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


Allan Antonio Flores-Fuentes has a total of 58 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Prediction of H2–CNT Interaction Energies on a Chiral (2,1) Carbon Nanotube Using Multilayer Perceptrons

    by Luis Josimar Vences Reynoso, Roberto Alejo Eleuterio, Everardo Efrén Granda Gutiérrez, Daniel Villanueva Vázquez, Juan Horacio Pacheco Sánchez, Allan A. Flores Fuentes, Federico Del Razo López

    Accurate estimation of molecule–nanotube interaction energies is critical for the computational screening of carbon-based materials for hydrogen storage; however, density functional theory (DFT) calculations remain computationally expensive for extensive configurational sampling. In this work, we develop a multilayer perceptron (MLP) surrogate model to predict H2–CNT interaction energies, represented by Eads, for H2 interactions with a chiral (2,1) carbon nanotube. A curated dataset comprising 696 configurations was generated using DMol3 (BIOVIA Materials Studio), varying intermolecular distance, molecular orientation, and interaction site across three regions: internal cavity, edges, and external surface. The proposed MLP architecture (64–32–1) incorporates GELU activation functions, L2 regularization, and dropout to improve generalization. The model achieves coefficients of determination in the range R2 = 0.90–0.96 across all interaction regions, with particularly strong performance at the nanotube edges (R2 = 0.9358, MSE = 0.046 eV2), as well as on the external surface (R2 = 0.9625, MSE = 0.574 eV2) and within the internal cavity (R2 = 0.9051, MSE = 1.506 eV2). The original Eads distribution had a mean of 4.0955 eV and a sample standard deviation of 4.3189 eV. The elevated energy values observed in the internal cavity (up to 12 eV) are consistent with steric repulsion induced by geometric confinement rather than predictive artifacts. The trained MLP showed close agreement with DFT-derived trends, enabling exploration of interaction-energy landscapes spanning both attractive and repulsive regimes. These results indicate that MLP-based models trained on diverse configurational datasets provide a computationally efficient alternative for screening carbon nanostructures in hydrogen storage applications, without substantially compromising accuracy relative to first-principles methods.

  • Open Access

    Python-based web tool to simulate atomic optical emission spectra

    by O. Rosales-Martínez, Allan A. Flores-Fuentes, R. Peña-Eguiluz, A. Mercado-Cabrera, E. E. Granda-Guitérrez, J. F. García-Mejía

    Optical emission spectroscopy (OES) is an experimental technique for analyzing, diagnosing, and characterizing atomic and molecular species in physics and chemistry. In this work, an interactive web tool is designed to simulate atomic OES from which users can generate synthetic data from optical emission spectra at a wavelength range from 390 to 700 nm with any reported energy level. The reference data for eighty-three elements was retrieved from the National Institute of Standards and Technology (NIST) using web scraping techniques. The web tool incorporates key parameters such as wavelength step size (λ), full width at half maximum (FWHM), and emission source temperature (T). The proposed method for generating spectra consists of preprocessing, calculation, and plotting of the data using Python, Pandas, NumPy, and Matplotlib, respectively. Finally, the interactive user interface, built with the open-source Python framework Streamlit, displays changes in spectral plots generated from input data and updates live, supporting zoom, serving as a valuable resource for researchers and students in the field of OES.

  • Stress Detection of Students via Low-Resolution Thermal Images Using ROIs

    by Miguel Angel López-Pérez, Rosa María Valdovinos, Cristian Yuriana González, Allan Antonio Flores-Fuentes, Rosendo Peña-Eguiluz, González


  • Open Access

    Spectral Derivatives Improve FTIR-Based Machine Learning Classification of Plastic Polymers

    by Octavio Rosales-Martínez, Everardo Efrén Granda-Gutiérrez, René Arnulfo García-Hernández, Roberto Alejo-Eleuterio, Allan Antonio Flores-Fuentes

    Accurate identification of plastic polymers is essential for effective recycling, quality control, and environmental monitoring. This study assesses how spectral derivative preprocessing affects the classification of six common plastic polymers: Polyethylene Terephthalate (PET), Polyvinyl Chloride (PVC), Polypropylene (PP), Polystyrene (PS), and both High- and Low-Density Polyethylene (HDPE and LDPE), based on Fourier Transform Infrared (FTIR) spectroscopy data acquired at a resolution of 8 cm−1. Using Savitzky–Golay derivatives (orders 0, 1, and 2), five machine learning algorithms, namely Multilayer Perceptron (MLP), Extremely Randomized Trees (ET), Linear Discriminant Analysis (LDA), Support Vector Classifier (SVC), and Random Forest (RF), were tested within a strict framework involving stratified repeated cross-validation and a final hold-out test set to evaluate generalization. The first spectral derivative notably improved the model performance, especially for MLP and SVC, and increased the stability of the ET, LDA, and RF classifiers. The combination of the first derivative with the ET model provided the best results, achieving a mean F1-score of 0.99995 (±0.00033) in cross-validation and perfect classification (1.0 in Accuracy, F1-score, Cohen’s Kappa, and Matthews Correlation Coefficient) on the independent test set. LDA also performed very well, underscoring the near-linear separability of spectral data after derivative transformation. These results demonstrate the value of derivative-based preprocessing and confirm a robust method for creating high-precision, interpretable, and transferable machine learning models for automated plastic polymer identification.


