Publications

@article{romero2023,

title = {Tuning 3D-printing parameters to produce vertical ultra-hydrophobic PETG parts with low ice adhesion: A food industry case study},

author = {Pablo E. Romero and Juan M, Barrios and Esther Molero and Andres Bustillo},

url = {https://doi.org/10.1177/09544054231178970},

doi = {10.1177/09544054231178970},

year  = {2023},

date = {2023-06-06},

urldate = {2023-06-06},

journal = {Proc IMechE Part B: J Engineering Manufacture},

pages = {1-9},

abstract = {The food industry is a dynamic component of the European economy. A wide variety of products and small batch are demanded in a market that is accustomed to frequenting changes in food packaging formats. Cheaper and lighter 3D-printed tools are replacing expensive metallic ones, producing previously impossible product geometries and processing fish and meat products more quickly and in more reliable ways. In addition to food contact, these printed parts are often required to have hydrophobic surfaces that facilitate cleaning and have low adhesion both foodstuffs and ice. In this study, the surface wettability of PolyEthylene Terephthalate Glycol (PETG) printed parts via fused filament fabrication is assessed. Specifically, several printing parameters (layer height, extrusion temperature, printing speed, acceleration, and flow) and their influence on the hydrophobicity of 3D printed parts with vertical orientation are analyzed. The experimental results indicated that the parameter with the strongest influence on the wettability of the XZ parts was flow: low-flow values generated ultra-hydrophobic surfaces, with contact angles higher than 120°. Acceleration had no influence at low flow values; however, for high flow values, low acceleration rates yielded higher contact angles. In addition, it was experimentally proven that the 3D-printed PETG parts with high-contact angle surfaces showed lower adhesion to ice than those with low contact-angle surfaces. The technology was applied to a case study of a 3D-printed hopper for the ice duct of an ice-cube machine.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{barbero-aparicio2023,

title = {Deep learning and support vector machines for transcription start site identification},

author = {José A. Barbero-Aparicio and Alicia Olivares-Gil and José F. Díez-Pastor and César García-Osorio},

editor = {Carlos Fernandez-Lozano},

url = {https://doi.org/10.7717/peerj-cs.1340},

doi = {10.7717/peerj-cs.1340},

issn = {2376-5992},

year  = {2023},

date = {2023-04-17},

urldate = {2023-04-17},

journal = {PeerJ Computer Science},

volume = {9},

issue = {e1340},

abstract = {Recognizing transcription start sites is key to gene identification. Several approaches have been employed in related problems such as detecting translation initiation sites or promoters, many of the most recent ones based on machine learning. Deep learning methods have been proven to be exceptionally effective for this task, but their use in transcription start site identification has not yet been explored in depth. Also, the very few existing works do not compare their methods to support vector machines (SVMs), the most established technique in this area of study, nor provide the curated dataset used in the study. The reduced amount of published papers in this specific problem could be explained by this lack of datasets. Given that both support vector machines and deep neural networks have been applied in related problems with remarkable results, we compared their performance in transcription start site predictions, concluding that SVMs are computationally much slower, and deep learning methods, specially long short-term memory neural networks (LSTMs), are best suited to work with sequences than SVMs. For such a purpose, we used the reference human genome GRCh38. Additionally, we studied two different aspects related to data processing: the proper way to generate training examples and the imbalanced nature of the data. Furthermore, the generalization performance of the models studied was also tested using the mouse genome, where the LSTM neural network stood out from the rest of the algorithms. To sum up, this article provides an analysis of the best architecture choices in transcription start site identification, as well as a method to generate transcription start site datasets including negative instances on any species available in Ensembl. We found that deep learning methods are better suited than SVMs to solve this problem, being more efficient and better adapted to long sequences and large amounts of data. We also create a transcription start site (TSS) dataset large enough to be used in deep learning experiments},

keywords = {bioinformatics, Convolutional neural network, Deep learning, Long short-term memory, Machine learning, Support vector machines, transcription start site},

pubstate = {published},

tppubtype = {article}

}

@article{ramirez-sanz2023,

title = {A Low-Cost System Using a Big-Data Deep-Learning Framework for Assessing Physical Telerehabilitation: A Proof-of-Concept },

author = {José Miguel Ramírez-Sanz and José Luis Garrido-Labrador and Alicia Olivares-Gil and Álvaro García-Bustillo and Álvar Arnaiz-González and José-Francisco Díez-Pastor and Maha Jahouh and Josefa González-Santos and Jerónimo J. González-Bernal and Marta Allende-Río and Florita Valiñas-Sieiro and Jose M. Trejo-Gabriel-Galan and Esther Cubo},

editor = {Maria-Esther Vidal and José Alberto Benítez Andrades and Alejandro Rodríguez-González},

url = {https://www.mdpi.com/2227-9032/11/4/507},

doi = {10.3390/healthcare11040507},

issn = {2227-9032 },

year  = {2023},

date = {2023-02-09},

urldate = {2023-02-09},

journal = {Healthcare},

volume = {11},

number = {507},

issue = {4},

abstract = {first_page

settings

Order Article Reprints

Open AccessArticle

A Low-Cost System Using a Big-Data Deep-Learning Framework for Assessing Physical Telerehabilitation: A Proof-of-Concept

by José Miguel Ramírez-Sanz

1 [ORCID] , José Luis Garrido-Labrador

1 [ORCID] , Alicia Olivares-Gil

1 [ORCID] , Álvaro García-Bustillo

2 [ORCID] , Álvar Arnaiz-González

1,* [ORCID] , José-Francisco Díez-Pastor

1, Maha Jahouh

3, Josefa González-Santos

3, Jerónimo J. González-Bernal

3 [ORCID] , Marta Allende-Río

4, Florita Valiñas-Sieiro

4, Jose M. Trejo-Gabriel-Galan

4 and Esther Cubo

4

1

Escuela Politécnica Superior, Departamento de Ingeniería Informática, Universidad de Burgos, Avda. Cantabria s/n, 09006 Burgos, Spain

2

Fundación Burgos por la Investigación de la Salud, 09006 Burgos, Spain

3

Departamento de la Salud, Facultad de Ciencias de la Salud, Universidad de Burgos, Paseo Comendadores s/n, 09001 Burgos, Spain

4

Servicio de Neurología, Hospital Universitario de Burgos, 09006 Burgos, Spain

*

Author to whom correspondence should be addressed.

Healthcare 2023, 11(4), 507; https://doi.org/10.3390/healthcare11040507 (registering DOI)

Received: 19 December 2022 / Revised: 20 January 2023 / Accepted: 7 February 2023 / Published: 9 February 2023

(This article belongs to the Special Issue Analysis of Healthcare Big Data and Health Informatics)

Download Browse Figures

Versions Notes

The consolidation of telerehabilitation for the treatment of many diseases over the last decades is a consequence of its cost-effective results and its ability to offer access to rehabilitation in remote areas. Telerehabilitation operates over a distance, so vulnerable patients are never exposed to unnecessary risks. Despite its low cost, the need for a professional to assess therapeutic exercises and proper corporal movements online should also be mentioned. The focus of this paper is on a telerehabilitation system for patients suffering from Parkinson’s disease in remote villages and other less accessible locations. A full-stack is presented using big data frameworks that facilitate communication between the patient and the occupational therapist, the recording of each session, and real-time skeleton identification using artificial intelligence techniques. Big data technologies are used to process the numerous videos that are generated during the course of treating simultaneous patients. Moreover, the skeleton of each patient can be estimated using deep neural networks for automated evaluation of corporal exercises, which is of immense help to the therapists in charge of the treatment programs.

},

keywords = {artificial intelligence in healthcare, Big data, Parkinson's disease, telemedicine, telerehabilitation},

pubstate = {published},

tppubtype = {article}

}

@article{miguel-alonso2023,

title = {Countering the Novelty Effect: A Tutorial for Immersive Virtual Reality Learning Environments },

author = {Inés Miguel-Alonso and Bruno Rodriguez-Garcia and David Checa and Andrés Bustillo},

editor = {MDPI},

url = {https://www.mdpi.com/2076-3417/13/1/593  

https://www.mdpi.com/journal/applsci/special_issues/HK43Y20XK5},

doi = {10.3390/app13010593  },

issn = {2076-3417 },

year  = {2023},

date = {2023-01-02},

urldate = {2023-01-02},

journal = {Applied Sciences},

volume = {13},

number = {593},

issue = {1},

abstract = {Immersive Virtual Reality (iVR) is a new technology, the novelty effect of which can reduce the enjoyment of iVR experiences and, especially, learning achievements when presented in the classroom; an effect that the interactive tutorial proposed in this research can help overcome. Its increasingly complex levels are designed on the basis of Mayer’s Cognitive Theory of Multimedia Learning, so that users can quickly gain familiarity with the iVR environment. The tutorial was included in an iVR learning experience for its validation with 65 users. It was a success, according to the user satisfaction and tutorial usability survey. First, it gained very high ratings for satisfaction, engagement, and immersion. Second, high skill rates suggested that it helped users to gain familiarity with controllers. Finally, a medium-high value for flow pointed to major concerns related to skill and challenges with this sort of iVR experience. A few cases of cybersickness also arose. The survey showed that only intense cybersickness levels significantly limited performance and enjoyment; low levels had no influence on flow and immersion and little influence on skill, presence, and engagement, greatly reducing the benefits of the tutorial, despite which it remained useful. },

keywords = {cybersickness, education, novelty effect, tutorial, Virtual Reality},

pubstate = {published},

tppubtype = {article}

}

@article{Barbero-Aparicio2022,

title = {Nonlinear physics opens a new paradigm for accurate transcription start site prediction},

author = { José Antonio Barbero-Aparicio and Santiago Cuesta-Lopez and César Ignacio García-Osorio and Javier Pérez-Rodríguez and Nicolás García-Pedrajas },

editor = {José Manuel Benítez},

url = {https://doi.org/10.1186/s12859-022-05129-4},

doi = {10.1186/s12859-022-05129-4},

issn = {1471-2105},

year  = {2022},

date = {2022-12-30},

urldate = {2022-12-30},

journal = {BMC Bioinformatics},

volume = {23},

number = {565},

abstract = {There is evidence that DNA breathing (spontaneous opening of the DNA strands) plays a relevant role in the interactions of DNA with other molecules, and in particular in the transcription process. Therefore, having physical models that can predict these openings is of interest. However, this source of information has not been used before either in transcription start sites (TSSs) or promoter prediction. In this article, one such model is used as an additional information source that, when used by a machine learning (ML) model, improves the results of current methods for the prediction of TSSs. In addition, we provide evidence on the validity of the physical model, as it is able by itself to predict TSSs with high accuracy. This opens an exciting avenue of research at the intersection of statistical mechanics and ML, where ML models in bioinformatics can be improved using physical models of DNA as feature extractors.},

keywords = {DNA breathing, DNA modelling, Machine learning, String kernels, SVM, TSS prediction},

pubstate = {published},

tppubtype = {article}

}

@article{kim2022,

title = {A New Measure for Serious Games Evaluation: Gaming Educational Balanced (GEB) Model},

