Eduardo Todt

Verified

Eduardo verified their affiliation via an institutional email.

Learn more

Verified

Eduardo verified their affiliation via an institutional email.

Learn more

• PhD
• Professor (Associate) at Federal University of Paraná

This study explores the impact of educational robotics on student engagement in a nonformal learning environment , specifically within a non-governmental organization serving socioeconomically vulnerable children aged 7 to 13. Utilizing action research methodology, the study was conducted through a series of weekly workshops focused on unplugged co...

This paper presents the ROME project as a cooperative and collaborative learning tool for high school and university students. The authors validate the platform by implementing STEM education, incorporating concepts of PBL and maker culture, and conducting mini-courses at UniCuritiba. The ROME project aims to develop a solid and documented foundati...

A Plataforma MEC de Recursos Educacionais Digitais (MEC RED) centraliza conteúdos de usuários e dos principais portais do Ministério da Educação do Brasil (MEC) para todas as pessoas interessadas em educação e cultura digital. Este estudo avalia a MEC RED com o objetivo de atender à demanda do MEC de melhorar a Experiência do Usuário e ampliar as s...

Este artigo apresenta a aplicação da narração de histórias por meio de vídeos para a introdução de conceitos de computação em uma ONG no interior do Paraná. Alinhadas ao complemento de computação da Base Nacional Comum Curricular (BNCC), as atividades propostas buscam ser um passo introdutório para as aprendizagens essenciais em computação, as quai...

Este relatório apresenta os resultados da Avaliação da Plataforma MEC de Recursos Educacionais Digitais com especialistas em Experiência do Usuário (UX) e especialistas em Educação/Tecnologias Educacionais. A avaliação foi realizada atendendo a meta “Planejar e conduzir oficinas Semi-Participativas virtuais e reais com representantes do público-alv...

The integration of robotics research with Artificial Intelligence (AI) and Computer Vision (CV) has enabled the solution of practical tasks previously challenging with traditional techniques. This interdisciplinary approach focuses on developing intelligent computational systems for decision-making, planning, and object recognition, minimizing huma...

Since 2005, the deep learning community has had access to input graphs to their models. So, the natural language processing (NLP) community started using this technique to process text. However, a challenge that the graph neural networks (GNN) may encounter is the sensibility to representation format. Since different graphs can represent the same t...

This paper compares the golden standard PD and the alternative dynamic PD, two control systems that can be used for line follower robots. In the dynamic PD, the parameters change over time, allowing local optimizations. A test track was made to measure the performance of both controllers. The total elapsed time that the robot took to complete the c...

This paper presents a systematic mapping study on the application of educational robotics in non-formal educational settings such as science clubs, museums, libraries, extracurricular activities, and non-governmental organizations (NGOs). The aim of this study is to explore the potential and challenges of educational robotics in these settings, spe...

Robotics and the Internet of Things (IoT) have emerged as powerful tools to enhance teaching and learning processes, aligning with the National Common Curriculum Base (BNCC). This systematic mapping study provides an overview of existing research on the use of robotics and IoT in basic education in the context of the BNCC. It involved a comprehensi...

Recognizing where humans are looking is a relevant and challenging task. Modern publicly available AI can compute gaze direction with less than 10°of average angular error. However, these models still have an inference time which may be too long to be used in real-time applications such as social robots and driving monitoring systems that need to c...

This paper presents a systematic mapping study on the application of educational robotics in non-formal educational settings such as science clubs, museums, libraries, extracurricular activities, and non-governmental organizations (NGOs). The aim of this study is to explore the potential and challenges of educational robotics in these settings, spe...

O governo brasileiro possui diversos programas para melhorar a vida da sociedade brasileira, como o Sistema Único de Saúde (SUS), o Programa Nacional do Livro e do Material Didático (PNLD) e o Programa Universidade Para Todos (PROUNI). Esses programas tem revisões periódicas de regras, o que afeta sistemas computacionais, fazendo com que novos soft...

This paper addresses the challenge of typeface recognition, withinthe broader scope of optical character recognition of historicalGerman-Brazilian periodicals. A dataset of words containing annotationsof font types and transcriptions for training neural networksfor typeface and text recognition is presented. By enabling wordleveltypeface and text r...

