Marco Antonio Aceves-Fernández

By Pedraza-Ortega Jesus Carlos, Gorrostieta-Hurtado Efren, Aceves-Fernandez Marco Antonio, Sotomayor-Olmedo Artemio, Ramos-Arreguin Juan Manuel, Tovar-Arriaga Saul and Vargas-Soto Jose Emilio

Part of the book: Fourier Transforms

By Aceves-Fernandez Marco Antonio, Sotomayor-Olmedo Artemio, Gorrostieta-Hurtado Efren, Pedraza-Ortega Jesus Carlos, Ramos-Arreguín Juan Manuel, Canchola-Magdaleno Sandra and Vargas-Soto Emilio

Part of the book: Air Quality

By Gorrostieta-Hurtado Efren, Pedraza-Ortega Jesus Carlos, Aceves-Fernández Marco Antonio, Ramos-Arreguín Juan Manuel, Tovar-Arriaga Saúl and Sotomayor-Olmedo Artemio

Part of the book: Fuzzy Logic

By Marco Antonio Olguin-Sanchez, Marco Antonio Aceves-Fernández, Jesus Carlos Pedraza-Ortega and Juan Manuel Ramos-Arreguín

Forecasting air pollution is a challenging problem today that requires special attention in large cities since they are home to millions of people who are at risk of respiratory diseases every day. At the same time, there has been exponential growth in the research and application of deep learning, which is useful to treat temporary data such as pollution levels, leaving aside the physical and chemical characteristics of the particles and only focusing on predicting the next levels of contamination. This work seeks to contribute to society by presenting a useful way to optimize recurrent neural networks of the short and long-term memory type through a statistical process (Gaussian processes) for the correct optimization of the processes.

Part of the book: Swarm Intelligence

By Jose Luis Maciel-Jacobo, Marco Antonio Aceves-Fernández, Jesus Carlos Pedraza-Ortega and Efren Gorrostieta-Hurtado

In this comprehensive research project, our goal is to predict the concentration levels of PM2.5, a critical air pollutant, in Mexico City. To address this challenge, we use an innovative approach based on the transformer model, specifically a modified version called the Informer. This project focuses on improving air quality prediction, a key step in tackling public health concerns and aiding decision-making in environmental management in one of the world’s most densely populated cities. We trained the Informer model using a robust dataset of historical air quality records and evaluated its performance with standard metrics: mean absolute error (MAE) and mean squared error (MSE). The results showed MAE values of 4.6266 and 5.5844, and MSE values of 40.7972 and 55.4009 for each monitoring station, demonstrating the model’s effectiveness in predicting PM2.5 levels. These results highlight the potential of the Informer in enhancing air quality management strategies. We also compared the Informer’s performance with the LSTM model, showing that the Informer not only competes with but may outperform the LSTM in air quality prediction tasks. This underscores the promise of the Informer for future environmental monitoring.

Part of the book: Artificial Intelligence Annual Volume 2024