@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 = {Clustering, Neural Networks, Self-organizing map, Unsupervised},

pubstate = {published},

tppubtype = {article}

}

@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 = {Clustering, Growing cell structures, Health, Self-organizing map},

pubstate = {published},

tppubtype = {article}

}

@article{DBLP:journals/jifs/Rodriguez-Fernandez17,

title = {A study on performance metrics and clustering methods for analyzing behavior in UAV operations},

author = {Víctor Rodríguez-Fernández and Héctor D Menéndez and David Camacho},

url = {http://dx.doi.org/10.3233/JIFS-169129},

doi = {10.3233/JIFS-169129},

year  = {2017},

date = {2017-01-01},

urldate = {2017-01-01},

journal = {Journal of Intelligent and Fuzzy Systems},

volume = {32},

number = {2},

pages = {1307--1319},

keywords = {Behavioral Patterns, Clustering, Industry, Operator, Performance Metrics, Unmanned Aircraft Systems},

pubstate = {published},

tppubtype = {article}

}

@article{rodriguez20171Analysing,

title = {Analysing temporal performance profiles of UAV operators using time series clustering},

author = {Víctor Rodríguez-Fernández and Héctor D Menéndez and David Camacho},

url = {http://www.sciencedirect.com/science/article/pii/S0957417416305851},

doi = {http://dx.doi.org/10.1016/j.eswa.2016.10.044},

issn = {0957-4174},

year  = {2017},

date = {2017-01-01},

urldate = {2017-01-01},

journal = {Expert Systems with Applications},

volume = {70},

pages = {103--118},

keywords = {Clustering, Operator, Performance Metrics, Simulation-based Training, Time Series, Unmanned Aircraft Systems},

pubstate = {published},

tppubtype = {article}

}

@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 = {Clustering, Metabolic network, Self-organizing map, Topology preserving, Unsupervised},

pubstate = {published},

tppubtype = {article}

}

@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 = {Clustering, Distance Measures, Growing cell structures, Self-organizing map},

pubstate = {published},

tppubtype = {article}

}

@article{menendez2014genetic,

title = {A Genetic Graph-based Approach for Partitional Clustering},

author = {Héctor D Menéndez and David F Barrero and David Camacho},

year  = {2014},

date = {2014-01-01},

journal = {International journal of neural systems},

volume = {24},

number = {03},

publisher = {World Scientific Publishing Company},

keywords = {Clustering, Genetic Algorithms, Graph Theory},

pubstate = {published},

tppubtype = {article}

}

@article{bello2014combining,

title = {Combining Social-Based Data Mining Techniques To Extract Collective Trends From Twitter},

author = {Gema Bello-Orgaz and Héctor D Menéndez and Shintaro Okazaki and David Camacho},

url = {https://aida.etsisi.upm.es/wp-content/uploads/2014/12/MJCS13_BelloOrgaz-Menendez.pdf},

isbn = {0127-9084},

year  = {2014},

date = {2014-01-01},

urldate = {2014-01-01},

journal = {Malaysian Journal of Computer Science},

volume = {27},

number = {2},

keywords = {Classification, Clustering, Collective Trends, Social Networks, Twitter},

pubstate = {published},

tppubtype = {article}

}

@article{Menendez:2013:JSSC,

title = {Extracting Behavioural Models from 2010 FIFA World Cup},

author = {Hector D Menendez and Gema Bello-Orgaz and David Camacho},

url = {http://link.springer.com/article/10.1007%2Fs11424-013-2289-9},

issn = {1009-6124},

year  = {2013},

date = {2013-02-01},

urldate = {2013-02-01},

journal = {Journal of Systems Science and Complexity},

volume = {26},

number = {1},

pages = {43-61},

publisher = {Academy of Mathematics and Chinese Academy Sciences of Systems Science},

abstract = {The FIFA World Cup™ is the most profitable worldwide event. The FIFA publishes global statistics of this competition which provide global data about the players and teams during the competition. This work is focused on the extraction of behavioural patterns for both, players and teams strategies, through the automated analysis of this dataset. The knowledge and models extracted in this work could be applied to soccer leagues or even it could be oriented to sport betting. However, the main contribution is related to the study on several automatic knowledge extraction techniques, such as clustering methods, and how these techniques can be used to obtain useful behavioural models from a global statistics dataset. The information provided by the clustering algorithms shows similar properties which have been combined to define the models, making the human interpretation of these statistics easier. Finally, the most successful teams strategies have been analysed and compared.},

keywords = {Clustering, Information Extraction, Knowledge-based Systems},

pubstate = {published},

tppubtype = {article}

}

@article{Granados20128537,

title = {Is the contextual information relevant in text clustering by compression?},

author = {David Camacho and Ana Granados and Francisco Borja Rodrí­guez},

url = {http://dx.doi.org/10.1016/j.eswa.2012.01.215},

issn = {0957-4174},

year  = {2012},

date = {2012-08-01},

urldate = {2012-08-01},

journal = {Expert Systems with Applications},

volume = {39},

number = {10},

pages = {8537 - 8546},

publisher = {Elsevier},

keywords = {Clustering, Contextual information, Data Compression, Text Clustering, Word Removal},

pubstate = {published},

tppubtype = {article}

}

@article{Bello-Orgaz:2012:IJNS,

title = {Adaptive K-Means Algorithm for overlapped graph clustering},

author = {Gema Bello-Orgaz and Hector D Menendez and David Camacho},

url = {http://www.worldscientific.com/doi/abs/10.1142/S0129065712500189 

https://aida.etsisi.upm.es/wp-content/uploads/2012/09/ijns-2012.pdf},

issn = {0129-0657},

year  = {2012},

date = {2012-06-18},

urldate = {2012-06-18},

journal = {International Journal of Neural Systems},

volume = {22 (Impact Factor:5.1 -Q1)},

number = {05},

pages = {1250018 1--19},

keywords = {Clustering, Genetic Algorithms, Graph Theory, Overlapping Clustering},

pubstate = {published},

tppubtype = {article}

}

@article{5582094,

title = {Reducing the Loss of Information through Annealing Text Distortion},

author = {David Camacho and Ana Granados and Manuel Cebrián and Francisco Borja Rodrí­guez},

url = {http://dx.doi.org/10.1109/TKDE.2010.173},

issn = {1041-4347},

year  = {2011},

date = {2011-07-01},

urldate = {2011-07-01},

journal = {IEEE Transactions on Knowledge and Data Engineering},

volume = {23},

number = {7},

pages = {1090-1102},

publisher = {IEEE Press},

keywords = {Clustering, Data Compression, Data Mining, Text Analysis},

pubstate = {published},

tppubtype = {article}

}

@article{DBLP:journals/corr/abs-0711-4075,

title = {Evaluating the Impact of Information Distortion on Normalized Compression Distance-driven Text Clustering},

author = {Ana Granados and Manuel Cebrián and David Camacho and Francisco Borja Rodrí­guez},

year  = {2007},

date = {2007-01-01},

urldate = {2007-01-01},

journal = {CoRR},

volume = {abs/0711.4075},

keywords = {Clustering, Data Analysis},

pubstate = {published},

tppubtype = {article}

}