Publications
2025
Jáñez-Martino, Francisco; Alaiz-Rodríguez, Rocío; González-Castro, Víctor; Fidalgo, Eduardo; Alegre, Enrique
Spam email classification based on cybersecurity potential risk using natural language processing Artículo de revista
En: Knowledge-Based Systems, vol. 310, pp. 112939, 2025, ISSN: 0950-7051.
Resumen | Enlaces | BibTeX | Etiquetas: Cybersecurity, Feature extraction, Malicious spam email detection, NLP, Security awareness
@article{JANEZMARTINO2025112939,
title = {Spam email classification based on cybersecurity potential risk using natural language processing},
author = {Francisco Jáñez-Martino and Rocío Alaiz-Rodríguez and Víctor González-Castro and Eduardo Fidalgo and Enrique Alegre},
url = {https://www.sciencedirect.com/science/article/pii/S0950705124015739},
doi = {https://doi.org/10.1016/j.knosys.2024.112939},
issn = {0950-7051},
year = {2025},
date = {2025-01-01},
journal = {Knowledge-Based Systems},
volume = {310},
pages = {112939},
abstract = {Spam emails go beyond being merely annoying messages, they have become one of the most used vectors for cyberattacks such as stealing personal information or spreading malware. These breaches in cybersecurity lead to financial and data loss for individuals and organisations. Thus, the ability to differentiate potentially risky emails is crucial to launch earlier warnings and gain relevant information for cybersecurity experts. Recent works have proposed models to detect phishing, fraudulent or critical spam emails. However, their focus is often restricted to a particular email type or only evaluated on spam emails received by organisations. In this work, we propose a new set of 56 features extracted using Natural Language Processing (NLP) techniques and grouped into five categories: Headers, Text, Attachments, URLs, and Protocols. We build a dataset, Spam Email Risk Classification (SERC), divided into two sub-datasets: one collected from a private source and another from Bruce Guenter’s public corpus. To assess the potential risk of spam emails for users, we follow two strategies: a binary classification using low and high risk and a regression approach to predict the level of risk from 1 to 10. We evaluated three Machine Learning classifiers and three regression models. Random Forest obtains the highest classification performance with 0.914 of F1-Score on SERC and Random Forest Regressor achieves the lowest Mean Square Error (MSE) of 0.781 for regression. We also conduct an analysis of the feature importance in terms of each feature and group where those from the Headers and Text groups become more relevant.},
keywords = {Cybersecurity, Feature extraction, Malicious spam email detection, NLP, Security awareness},
pubstate = {published},
tppubtype = {article}
}
2024
Medina, Pablo Blanco; Biswas, Rubel; Castro, Victor González; Rodríguez, Rocío Alaiz; Fidalgo, Eduardo; Alegre, Enrique
Mejoras en extracción de URLs en smishing mediante text spotting Artículo de revista
En: Jornadas de Automática, no 45, 2024.
Resumen | Enlaces | BibTeX | Etiquetas:
@article{medina2024mejoras,
title = {Mejoras en extracción de URLs en smishing mediante text spotting},
author = {Pablo Blanco Medina and Rubel Biswas and Victor González Castro and Rocío Alaiz Rodríguez and Eduardo Fidalgo and Enrique Alegre},
url = {https://dialnet.unirioja.es/servlet/articulo?codigo=9724124},
year = {2024},
date = {2024-01-01},
urldate = {2024-01-01},
journal = {Jornadas de Automática},
number = {45},
abstract = {Computer Emergency Response Teams (CERTs) often get screenshots showcasing brief texts with doubtful content. Smishing attempts to mimic reputable organizations, urging individuals to act promptly by clicking on a link, aiming to hijack personal information or illicitly debit funds from their accounts. CERTs may find value in automated solutions that can retrieve URLs from screenshots for subsequent validation. Approaches based on Optical Character Recognizers (OCRs) could be used to extract text. However, their performance is low due to the poor performance of OCR in certain images. In this work, we propose a pipeline for Smishing URL extraction based on Text Spotting, which will later be applied to a custom URL reconstruction using highlighted features. We applied the proposed pipeline to a custom set of 117 screenshots containing 121 URLs, resulting in aprecision increase on the URL recovery task from 3,05 % to 22,90 %. This allows the original URL to be restored for subsequent processing in the analysis o fSmishing messages.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
2023
Jáñez-Martino, Francisco; Alaiz-Rodríguez, Rocío; González-Castro, Víctor; Fidalgo, Eduardo; Alegre, Enrique
A review of spam email detection: analysis of spammer strategies and the dataset shift problem Artículo de revista
En: Artificial Intelligence Review, vol. 56, no 2, pp. 1145–1173, 2023.