  • LQR Control Tuning Applied in a 2-DoF Helicopter Based on Optimization Algorithms

    by García Jaime Jhovani, García Mejía Juan Fernando, Granda Gutiérrez Everardo Efrén, Flores Fuentes Allan Antonio


  • Open Access

    Design of a LQR by a WOA Applied to the Position Regulation of a Pivoted Helicopter

    by Jhovani García-Jaime, Juan Fernando García-Mejía, Everardo Efrén Granda-Gutiérrez, Allan Antonio Flores-Fuentes, Ricardo Arturo Vázquez-Robledo, Rigoberto Reyes-Morales

    Un área de aplicación de la Inteligencia Artificial es el diseño de reguladores de posición de helicópteros pivotados. Estos comúnmente son controlados por medio de técnicas de control óptimo como los Reguladores Lineales Cuadráticos (LQR), los cuales son susceptibles de optimizarse por medio de algoritmos bio-inspirados. Estos algoritmos permiten la búsqueda eficiente de soluciones en el espacio de parámetros para afinar los reguladores de manera efectiva. Este trabajo de investigación se centra en la optimización inteligente de un LQR para el control de un helicóptero pivotado, por medio de un Algoritmo de Optimización de Ballenas (WOA). Este algoritmo propuesto disminuye significativamente los índices de desempeño del control, con respecto del método de ajuste analítico y un Algoritmo Genético.

  • Open Access

    Application of the Honey Badger Algorithm in the Cooling Regulation of Thermoelectric Cells

    by García- Mejía, Juan Fernando, Granda- Gutiérrez, Everardo Efrén, Allan Antonio Flores-Fuentes, José Antonio, Vázquez- Robledo, Ricardo Arturo

    En este artículo se presenta un algoritmo basado en inteligencia de enjambre llamado Algoritmo de Tejón Mielero, un pequeño mamífero carnívoro que tiene dos atributos que lo caracterizan: su fuerte sentido del olfato para localizar comida y garras lo suficientemente potentes como para cavar con el fin de obtener su alimento. La implementación computacional de este algoritmo basa su funcionamiento en una función cardioide. Como caso de estudio, se diseña un regulador clásico, concretamente un PID aplicado al control de temperatura de una célula termoeléctrica. Los resultados obtenidos con estas heurísticas se comparan, según la literatura especializada, con un regulador diseñado mediante un algoritmo denominado Optimización de inmunidad de rebaño al Coronavirus. La comparación muestra que el algoritmo del Tejón Melero reduce significativamente algunos índices de rendimiento, como el error cuadrático medio, con una convergencia rápida.

  • INFLUENCE OF THE ELECTROLYTE FLOW AND CLEANING AIR PRESSURE ON THE OVERCUT IN BIPOLAR PULSED ELECTROCHEMICAL MICRO-MACHINING PROCESSES

    by Octavio Catarino Aguilar, Everardo Granda Gutierrez, Jose Arturo Perez Martinez, Jose Luis Tapia Fabela, Allan Antonio Flores Fuentes, Juan Fernando Garcia Mejia

    This paper presents an experimental investigation on the reduction of overcutting in the bipolar pulsed electrochemical pulsed machining process. It is described how this unconventional manufacturing method, which involves the anodic dissolution of a metal part immersed in an electrolytic medium, can be improved by incorporating compressed air as a residue-cleaning medium and modifying the electrolyte flow rate to reduce overcutting. These results can be helpful for the inclusion of these variables in process control systems and generate significant improvements in the fabrication of components at micrometer scales. Keywords: micromachining, electrochemical machining, overcut, electrolyte, automatic processes.

  • Machine Learning for Identifying Atomic Species from Optical Emission Spectra Generated by an Atmospheric Pressure Non-thermal Plasma

    by Octavio Rosales-Martínez, Allan A. Flores-Fuentes, Antonio Mercado-Cabrera, Rosendo Peña-Eguiluz, Everardo Efrén Granda-Gutiérrez, Juan Fernando García-Mejía


  • Development and Characterization of a Non-Thermal Plasma Source for Therapeutic Treatments

    by Rosendo Pena-Eguiluz, Jorge H. Serment-Guerrero, Erika P. Azorin-Vega, Antonio Mercado-Cabrera, Allan A. Flores-Fuentes, Betsabeth Jaramillo-Sierra, Alma N. Hernandez-Arias, Karina Giron-Romero, Regulo Lopez-Callejas, Benjamin G. Rodriguez-Mendez, et al.

    Objective: an innovative non-thermal plasma (NTP) system constituted by a radiofrequency (RF) power generator directly coupled to a treatment probe is described and characterized. This system is intended to be applied as a medical device for therapeutic treatments. Methods: electrical characterization of the radiofrequency power generator supplying the treatment probe was performed. Meanwhile, generated NTP was optically analyzed. Obtained data were studied to establish the safety profile of plasma application on heat sensitive matter. Results: the NTP system was validated through bacterial deactivation trials, as well as, of being capable of deactivating carcinogenic cells. Besides promoting and accelerating wound closure in vivo performed in mice, demonstrating faster healing than that done with conventional treatments. Conclusion: the NTP system's characterization is an essential stage to determine the adequate application of the generated plasma over organic media. The therapeutic benefits of the NTP system were proved by the development of in vivo experiences involving laboratory mice. Significance: the generated NTP interacts with surrounding air particles producing reactive oxygen and nitrogen species, which, exhibit bactericidal and antiseptic effects due to their strong biochemical reactivity; functioning like critical mediators in animal physiology and promoting wound healing processes. These properties make the NTP system a feasible technology intended for therapeutic treatments.