Publications
2022 |
A. M. Chacón-Maldonado and M. A. Molina and A. Troncoso and F. Martínez-Álvarez and G. Asencio-Cortés Olive Phenology Forecasting Using Information Fusion-Based Imbalanced Preprocessing and Automated Deep Learning (Conference) HAIS 17th International Conference on Hybrid Artificial Intelligence Systems, Lecture Notes in Computer Science 2022. (Links | BibTeX | Tags: deep learning, pattern recognition, time series) @conference{HAIS22_Andres, title = {Olive Phenology Forecasting Using Information Fusion-Based Imbalanced Preprocessing and Automated Deep Learning}, author = {A. M. Chacón-Maldonado and M. A. Molina and A. Troncoso and F. Martínez-Álvarez and G. Asencio-Cortés}, url = {https://link.springer.com/chapter/10.1007/978-3-031-15471-3_24}, year = {2022}, date = {2022-09-12}, booktitle = {HAIS 17th International Conference on Hybrid Artificial Intelligence Systems}, journal = {HAIS 17th International Conference on Hybrid Artificial Intelligence Systems, Lecture Notes in Computer Science 2022}, pages = {274-285}, series = {Lecture Notes in Computer Science}, keywords = {deep learning, pattern recognition, time series}, pubstate = {published}, tppubtype = {conference} } |
L. Melgar-García and D. Gutiérrez-Avilés and M. T. Godinho and R. Espada and I. S. Brito and F. Martínez-Álvarez and A. Troncoso and C. Rubio-Escudero A new big data triclustering approach for extracting three-dimensional patterns in precision agriculture (Journal Article) Neurocomputing, 500 , pp. 268-278, 2022. (Abstract | Links | BibTeX | Tags: big data, pattern recognition) @article{MELGAR21_NEUCOMb, title = {A new big data triclustering approach for extracting three-dimensional patterns in precision agriculture}, author = {L. Melgar-García and D. Gutiérrez-Avilés and M. T. Godinho and R. Espada and I. S. Brito and F. Martínez-Álvarez and A. Troncoso and C. Rubio-Escudero}, url = {https://www.sciencedirect.com/science/article/abs/pii/S0925231222006415}, doi = {https://doi.org/10.1016/j.neucom.2021.06.101}, year = {2022}, date = {2022-01-01}, journal = {Neurocomputing}, volume = {500}, pages = {268-278}, abstract = {Precision agriculture focuses on the development of site-specific harvest considering the variability of each crop area. Vegetation indices allow the study and delineation of different characteristics of each field zone, generally invisible to the naked-eye. This paper introduces a new big data triclustering approach based on evolutionary algorithms. The algorithm shows its capability to discover three-dimensional patterns on the basis of vegetation indices from vine crops. Different vegetation indices have been tested to find different patterns in the crops. The results reported using a vineyard crop located in Portugal depicts four areas with different moisture stress particularities that can lead to changes in the management of the vineyard. Furthermore, scalability studies have been performed, showing that the proposed algorithm is suitable for dealing with big datasets.}, keywords = {big data, pattern recognition}, pubstate = {published}, tppubtype = {article} } Precision agriculture focuses on the development of site-specific harvest considering the variability of each crop area. Vegetation indices allow the study and delineation of different characteristics of each field zone, generally invisible to the naked-eye. This paper introduces a new big data triclustering approach based on evolutionary algorithms. The algorithm shows its capability to discover three-dimensional patterns on the basis of vegetation indices from vine crops. Different vegetation indices have been tested to find different patterns in the crops. The results reported using a vineyard crop located in Portugal depicts four areas with different moisture stress particularities that can lead to changes in the management of the vineyard. Furthermore, scalability studies have been performed, showing that the proposed algorithm is suitable for dealing with big datasets. |