Resumen | Enlaces | BibTeX | Etiquetas:
@article{Jáñez-Martino2023,
title = {A review of spam email detection: analysis of spammer strategies and the dataset shift problem},
author = {Francisco Jáñez-Martino and Rocío Alaiz-Rodríguez and Víctor González-Castro and Eduardo Fidalgo and Enrique Alegre},
url = {https://doi.org/10.1007/s10462-022-10195-4},
doi = {10.1007/s10462-022-10195-4},
year = {2023},
date = {2023-01-01},
journal = {Artificial Intelligence Review},
volume = {56},
number = {2},
pages = {1145–1173},
abstract = {Spam emails have been traditionally seen as just annoying and unsolicited emails containing advertisements, but they increasingly include scams, malware or phishing. In order to ensure the security and integrity for the users, organisations and researchers aim to develop robust filters for spam email detection. Recently, most spam filters based on machine learning algorithms published in academic journals report very high performance, but users are still reporting a rising number of frauds and attacks via spam emails. Two main challenges can be found in this field: (a) it is a very dynamic environment prone to the dataset shift problem and (b) it suffers from the presence of an adversarial figure, i.e. the spammer. Unlike classical spam email reviews, this one is particularly focused on the problems that this constantly changing environment poses. Moreover, we analyse the different spammer strategies used for contaminating the emails, and we review the state-of-the-art techniques to develop filters based on machine learning. Finally, we empirically evaluate and present the consequences of ignoring the matter of dataset shift in this practical field. Experimental results show that this shift may lead to severe degradation in the estimated generalisation performance, with error rates reaching values up to 48.81%.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Chaves, D.; Agarwal, N.; Fidalgo, E.; Alegre, E.
A Data Augmentation Strategy for Improving Age Estimation to Support CSEM Detection Artículo de revista
En: Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, vol. 5, no ISBN 978-989-758-634-7, ISSN 2184-4321, pp. 692–699, 2023, (Publisher: 10.5220/0011719700003417).
Resumen | Enlaces | BibTeX | Etiquetas: age stimation, CSEM, data augmentation, facial occlusion, prevention, synthetic datasets
@article{chaves_data_2023,
title = {A Data Augmentation Strategy for Improving Age Estimation to Support CSEM Detection},
author = {D. Chaves and N. Agarwal and E. Fidalgo and E. Alegre},
url = {https://www.scitepress.org/PublishedPapers/2023/117197/117197.pdf},
year = {2023},
date = {2023-01-01},
journal = {Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications},
volume = {5},
number = {ISBN 978-989-758-634-7, ISSN 2184-4321},
pages = {692–699},
abstract = {Leveraging image-based age estimation in preventing Child Sexual Exploitation Material (CSEM) content over the internet is not investigated thoroughly in the research community. While deep learning methods are considered state-of-the-art for general age estimation, they perform poorly in predicting the age group of minors and older adults due to the few examples of these age groups in the existing datasets. In this work, we present a data augmentation strategy to improve the performance of age estimators trained on imbalanced data based on synthetic image generation and artificial facial occlusion. Facial occlusion is focused on modelling as CSEM criminals tend to cover certain parts of the victim, such as the eyes, to hide their identity. The proposed strategy is evaluated using the Soft Stagewise Regression Network (SSR-Net), a compact size age estimator and three publicly available datasets composed mainly of non-occluded images. Therefore, we create the Synthetic Augmented with Occluded Faces (SAOF-15K) dataset to assess the performance of eye and mouthoccluded images. Results show that our strategy improves the performance of the evaluated age estimator.},
note = {Publisher: 10.5220/0011719700003417},
keywords = {age stimation, CSEM, data augmentation, facial occlusion, prevention, synthetic datasets},
pubstate = {published},
tppubtype = {article}
}
Joshi, Akanksha; Fidalgo, Eduardo; Alegre, Enrique; Fernández-Robles, Laura
DeepSumm: Exploiting topic models and sequence to sequence networks for extractive text summarization Artículo de revista
En: Expert Systems with Applications, vol. 211, pp. 118442, 2023, ISSN: 0957-4174.
Resumen | Enlaces | BibTeX | Etiquetas: Attention networks, Extractive, Seq2seq, Text summarization, Topic models
@article{JOSHI2023118442,
title = {DeepSumm: Exploiting topic models and sequence to sequence networks for extractive text summarization},
author = {Akanksha Joshi and Eduardo Fidalgo and Enrique Alegre and Laura Fernández-Robles},
url = {https://www.sciencedirect.com/science/article/pii/S0957417422015391},
doi = {https://doi.org/10.1016/j.eswa.2022.118442},
issn = {0957-4174},
year = {2023},
date = {2023-01-01},
journal = {Expert Systems with Applications},
volume = {211},
pages = {118442},
abstract = {In this paper, we propose DeepSumm, a novel method based on topic modeling and word embeddings for the extractive summarization of single documents. Recent summarization methods based on sequence networks fail to capture the long range semantics of the document which are encapsulated in the topic vectors of the document. In DeepSumm, our aim is to utilize the latent information in the document estimated via topic vectors and sequence networks to improve the quality and accuracy of the summarized text. Each sentence is encoded through two different recurrent neural networks based on probabilistic topic distributions and word embeddings, and then a sequence to sequence network is applied to each sentence encoding. The outputs of the encoder and the decoder in the sequence to sequence networks are combined after weighting using an attention mechanism and converted into a score through a multi-layer perceptron network. We refer to the score obtained through the topic model as Sentence Topic Score (STS) and to the score generated through word embeddings as Sentence Content Score (SCS). In addition, we propose Sentence Novelty Score (SNS) and Sentence Position Score (SPS) and perform a weighted fusion of the four scores for each sentence in the document to compute a Final Sentence Score (FSS). The proposed DeepSumm framework was evaluated on the standard DUC 2002 benchmark and CNN/DailyMail datasets. Experimentally, it was demonstrated that our method captures both the global and the local semantic information of the document and essentially outperforms existing state-of-the-art approaches for extractive text summarization with ROUGE-1, ROUGE-2, and ROUGE-L scores of 53.2, 28.7 and 49.2 on DUC 2002 and 43.3, 19.0 and 38.9 on CNN/DailyMail dataset.},
keywords = {Attention networks, Extractive, Seq2seq, Text summarization, Topic models},
pubstate = {published},
tppubtype = {article}
}
Jáñez-Martino, Francisco; Alaiz-Rodríguez, Rocío; González-Castro, Víctor; Fidalgo, Eduardo; Alegre, Enrique
Classifying spam emails using agglomerative hierarchical clustering and a topic-based approach Artículo de revista
En: Applied Soft Computing, vol. 139, pp. 110226, 2023, ISSN: 1568-4946.
