Open Access
Multimodal fuzzy fusion for enhancing the motor-imagery-based brain computer interface
(IEEE, 2019) Ko, Li-Wei; Lu, Yi-Chen; Bustince Sola, Humberto; Chang, Yu-Cheng; Chang, Yang; Fernández Fernández, Francisco Javier; Wang, Yu-Kai; Sanz Delgado, José Antonio; Pereira Dimuro, Graçaliz; Lin, Chin-Teng; Estatistika, Informatika eta Matematika; Institute of Smart Cities - ISC; Estadística, Informática y Matemáticas
Brain–computer interface technologies, such as steady-state visually evoked potential, P300, and motor imagery are methods of communication between the human brain and the external devices. Motor imagery–based brain–computer interfaces are popular because they avoid unnecessary external stimulus. Although feature extraction methods have been illustrated in several machine intelligent systems in motor imagery-based brain–computer interface studies, the performance remains unsatisfactory. There is increasing interest in the use of the fuzzy integrals, the Choquet and Sugeno integrals, that are appropriate for use in applications in which fusion of data must consider possible data interactions. To enhance the classification accuracy of brain-computer interfaces, we adopted fuzzy integrals, after employing the classification method of traditional brain–computer interfaces, to consider possible links between the data. Subsequently, we proposed a novel classification framework called the multimodal fuzzy fusion-based brain-computer interface system. Ten volunteers performed a motor imagery-based brain-computer interface experiment, and we acquired electroencephalography signals simultaneously. The multimodal fuzzy fusion-based brain-computer interface system enhanced performance compared with traditional brain–computer interface systems. Furthermore, when using the motor imagery-relevant electroencephalography frequency alpha and beta bands for the input features, the system achieved the highest accuracy, up to 78.81% and 78.45% with the Choquet and Sugeno integrals, respectively. Herein, we present a novel concept for enhancing brain–computer interface systems that adopts fuzzy integrals, especially in the fusion for classifying brain–computer interface commands.
Open Access
dCF-integrals: generalizing CF-integrals by means of restricted dissimilarity functions
(IEEE, 2022) Wieczynski, Jonata; Lucca, Giancarlo; Pereira Dimuro, Graçaliz; Borges, Eduardo N.; Sanz Delgado, José Antonio; Da Cruz Asmus, Tiago; Fernández Fernández, Francisco Javier; Bustince Sola, Humberto; Estatistika, Informatika eta Matematika; Institute of Smart Cities - ISC; Estadística, Informática y Matemáticas; Universidad Pública de Navarra / Nafarroako Unibertsitate Publikoa, PJUPNA1926
The Choquet integral (CI) is an averaging aggregation function that has been used, e.g., in the fuzzy reasoning method (FRM) of fuzzy rule-based classification systems (FRBCSs) and in multicriteria decision making in order to take into account the interactions among data/criteria. Several generalizations of the CI have been proposed in the literature in order to improve the performance of FRBCSs and also to provide more flexibility in the different models by relaxing both the monotonicity requirement and averaging conditions of aggregation functions. An important generalization is the CF -integrals, which are preaggregation functions that may present interesting nonaveraging behavior depending on the function F adopted in the construction and, in this case, offering competitive results in classification. Recently, the concept of d-Choquet integrals was introduced as a generalization of the CI by restricted dissimilarity functions (RDFs), improving the usability of CIs, as when comparing inputs by the usual difference may not be viable. The objective of this article is to introduce the concept of dCF -integrals, which is a generalization of CF -integrals by RDFs. The aim is to analyze whether the usage of dCF -integrals in the FRM of FRBCSs represents a good alternative toward the standard CF -integrals that just consider the difference as a dissimilarity measure. For that, we consider six RDFs combined with five fuzzy measures, applied with more than 20 functions F . The analysis of the results is based on statistical tests, demonstrating their efficiency. Additionally, comparing the applicability of dCF -integrals versus CF -integrals, the range of the good generalizations of the former is much larger than that of the latter.
