210 results on '"Elizondo, David A."'
Search Results
202. Incorporating Expert Advice into Reinforcement Learning Using Constructive Neural Networks
- Author
-
Ollington, Robert, Vamplew, Peter, Swanson, John, Kacprzyk, Janusz, editor, Franco, Leonardo, editor, Elizondo, David A., editor, and Jerez, José M., editor
- Published
- 2009
- Full Text
- View/download PDF
203. Active Learning Using a Constructive Neural Network Algorithm
- Author
-
Subirats, José L., Franco, Leonardo, Molina, Ignacio, Jerez, José M., Kacprzyk, Janusz, editor, Franco, Leonardo, editor, Elizondo, David A., editor, and Jerez, José M., editor
- Published
- 2009
- Full Text
- View/download PDF
204. Fuzzy Logic Applied to System Monitors
- Author
-
Lipika Deka, Miguel A. Molina-Cabello, David Elizondo, Noel Khan, [Khan, Noel] De Montfort Univ, Sch Comp Sci & Informat, Leicester LE1 9B1L, Leics, England, [Elizondo, David A.] De Montfort Univ, Sch Comp Sci & Informat, Leicester LE1 9B1L, Leics, England, [Deka, Lipika] De Montfort Univ, Sch Comp Sci & Informat, Leicester LE1 9B1L, Leics, England, [Molina-Cabello, Miguel A.] Univ Malaga, Dept Comp Languages & Comp Sci, Malaga 29071, Spain, [Molina-Cabello, Miguel A.] Inst Invest Biomed Malaga IBIMA, Malaga 29010, Spain, Ministry of Science, Innovation and Universities of Spain through the Project Automated Detection With Low-Cost Hardware of Unusual Activities in Video Sequences, Autonomous Government of Andalusia (Spain) through the Project Detection of Anomalous Behavior Agents by Deep Learning in Low-Cost Video Surveillance Intelligent Systems, European Regional Development Fund (ERDF), Universidad de Malaga, and Instituto de Investigacion Biomedica de Malaga (IBIMA)
- Subjects
Market research ,Fuzzy sets ,Monitoring ,General Computer Science ,Computer science ,Mission critical ,Fuzzy set ,02 engineering and technology ,Software reliability ,01 natural sciences ,Fuzzy logic ,0202 electrical engineering, electronic engineering, information engineering ,General Materials Science ,0101 mathematics ,Productivity ,business.industry ,010102 general mathematics ,Uncertainty ,General Engineering ,Fault tolerance ,Linguistics ,Usability ,Fuzzy systems ,Fuzzy control system ,software reliability ,Autonomous systems ,TK1-9971 ,Reliability engineering ,Variety (cybernetics) ,monitoring ,fuzzy systems ,020201 artificial intelligence & image processing ,fault tolerance ,Electrical engineering. Electronics. Nuclear engineering ,State (computer science) ,business - Abstract
The Publisher's final version can be found by following the DOI link. Open access article. System monitors are applications used to monitor other systems (often mission critical) and take corrective actions upon a system failure. Rather than reactively take action after a failure, the potential of fuzzy logic to anticipate and proactively take corrective actions is explored here. Failures adversely affect a system’s non-functional qualities (e.g., availability, reliability, and usability) and may result in a variety of losses such as data, productivity, or safety losses. The detection and prevention of failures necessarily improves a critical system’s non-functional qualities and avoids losses. The paper is self-contained and reviews set and logic theory, fuzzy inference systems (FIS), explores parameterization, and tests the neighborhood of rule thresholds to evaluate the potential for anticipating failures. Results demonstrate detectable gradients in FIS state spaces and means fuzzy logic based system monitors can anticipate rule violations or system failures.