Resumen | Enlaces | BibTeX | Etiquetas: Hidden text, Image-based spam, Multi-classification, Spam detection, Term frequency, Text classification, Word embedding
@article{JANEZMARTINO2023110226b,
title = {Classifying spam emails using agglomerative hierarchical clustering and a topic-based approach},
author = {Francisco Jáñez-Martino and Rocío Alaiz-Rodríguez and Víctor González-Castro and Eduardo Fidalgo and Enrique Alegre},
url = {https://www.sciencedirect.com/science/article/pii/S1568494623002442},
doi = {https://doi.org/10.1016/j.asoc.2023.110226},
issn = {1568-4946},
year = {2023},
date = {2023-01-01},
urldate = {2023-01-01},
journal = {Applied Soft Computing},
volume = {139},
pages = {110226},
abstract = {Spam emails are unsolicited, annoying and sometimes harmful messages which may contain malware, phishing or hoaxes. Unlike most studies that address the design of efficient anti-spam filters, we approach the spam email problem from a different and novel perspective. Focusing on the needs of cybersecurity units, we follow a topic-based approach for addressing the classification of spam email into multiple categories. We propose SPEMC-15K-E and SPEMC-15K-S, two novel datasets with approximately 15K emails each in English and Spanish, respectively, and we label them using agglomerative hierarchical clustering into 11 classes. We evaluate 16 pipelines, combining four text representation techniques -Term Frequency-Inverse Document Frequency (TF-IDF), Bag of Words, Word2Vec and BERT- and four classifiers: Support Vector Machine, Näive Bayes, Random Forest and Logistic Regression. Experimental results show that the highest performance is achieved with TF-IDF and LR for the English dataset, with a F1 score of 0.953 and an accuracy of 94.6%, and while for the Spanish dataset, TF-IDF with NB yields a F1 score of 0.945 and 98.5% accuracy. Regarding the processing time, TF-IDF with LR leads to the fastest classification, processing an English and Spanish spam email in 2ms and 2.2ms on average, respectively.},
keywords = {Hidden text, Image-based spam, Multi-classification, Spam detection, Term frequency, Text classification, Word embedding},
pubstate = {published},
tppubtype = {article}
}
2022
Castejón-Limas, Manuel; Fernández-Robles, Laura; Alaiz-Moretón, Héctor; Cifuentes-Rodriguez, Jaime; Fernández-Llamas, Camino
A framework for the optimization of complex cyber-physical systems via directed acyclic graph Artículo de revista
En: Sensors, vol. 22, no 4, pp. 1490, 2022, (Publisher: MDPI).
Resumen | Enlaces | BibTeX | Etiquetas: Cyber-Physical Systems, Directed Acyclic Graphs, Lean Manufacturing, machine learning models, pipegraph, scikit-learn
@article{castejon-limas_framework_2022,
title = {A framework for the optimization of complex cyber-physical systems via directed acyclic graph},
author = {Manuel Castejón-Limas and Laura Fernández-Robles and Héctor Alaiz-Moretón and Jaime Cifuentes-Rodriguez and Camino Fernández-Llamas},
url = {https://www.mdpi.com/1424-8220/22/4/1490},
year = {2022},
date = {2022-01-01},
journal = {Sensors},
volume = {22},
number = {4},
pages = {1490},
abstract = {Mathematical modeling and data-driven methodologies are frequently required to optimize industrial processes in the context of Cyber-Physical Systems (CPS). This paper introduces the PipeGraph software library, an open-source python toolbox for easing the creation of machine learning models by using Directed Acyclic Graph (DAG)-like implementations that can be used for CPS. scikit-learn’s Pipeline is a very useful tool to bind a sequence of transformers and a final estimator in a single unit capable of working itself as an estimator. It sequentially assembles several steps that can be cross-validated together while setting different parameters. Steps encapsulation secures the experiment from data leakage during the training phase. The scientific goal of PipeGraph is to extend the concept of Pipeline by using a graph structure that can handle scikit-learn’s objects in DAG layouts. It allows performing diverse operations, instead of only transformations, following the topological ordering of the steps in the graph; it provides access to all the data generated along the intermediate steps; and it is compatible with GridSearchCV function to tune the hyperparameters of the steps. It is also not limited to (𝑋,𝑦) entries. Moreover, it has been proposed as part of the scikit-learn-contrib supported project, and is fully compatible with scikit-learn. Documentation and unitary tests are publicly available together with the source code. Two case studies are analyzed in which PipeGraph proves to be essential in improving CPS modeling and optimization: the first is about the optimization of a heat exchange management system, and the second deals with the detection of anomalies in manufacturing processes.},
note = {Publisher: MDPI},
keywords = {Cyber-Physical Systems, Directed Acyclic Graphs, Lean Manufacturing, machine learning models, pipegraph, scikit-learn},
pubstate = {published},
tppubtype = {article}
}
2020
Conde, Miguel Á; Rodríguez-Sedano, Francisco J; Fernández, Camino; Gutiérrez-Fernández, Alexis; Fernández-Robles, Laura; Limas, Manuel Castejón
A Learning Analytics tool for the analysis of students’ Telegram messages in the context of teamwork virtual activities Artículo de revista
En: Eighth International Conference on Technological Ecosystems for Enhancing Multiculturality, pp. 719–724, 2020.