E. T. Habtermariam and K. Kekeba and A. Troncoso and F. Martínez-Álvarez A Cluster-Based Deep Learning Model for Energy Consumption Forecasting in Ethiopia (Conference) SOCO 17th International Conference on Soft Computing Models in Industrial and Environmental Applications , 531 , Lecture Notes in Networks and Systems 2022. (Links | BibTeX | Tags: deep learning, energy, pattern recognition, time series) @conference{SOCO22_Ejigu, title = {A Cluster-Based Deep Learning Model for Energy Consumption Forecasting in Ethiopia}, author = {E. T. Habtermariam and K. Kekeba and A. Troncoso and F. Martínez-Álvarez}, url = {https://link.springer.com/chapter/10.1007/978-3-031-18050-7_41}, year = {2022}, date = {2022-01-01}, booktitle = {SOCO 17th International Conference on Soft Computing Models in Industrial and Environmental Applications }, journal = {SOCO 17th International Conference on Soft Computing Models in Industrial and Environmental Applications, Lecture Notes in Networks Systems, Vol. 531.}, volume = {531}, pages = {423-432}, series = {Lecture Notes in Networks and Systems}, keywords = {deep learning, energy, pattern recognition, time series}, pubstate = {published}, tppubtype = {conference} } |
M.A. Castán-Lascorz and P. Jiménez-Herrera and A. Troncoso and G. Asencio-Cortés A new hybrid method for predicting univariate and multivariate time series based on pattern forecasting (Journal Article) Information Sciences, 586 , pp. 611–627, 2022. (Abstract | Links | BibTeX | Tags: energy, pattern recognition, time series) @article{castan2022, title = {A new hybrid method for predicting univariate and multivariate time series based on pattern forecasting}, author = {M.A. Castán-Lascorz and P. Jiménez-Herrera and A. Troncoso and G. Asencio-Cortés}, url = {https://www.sciencedirect.com/science/article/pii/S0020025521012226?via%3Dihub}, doi = {10.1016/j.ins.2021.12.001}, year = {2022}, date = {2022-01-01}, journal = {Information Sciences}, volume = {586}, pages = {611--627}, abstract = {Time series forecasting has become indispensable for multiple applications and industrial processes. Currently, a large number of algorithms have been developed to forecast time series, all of which are suitable depending on the characteristics and patterns to be inferred in each case. In this work, a new algorithm is proposed to predict both univariate and multivariate time series based on a combination of clustering, classification and forecasting techniques. The main goal of the proposed algorithm is first to group windows of time series values with similar patterns by applying a clustering process. Then, a specific forecasting model for each pattern is built and training is only conducted with the time windows corresponding to that pattern. The new algorithm has been designed using a flexible framework that allows the model to be generated using any combination of approaches within multiple machine learning techniques. To evaluate the model, several experiments are carried out using different configurations of the clustering, classification and forecasting methods that the model consists of. The results are analyzed and compared to classical prediction models, such as autoregressive, integrated, moving average and Holt-Winters models, to very recent forecasting methods, including deep, long short-term memory neural networks, and to well-known methods in the literature, such as k nearest neighbors, classification and regression trees, as well as random forest.}, keywords = {energy, pattern recognition, time series}, pubstate = {published}, tppubtype = {article} } Time series forecasting has become indispensable for multiple applications and industrial processes. Currently, a large number of algorithms have been developed to forecast time series, all of which are suitable depending on the characteristics and patterns to be inferred in each case. In this work, a new algorithm is proposed to predict both univariate and multivariate time series based on a combination of clustering, classification and forecasting techniques. The main goal of the proposed algorithm is first to group windows of time series values with similar patterns by applying a clustering process. Then, a specific forecasting model for each pattern is built and training is only conducted with the time windows corresponding to that pattern. The new algorithm has been designed using a flexible framework that allows the model to be generated using any combination of approaches within multiple machine learning techniques. To evaluate the model, several experiments are carried out using different configurations of the clustering, classification and forecasting methods that the model consists of. The results are analyzed and compared to classical prediction models, such as autoregressive, integrated, moving average and Holt-Winters models, to very recent forecasting methods, including deep, long short-term memory neural networks, and to well-known methods in the literature, such as k nearest neighbors, classification and regression trees, as well as random forest. |
