Research

2022

Stevenson, Emma; Rodríguez-Fernández, Víctor; Taillan, Christophe; Urrutxua, Hodei; Camacho, David

A deep learning-based framework for operational all-vs-all conjunction screening Inproceedings

In: 2nd International Stardust Conference (STARCON-2), ESTEC, the Netherlands, 2022.

Stevenson, Emma; Rodriguez-Fernandez, Victor; Urrutxua, Hodei

Towards graph-based machine learning for conjunction assessment Inproceedings

In: 2022 Advanced Maui Optical and Space Surveillance Technologies Conference (AMOS), Maui, Hawaii, USA, 2022.

Abstract | BibTeX

Huertas-Tato, Javier; Martín, Alejandro; Camacho, David

SILT: Efficient transformer training for inter-lingual inference Journal Article

In: Expert Systems with Applications, vol. 200, pp. 116923, 2022, ISSN: 0957-4174.

@article{huertas-tato_silt_2022,

title = {SILT: Efficient transformer training for inter-lingual inference},

author = {Javier Huertas-Tato and Alejandro Martín and David Camacho},

url = {https://www.sciencedirect.com/science/article/pii/S0957417422003578},

doi = {10.1016/j.eswa.2022.116923},

issn = {0957-4174},

year  = {2022},

date = {2022-08-01},

urldate = {2022-08-01},

journal = {Expert Systems with Applications},

volume = {200},

pages = {116923},

abstract = {The ability of transformers to perform precision tasks such as question answering, Natural Language Inference (NLI) or summarizing, has enabled them to be ranked as one of the best paradigms to address Natural Language Processing (NLP) tasks. NLI is one of the best scenarios to test these architectures, due to the knowledge required to understand complex sentences and established relationships between a hypothesis and a premise. Nevertheless, these models suffer from the incapacity to generalize to other domains or from difficulties to face multilingual and interlingual scenarios. The leading pathway in the literature to address these issues involve designing and training extremely large architectures, but this causes unpredictable behaviors and establishes barriers which impede broad access and fine tuning. In this paper, we propose a new architecture called Siamese Inter-Lingual Transformer (SILT). This architecture is able to efficiently align multilingual embeddings for Natural Language Inference, allowing for unmatched language pairs to be processed. SILT leverages siamese pre-trained multi-lingual transformers with frozen weights where the two input sentences attend to each other to later be combined through a matrix alignment method. The experimental results carried out in this paper evidence that SILT allows to reduce drastically the number of trainable parameters while allowing for inter-lingual NLI and achieving state-of-the-art performance on common benchmarks.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

Stevenson, Emma; Martinez, Riansares; Rodriguez-Fernandez, Victor; Camacho, David

Predicting the effects of kinetic impactors on asteroid deflection using end-to-end deep learning Inproceedings

In: 2022 IEEE Congress on Evolutionary Computation (CEC), pp. 1-8, Padua, Italy, 2022.

@inproceedings{9870215,

title = {Predicting the effects of kinetic impactors on asteroid deflection using end-to-end deep learning},

author = {Emma Stevenson and Riansares Martinez and Victor Rodriguez-Fernandez and David Camacho},

doi = {10.1109/CEC55065.2022.9870215},

year  = {2022},

date = {2022-07-18},

urldate = {2022-07-18},

booktitle = {2022 IEEE Congress on Evolutionary Computation (CEC)},

pages = {1-8},

address = {Padua, Italy},

abstract = {One possible approach to deflect the trajectory of an asteroid on a collision course with the Earth, and prevent a potentially devastating impact, is the use of a kinetic impactor. The upcoming NASA DART and ESA Hera space missions will be the first to study and demonstrate this technique, by driving a spacecraft into the moon of a binary asteroid system with the aim of altering its momentum, and knocking it off course. In this work, we seek to predict critical parameters associated with such an impact, namely the momentum transfer efficiency and axial ratio of the target body, based on light curve data observed from ground before and after the impact in order to give insights into the real effect of the deflection effort. We present here our approach to this problem, which we address from a purely data-driven perspective based on simulated data provided as a part of the Andrea Milani Planetary Defence Challenge, organised by the EU H2020 Stardust-R research network in conjunction with ESA. Formulating the problem as a time series regression task, we develop an end-to-end deep learning pipeline in which we apply the latest advances in deep learning for time series, such as the use of the Transformer architecture as well as ensembling and self-supervised learning techniques. Exploiting these techniques for the challenge, we achieved second place out of the student teams, and fifth place overall without relying on any a priori knowledge of the physics of the asteroid system.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

Stevenson, Emma; Rodriguez-Fernandez, Victor; Urrutxua, Hodei; Camacho, David

Deep learning for all-vs-all conjunction detection Inproceedings

In: 5th Workshop on Key Topics in Orbit Propagation Applied to Space Situational Awareness (KePASSA), Logroño, Spain, 2022.

Abstract | BibTeX

Huertas-García, Álvaro; Martín, Alejandro; Huertas-Tato, Javier; Camacho, David

Exploring Dimensionality Reduction Techniques in Multilingual Transformers Miscellaneous

CoRR, 2022.