Resumen | Enlaces | BibTeX | Etiquetas: instant messaging tools, learning analytics, online education, teamwork evaluation, telegram in education
@article{conde_learning_2020,
title = {A Learning Analytics tool for the analysis of students’ Telegram messages in the context of teamwork virtual activities},
author = {Miguel Á Conde and Francisco J Rodríguez-Sedano and Camino Fernández and Alexis Gutiérrez-Fernández and Laura Fernández-Robles and Manuel Castejón Limas},
url = {https://dl.acm.org/doi/abs/10.1145/3434780.3436601},
year = {2020},
date = {2020-01-01},
journal = {Eighth International Conference on Technological Ecosystems for Enhancing Multiculturality},
pages = {719–724},
abstract = {In the current COVID-19 pandemic situation, online education has been the only approach of most educational institutions. It is necessary to have tools to assess students in online education, even when they carry out activities that are most common in face to face contexts such as teamwork. In order to do so, different methodologies and learning analytics tools can be employed. However, in a complete online context the students not only interact with the asynchronous tools that educational platforms provide but they also use instant messaging tools. This paper describes a Learning Analytics tool that facilitates teachers the evaluation of students’ interactions in Telegram Instant Messaging Tool. It has been employed in the context of the evaluation of the individual acquisition of teamwork competence. The tool has been tested in a computer science course. It had associated an improvement on students’ grades and they show their preference in using instant messaging tools because by using them conversations are more natural.},
keywords = {instant messaging tools, learning analytics, online education, teamwork evaluation, telegram in education},
pubstate = {published},
tppubtype = {article}
}
2019
Cueto-López, Nahúm; García-Ordás, Maria Teresa; Dávila-Batista, Verónica; Moreno, Víctor; Aragonés, Nuria; Alaiz-Rodríguez, Rocío
A comparative study on feature selection for a risk prediction model for colorectal cancer Artículo de revista
En: Computer methods and programs in biomedicine, vol. 177, pp. 219–229, 2019, (Publisher: Elsevier).
Resumen | Enlaces | BibTeX | Etiquetas: algorithm stability, colorectal cancer, feature selection, ranking methods, risk prediction models
@article{cueto-lopez_comparative_2019,
title = {A comparative study on feature selection for a risk prediction model for colorectal cancer},
author = {Nahúm Cueto-López and Maria Teresa García-Ordás and Verónica Dávila-Batista and Víctor Moreno and Nuria Aragonés and Rocío Alaiz-Rodríguez},
url = {https://arxiv.org/abs/2402.05293},
year = {2019},
date = {2019-01-01},
journal = {Computer methods and programs in biomedicine},
volume = {177},
pages = {219–229},
abstract = {The aim of this study is to evaluate risk prediction models to identify individuals at higher risk of developing colorectal cancer, focusing on feature selection methods. This is crucial for improving model performance, avoiding overfitting, and highlighting key risk factors. Additionally, the stability of feature selection/ranking methods is analyzed using conventional metrics and a visual approach proposed in this study.},
note = {Publisher: Elsevier},
keywords = {algorithm stability, colorectal cancer, feature selection, ranking methods, risk prediction models},
pubstate = {published},
tppubtype = {article}
}
Aláiz-Moretón, Héctor; Castejón-Limas, Manuel; Casteleiro-Roca, José-Luis; Jove, Esteban; Robles, Laura Fernández; Calvo-Rolle, José Luis
A fault detection system for a geothermal heat exchanger sensor based on intelligent techniques Artículo de revista
En: Sensors, vol. 19, no 12, pp. 2740, 2019, (Publisher: MDPI).
