RESUMOTrata-se de projeto multidisciplinar envolvendo duas áreas: Engenharia de Produção e Psicologia. Pretende-se desenvolver um modelo matemático, implementado em aplicativo computacional, sustentado nas técnicas Integral-Fuzzy e Redes Neurais Artificiais (RNA), para processar dados oriundos de pesquisas da área de psicologia. Devem ser geradas informações significativas sobre o desempenho cognitivo coletivo e individual de alunos do curso de Engenharia de Produção, permitindo potencializar as políticas educacionais positivas em funcionamento, mitigar outras negativas e sugerir algumas que possam otimizar o potencial do aluno, segundo as suas restrições coletivas e individuais. Foram estudadas as funções cognitivas mais relevantes para se traçar o perfil cognitivo e o Quociente de Inteligência Total (QIT). Tais funções foram transformadas em atributos de entrada do modelo pela identificação do universo de discurso, termos linguísticos e funções de pertinência. Para gerar o QIT, desenvolveu-se uma Rede Neural Artificial que possibilitou reproduzir o pensamento humano sobre o relacionamento com as funções cognitivas. Com base nos dados simulados, concluiu-se que o modelo responde adequadamente. Na amostra avaliada, obteve-se o QIT coletivo de 100,22, denotando desenvolvimento cognitivo médio, podendo variar de 90 até 109, sendo 90 a pior situação. Foram avaliados também os indicadores parciais obtidos a partir da Rede Neural Artificial, com vistas a inferências educacionais. ABSTRACTThis is a multidisciplinary project involving two areas: production and engineering psychology. It is intended to develop a mathematical model, implemented in computer application, sustained on Fuzzy-Integral techniques and artificial neural networks to process data from psychology area of research. Should be generating significant information about the collective cognitive performance and individual students of production engineering, allowing to enhance the positive educational policies in place, mitigate other negative and suggest some that can optimize the potential of the student, according to their collective and individual restrictions. The most important cognitive functions to trace the cognitive profile and Total Intelligence Quotient (TIQ) were studied. These functions have been transformed into model input attributes for identifying the universe of discourse, linguistic terms and membership functions. To generate the TIQ developed an artificial neural network that made it possible to reproduce human thought about the relationship with cognitive function. Based on the simulated data, it was concluded that the model responds appropriately. In the sample was obtained collective TIQ of 100.22, showing Medium cognitive development, ranging from 90 to 109, for 90 the situation worse. Also evaluated the partial indicators obtained from the Artificial Neural Network to translate into educational inferences.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.