@misc{nokey,

title = {Exploring Dimensionality Reduction Techniques in Multilingual Transformers},

author = {Álvaro Huertas-García and Alejandro Martín and Javier Huertas-Tato and David Camacho},

url = {https://doi.org/10.48550/arxiv.2204.08415},

doi = {10.48550/ARXIV.2204.08415},

year  = {2022},

date = {2022-04-18},

urldate = {2022-04-18},

abstract = {Both in scientific literature and in industry,, Semantic and context-aware Natural Language Processing-based solutions have been gaining importance in recent years. The possibilities and performance shown by these models when dealing with complex Language Understanding tasks is unquestionable, from conversational agents to the fight against disinformation in social networks. In addition, considerable attention is also being paid to developing multilingual models to tackle the language bottleneck. The growing need to provide more complex models implementing all these features has been accompanied by an increase in their size, without being conservative in the number of dimensions required. This paper aims to give a comprehensive account of the impact of a wide variety of dimensional reduction techniques on the performance of different state-of-the-art multilingual Siamese Transformers, including unsupervised dimensional reduction techniques such as linear and nonlinear feature extraction, feature selection, and manifold techniques. In order to evaluate the effects of these techniques, we considered the multilingual extended version of Semantic Textual Similarity Benchmark (mSTSb) and two different baseline approaches, one using the pre-trained version of several models and another using their fine-tuned STS version. The results evidence that it is possible to achieve an average reduction in the number of dimensions of 91.58%±2.59% and 54.65%±32.20%, respectively. This work has also considered the consequences of dimensionality reduction for visualization purposes. The results of this study will significantly contribute to the understanding of how different tuning approaches affect performance on semantic-aware tasks and how dimensional reduction techniques deal with the high-dimensional embeddings computed for the STS task and their potential for highly demanding NLP tasks },

howpublished = {CoRR},

keywords = {},

pubstate = {published},

tppubtype = {misc}

}

Stevenson, Emma; Rodriguez-Fernandez, Victor; Minisci, Edmondo; Camacho, David

A deep learning approach to solar radio flux forecasting Journal Article

In: Acta Astronautica, vol. 193, pp. 595-606, 2022, ISSN: 0094-5765.

@article{STEVENSON2022595,

title = {A deep learning approach to solar radio flux forecasting},

author = {Emma Stevenson and Victor Rodriguez-Fernandez and Edmondo Minisci and David Camacho},

url = {https://www.sciencedirect.com/science/article/pii/S009457652100415X},

doi = {https://doi.org/10.1016/j.actaastro.2021.08.004},

issn = {0094-5765},

year  = {2022},

date = {2022-01-01},

journal = {Acta Astronautica},

volume = {193},

pages = {595-606},

abstract = {The effect of atmospheric drag on spacecraft dynamics is considered one of the predominant sources of uncertainty in Low Earth Orbit. These effects are characterised in part by the atmospheric density, a quantity highly correlated to space weather. Current atmosphere models typically account for this through proxy indices such as the F10.7, but with variations in solar radio flux forecasts leading to significant orbit differences over just a few days, prediction of these quantities is a limiting factor in the accurate estimation of future drag conditions, and consequently orbital prediction. In this work, a novel deep residual architecture for univariate time series forecasting, N-BEATS, is employed for the prediction of the F10.7 solar proxy on the days-ahead timescales relevant to space operations. This untailored, pure deep learning approach has recently achieved state-of-the-art performance in time series forecasting competitions, outperforming well-established statistical, as well as statistical hybrid models, across a range of domains. The approach was found to be effective in single point forecasting up to 27-days ahead, and was additionally extended to produce forecast uncertainty estimates using deep ensembles. These forecasts were then compared to a persistence baseline and two operationally available forecasts: one statistical (provided by BGS, ESA), and one multi-flux neural network (by CLS, CNES). It was found that the N-BEATS model systematically outperformed the baseline and statistical approaches, and achieved an improved or similar performance to the multi-flux neural network approach despite only learning from a single variable.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

Panizo-Lledot, Angel; Pedemonte, Mart'in; Bello-Orgaz, Gema; Camacho, David

Addressing Evolutionary-Based Dynamic Problems: A New Methodology for Evaluating Immigrants Strategies in MOGAs Journal Article

In: IEEE Access, vol. 10, pp. 27611–27629, 2022.

2021

Stevenson, Emma; Rodriguez-Fernandez, Victor; Urrutxua, Hodei; Morand, Vincent; Camacho, David

Self-supervised machine learning based approach to orbit modelling applied to space traffic management Inproceedings

In: 11th International Association for the Advancement of Space Safety Conference (IAASS), (Virtual), Osaka, Japan, 2021.

Abstract | BibTeX

Huertas-García, Álvaro; Huertas-Tato, Javier; Martín, Alejandro; Camacho, David

CIVIC-UPM at CheckThat! 2021: Integration of Transformers in Misinformation Detection and Topic Classification Inproceedings

In: Conference and Labs of the Evaluation Forum (CLEF) Working Notes, pp. 520–530, 2021.

Javadi, Mahrokh; Ramirez-Atencia, Cristian; Mostaghim, Sanaz

Combining manhattan and crowding distances in decision space for multimodal multi-objective optimization problems Incollection

In: Advances in Evolutionary and Deterministic Methods for Design, Optimization and Control in Engineering and Sciences, vol. 55, pp. 131–145, Springer, Cham, 2021, ISBN: 978-3-030-57422-2.

Guamán, Daniel; Delgado, Maria Soledad; Pérez, Jennifer

Classifying Model-View-Controller Software Applications Using Self-Organizing Maps Journal Article

In: IEEE Access, vol. 9, pp. 45201-45229, 2021, ISBN: 2169-3536.

