RCRoberto Castaneda-Sheissa

Roberto Castaneda-Sheissa

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Roberto Castaneda-Sheissa has a total of 28 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    A Novel Dataset for Early Cardiovascular Risk Detection in School Children Using Machine Learning

    by Rafael Alejandro Olivera Solís, Emilio Francisco González Rodríguez, Roberto Castañeda Sheissa, Juan Valentín Lorenzo-Ginori, José García

    This study introduces the PROCDEC dataset, a novel collection of 1140 cases with 30 cardiovascular risk factors gathered over a 10-year period from school children in Santa Clara, Cuba. The dataset was curated with input from medical experts in pediatric cardiology, endocrinology, general medicine, and clinical laboratory, ensuring its clinical relevance. We conducted a rigorous performance evaluation of 10 machine learning (ML) algorithms to classify cardiovascular risk into two categories: at risk and not at risk. The models were assessed using a stratified k-fold cross-validation approach to enhance the reliability of the findings. Among the evaluated models—Bayes Net, Naive Bayes, SMO, K-Nearest Neighbors (KNN), Logistic Regression, AdaBoost, Multilayer Perceptron (MLP), J48, Logistic Model Tree (LMT), and Random Forest (RF)—the best-performing classifiers (MLP, LMT, J48 and Logistic Regression) achieved F1-score values exceeding 0.83, indicating strong predictive capability. To improve interpretability, we employed feature selection techniques to rank the most influential risk factors. Key contributors to classification performance included hypertension, hyperreactivity, body mass index (BMI), uric acid, cholesterol, parental hypertension, and sibling dyslipidemia. These findings align with established clinical knowledge and reinforce the potential of ML models for pediatric cardiovascular risk assessment. Unlike previous studies, our research not only evaluates multiple ML techniques but also emphasizes their clinical applicability and interpretability, which are critical for real-world implementation. Future work will focus on validating these models with external datasets and integrating them into decision-support systems for early risk detection.

  • Open Access

    FPGA Implementation of Homotopic Path Planning Method with Automatic Assignment of Repulsion Parameter

    by Hector Eduardo De Cos-Cholula, Gerardo Ulises Diaz-Arango, Luis Hernandez-Martinez, Hector Vazquez-Leal, Arturo Sarmiento-Reyes, Maria Teresa Sanz-Pascual, Agustin Leobardo Herrera-May, Roberto Castaneda-Sheissa

    In recent times, autonomous robots have become more relevant, aiming not only to be an extension of mobility and human performance but also allowing them to independently solve specific problems such as finding free-collision paths within some defined environments. In order to achieve this, several techniques have been developed, like action-reaction algorithms, sampling-based algorithms, and deterministic algorithms such as the Homotopy Path Planning Method (HPPM). This work presents, for the first time, a complete deterministic collision-free path planning scheme implemented in FPGA, which is mounted on a Scribbler 2 robot from Parallax. Then, an automatic algorithm of the repulsion parameter for the HPPM method is presented, using as a reference the minimum distance between the center of each obstacle with respect to the homotopic ideal path; furthermore, an algorithm is proposed for discriminating dead-end routes and collision risk trajectories, which allows us to obtain a feasible free-collision path that takes into account the robot dimensions. Besides, comparative performance tests have been carried out against other path-finding methods from the low degrees of freedom (low DoF) and sampling-based planners. Our proposal exhibits path calculation times which are 5 to 10 times faster on FPGA implementation, compared to the other methods and 10 to 100 times faster on PC implementation also compared to the rest. Similar results are obtained with regards to memory consumption, namely 20 to 200 times lower on FPGA implementation and 10 to 100 times lower on PC implementation.


  • Open Access

    Speed-up hyperspheres homotopic path tracking algorithm for PWL circuits simulations

    by A. Ramirez-Pinero, H. Vazquez-Leal, V. M. Jimenez-Fernandez, H. M. Sedighi, M. M. Rashidi, U. Filobello-Nino, R. Castaneda-Sheissa, J. Huerta-Chua, L. A. Sarmiento-Reyes, J. R. Laguna-Camacho, et al.


  • Open Access

    A handy approximation for a mediated bioelectrocatalysis process, related to Michaelis-Menten equation

    by Uriel Filobello-Nino, Hector Vazquez-Leal, Brahim Benhammouda, Luis Hernandez-Martinez, Yasir Khan, Victor Manuel Jimenez-Fernandez, Agustin Leobardo Herrera-May, Roberto Castaneda-Sheissa, Domitilo Pereyra-Diaz, Juan Cervantes-Perez, et al.

    In this article, Perturbation Method (PM) is employed to obtain a handy approximate solution to the steady state nonlinear reaction diffusion equation containing a nonlinear term related to Michaelis-Menten of the enzymatic reaction. Comparing graphics between the approximate and exact solutions, it will be shown that the PM method is quite efficient.


  • Open Access

    Symbolic analysis and reordering of nonlinear circuit's equations in order to accelerate homotopy simulation

    by H. Vazquez-Leal, A. Sarmiento-Reyes, Y. Khan, L. Hernandez-Martinez, J. Sanchez-Orea, A. Herrera-May, V.M. Jimenez-Fernandez, A. Diaz-Sanchez, J. Huerta-Chua, R. Castaneda-Sheissa