author = {Kim Martinez and María Isabel Menéndez-Menéndez and Andres Bustillo

},

editor = {Maya Satratzemi and Stelios Xinogalos},

doi = {10.3390/app122211757},

issn = {2076-3417},

year  = {2022},

date = {2022-11-19},

urldate = {2022-11-19},

journal = {Applied Sciences},

volume = {12},

number = {11757},

issue = {22},

abstract = {Serious games have to meet certain characteristics relating to gameplay and educational content to be effective as educational tools. There are some models that evaluate these aspects, but they usually lack a good balance between both ludic and learning requirements, and provide no guide for the design of new games. This study develops the Gaming Educational Balanced (GEB) Model which addresses these two limitations. GEB is based on the Mechanics, Dynamics and Aesthetics framework and the Four Pillars of Educational Games theory. This model defines a metric to evaluate serious games, which can also be followed to guide their subsequent development. This rubric is tested with three indie serious games developed using different genres to raise awareness of mental illnesses. This evaluation revealed two main issues: the three games returned good results for gameplay, but the application of educational content was deficient, due in all likelihood to the lack of expert educators participating in their development. A statistical and machine learning validation of the results is also performed to ensure that the GEB metric features are clearly explained and the players are able to evaluate them correctly. These results underline the usefulness of the new metric tool for identifying game design strengths and weaknesses. Future works will apply this metric to more serious games to further test its effectiveness and to guide the design of new serious games.},

keywords = {game design, game evaluation, metrics, serious games},

pubstate = {published},

tppubtype = {article}

}

@article{Pimenov2022,

title = {Artificial intelligence systems for tool condition monitoring in machining: analysis and critical review},

author = {Danil Yurievich Pimenov and Andrés Bustillo and Szymon Wojciechowski and Vishal Santosh Sharma and Munish Kumar Gupta and Mustafa Kuntğlu},

url = {https://link.springer.com/article/10.1007/s10845-022-01923-2#citeas},

doi = {10.1007/s10845-022-01923-2},

issn = {0956-5515},

year  = {2022},

date = {2022-03-12},

journal = {Journal of Intelligent Manufacturing},

volume = {2022},

abstract = {The wear of cutting tools, cutting force determination, surface roughness variations and other machining responses are of keen interest to latest researchers. The variations of these machining responses results in change in dimensional accuracy and productivity upto great extent. In addition, an excessive increase in wear leads to catastrophic consequences, exceeding the tool breakage. Therefore, this article discusses the online trend of modern approaches in tool condition monitoring while different machining operations. For this purpose, the effective use of new sensors and artificial intelligence (AI) is considered and followed during this holistic review work. The sensor systems used for monitoring tool wear are dynamometers, accelerometers, acoustic emission sensors, current and power sensors, image sensors, other sensors. These systems allow to solve the problem of automation and modeling of technological parameters of the main types of cutting, such as turning, milling, drilling and grinding. The modern artificial intelligence methods are considered, such as: Neural networks, Image recognition, Fuzzy logic, Adaptive neuro-fuzzy inference systems, Bayesian Networks, Support vector machine, Ensembles, Decision and regression trees, k-nearest neighbors, Artificial Neural Network, Markov model, Singular Spectrum Analysis, Genetic algorithms. Discussions also includes the main advantages, disadvantages and prospects of using various AI methods for tool wear monitoring. Moreover, the problems and future directions of the main processing methods using AI models are also highlighted.},

keywords = {Artificial intelligence, Machining, Sensor, tool condition monitoring, Tool life, Wear},

pubstate = {published},

tppubtype = {article}

}

@article{Ramos-Pérez2022,

title = {When is resampling beneficial for feature selection with imbalanced wide data?},

author = {Ismael Ramos-Pérez and Álvar Arnaiz-González and Juan José Rodríguez and César García-Osorio},

url = {https://www.sciencedirect.com/science/article/pii/S0957417421013622},

doi = {https://doi.org/10.1016/j.eswa.2021.116015},

issn = {0957-4174},

year  = {2022},

date = {2022-02-01},

journal = {Expert Systems with Applications},

volume = {188},

pages = {116015},

abstract = {This paper studies the effects that combinations of balancing and feature selection techniques have on wide data (many more attributes than instances) when different classifiers are used. For this, an extensive study is done using 14 datasets, 3 balancing strategies, and 7 feature selection algorithms. The evaluation is carried out using 5 classification algorithms, analyzing the results for different percentages of selected features, and establishing the statistical significance using Bayesian tests.



Some general conclusions of the study are that it is better to use RUS before the feature selection, while ROS and SMOTE offer better results when applied afterwards. Additionally, specific results are also obtained depending on the classifier used, for example, for Gaussian SVM the best performance is obtained when the feature selection is done with SVM-RFE before balancing the data with RUS.},

keywords = {Feature selection, High dimensional data, Machine learning, Unbalanced, Very low sample size, Wide data},

pubstate = {published},

tppubtype = {article}

}

@article{Cruz2022b,

title = {Using Machine-Learning techniques and Virtual Reality to design cutting tools for energy optimization in milling operations},

author = {David Checa Cruz and Gorka Urbikain and Aitor Beranoagirre and Andrés Bustillo and Luis Norberto López de Lacalle},

url = {https://www.tandfonline.com/doi/full/10.1080/0951192X.2022.2027020},

doi = {10.1080/0951192X.2022.2027020},

issn = {0951-192X},

year  = {2022},

date = {2022-01-19},

journal = {International Journal of Computer Integrated Manufacturing},

volume = {35},

number = {1},

pages = {1-21},

abstract = {The selection of a proper cutting tool in machining operations is a critical issue. Tool geometric parameters are essential for milling performance. However, the process engineer has very limited experience of the best parameter combination, due to the high cost of cutting tool tests. The same holds true for bachelor studies on machining processes. This study proposes a new strategy that combines experimental tests, machine-learning modelling and Virtual Reality visualization to overcome these limitations. First, tools with different geometric parameters are tested. Second, the experimental data are modeled with different machine-learning techniques (regression trees, multilayer perceptrons, bagging and random forest ensembles). An in-depth analysis of the influence of each input on model accuracy is performed to reduce experimental costs. The results show that the best model with no cutting-force inputs performed worse than the best model with all the inputs. Third, the most accurate model is used to build 3D graphs of special interest to engineering students as well as process engineers, for the optimization of power consumption under different cutting conditions. Finally, a Virtual Reality environment is presented to train engineering students in the study of the best tool design and cutting parameter optimization.},

keywords = {energy optimization, Ensembles, Multilayer perceptron, serrated cutters, Virtual Reality},

pubstate = {published},

tppubtype = {article}

}

@article{Cruz2022,

title = {Virtual Reality Training Application for the Condition-Based Maintenance of Induction Motors},

author = {David Checa Cruz and Juan José Saucedo-Dorantes and Roque Alfredo Osorno Ríos and José Alfonso Antonio-Daviu and Andrés Bustillo},

url = {https://www.mdpi.com/2076-3417/12/1/414},

doi = {10.3390/app12010414},

issn = {2076-3417},

year  = {2022},

date = {2022-01-01},

journal = {Applied Sciences},

volume = {12},

number = {1},

pages = {414},

abstract = {The incorporation of new technologies as training methods, such as virtual reality (VR), facilitates instruction when compared to traditional approaches, which have shown strong limitations in their ability to engage young students who have grown up in the smartphone culture of continuous entertainment. Moreover, not all educational centers or organizations are able to incorporate specialized labs or equipment for training and instruction. Using VR applications, it is possible to reproduce training programs with a high rate of similarity to real programs, filling the gap in traditional training. In addition, it reduces unnecessary investment and prevents economic losses, avoiding unnecessary damage to laboratory equipment. The contribution of this work focuses on the development of a VR-based teaching and training application for the condition-based maintenance of induction motors. The novelty of this research relies mainly on the use of natural interactions with the VR environment and the design’s optimization of the VR application in terms of the proposed teaching topics. The application is comprised of two training modules. The first module is focused on the main components of induction motors, the assembly of workbenches and familiarization with induction motor components. The second module employs motor current signature analysis (MCSA) to detect induction motor failures, such as broken rotor bars, misalignments, unbalances, and gradual wear on gear case teeth. Finally, the usability of this VR tool has been validated with both graduate and undergraduate students, assuring the suitability of this tool for: (1) learning basic knowledge and (2) training in practical skills related to the condition-based maintenance of induction motors.},

keywords = {eye tracking, fault detection, FFT, induction motors, Virtual Reality},

pubstate = {published},

tppubtype = {article}

}

@article{Cruz2021b,

title = {Immersive virtual-reality computer-assembly serious game to enhance autonomous learning},

author = {David Checa Cruz and Inés Miguel Alonso and Andrés Bustillo},

url = {https://link.springer.com/article/10.1007%2Fs10055-021-00607-1},

doi = {10.1007/s10055-021-00607-1},

issn = {1434-9957},

year  = {2021},

date = {2021-12-23},

journal = {Virtual Reality},

abstract = {Immersive virtual reality (VR) environments create a very strong sense of presence and immersion. Nowadays, especially when student isolation and online autonomous learning is required, such sensations can provide higher satisfaction and learning rates than conventional teaching. However, up until the present, learning outcomes with VR tools have yet to prove their advantageous aspects over conventional teaching. The project presents a VR serious game for teaching concepts associated with computer hardware assembly. These concepts are often included in any undergraduate’s introduction to Computer Science. The learning outcomes are evaluated using a pre-test of previous knowledge, a satisfaction/usability test, and a post-test on knowledge acquisition, structured with questions on different knowledge areas. The results of the VR serious game are compared with another two learning methodologies adapted to online learning: (1) an online conventional lecture; and (2) playing the same serious game on a desktop PC. An extensive sample of students (n = 77) was formed for this purpose. The results showed the strong potential of VR serious games to improve student well-being during spells of confinement, due to higher learning satisfaction. Besides, ease of usability and the use of in-game tutorials are directly related with game-user satisfaction and performance. The main novelty of this research is related to academic performance. Although a very limited effect was noted for learning theoretical knowledge with the VR application in comparison with the other methodologies, this effect was significantly improved through visual knowledge, understanding and making connections between different concepts. It can therefore be concluded that the proposed VR serious game has the potential to increase student learning and therefore student satisfaction, by imparting a deeper understanding of the subject matter to students.},

keywords = {active learning, computer science, e-learning, educational game, game engine, head mounted display, Virtual Reality},

pubstate = {published},

tppubtype = {article}

}

@article{Martínez2021,

title = {A systematic review of serious games for children and adolescents: awareness, prevention, detection and therapy for depression and anxiety},

author = {Kim Martínez and María Isabel Menéndez Menéndez and Andrés Bustillo},

url = {https://games.jmir.org/2021/4/e30482},

doi = {10.2196/30482},

issn = {2291-9279},

year  = {2021},

date = {2021-12-16},

journal = {JMIR Serious Games},

volume = {9},

number = {4 (2021)},

abstract = {Background:

Depression and anxiety in children and adolescents are major health problems worldwide. In recent years, serious games research has advanced in the development of tools to address these mental health conditions. However, there has not been an extensive analysis of these games, their tendencies, and capacities.



Objective:

This review aims to gather the most current serious games, published from 2015 to 2020, with a new approach focusing on their applications: awareness, prevention, detection, and therapy. The purpose is also to analyze the implementation, development, and evaluation of these tools to obtain trends, strengths, and weaknesses for future research lines.