@article{9380344,

title = {Classifying Model-View-Controller Software Applications Using Self-Organizing Maps},

author = {Daniel Guamán and Maria Soledad Delgado and Jennifer Pérez},

doi = {10.1109/ACCESS.2021.3066348},

isbn = {2169-3536},

year  = {2021},

date = {2021-01-01},

urldate = {2021-01-01},

journal = {IEEE Access},

volume = {9},

pages = {45201-45229},

abstract = {The new era of information and the needs of our society require continuous change in software and technology. Changes are produced very quickly and software systems require evolving at the same velocity, which implies that the decision-making process of software architectures should be (semi-)automated to satisfy changing needs and to avoid wrong decisions. This issue is critical since suboptimal architecture design decisions may lead to high cost and poor software quality. Therefore, systematic and (semi-)automated mechanisms that help software architects during the decision-making process are required. Architectural patterns are one of the most important features of software applications, but the same pattern can be implemented in different ways, leaving to results of different quality. When an application requires to evolve, knowledge extracted from similar applications is useful for driving decisions, since quality pattern implementations can be reproduced in similar applications to improve specific quality attributes. Therefore, clustering methods are especially suitable for classifying similar pattern implementations. In this paper, we apply a novel unsupervised clustering technique, based on the well-known artificial neural network model Self-Organizing Maps, to classify Model-View-Controller (MVC) pattern from a quality point of view. Software quality is analyzed by 24 metrics organized into the categories of Count/Size, Maintainability, Duplications, Complexity, and Design Quality. The main goal of this work is twofold: to identify the quality features that establish the similarity of MVC applications without software architect bias, and to classify MVC applications by means of Self-Organizing Maps based on quality metrics. To that end, this work performs an exploratory study by conducting two analyses with a dataset of 87 Java MVC applications characterized by the 24 metrics and two attributes that describe the technology dimension of the application. The stated findings provide a knowledge base that can help in the decision-making process for the architecture of Java MVC applications.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

The new era of information and the needs of our society require continuous change in software and technology. Changes are produced very quickly and software systems require evolving at the same velocity, which implies that the decision-making process of software architectures should be (semi-)automated to satisfy changing needs and to avoid wrong decisions. This issue is critical since suboptimal architecture design decisions may lead to high cost and poor software quality. Therefore, systematic and (semi-)automated mechanisms that help software architects during the decision-making process are required. Architectural patterns are one of the most important features of software applications, but the same pattern can be implemented in different ways, leaving to results of different quality. When an application requires to evolve, knowledge extracted from similar applications is useful for driving decisions, since quality pattern implementations can be reproduced in similar applications to improve specific quality attributes. Therefore, clustering methods are especially suitable for classifying similar pattern implementations. In this paper, we apply a novel unsupervised clustering technique, based on the well-known artificial neural network model Self-Organizing Maps, to classify Model-View-Controller (MVC) pattern from a quality point of view. Software quality is analyzed by 24 metrics organized into the categories of Count/Size, Maintainability, Duplications, Complexity, and Design Quality. The main goal of this work is twofold: to identify the quality features that establish the similarity of MVC applications without software architect bias, and to classify MVC applications by means of Self-Organizing Maps based on quality metrics. To that end, this work performs an exploratory study by conducting two analyses with a dataset of 87 Java MVC applications characterized by the 24 metrics and two attributes that describe the technology dimension of the application. The stated findings provide a knowledge base that can help in the decision-making process for the architecture of Java MVC applications.

Delgado, Maria Soledad; Morán, Federico; José, José Carlos San; Burgos, Daniel

Analysis of Students’ Behavior Through User Clustering in Online Learning Settings, Based on Self Organizing Maps Neural Networks Journal Article

In: IEEE Access, vol. 9, pp. 132592-132608, 2021, ISSN: 2169-3536 .

2020

Stevenson, Emma; Rodriguez-Fernandez, Victor; Minisci, Edmondo; Camacho, David

A deep learning approach to space weather proxy forecasting for orbital prediction Inproceedings

In: 71st International Astronautical Congress (IAC), The CyberSpace Edition, 2020.

@inproceedings{stevenson2020_iac,

title = {A deep learning approach to space weather proxy forecasting for orbital prediction},

author = {Emma Stevenson and Victor Rodriguez-Fernandez and Edmondo Minisci and David Camacho},

url = {http://oa.upm.es/64345/},

year  = {2020},

date = {2020-10-01},

booktitle = {71st International Astronautical Congress (IAC)},

address = {The CyberSpace Edition},

abstract = {The effect of atmospheric drag on spacecraft dynamics is considered one of the predominant sources of uncertainty in Low Earth Orbit. These effects are characterised in part by the atmospheric density, a quantity highly correlated to space weather. Current atmosphere models typically account for this through proxy indices such as the F10.7, but with variations in solar radio flux forecasts leading to significant orbit differences over just a few days, prediction of these quantities is a limiting factor in the accurate estimation of future drag conditions, and consequently orbital prediction. This has fundamental implications both in the short term, in the day-to-day management of operational spacecraft, and in the mid-to-long term, in determining satellite orbital lifetime. In this work, a novel deep residual architecture for univariate time series forecasting, N-BEATS, is employed for the prediction of the F10.7 solar proxy on the days-ahead timescales relevant to space operations. This untailored, pure deep learning approach has recently achieved state-of-the-art performance in time series forecasting competitions, outperforming well-established statistical, as well as statistical hybrid models, across a range of domains. The approach was found to be effective in single point forecasting up to 27-days ahead, and was additionally extended to produce forecast uncertainty estimates using deep ensembles. These forecasts were then compared to a persistence baseline and two operationally available forecasts: one statistical (provided by BGS, ESA), and one multi-flux neural network (by CLS, CNES). It was found that the N-BEATS model systematically outperformed the baseline and statistical approaches, and achieved an improved or similar performance to the multi-flux neural network approach despite only learning from a single variable},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

Javadi, Mahrokh; Ramirez-Atencia, Cristian; Mostaghim, Sanaz

A novel grid-based crowding distance for multimodal multi-objective optimization Inproceedings

In: 2020 IEEE Congress on Evolutionary Computation (CEC), pp. 1–8, IEEE 2020, ISBN: 978-1-7281-6929-3.

