smart Cities is a trend in large cities. Intelligent Transportation Systems) plays... more The concept of Smart Cities is a trend in large cities. Intelligent Transportation Systems) plays an essential role in providing accurate information on bus travel times. It improves the planning of passengers and the agency responsible for public transport. The purpose of this paper is to create a new methodology to predict the travel times of buses based on open data collected in real-time. We constructed a dataset from Sao Paulo City bus fleet location data, real-time traffic data, and traffic forecast from Google Maps. In the following, we trained an Artificial Neural Network (ANN). In the ANN training process, we alternated the dataset and its hyperparameters to find out the combination that provides the lower prediction error. The mean absolute percentage error found was 8.97%, using all data sets except weather data. We showed that our method could provide an accurate bus travel time prediction from web data collected in real-time.
International experience shows that several organizations have used traffic data and events occur... more International experience shows that several organizations have used traffic data and events occurred on roadways to build quality indicators. This paper explores methods that allow estimating traffic conditions at a given moment or over a given period of time. Traffic data were collected using Module of Intelligent Transport System (MITS), and were processed by means of Artificial Intelligence (AI) techniques based on Highway Capacity Manual (HCM) methodology. Part of these data were used to train the Artificial Neural Network (ANN) and another part were used to compare with that estimated by ANN. Experimental results show that ANN has estimated the level of service (LOS) of traffic with less than 3% error. This method can help the highway users decide the best window time for your displacement.
The development of mobile phone technology, beginning in the introduction of the first cellular s... more The development of mobile phone technology, beginning in the introduction of the first cellular systems in the mid-eighties, caused a rupture in the telecommunications industry service model. To fill the gaps created by the technological breakthrough in the service availability architecture, which arose in the transition from first generation (analog) to the second (digital) and the popularization of Internet access, the 3GPP (an ITU-T group) has developed a model that resulted in an architecture called IMS -IP Multimedia Subsystem. The IMS architecture was initially developed in order to meet the needs of 3GPP in the context of cellular systems and became the basis of the session control architecture for third-generation networks (3G) and their evolution (4G and beyond), where the focus is no longer the increase in capacity or bandwidth, but the interoperability between heterogeneous access networks, such as LTE and WiMAX, enhanced services control and service quality. Based on the...
Although Intelligent Transportation Systems – ITS applications are quite advanced for metro-rail,... more Although Intelligent Transportation Systems – ITS applications are quite advanced for metro-rail, aviation and road modes of transportation, for BRT corridors there is a need of deepening the concepts in terms of the reference architecture, service group (domains ) and well established ITS functionalities. This paper focuses on determining how ITS systems can support the implementation of BRT corridors. It contains the definition of the main players directly involved or benefited by ITS. A proposal is also made for a Public Urban Transportation ITS architecture to be applied on BRT corridors. To do so, it was adopted a systematic identification process for ITS functionalities and its classification into groups of services. This approach can be used as a reference to improve ITS functionalities in future BRT corridors projects. Key-Words: Intelligent Transportation Systems, Public Urban Transportation, Bus Rapid Transit, ITS4BRT Architecture, BRT, ITS.
In order to implement the Internet of things, the case study uses the technologies associated wit... more In order to implement the Internet of things, the case study uses the technologies associated with sensors installed in the vehicle in order to identify the vehicle when it passes through a portal and the associated information available as RFID (Radio Frequency Identification): temperature, average speed, doors and other relevant information. The paper presents a case study in order to use ITS technologies applied to conduct activities, mainly for the bus tracking. The case study is proposed with this paper, using the concept of IoT (Internet of Things) is the inspection of trucks.
Smarter cities provide sustainable economic growth and prosperity to their citizens. Their leader... more Smarter cities provide sustainable economic growth and prosperity to their citizens. Their leaders should have the tools to analyze municipality data from its environment to support best decisions, anticipating problems to resolve them proactively and to coordinate resources to operate effectively. For this reason, smart cities become sensitive, when instrumented with technological framework to collect environmental information. Providing a comprehensive view of the city requires a large number of sensors, in addition to a constant increase in order to follow the growth of the city. However, if the sensors are hosted on public transportation vehicles, the route is verified to cover the main populated areas, with a dynamic principle of growth, which adapts to the development of the city. Taking advantage of these principles, this paper proposes the best placement for the components of sensor network for environmental monitoring, which is maintained by the information from the sensors...