Methods:

The identification of the serious games through a literature search was conducted on the databases PubMed, Scopus, Wiley, Taylor and Francis, Springer, PsycINFO, PsycArticles, Web of Science, and Science Direct. The identified records were screened to include only the manuscripts meeting these criteria: a serious game for PC, smartphone, or virtual reality; developed by research teams; targeting only depression or anxiety or both; aiming specifically at children or adolescents.



Results:

A total of 34 studies have been found that developed serious games for PC, smartphone, and virtual reality devices and tested them in children and adolescents. Most of the games address both conditions and are applied in prevention and therapy. Nevertheless, there is a trend that anxiety is targeted more in childhood and depression targeted more in adolescence. Regarding design, the game genres arcade minigames, adventure worlds, and social simulations are used, in this order. For implementation, these serious games usually require sessions of 1 hour and are most often played using a PC. Moreover, the common evaluation tools are normalized questionnaires that measure acquisition of skills or reduction of symptoms. Most studies collect and compare these data before and after the participants play.



Conclusions:

The results show that more awareness and detection games are needed, as well as games that mix the awareness, prevention, detection, and therapy applications. In addition, games for depression and anxiety should equally target all age ranges. For future research, the development and evaluation of serious games should be standardized, so the implementation of serious games as tools would advance. The games should always offer support while playing, in addition to collecting data on participant behavior during the game to better analyze their learning. Furthermore, there is an open line regarding the use of virtual reality for these games due to the capabilities offered by this technology.},

keywords = {adolescents, anxiety, awareness, children, depression, detection, mental health, prevention, serious games, therapy, Virtual Reality},

pubstate = {published},

tppubtype = {article}

}

@article{Juez-Gil2021bb,

title = {Approx-SMOTE: Fast SMOTE for Big Data on Apache Spark},

author = {Mario Juez-Gil and Álvar Arnaiz-González and Juan José Rodríguez and Carlos López-Nozal and César García-Osorio},

url = {https://www.sciencedirect.com/science/article/pii/S0925231221012832},

doi = {https://doi.org/10.1016/j.neucom.2021.08.086},

issn = {0925-2312},

year  = {2021},

date = {2021-11-13},

journal = {Neurocomputing},

volume = {464},

pages = {432-437},

abstract = {One of the main goals of Big Data research, is to find new data mining methods that are able to process large amounts of data in acceptable times. In Big Data classification, as in traditional classification, class imbalance is a common problem that must be addressed, in the case of Big Data also looking for a solution that can be applied in an acceptable execution time. In this paper we present Approx-SMOTE, a parallel implementation of the SMOTE algorithm for the Apache Spark framework. The key difference with the original SMOTE, besides parallelism, is that it uses an approximated version of k-Nearest Neighbor which makes it highly scalable. Although an implementation of SMOTE for Big Data already exists (SMOTE-BD), it uses an exact Nearest Neighbor search, which does not make it entirely scalable. Approx-SMOTE on the other hand is able to achieve up to 30 times faster run times without sacrificing the improved classification performance offered by the original SMOTE.},

keywords = {Big data, Data Mining, imbalance, SMOTE, Spark},

pubstate = {published},

tppubtype = {article}

}

@article{Cruz2021,

title = {Virtual Reality opportunities in the reduction of occupational hazards in industry 4.0},

author = {David Checa Cruz and Kim Martínez and Roque Alfredo Osorno Ríos and Andrés Bustillo},

url = {https://www.revistadyna.com/search/virtual-reality-opportunities-in-the-reduction-of-occupational-hazards-in-industry-40},

doi = {https://doi.org/10.6036/10241},

issn = {0012-7361},

year  = {2021},

date = {2021-11-01},

journal = {DYNA},

volume = {96},

number = {6},

pages = {620-626},

abstract = {This work discuss the possibilities of Immersive Virtual Reality (iVR) environments in occupational risk prevention in the manufacturing industry. Firstly, a framework for iVR experiences design is presented. Secondly, two examples to demonstrate the usefulness of this scheme for the detection of occupational hazards are discussed. In the first one, the worker controls an overhead crane in a realistic iVR environment. Realism is searched to intensify user´s presence in the iVR and, therefore, learning effectiveness. Visual quality is maximized and natural movements and load´s inertias are programmed with this objective. The user performs different critical operations in this application. The tasks becomes more complex while the user gets used to the iVR serious game: noise level, bad lighting, presence of other workers in the working area and, especially, load unbalance. Under these conditions, the user must carry out different common tasks while avoiding accidents. In the second one, the worker moves through a factory and identifies different risk situations, taking the corresponding corrective measures. While in the first application, the user interacts with the virtual environment using a real overhead crane keypad to increase his immersion, in the second one a standard iVR interface is used, because it simulates in a natural way the interaction with virtual objects. In both cases, a data acquisition system, including positioning and eyetracking, allows the trainer to directly provide feedback to the user on his performance.

Keywords: Virtual Reality; Occupational Risk Prevention; Industry 4.0; Overhead crane; Educational Games},

keywords = {Educational Games, Industria 4.0, Industry 4.0, Juegos educativos, Occupational Risk Prevention, Overhead crane, Prevención de Riesgos Laborales, Puente grúa, Realidad Virtual, Virtual Reality},

pubstate = {published},

tppubtype = {article}

}

@article{Juez-Gil2021,

title = {Rotation Forest for Big Data},

author = {Mario Juez-Gil and Álvar Arnaiz-González and Juan José Rodríguez and Carlos López-Nozal and César García-Osorio},

url = {https://www.sciencedirect.com/science/article/pii/S1566253521000634},

doi = {10.1016/j.inffus.2021.03.007},

issn = {1566-2535},

year  = {2021},

date = {2021-10-01},

journal = {Information Fusion},

volume = {74},

pages = {39-49},

abstract = {The Rotation Forest classifier is a successful ensemble method for a wide variety of data mining applications. However, the way in which Rotation Forest transforms the feature space through PCA, although powerful, penalizes training and prediction times, making it unfeasible for Big Data. In this paper, a MapReduce Rotation Forest and its implementation under the Spark framework are presented. The proposed MapReduce Rotation Forest behaves in the same way as the standard Rotation Forest, training the base classifiers on a rotated space, but using a functional implementation of the rotation that enables its execution in Big Data frameworks. Experimental results are obtained using different cloud-based cluster configurations. Bayesian tests are used to validate the method against two ensembles for Big Data: Random Forest and PCARDE classifiers. Our proposal incorporates the parallelization of both the PCA calculation and the tree training, providing a scalable solution that retains the performance of the original Rotation Forest and achieves a competitive execution time (in average, at training, more than 3 times faster than other PCA-based alternatives). In addition, extensive experimentation shows that by setting some parameters of the classifier (i.e., bootstrap sample size, number of trees, and number of rotations), the execution time is reduced with no significant loss of performance using a small ensemble.},

keywords = {Big data, Ensemble learning, Machine learning, Random forest, Rotation forest, Spark},

pubstate = {published},

tppubtype = {article}

}

@article{Juez-Gil2021b,

title = {Experimental evaluation of ensemble classifiers for imbalance in Big Data},

author = {Mario Juez-Gil and Álvar Arnaiz-González and Juan José Rodríguez and César García-Osorio},

url = {https://www.sciencedirect.com/science/article/pii/S1568494621003707?via%3Dihub},

doi = {10.1016/j.asoc.2021.107447},

issn = {1568-4946},

year  = {2021},

date = {2021-09-01},

journal = {Applied Soft Computing},

volume = {108},

number = {107447},

abstract = {Datasets are growing in size and complexity at a pace never seen before, forming ever larger datasets known as Big Data. A common problem for classification, especially in Big Data, is that the numerous examples of the different classes might not be balanced. Some decades ago, imbalanced classification was therefore introduced, to correct the tendency of classifiers that show bias in favor of the majority class and that ignore the minority one. To date, although the number of imbalanced classification methods have increased, they continue to focus on normal-sized datasets and not on the new reality of Big Data. In this paper, in-depth experimentation with ensemble classifiers is conducted in the context of imbalanced Big Data classification, using two popular ensemble families (Bagging and Boosting) and different resampling methods. All the experimentation was launched in Spark clusters, comparing ensemble performance and execution times with statistical test results, including the newest ones based on the Bayesian approach. One very interesting conclusion from the study was that simpler methods applied to unbalanced datasets in the context of Big Data provided better results than complex methods. The additional complexity of some of the sophisticated methods, which appear necessary to process and to reduce imbalance in normal-sized datasets were not effective for imbalanced Big Data.},

keywords = {Big data, ensemble, imbalance, resampling, Spark, unbalance},

pubstate = {published},

tppubtype = {article}

}

@article{Cerro2021,

title = {Use of machine learning algorithms for surface roughness prediction of printed parts in polyvinyl butyral via fused deposition modeling},

author = {Azahara Cerro and Pablo E. Romero and Okan Yiğit and Andrés Bustillo},

url = {https://link.springer.com/article/10.1007/s00170-021-07300-2},

doi = {https://doi.org/10.1007/s00170-021-07300-2},

issn = {0268-3768},

year  = {2021},

date = {2021-05-25},

journal = {The International Journal of Advanced Manufacturing Technology},

abstract = {Machine learning algorithms for classification are employed in this study to generate different models that can predict the surface roughness of parts manufactured from polyvinyl butyral by means of Fused Deposition Modeling (FDM). Five input variables are defined (layer height, print speed, number of perimeters, wall angle, and extruder temperature), and 16 parts are 3D printed, each with three different surfaces (48 surfaces in total). The print values used to print each part were defined by a fractionated orthogonal experimental design. Using a perthometer, the average value of surface roughness, Ra, on each surface was obtained. From these experimental values, 40 models were trained and validated. The model with the best prediction results was the one generated by bagging and Multilayer Perceptron (BMLP), with a Kappa statistic of 0.9143. The input variables with the highest influence on the surface finish are the wall angle and the layer height.},

keywords = {3d printing, Fused deposition modeling Fused filament fabrication, Machine learning, surface roughness, WEKA},

pubstate = {published},

tppubtype = {article}

}

@article{Rodríguez2021,

title = {Rotation Forest for multi-target regression},

author = {Juan José Rodríguez and Mario Juez-Gil and Carlos López-Nozal and Álvar Arnaiz-González},

url = {https://link.springer.com/article/10.1007/s13042-021-01329-1},

doi = {https://doi.org/10.1007/s13042-021-01329-1},

issn = {1868-808X},

year  = {2021},

date = {2021-04-22},

journal = {International Journal of Machine Learning and Cybernetics},

abstract = {The prediction of multiple numeric outputs at the same time is called multi-target regression (MTR), and it has gained attention during the last decades. This task is a challenging research topic in supervised learning because it poses additional difficulties to traditional single-target regression (STR), and many real-world problems involve the prediction of multiple targets at once. One of the most successful approaches to deal with MTR, although not the only one, consists in transforming the problem in several STR problems, whose outputs will be combined building up the MTR output. In this paper, the Rotation Forest ensemble method, previously proposed for single-label classification and single-target regression, is adapted to MTR tasks and tested with several regressors and data sets. Our proposal rotates the input space in an efficient and novel fashion, avoiding extra rotations forced by MTR problem decomposition. Four approaches for MTR are used: single-target (ST), stacked-single target (SST), Ensembles of Regressor Chains (ERC), and Multi-target Regression via Quantization (MRQ). For assessing the benefits of the proposal, a thorough experimentation with 28 MTR data sets and statistical tests are used, concluding that Rotation Forest, adapted by means of these approaches, outperforms other popular ensembles, such as Bagging and Random Forest.},