Ramirez-Atencia, Cristian; Benecke, Tobias; Mostaghim, Sanaz

T-EA: A traceable evolutionary algorithm Inproceedings

In: 2020 IEEE Congress on Evolutionary Computation (CEC), pp. 1–8, IEEE 2020, ISBN: 978-1-7281-6929-3.

Panizo-LLedot, Angel; Bello-Orgaz, Gema; Camacho, David

A multi-objective genetic algorithm for detecting dynamic communities using a local search driven immigrant’s scheme Journal Article

In: Future Generation Computer Systems, vol. 110, pp. 960–975, 2020.

Pedemonte, Martín; Panizo-LLedot, Ángel; Bello-Orgaz, Gema; Camacho, David

Exploring multi-objective cellular genetic algorithms in community detection problems Inproceedings

In: International Conference on Intelligent Data Engineering and Automated Learning, pp. 223–235, Springer 2020.

Ramirez-Atencia, Cristian; Rodriguez-Fernandez, Victor; Camacho, David

A revision on multi-criteria decision making methods for multi-UAV mission planning support Journal Article

In: Expert Systems with Applications, vol. 160, pp. 113708, 2020, ISSN: 0957-4174.

@article{RAMIREZATENCIA2020113708,

title = {A revision on multi-criteria decision making methods for multi-UAV mission planning support},

author = {Cristian Ramirez-Atencia and Victor Rodriguez-Fernandez and David Camacho},

url = {https://www.sciencedirect.com/science/article/pii/S0957417420305327},

doi = {https://doi.org/10.1016/j.eswa.2020.113708},

issn = {0957-4174},

year  = {2020},

date = {2020-01-01},

urldate = {2020-01-01},

journal = {Expert Systems with Applications},

volume = {160},

pages = {113708},

abstract = {Over the last decade, Unmanned Aerial Vehicles (UAVs) have been extensively used in many commercial applications due to their manageability and risk avoidance. One of the main problems considered is the mission planning for multiple UAVs, where a solution plan must be found satisfying the different constraints of the problem. This problem has multiple variables that must be optimized simultaneously, such as the makespan, the cost of the mission or the risk. Therefore, the problem has a lot of possible optimal solutions, and the operator must select the final solution to be executed among them. In order to reduce the workload of the operator in this decision process, a Decision Support System (DSS) becomes necessary. In this work, a DSS consisting of ranking and filtering systems, which order and reduce the optimal solutions, has been designed. With regard to the ranking system, a wide range of Multi-Criteria Decision Making (MCDM) methods, including some fuzzy MCDM, are compared on a multi-UAV mission planning scenario, in order to study which method could fit better in a multi-UAV decision support system. Expert operators have evaluated the solutions returned, and the results show, on the one hand, that fuzzy methods generally achieve better average scores, and on the other, that all of the tested methods perform better when the preferences of the operators are biased towards a specific variable, and worse when their preferences are balanced. For the filtering system, a similarity function based on the proximity of the solutions has been designed, and on top of that, a threshold is tuned empirically to decide how to filter solutions without losing much of the hypervolume of the space of solutions.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

Camacho, David; Panizo-LLedot, Ángel; Bello-Orgaz, Gema; Gonzalez-Pardo, Antonio; Cambria, Erik

The four dimensions of social network analysis: An overview of research methods, applications, and software tools Journal Article

In: Information Fusion, vol. 63, pp. 88–120, 2020.

2019

Ramirez-Atencia, Cristian; Camacho, David

Constrained multi-objective optimization for multi-UAV planning Journal Article

In: Journal of Ambient Intelligence and Humanized Computing, vol. 10, no. 6, pp. 2467–2484, 2019, ISSN: 1868-5145.

Ramirez-Atencia, Cristian; Ser, Javier Del; Camacho, David

Weighted strategies to guide a multi-objective evolutionary algorithm for multi-UAV mission planning Journal Article

In: Swarm and Evolutionary Computation, vol. 44, pp. 480–495, 2019, ISSN: 2210-6502.

@article{ramirez2019weighted,

title = {Weighted strategies to guide a multi-objective evolutionary algorithm for multi-UAV mission planning},

author = {Cristian Ramirez-Atencia and Javier Del Ser and David Camacho},

doi = {10.1016/j.swevo.2018.06.005},

issn = {2210-6502},

year  = {2019},

date = {2019-02-01},

journal = {Swarm and Evolutionary Computation},

volume = {44},

pages = {480--495},

publisher = {Elsevier},

abstract = {Management and mission planning over a swarm of unmanned aerial vehicle (UAV) remains to date as a challenging research trend in what regards to this particular type of aircrafts. These vehicles are controlled by a number of ground control station (GCS), from which they are commanded to cooperatively perform different tasks in specific geographic areas of interest. Mathematically the problem of coordinating and assigning tasks to a swarm of UAV can be modeled as a constraint satisfaction problem, whose complexity and multiple conflicting criteria has hitherto motivated the adoption of multi-objective solvers such as multi-objective evolutionary algorithm (MOEA). The encoding approach consists of different alleles representing the decision variables, whereas the fitness function checks that all constraints are fulfilled, minimizing the optimization criteria of the problem. In problems of high complexity involving several tasks, UAV and GCS, where the space of search is huge compared to the space of valid solutions, the convergence rate of the algorithm increases significantly. To overcome this issue, this work proposes a weighted random generator for the creation and mutation of new individuals. The main objective of this work is to reduce the convergence rate of the MOEA solver for multi-UAV mission planning using weighted random strategies that focus the search on potentially better regions of the solution space. Extensive experimental results over a diverse range of scenarios evince the benefits of the proposed approach, which notably improves this convergence rate with respect to a naïve MOEA approach.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