2021 |
R. Scitovski and K. Sabo and F. Martínez-Álvarez and S. Ungar Cluster analysis and applications (Book) Springer, 2021, ISBN: 978-3-030-74551-6. (Abstract | Links | BibTeX | Tags: pattern recognition) @book{SCITOVSKI21, title = {Cluster analysis and applications}, author = {R. Scitovski and K. Sabo and F. Martínez-Álvarez and S. Ungar}, url = {https://www.springer.com/gp/book/9783030745516}, doi = {10.1007/978-3-030-74552-3 tppubtype = book}, isbn = {978-3-030-74551-6}, year = {2021}, date = {2021-09-26}, publisher = {Springer}, abstract = {With the development of Big Data platforms for managing massive amount of data and wide availability of tools for processing these data, the biggest limitation is the lack of trained experts who are qualified to process and interpret the results. This textbook is intended for graduate students and experts using methods of cluster analysis and applications in various fields. Suitable for an introductory course on cluster analysis or data mining, with an in-depth mathematical treatment that includes discussions on different measures, primitives (points, lines, etc.) and optimization-based clustering methods, Cluster Analysis and Applications also includes coverage of deep learning based clustering methods. With clear explanations of ideas and precise definitions of concepts, accompanied by numerous examples and exercises together with Mathematica programs and modules, Cluster Analysis and Applications may be used by students and researchers in various disciplines, working in data analysis or data science.}, keywords = {pattern recognition}, pubstate = {published}, tppubtype = {book} } With the development of Big Data platforms for managing massive amount of data and wide availability of tools for processing these data, the biggest limitation is the lack of trained experts who are qualified to process and interpret the results. This textbook is intended for graduate students and experts using methods of cluster analysis and applications in various fields. Suitable for an introductory course on cluster analysis or data mining, with an in-depth mathematical treatment that includes discussions on different measures, primitives (points, lines, etc.) and optimization-based clustering methods, Cluster Analysis and Applications also includes coverage of deep learning based clustering methods. With clear explanations of ideas and precise definitions of concepts, accompanied by numerous examples and exercises together with Mathematica programs and modules, Cluster Analysis and Applications may be used by students and researchers in various disciplines, working in data analysis or data science. |
A. Morales-Esteban and F. Martínez-Álvarez and S. Scitovski and R. Scitovski Mahalanobis clustering for the determination of incidence-magnitude seismic parameters for the Iberian Peninsula and the Republic of Croatia (Journal Article) Computers and Geosciences, 156 , pp. 104873, 2021. (Abstract | Links | BibTeX | Tags: natural disasters, pattern recognition) @article{MORALES21, title = {Mahalanobis clustering for the determination of incidence-magnitude seismic parameters for the Iberian Peninsula and the Republic of Croatia}, author = {A. Morales-Esteban and F. Martínez-Álvarez and S. Scitovski and R. Scitovski}, url = {https://www.sciencedirect.com/science/article/pii/S0098300421001667}, doi = {https://doi.org/10.1016/j.cageo.2021.104873}, year = {2021}, date = {2021-07-09}, journal = {Computers and Geosciences}, volume = {156}, pages = {104873}, abstract = {The aim of this paper is to analyse the seismic activity of the Iberian Peninsula and a wide area of the Republicof Croatia. To do so, two incidence-magnitude seismic parameters have been defined. First, the areas have beendivided into several ellipsoidal clusters using Mahalanobis clustering. Four generalised indexes (Mahalanobis Calinski Harabasz, Mahalanobis Davies–Bouldin, Mahalanobis Simplified Silhouette Width Criterion and Mahalanobis Area) have been used to determine the most appropriate number of ellipsoidal clusters, on the basis of which a partition with four and a partition with eleven clusters have