- Published
- 2021
205. Aggregation of Convolutional Neural Network Estimations of Homographies by Color Transformations of the Inputs
- Author
-
David Elizondo, Miguel A. Molina-Cabello, Ezequiel López-Rubio, Rafael Marcos Luque-Baena, [Molina-Cabello, Miguel A.] Univ Malaga, Dept Comp Languages & Comp Sci, Malaga 29071, Spain, [Marcos Luque-Baena, Rafael] Univ Malaga, Dept Comp Languages & Comp Sci, Malaga 29071, Spain, [Lopez-Rubio, Ezequiel] Univ Malaga, Dept Comp Languages & Comp Sci, Malaga 29071, Spain, [Molina-Cabello, Miguel A.] Biomed Res Inst Malaga IBIMA, Malaga 29010, Spain, [Marcos Luque-Baena, Rafael] Biomed Res Inst Malaga IBIMA, Malaga 29010, Spain, [Lopez-Rubio, Ezequiel] Biomed Res Inst Malaga IBIMA, Malaga 29010, Spain, [Elizondo, David A.] De Montfort Univ, Dept Comp Technol, Leicester LE1 9BH, Leics, England, Ministry of Economy and Competitiveness of Spain, Ministry of Science, Innovation and Universities of Spain, Autonomous Government of Andalusia, Spain, through the Project Detection of Anomalous Behavior Agents by the Deep Learning in Low Cost Video Surveillance Intelligent Systems, and European Regional Development Fund (ERDF)
- Subjects
General Computer Science ,Computer science ,business.industry ,General Engineering ,ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION ,Pattern recognition ,Convolutional neural network ,Algorithm ,homography estimation ,Deep convolutional neural networks ,General Materials Science ,Deep homography ,Artificial intelligence ,lcsh:Electrical engineering. Electronics. Nuclear engineering ,business ,color transformations ,lcsh:TK1-9971 ,Sports - Abstract
The standard approach to the estimation of homographies consists in the application of the RANSAC algorithm to a set of tentative matches. More recent strategies based on deep learning, namely convolutional architectures, have become available. In this work, a new algorithm for the estimation of homographies is developed. It is rooted in a convolutional neural network for homography estimation, which is provided with a range of versions of the input pair of pictures. Such versions are generated by perturbation of the color levels of the input images. Each generated pair of images yields a distinct estimation of the homography, and then the estimations are combined together to obtain a final, more robust estimation. Experiments have been designed and carried out to test the validity of our approach, including qualitative and quantitative performance measures. In particular, it is demonstrated that our approach consistently outperforms the baseline approach consisting of using the output of the homography estimation deep network for the original input pair of images.
- Published
- 2020
206. Improving Uncertainty Estimation With Semi-Supervised Deep Learning for COVID-19 Detection Using Chest X-Ray Images
- Author
-
Simon Colreavy-Donnelly, Saul Calderon-Ramirez, Shengxiang Yang, Ezequiel López-Rubio, David Elizondo, Manuel F. Jiménez-Navarro, Armaghan Moemeni, Luis Oala, Jorge Rodriguez-Capitan, Miguel A. Molina-Cabello, [Calderon-Ramirez, Saul] De Montfort Univ, Sch Comp Sci & Informat, Leicester LE1 9BH, Leics, England, [Yang, Shengxiang] De Montfort Univ, Sch Comp Sci & Informat, Leicester LE1 9BH, Leics, England, [Colreavy-Donnelly, Simon] De Montfort Univ, Sch Comp Sci & Informat, Leicester LE1 9BH, Leics, England, [Elizondo, David A.] De Montfort Univ, Sch Comp Sci & Informat, Leicester LE1 9BH, Leics, England, [Calderon-Ramirez, Saul] Inst Tecnol Costa Rica, Cartago 30101, Costa Rica, [Moemeni, Armaghan] Univ Nottingham, Sch Comp Sci, Nottingham NG8 1BB, England, [Oala, Luis] Fraunhofer Heinrich Hertz Inst, XAI Grp, Artificial Intelligence Dept, D-10587 Berlin, Germany, [Rodriguez-Capitan, Jorge] Hosp Univ Virgen Victoria, CIBERCV, Malaga 29010, Spain, [Jimenez-Navarro, Manuel] Hosp Univ Virgen Victoria, CIBERCV, Malaga 29010, Spain, [Lopez-Rubio, Ezequiel] Univ Malaga, Dept Comp Languages & Comp Sci, Malaga 29071, Spain, [Molina-Cabello, Miguel A.] Univ Malaga, Dept Comp Languages & Comp Sci, Malaga 29071, Spain, [Lopez-Rubio, Ezequiel] Inst Invest Biomed Malaga IBIMA, Malaga 29010, Spain, [Molina-Cabello, Miguel A.] Inst Invest Biomed Malaga IBIMA, Malaga 29010, Spain, Universidad de Malaga, Instituto de Investigacion Biomedica de Malaga (IBIMA), and Publica
- Subjects