keywords = {ensemble, multi-target regression, Rotation forest},

pubstate = {published},

tppubtype = {article}

}

@article{Díez-Pastor2021,

title = {High-accuracy classification of thread quality in tapping processes with ensembles of classifiers for imbalanced learning},

author = {José Francisco Díez-Pastor and Alain Gil del Val and Fernando Veiga and Andrés Bustillo},

url = {https://www.sciencedirect.com/science/article/pii/S0263224120308654},

doi = {https://doi.org/10.1016/j.measurement.2020.108328},

issn = {0263-2241},

year  = {2021},

date = {2021-01-15},

journal = {Measurement},

volume = {168},

number = {108328},

abstract = {Industrial threading processes that use cutting taps are in high demand. However, industrial conditions differ markedly from laboratory conditions. In this study, a machine-learning solution is presented for the correct classification of threads, based on industrial requirements, to avoid expensive manual measurement of quality indicators. First, quality states are categorized. Second, process inputs are extracted from the torque signals including statistical parameters. Third, different machine-learning algorithms are tested: from base classifiers, such as decision trees and multilayer perceptrons, to complex ensembles of classifiers especially designed for imbalanced datasets, such as boosting and bagging decision-tree ensembles combined with SMOTE and under-sampling balancing techniques. Ensembles demonstrated the lowest sensitivity to window sizes, the highest accuracy for smaller window sizes, and the greatest learning ability with small datasets. Fourth, the combination of models with both high Recall and high Precision resulted in a reliable industrial tool, tested on an extensive experimental dataset.},

keywords = {Bagging, Cutting taps, Imbalanced datasets, Quality assessment, Threading},

pubstate = {published},

tppubtype = {article}

}

@article{Díez-Pastor2020,

title = {“You Are Not My Type”: An Evaluation of Classification Methods for Automatic Phytolith Identification},

author = {José Francisco Díez-Pastor and Pedro Latorre-Carmona and Álvar Arnaiz-González and Javier Ruiz-Pérez and Débora Zurro},

url = {https://www.cambridge.org/core/journals/microscopy-and-microanalysis/article/you-are-not-my-type-an-evaluation-of-classification-methods-for-automatic-phytolith-identification/48F88E9407086B797BBE383B8BC15904},

doi = {https://doi.org/10.1017/S1431927620024629},

issn = {1431-9276},

year  = {2020},

date = {2020-11-10},

journal = {Microscopy and Microanalysis},

volume = {26},

pages = { 1158-1167},

abstract = {Phytoliths can be an important source of information related to environmental and climatic change, as well as to ancient plant use by humans, particularly within the disciplines of paleoecology and archaeology. Currently, phytolith identification and categorization is performed manually by researchers, a time-consuming task liable to misclassifications. The automated classification of phytoliths would allow the standardization of identification processes, avoiding possible biases related to the classification capability of researchers. This paper presents a comparative analysis of six classification methods, using digitized microscopic images to examine the efficacy of different quantitative approaches for characterizing phytoliths. A comprehensive experiment performed on images of 429 phytoliths demonstrated that the automatic phytolith classification is a promising area of research that will help researchers to invest time more efficiently and improve their recognition accuracy rate.},

keywords = {Feature extraction, Machine learning, Microfossils, Morphometry, Proxy},

pubstate = {published},

tppubtype = {article}

}

@article{Juez-Gil2020,

title = {Early and extremely early multi-label fault diagnosis in induction motors},

author = {Mario Juez-Gil and Juan José Saucedo-Dorantes and Álvar Arnaiz-González and Carlos López-Nozal and César García-Osorio and David Lowe},

url = {https://www.sciencedirect.com/science/article/pii/S0019057820302755},

doi = {https://doi.org/10.1016/j.isatra.2020.07.002},

issn = {0019-0578},

year  = {2020},

date = {2020-11-01},

journal = {ISA Transactions},

volume = {106},

pages = {367-381},

abstract = {The detection of faulty machinery and its automated diagnosis is an industrial priority because efficient fault diagnosis implies efficient management of the maintenance times, reduction of energy consumption, reduction in overall costs and, most importantly, the availability of the machinery is ensured. Thus, this paper presents a new intelligent multi-fault diagnosis method based on multiple sensor information for assessing the occurrence of single, combined, and simultaneous faulty conditions in an induction motor. The contribution and novelty of the proposed method include the consideration of different physical magnitudes such as vibrations, stator currents, voltages, and rotational speed as a meaningful source of information of the machine condition. Moreover, for each available physical magnitude, the reduction of the original number of attributes through the Principal Component Analysis leads to retain a reduced number of significant features that allows achieving the final diagnosis outcome by a multi-label classification tree. The effectiveness of the method was validated by using a complete set of experimental data acquired from a laboratory electromechanical system, where a healthy and seven faulty scenarios were assessed. Also, the interpretation of the results do not require any prior expert knowledge and the robustness of this proposal allows its application in industrial applications, since it may deal with different operating conditions such as different loads and operating frequencies. Finally, the performance was evaluated using multi-label measures, which to the best of our knowledge, is an innovative development in the field condition monitoring and fault identification.},

keywords = {Early detection, Load insensitive model, Multi-fault detection, Multi-label classification, Prediction at low operating frequencies, Principal component analysis},

pubstate = {published},

tppubtype = {article}

}

@article{Bustillo2020,

title = {Improving the accuracy of machine-learning models with data from machine test repetitions},

author = {Andrés Bustillo and Roberto Reis and Alisson R. Machado and Danil Yurievich Pimenov},

url = {https://link.springer.com/article/10.1007%2Fs10845-020-01661-3},

doi = {https://doi.org/10.1007/s10845-020-01661-3},

issn = {0956-5515},

year  = {2020},

date = {2020-09-17},

journal = {Journal of Intelligent Manufacturing},

abstract = {The modelling of machining processes by means of machine-learning algorithms is still based on principles that are especially adapted to mechanical approaches, in which very few inputs are varied with little repetition of experimental conditions. These principles might not be ideal to achieve accurate machine-learning models and they are certainly not aligned with the practicalities of industrial machining in factories. In this research the effect of a new strategy to improve machine-learning model accuracy is studied: experimental repetition. Tool-life prediction in the face-turning operations of AISI 1045 steel discs, depending on different cooling systems and tool geometries, is selected as a case study. Both the side rake and the relief angles of HSS tools are optimized using the Brandsma facing test under dry, MQL, and flooding conditions. Different machine-learning algorithms, such as regression trees, kNNs, artificial neural networks, and ensembles (bagging and Random Forest) are tested. On the one hand, the results of the study showed that artificial neural networks of Radial Basis Functions presented the highest model accuracy (11.4 mm RMSE), but required a very sensitive and complex tuning process. On the other hand, they demonstrated that ensembles, especially Random Forest, provided models with accuracy in the same range, but with no tuning procedure (12.8 mm RMSE). Secondly, the effect of an increased dataset size, by means of experimental repetition, is evaluated and compared with traditional experimental modelling that used average values. The results showed that some machine-learning techniques, including both ensemble types, significantly improved their accuracy with this strategy, by up to 23%. The results therefore suggested that the use of raw experimental data, rather than their averaged values, can achieve machine-learning models of higher accuracy for tool-wear processes.},

keywords = {Artificial intelligence, Brandsma facing tests, Ensembles, Machine learning, Tool geometry, Turning},

pubstate = {published},

tppubtype = {article}

}

@article{Bustillo2020b,

title = {Machine-learning for automatic prediction of flatness deviation considering the wear of the face mill teeth},

author = {Andrés Bustillo and Danil Yurievich Pimenov and Mozammel Mia and Wojciech Kapłonek},

url = {https://link.springer.com/article/10.1007/s10845-020-01645-3},

doi = {https://doi.org/10.1007/s10845-020-01645-3},

issn = {0956-5515},

year  = {2020},

date = {2020-09-03},

journal = {Journal of Intelligent Manufacturing},

abstract = {The acceptance of the machined surfaces not only depends on roughness parameters but also in the flatness deviation (Δfl). Hence, before reaching the threshold of flatness deviation caused by the wear of the face mill, the tool inserts need to be changed to avoid the expected product rejection. As current CNC machines have the facility to track, in real-time, the main drive power, the present study utilizes this facility to predict the flatness deviation—with proper consideration to the amount of wear of cutting tool insert’s edge. The prediction of deviation from flatness is evaluated as a regression and a classification problem, while different machine-learning techniques like Multilayer Perceptrons, Radial Basis Functions Networks, Decision Trees and Random Forest ensembles have been examined. Finally, Random Forest ensembles combined with Synthetic Minority Over-sampling Technique (SMOTE) balancing technique showed the highest performance when the flatness levels are discretized taking into account industrial requirements. The SMOTE balancing technique resulted in a very useful strategy to avoid the strong limitations that small experiment datasets produce in the accuracy of machine-learning models.},

keywords = {Cutting power, Face milling, Flatness deviation, Random forest, SMOTE, tool condition monitoring, Tool life, Wear},

pubstate = {published},

tppubtype = {article}

}

@article{Rodríguez2020,

title = {An experimental evaluation of mixup regression forests},

author = {Juan José Rodríguez and Mario Juez-Gil and Álvar Arnaiz-González and Ludmila I Kuncheva},

url = {https://www.sciencedirect.com/science/article/abs/pii/S0957417420302013?via%3Dihub},

doi = {10.1016/j.eswa.2020.113376},

issn = {0957-4174},

year  = {2020},

date = {2020-08-01},

journal = {Expert Systems with Applications},

volume = {151},

number = {113376},

abstract = {Over the past few decades, the remarkable prediction capabilities of ensemble methods have been used within a wide range of applications. Maximization of base-model ensemble accuracy and diversity are the keys to the heightened performance of these methods. One way to achieve diversity for training the base models is to generate artificial/synthetic instances for their incorporation with the original instances. Recently, the mixup method was proposed for improving the classification power of deep neural networks (Zhang, Cissé, Dauphin, and Lopez-Paz, 2017). Mixup method generates artificial instances by combining pairs of instances and their labels, these new instances are used for training the neural networks promoting its regularization. In this paper, new regression tree ensembles trained with mixup, which we will refer to as Mixup Regression Forest, are presented and tested. The experimental study with 61 datasets showed that the mixup approach improved the results of both Random Forest and Rotation Forest.},

keywords = {Mixup, Random forest, Regression, Rotation forest},

pubstate = {published},

tppubtype = {article}

}

@article{Garrido-Labrador2020,

title = {Using Ensembles for Accurate Modelling of Manufacturing Processes in an IoT Data-Acquisition Solution},

author = {José Luis Garrido-Labrador and Daniel Puente-Gabarri and José Miguel Ramirez-Sanz and David Ayala-Dulanto and Jesús Maudes},