been considered. For the widearea of the Republic of Croatia there are fourteen clusters and the five areas that just affect Croatia have been analysed in detail. Then, to analyse the seismic activity of the areas, two incidence-magnitude seismic parameters have been defined and calculated: a) 𝛥(4), that represents the minimal number of successive years in which at least one earthquake of magnitude between 4 and 5 has been registered; b) 𝛥(5), that shows the number of years in which at least one earthquake of magnitude larger than 5 occurred. The calculation of 𝛥(4) for the South-west and the South-east of the Iberian Peninsula has provided two years for both. Regarding 𝛥(5), 10 and 12 years have been obtained for the South-west and the South-east of the Iberian Peninsula,respectively. The analysis of Croatia has shown that the Ston–Metković area has the highest seismic activity. The following results have been determined: 5 years for 𝛥(4) and 22 for 𝛥(5). It should be mentioned that the seresults cannot be used for predicting earthquakes. However, data about the incidences of earthquake events and their magnitudes can certainly serve as useful information in civil engineering.}, keywords = {natural disasters, pattern recognition}, pubstate = {published}, tppubtype = {article} } The aim of this paper is to analyse the seismic activity of the Iberian Peninsula and a wide area of the Republicof Croatia. To do so, two incidence-magnitude seismic parameters have been defined. First, the areas have beendivided into several ellipsoidal clusters using Mahalanobis clustering. Four generalised indexes (Mahalanobis Calinski Harabasz, Mahalanobis Davies–Bouldin, Mahalanobis Simplified Silhouette Width Criterion and Mahalanobis Area) have been used to determine the most appropriate number of ellipsoidal clusters, on the basis of which a partition with four and a partition with eleven clusters have been considered. For the widearea of the Republic of Croatia there are fourteen clusters and the five areas that just affect Croatia have been analysed in detail. Then, to analyse the seismic activity of the areas, two incidence-magnitude seismic parameters have been defined and calculated: a) 𝛥(4), that represents the minimal number of successive years in which at least one earthquake of magnitude between 4 and 5 has been registered; b) 𝛥(5), that shows the number of years in which at least one earthquake of magnitude larger than 5 occurred. The calculation of 𝛥(4) for the South-west and the South-east of the Iberian Peninsula has provided two years for both. Regarding 𝛥(5), 10 and 12 years have been obtained for the South-west and the South-east of the Iberian Peninsula,respectively. The analysis of Croatia has shown that the Ston–Metković area has the highest seismic activity. The following results have been determined: 5 years for 𝛥(4) and 22 for 𝛥(5). It should be mentioned that the seresults cannot be used for predicting earthquakes. However, data about the incidences of earthquake events and their magnitudes can certainly serve as useful information in civil engineering. |
M. García-Torres and F. Gómez-Vela and F. Divina and D.P. Pinto-Roa and J.L. Vázquez Noguera and J.C. Román Scatter search for high-dimensional feature selection using feature grouping (Conference) GECCO Genetic and Evolutionary Computation Conference, 2021. (Links | BibTeX | Tags: big data, feature selection, pattern recognition) @conference{garcia2021scatter, title = {Scatter search for high-dimensional feature selection using feature grouping}, author = {M. García-Torres and F. Gómez-Vela and F. Divina and D.P. Pinto-Roa and J.L. Vázquez Noguera and J.C. Román}, doi = {10.1145/3449726.3459481 pages=149--150}, year = {2021}, date = {2021-07-01}, booktitle = {GECCO Genetic and Evolutionary Computation Conference}, keywords = {big data, feature selection, pattern recognition}, pubstate = {published}, tppubtype = {conference} } |