Open Access
IIVFDT: ignorance functions based interval-valued fuzzy decision tree with genetic tuning
(World Scientific Publishing Company, 2012) Sanz Delgado, José Antonio; Fernández, Alberto; Bustince Sola, Humberto; Herrera, Francisco; Automática y Computación; Automatika eta Konputazioa
The choice of membership functions plays an essential role in the success of fuzzy systems. This is a complex problem due to the possible lack of knowledge when assigning punctual values as membership degrees. To face this handicap, we propose a methodology called Ignorance functions based Interval-Valued Fuzzy Decision Tree with genetic tuning, IIVFDT for short, which allows to improve the performance of fuzzy decision trees by taking into account the ignorance degree. This ignorance degree is the result of a weak ignorance function applied to the punctual value set as membership degree. Our IIVFDT proposal is composed of four steps: (1) the base fuzzy decision tree is generated using the fuzzy ID3 algorithm; (2) the linguistic labels are modeled with Interval-Valued Fuzzy Sets. To do so, a new parametrized construction method of Interval-Valued Fuzzy Sets is defined, whose length represents such ignorance degree; (3) the fuzzy reasoning method is extended to work with this representation of the linguistic terms; (4) an evolutionary tuning step is applied for computing the optimal ignorance degree for each Interval-Valued Fuzzy Set. The experimental study shows that the IIVFDT method allows the results provided by the initial fuzzy ID3 with and without Interval-Valued Fuzzy Sets to be outperformed. The suitability of the proposed methodology is shown with respect to both several state-of-the-art fuzzy decision trees and C4.5. Furthermore, we analyze the quality of our approach versus two methods that learn the fuzzy decision tree using genetic algorithms. Finally, we show that a superior performance can be achieved by means of the positive synergy obtained when applying the well known genetic tuning of the lateral position after the application of the IIVFDT method. The choice of membership functions plays an essential role in the success of fuzzy systems. This is a complex problem due to the possible lack of knowledge when assigning punctual values as membership degrees. To face this handicap, we propose a methodology called Ignorance functions based Interval-Valued Fuzzy Decision Tree with genetic tuning, IIVFDT for short, which allows to improve the performance of fuzzy decision trees by taking into account the ignorance degree. This ignorance degree is the result of a weak ignorance function applied to the punctual value set as membership degree. Our IIVFDT proposal is composed of four steps: (1) the base fuzzy decision tree is generated using the fuzzy ID3 algorithm; (2) the linguistic labels are modeled with Interval-Valued Fuzzy Sets. To do so, a new parametrized construction method of Interval-Valued Fuzzy Sets is defined, whose length represents such ignorance degree; (3) the fuzzy reasoning method is extended to work with this representation of the linguistic terms; (4) an evolutionary tuning step is applied for computing the optimal ignorance degree for each Interval-Valued Fuzzy Set. The experimental study shows that the IIVFDT method allows the results provided by the initial fuzzy ID3 with and without Interval-Valued Fuzzy Sets to be outperformed. The suitability of the proposed methodology is shown with respect to both several state-of-the-art fuzzy decision trees and C4.5. Furthermore, we analyze the quality of our approach versus two methods that learn the fuzzy decision tree using genetic algorithms. Finally, we show that a superior performance can be achieved by means of the positive synergy obtained when applying the well known genetic tuning of the lateral position after the application of the IIVFDT method.
Open Access
Construction of capacities from overlap indexes
(Springer, 2017) Sanz Delgado, José Antonio; Galar Idoate, Mikel; Mesiar, Radko; Bustince Sola, Humberto; Fernández Fernández, Francisco Javier; Automatika eta Konputazioa; Institute of Smart Cities - ISC; Automática y Computación
In this chapter, we show how the concepts of overlap function and overlap index can be used to define fuzzy measures which depend on the specific data of each considered problem.
