Francisco Charte
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Francisco Charte has a total of 55 co-authors. Here are the top co-authors by number of shared publications:
- Antonio Jesús Rivera
University of Jaén
36 shared publications - María José del Jesus
University of Jaén
30 shared publications - Francisco Herrera
University of Granada
14 shared publications Francisco Herrera
12 shared publications- David Charte
University of Granada
9 shared publications - María Dolores Pérez-Godoy
University of Jaén
8 shared publications
Latest Publications
- 6 November 2026
- Published by Springer Nature
- p. 167-179
A Study on Self-supervised Learning Objectives for Intrusion Detection
- 6 November 2026
- Published by Springer Nature
- p. 167-179
A Study on Self-supervised Learning Objectives for Intrusion Detection
- 1 October 2025
- Published by Springer Nature
- p. 561-574
MORENA: Empty Images Detection Based on Unsupervised Reconstruction Error Analysis
- 1 October 2025
- Published by Springer Nature
- p. 561-574
MORENA: Empty Images Detection Based on Unsupervised Reconstruction Error Analysis
- Open Access
- 6 March 2024
- Published by Elsevier in Neurocomputing
- Vol. 580
DESReg: Dynamic Ensemble Selection library for Regression tasks
- 6 March 2024
- Published by Elsevier in Neurocomputing
- Vol. 580
Open AccessDESReg: Dynamic Ensemble Selection library for Regression tasks
- 1 October 2023
- Published by Springer Nature
- p. 39-51
NOSpcimen: A First Approach to Unsupervised Discarding of Empty Photo Trap Images
- 1 October 2023
- Published by Springer Nature
- p. 39-51
NOSpcimen: A First Approach to Unsupervised Discarding of Empty Photo Trap Images
- Open Access
- 16 September 2023
- Published by Elsevier in Neurocomputing
- Vol. 559
mldr.resampling: Efficient reference implementations of multilabel resampling algorithms
- 16 September 2023
- Published by Elsevier in Neurocomputing
- Vol. 559
Open Accessmldr.resampling: Efficient reference implementations of multilabel resampling algorithms
- 21 April 2023
- Published by The R Foundation
mldr.resampling: Resampling Algorithms for Multi-Label Datasets
- 21 April 2023
- Published by The R Foundation
mldr.resampling: Resampling Algorithms for Multi-Label Datasets
- Open Access
- 20 January 2023
- Published by Elsevier in Artificial Intelligence in Medicine
- Vol. 137, 102494
XAIRE: An ensemble-based methodology for determining the relative importance of variables in regression tasks. Application to a hospital emergency department
- 20 January 2023
- Published by Elsevier in Artificial Intelligence in Medicine
- Vol. 137, 102494
Open AccessXAIRE: An ensemble-based methodology for determining the relative importance of variables in regression tasks. Application to a hospital emergency department
- 29 June 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-7
Low-cost IoT gas concentrator system prototype
Currently, IoT (Internet of Things) applications based on gas monitoring are essential for areas such as food, health and industry, examples of which are detecting the fresh-ness of food [1], gastrointestinal diseases [2] or pipe leaks [3]. IoT systems are based on one or more electronic devices with sensors and/or actuators that send information to the outside for monitoring. A major drawback to overcome is the high cost of these devices or IoT systems. This paper presents a low-cost IoT system for gas concentrators to detect anomalies. This IoT system, which has been evaluated, concentrates and analyses exhaled air using an MQ sensor.
- 29 June 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-7
Low-cost IoT gas concentrator system prototype
Currently, IoT (Internet of Things) applications based on gas monitoring are essential for areas such as food, health and industry, examples of which are detecting the fresh-ness of food [1], gastrointestinal diseases [2] or pipe leaks [3]. IoT systems are based on one or more electronic devices with sensors and/or actuators that send information to the outside for monitoring. A major drawback to overcome is the high cost of these devices or IoT systems. This paper presents a low-cost IoT system for gas concentrators to detect anomalies. This IoT system, which has been evaluated, concentrates and analyses exhaled air using an MQ sensor.
- 12 November 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 44 (12) , 9549-9560
Reducing Data Complexity Using Autoencoders With Class-Informed Loss Functions
Available data in machine learning applications is becoming increasingly complex, due to higher dimensionality and difficult classes. There exists a wide variety of approaches to measuring complexity of labeled data, according to class overlap, separability or boundary shapes, as well as group morphology. Many techniques can transform the data in order to find better features, but few focus on specifically reducing data complexity. Most data transformation methods mainly treat the dimensionality aspect, leaving aside the available information within class labels which can be useful when classes are somehow complex. This paper proposes an autoencoder-based approach to complexity reduction, using class labels in order to inform the loss function about the adequacy of the generated variables. This leads to three different new feature learners, Scorer, Skaler and Slicer. They are based on Fisher’s discriminant ratio, the Kullback-Leibler divergence and least-squares support vector machines, respectively. They can be applied as a preprocessing stage for a binary classification problem. A thorough experimentation across a collection of 27 datasets and a range of complexity and classification metrics shows that class-informed autoencoders perform better than 4 other popular unsupervised feature extraction techniques, especially when the final objective is using the data for a classification task.
- 12 November 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 44 (12) , 9549-9560
Reducing Data Complexity Using Autoencoders With Class-Informed Loss Functions
Available data in machine learning applications is becoming increasingly complex, due to higher dimensionality and difficult classes. There exists a wide variety of approaches to measuring complexity of labeled data, according to class overlap, separability or boundary shapes, as well as group morphology. Many techniques can transform the data in order to find better features, but few focus on specifically reducing data complexity. Most data transformation methods mainly treat the dimensionality aspect, leaving aside the available information within class labels which can be useful when classes are somehow complex. This paper proposes an autoencoder-based approach to complexity reduction, using class labels in order to inform the loss function about the adequacy of the generated variables. This leads to three different new feature learners, Scorer, Skaler and Slicer. They are based on Fisher’s discriminant ratio, the Kullback-Leibler divergence and least-squares support vector machines, respectively. They can be applied as a preprocessing stage for a binary classification problem. A thorough experimentation across a collection of 27 datasets and a range of complexity and classification metrics shows that class-informed autoencoders perform better than 4 other popular unsupervised feature extraction techniques, especially when the final objective is using the data for a classification task.