Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


João Inácio da Silva Filho has a total of 120 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    RamanScan-PAL2V: digitalização e filtragem de espectros Raman por Lógica Paraconsistente Anotada (LPA2v)

    by Márcio Corrêa, Landulfo Silveira Jr, Marcos Tadeu Pacheco, Joao Inácio Silva Filho

    Much of the reference material in Raman spectroscopy is available only as low-quality images in public databases, with no access to the original numerical series, which prevents comparing, measuring peaks and reprocessing the spectra. This work presents RamanScan-PAL2V, a software that reconstructs the (x,y) series from a spectrum image and treats its noise with a filter based on two-value Paraconsistent Annotated Logic (PAL2v), with an adjustable number of Paraconsistent Artificial Neural Cells of Learning (PANCelll), providing students and researchers with previously inaccessible data and a smoothing that preserves the spectrum structure, demonstrated in a practical digitizing and pre-processing case.

  • Open Access

    Comissão Organizadora XV ENPG

    by João Inácio Silva Filho

    ORGANIZAÇÃO XV ENPG – 2026 Coordenador Geral: Prof. Dr. MARCOS TADEU TAVARES PACHECO COMISSÃO CIENTÍFICA Coordenação: Prof. Dr. JOÃO INÁCIO DA SILVA FILHO ORGANIZAÇÃO DOS ANAIS Coordenação: Prof. Dr. FABIO GIORDANO

  • Open Access

    Programação XV ENPG

    by João Inácio Silva Filho

    O arquivo anexo em apresenta a programação do XV Encontro Nacional de Pós-graduação 2026 realizado na Unisanta.

  • Open Access

    Estudo sobre transferência de oxigênio para água através de Venturi

    by Ronan Sousa, Carlos José Lima, João Inácio Silva Filho

    Oxygen transfer to water is widely used in domestic, industrial, and wastewater treatment settings; it is typically achieved by bubbling gas through a porous component connected to a rigid or flexible gas-conveying conduit, all within a system known as a bubble column reactor. Another method involves a hydrodynamic system driven by a hydraulic pump that forces water flow; connected in series with this pump is a three-way element known as a Venturi injector, which introduces gas into the forced water flow via its third port. The resulting fluid dynamics and mixing offer effective oxygen transfer to the water. This study aims to compare the best method for incorporating oxygen into water at a fixed ambient temperature. Two gasification methods were tested: one using a bubble column reactor and the other employing a hydraulic circuit with a Venturi injector connected to a centrifugal pump. The performance of each method regarding oxygen transfer to the water was evaluated. The results indicated that the hydrodynamic method using the Venturi injector is significantly more efficient at transferring oxygen to the water than the traditional bubble column reactor method. It is concluded that the dynamic action of the water combined with the Venturi injector yields superior oxygenation performance.

  • Open Access

    Inteligência Artificial e Lógicas Paraconsistentes Modernas: Uma Ferramenta de Apoio à Resolução de Inconsistências em Indústrias

    by Thyrson Sousa, João Inácio Silva Filho

    This article addresses the use of Artificial Intelligence integrated with Paraconsistent Logic, which enables the handling of uncertain, incomplete, and contradictory data without interrupting the analysis process. PAL2v represents and processes both favorable and unfavorable evidence, proving useful in automation, industrial control, predictive maintenance, robotics, and decision support. Integrating this approach into the control of systems that handle inconsistent information makes industrial systems more robust and intelligent, capable of making decisions in the face of conflicting information.

  • Open Access

    Aplicação da LPA2v à Modelagem do Experimento Mental do Gato de Schrödinger

    by Alexandre Martins, Marcos Rodrigues, Arnaldo Carvalho Junior, João Inácio da Silva Filho

    This paper presents an approach to modeling Schrödinger's Cat thought experiment using Paraconsistent Annotated Logic with annotation of two values (PAL2v). In quantum mechanics, state superposition challenges the classical Principle of Non-Contradiction, generating ambiguities in interpreting wave-function collapse. Through the PAL2v formalism, life and death states are mapped onto a two-value annotation lattice (μ, λ), representing degrees of favorable and unfavorable evidence. It is shown that the quantum superposition state can be analytically represented in the paraconsistent lattice without logical trivialization, providing a quantitative metric, Degree of Certainty (DC) and Degree of Contradiction (DCt), before and after measurement.

