Publications

@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{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{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, SELECTED, 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{ArnaizGonzálezLSHIS2016,

title = {Instance selection of linear complexity for big data},

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

url = {http://www.sciencedirect.com/science/article/pii/S0950705116301617},

doi = {10.1016/j.knosys.2016.05.056},

issn = {0950-7051},

year  = {2016},

date = {2016-01-01},

journal = {Knowledge-Based Systems},

volume = {107},

pages = {83–95},

abstract = {Abstract Over recent decades, database sizes have grown considerably. Larger sizes present new challenges, because machine learning algorithms are not prepared to process such large volumes of information. Instance selection methods can alleviate this problem when the size of the data set is medium to large. However, even these methods face similar problems with very large-to-massive data sets. In this paper, two new algorithms with linear complexity for instance selection purposes are presented. Both algorithms use locality-sensitive hashing to find similarities between instances. While the complexity of conventional methods (usually quadratic, O ( n 2 ) , or log-linear, O ( n log n ) ) means that they are unable to process large-sized data sets, the new proposal shows competitive results in terms of accuracy. Even more remarkably, it shortens execution time, as the proposal manages to reduce complexity and make it linear with respect to the data set size. The new proposal has been compared with some of the best known instance selection methods for testing and has also been evaluated on large data sets (up to a million instances).},

keywords = {Big data, Data Mining, Data reduction, Hashing, Instance selection, Nearest neighbors, SELECTED},

pubstate = {published},

tppubtype = {article}

}

@article{1746771,

title = {Democratic instance selection: A linear complexity instance selection algorithm based on classifier ensemble concepts},

author = {César García-Osorio and Aida Haro-García and Nicolás García-Pedrajas},

doi = {10.1016/j.artint.2010.01.001},

issn = {0004-3702},

year  = {2010},

date = {2010-01-01},

journal = {Artif. Intell.},

volume = {174},

number = {5-6},

pages = {410–441},

publisher = {Elsevier Science Publishers Ltd.},

address = {Essex, UK},

keywords = {Big data, Data Mining, Instance selection},

pubstate = {published},

tppubtype = {article}

}