Due to the COVID-19 global pandemic, computer-assisted diagnoses of medical images have gained much attention, and robust methods of semantic segmentation of Computed Tomography (CT) images have become highly desirable. In this work, we present a deeper analysis of how data augmentation techniques improve segmentation performance on this problem. W...

Due to the COVID-19 global pandemic, computer-assisted diagnoses of medical images have gained much attention, and robust methods of semantic segmentation of Computed Tomography (CT) images have become highly desirable. In this work, we present a deeper analysis of how data augmentation techniques improve segmentation performance on this problem. W...

The use of Unmanned Aerial Vehicle (UAV) have been shown to be increasingly frequent for a diversity of applications , mainly in agriculture. The mapping of large areas for analysis purposes is common and it is considered a challenge due to the short range of the UAVs. The base stations utilization for drone recharge and important information obtai...

This extension project stimulates students’ interest in maker cultureand various areas of robotics such as mechanics, electronics, andcomputing. The mobile robot educational kit presents differentialsas scalability in production, low cost, flexibility in assembly withoutscrews, and print circuit board project. We researched the literatureon active...

With the COVID-19 global pandemic, computer-assisted diagnoses of medical images have gained much attention, and robust methods of Semantic Segmentation of Computed Tomography (CT) became highly desirable. Semantic Segmentation of CT is one of many research fields of automatic detection of COVID-19 and has been widely explored since the COVID-19 ou...

With the COVID-19 global pandemic, computer-assisted diagnoses of medical images have gained much attention, and robust methods of Semantic Segmentation of Computed Tomography (CT) became highly desirable. Semantic Segmentation of CT is one of many research fields of automatic detection of COVID-19 and has been widely explored since the COVID-19 ou...

Text classification is an essential task in Natural Language Processing. The researchers and developers need data in the desired language to build new models and algorithms to develop this task. In this paper, we discuss and make available three datasets of text classification in Portuguese based on data of the B2W group, which is an important cont...

With the COVID-19 global pandemic, computerassisted diagnoses of medical images have gained a lot of attention, and robust methods of Semantic Segmentation of Computed Tomography (CT) turned highly desirable. Semantic Segmentation of CT is one of many research fields of automatic detection of Covid-19 and was widely explored since the Covid19 outbr...

In major hearing cultures, deaf people still face difficulties related to the teaching-learning processes, being computational tools one of them. This scenario triggered our research path in 2007 aiming to attend to the communicational needs of the Brazilian Deaf communities This effort has involved researchers from Computer Science and Linguistics...

With the rise of automation, unmanned vehicles became a hot topic both as commercial products and as a scientific research topic. It composes a multi-disciplinary field of robotics that encompasses embedded systems, control theory, path planning, Simultaneous Localization and Mapping (SLAM), scene reconstruction, and pattern recognition. In this wo...

To navigate a robotic base in an unfamiliar environment , techniques to estimate position and localization must be provided. The most common practice uses embedded sensors in the mechanical system to measure internal information and then apply some algorithm to define position and orientation. When the base is navigating and uses these techniques,...

Deep learning models uses many parameters to work properly. As they become more complex, the authors of these novel models cannot explore in their papers the variation of each parameter of their model. Therefore, this work describes an analysis of the impact of four different parameters (Early Stopping, Learning Rate, Dropout, and Hidden 1) in the...

3D Avatars are an efficient solution to complement the representation of sign languages in computational environments. A challenge, however, is to generate facial expressions realistically, without high computational cost in the synthesis process. This work synthesizes facial expressions with precise control through spatio-temporal parameters autom...

This article presents a study of the resources necessary to providemovement and localization in three wheeled omnidirectionalrobots, through the detailed presentation of the mathematical proceduresapplicable in the construction of the inverse kinematic model,the presentation of the main hardware and software componentsused for the construction of a...

This paper presents an efficient and layout-independent Automatic License Plate Recognition (ALPR) system based on the state-of-the-art YOLO object detector that contains a unified approach for license plate (LP) detection and layout classification to improve the recognition results using post-processing rules. The system is conceived by evaluating...