Technological evolutions at Intelligent Transport Systems (ITS) is allowing that ubiquitous socie... more Technological evolutions at Intelligent Transport Systems (ITS) is allowing that ubiquitous society use the ITS facilities to conducting their activities. At this scenario the paper presents a study case that is being developed to SEFAZ (Treasury Department) of São Paulo state in order to use ITS technologies applied to conduct his activities, mainly for tax inspection. The study case presented in this paper uses the Optical Character Recognition to identify and monitor the vehicles that does not pay the IPVA (motor vehicle tax), all study case considers the use of existing ITS infrastructure, as well as the deployment of new infrastructure. The advantage of OCR is the ability to identify vehicles without disrupting the normal flow or even cause a decrease in speed and to be non-intrusive in perspective of vehicles owners. Key-Words: ITS, OCR, Inspection, Goods, Trucks, Tax.
The aim of intelligent transport system (ITS) is to enhance the urban mobility in relation to saf... more The aim of intelligent transport system (ITS) is to enhance the urban mobility in relation to safety, usability, mobility, quality and productivity through the use of information and communication technology (ICT), and one of the main problems is to ensure that the elements of ITS such as cars, buses sensors, actuators, traffic lights, among others are exchanging data with each other, due to the size of this environment, the communication infrastructure between transport management system (TMS) and ITS elements and between ITS elements are extremely important In this context, this paper proposes the use of communication technologies considered for the smart grid, that is the Power Line Communication (PLC) system which consists of data communication through the grid which is available in large urban centers, and may even share with the existing network of smart grid. Key-Words: ITS, Smart Grid, Infrastructure, PLC, Sensors Network, Transport Management System
The use of embedded hardware and software are growing in the automotive applications. However, th... more The use of embedded hardware and software are growing in the automotive applications. However, the development effort required is increasing at the same time that schedule is becoming tight. In this paper we present a methodology for the development of embedded systems suited to the dynamics of the automotive sector. We propose a development framework that adds the concepts of component-base software engineering, reusable hardware platforms and pair-wise testing techniques. The effectiveness was evaluated through a case study of developing a telematic module. Development cycle of automotive embedded system can be accelerated by using framework.
In order to define a map of resources to users, operators, managers, equipment providers, applica... more In order to define a map of resources to users, operators, managers, equipment providers, application providers and other stakeholders, which can use as a guide for the implementation of its activities, it is used BRT, the Bus Rapid Transit (BRT) is an efficient transport system for cities that need to quickly expand your network of public transport, with a minimal investment compared to other systems. The BRT uses dedicated corridors to reduce user travel time, but these corridors should be within the existing road network, so it is necessary to implement automation systems that can coordinate BRT operations with other city transport modes. This automation system, known as ITS, has features that make this management, how to act at the traffic lights along the corridor in order to prioritize the passage of BRT, which also has other features in other areas that allow the proper functioning of the BRT. Key-Words: Map, BRT, ITS, Specification, Mobility, Transportation
2021 IEEE International Intelligent Transportation Systems Conference (ITSC), 2021
Automatic vehicle classification is one of the most critical subsystems in the Intelligent Transp... more Automatic vehicle classification is one of the most critical subsystems in the Intelligent Transport Systems, as it is responsible for the validation of vehicle categories in Electronic Toll Collection Systems. The accuracy of the classification in this kind of process needs to be high. Therefore, it is necessary to use several intrusive sensors in traffic lanes and sophisticated classification algorithms in practical applications. This article proposes a new classification method based on binary images of vehicle profiles extracted from a non-intrusive optical barrier sensor. We use an AlexNet convolutional neural network as a vehicle classification algorithm. The last layers of the network have been modified for the vehicle classification domain. In the training process, we use transfer learning and data augmentation techniques. The proposed method was tested using data collected at a toll plaza in the São Paulo State Highway, Brazil. The first experiment was carried out, with 11,233 images grouped in 11 categories, resulting in a classification accuracy of 98.02%. In the second experiment, we used 194,361 images collected over four days. We were able to evaluate the performance of the method in adverse conditions, specifically heavy rains. In this scenario, the proposed method reached an accuracy of 96.41%, which indicates that the replacement of a set of intrusive sensors with only an optical barrier can be a viable alternative for vehicle classification. Additionally, we become available all the images data used in this study in Mendeley's open repository.
It is important to bring to Urban Transportation, in specific of medium capacity, solutions that ... more It is important to bring to Urban Transportation, in specific of medium capacity, solutions that allow it to increase efficiency. This article shows functionalities associated to Intelligent Transportation Systems that can contribute to the increase in efficiency of Urban Collective Transportation. In particularly, the automation of a conventional bus by way of Autonomous Guidance Technology, which consists of magnetic sensing, computational intelligence and electro-mechanical actuator. The automation of the lateral guidance provides for docking maneuvers with better precision at the stops, in addition to allowing the vehicle to travel on narrow routes quickly and safely. One application of this technology is presented in Expresso Tiradentes bus corridor in São Paulo, where the achieved results demonstrate improvements in the efficiency of bus operations.
SAE Technical Paper Series, 2010