Delgado, Maria Soledad; Moreno, Miguel; Vázquez, Luis; Martín-Gago, José A.; Briones, Carlos

Morphology Clustering Software for AFM Images, Based on Particle Isolation and Artificial Neural Networks Journal Article

In: 2019.

@article{<LineBreak>	10261_210788,

title = {Morphology Clustering Software for AFM Images, Based on Particle Isolation and Artificial Neural Networks},

author = {Maria Soledad Delgado and Miguel Moreno and Luis Vázquez and José A. Martín-Gago and Carlos Briones},

doi = {10.1109/ACCESS.2019.2950984},

year  = {2019},

date = {2019-01-01},

urldate = {2019-01-01},

organization = {This work was supported in part by the Spanish Ministry of Economy and Competitiveness (MINECO) funded by the EU through the FEDER Programme under Grant BIO2016-79618-R and Grant MAT2017-85089-C2-1-R, in part by the Spanish State Research Agency (AEI) through the Unidad de Excelencia María de Maeztu-Centro de Astrobiología (CSIC-INTA) under Project MDM-2017-0737, and in part by the Comunidad de Madrid under Grant S2018/NMT-4349.},

abstract = {[EN] Advanced microscopy techniques currently allow scientists to visualize biomolecules at high resolution. Among them, atomic force microscopy (AFM) shows the advantage of imaging molecules in their native state, without requiring any staining or coating of the sample. Biopolymers, including proteins and structured nucleic acids, are flexible molecules that can fold into alternative conformations for any given monomer sequence, as exemplified by the different three-dimensional structures adopted by RNA in solution. Therefore, the manual analysis of images visualized by AFM and other microscopy techniques becomes very laborious and time-consuming (and may also be inadvertently biased) when large populations of biomolecules are studied. Here we present a novel morphology clustering software, based on particle isolation and artificial neural networks, which allows the automatic image analysis and classification of biomolecules that can show alternative conformations. It has been tested with a set of AFM images of RNA molecules (a 574 nucleotides-long functinal region of the hepatitis C virus genome that contains its internal ribosome entry site element) structured in folding buffers containing 0, 2, 4, 6 or 10 mM Mg. The developed software shows a broad applicability in the microscopy-based analysis of biopolymers and other complex biomolecules.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

Hernández, Alfonso; Panizo-LLedot, Ángel; Camacho, David

An ensemble algorithm based on deep learning for tuberculosis classification Inproceedings

In: International conference on intelligent data engineering and automated learning, pp. 145–154, Springer 2019.

Osaba, Eneko; Ser, Javier Del; Panizo-LLedot, Angel; Camacho, David; Galvez, Akemi; Iglesias, Andres

Combining bio-inspired meta-heuristics and novelty search for community detection over evolving graph streams Inproceedings

In: Proceedings of the genetic and evolutionary computation conference companion, pp. 1329–1335, 2019.

2018

Ramirez-Atencia, Cristian

Automated mission planning and decision support systems for multiple unmanned aerial vehicles PhD Thesis

Universidad Autónoma de Madrid, 2018.

Ramirez-Atencia, Cristian; Rodriguez-Fernandez, Victor; Camacho, David

A multi-criteria decision support system for multi-UAV mission planning Incollection

In: Data Science and Knowledge Engineering for Sensing Decision Support, vol. 11, pp. 1083–1090, World Scientific, 2018, ISBN: 978-981-3273-22-1.

Panizo-LLedot, Ángel; Bello-Orgaz, Gema; Carnero, Mercedes; Hernández, José; Sánchez, Mabel; Camacho, David

An Artificial Bee Colony algorithm for optimizing the design of sensor networks Inproceedings

In: International Conference on Intelligent Data Engineering and Automated Learning, pp. 316–324, Springer 2018.

Camacho-Gómez, C.; Wang, X.; Pereira, E.; Díaz, I. M.; Salcedo-Sanz, S.

Active vibration control design using the Coral Reefs Optimization with Substrate Layer algorithm Journal Article

In: Engineering Structures, vol. 157, pp. 14-26, 2018, ISSN: 0141-0296.

