Cardiovascular diseases claim millions of lives each year, yet timely diagnosis remains a significant challenge due to the high number of patients and associated costs. Although various machine learning solutions have been proposed for this problem, most approaches rely on careful data preprocessing and feature engineering workflows that could benefit from more comprehensive documentation in research publications. To address this issue, this paper presents a machine learning framework for predicting heart attack risk online. Our systematic methodology integrates a unified pipeline featuring advanced data preprocessing, optimized feature selection, and an exhaustive hyperparameter search using cross-validated grid evaluation. We employ a metamodel ensemble strategy, testing and combining six traditional supervised models along with six stacking and voting ensemble models. The proposed system achieves accuracies ranging from 90.2% to 98.9% on three independent clinical datasets, outperforming current state-of-the-art methods. Additionally, it powers a deployable, lightweight web application for real-time decision support. By merging cutting-edge AI with clinical usability, this work offers a scalable solution for early intervention in cardiovascular care.

La predicción precisa de la velocidad del viento es importante para optimizar la generación de energía eólica, ya que mejora la planificación del suministro eléctrico y el mantenimiento de los aerogeneradores. Este trabajo propone un modelo híbrido que integra la Transformada Wavelet Discreta (DWT por sus siglas en inglés) con redes neuronales LSTM para el pronóstico a corto plazo. Se utilizó una serie temporal de datos de velocidad de viento de Nizanda, Oaxaca, aplicando la wavelet Daubechies 4 (db4) para descomponer la señal en componentes de aproximación y detalles. Se evaluaron múltiples configuraciones de reconstrucción parcial para filtrar el ruido y resaltar patrones relevantes. Los resultados experimentales muestran que la reconstrucción selectiva utilizando la aproximación y los primeros dos primeros niveles de detalle, no solo supera al modelo base, el cual consiste en una LSTM alimentada con datos de velocidad de viento sin transformada wavelet, sino también a los modelos tradicionales de referencia (persistencia, ARIMA, SARIMA). Esta configuración alcanzó un R2 de 0.934 y un RMSE de 0.979 en el conjunto de prueba.

This work presents an automatic detection system for the mite Phyllocoptruta oleivora using deep learning image classification. Three convolutional archi- tectures (a base CNN, MobileNetV2, and ResNet50) are compared under a homogeneous preprocessing, transfer learning, and data augmentation protocol. From a set of images captured in the field and validated by experts, the results show that a lightweight model such as MobileNetV2 offers the best balance between performance, robustness, and computational efficiency for deployment in agricultural environments. On the other hand, ResNet50 is presented as a competitive alternative when greater computing power is available. Design con- siderations, limitations, and future directions oriented toward mobile applications and monitoring platforms in precision agriculture are discussed.