General Computer Science ,Computer science ,Measurement uncertainty ,Monte Carlo method ,Uncertainty estimation ,010501 environmental sciences ,Machine learning ,computer.software_genre ,01 natural sciences ,chest x-ray ,Imaging ,03 medical and health sciences ,General Materials Science ,Uncertainty quantification ,Reliability (statistics) ,Dropout (neural networks) ,030304 developmental biology ,0105 earth and related environmental sciences ,0303 health sciences ,Measurement ,computer aided diagnosis ,business.industry ,Deep learning ,X-ray imaging ,General Engineering ,Uncertainty ,COVID-19 ,TK1-9971 ,Coronavirus ,Softmax function ,Metric (mathematics) ,semi-supervised deep learning ,MixMatch ,Computational and Artificial Intelligence ,Artificial intelligence ,Electrical engineering. Electronics. Nuclear engineering ,business ,Covid-19 ,computer ,Estimation - Abstract
In this work we implement a COVID-19 infection detection system based on chest X-ray images with uncertainty estimation. Uncertainty estimation is vital for safe usage of computer aided diagnosis tools in medical applications. Model estimations with high uncertainty should be carefully analyzed by a trained radiologist. We aim to improve uncertainty estimations using unlabelled data through the MixMatch semi-supervised framework. We test popular uncertainty estimation approaches, comprising Softmax scores, Monte-Carlo dropout and deterministic uncertainty quantification. To compare the reliability of the uncertainty estimates, we propose the usage of the Jensen-Shannon distance between the uncertainty distributions of correct and incorrect estimations. This metric is statistically relevant, unlike most previously used metrics, which often ignore the distribution of the uncertainty estimations. Our test results show a significant improvement in uncertainty estimates when using unlabelled data. The best results are obtained with the use of the Monte Carlo dropout method.
- Published
- 2021
207. Skin Lesion Classification by Ensembles of Deep Convolutional Networks and Regularly Spaced Shifting
- Author
-
Karl Thurnhofer-Hemsi, Enrique Domínguez, Ezequiel López-Rubio, David Elizondo, [Thurnhofer-Hemsi, Karl] Univ Malaga, Dept Comp Languages & Comp Sci, Malaga 29071, Spain, [Lopez-Rubio, Ezequiel] Univ Malaga, Dept Comp Languages & Comp Sci, Malaga 29071, Spain, [Dominguez, Enrique] Univ Malaga, Dept Comp Languages & Comp Sci, Malaga 29071, Spain, [Thurnhofer-Hemsi, Karl] Biomed Res Inst Malaga IBIMA, Malaga 29010, Spain, [Lopez-Rubio, Ezequiel] Biomed Res Inst Malaga IBIMA, Malaga 29010, Spain, [Dominguez, Enrique] Biomed Res Inst Malaga IBIMA, Malaga 29010, Spain, [Elizondo, David A.] De Montfort Univ, Sch Comp Sci & Informat, Leicester LE1 9BH, Leics, England, Ministry of Science, Innovation, and Universities of Spain, through European Regional Development Fund (ERDF), Autonomous Government of Andalusia, Spain, through ERDF, University of Malaga, Spain, Universidad de Malaga, and Instituto de Investigacion Biomedica de Malaga (IBIMA)
- Subjects
General Computer Science ,Computer science ,Feature extraction ,skin lesion ,Image processing ,Convolutional neural network ,medicine ,General Materials Science ,Medical diagnosis ,Melanoma ,Skin ,Contextual image classification ,Standard test image ,business.industry ,Deep learning ,General Engineering ,deep learning ,Pattern recognition ,medicine.disease ,TK1-9971 ,classification ,Piel - Enfermedades ,Task analysis ,Lesions ,Image ,Convolutional neural networks ,Artificial intelligence ,Electrical engineering. Electronics. Nuclear engineering ,Skin cancer ,business - Abstract
Skin lesions are caused due to multiple factors, like allergies, infections, exposition to the sun, etc. These skin diseases have become a challenge in medical diagnosis due to visual similarities, where image classification is an essential task to achieve an adequate diagnostic of different lesions. Melanoma is one of the best-known types of skin lesions due to the vast majority of skin cancer deaths. In this work, we propose an ensemble of improved convolutional neural networks combined with a test-time regularly spaced shifting technique for skin lesion classification. The shifting technique builds several versions of the test input image, which are shifted by displacement vectors that lie on a regular lattice in the plane of possible shifts. These shifted versions of the