Resumen | Enlaces | BibTeX | Etiquetas: adaptative boosting, extremely randomized trees, fault detection, geothermal heat exchanger, gradient boosting, k-nearest neighbors, random decision forest, shallow neural networks
@article{alaiz-moreton_fault_2019,
title = {A fault detection system for a geothermal heat exchanger sensor based on intelligent techniques},
author = {Héctor Aláiz-Moretón and Manuel Castejón-Limas and José-Luis Casteleiro-Roca and Esteban Jove and Laura Fernández Robles and José Luis Calvo-Rolle},
url = {https://www.mdpi.com/1424-8220/19/12/2740},
year = {2019},
date = {2019-01-01},
journal = {Sensors},
volume = {19},
number = {12},
pages = {2740},
abstract = {his paper proposes a methodology for dealing with an issue of crucial practical importance in real engineering systems such as fault detection and recovery of a sensor. The main goal is to define a strategy to identify a malfunctioning sensor and to establish the correct measurement value in those cases. As study case, we use the data collected from a geothermal heat exchanger installed as part of the heat pump installation in a bioclimatic house. The sensor behaviour is modeled by using six different machine learning techniques: Random decision forests, gradient boosting, extremely randomized trees, adaptive boosting, k-nearest neighbors, and shallow neural networks. The achieved results suggest that this methodology is a very satisfactory solution for this kind of systems.},
note = {Publisher: MDPI},
keywords = {adaptative boosting, extremely randomized trees, fault detection, geothermal heat exchanger, gradient boosting, k-nearest neighbors, random decision forest, shallow neural networks},
pubstate = {published},
tppubtype = {article}
}
Díez-González, Javier; Álvarez, Rubén; Sánchez-González, Lidia; Fernández-Robles, Laura; Pérez, Hilde; Castejón-Limas, Manuel
3D Tdoa problem solution with four receiving nodes Artículo de revista
En: Sensors, vol. 19, no 13, pp. 2892, 2019, (Publisher: MDPI).
Resumen | Enlaces | BibTeX | Etiquetas: 3D, LPSs, positioning, TDOA
@article{diez-gonzalez_3d_2019,
title = {3D Tdoa problem solution with four receiving nodes},
author = {Javier Díez-González and Rubén Álvarez and Lidia Sánchez-González and Laura Fernández-Robles and Hilde Pérez and Manuel Castejón-Limas},
url = {https://www.mdpi.com/1424-8220/19/13/2892},
year = {2019},
date = {2019-01-01},
journal = {Sensors},
volume = {19},
number = {13},
pages = {2892},
abstract = {Time difference of arrival (TDOA) positioning methods have experienced growing importance over the last few years due to their multiple applications in local positioning systems (LPSs). While five sensors are needed to determine an unequivocal three-dimensional position, systems with four nodes present two different solutions that cannot be discarded according to mathematical standards. In this paper, a new methodology to solve the 3D TDOA problems in a sensor network with four beacons is proposed. A confidence interval, which is defined in this paper as a sphere, is defined to use positioning algorithms with four different nodes. It is proven that the separation between solutions in the four-beacon TDOA problem allows the transformation of the problem into an analogous one in which more receivers are implied due to the geometric properties of the intersection of hyperboloids. The achievement of the distance between solutions needs the application of genetic algorithms in order to find an optimized sensor distribution. Results show that positioning algorithms can be used 96.7% of the time with total security in cases where vehicles travel at less than 25 m/s.},
note = {Publisher: MDPI},
keywords = {3D, LPSs, positioning, TDOA},
pubstate = {published},
tppubtype = {article}
}
2017
García-Ordás, María Teresa; Alegre, Enrique; González-Castro, Víctor; Alaiz-Rodríguez, Rocío
A computer vision approach to analyze and classify tool wear level in milling processes using shape descriptors and machine learning techniques Artículo de revista
En: The International Journal of Advanced Manufacturing Technology, vol. 90, pp. 1947–1961, 2017, (Publisher: Springer London).
Resumen | Enlaces | BibTeX | Etiquetas: Computer vision, cutting tool wear, machine learning, shape descriptors, wear monitoring automation
@article{garcia-ordas_computer_2017,
title = {A computer vision approach to analyze and classify tool wear level in milling processes using shape descriptors and machine learning techniques},
author = {María Teresa García-Ordás and Enrique Alegre and Víctor González-Castro and Rocío Alaiz-Rodríguez},
url = {https://link.springer.com/article/10.1007/s00170-016-9541-0},
year = {2017},
date = {2017-01-01},
journal = {The International Journal of Advanced Manufacturing Technology},
volume = {90},
pages = {1947–1961},
abstract = {In this paper, we present a new approach to categorize the wear of cutting tools used in edge profile milling processes. It is based on machine learning and computer vision techniques, specifically using B-ORCHIZ, a novel shape-based descriptor computed from the wear region image. A new Insert dataset with 212 images of tool wear has been created to evaluate our approach. It contains two subsets: one with images of the main cutting edge and the other one with the edges that converge to it (called Insert-C and Insert-I, respectively). The experiments were conducted trying to discriminate between two (low-high) and three (low-medium-high) different wear levels, and the classification stage was carried out using a support vector machine (SVM). Results show that B-ORCHIZ outperforms other shape descriptors (aZIBO and ZMEG) achieving accuracy values between 80.24 and 88.46 % in the different scenarios evaluated. Moreover, a hierarchical cluster analysis was performed, offering prototype images for wear levels, which may help researchers and technicians to understand how the wear process evolves. These results show a very promising opportunity for wear monitoring automation in edge profile milling processes.},
note = {Publisher: Springer London},
keywords = {Computer vision, cutting tool wear, machine learning, shape descriptors, wear monitoring automation},
pubstate = {published},
tppubtype = {article}
}
Mazo, Claudia; Salazar, Liliana; Corcho, Oscar; Trujillo, Maria; Alegre, Enrique
A histological ontology of the human cardiovascular system Artículo de revista
En: Journal of biomedical semantics, vol. 8, pp. 1–15, 2017, (Publisher: BioMed Central).
