Coleção de Trabalhos Apresentados em Eventos
URI permanente para esta coleçãohttps://repositorio.insper.edu.br/handle/11224/3236
Navegar
13 resultados
Resultados da Pesquisa
Trabalho de Evento Study of The Concept of Diesel and Ethanol Dual-Fuel in a SIngle-Cylinder Research Engine(2024) Dias, Fábio Jairo; Lacava, Pedro Teixeira; Oliveira, Enrico Rapetti Malheiro de; Argachoy, CelsoThis study examines the concept of dual-fuel combustion, and focuses in particular on the combination of diesel and ethanol in a compression ignition engine. Ethanol, as a renewable fuel source, plays a fundamental role in reducing dependence on fossil fuels and reducing greenhouse gas emissions. In the test setup ethanol is injected into the intake manifold (Port-Fuel Injection, PFI), while diesel is injected directly into the combustion chamber (Direct Injection, DI). The engine under investigation is a single-cylinder research engine designed to run on two fuels. In this configuration, diesel acts as the ignition fuel, which stimulates the ignition of the ethanol-air mixture. The aim of this study was to analyze the highest rate of substitution of diesel by ethanol while reducing engine load. In the method used the engine was first operated with diesel and ethanol. Subsequently, the ethanol injection was stopped, which led to a decrease in engine load. In order to correct the engine performance and achieve the same load again, the mass of the injected diesel had to be increased. This method has shown that it is possible to achieve the same workload with an ethanol fraction as with diesel alone.. In terms of thermodynamic and emission results, substituting a fraction of diesel with an equivalent amount of ethanol to achieve the same IMEP (Indicated Mean Effective Pressure) is a viable alternative. In addition the presence of ethanol was found to retard combustion compared to running on 100% diesel. The emission results show that dual-fuel operation keeps soot levels close to those achieved when running on diesel alone.Trabalho de Evento Extended Reality System for Robotic Learning from Human Demonstration(2025) Ngui, Isaac; McBeth, Courtney; He, Grace; Santos, André Corrêa; Morales, Marco; LUCIANO PEREIRA SOARES; Amato, Nancy M.Many real-world tasks are intuitive for a human to perform, but difficult to encode algorithmically when utilizing a robot to perform the tasks. In these scenarios, robotic systems can benefit from expert demonstrations, wherein human operators physically move the robot along trajectories, to learn how to perform each task. In many settings, it may be difficult or unsafe to use a physical robot to provide these demonstrations, for example, considering cooking task such as slicing with a knife. Extended reality provides a natural setting for demonstrating robotic trajectories while bypassing safety concerns and providing a broader range of interaction modalities. We propose the Robot Action Demonstration in Extended Reality (RADER) system, a generic extended reality interface for learning from demonstration. We additionally present its application to an existing state-of-the-art learning from demonstration approach and show comparable results between demonstrations given on a physical robot and those given using our extended reality system.Trabalho de Evento Evaluating mastery-oriented grading in an intensive CS1 course(2024) Montagner, Igor dos Santos; RAFAEL CORSI FERRÃO; Kurauchi, Andrew; Silva, Mariana; Zilles, CraigAllowing students to re-attempt assessments has been shown to be effective in traditional university-level courses in improving student mastery of course content. In this paper, we analyse an intensive programming introductory experience, where first semes ter university students’ full load is a single semester-long course that teaches the basics of programming and software engineering. We study its use of mastery-based grading: offering five (formative) low-stakes quizzes (with retakes), each focused on a single topic, and five (summative) higher-stakes exams that assess all learn ing objectives. Our research questions are: (i) “Do second chances help students to increase their performance over time in intensive courses?”; and (ii) “Are second chances effective in reducing stress/- mental load/weight of assessments in intensive courses?”. We find that (i) offering second chances on quizzes decreases the number of students at risk of failing before the first exam; (ii) students’ proficiency in coding tasks (as measured by exam grades) improve during the semester; and (iii) that our schedule reduces anxiety and mental load for students, but only after students take the first chance.Trabalho de Evento Using Multi-objective Optimization to Generate Timely Responsive BDI Agents(2022) Stabile Junior, Márcio FernandoA BDI agent’s ability to perform well depends on its reasoning time.If the reasoning is slow, it is possible that the environment has changed and the action selected is no longer optimal by the time the agent has finished to deliberate. This work then builds a BDI architecture using Anytime Algorithms that can control the amount of time used by the agent to reason and act on the environment. I briefly describe the proposed architecture and its implementation in the Jason agent language.Trabalho de Evento Game development learning with PBL approach as a tool to assess computer engineering competences(2023) Freme, Pedro H. E. P; Sanches, Thiago; LUCIANO PEREIRA SOARESThis paper presents strategies for a Game Development course that aims to develop hard and soft skills in computer engineering students. There is a focus on soft skills that are considered essential for success in the 21st-century professional world. The design for this course is based on the Project-Based Learning approach, which allows students to explore different techniques and encourages creativity, while still having clear objectives and pre-defined milestones. The article discusses the use of continuous monitoring, peer assessments, and the Agile project approach to evaluate student progress and ensure that each student experiences different roles in project management.Trabalho de Evento Adapting SCRUM Ceremonies in Undergraduate Capstone Projects(2022) Ziv, Hadar; Kalafatis, Stavros; LUCIANO