test image are subsequently passed on to each of the classifiers of an ensemble. Finally, all the outputs from the classifiers are combined to yield the final result. Experiment results show a significant improvement on the well-known HAM10000 dataset in terms of accuracy and Fscore. In particular, it is demonstrated that our combination of ensembles with test-time regularly spaced shifting yields better performance than any of the two methods when applied alone. This work is partially supported by the Ministry of Science, Innovation and Universities of Spain under grant RTI2018-094645-B-I00, project name Automated detection with low-cost hardware of unusual activities in video sequences. It is also partially supported by the Autonomous Government of Andalusia (Spain) under project UMA18-FEDERJA-084, project name Detection of anomalous behavior agents by deep learning in low-cost video surveillance intelligent systems. All of them include funds from the European Regional Development Fund (ERDF). It is also partially supported by the University of Malaga (Spain) under grants B1-2019_02, project name Self-Organizing Neural Systems for Non-Stationary Environments, and B1-2019_01, project name Anomaly detection on roads by moving cameras. The authors thankfully acknowledge the computer resources, technical expertise and assistance provided by the SCBI (Supercomputing and Bioinformatics) center of the University of Málaga. They also gratefully acknowledge the support of NVIDIA Corporation with the donation of two Titan X GPUs. The authors acknowledge the funding from the Universidad de Málaga. Funding for open access charge: Universidad de Málaga / CBUA.
- Published
- 2021
208. Correcting Data Imbalance for Semi-Supervised Covid-19 Detection Using X-ray Chest Images
- Author
-
Shengxiang Yang, Miguel A. Molina-Cabello, Saul Calderon-Ramirez, David Elizondo, Luis Fernando Chavarria-Estrada, Armaghan Moemeni, Simon Colreavy-Donnelly, [Calderon-Ramirez, Saul] De Montfort Univ, Ctr Computat Intelligence CCI, Leicester, Leics, England, [Yang, Shengxiang] De Montfort Univ, Ctr Computat Intelligence CCI, Leicester, Leics, England, [Elizondo, David] De Montfort Univ, Ctr Computat Intelligence CCI, Leicester, Leics, England, [Colreavy-Donnelly, Simon] De Montfort Univ, Ctr Computat Intelligence CCI, Leicester, Leics, England, [Calderon-Ramirez, Saul] Inst Tecnol Costa Rica, Cartago, Costa Rica, [Moemeni, Armaghan] Univ Nottingham, Sch Comp Sci, Nottingham, England, [Chavarria-Estrada, Luis Fernando] Imagenes Med Dr Chavarria Estrada, San Jose, Costa Rica, [Molina-Cabello, Miguel A.] Univ Malaga, Dept Comp Languages & Comp Sci, Malaga, Spain, [Molina-Cabello, Miguel A.] Inst Invest Biomed Malaga IBIMA, Malaga, Spain, European Regional Development Fund (ERDF), and Universidad de Malaga, Spain
- Subjects
FOS: Computer and information sciences ,Computer Science - Machine Learning ,Data imbalance ,Computer science ,Computer Vision and Pattern Recognition (cs.CV) ,Semi-Supervised Learning ,Computer Science - Computer Vision and Pattern Recognition ,Context (language use) ,Semi-supervised learning ,Article ,Machine Learning (cs.LG) ,FOS: Electrical engineering, electronic engineering, information engineering ,Features ,Contextual image classification ,business.industry ,Deep learning ,Image and Video Processing (eess.IV) ,Deep ,COVID-19 ,Pattern recognition ,Electrical Engineering and Systems Science - Image and Video Processing ,Class (biology) ,Computer aided diagnosis ,Coronavirus ,Identification (information) ,Binary classification ,Computer-aided diagnosis ,Computer Aided Diagnosis ,Artificial intelligence ,Radiology ,Covid-19 ,business ,Software - Abstract
The Corona Virus (COVID-19) is an internationalpandemic that has quickly propagated throughout the world. The application of deep learning for image classification of chest X-ray images of Covid-19 patients, could become a novel pre-diagnostic detection methodology. However, deep learning architectures require large labelled datasets. This is often a limitation when the subject of research is relatively new as in the case of the virus outbreak, where dealing with small labelled datasets is a challenge. Moreover, in the context of a new highly infectious disease, the datasets are also highly imbalanced,with few observations from positive cases of the new disease. In this work we evaluate