Resumen | Enlaces | BibTeX | Etiquetas: bioinformatics, cardiovascular system, histological ontology, medical teaching and research
@article{mazo_histological_2017,
title = {A histological ontology of the human cardiovascular system},
author = {Claudia Mazo and Liliana Salazar and Oscar Corcho and Maria Trujillo and Enrique Alegre},
url = {https://link.springer.com/article/10.1186/s13326-017-0158-5},
year = {2017},
date = {2017-01-01},
journal = {Journal of biomedical semantics},
volume = {8},
pages = {1–15},
abstract = {introduces a histological ontology of the human cardiovascular system, developed collaboratively by histology experts and computer scientists. The ontology follows a methodology based on Conceptual Models (CMs) and is validated using tools like OOPS!, expert evaluations, and its ability to answer Competency Questions (CQs). The ontology is publicly accessible at BioPortal and W3ID.
The ontology is designed to support complex applications, including teaching, medical practices, bio-medical research, and natural language interactions.},
note = {Publisher: BioMed Central},
keywords = {bioinformatics, cardiovascular system, histological ontology, medical teaching and research},
pubstate = {published},
tppubtype = {article}
}
The ontology is designed to support complex applications, including teaching, medical practices, bio-medical research, and natural language interactions.
Hernandez, Maria Valdes; Gonzalez-Castro, Victor
21st Annual Conference on Medical Image Understanding and Analysis, MIUA 2017 Artículo de revista
En: 21st Annual Conference on Medical Image Understanding and Analysis, MIUA 2017, pp. 1–949, 2017, (Publisher: Springer-Verlag).
Resumen | Enlaces | BibTeX | Etiquetas: 21st, analysis, conference, image, medical, MIUA, understanding
@article{hernandez_21st_2017,
title = {21st Annual Conference on Medical Image Understanding and Analysis, MIUA 2017},
author = {Maria Valdes Hernandez and Victor Gonzalez-Castro},
url = {https://www.research.ed.ac.uk/en/publications/21st-annual-conference-on-medical-image-understanding-and-analysi},
year = {2017},
date = {2017-01-01},
journal = {21st Annual Conference on Medical Image Understanding and Analysis, MIUA 2017},
pages = {1–949},
abstract = {The proceedings contain 81 papers. The special focus in this conference is on Medical Image Understanding and Analysis. The topics include: End-to-end learning of a conditional random field for intra-retinal layer segmentation in optical coherence tomography; superpixel-based line operator for retinal blood vessel segmentation; automatic detection and identification of retinal vessel junctions in colour fundus photography; fast optic disc segmentation in retinal images using polar transform; a novel technique for splat generation and patch level prediction in diabetic retinopathy; deep residual networks for quantification of muscle fiber orientation and curvature from ultrasound images; multi-level trainable segmentation for measuring gestational and yolk sacs from ultrasound images; weakly supervised learning of placental ultrasound images with residual networks; edge aware geometric filter for ultrasound image ENHA; tissues classification of the cardiovascular system using texture descriptors; multidimensional assessments of abdominal aortic aneurysms by magnetic resonance against ultrasound diameter measurements; comparison of automatic vessel segmentation techniques for whole body magnetic resonance angiography with limited ground truth data; evaluating classifiers for atherosclerotic plaque component segmentation in MRI; classification of cross-sections for vascular skeleton extraction using convolutional neural networks; improved CTA coronary segmentation with a volume-specific intensity threshold; multi task fully convolutional network for brain tumour segmentation; classification of cervical-cancer using pap-smear images ...},
note = {Publisher: Springer-Verlag},
keywords = {21st, analysis, conference, image, medical, MIUA, understanding},
pubstate = {published},
tppubtype = {article}
}
2012
Morala-Argüello, Patricia; Barreiro, Joaquín; Alegre, Enrique
A evaluation of surface roughness classes by computer vision using wavelet transform in the frequency domain Artículo de revista
En: The International Journal of Advanced Manufacturing Technology, vol. 59, pp. 213–220, 2012, (Publisher: Springer-Verlag).