Open Access
A proposal for tuning the α parameter in CαC-integrals for application in fuzzy rule-based classification systems
(Springer, 2020) Lucca, Giancarlo; Sanz Delgado, José Antonio; Pereira Dimuro, Graçaliz; Bedregal, Benjamin; Bustince Sola, Humberto; Estatistika, Informatika eta Matematika; Institute of Smart Cities - ISC; Estadística, Informática y Matemáticas
In this paper, we consider the concept of extended Choquet integral generalized by a copula, called CC-integral. In particular, we adopt a CC-integral that uses a copula defined by a parameter α, which behavior was tested in a previous work using different fixed values. In this contribution, we propose an extension of this method by learning the best value for the parameter α using a genetic algorithm. This new proposal is applied in the fuzzy reasoning method of fuzzy rule-based classification systems in such a way that, for each class, the most suitable value of the parameter α is obtained, which can lead to an improvement on the system's performance. In the experimental study, we test the performance of 4 different so called CαC-integrals, comparing the results obtained when using fixed values for the parameter α against the results provided by our new evolutionary approach. From the obtained results, it is possible to conclude that the genetic learning of the parameter α is statistically superior than the fixed one for two copulas. Moreover, in general, the accuracy achieved in test is superior than that of the fixed approach in all functions. We also compare the quality of this approach with related approaches, showing that the methodology proposed in this work provides competitive results. Therefore, we demonstrate that CαC-integrals with α learned genetically can be considered as a good alternative to be used in fuzzy rule-based classification systems.
Open Access
Automatic detection of high-voltage power lines in LiDAR surveys using data mining techniques
(Springer, 2020) Chasco Hernández, Daniel; Sanz Delgado, José Antonio; García Morales, Víctor; Álvarez-Mozos, Jesús; Ingeniería; Estadística, Informática y Matemáticas; Ingeniaritza; Estatistika, Informatika eta Matematika
The correct classification of power lines in LiDAR point clouds has attracted the interest of the mapping community in the last years. The objective of this research is the detection and automatic extraction of high-voltage transmission lines from LiDAR data using data mining techniques. With this aim, a Single Photon LiDAR (SPL) survey acquired over the region of Navarre (Spain) in 2017 was used, with a mean point density of 14 pt/m2. Different data mining techniques were evaluated, including decision trees (C4.5 and CART) and ensemble learning algorithms (Random Forests, Bagging and AdaBoost). Fifteen test sites were studied corresponding to areas with high-voltage power lines over different conditions regarding the underlying vegetation and topography. For these sites 92,104 LiDAR points were identified as power lines and more than 4M points as not power lines using existing cartography. This dataset was randomly split in train and test sets and then balanced two obtain a similar amount of data for the two classes. The results obtained show the importance of balancing the training data with improvements in accuracy of ~10% with respect to the imbalanced case. Accuracies higher than 87% were obtained in all balanced cases, with particularly successful results for ensemble learning techniques, being AdaBoost the technique with the highest accuracy 91%. These results suggest that the combination of SPL surveys and data mining tools can be successfully used for the operational mapping of high voltage power lines.
Open Access
Improving the performance of fuzzy rule-based classification systems based on a nonaveraging generalization of CC-integrals named C-F1F2-integrals
(IEEE, 2019) Lucca, Giancarlo; Pereira Dimuro, Graçaliz; Fernández Fernández, Francisco Javier; Bustince Sola, Humberto; Bedregal, Benjamin; Sanz Delgado, José Antonio; Estatistika, Informatika eta Matematika; Institute of Smart Cities - ISC; Estadística, Informática y Matemáticas
A key component of fuzzy rule-based classification systems (FRBCS) is the fuzzy reasoning method (FRM) since it infers the class predicted for new examples. A crucial stage in any FRM is the way in which the information given by the fired rules during the inference process is aggregated. A widely used FRM is the winning rule, which applies the maximum to accomplish this aggregation. The maximum is an averaging operator, which means that its result is within the range delimited by the minimum and the maximum of the aggregated values. Recently, new averaging operators based on generalizations of the Choquet integral have been proposed to perform this aggregation process. However, the most accurate FRBCSs use the FRM known as additive combination that considers the normalized sum as the aggregation operator, which is nonaveraging. For this reason, this paper is aimed at introducing a new nonaveraging operator named C-F1F2-integral, which is a generalization of the Choquet-like Copula-based integral (CC-integral). C-F1F2-integrals present the desired properties of an aggregation-like operator since they satisfy appropriate boundary conditions and have some kind of increasingness property. We show that C-F1F2 -integrals, when used to cope with classification problems, enhance the results of the previous averaging generalizations of the Choquet integral and provide competitive results (even better) when compared with state-of-the-art FRBCSs.