the performance of the semi-supervised deep learning architecture known as MixMatch using a very limited number of labelled observations and highly imbalanced labelled dataset. We propose a simple approach for correcting data imbalance, re-weight each observationin the loss function, giving a higher weight to the observationscorresponding to the under-represented class. For unlabelled observations, we propose the usage of the pseudo and augmentedlabels calculated by MixMatch to choose the appropriate weight. The MixMatch method combined with the proposed pseudo-label based balance correction improved classification accuracy by up to 10%, with respect to the non balanced MixMatch algorithm, with statistical significance. We tested our proposed approach with several available datasets using 10, 15 and 20 labelledobservations. Additionally, a new dataset is included among thetested datasets, composed of chest X-ray images of Costa Rican adult patients, Under journal review
- Published
- 2020
209. A comparison of the generalization ability of different genetic programming frameworks
- Author
-
Luca Manzoni, Mauro Castelli, Sara Silva, Leonardo Vanneschi, Elizondo, David, Solanas, Agusti, Martinez-Balleste, Antoni, Castelli, Mauro, Manzoni, Luca, Silva, Sara, Vanneschi, Leonardo, Castelli, M, Manzoni, L, Silva, S, and Vanneschi, L
- Subjects
Training set ,Generalization ,Computer science ,business.industry ,Applied Mathematics ,Genetic programming ,Machine learning ,computer.software_genre ,Inductive programming ,Field (computer science) ,Computational Theory and Mathematic ,Genetic algorithm ,Genetic representation ,Artificial intelligence ,business ,computer ,Test data - Abstract
Generalization is an important issue in machine learning. In fact, in several applications good results over training data are not as important as good results over unseen data. While this problem was deeply studied in other machine learning techniques, it has become an important issue for genetic programming only in the last few years. In this paper we compare the generalization ability of several different genetic programming frameworks, including some variants of multi-objective genetic programming and operator equalization, a recently defined bloat free genetic programming system. The test problem used is a hard regression real-life application in the field of drug discovery and development, characterized by a high number of features and where the generalization ability of the proposed solutions is a crucial issue. The results we obtained show that, at least for the considered problem, multi-optimization is effective in improving genetic programming generalization ability, outperforming all the other methods on test data. © 2010 IEEE.
- Published
- 2010
210. Improving Uncertainty Estimation With Semi-Supervised Deep Learning for COVID-19 Detection Using Chest X-Ray Images.
- Author
-
Calderon-Ramirez S, Yang S, Moemeni A, Colreavy-Donnelly S, Elizondo DA, Oala L, Rodriguez-Capitan J, Jimenez-Navarro M, Lopez-Rubio E, and Molina-Cabello MA
- Abstract
In this work we implement a COVID-19 infection detection system based on chest X-ray images with uncertainty estimation. Uncertainty estimation is vital for safe usage of computer aided diagnosis tools in medical applications. Model estimations with high uncertainty should be carefully analyzed by a trained radiologist. We aim to improve uncertainty estimations using unlabelled data through the MixMatch semi-supervised framework. We test popular uncertainty estimation approaches, comprising Softmax scores, Monte-Carlo dropout and deterministic uncertainty quantification. To compare the reliability of the uncertainty estimates, we propose the usage of the Jensen-Shannon distance between the uncertainty distributions of correct and incorrect estimations. This metric is statistically relevant, unlike most previously used metrics, which often ignore the distribution of the uncertainty estimations. Our test results show a significant improvement in uncertainty estimates when using unlabelled data. The best results are obtained with the use of the Monte Carlo dropout method., (This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/.)
- Published
- 2021
- Full Text
- View/download PDF
Catalog
Discovery Service for Jio Institute Digital Library
For full access to our library's resources, please sign in.