Resumen | Enlaces | BibTeX | Etiquetas: neural networks, quality inspection, surface roughness, texture analysis, wavelet transform
@article{morala-arguello_evaluation_2012,
title = {A evaluation of surface roughness classes by computer vision using wavelet transform in the frequency domain},
author = {Patricia Morala-Argüello and Joaquín Barreiro and Enrique Alegre},
url = {https://link.springer.com/article/10.1007/s00170-011-3480-6},
year = {2012},
date = {2012-01-01},
journal = {The International Journal of Advanced Manufacturing Technology},
volume = {59},
pages = {213–220},
abstract = {This study proposes a multiresolution method for unmanned visual quality inspection and surface roughness discrimination in turning. Using wavelet transform, texture features were extracted from surface images, focusing on gray levels in vertical detail sub-images. A multilayer Perceptron neural network classified textures, achieving error rates between 2.59% and 4.17%.},
note = {Publisher: Springer-Verlag},
keywords = {neural networks, quality inspection, surface roughness, texture analysis, wavelet transform},
pubstate = {published},
tppubtype = {article}
}
2011
Robles, L Fernández; González-Castro, V; Garcıa-Olalla, O; Garcıa-Ordás, MT; Alegre, E
A local invariant features approach for classifying acrosome integrity in boar spermatozoa Artículo de revista
En: Computational Vision and Medical Image Processing: VipIMAGE 2011, pp. 199, 2011, (Publisher: CRC Press).
Resumen | Enlaces | BibTeX | Etiquetas: acrosome state, sperm cell analysis, SURF method, texture descriptors, veterinary applications
@article{robles_local_2011,
title = {A local invariant features approach for classifying acrosome integrity in boar spermatozoa},
author = {L Fernández Robles and V González-Castro and O Garcıa-Olalla and MT Garcıa-Ordás and E Alegre},
url = {https://books.google.es/books?hl=en&lr=&id=rr7LBQAAQBAJ&oi=fnd&pg=PA199&dq=info:qN1Kvkc9MngJ:scholar.google.com&ots=wusFRCDzZe&sig=uD2_yECMO1Ldc5iYS0gzYkLkGp8&redir_esc=y#v=onepage&q&f=false},
year = {2011},
date = {2011-01-01},
journal = {Computational Vision and Medical Image Processing: VipIMAGE 2011},
pages = {199},
abstract = {In this work we have used a number of texture descriptors to characterize the acrosome state of boar sperm cells, which is a key factor in semen quality control applications. Laws masks, Legendre and Zernike moments, Haralick features extracted from the original image and from the coefficients of the Discrete Wavelet Transform, and descriptors based on interest points using the Speeded-Up Robust Features (SURF) method have been evaluated. Classification using kNN show that the best results were obtained by SURF, with an overall hit rate of 94.88% and, what is more important, a higher hit rate in the damaged (96.86%) than in the intact class (92.89%). These results make this descriptor very attractive for the veterinary community.},
note = {Publisher: CRC Press},
keywords = {acrosome state, sperm cell analysis, SURF method, texture descriptors, veterinary applications},
pubstate = {published},
tppubtype = {article}
}
2009
González-Castro, V; Alegre, Enrique; Morala-Argüello, P; Suarez, SA
A combined and intelligent new segmentation method for boar semen based on thresholding and watershed transform Artículo de revista
En: International Journal of Imaging, vol. 2, no 9 S, pp. 70–80, 2009, (Publisher: Indian Society for Development and Environment Research).
Resumen | Enlaces | BibTeX | Etiquetas: images, segmentation, segmentation method, semen, threshold, watershed
@article{gonzalez-castro_combined_2009,
title = {A combined and intelligent new segmentation method for boar semen based on thresholding and watershed transform},
author = {V González-Castro and Enrique Alegre and P Morala-Argüello and SA Suarez},
url = {https://www.research.ed.ac.uk/en/publications/a-combined-and-intelligent-new-segmentation-method-for-boar-semen},
year = {2009},
date = {2009-01-01},
journal = {International Journal of Imaging},
volume = {2},
number = {9 S},
pages = {70–80},
abstract = {This work presents a new method to segment images of alive and dead spermatozoa in ositive phase contrast. This method improves previous segmentation methods applying an intelligent threshold combined with watershed segmentation. First, it applies an intelligent thresholding segmentation that changes the value of threshold when the binary image obtained is not fulfill the surface and eccentricity factors. Then, using the same automatic criteria, the bad segmented images are processed by means of the watershed transform. Using this new method a 90.96% of the spermatozoa have been correctly segmented. This approach could be useful to commercial Computer Assisted Semen Analysis systems that need new and more accurate segmentation processes.},
note = {Publisher: Indian Society for Development and Environment Research},
keywords = {images, segmentation, segmentation method, semen, threshold, watershed},
pubstate = {published},
tppubtype = {article}
}
Castro, V; Alonso, R; Llamas, F
154. DE PLANTIS LEGIONENSIBUS. NOTULA XXV1 Artículo de revista
En: NOTAS TAXONÓMICAS Y COROLÓGICAS PARA LA FLORA DE LA PENÍNSULA IBÉRICA Y EL MAGREB NOTAS 145-157, vol. 29, pp. 322, 2009.