url = {https://www.mdpi.com/2076-3417/10/13/4606/htm},

doi = {https://doi.org/10.3390/app10134606},

issn = {2076-3417},

year  = {2020},

date = {2020-07-02},

journal = {Applied Sciences},

volume = {10},

number = {13},

abstract = {The development of complex real-time platforms for the Internet of Things (IoT) opens up a promising future for the diagnosis and the optimization of machining processes. Many issues have still to be solved before IoT platforms can be profitable for small workshops with very flexible workloads and workflows. The main obstacles refer to sensor implementation, IoT architecture, and data processing, and analysis. In this research, the use of different machine-learning techniques is proposed, for the extraction of different information from an IoT platform connected to a machining center, working under real industrial conditions in a workshop. The aim is to evaluate which algorithmic technique might be the best to build accurate prediction models for one of the main demands of workshops: the optimization of machining processes. This evaluation, completed under real industrial conditions, includes very limited information on the machining workload of the machining center and unbalanced datasets. The strategy is validated for the classification of the state of a machining center, its working mode, and the prediction of the thermal evolution of the main machine-tool motors: the axis motors and the milling head motor. The results show the superiority of the ensembles for both classification problems under analysis and all four regression problems. In particular, Rotation Forest-based ensembles turned out to have the best performance in the experiments for all the metrics under study. The models are accurate enough to provide useful conclusions applicable to current industrial practice, such as improvements in machine programming to avoid cutting conditions that might greatly reduce tool lifetime and damage machine components.},

keywords = {Ensembles, internet of things, Milling, rotation forests, unbalanced datasets},

pubstate = {published},

tppubtype = {article}

}

@article{Rodríguez2019,

title = {Random Balance ensembles for multiclass imbalance learning},

author = {Juan José Rodríguez and José Francisco Díez-Pastor and Álvar Arnaiz-González and Ludmila I Kuncheva},

url = {https://www.sciencedirect.com/science/article/pii/S0950705119306598},

doi = {10.1016/j.knosys.2019.105434},

issn = {0950-7051},

year  = {2020},

date = {2020-04-06},

journal = {Knowledge-Based Systems},

abstract = {Random Balance strategy (RandBal) has been recently proposed for constructing classifier ensembles for imbalanced, two-class data sets. In RandBal, each base classifier is trained with a sample of the data with a random class prevalence, independent of the a priori distribution. Hence, for each sample, one of the classes will be undersampled while the other will be oversampled. RandBal can be applied on its own or can be combined with any other ensemble method. One particularly successful variant is RandBalBoost which integrates Random Balance and boosting. Encouraged by the success of RandBal, this work proposes two approaches which extend RandBal to multiclass imbalance problems. Multiclass imbalance implies that at least two classes have substantially different proportion of instances. In the first approach proposed here, termed Multiple Random Balance (MultiRandBal), we deal with all classes simultaneously. The training data for each base classifier are sampled with random class proportions. The second approach we propose decomposes the multiclass problem into two-class problems using one-vs-one or one-vs-all, and builds an ensemble of RandBal ensembles. We call the two versions of the second approach OVO-RandBal and OVA-RandBal, respectively. These two approaches were chosen because they are the most straightforward extensions of RandBal for multiple classes. Our main objective is to evaluate both approaches for multiclass imbalanced problems. To this end, an experiment was carried out with 52 multiclass data sets. The results suggest that both MultiRandBal, and OVO/OVA-RandBal are viable extensions of the original two-class RandBal. Collectively, they consistently outperform acclaimed state-of-the art methods for multiclass imbalanced problems.},

keywords = {Classifier ensembles, Imbalanced data, Multiclass classification},

pubstate = {published},

tppubtype = {article}

}

@article{Checa2019b,

title = {A review of immersive virtual reality serious games to enhance learning and training},

author = {David Checa and Andrés Bustillo},

url = {https://link.springer.com/article/10.1007/s11042-019-08348-9?wt_mc=Internal.Event.1.SEM.ArticleAuthorOnlineFirst&utm_source=ArticleAuthorOnlineFirst&utm_medium=email&utm_content=AA_en_06082018&ArticleAuthorOnlineFirst_20191206},

doi = {10.1007/s11042-019-08348-9},

issn = {1380-7501},

year  = {2019},

date = {2019-12-05},

journal = {Multimedia Tools and Applications},

pages = {1-21},

abstract = {The merger of game-based approaches and Virtual Reality (VR) environments that can enhance learning and training methodologies have a very promising future, reinforced by the widespread market-availability of affordable software and hardware tools for VR-environments. Rather than passive observers, users engage in those learning environments as active participants, permitting the development of exploration-based learning paradigms. There are separate reviews of VR technologies and serious games for educational and training purposes with a focus on only one knowledge area. However, this review covers 135 proposals for serious games in immersive VR-environments that are combinations of both VR and serious games and that offer end-user validation. First, an analysis of the forum, nationality, and date of publication of the articles is conducted. Then, the application domains, the target audience, the design of the game and its technological implementation, the performance evaluation procedure, and the results are analyzed. The aim here is to identify the factual standards of the proposed solutions and the differences between training and learning applications. Finally, the study lays the basis for future research lines that will develop serious games in immersive VR-environments, providing recommendations for the improvement of these tools and their successful application for the enhancement of both learning and training tasks.},

keywords = {Evaluation, Learning, Serious Game, Systematic Literature Review, Virtual Reality},

pubstate = {published},

tppubtype = {article}

}

@article{Kordos2019,

title = {Evolutionary prototype selection for multi-output regression},

author = {Mirosław Kordos and Álvar Arnaiz-González and César García-Osorio},

url = {https://www.sciencedirect.com/science/article/pii/S0925231219307611?fbclid=IwAR1qb5kLk1-PyqfAPprRnb6Jv75rMgJS3dY1rDqWF610G2lCttEW3QIBU4c},

doi = {10.1016/j.neucom.2019.05.055},

issn = {0925-2312},

year  = {2019},

date = {2019-09-17},

journal = {Neurocomputing},

volume = {358},

pages = {309-320},

abstract = {A novel approach to prototype selection for multi-output regression data sets is presented. A multi-objective evolutionary algorithm is used to evaluate the selections using two criteria: training data set compression and prediction quality expressed in terms of root mean squared error. A multi-target regressor based on k-NN was used for that purpose during the training to evaluate the error, while the tests were performed using four different multi-target predictive models. The distance matrices used by the multi-target regressor were cached to accelerate operational performance. Multiple Pareto fronts were also used to prevent overfitting and to obtain a broader range of solutions, by using different probabilities in the initialization of populations and different evolutionary parameters in each one. The results obtained with the benchmark data sets showed that the proposed method greatly reduced data set size and, at the same time, improved the predictive capabilities of the multi-output regressors trained on the reduced data set.},

keywords = {Multi-output, Multi-target, Prototype selection, Regression},

pubstate = {published},

tppubtype = {article}

}

@article{Juez-Gil2019,

title = {A regression-tree multilayer-perceptron hybrid strategy for the prediction of ore crushing-plate lifetimes},

author = {Mario Juez-Gil and Ivan Nikolaevich Erdakov and Andrés Bustillo and Danil Yurievich Pimenov},

doi = {10.1016/j.jare.2019.03.008},

issn = {2090-1232},

year  = {2019},

date = {2019-07-01},

journal = {Journal of Advanced Research},

volume = {July 2019},

number = {18},

pages = {173-184},

abstract = {Highly tensile manganese steel is in great demand owing to its high tensile strength under shock loads. All workpieces are produced through casting, because it is highly difficult to machine. The probabilistic aspects of its casting, its variable composition, and the different casting techniques must all be considered for the optimisation of its mechanical properties. A hybrid strategy is therefore proposed which combines decision trees and artificial neural networks (ANNs) for accurate and reliable prediction models for ore crushing plate lifetimes. The strategic blend of these two high-accuracy prediction models is used to generate simple decision trees which can reveal the main dataset features, thereby facilitating decision-making. Following a complexity analysis of a dataset with 450 different plates, the best model consisted of 9 different multilayer perceptrons, the inputs of which were only the Fe and Mn plate compositions. The model recorded a low root mean square error (RMSE) of only 0.0614 h for the lifetime of the plate: a very accurate result considering their varied lifetimes of between 746 and 6902 h in the dataset. Finally, the use of these models under real industrial conditions is presented in a heat map, namely a 2D representation of the main manufacturing process inputs with a colour scale which shows the predicted output, i.e. the expected lifetime of the manufactured plates. Thus, the hybrid strategy extracts core training dataset information in high-accuracy prediction models. This novel strategy merges the different capabilities of two families of machine-learning algorithms. It provides a high-accuracy industrial tool for the prediction of the full lifetime of highly tensile manganese steel plates. The results yielded a precision prediction of (RMSE of 0.061 h) for the full lifetime of (light, medium, and heavy) crusher plates manufactured with the three (experimental, classic, and highly efficient (new)) casting methods.},

keywords = {Artificial intelligence, Hadfield steel, Lifetime prediction, Multi-layer perceptrons, Regression trees, Resource savings},

pubstate = {published},

tppubtype = {article}

}

@article{Kuncheva2019,

title = {Instance selection improves geometric mean accuracy: a study on imbalanced data classification},

author = {Ludmila I Kuncheva and Álvar Arnaiz-González and José Francisco Díez-Pastor and Iain A D Gunn},

url = {https://link.springer.com/article/10.1007/s13748-019-00172-4?wt_mc=Internal.Event.1.SEM.ArticleAuthorOnlineFirst&utm_source=ArticleAuthorContributingOnlineFirst&utm_medium=email&utm_content=AA_en_06082018&ArticleAuthorContributingOnlineFirst_20190209},

doi = {10.1007/s13748-019-00172-4},

issn = {2192-6352},

year  = {2019},

date = {2019-06-01},

journal = {Progress in Artificial Intelligence},

volume = {8},

number = {2},

pages = {215-228},

abstract = {A natural way of handling imbalanced data is to attempt to equalise the class frequencies and train the classifier of choice on balanced data. For two-class imbalanced problems, the classification success is typically measured by the geometric mean (GM) of the true positive and true negative rates. Here we prove that GM can be improved upon by instance selection, and give the theoretical conditions for such an improvement. We demonstrate that GM is non-monotonic with respect to the number of retained instances, which discourages systematic instance selection. We also show that balancing the distribution frequencies is inferior to a direct maximisation of GM. To verify our theoretical findings, we carried out an experimental study of 12 instance selection methods for imbalanced data, using 66 standard benchmark data sets. The results reveal possible room for new instance selection methods for imbalanced data.},

keywords = {Ensemble methods, geometric mean (GM), Imbalanced data, instance/prototype selection, nearest neighbour, Theoretical perspective},

pubstate = {published},

tppubtype = {article}

}

@article{Alonso-Abad2019,

title = {Label prediction on issue tracking systems using text mining},

author = {Jesús M. Alonso-Abad and Carlos López-Nozal and Jesús Maudes-Raedo and Raúl Marticorena-Sánchez},

url = {https://link.springer.com/article/10.1007/s13748-019-00182-2?wt_mc=Internal.Event.1.SEM.ArticleAuthorOnlineFirst&utm_source=ArticleAuthorOnlineFirst&utm_medium=email&utm_content=AA_en_06082018&ArticleAuthorOnlineFirst_20190331},

