Dionne Cavalcante Monteiro

A New Cooperative Evolutionary Multi-Swarm Optimizer Algorithm Based on CUDA Architecture Applied to Engineering Optimization

This paper presents a new Cooperative Evolutionary Multi-Swarm Optimization Algorithm (CEMSO-GPU) based on CUDA parallel architecture applied to solve engineering problems. The focus of this approach is: the use of the concept of master/slave swarm with a mechanism of data sharing; and, the parallelism method based on the paradigm of General Purpose Computing on Graphics Processing Units (GPGPU) with CUDA architecture, brought by NVIDIA corporation. All these improvements were made aiming to produce better solutions in fewer iterations of the algorithm and to improve the search for best results. The algorithm was tested for some well-known engineering problems (WBD, ATD, MWTCS, SRD-11) and the results compared to other approaches.

Ensino e Aprendizagem de Programação: Análise da Aplicação de Proposta Metodológica Baseada no Sistema Personalizado de Ensino

Ensino e aprendizagem de programacao tem sido foco de muitas pesquisas, nas quais se pode destacar uma enfase significativa na questao das dificuldades discentes no entendimento de conceitos relacionados a esse aprendizado. Neste artigo sera apresentada a concepcao e implementacao de um metodo de ensino baseado no Sistema Personalizado de Ensino, e de uma ferramenta integrada ao AVA Moodle, bem como uma analise de resultados de sua implantacao em uma instituicao de ensino. Os resultados obtidos, em confronto com o historico de desempenho na disciplina, sao bastante animadores para a continuidade da aplicacao dessa metodologia.

ALE RPG Jogo Digital para Aprendizado de Crianças em Leitura e Escrita

O trabalho descreve um jogo digital de estilo RPG que possibilita ajudar criancas com deficiencia em leitura e escrita. Para isso insere elementos ludicos no jogo para elevar os aspectos motivacionais das criancas envolvidas.

Optimizing tasks generation for children in the early stages of literacy teaching: a study using bio-inspired metaheuristics

Behavioral teaching procedures can be used to promote the individualized learning of reading skills for children, and computational processes can assist instructors in the generation of a set of tasks. However, the automatic generation of these tasks can be unfeasible due to the high-order search space for the possible combinations of tasks; this complexity increases when considering the possible constraints as well as adapting the tasks to the individual characteristics of each student. This paper presents a new method to automatically generate teaching matching-to-sample tasks, adapting the difficulty by using bio-inspired optimization metaheuristics. Genetic algorithms, ant colony optimization, and integer and categorical particle swarm optimization were evaluated to determine their stability and capacity to generate adapted tasks. A comparison of the results between the algorithms showed a better rate of convergence for the genetic algorithms, which were able to generate tasks at an adapted level of difficulty to students. These tasks were applied to a group of students at a Brazilian public school in the early stages of a literacy course indicating satisfactory effects in the individual learning process.

A Novel Competitive Quantum-Behaviour Evolutionary Multi-Swarm Optimizer Algorithm Based on CUDA Architecture Applied to Constrained Engineering Design

This paper presents a new bio-inspired algorithm named Competitive Quantum-Behaviour Evolutionary Multi-Swarm Optimization (CQEMSO) based on CUDA parallel architecture applied to solve engineering problems, using the concept of master/slave swarm working under a competitive scheme and being executed over the paradigm of General Purpose Computing on Graphics Processing Units (GPGPU). The efforts on implementing the CQEMSO algorithm are focused at generating a solution which includes greater quality of search and higher speed of convergence by using mechanisms of evolutionary strategies with the procedures of search and optimization found in the classic QPSO. For performance analysis, the proposed solution was submitted to some well-known engineering problems (WBD, DPV) and its results compared to other solutions found on scientific literature.

Text2MARK: A text mining tool in the aid of knowledge representation

Representing knowledge in the beginning of the 21st century has become a challenge due to the large volume of information to which we are submitted. Associate intelligent techniques have become a relevant method in this context, however studies are still lacking with the aim of making the process simpler for the user. Considering the current state of the art of NLP text labelers, this proposal is based on texting efficiently and without complexity through the use of free texts. We evaluated this proposal using concept maps to represent knowledge of entity relationships and compared the maps with the approach of the conceptual model. This proposal was able to satisfy the representation with a correct percentage rate of over 90%.

A Fuzzy System for Educational Tasks for Children with Reading and Writing Disabilities

This paper proposes a computational approach that aims the use of Artificial Intelligence in Education (AIED) to aid teachers, psychologists and educationalists in the learning process of reading. This approach aims at generating teaching tasks which can be accordingly adapted to the individual needs of each student. While the tasks are being executed, a Machine Learning (ML) system will collect and process data to allow an analysis of the student’s learning process for each individual word in reading and writing abilities. The fuzzy system will propose an appropriate task based on the data collected by the ML. The output of the fuzzy system is an adapted task that will motivate the children in execution of the tasks.

Máquina de aprendizagem como ferramenta de auxílio na análise comportamental no ensino da leitura

Este artigo descreve um modelo de maquina de aprendizado com o objetivo de auxiliar na analise comportamental de alunos com deficit de aprendizado no processo de ensino da leitura baseado em definicoes de dificuldade formuladas. Com essa analise o analista do comportamento podera obter informacoes do aprendizado individualizado de alunos nas palavras do programa de ensino utilizado, que indicam o estado de conhecimento do aluno sobre uma determinada palavra.

Simulator of the Glycolytic Pathway in a Virtual Reality Environment as a Learning Resource for Teaching Cellular Respiration

The process of cellular respiration approached in molecular biology, specifically glycolysis, have high complexity and abstraction in the approach used in the subjects that explore the theme, especially because of the materials used, making the visualization of chemical reactions and formation of molecular compounds a hard task. Virtual Reality presents itself as a teaching resource for a diverse range of topics, including biology, making it possible to simplificate the learning process of complex subjects. This paper relates the development of a simulator that acts in an Virtual Reality environment to present a glycolytic chain and its interactions between the process substrates, allowing the users to interact, through a Virtual Reality Headset and controllers, the molecular compounds and analyze essential chemical reactions to the cellular respiration process. As result, we have an VR environment that facilitates the learning process and indicates a new teaching tool to molecular biology.

A PSO FPGA based architecture to optimize constrained functions

The search for optimal solutions in Science and Technology is one of the greatest challenges, because performance optimization, especially in complex systems, is often ruled with antagonistic variables such as budget constraints, security requirements and real-time responses. In light of this, many system optimization techniques are constantly being developed and presented to the scientific community. This paper proposes a parallels hardware architecture with FPGA (Field-Programmable Gate Arrays) that can make use of the parallel features that the Swarm Intelligence algorithm PSO (Particle Swarm Optimization) offers to mitigate the engineering Design Pressure Vessel (DPV) problem under constraints. We believe our proposed hardware architecture can be used as an alternative to the PSO software solution because its results are very promising when compared to those obtained by others papers which have relied on software as a solution platform.