Aurora Torres Soto
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Aurora Torres Soto has a total of 42 co-authors. Here are the top co-authors by number of shared publications:
- María Dolores Torres Soto
Universidad Autónoma de Aguascalientes
11 shared publications - Alberto Ochoa-Zezzatti
Universidad Autónoma de Ciudad Juárez
3 shared publications - Daniel Alejandro Barajas Aranda
Universidad Autónoma de Aguascalientes
3 shared publications - Eunice Esther Ponce-De-Leon-Senti
Universidad Autónoma de Aguascalientes
3 shared publications - María Dolores Torres Soto
Universidad Autónoma de Aguascalientes
3 shared publications - Alexis Edmundo Gallegos Acosta
Benemérita Universidad Autónoma de Aguascalientes
2 shared publications
Latest Publications
- 4 November 2026
- Published by Springer Nature
- p. 414-433
Mexican Traffic Sign Detection and Recognition Using Convolutional Neural Networks and YOLO11n Architecture
- 4 November 2026
- Published by Springer Nature
- p. 414-433
Mexican Traffic Sign Detection and Recognition Using Convolutional Neural Networks and YOLO11n Architecture
- 4 November 2026
- Published by Springer Nature
- p. 296-314
Artificial Intelligence for Pulmonary Disease Diagnosis: A Comparative Review of Medical Imaging Modalities and Deep Learning Approaches
- 4 November 2026
- Published by Springer Nature
- p. 296-314
Artificial Intelligence for Pulmonary Disease Diagnosis: A Comparative Review of Medical Imaging Modalities and Deep Learning Approaches
- 3 November 2026
- Published by Springer Nature
- p. 282-293
Intelligent Geographic Model for Crime Prevention in Aguascalientes: Random Forest and SVM
- 3 November 2026
- Published by Springer Nature
- p. 282-293
Intelligent Geographic Model for Crime Prevention in Aguascalientes: Random Forest and SVM
- 1 October 2025
- Published by Springer Nature
- p. 161-169
Mobile-Optimized Fake News Detection: A Comparative Study of Classic Machine Learning and Transformer-Based Models
- 1 October 2025
- Published by Springer Nature
- p. 161-169
Mobile-Optimized Fake News Detection: A Comparative Study of Classic Machine Learning and Transformer-Based Models
- 1 October 2025
- Published by Springer Nature
- p. 42-53
Automated Information Extraction from Construction Regulations Using LangChain: A Case Study in Aguascalientes
- 1 October 2025
- Published by Springer Nature
- p. 42-53
Automated Information Extraction from Construction Regulations Using LangChain: A Case Study in Aguascalientes
- 1 October 2025
- Published by Springer Nature
- p. 51-61
Genetic Algorithm Focused on Automatic Design of Passive Analog Filters
- 1 October 2025
- Published by Springer Nature
- p. 51-61
Genetic Algorithm Focused on Automatic Design of Passive Analog Filters
- 12 December 2024
- Published by Springer Nature
- p. 133-152
Mood-Based Prioritization Model in People with Suicidal Tendencies Using Topsis
- 12 December 2024
- Published by Springer Nature
- p. 133-152
Mood-Based Prioritization Model in People with Suicidal Tendencies Using Topsis
- Open Access
- 4 December 2024
- Published by Universidad de Guadalajara in RECIBE, REVISTA ELECTRÓNICA DE COMPUTACIÓN, INFORMÁTICA, BIOMÉDICA Y ELECTRÓNICA
- Vol. 13 (3) , E3-8
Desarrollo de un agente inteligente capaz de jugar un videojuego de peleas
Los videojuegos son una herramienta importante como campo de pruebas de algoritmos de aprendizaje por refuerzo, sin embargo, también son una buena herramienta para generar inteligencia artificial para los mismos. Esta investigación se dividió en dos fases generales, el desarrollo de un demo de videojuego de peleas llamado Brain Fighter y la creación de un modelo de aprendizaje por refuerzo basado en el algoritmo llamado Proximal Policy Optimization para entrenar un agente inteligente de modo que sea capaz de jugar satisfactoriamente Brain Fighter.En este artículo se presenta el mejor modelo obtenido como resultado de haber experimentado con seis modelos diferentes, además se expone la metodología utilizada para llevar a cabo toda la investigación, que constituye desde la creación de Brain Fighter en Unity, la elección del algoritmo de aprendizaje por refuerzo a utilizar disponible en ML Agents, la creación del modelo, el entrenamiento y los resultados obtenidos además de las conclusiones generales del trabajo.
