Publications by authors named "Jose Tuxpan-Vargas"

This systematic review provides a state-of-art of Artificial Intelligence (AI) models such as Machine Learning (ML) and Deep Learning (DL) development and its applications in Mexico in diverse fields. These models are recognized as powerful tools in many fields due to their capability to carry out several tasks such as forecasting, image classification, recognition, natural language processing, machine translation, etc. This review article aimed to provide comprehensive information on the Machine Learning and Deep Learning algorithms applied in Mexico.

View Article and Find Full Text PDF
Article Synopsis
  • Marine oil spills are a global concern that need effective tools for response and recovery, leading to the exploration of Deep Learning models for classification and segmentation using Sentinel-1 SAR imagery.
  • Researchers created a new dataset and tested 90 configurations of Convolutional Neural Networks (CNNs) for classification, finding that a model with six layers and 32 filters achieved 99% accuracy.
  • For segmentation, the U-Net model demonstrated 99% accuracy and 96% Intersection over Union (IoU) with specific configurations, resulting in a proposed framework achieving 95% overall accuracy and 90% IoU.
View Article and Find Full Text PDF

Water shortage and contamination is a problem worldwide, impacting the human health. This research provides a comprehensive assessment of water quality and its possible impact on public health in San Luis Potosi, a region in Mexico facing critical water challenges. Throughout the study of various pollutant sources, the contaminants were identified and analyzed.

View Article and Find Full Text PDF

This study aims to improve the current method of studying potentially toxic elements (PTEs) in urban dust using direct chemical evidence (from dust, rock, and emission source samples) and robust geochemical methods. The provenance of urban dust was determined using rare earth elements (REEs) and geochemical diagrams (V-Ni-Th*10, TiO vs. Zr, and Zr/Ti vs.

View Article and Find Full Text PDF

The method's development to detect oil-spills, and concentration monitoring of marine environments, are essential in emergency response. To develop a classification model, this work was based on the spectral response of surfaces using reflectance data, and machine learning (ML) techniques, with the objective of detecting oil in Landsat imagery. Additionally, different concentration oil data were used to obtain a concentration-estimation model.

View Article and Find Full Text PDF