L. Melgar-García and D. Gutiérrez-Avilés and C. Rubio-Escudero and A. Troncoso Discovering three-dimensional patterns in real-time from data streams: An online triclustering approach (Journal Article) Information Sciences, 558 , pp. 174-193, 2021. (Abstract | Links | BibTeX | Tags: big data, IoT, pattern recognition) @article{Melgar21_IS, title = {Discovering three-dimensional patterns in real-time from data streams: An online triclustering approach}, author = {L. Melgar-García and D. Gutiérrez-Avilés and C. Rubio-Escudero and A. Troncoso}, url = {https://www.sciencedirect.com/science/article/pii/S0020025521000220}, doi = {10.1016/j.ins.2020.12.089}, year = {2021}, date = {2021-01-01}, journal = {Information Sciences}, volume = {558}, pages = {174-193}, abstract = {Triclustering algorithms group sets of coordinates of 3-dimensional datasets. In this paper, a new triclustering approach for data streams is introduced. It follows a streaming scheme of learning in two steps: offline and online phases. First, the offline phase provides a summary model with the components of the triclusters. Then, the second stage is the online phase to deal with data in streaming. This online phase consists in using the summary model obtained in the offline stage to update the triclusters as fast as possible with genetic operators. Results using three types of synthetic datasets and a real-world environmental sensor dataset are reported. The performance of the proposed triclustering streaming algorithm is compared to a batch triclustering algorithm, showing an accurate performance both in terms of quality and running times. }, keywords = {big data, IoT, pattern recognition}, pubstate = {published}, tppubtype = {article} } Triclustering algorithms group sets of coordinates of 3-dimensional datasets. In this paper, a new triclustering approach for data streams is introduced. It follows a streaming scheme of learning in two steps: offline and online phases. First, the offline phase provides a summary model with the components of the triclusters. Then, the second stage is the online phase to deal with data in streaming. This online phase consists in using the summary model obtained in the offline stage to update the triclusters as fast as possible with genetic operators. Results using three types of synthetic datasets and a real-world environmental sensor dataset are reported. The performance of the proposed triclustering streaming algorithm is compared to a batch triclustering algorithm, showing an accurate performance both in terms of quality and running times. |
S.A. Grillo and J.C. Román and J.D. Mello-Román and J.L. Vázquez Noguera and M. García-Torres and F. Divina and P.E. Sotomayor Adjacent Inputs With Different Labels and Hardness in Supervised Learning (Journal Article) IEEE Access, pp. 162487–162498, 2021. (Links | BibTeX | Tags: feature selection, pattern recognition) @article{grillo2021adjacent, title = {Adjacent Inputs With Different Labels and Hardness in Supervised Learning}, author = {S.A. Grillo and J.C. Román and J.D. Mello-Román and J.L. Vázquez Noguera and M. García-Torres and F. Divina and P.E. Sotomayor}, doi = {10.1109/ACCESS.2021.3131150 volume=9}, year = {2021}, date = {2021-01-01}, journal = {IEEE Access}, pages = {162487--162498}, publisher = {IEEE pubstate = published}, keywords = {feature selection, pattern recognition}, pubstate = {published}, tppubtype = {article} } |
R. Parra and V. Ojeda and J.L. Vázquez Noguera and M. García-Torres and J.C. Mello-Román and C. Villalba and J. Facon and F. Divina and O. Cardozo and V. Castillo A Trust-Based Methodology to Evaluate Deep Learning Models for Automatic Diagnosis of Ocular Toxoplasmosis from Fundus Images (Journal Article) Diagnostics, 11 (11), pp. 1951, 2021. (Links | BibTeX | Tags: bioinformatics, deep learning, pattern recognition) @article{parra2021trust, title = {A Trust-Based Methodology to Evaluate Deep Learning Models for Automatic Diagnosis of Ocular Toxoplasmosis from Fundus Images}, author = {R. Parra and V. Ojeda and J.L. Vázquez Noguera and M. García-Torres and J.C. Mello-Román and C. Villalba and J. Facon and F. Divina and O. Cardozo and V. Castillo}, doi = {10.3390/diagnostics11111951}, year = {2021}, date = {2021-01-01}, journal = {Diagnostics}, volume = {11}, number = {11}, pages = {1951}, publisher = {Multidisciplinary Digital Publishing Institute pubstate = published}, keywords = {bioinformatics, deep learning, pattern recognition}, pubstate = {published}, tppubtype = {article} } |