- 4 December 2024
- Published by Universidad de Guadalajara in RECIBE, REVISTA ELECTRÓNICA DE COMPUTACIÓN, INFORMÁTICA, BIOMÉDICA Y ELECTRÓNICA
- Vol. 13 (3) , E3-8
Open AccessDesarrollo de un agente inteligente capaz de jugar un videojuego de peleas
Los videojuegos son una herramienta importante como campo de pruebas de algoritmos de aprendizaje por refuerzo, sin embargo, también son una buena herramienta para generar inteligencia artificial para los mismos. Esta investigación se dividió en dos fases generales, el desarrollo de un demo de videojuego de peleas llamado Brain Fighter y la creación de un modelo de aprendizaje por refuerzo basado en el algoritmo llamado Proximal Policy Optimization para entrenar un agente inteligente de modo que sea capaz de jugar satisfactoriamente Brain Fighter.En este artículo se presenta el mejor modelo obtenido como resultado de haber experimentado con seis modelos diferentes, además se expone la metodología utilizada para llevar a cabo toda la investigación, que constituye desde la creación de Brain Fighter en Unity, la elección del algoritmo de aprendizaje por refuerzo a utilizar disponible en ML Agents, la creación del modelo, el entrenamiento y los resultados obtenidos además de las conclusiones generales del trabajo.
- 17 October 2024
- Published by Springer Nature
- p. 154-167
From EEG Signal Acquisition and Classification to Mobile Integration: A Comprehensive Framework
- 17 October 2024
- Published by Springer Nature
- p. 154-167
From EEG Signal Acquisition and Classification to Mobile Integration: A Comprehensive Framework
- 1 January 2024
- Published by UK Zhende Publishing Limited Company in DYNA New Technologies
- Vol. 11 (1) , [10P.]
COMPARISON AND EXPLANABILITY OF MACHINE LEARNING MODELS IN PREDICTIVE SUICIDE ANALYSIS
In this comparative study of machine learning models for predicting suicidal behavior, three approaches were evaluated: neural network, logistic regression, and decision trees. The results revealed that the neural network showed the best predictive performance, with an accuracy of 82.35%, followed by logistic regression (76.47%) and decision trees (64.71%). Additionally, the explainability analysis revealed that each model assigned different importance to the features in predicting suicidal behavior, highlighting the need to understand how models interpret features and how they influence predictions. The study provides valuable information for healthcare professionals and suicide prevention experts, enabling them to design more effective interventions and better understand the risk factors associated with suicidal behavior. However, it is noted the need to consider other factors, such as model interpretability and its applicability in different contexts or populations. Furthermore, further research and validation in different datasets are recommended to strengthen the understanding and applicability of the models in different contexts. In summary, this study significantly contributes to the field of predicting suicidal behavior using machine learning models, offering a detailed insight into the strengths and weaknesses of each approach and highlighting the importance of model interpretation for better understanding the underlying factors of suicidal behavior. Key words: Suicidal behavior prediction, Machine learning models, Neural network, Logistic regression, Decision tres, Explainability análisis, Healthcare intervention
- 1 January 2024
- Published by UK Zhende Publishing Limited Company in DYNA New Technologies
- Vol. 11 (1) , [10P.]
COMPARISON AND EXPLANABILITY OF MACHINE LEARNING MODELS IN PREDICTIVE SUICIDE ANALYSIS
In this comparative study of machine learning models for predicting suicidal behavior, three approaches were evaluated: neural network, logistic regression, and decision trees. The results revealed that the neural network showed the best predictive performance, with an accuracy of 82.35%, followed by logistic regression (76.47%) and decision trees (64.71%). Additionally, the explainability analysis revealed that each model assigned different importance to the features in predicting suicidal behavior, highlighting the need to understand how models interpret features and how they influence predictions. The study provides valuable information for healthcare professionals and suicide prevention experts, enabling them to design more effective interventions and better understand the risk factors associated with suicidal behavior. However, it is noted the need to consider other factors, such as model interpretability and its applicability in different contexts or populations. Furthermore, further research and validation in different datasets are recommended to strengthen the understanding and applicability of the models in different contexts. In summary, this study significantly contributes to the field of predicting suicidal behavior using machine learning models, offering a detailed insight into the strengths and weaknesses of each approach and highlighting the importance of model interpretation for better understanding the underlying factors of suicidal behavior. Key words: Suicidal behavior prediction, Machine learning models, Neural network, Logistic regression, Decision tres, Explainability análisis, Healthcare intervention