doi = {10.1007/s13748-019-00182-2},

issn = {2192-6360},

year  = {2019},

date = {2019-03-28},

journal = {Progress in Artificial Intelligence},

pages = {1-18},

abstract = {Issue tracking systems are overall change-management tools in software development. The issue-solving life cycle is a complex socio-technical activity that requires team discussion and knowledge sharing between members. In that process, issue classification facilitates an understanding of issues and their analysis. Issue tracking systems permit the tagging of issues with default labels (e.g., bug, enhancement) or with customized team labels (e.g., test failures, performance). However, a current problem is that many issues in open-source projects remain unlabeled. The aim of this paper is to improve maintenance tasks in development teams, evaluating models that can suggest a label for an issue using its text comments. We analyze data on issues from several GitHub trending projects, first by extracting issue information and then by applying text mining classifiers (i.e., support vector machine and naive Bayes multinomial). The results suggest that very suitable classifiers may be obtained to label the issues or, at least, to suggest the most suitable candidate labels.},

keywords = {Experimentation in software engineering, Issue tracker system, Label prediction, Text classifier, Text mining},

pubstate = {published},

tppubtype = {article}

}

@article{Beranoagirre2019,

title = {Sensitivity Analysis of Tool Wear in Drilling of Titanium Aluminides},

author = {Aitor Beranoagirre and Gorka Urbikain and Raúl Marticorena-Sánchez and Andrés Bustillo and and Luis Norberto López de Lacalle},

doi = {10.3390/met9030297},

issn = {2075-4701},

year  = {2019},

date = {2019-03-06},

journal = {Metals},

volume = {9},

number = {3},

pages = {297},

abstract = {In the aerospace industry, a large number of holes need to be drilled to mechanically connect the components of aircraft engines. The working conditions for such components demand a good response of their mechanical properties at high temperatures. The new gamma TiAl are in the transition between the 2nd and 3rd generation, and several applications are proposed for that sector. Thus, NASA is proposing the use of the alloys in the Revolutionary Turbine Accelerator/Turbine-Based Combined Cycle (RTA/TBCC) Program for the next-generation launch vehicle, with gamma TiAl as a potential compressor and structural material. However, the information and datasets available regarding cutting performance in titanium aluminides are relatively scarce. So, a considerable part of the current research efforts in this field is dedicated to process optimization of cutting parameters and tool geometries. The present work is framed in the study of wear when machining holes in these difficult-to-cut alloys. In particular, the work presents the results from drilling tests on three types of gamma TiAl alloys, extruded MoCuSi, ingot MoCuSi, and TNB type, to define an optimal set of cutting parameters. Maintaining uniform, gradual wear is key to avoiding tool breakage and enabling good hole dimensional accuracy. So, this paper proposes a model based on ANOVA analysis to identify the relationships between cutting conditions and resulting wear and estimate tool life. The best cutting parameters were found at vc = 10–15 m/min and fn = 0.025 mm/rev.},

keywords = {difficult-to-cut materials, drilling, gamma TiAl, titanium aluminides},

pubstate = {published},

tppubtype = {article}

}

@article{Pimenov2019,

title = {Effect of the Relative Position of the Face Milling Tool towards the Workpiece on Machined Surface Roughness and Milling Dynamics},

author = {Danil Yurievich Pimenov and Amauri Hassui and Szymon Wojciechowski and Mozammel Mia and Aristides Magri and Daniel I. Suyama and Andrés Bustillo and Grzegorz Krolczyk and Munish Kumar Gupta},

doi = {10.3390/app9050842},

issn = {2076-3417},

year  = {2019},

date = {2019-02-27},

journal = {Applied Sciences},

volume = {9},

number = {5},

pages = {842},

abstract = {In face milling one of the most important parameters of the process quality is the roughness of the machined surface. In many articles, the influence of cutting regimes on the roughness and cutting forces of face milling is considered. However, during flat face milling with the milling width B lower than the cutter’s diameter D, the influence of such an important parameter as the relative position of the face mill towards the workpiece and the milling kinematics (Up or Down milling) on the cutting force components and the roughness of the machined surface has not been sufficiently studied. At the same time, the values of the cutting force components can vary significantly depending on the relative position of the face mill towards the workpiece, and thus have a different effect on the power expended on the milling process. Having studied this influence, it is possible to formulate useful recommendations for a technologist who creates a technological process using face milling operations. It is possible to choose such a relative position of the face mill and workpiece that will provide the smallest value of the surface roughness obtained by face milling. This paper shows the influence of the relative position of the face mill towards the workpiece and milling kinematics on the components of the cutting forces, the acceleration of the machine spindle in the process of face milling (considering the rotation of the mill for a full revolution), and on the surface roughness obtained by face milling. Practical recommendations on the assignment of the relative position of the face mill towards the workpiece and the milling kinematics are given.},

keywords = {acceleration, cutting force, Face milling, relative position, surface roughness},

pubstate = {published},

tppubtype = {article}

}

@article{Faithfull2019,

title = {Combining univariate approaches for ensemble change detection in multivariate data},

author = {William J Faithfull and Juan José Rodríguez and Ludmila I Kuncheva},

url = {https://www.sciencedirect.com/science/article/pii/S1566253517301239},

doi = {10.1016/j.inffus.2018.02.003},

issn = {1566-2535},

year  = {2019},

date = {2019-01-01},

journal = {Information Fusion},

volume = {45},

pages = {202-214},

abstract = {Detecting change in multivariate data is a challenging problem, especially when class labels are not available. There is a large body of research on univariate change detection, notably in control charts developed originally for engineering applications. We evaluate univariate change detection approaches —including those in the MOA framework — built into ensembles where each member observes a feature in the input space of an unsupervised change detection problem. We present a comparison between the ensemble combinations and three established ‘pure’ multivariate approaches over 96 data sets, and a case study on the KDD Cup 1999 network intrusion detection dataset. We found that ensemble combination of univariate methods consistently outperformed multivariate methods on the four experimental metrics.},

keywords = {Change detection, Ensemble methods, Multivariate data},

pubstate = {published},

tppubtype = {article}

}

@article{Arnaiz-González2018,

title = {Study of data transformation techniques for adapting single-label prototype selection algorithms to multi-label learning},

author = {Álvar Arnaiz-González and José Francisco Díez-Pastor and Juan José Rodríguez and César García-Osorio},

url = {https://www.sciencedirect.com/science/article/pii/S0957417418303087},

doi = {10.1016/j.eswa.2018.05.017},

issn = {0957-4174},

year  = {2018},

date = {2018-11-01},

journal = {Expert Systems with Applications},

volume = {109},

pages = {114-130},

abstract = {In this paper, the focus is on the application of prototype selection to multi-label data sets as a preliminary stage in the learning process. There are two general strategies when designing Machine Learning algorithms that are capable of dealing with multi-label problems: data transformation and method adaptation. These strategies have been successfully applied in obtaining classifiers and regressors for multi-label learning. Here we investigate the feasibility of data transformation in obtaining prototype selection algorithms for multi-label data sets from three prototype selection algorithms for single-label. The data transformation methods used were: binary relevance, dependent binary relevance, label powerset, and random k-labelsets. The general conclusion is that the methods of prototype selection obtained using data transformation are not better than those obtained through method adaptation. Moreover, prototype selection algorithms designed for multi-label do not do an entirely satisfactory job, because, although they reduce the size of the data set, without affecting significantly the accuracy, the classifier trained with the reduced data set does not improve the accuracy of the classifier when it is trained with the whole data set.},

keywords = {Binary relevance, Label powerset, Multi-label classification, Prototype selection, RAkEL},

pubstate = {published},

tppubtype = {article}

}

@article{OLEAGA201834,

title = {A machine-learning based solution for chatter prediction in heavy-duty milling machines},

author = {Ibone Oleaga and Carlos Pardo and Juan J Zulaika and Andres Bustillo},

url = {http://www.sciencedirect.com/science/article/pii/S0263224118305542},

doi = {https://doi.org/10.1016/j.measurement.2018.06.028},

issn = {0263-2241},

year  = {2018},

date = {2018-11-01},

journal = {Measurement},

volume = {128},

pages = {34 - 44},

abstract = {The main productivity constraints of milling operations are self-induced vibrations, especially regenerative chatter vibrations. Two key parameters are linked to these vibrations: the depth of cut achievable without vibrations and the chatter frequency. Both parameters are linked to the dynamics of machine component excitation and the milling operation parameters. Their identification in any cutting direction in milling machine operations requires complex analytical models and mechatronic simulations, usually only applied to identify the worst cutting conditions in operating machines. This work proposes the use of machine learning techniques with no need to calculate the two above-mentioned parameters by means of a 3-step strategy. The strategy combines: 1) experimental frequency responses collected at the tool center point; 2) analytical calculations of both parameters; and, 3) different machine learning techniques. The results of these calculations can then be used to predict chatter under different combinations of milling directions and machine positions. This strategy is validated with real experiments on a bridge milling machine performing concordance roughing operations on AISI 1045 steel with a 125 mm diameter mill fitted with nine cutters at 45°, the results of which have confirmed the high variability of both parameters along the working volume. The following regression techniques are tested: artificial neural networks, regression trees and Random Forest. The results show that Random Forest ensembles provided the highest accuracy with a statistical advantage over the other machine learning models; they achieved a final accuracy of 0.95 mm for the critical depth and 7.3 Hz for the chatter frequency (RMSE) in the whole working volume and in all feed directions, applying a 10 × 10 cross validation scheme. These RMSE values are acceptable from the industrial point of view, taking into account that the critical depth of this range varies between 0.68 mm and 19.20 mm and the chatter frequency between 1.14 Hz and 65.25 Hz. Besides, Random Forest ensembles are more easily optimized than artificial neural networks (1 parameter configuration versus 210 MLPs). Additionally, tools that incorporate regression trees are interesting and highly accurate, providing immediately accessible and useful information in visual formats on critical machine performance for the design engineer.},

keywords = {Chatter, Milling, Polar diagrams, Random forest, Regression trees, Vibrations},

pubstate = {published},

tppubtype = {article}

}

@article{CHECA2018,

title = {Optimización del proceso de mecanizado de grandes piezas de fundición mediante la monitorización remota y la visualización 3D},

author = {David Checa and Juan J Zulaika and Iñigo Lazkanotegi and Andrés Bustillo},

url = {http://www.revistadyna.com/Articulos/Ficha.aspx?IdMenu=a5c9d895-28e0-4f92-b0c2-c0f86f2a940b&Cod=8816&Idioma=es-ES},

doi = {10.6036/8816},

issn = {19891490},

year  = {2018},

date = {2018-11-01},

journal = {DYNA Ingeniería e Industria},

volume = {93},

number = {1},

pages = {668--674},

abstract = {El desarrollo en los últimos años de distintas tecnologías englobadas en el paradigma Industria 4.0 abre la puerta a la monitorización intensiva de las máquinas herramienta. En este trabajo se presenta una plataforma de adquisición y monitorización tanto 2D como 3D del funcionamiento de máquinas-herramienta que busca facilitar la toma de decisiones para la optimización de la producción. Esta plataforma está compuesta por: 1) un sistema de adquisición de datos que procesa la información recopilada por el PLC y el CNC de la máquina y por cualquier otro sensor integrado en la misma, 2) un servidor remoto que guarda los datos recogidos y 3) un conjunto de interfaces 2D y 3D que permiten tanto calcular indicadores claves de rendimiento en tiempo real como analizar un proceso concreto de mecanizado en un entorno virtual 3D mediante Oculus Rift y Oculus Touch para detectar anomalías en el proceso de mecanizado. El funcionamiento de esta plataforma se ha validado en una fresadora de pórtico que realiza el mecanizado de una pieza de fundición de grandes dimensiones. El resultado de este estudio muestra cómo se pueden detectar tres tipos de anomalías en el proceso de mecanizado y cómo el entorno inmersivo 3D facilita que el ingeniero de proceso detecte estas anomalías, en especial en el caso de ingenieros de proceso junior.},