@article{CAMACHOGOMEZ201814,

title = {Active vibration control design using the Coral Reefs Optimization with Substrate Layer algorithm},

author = {C. Camacho-Gómez and X. Wang and E. Pereira and I. M. Díaz and S. Salcedo-Sanz},

url = {https://www.sciencedirect.com/science/article/pii/S0141029617311719},

doi = {https://doi.org/10.1016/j.engstruct.2017.12.002},

issn = {0141-0296},

year  = {2018},

date = {2018-01-01},

urldate = {2018-01-01},

journal = {Engineering Structures},

volume = {157},

pages = {14-26},

abstract = {Active vibration control (AVC) via inertial-mass actuators is a viable technique to mitigate human-induced vibrations in civil structures. A multi-input multi-output (MIMO) AVC has been previously proposed in the literature to simultaneously find the sensor/actuator pairs’ optimal placements and tune the control gains. However, the method involved local gradient-based methods, which is not affordable when the number of possible locations of actuators is large. In this case, the computation time to obtain a local solution may be huge and unaffordable, which limits the number of test points and/or actuators/sensors considered. This paper proposes an alternative approach based on a recently proposed meta-heuristic, the Coral Reefs Optimization (CRO) algorithm. More concretely, an enhanced version of the CRO is considered, the Coral Reefs Optimization with Substrate Layer (CRO-SL). The CRO-SL is a competitive co-evolution algorithm in which different exploration procedures are jointly evolved within a single population of potential solutions to the problem. The proposed algorithm is thus able to promote competition among different search methods to solve hard optimization problems. In terms of structural design, this work provides an important step to improve the applicability of AVC systems to real complex structures (with a large number of vibration modes and/or with a large number of test points) by achieving global optimum designs with affordable computation time. A finite element model of a real complex floor structure is used to illustrate the contributions of this paper.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

2017

Ramirez-Atencia, Cristian; R-Moreno, Maria D; Camacho, David

Handling swarm of UAVs based on evolutionary multi-objective optimization Journal Article

In: Progress in Artificial Intelligence, vol. 6, iss. 3, pp. 263-274, 2017, ISSN: 2192-6352.

@article{Ramirez-Atencia2017,

title = {Handling swarm of UAVs based on evolutionary multi-objective optimization},

author = {Cristian Ramirez-Atencia and Maria D R-Moreno and David Camacho},

url = {http://link.springer.com/10.1007/s13748-017-0123-7},

doi = {10.1007/s13748-017-0123-7},

issn = {2192-6352},

year  = {2017},

date = {2017-09-01},

urldate = {2017-01-01},

journal = {Progress in Artificial Intelligence},

volume = {6},

issue = {3},

pages = {263-274},

publisher = {Springer Berlin Heidelberg},

abstract = {The fast technological improvements in unmanned aerial vehicles (UAVs) has created new scenarios where a swarm of UAVs could operate in a distributed way. This swarm of vehicles needs to be controlled from a set of ground control stations, and new reliable mission planning systems, which should be able to handle the large amount of variables and constraints. This paper presents a new approach where this complex problem has been modelled as a constraint satisfaction problem (CSP), and is solved using a multi-objective genetic algorithm (MOGA). The algorithm has been designed to minimize several variables of the mission, such as the fuel consumption or the makespan among others. The designed fitness function, used by the algorithm, takes into consideration, as a weighted penalty function, the number of constraints fulfilled for each solution. Therefore, the MOGA algorithm is able to manage the number of constraints fulfilled by the selected plan, so it is possible to maximize in the elitism phase of the MOGA the quality of the solutions found. This approach allows to alleviate the computational effort carried out by the CSP solver, finding new solutions from the Pareto front, and therefore reducing the execution time to obtain a solution. In order to test the performance of this new approach 16 different mission scenarios have been designed. The experimental results show that the approach outperforms the convergence of the algorithm in terms of number of generations and runtime.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

Ramirez-Atencia, Cristian; Bello-Orgaz, Gema; R-Moreno, Maria D; Camacho, David

Solving complex multi-UAV mission planning problems using multi-objective genetic algorithms Journal Article

In: Soft Computing, vol. 21, iss. 17, pp. 4883-4900, 2017, ISSN: 1432-7643; 1433-7479.

Ramirez-Atencia, Cristian; Mostaghim, Sanaz; Camacho, David

A Knee Point Based Evolutionary Multi-objective Optimization for Mission Planning Problems Inproceedings

In: Proceedings of the Genetic and Evolutionary Computation Conference, pp. 1216–1223, ACM, Berlin, Germany, 2017, ISBN: 978-1-4503-4920-8.

Rodríguez-Fernández, Víctor; Menéndez, Héctor D; Camacho, David

A study on performance metrics and clustering methods for analyzing behavior in UAV operations Journal Article

In: Journal of Intelligent and Fuzzy Systems, vol. 32, no. 2, pp. 1307–1319, 2017.

Rodríguez-Fernández, Víctor; Menéndez, Héctor D; Camacho, David

Analysing temporal performance profiles of UAV operators using time series clustering Journal Article

In: Expert Systems with Applications, vol. 70, pp. 103–118, 2017, ISSN: 0957-4174.

Delgado, Maria Soledad; Higuera, Clara; Calle-Espinosa, Jorge; Morán, Federico; Montero, Francisco

A SOM prototype-based cluster analysis methodology Journal Article

In: Expert Systems with Applications, vol. 88, pp. 14-28, 2017, ISSN: 0957-4174.