J. Ayala and M. García-Torres and J.L. Vázquez Noguera and F. Gómez-Vela and F. Divina Technical analysis strategy optimization using a machine learning approach in stock market indices (Journal Article) Knowledge-Based Systems, pp. 107119, 2021. (Links | BibTeX | Tags: deep learning, pattern recognition) @article{ayala2021technical, title = {Technical analysis strategy optimization using a machine learning approach in stock market indices}, author = {J. Ayala and M. García-Torres and J.L. Vázquez Noguera and F. Gómez-Vela and F. Divina}, doi = {10.1016/j.knosys.2021.107119 volume=225}, year = {2021}, date = {2021-01-01}, journal = {Knowledge-Based Systems}, pages = {107119}, publisher = {Elsevier pubstate = published}, keywords = {deep learning, pattern recognition}, pubstate = {published}, tppubtype = {article} } |
A. Lopez-Fernandez and D. Rodriguez-Baena and F. Gomez-Vela and F. Divina and M. Garcia-Torres A multi-GPU biclustering algorithm for binary datasets (Journal Article) Journal of Parallel and Distributed Computing, 147 , pp. 209–219, 2021. (Links | BibTeX | Tags: bioinformatics, pattern recognition) @article{lopez2021multi, title = {A multi-GPU biclustering algorithm for binary datasets}, author = {A. Lopez-Fernandez and D. Rodriguez-Baena and F. Gomez-Vela and F. Divina and M. Garcia-Torres}, doi = {10.1016/j.jpdc.2020.09.009}, year = {2021}, date = {2021-01-01}, journal = {Journal of Parallel and Distributed Computing}, volume = {147}, pages = {209--219}, publisher = {Elsevier pubstate = published}, keywords = {bioinformatics, pattern recognition}, pubstate = {published}, tppubtype = {article} } |
2020 |
L. Melgar-García and M. T. Godinho and R. Espada and D. Gutiérrez-Avilés and I. S. Brito and F. Martínez-Álvarez and A. Troncoso and C. Rubio-Escudero Discovering Spatio-Temporal Patterns in Precision Agriculture Based on Triclustering (Conference) SOCO 15th International Conference on Soft Computing Models in Industrial and Environmental Applications, Advances in Intelligent Systems and Computing 2020. (Links | BibTeX | Tags: IoT, pattern recognition) @conference{SOCO20, title = {Discovering Spatio-Temporal Patterns in Precision Agriculture Based on Triclustering}, author = {L. Melgar-García and M. T. Godinho and R. Espada and D. Gutiérrez-Avilés and I. S. Brito and F. Martínez-Álvarez and A. Troncoso and C. Rubio-Escudero}, url = {https://link.springer.com/chapter/10.1007/978-3-030-57802-2_22}, year = {2020}, date = {2020-08-29}, booktitle = {SOCO 15th International Conference on Soft Computing Models in Industrial and Environmental Applications}, pages = {226-236}, series = {Advances in Intelligent Systems and Computing }, keywords = {IoT, pattern recognition}, pubstate = {published}, tppubtype = {conference} } |
C. Lezcano and J.L. Vázquez Noguera and D. P. Pinto-Roa and M. García-Torres and C. Gaona and P. E. Gardel-Sotomayor A multi-objective approach for designing optimized operation sequence on binary image processing (Journal Article) Heliyon, 6 (4), pp. e03670, 2020. (Abstract | BibTeX | Tags: pattern recognition) @article{Lezcano20, title = {A multi-objective approach for designing optimized operation sequence on binary image processing}, author = {C. Lezcano and J.L. Vázquez Noguera and D. P. Pinto-Roa and M. García-Torres and C. Gaona and P. E. Gardel-Sotomayor}, year = {2020}, date = {2020-01-01}, journal = {Heliyon}, volume = {6}, number = {4}, pages = {e03670}, abstract = {In binary image segmentation, the choice of the order of the operation sequence may yield to suboptimal results. In this work, we propose to tackle the associated optimization problem via multi-objective approach. Given the original image, in combination with a list of morphological, logical and stacking operations, the goal is to obtain the ideal output at the lowest computational cost. We compared the performance of two Multi-objective Evolutionary Algorithms (MOEAs): the Non-dominated Sorting Genetic Algorithm (NSGA-II) and the Strength Pareto Evolutionary Algorithm 2 (SPEA2). NSGA-II has better results in most cases, but the difference does not reach statistical significance. The results show that the similarity measure and the computational cost are objective functions in conflict, while the number of operations available and type of input images impact on the quality of Pareto set.}, keywords = {pattern recognition}, pubstate = {published}, tppubtype = {article} } In binary image segmentation, the choice of the order of the operation sequence may yield to suboptimal results. In this work, we propose to tackle the associated optimization problem via multi-objective approach. Given the original image, in combination with a list of morphological, logical and stacking operations, the goal is to obtain the ideal output at the lowest computational cost. We compared the performance of two Multi-objective Evolutionary Algorithms (MOEAs): the Non-dominated Sorting Genetic Algorithm (NSGA-II) and the Strength Pareto Evolutionary Algorithm 2 (SPEA2). NSGA-II has better results in most cases, but the difference does not reach statistical significance. The results show that the similarity measure and the computational cost are objective functions in conflict, while the number of operations available and type of input images impact on the quality of Pareto set. |