This paper presents an efficient and layout-independent Automatic License Plate Recognition (ALPR) system based on the state-of-the-art YOLO object detector that contains a unified approach for license plate (LP) detection and layout classification to improve the recognition results using post-processing rules. The system is conceived by evaluating...

Education 4.0 is defined as a student-centered learning model that prepares young for the challenges of the 21st Century, how to deal with emerging technological resources and processes. This case study aimed to encourage 21st Century skills and competencies seen as relevant to Education 4.0, such as teamwork, communication, autonomy, creativity, a...

Emotions can be synthesized in virtual environments through spatial calculations that define regions and intensities of displacement, using landmark controllers that consider spatio-temporal variations. This work presents a proposal for calculating spatio-temporal mesh for 3D objects that can be used in the realistic synthesis of emotions in virtua...

In this paper, we present an Improved Data Augmentation (IDA) technique focused on Salient Object Detection (SOD). Standard data augmentation techniques proposed in the literature, such as image cropping, rotation, flipping, and resizing, only generate variations of the existing examples, providing a limited generalization. Our method combines imag...

There is an increasing interest in image-to-image translation withapplications ranging from generating maps from satellite images tocreating entire clothes’ images from only contours. In the presentwork, we investigate image-to-image translation using GenerativeAdversarial Networks (GANs) for generating new data, taking as acase study the morphing...

Civilian Unmanned Aerial Vehicles (UAVs) are becoming more accessible for domestic use. Currently, UAV manufacturer DJI dominates the market, and their drones have been used for a wide range of applications. Model lines such as the Phantom can be applied for autonomous navigation where Global Positioning System (GPS) signals are not reliable, with...

As universidades públicas brasileiras têm papel chave como promotoras do desenvolvimento econômico, tecnológico e social do país. Diversas instituições de ensino e pesquisa, com seus laboratórios e grupos, têm contribuído fortemente não apenas com a formação de recursos humanos de alta qualidade, mas também com o desenvolvimento científico e tecnol...

There is an increasing interest in image-to-image translation with applications ranging from generating maps from satellite images to creating entire clothes' images from only contours. In the present work, we investigate image-to-image translation using Generative Adversarial Networks (GANs) for generating new data, taking as a case study the morp...

The availability of large Open Data sources creates opportunities for data analytics on different domains. But in order to be effectively used, the data needs to be correctly extracted, formatted and integrated, which is a specially challenging task on Open Data sources, since there is usually less rigour in standardizing subsequent data releases....

Industrial automation is undergoing a major transformation due to the ease of access to information we have today, as well as the popular use of free hardware / software. Projects that were previously developed by experts in the field today can easily be developed with low cost equipment. This paper presents the prototype of an automated feeder tha...

This paper presents an enviroment for the collection of sensor readings and information storage in a database accessed by a REST API, that allows the monitoring of the readings with visualization of the data in JSON format or through reports generated with the help of JasperReports. Due to the different sensor models available in the industry, the...

Sensor fusion is a well-explored area with constant research over the last thirty years for application in mobile robot localization. This systematic mapping study (SMS) identifies areas for more primary studies to be conducted. The goal of the study is to identify the main methods of sensor fusion and sensor types, aiming at application with multi...

In this paper, we propose a novel data augmentation technique (ANDA) applied to the Salient Object Detection (SOD) context. Standard data augmentation techniques proposed in the literature, such as image cropping, rotation, flipping, and resizing, only generate variations of the existing examples, providing a limited generalization. Our method has...

In this paper, we propose a broad comparison between Fully Convolutional Networks (FCNs) and Mask Region-based Convolutional Neural Networks (Mask-RCNNs) applied in the Salient Object Detection (SOD) context. Studies in the SOD literature usually explore architectures based in FCNs to detect salient regions and objects in visual scenes. However, be...

This work presents a proposal for a cooperation system aimed to optimize flights of unmanned aerial vehicle like a quadricopter, applied to precision agriculture. The system uses technologies that allow the opening, which is the property of inserting and removing system elements at any time, and dynamicity, allowing the system to recover itself fro...