Resumen | Enlaces | BibTeX | Etiquetas: carológica, flora, magreb, península ibérica, taxonómica
@article{castro_154_2009,
title = {154. DE PLANTIS LEGIONENSIBUS. NOTULA XXV1},
author = {V Castro and R Alonso and F Llamas},
url = {https://institucional.us.es/revistas/lagascalia/29/Lagascalia%2029-8%20Notas.pdf#page=52},
year = {2009},
date = {2009-01-01},
journal = {NOTAS TAXONÓMICAS Y COROLÓGICAS PARA LA FLORA DE LA PENÍNSULA IBÉRICA Y EL MAGREB NOTAS 145-157},
volume = {29},
pages = {322},
abstract = {En el presente trabajo se aportan datos sobre varios taxones que resultan novedades florísticas para la provincia de León, o cuya presencia en la misma es escasa, siendo segundas o terceras citas. Fundamentalmente se trata de plantas cuyo hábitat son charcas, lagunas y humedales del sureste de la provincia de León (Sector Castellano-Duriense, provincia Mediterránea Ibérica Central, subregión Mediterránea Occidental, Región Mediterránea). Varias de ellas tienen gran interés conservacionista, mientras que otras resultan abundantes en la Península Ibérica o son alóctonas. Todos los materiales testigo de estas citas están depositados en el Herbario LEB-Jaime Andrés de la Facultad de Ciencias Biológicas y Ambientales de la Universidad de León. Para cada cita se aportan, si están disponibles, los siguientes datos: localidad, cuadrícula UTM, hábitat, altitud, fecha de recolección, colectores y número de registro en el herbario LEB. La relación de táxones sigue un orden alfabético.},
keywords = {carológica, flora, magreb, península ibérica, taxonómica},
pubstate = {published},
tppubtype = {article}
}
2007
Castejón, M.; Alegre, E.; Barreiro, J.; Hernández, L. K.
On-line tool wear monitoring using geometric descriptors from digital images Artículo de revista
En: International Journal of Machine Tools and Manufacture, vol. 47, no 12, pp. 1847-1853, 2007, ISSN: 0890-6955.
Resumen | Enlaces | BibTeX | Etiquetas: Computer vision, Image classification, Monitoring, Tool wear
@article{CASTEJON20071847,
title = {On-line tool wear monitoring using geometric descriptors from digital images},
author = {M. Castejón and E. Alegre and J. Barreiro and L. K. Hernández},
url = {https://www.sciencedirect.com/science/article/pii/S0890695507000892},
doi = {https://doi.org/10.1016/j.ijmachtools.2007.04.001},
issn = {0890-6955},
year = {2007},
date = {2007-01-01},
journal = {International Journal of Machine Tools and Manufacture},
volume = {47},
number = {12},
pages = {1847-1853},
abstract = {A new method based on a computer vision and statistical learning system is proposed to estimate the wear level in cutting inserts in order to identify the time for its replacement. A CNC parallel lathe and a computer vision system have been used to obtain 1383 flank images. A binary image for each of the former wear flank images have been obtained by applying several pre-processing and segmenting operations. Every wear flank region has been described by means of nine geometrical descriptors. LDA (linear discriminant analysis) shows that three out of the nine descriptors provide the 98.63% of the necessary information to carry out the classification, which are eccentricity, extent and solidity. The result obtained using a finite mixture model approach shows the presence of three clusters using these descriptors, which correspond with low, medium and high wear level. A monitoring approach is performed using the tool wear evolution for each insert along machining and the discriminant analysis. This evolution represents the probability of belonging to each one of the wear classes (low, medium and high). The estimate of the wear level allows to replace the tool when the wear level is located at the end of the M class (medium), preventing that the tool enters into the H class (high).},
keywords = {Computer vision, Image classification, Monitoring, Tool wear},
pubstate = {published},
tppubtype = {article}
}
2004
Guerrero-Curieses, Alicia; Alaiz-Rodríguez, Rocío; Cid-Sueiro, Jesús
A fixed-point algorithm to minimax learning with neural networks Artículo de revista
En: IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews), vol. 34, no 4, pp. 383–392, 2004, (Publisher: IEEE).
Resumen | Enlaces | BibTeX | Etiquetas: loss functions, minimax learning strategy, neural networks, robust classifiers
@article{guerrero-curieses_fixed-point_2004,
title = {A fixed-point algorithm to minimax learning with neural networks},
author = {Alicia Guerrero-Curieses and Rocío Alaiz-Rodríguez and Jesús Cid-Sueiro},
url = {https://ieeexplore.ieee.org/abstract/document/1347290},
year = {2004},
date = {2004-01-01},
journal = {IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews)},
volume = {34},
number = {4},
pages = {383–392},
abstract = {In some real applications, such as medical diagnosis or remote sensing, available training data do not often reflect the true a priori probabilities of the underlying data distribution. The classifier designed from these data may be suboptimal. Building classifiers that are robust against changes in prior probabilities is possible by applying a minimax learning strategy. In this paper, we propose a simple fixed-point algorithm that is able to train a neural minimax classifier [i.e., a classifier minimizing the worst (maximum) possible risk]. Moreover, we present a new parametric family of loss functions that is able to provide the most accurate estimates for the posterior class probabilities near the decision regions, and we also discuss the application of these functions together with a minimax learning strategy. The results of the experiments carried out on different real databases point out the ability of the proposed algorithm to find the minimax solution and produce a robust classifier when the real a priori probabilities differ from the estimated ones.},
note = {Publisher: IEEE},
keywords = {loss functions, minimax learning strategy, neural networks, robust classifiers},
pubstate = {published},
tppubtype = {article}
}