F. Daumas-Ladouce and M. García-Torres and J.L. Vázquez Noguera and D. P. Pinto-Roa and H. Legal-Alaya Multi-Objective Pareto Histogram Equalization (Journal Article) Electronic Notes in Theoretical Computer Science, 349 , pp. 3-23, 2020. (Abstract | BibTeX | Tags: pattern recognition) @article{Daumas-Ladouce20, title = {Multi-Objective Pareto Histogram Equalization}, author = {F. Daumas-Ladouce and M. García-Torres and J.L. Vázquez Noguera and D. P. Pinto-Roa and H. Legal-Alaya}, year = {2020}, date = {2020-01-01}, journal = {Electronic Notes in Theoretical Computer Science}, volume = {349}, pages = {3-23}, abstract = {Several histogram equalization methods focus on enhancing the contrast as one of their main objectives, but usually without considering the details of the input image. Other methods seek to keep the brightness while improving the contrast, causing distortion. Among the multi-objective algorithms, the classical optimization (a priori) techniques are commonly used given their simplicity. One of the most representative method is the weighted sum of metrics used to enhance the contrast of an image. These type of techniques, beside just returning a single image, have problems related to the weight assignment for each selected metric. To avoid the pitfalls of the algorithms just mentioned, we propose a new method called MOPHE (MultiObjective Pareto Histogram Equalization) which is based on Multi-objective Particle Swarm Optimization (MOPSO) approach combining different metrics in a posteriori selection criteria context. The goal of this method is three-fold: (1) improve the contrast (2) without losing important details, (3) avoiding an excessive distortion. MOPHE, is a pure multi-objective optimization algorithm, consequently a set of tradeoff optimal solutions are generated, thus providing alternative solutions to the decision-maker, allowing the selection of one or more resulting images, depending on the application needs. Experimental results indicate that MOPHE is a promising approach, as it calculates a set of trade-off optimal solutions that are better than the results obtained from representative algorithms from the state-of-the-art regarding visual quality and metrics measurement.}, keywords = {pattern recognition}, pubstate = {published}, tppubtype = {article} } Several histogram equalization methods focus on enhancing the contrast as one of their main objectives, but usually without considering the details of the input image. Other methods seek to keep the brightness while improving the contrast, causing distortion. Among the multi-objective algorithms, the classical optimization (a priori) techniques are commonly used given their simplicity. One of the most representative method is the weighted sum of metrics used to enhance the contrast of an image. These type of techniques, beside just returning a single image, have problems related to the weight assignment for each selected metric. To avoid the pitfalls of the algorithms just mentioned, we propose a new method called MOPHE (MultiObjective Pareto Histogram Equalization) which is based on Multi-objective Particle Swarm Optimization (MOPSO) approach combining different metrics in a posteriori selection criteria context. The goal of this method is three-fold: (1) improve the contrast (2) without losing important details, (3) avoiding an excessive distortion. MOPHE, is a pure multi-objective optimization algorithm, consequently a set of tradeoff optimal solutions are generated, thus providing alternative solutions to the decision-maker, allowing the selection of one or more resulting images, depending on the application needs. Experimental results indicate that MOPHE is a promising approach, as it calculates a set of trade-off optimal solutions that are better than the results obtained from representative algorithms from the state-of-the-art regarding visual quality and metrics measurement. |