The mobile robots popularization, in terrestrial, aerial or aquatic context, opens the possibility of a new research niche: the use of these robots for activities such as monitoring, search/rescue, cleaning services, as well their use in precision agriculture. As many times the area of operation of these robots is very large, it becomes unfeasible...

To use Unmanned Aerial Vehicles in precision agriculture is a very common and efficient practice, however, the vast majority of applications make use of Fixed-Wing Aerial Vehicles due to their autonomy that is several times higher than that of the Rotating-Wing Aerial Vehicles type. Meanwhile, as its autonomy increases, so does its cost, and with t...

We present HOTMapper, a tool that maps tables of Open Data with historical information into unified data sources. The tool couples data exchange and integration techniques implemented into two main components: 1) a CLI script with commands to create and update tables, and to insert and update the data, using 2) a simple mapping definition file, int...

This work presents the development of a wireless system for noninva-sive and continuous monitoring of arterial blood pressure applied to diagnosis support and personal use. The system performs the measurement of heart rate, blood oxygen saturation (SpO2) and estimates the blood pressure. It comprises two plethysmographic sensors and a device for si...

A drone is a type of Unmanned Aerial Vehicles (UAV) that most of the times can have four propellers. They can be used in many applications, one of those is to move through places of difficult access. Besides drones practicity over other aerial vehicles, its price is way lower compared to large vehicles, which turns them attractive to many activitie...

Unmanned aerial vehicles (UAVs) like quadrotors are becoming more popular and are being used in many different applications. While there are many ready-made models on the market, their cost is often high due to industrial value, patents, among other costs. Today it is possible to assemble low cost quadricopters, however, the control of this t...

Drones, or unmanned aerial vehicles, beyond being a model airplane hobby gain market space by acting as an important data capture tool and helping in routine tasks, such as in agriculture management areas and goods delivery. The main reasons of its increasing popularity are the technological advancements and improvements of the hardware. Thus, the...

Unmanned aerial vehicles (UAVs) like quadrotors are becoming more popular and are being used in many different applications. While there are many ready-made models on the market, their cost is often high due to industrial value, patents, among other costs. Today it is possible to assemble low cost quadricopters, however, the control of this type of...

In this work a prototype involving hardware and software is proposed , aiming at the development of a platform for monitoring and tracking a car. Given the difficulties to obtain a real vehicle for the tests of this type of academic work, this work presents a model of hardware that allows to run tests in certain features of a car. For the proposed...

Open Educational Resources (OER) are educational resources openly available to be used by educators and students and are an important tool to support education. A considerable effort has been made to build repositories that allow the sharing and reuse of these OERs. However, many of these repositories offer unsatisfactory search engines, resulting...

The speech was about the futures and technologies developed by C3SL on the customization of the distribution Ubuntu for an environment dedicated to schools.

The large availability of open government data raises enormous opportunities for open big data analytics. However, providing an end-to-end framework able to handle tasks from data extraction and processing to a web interface involves many challenges. One critical factor is the existence of many players with different knowledge, who need to interact...

Este trabalho apresenta o desenvolvimento de um protótipo de uma estufa automatizada. A estufa deve realizar a irrigação e controlar a abertura das cortinas laterais. Estes acionamentos podem ser feitos a partir do que foi especificado pelo usuário (parametrizado) ou por meio de comandos enviados de forma remota, utilizando uma aplicação para dispo...

Temperature monitoring in a silo is necessary because temperature is the main factor involved in the deterioration of stored grain. By controlling the temperature it is possible to reduce losses due to the proliferation of fungi and to avoid the germination of the grains. This work proposes a system for monitoring the internal temperature of a silo...

Artificial Intelligence Models (AI) were tested for aboveground dry biomass estimation of 4,004 trees collected in forests throughout the Tropics, and compared to a classic Allometric model of literature. The data come from various countries, in the Neotropics, Africa, Southeast Asia, and Oceania. Statistical analysis of the data showed that they d...