@article{DELGADO201714,

title = {A SOM prototype-based cluster analysis methodology},

author = {Maria Soledad Delgado and Clara Higuera and Jorge Calle-Espinosa and Federico Morán and Francisco Montero},

url = {https://www.sciencedirect.com/science/article/pii/S0957417417304396},

doi = {https://doi.org/10.1016/j.eswa.2017.06.022},

issn = {0957-4174},

year  = {2017},

date = {2017-01-01},

journal = {Expert Systems with Applications},

volume = {88},

pages = {14-28},

abstract = {Data clustering is aimed at finding groups of data that share common hidden properties. These kinds of techniques are especially critical at early stages of data analysis where no information about the dataset is available. One of the mayor shortcomings of the clustering algorithms is the difficulty for non-experts users to configure them and, in some cases, interpret the results. In this work a computational approach with a two-layer structure based on Self-Organizing Map (SOM) is presented for cluster analysis. In the first level, a quantization of the data samples using topology-preserving metrics to automatically determine the number of units in the SOM is proposed. In the second level the obtained SOM prototypes are clustered by means of a connectivity analysis to explore the quality of the partitioning with different number of clusters. The most important benefit of this two-layer procedure is that computational load decreases considerably in comparison with data based clustering methods, making it possible to cluster large data sets and to consider several different clustering alternatives in a limited time. This methodology produces a two-dimensional map representation of the, usually, high dimensional input space, along with quantitative information on viable clustering alternatives, which facilitates the exploration of the possible partitions in a dataset. The efficiency and interpretation of the methodology is illustrated by its application to artificial, benchmark and real complex biological datasets. The experimental results demonstrate the ability of the method to identify possible segmentations in a dataset, compared to algorithms that only yield a single clustering solution. The proposed algorithm tackles the intrinsic limitations of SOM and the parameter settings associated with the clustering methodology, without requiring the number of clusters or the SOM architecture as a prerequisite, among others. This way, it makes possible its application even by researchers with a limited expertise in machine learning.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

Data clustering is aimed at finding groups of data that share common hidden properties. These kinds of techniques are especially critical at early stages of data analysis where no information about the dataset is available. One of the mayor shortcomings of the clustering algorithms is the difficulty for non-experts users to configure them and, in some cases, interpret the results. In this work a computational approach with a two-layer structure based on Self-Organizing Map (SOM) is presented for cluster analysis. In the first level, a quantization of the data samples using topology-preserving metrics to automatically determine the number of units in the SOM is proposed. In the second level the obtained SOM prototypes are clustered by means of a connectivity analysis to explore the quality of the partitioning with different number of clusters. The most important benefit of this two-layer procedure is that computational load decreases considerably in comparison with data based clustering methods, making it possible to cluster large data sets and to consider several different clustering alternatives in a limited time. This methodology produces a two-dimensional map representation of the, usually, high dimensional input space, along with quantitative information on viable clustering alternatives, which facilitates the exploration of the possible partitions in a dataset. The efficiency and interpretation of the methodology is illustrated by its application to artificial, benchmark and real complex biological datasets. The experimental results demonstrate the ability of the method to identify possible segmentations in a dataset, compared to algorithms that only yield a single clustering solution. The proposed algorithm tackles the intrinsic limitations of SOM and the parameter settings associated with the clustering methodology, without requiring the number of clusters or the SOM architecture as a prerequisite, among others. This way, it makes possible its application even by researchers with a limited expertise in machine learning.

Martín, Alejandro; Lara-Cabrera, Raúl; Fuentes-Hurtado, Félix; Naranjo, Valery; Camacho, David

EvoDeep: a new Evolutionary approach for automatic Deep Neural Networks parametrisation Journal Article

In: Journal of Parallel and Distributed Computing, 2017.

Martín, Alejandro; Fuentes-Hurtado, Félix; Naranjo, Valery; Camacho, David

Evolving deep neural networks architectures for Android malware classification Inproceedings

In: Evolutionary Computation (CEC), 2017 IEEE Congress on, pp. 1659–1666, IEEE 2017.

2016

Ramirez-Atencia, Cristian; Bello-Orgaz, Gema; R-Moreno, Maria D; Camacho, David

A Weighted Penalty Fitness for a Hybrid MOGA-CSP to solve Mission Planning Problems Inproceedings

In: XI Congreso Español de Metaheurísticas, Algoritmos Evolutivos y Bioinspirados (MAEB 2016), pp. 305–314, 2016.

Ramirez-Atencia, Cristian; Bello-Orgaz, Gema; R-Moreno, Maria D; Camacho, David

MOGAMR: A Multi-Objective Genetic Algorithm for Real-Time Mission Replanning Inproceedings

In: 2016 IEEE Symposium Series on Computational Intelligence (SSCI), 2016, ISBN: 978-1-5090-4240-1, 978-1-5090-4241-8.

@inproceedings{Ramirez-Atencia2016b,

title = {MOGAMR: A Multi-Objective Genetic Algorithm for Real-Time Mission Replanning},

author = {Cristian Ramirez-Atencia and Gema Bello-Orgaz and Maria D R-Moreno and David Camacho},

doi = {10.1109/SSCI.2016.7850235},

isbn = {978-1-5090-4240-1, 978-1-5090-4241-8},

year  = {2016},

date = {2016-01-01},

booktitle = {2016 IEEE Symposium Series on Computational Intelligence (SSCI)},

abstract = {From the last few years the interest and repercussion on Unmanned Aerial Vehicle (UAV) technologies have been extended from pure military applications to industrial and societal applications. One of the basic tasks to any UAV problems is related to the Mission Planning. This problem is particularly complex when a set of UAVs is considered. In the field of MultiUAV Mission Planning, some approaches have been carried out in the last years. However, there are few works related to realtime Mission Replanning, which is the focus of this work. In Mission Replanning, some changes in the mission, such as the arrival of new tasks, require to update the preplanned solution as fast as possible. In this paper a Multi-Objective Genetic Algorithm for Mission Replanning (MOGAMR) is proposed to handle this problem. This approach uses a set of previous plans (or solutions), generated using an offlline planning process, in order to initialize the population of the algorithm, then acts as a complete regeneration method. In order to simulate a real-time system we have fixed a time limit of 2 minutes. This has been considered as an appropriate time for a human operator to take a decision. Using this time restriction, a set of experiments adding from 1 to 5 new tasks in the Replanning Problems has been carried out. The experiments show that the algorithm works well with this few number of new tasks during the replanning process generating a set of feasible solutions under the time restriction considered.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

Martín, Alejandro; Menéndez, Héctor D; Camacho, David

MOCDroid: multi-objective evolutionary classifier for Android malware detection Journal Article

In: Soft Computing, pp. 1–11, 2016.