keywords = {Indicadores claves de rendimiento, Máquina herramienta, Optimización del mecanizado, Realidad Virtual},

pubstate = {published},

tppubtype = {article}

}

@article{BUSTILLO2018215,

title = {Using artificial intelligence models for the prediction of surface wear based on surface isotropy levels},

author = {A Bustillo and D.Yu. Pimenov and M Matuszewski and T Mikolajczyk},

url = {http://www.sciencedirect.com/science/article/pii/S0736584517303733},

doi = {https://doi.org/10.1016/j.rcim.2018.03.011},

issn = {0736-5845},

year  = {2018},

date = {2018-10-01},

journal = {Robotics and Computer-Integrated Manufacturing},

volume = {53},

pages = {215 - 227},

abstract = {Currently, a key industrial challenge in friction processes is the prediction of surface roughness and loss of mass under different machining processes, such as Electro-Discharge Machining (EDM), and turning and grinding processes. Under industrial conditions, only the sliding distance is easily evaluated in friction processes, while the acquisition of other variables usually implies expensive costs for production centres, such as the integration of sensors in functioning machine-tools. Besides, appropriate datasets are usually very small, because the testing of different friction conditions is also expensive. These two restrictions, small datasets and very few inputs, make it very difficult to use Artificial Intelligence (AI) techniques to model the industrial problem. So, the use of the isotropy level of the surface structure is proposed, as another input that is easily evaluated prior to the friction process. In this example, the friction processes of a cubic sample of 102Cr6 (40 HRC) steel and a further element made of X210Cr12 (60 HRC) steel are considered. Different artificial intelligence techniques, such as artificial regression trees, multilayer perceptrons (MLPs), radial basis networks (RBFs), and Random Forest, were tested considering the isotropy level as either a nominal or a numeric attribute, to evaluate improvements in the accuracy of surface roughness and loss-of-mass predictions. The results obtained with real datasets showed that RBFs and MLPs provided the most accurate models for loss of mass and surface roughness prediction, respectively. MLPs have slightly higher surface prediction accuracy than Random Forest, although MLP models are very sensitive to the tuning of their parameters (a small mismatch between the learning rate and the momentum in the MLP will drastically reduce the accuracy of the model). In contrast, Random Forest has no parameter to be tuned and its prediction is almost as good as MLPs for surface roughness, so Random Forest will be more suitable for industrial use where no expert in AI model tuning is available. Moreover, the inclusion of the isotropy level in the dataset, especially as a numeric attribute, greatly improved the accuracy of the models, in some cases, by up to 52% for MLPs, and by a smaller proportion of 16% in the Random Forest models in terms of Root Mean Square Error. Finally, Random Forest ensembles only trained with low and very high isotropy level experimental datasets generated reliable models for medium levels of isotropy, thereby offering a solution to reduce the size of training datasets.},

keywords = {Ensembles, Isotropy level geometric structure of the surface, Roughness, Small size dataset, Wear},

pubstate = {published},

tppubtype = {article}

}

@article{Kuncheva2018b,

title = {On feature selection protocols for very low-sample-size data},

author = {Ludmila I Kuncheva and Juan José Rodríguez},

url = {https://www.sciencedirect.com/science/article/pii/S003132031830102X},

doi = {10.1016/j.patcog.2018.03.012},

issn = {0031-3203},

year  = {2018},

date = {2018-09-01},

journal = {Pattern Recognition},

volume = {81},

pages = {660-673},

abstract = {High-dimensional data with very few instances are typical in many application domains. Selecting a highly discriminative subset of the original features is often the main interest of the end user. The widely-used feature selection protocol for such type of data consists of two steps. First, features are selected from the data (possibly through cross-validation), and, second, a cross-validation protocol is applied to test a classifier using the selected features. The selected feature set and the testing accuracy are then returned to the user. For the lack of a better option, the same low-sample-size dataset is used in both steps. Questioning the validity of this protocol, we carried out an experiment using 24 high-dimensional datasets, three feature selection methods and five classifier models. We found that the accuracy returned by the above protocol is heavily biased, and therefore propose an alternative protocol which avoids the contamination by including both steps in a single cross-validation loop. Statistical tests verify that the classification accuracy returned by the proper protocol is significantly closer to the true accuracy (estimated from an independent testing set) compared to that returned by the currently favoured protocol.},

keywords = {Cross-validation, Experimental protocol, Feature selection, Training/testing, Wide datasets},

pubstate = {published},

tppubtype = {article}

}

@article{BUSTILLO2018b,

title = {Smart optimization of a friction-drilling process based on boosting ensembles},

author = {Andres Bustillo and Gorka Urbikain and Jose M Perez and Octavio M Pereira and Luis Lopez N de Lacalle},

url = {http://www.sciencedirect.com/science/article/pii/S0278612518301249},

doi = {https://doi.org/10.1016/j.jmsy.2018.06.004},

issn = {0278-6125},

year  = {2018},

date = {2018-08-16},

journal = {Journal of Manufacturing Systems},

abstract = {Form and friction drilling techniques are now promising alternatives in light and medium boilermaking that will very probably supersede conventional drilling techniques, as rapid and economic solutions for producing nutless bolted joints. Nonetheless, given the number of cutting parameters involved, optimization of the process requires calibration of the main input parameters in relation to the desired output values. Among these values, the gap between plates determines the service life of the joint. In this paper, a suitable smart manufacturing strategy for real industrial conditions is proposed, where it is necessary to identify the most accurate machine-learning technique to process experimental datasets of a small size. The strategy is first to generate a small-size dataset under real industrial conditions, then the gap is discretized taking into account the specific industrial needs of this quality indicator for each product. Finally, the different machine learning models are tested and fine-tuned to ascertain the most accurate model at the lowest cost. The strategy is validated with a 48 condition-dataset where only feed-rate and rotation speed are used as inputs and the gap as the output. The results on this dataset showed that the Adaboost ensembles provided the highest accuracy and were more easily optimized than artificial neural networks.},

keywords = {Boosting, Ensembles, Friction drilling, Gap prediction, Small-size dataset},

pubstate = {published},

tppubtype = {article}

}

@article{Arnaiz-González2018b,

title = {Local sets for multi-label instance selection},

author = {Álvar Arnaiz-González and José Francisco Díez-Pastor and Juan José Rodríguez and César García-Osorio},

url = {https://www.sciencedirect.com/science/article/pii/S1568494618302072},

doi = {10.1016/j.asoc.2018.04.016},

issn = {1568-4946},

year  = {2018},

date = {2018-07-01},

journal = {Applied Soft Computing},

volume = {68},

pages = {651-666},

abstract = {The multi-label classification problem is an extension of traditional (single-label) classification, in which the output is a vector of values rather than a single categorical value. The multi-label problem is therefore a very different and much more challenging one than the single-label problem. Recently, multi-label classification has attracted interest, because of its real-life applications, such as image recognition, bio-informatics, and text categorization, among others. Unfortunately, there are few instance selection techniques capable of processing the data used for these applications. These techniques are also very useful for cleaning and reducing the size of data sets.



In single-label problems, the local set of an instance x comprises all instances in the largest hypersphere centered on x, so that they are all of the same class. This concept has been successfully integrated in the design of Iterative Case Filtering, one of the most influential instance selection methods in single-label learning. Unfortunately, the concept that was originally defined for single-label learning cannot be directly applied to multi-label data, as each instance has more than one label.



An adaptation of the local set concept to multi-label data is proposed in this paper and its effectiveness is verified in the design of two new algorithms that yielded competitive results. One of the adaptations cleans the data sets, to improve their predictive capabilities, while the other aims to reduce data set sizes. Both are tested and compared against the state-of-the-art instance selection methods available for multi-label learning.},

keywords = {Data reduction, Instance selection, Local set, Multi-label classification, Nearest neighbor},

pubstate = {published},

tppubtype = {article}

}

@article{Pimenov2018,

title = {Artificial intelligence for automatic prediction of required surface roughness by monitoring wear on face mill teeth},

author = {Yu. D Pimenov and A Bustillo and T Mikolajczyk},

url = {https://doi.org/10.1007/s10845-017-1381-8},

doi = {10.1007/s10845-017-1381-8},

issn = {1572-8145},

year  = {2018},

date = {2018-06-01},

journal = {Journal of Intelligent Manufacturing},

volume = {29},

number = {5},

pages = {1045--1061},

abstract = {Nowadays, face milling is one of the most widely used machining processes for the generation of flat surfaces. Following international standards, the quality of a machined surface is measured in terms of surface roughness, Ra, a parameter that will decrease with increased tool wear. So, cutting inserts of the milling tool have to be changed before a given surface quality threshold is exceeded. The use of artificial intelligence methods is suggested in this paper for real-time prediction of surface roughness deviations, depending on the main drive power, and taking tool wear, $$V_B$$ V B into account. This method ensures comprehensive use of the potential of modern CNC machines that are able to monitor the main drive power, N, in real-time. It can likewise estimate the three parameters -maximum tool wear, machining time, and cutting power- that are required to generate a given surface roughness, thereby making the most efficient use of the cutting tool. A series of artificial intelligence methods are tested: random forest (RF), standard Multilayer perceptrons (MLP), Regression Trees, and radial-based functions. Random forest was shown to have the highest model accuracy, followed by regression trees, displaying higher accuracy than the standard MLP and the radial-basis function. Moreover, RF techniques are easily tuned and generate visual information for direct use by the process engineer, such as the linear relationships between process parameters and roughness, and thresholds for avoiding rapid tool wear. All of this information can be directly extracted from the tree structure or by drawing 3D charts plotting two process inputs and the predicted roughness depending on workshop requirements.},

keywords = {Cutting power, Face milling Wear, Processing time, Random forest, surface roughness},

pubstate = {published},

tppubtype = {article}

}

@article{MIKOLAJCZYK2018503,

title = {Predicting tool life in turning operations using neural networks and image processing},

author = {T Mikołajczyk and K Nowicki and A Bustillo and Yu D Pimenov},

url = {http://www.sciencedirect.com/science/article/pii/S088832701730599X},

doi = {https://doi.org/10.1016/j.ymssp.2017.11.022},

issn = {0888-3270},

year  = {2018},

date = {2018-05-01},

journal = {Mechanical Systems and Signal Processing},

volume = {104},

pages = {503 - 513},

abstract = {A two-step method is presented for the automatic prediction of tool life in turning operations. First, experimental data are collected for three cutting edges under the same constant processing conditions. In these experiments, the parameter of tool wear, VB, is measured with conventional methods and the same parameter is estimated using Neural Wear, a customized software package that combines flank wear image recognition and Artificial Neural Networks (ANNs). Second, an ANN model of tool life is trained with the data collected from the first two cutting edges and the subsequent model is evaluated on two different subsets for the third cutting edge: the first subset is obtained from the direct measurement of tool wear and the second is obtained from the Neural Wear software that estimates tool wear using edge images. Although the complete-automated solution, Neural Wear software for tool wear recognition plus the ANN model of tool life prediction, presented a slightly higher error than the direct measurements, it was within the same range and can meet all industrial requirements. These results confirm that the combination of image recognition software and ANN modelling could potentially be developed into a useful industrial tool for low-cost estimation of tool life in turning operations.},