The cooperation between autonomous vehicles is receiving a growing attention from the academic literature. As a promising field, there is a need for studies that can provide both an overview and a structured analysis of the present literature. This paper presents a systematic mapping for the scenario of systems with cooperation of non-urban vehicle...

Weather stations are a valuable tool to many different areas, like agriculture, aviation, construction, sports and recreation, specially because they collect weather data, which can be stored and processed to gather specific information to correlate events to the weather action. This work shows a development model of a low cost weather station, usi...

Facial expressions and associates emotions important factors defining the message tone and context information in both spoken and sign language communication. Sign language virtual systems use structural models that define control values specifying body configurations in the animation process, where facial parameters are generally relegated to simp...

Designing solutions for the IoT domain has been recognized as a challenging and complex scenario for which our technical-centered approaches seem not to hold anymore. This paper draws on a real project experience to discuss how a sociotechnical perspective to the development of an IoT solution can support a better understanding of a project, includ...

This paper presents deals with the design and implementation of a system to monitor the vital signs of a baby, to support the diagnosis and pediatric use. The text presents an approach on monitoring signals, normality standards, and measurement devices. It also represents how tools used to implement the project, and how they are associated. The con...

The present paper discusses the implementation of the Harris and Stephen corner detector algorithm optimized for an embedded system-on-a-chip (SOC) platform that integrates a multicore ARM processor and FPGA fabric in a single chip, the Xilinx Zynq-7000. The algorithm is implemented as a hardware co-processor on the FPGA portion of the SoC. As a wh...

The Federal University of Paran´a (UFPR) hosts the cross-disciplinary research group C3SL, which has been investigating on open-source solutions for digital inclusion, covering different topics over the last fifteen years. It has been acting as a partner of different Brazilian public institutions and governments, backing up them for strategic choic...

The invariant feature detectors are essential components in many computer vision applications, such as tracking, simultaneous localization and mapping (SLAM), image search, machine vision, object recognition, 3D reconstruction from multiple images, augmented reality, stereo vision, and others. However, it is very challenging to detect high quality...

This paper briefly presents a model for monitoring a large, heterogeneous and geographically scattered computer park. The data collection is performed by a software agent. The collected data are sent to the central server over the Internet, and stored by the storage system. An on-line portal makes up the visualization system, featuring charts, repo...

Vision-based robot localization outdoors has remained more elusive than its indoors counterpart. Drastic illumination changes and the scarceness of suitable landmarks are the main difficulties. This paper attempts to surmount them by deviating from the main trend of using local features. Instead, a global descriptor called landmark-view is defined,...

Independent spanning trees (ISTs) provide a number of advantages in data broadcasting. One can cite the use in fault tolerance network protocols for distributed computing and bandwidth. However, the problem of constructing multiple ISTs is considered hard for arbitrary graphs. In this paper we present an efficient algorithm to construct ISTs on hy...

This work presents an efficient CUDA implementation of the Canny edge detection Filter for the Insight Segmentation and Registration Toolkit (ITK). The algorithm is tested on three generations of NVidia GPGPUs, showing performance gains of 3.6 to 50 times when compared to the standard ITK Canny running on two CPU models. The CUDA-enabled Canny is a...

Redes de Petri e suas propriedades algébricas são usadas para modelar e analisar sistemas envolvendo paralelismo, concorrência e sincronização. Este artigo apresenta uma aplicação da técnica de Tempo Global (GTT - global time technique) que é uma abordagem para construir grafos de classes de redes de Petri temporais baseada nos tempos relativo e gl...

This paper analyses the technological evolution and the trends of Automated People Movers (APM) in recent years. It establishes a baseline of the technological and economic aspects in order to support the development process of an enhanced version of the Aeromovel system (APM that uses air flow for propulsion on an elevated track). For the definiti...

Este artigo enfoca a evolução do mercado e as tendências dos sistemas Automated People Movers, APM, nos últimos anos, estabelecendo um balizamento dos indicadores tecnológicos e econômicos para o desenvolvimento do novo projeto do Sistema Aeromóvel, confrontando-o com as alternativas existentes no mercado. Para a definição dos indicadores de projet...