Suárez, Óscar Manuel Losada; Rodríguez-Fernández, Víctor; Ramírez-Atencia, Cristian; Camacho, David

Desarrollo de una plataforma basada en Unity3D para la aplicación de IA en videojuegos Inproceedings

In: 3rd Congreso de la Sociedad Española para las Ciencias del Videojuego (CoSECiVi 2016), pp. 135–146, CEUR Workshop, Barcelona, Spain, 2016, ISSN: 16130073.

2015

Delgado, Maria Soledad; Morán, Federico; Mora, Antonio; Merelo, Juan Julián; Briones, Carlos

A novel representation of genomic sequences for taxonomic clustering and visualization by means of self-organizing maps Journal Article

In: Bioinformatics, vol. 31, no. 5, pp. 736-744, 2015, ISSN: 1367-4803.

@article{10.1093/bioinformatics/btu708,

title = {A novel representation of genomic sequences for taxonomic clustering and visualization by means of self-organizing maps},

author = {Maria Soledad Delgado and Federico Morán and Antonio Mora and Juan Julián Merelo and Carlos Briones},

url = {https://doi.org/10.1093/bioinformatics/btu708},

doi = {10.1093/bioinformatics/btu708},

issn = {1367-4803},

year  = {2015},

date = {2015-03-01},

urldate = {2015-03-01},

journal = {Bioinformatics},

volume = {31},

number = {5},

pages = {736-744},

abstract = {Motivation: Self-organizing maps (SOMs) are readily available bioinformatics methods for clustering and visualizing high-dimensional data, provided that such biological information is previously transformed to fixed-size, metric-based vectors. To increase the usefulness of SOM-based approaches for the analysis of genomic sequence data, novel representation methods are required that automatically and bijectively transform aligned nucleotide sequences into numeric vectors, dealing with both nucleotide ambiguity and gaps derived from sequence alignment.Results: Six different codification variants based on Euclidean space, just like SOM processing, have been tested using two SOM models: the classical Kohonen’s SOM and growing cell structures. They have been applied to two different sets of sequences: 32 sequences of small sub-unit ribosomal RNA from organisms belonging to the three domains of life, and 44 sequences of the reverse transcriptase region of the pol gene of human immunodeficiency virus type 1 belonging to different groups and sub-types. Our results show that the most important factor affecting the accuracy of sequence clustering is the assignment of an extra weight to the presence of alignment-derived gaps. Although each of the codification variants shows a different level of taxonomic consistency, the results are in agreement with sequence-based phylogenetic reconstructions and anticipate a broad applicability of this codification method.Contact:sole@eui.upm.esSupplementary information:Supplementary Data are available at Bioinformatics online.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

Ramirez-Atencia, Cristian; Bello-Orgaz, Gema; R-Moreno, María D; Camacho, David

A Hybrid MOGA-CSP for Multi-UAV Mission Planning Inproceedings

In: Proceedings of the Companion Publication of the 2015 on Genetic and Evolutionary Computation Conference, pp. 1205–1208, ACM 2015.

Ramírez-Atencia, Cristian; Bello-Orgaz, Gema; R-Moreno, Maria D; Camacho, David

Performance Evaluation of Multi-UAV Cooperative Mission Planning Models Inproceedings

In: Computational Collective Intelligence - 7th International Conference, ICCCI 2015, Madrid, Spain, September 21-23, 2015, Proceedings, Part II, pp. 203–212, 2015.

Rodriguez-Fernández, Victor; Ramirez-Atencia, Cristian; Camacho, David

A Summary of Player Assessment in a Multi-UAV Mission Planning Serious Game Inproceedings

In: 2nd Congreso de la Sociedad Espa~nola para las Ciencias del Videojuego (CoSeCiVi 2015), 2015.

Rodriguez-Fernandez, Victor; Ramirez-Atencia, Cristian; Camacho, David

A multi-UAV Mission Planning videogame-based framework for player analysis Inproceedings

In: Evolutionary Computation (CEC), 2015 IEEE Congress on, pp. 1490–1497, IEEE 2015.

Palero, Fernando; Gonzalez-Pardo, Antonio; Camacho, David

Simple gamer interaction analysis through tower defense games Conference

6th International Conference on Computational Collective Intelligence Technologies and Applications (ICCCI 2014), Lecture Notes in Artificial Intelligence of Springer-Verlag, 2015.

Rodríguez-Fernández, Víctor; Menéndez, Héctor D; Camacho, David

User Profile Analysis for UAV Operators in a Simulation Environment Inproceedings

In: Computational Collective Intelligence - 7th International Conference, ICCCI 2015, Madrid, Spain, September 21-23, 2015. Proceedings, Part I, pp. 338–347, 2015.

Palero, Fernando; Ramirez-Atencia, Cristian; Camacho, David

Online gamers classification using k-means Incollection

In: Intelligent Distributed Computing VIII, pp. 201–208, Springer, Cham, 2015.