PEREIRA SOARES; Prikladnicki, RafaelTrabalho de Evento Pair Teaching in Computer Graphics(2022) LUCIANO PEREIRA SOARES; FABIO ORFALIComputer Graphics is a course commonly found on Computer Science and Computer Engineering undergraduate programs. There are some convenient points on teaching computer graphics in these programs: Computer-Generated Imagery in movies and videogames are relevant examples of applied engineering and science that students experience in their lives, and this can be a potential motivation factor for students to get engaged on learning; furthermore, Computer Graphics relies on several fundamental and complex mathematical concepts, that can also be applied in other science areas, being an opportune moment to cover and practice mathematical learning goals, all connected with a base on computer science. Learning Computer Graphics depends on developing and integrating skills on computer science and mathematics, therefore, a learning plan must cover both topics. However, it must be considered that students need to relate these topics, and this is the trick, since ideally professors need the knowledge and pedagogy in both areas. The strategy presented in this document was based on two professors, one mathematician and one computer engineering, planning, and teaching an elective undergraduate course on Computer Graphics. The course was based on active learning strategies by design, heavily focused on Project Based Learning through three projects starting from scratch, each week learning and implementing new features on the projects. Students must program in regular programming languages like Python, C++ and Javascript, and build up their competence in mathematics from basic math concepts. As a result, students were able to develop a scanline renderer, and a ray-tracing renderer without any graphical Application Programming Interface and finally a 3D web application based on ThreeJS. Although students had a perception of a demanding course, they were engaged on proposed activities during all semester, and were able to implement all important features on projects, often above expectation, showing evidence that learning objectives were achieved.Trabalho de Evento Shedding Light on How Intelligent Techniques can Support Technical Debt Management and Influence Software Quality Attributes(2022) Albuquerque, Danyllo; GRAZIELA SIMONE TONIN; Chagas, Ferdinandy; Perkusich, Mirko; Guimaraes, Everton; Hyggo Almeida; Perkusich, AngeloTechnical Debt (TD) is a consequence of decision-making in the development process that can negatively impact Software Quality Attributes (SQA) in the long term. Technical Debt Management (TDM) is a complex task to minimize TD that relies on a decision process based on multiple and heterogeneous data that are not straightforward to synthesize. Recent studies show that Intelligent Techniques can be a promising opportunity to support TDM activities since they explore data for knowledge discovery, reasoning, learning, or supporting decision-making. Although these techniques can improve TDM activities, there is a need to identify and analyze solutions based on Intelligent Techniques to support TDM activities and their impact on SQA. For doing so, a Systematic Mapping Study was performed, covering publications between 2010 and 2020. From 2276 extracted studies, we selected 111 unique studies. We found a positive trend in applying Intelligent Techniques to support TDM activities being Machine Learning and Reasoning Under Uncertainty the most recurrent ones. Design and Code were the most frequently investigated TD types. TDM activities supported by intelligent techniques impact different characteristics of SQA, mainly Maintainability, Reliability, and Security. Although the research area is up-and-coming, it is still in its infancy, and this study provides a baseline for future research.Trabalho de Evento Exploration and Rescue of Shipwreck Survivors using Reinforcement Learning-Empowered Drone Swarms(2023) Abreu, Leonardo D. M. de; Carrete, Luis F. S.; Castanares, Manuel; Damiani, Enrico F.; Brancalion, Jose Fernando B.; Barth, Fabrício J.The goal of this project is to create a reinforcement learning algorithm that locates shipwrecked individuals using a swarm of drones. A simulated environment was developed to train and visualize the outcome of the trained algorithm considering the ocean’s dynamic circumstances. This project does not discuss image recognition of shipwrecked people, since the true focus of this project is to optimize the search routine of a drone to find the target in the most efficient way possible. The implemented Reinforce algorithm takes into account a dynamic map of probabilities, representing the chances of a person being found, as well as the position of other agents. Outcomes include an open-source Python package for the environment and the implementation of the reinforcement learning algorithm. The algorithm demonstrates superiority over the predefined approach, proving the advantages of reinforcement learning in efficiency and effectiveness.Trabalho de Evento Unsupervised Improvement of Audio-Text Cross-Modal Representations(2023) Wang, Zhepei; Subakan, Cem; Subramani, Krishna; Wu, Junkai; TIAGO FERNANDES TAVARES; FABIO JOSE AYRES; Smaragdis, ParisRecent advances in using language models to obtain cross-modal audio-text representations have overcome the limitations of conventional training approaches that use predefined labels. This has allowed the community to make progress in tasks like zero-shot classification, which would otherwise not be possible. However, learning such representations requires a large amount of human-annotated audio-text pairs. In this paper, we study unsupervised approaches to improve the learning framework of such representations with unpaired text and audio. We explore domain-unspecific and domain-specific curation methods to create audio-text pairs that we use to further improve the model. We also show that when domain-specific curation is used in conjunction with a soft-labeled contrastive loss, we are able to obtain significant improvement in terms of zero-shot classification performance on downstream sound event classification or acoustic scene classification tasks.