keywords = {Image analysis, Neural networks, Tool life prediction, Tool wear},

pubstate = {published},

tppubtype = {article}

}

@article{Kuncheva2018,

title = {Instance Selection Improves Geometric Mean Accuracy: A Study on Imbalanced Data Classification},

author = {Ludmila I Kuncheva and Álvar Arnaiz-González and José Francisco Díez-Pastor and Iain A D Gunn},

url = {https://arxiv.org/abs/1804.07155},

doi = {arXiv:1804.07155v1},

year  = {2018},

date = {2018-04-19},

journal = {arXiv},

abstract = {A natural way of handling imbalanced data is to attempt to equalise the class frequencies and train the classifier of choice on balanced data. For two-class imbalanced problems, the classification success is typically measured by the geometric mean (GM) of the true positive and true negative rates. Here we prove that GM can be improved upon by instance selection, and give the theoretical conditions for such an improvement. We demonstrate that GM is non-monotonic with respect to the number of retained instances, which discourages systematic instance selection. We also show that balancing the distribution frequencies is inferior to a direct maximisation of GM. To verify our theoretical findings, we carried out an experimental study of 12 instance selection methods for imbalanced data, using 66 standard benchmark data sets. The results reveal possible room for new instance selection methods for imbalanced data. },

keywords = {Ensemble methods, geometric mean (GM), Imbalanced data, instance/prototype selection, nearest neighbour},

pubstate = {published},

tppubtype = {article}

}

@article{Gunn2018,

title = {A taxonomic look at instance-based stream classifiers},

author = {Iain A D Gunn and Álvar Arnaiz-González and Ludmila I Kuncheva},

url = {https://www.sciencedirect.com/science/article/pii/S092523121830095X},

doi = {10.1016/j.neucom.2018.01.062},

issn = {0925-2312},

year  = {2018},

date = {2018-04-19},

journal = {Neurocomputing},

volume = {286},

pages = {167-178},

abstract = {Large numbers of data streams are today generated in many fields. A key challenge when learning from such streams is the problem of concept drift. Many methods, including many prototype methods, have been proposed in recent years to address this problem. This paper presents a refined taxonomy of instance selection and generation methods for the classification of data streams subject to concept drift. The taxonomy allows discrimination among a large number of methods which pre-existing taxonomies for offline instance selection methods did not distinguish. This makes possible a valuable new perspective on experimental results, and provides a framework for discussion of the concepts behind different algorithm-design approaches. We review a selection of modern algorithms for the purpose of illustrating the distinctions made by the taxonomy. We present the results of a numerical experiment which examined the performance of a number of representative methods on both synthetic and real-world data sets with and without concept drift, and discuss the implications for the directions of future research in light of the taxonomy. On the basis of the experimental results, we are able to give recommendations for the experimental evaluation of algorithms which may be proposed in the future.},

keywords = {Concept drift, Instance selection, Machine learning, Prototype generation, Stream classification},

pubstate = {published},

tppubtype = {article}

}

@article{Grzenda2018,

title = {Semi-supervised roughness prediction with partly unlabeled vibration data streams},

author = {Maciej Grzenda and Andres Bustillo},

url = {https://doi.org/10.1007/s10845-018-1413-z},

doi = {10.1007/s10845-018-1413-z},

issn = {1572-8145},

year  = {2018},

date = {2018-03-23},

journal = {Journal of Intelligent Manufacturing},

pages = {1-13},

abstract = {Experimental data sets that include tool settings, tool and machine-tool behavior, and surface roughness data for milling processes are usually of limited size, due mainly to the high costs of machining tests. This fact restricts the application of machine-learning techniques for surface roughness prediction in industrial settings. The primary objective of this work is to investigate the way data streams that are missing product features (i.e. unlabeled data streams) can contribute to the development of prediction models. The investigation is followed by a proposal for a semi-supervised approach to the development of roughness prediction models that can use partly unlabeled data to improve the accuracy of roughness prediction. Following this strategy, records collected during the milling process, which miss roughness measurements, but contain vibration data are used to increase the accuracy of the prediction models. The method proposed in this work is based on the selective use of such unlabelled instances, collected at tool settings that are not represented in the labeled data. This strategy, when applied properly, yields both extended training data sets and higher accuracy in the roughness prediction models that are derived from them. The scale of accuracy improvement and its statistical significance are shown in the study case of high-torque face milling of F114 steel. The semi-supervised approach proposed in this work has been used in combination with supervised k Nearest Neighbours and random forest techniques. Furthermore, the study of both continuous and discretized roughness prediction, showed higher gains in accuracy in the second.},

keywords = {Face milling, Roughness prediction, Semi-supervised techniques, Unlabeled data},

pubstate = {published},

tppubtype = {article}

}

@article{Santos2018,

title = {Identifying maximum imbalance in datasets for fault diagnosis of gearboxes},

author = {Pedro Santos and Jesús Maudes-Raedo and Andrés Bustillo},

url = {https://link.springer.com/article/10.1007%2Fs10845-015-1110-0},

doi = {10.1007/s10845-015-1110-0},

issn = { 0956-5515},

year  = {2018},

date = {2018-02-01},

journal = {Journal of Intelligent Manufacturing},

volume = {29},

number = {2},

pages = {333-351},

abstract = {Research into fault diagnosis in rotating machinery with a wide range of variable loads and speeds, such as the gearboxes of wind turbines, is of great industrial interest. Although appropriate sensors have been identified, an intelligent system that classifies machine states remains an open issue, due to a paucity of datasets with sufficient fault cases. Many of the proposed solutions have been tested on balanced datasets, containing roughly equal percentages of wind-turbine failure instances and instances of correct performance. In practice, however, it is not possible to obtain balanced datasets under real operating conditions. Our objective is to identify the most suitable classification technique that will depend least of all on the level of imbalance in the dataset. We start by analysing different metrics for the comparison of classification techniques on imbalanced datasets. Our results pointed to the Unweighted Macro Average of the F-measure, which we consider the most suitable metric for this diagnosis. Then, an extensive set of classification techniques was tested on datasets with varying levels of imbalance. Our conclusion is that a Rotation Forest ensemble of C4.4 decision trees, modifying the training phase of the classifier with a cost-sensitive approach, is the most suitable prediction model for this industrial task. It maintained its good performance even when the minority classes rate was as low as 6.5 %, while the majority of the other classifiers were more sensitive to the level of database imbalance and failed standard performance objectives, when the minority classes rate was lower than 10.5 %.},

keywords = {Fault diagnosis, Metrics Gearbox, Multi-class imbalance, Wind turbines Ensembles},

pubstate = {published},

tppubtype = {article}

}

@article{Güemes-Peña2018,

title = {Emerging topics in mining software repositories},

author = {Diego Güemes-Peña and Carlos López-Nozal and Raúl Marticorena-Sánchez and Jesús Maudes-Raedo},

url = {https://link.springer.com/content/pdf/10.1007/s13748-018-0147-7.pdf},

doi = {10.1007/s13748-018-0147-7},

issn = {2192-6360},

year  = {2018},

date = {2018-01-01},

journal = {Progress in Artificial Intelligence},

pages = {1-11},

abstract = {A software process is a set of related activities that culminates in the production of a software package: specification, design, implementation, testing, evolution into new versions, and maintenance. There are also other supporting activities such as configuration and change management, quality assurance, project management, evaluation of user experience, etc. Software repositories are infrastructures to support all these activities. They can be composed with several systems that include code change management, bug tracking, code review, build system, release binaries, wikis, forums, etc. This position paper on mining software repositories presents a review and a discussion of research in this field over the past decade. We also identify applied machine learning strategies, current working topics, and future challenges for the improvement of company decision-making systems. Machine learning is defined as the process of discovering patterns in data. It can be applied to software repositories, since every change is recorded as data. Companies can then use these patterns as the basis for their decision-making systems and for knowledge discovery.},

keywords = {Data Mining, Machine learning, Software engineering, Software process, Software repository},

pubstate = {published},

tppubtype = {article}

}

@article{MIKOLAJCZYK2018172,

title = {Selection of machining parameters with Android application made using MIT App Inventor bookmarks},

author = {Tadeusz Mikolajczyk and Hu Fuwen and Liviu Moldovan and Andres Bustillo and Maciej Matuszewski and Krzysztof Nowicki},

url = {http://www.sciencedirect.com/science/article/pii/S2351978918303214},

doi = {https://doi.org/10.1016/j.promfg.2018.03.027},

issn = {2351-9789},

year  = {2018},

date = {2018-01-01},

journal = {Procedia Manufacturing},

volume = {22},

pages = {172 - 179},

abstract = {Undoubtedly mobile devices are gaining more and more popularity. However, the breakthrough in mobile applications is yet to be followed by a breakthrough in manufacturing industry. The paper presents a new methodology for application development on the Android platform in MIT App Inventor bookmarks. The research method consists in an algorithm and application design. Also it was presented an example of an elaborate program SpeedCalc for the lathe spindle speed selection for the determined value of cutting speed in relation to the diameter of the work piece. The program can be used with a mobile phone or tablet.},

note = {11th International Conference Interdisciplinarity in Engineering, INTER-ENG 2017, 5-6 October 2017, Tirgu Mures, Romania},

keywords = {Android, machining parameters, MIT inventor, mobile application},

pubstate = {published},

tppubtype = {article}

}

@article{Maudes2017,

title = {Random Forest ensemble prediction of stent dimensions in microfabrication processes},

author = {Jesus Maudes and Andrés Bustillo and Antonio J Guerra and Joaquim Ciurana},

url = {https://doi.org/10.1007/s00170-016-9695-9},

doi = {10.1007/s00170-016-9695-9},

issn = {1433-3015},

year  = {2017},

date = {2017-07-01},

journal = {The International Journal of Advanced Manufacturing Technology},

volume = {91},

number = {1},

pages = {879--893},

abstract = {The recent development of new laser machine tools for the manufacture of micro-scale metallic components has boosted demand in the field of medical applications. However, the optimization of this process encounters a major problem: a knowledge gap concerning the relation between the controllable parameters of these machine tools and the quality of the machined components. Our research proposes a two-step strategy to approach this problem for the manufacture of stents. First, a screening test identifies good and bad performance conditions for the laser process and generates useful information on cutting performance; then, a stent is manufactured under different cutting conditions and the most accurate machine learning technique to model this process is identified. This strategy is validated with the performance of experiments that vary pulse duration, laser power, and cutting speed, and measure two geometrical characteristics of the stent geometry. The results showed that linear Support Vector Machines can identify good and bad cutting conditions, while Random Forest ensembles of regression trees can predict with high accuracy the two characteristics of the stent geometry under study. Besides, this technique can extract useful information from the screening test that improves its final accuracy. In view of the small dataset size, an alternative based on the leave-one-out technique was used, instead of standard cross validation, so as to assure the generalization capability of the models.},

keywords = {Data Mining, Ensembles of regressors, Random forest, Regression trees, Stents Laser machining},

pubstate = {published},

tppubtype = {article}

}