  • Open Access

    Controle de qualidade dimensional em esteira transportadora com Lógica Paraconsistente Anotada: a grandeza que decide

    by Alessandro Lima, João Inácio Silva Filho

    Automated dimensional inspection decides by comparison against a threshold, and disagreement between two sensors measuring the same part is usually removed by averaging before the decision. This work applies Paraconsistent Annotated Logic with annotation of two values to a conveyor belt quality gate, with two ultrasonic sensors assessing the proposition "the part measures between 1.0 and 1.5 cm". Numerical validation showed that the Para-Analyzer algorithm, by testing the Degree of Certainty before the Degree of Contradiction, approves parts while the sensors disagree by more than half the tolerance. Deciding by the Real Degree of Certainty fixes the case with no arbitrary threshold.

  • Open Access

    Paraconsistent-Lib: An Intuitive PAL2v Algorithm Python Library

    by Arnaldo De Carvalho Junior, Diego Oliveira da Cruz, Bruno da Silva Alves, Fernando da Silva Paulo Junior, João Inacio da Silva Filho

    This paper introduces Paraconsistent-Lib, an open-source, easy-to-use Python library for building PAL2v algorithms in reasoning and decision-making systems. Paraconsistent-Lib is designed as a general-purpose library of PAL2v standard calculations, presenting three types of results: paraconsistent analysis in one of the 12 classical lattice PAL2v regions, paraconsistent analysis node (PAN) outputs, and a decision output. With Paraconsistent-Lib, well-known PAL2v algorithms such as Para-analyzer, ParaExtrCTX, PAL2v Filter, paraconsistent analysis network (PANnet), and paraconsistent neural network (PNN) can be written in stand-alone or network form, reducing complexity, code size, and bugs, as two examples presented in this paper. Given its stable state, Paraconsistent-Lib is an active development to respond to user-required features and enhancements received on GitHub.

  • Open Access

    Aprendizado de máquina sem matemática e programação: um relato de experiência de uma abordagem utilizando o software Orange Data Mining para alunos de administração

    by Samuel Pinheiro Goncalves, Landulfo Silveira Júnior, João Inácio da Silva Filho

    Este artigo é um relato de experiência no ensino de aprendizado de máquina (AM) com alunos de graduação em Administração de empresas, sem precisarem ter conhecimentos avançados de matemática e algoritmos de programação. Utilizando o software Orange Data Mining, os alunos aprenderam conceitos de AM e aplicaram algoritmos de classificação e regressão para resolver problemas aplicados à sua área de formação. A abordagem centrada no software Orange facilitou a compreensão dos alunos, com sua interface predominantemente visual e bem amigável para experimentação em AM e com facilidade de interpretação de resultados. O relato destaca a eficácia do software Orange como uma ferramenta educacional, promovendo uma compreensão prática dos conceitos de AM contribuindo assim para uma formação mais completa e atualizada dos futuros profissionais de Administração.

  • Open Access

    Paraconsistent Artificial Neural Network (PANnet) applied to the Detection of (NOx) Nitrogen Oxides Emissions in Petrochemical Combustion Systems

    by Marcos Carneiro Rodrigues, Arnaldo de Carvalho Junior, Aldo Ramos Santos, Mauricio Conceição Mario, Vitor da Silva Rosa, João Inácio da Silva Filho, Hyghor Miranda Côrtes, Dorotéa Vilanova Garcia, Fábio Giordano, Germano Lambert-Torres

    The emissions of nitrogen oxides (NOx) that are produced during the combustion of fossil fuels in the petrochemical and metallurgical industries, when combined with other types of pollutants, can have significant impacts on human health and the environment. Therefore, it is essential to investigate techniques that allow the optimization of burning in industrial furnaces with moderate levels of NOx emissions and, for this, computational learning structures that detect and prevent emissions can create efficient AI models. With this objective, we present in this article an Artificial Neural Network-ANN composed of algorithms based on Paraconsistent Annotated Logic-PAL, which is a branch of non-classical logics that deals with situations in which data contains contradictions and inconsistencies in its information. The learning data used was obtained from a 6-burner Vertical Cylinder Industrial Furnace that is in operation in the Oil Refining process in Brazil. In the data preprocessing phase for training the PANNet structure, real data on the inlet air flow rate during combustion and real fuel flow rate data were used. These values collected in the SCADA system were transformed into normalized degrees of evidence and then applied to the PANNet inputs, creating support patterns for estimating and optimizing the combustion process. The comparative results with a conventional ANN showed that the Paraconsistent Artificial Neural Network-PANNet presents superior performance parameters, thus highlighting its efficiency in creating models that deal with complex modeling problems to estimate industrial NOx emissions in combustion furnaces.