D. S. Rodríguez-Baena and F. Gómez-Vela and M. García-Torres and F. Divina and C. D. Barranco and N- Díaz-Díaz and M. Jimenez and G. Montalvo Identifying livestock behavior patterns based on accelerometer dataset (Journal Article) Journal of Computational Science, 41 , pp. 101076, 2020. (Abstract | Links | BibTeX | Tags: pattern recognition) @article{Rodriguez-Baena20, title = {Identifying livestock behavior patterns based on accelerometer dataset}, author = {D. S. Rodríguez-Baena and F. Gómez-Vela and M. García-Torres and F. Divina and C. D. Barranco and N- Díaz-Díaz and M. Jimenez and G. Montalvo}, url = {https://doi.org/10.1016/j.jocs.2020.101076}, doi = {10.1016/j.jocs.2020.101076}, year = {2020}, date = {2020-01-01}, journal = {Journal of Computational Science}, volume = {41}, pages = {101076}, abstract = {In large livestock farming it would be beneficial to be able to automatically detect behaviors in animals. In fact, this would allow to estimate the health status of individuals, providing valuable insight to stock raisers. Traditionally this process has been carried out manually, relying only on the experience of the breeders. Such an approach is effective for a small number of individuals. However, in large breeding farms this may not represent the best approach, since, in this way, not all the animals can be effectively monitored all the time. Moreover, the traditional approach heavily rely on human experience, which cannot be always taken for granted. To this aim, in this paper, we propose a new method for automatically detecting activity and inactivity time periods of animals, as a behavior indicator of livestock. In order to do this, we collected data with sensors located in the body of the animals to be analyzed. In particular, the reliability of the method was tested with data collected on Iberian pigs and calves. Results confirm that the proposed method can help breeders in detecting activity and inactivity periods for large livestock farming.}, keywords = {pattern recognition}, pubstate = {published}, tppubtype = {article} } In large livestock farming it would be beneficial to be able to automatically detect behaviors in animals. In fact, this would allow to estimate the health status of individuals, providing valuable insight to stock raisers. Traditionally this process has been carried out manually, relying only on the experience of the breeders. Such an approach is effective for a small number of individuals. However, in large breeding farms this may not represent the best approach, since, in this way, not all the animals can be effectively monitored all the time. Moreover, the traditional approach heavily rely on human experience, which cannot be always taken for granted. To this aim, in this paper, we propose a new method for automatically detecting activity and inactivity time periods of animals, as a behavior indicator of livestock. In order to do this, we collected data with sensors located in the body of the animals to be analyzed. In particular, the reliability of the method was tested with data collected on Iberian pigs and calves. Results confirm that the proposed method can help breeders in detecting activity and inactivity periods for large livestock farming. |
M. A. Molina and G. Asencio-Cortés and J. C. Riquelme and F. Martínez-Álvarez A Preliminary Study on Deep Transfer Learning Applied to Image Classification for Small Datasets (Conference) SOCO 15th International Conference on Soft Computing Models in Industrial and Environmental Applications, 1268 , Advances in Intelligent Systems and Computing 2020. (Links | BibTeX | Tags: deep learning, pattern recognition, transfer learning) @conference{molina2021, title = {A Preliminary Study on Deep Transfer Learning Applied to Image Classification for Small Datasets}, author = {M. A. Molina and G. Asencio-Cortés and J. C. Riquelme and F. Martínez-Álvarez}, url = {https://link.springer.com/chapter/10.1007/978-3-030-57802-2_71}, year = {2020}, date = {2020-01-01}, booktitle = {SOCO 15th International Conference on Soft Computing Models in Industrial and Environmental Applications}, volume = {1268}, pages = {741-750}, series = {Advances in Intelligent Systems and Computing}, keywords = {deep learning, pattern recognition, transfer learning}, pubstate = {published}, tppubtype = {conference} } |