Open Access
Interval-valued aggregation functions based on moderate deviations applied to motor-imagery-based brain computer interface
(IEEE, 2021) Fumanal Idocin, Javier; Takáč, Zdenko; Fernández Fernández, Francisco Javier; Sanz Delgado, José Antonio; Goyena Baroja, Harkaitz; Lin, Chin-Teng; Wang, Yu-Kai; Bustince Sola, Humberto; Estatistika, Informatika eta Matematika; Institute of Smart Cities - ISC; Estadística, Informática y Matemáticas
In this work we develop moderate deviation functions to measure similarity and dissimilarity among a set of given interval-valued data to construct interval-valued aggregation functions, and we apply these functions in two MotorImagery Brain Computer Interface (MI-BCI) systems to classify electroencephalography signals. To do so, we introduce the notion of interval-valued moderate deviation function and, in particular, we study those interval-valued moderate deviation functions which preserve the width of the input intervals. In order to apply them in a MI-BCI system, we first use fuzzy implication operators to measure the uncertainty linked to the output of each classifier in the ensemble of the system, and then we perform the decision making phase using the new interval-valued aggregation functions. We have tested the goodness of our proposal in two MI-BCI frameworks, obtaining better results than those obtained using other numerical aggregation and interval-valued OWA operators, and obtaining competitive results versus some non aggregation-based frameworks.
Restricted
Herramienta para la adquisición de imágenes y detección del movimiento
(2006) Sanz Delgado, José Antonio; Escuela Técnica Superior de Ingenieros Industriales y de Telecomunicación; Telekomunikazio eta Industria Ingeniarien Goi Mailako Eskola Teknikoa; Automática y Computación; Automatika eta Konputazioa
Open Access
Motor-imagery-based brain-computer interface using signal derivation and aggregation functions
(IEEE, 2021) Fumanal Idocin, Javier; Wang, Yu-Kai; Lin, Chin-Teng; Fernández Fernández, Francisco Javier; Sanz Delgado, José Antonio; Bustince Sola, Humberto; Estatistika, Informatika eta Matematika; Institute of Smart Cities - ISC; Estadística, Informática y Matemáticas
Brain Computer Interface (BCI) technologies are popular methods of communication between the human brain and external devices. One of the most popular approaches to BCI is Motor Imagery (MI). In BCI applications, the ElectroEncephaloGraphy (EEG) is a very popular measurement for brain dynamics because of its non-invasive nature. Although there is a high interest in the BCI topic, the performance of existing systems is still far from ideal, due to the difficulty of performing pattern recognition tasks in EEG signals. This difficulty lies in the selection of the correct EEG channels, the signal-tonoise ratio of these signals and how to discern the redundant information among them. BCI systems are composed of a wide range of components that perform signal pre-processing, feature extraction and decision making. In this paper, we define a new BCI Framework, named Enhanced Fusion Framework, where we propose three different ideas to improve the existing MI-based BCI frameworks. Firstly, we include an additional pre-processing step of the signal: a differentiation of the EEG signal that makes it time-invariant. Secondly, we add an additional frequency band as feature for the system: the Sensory Motor Rhythm band, and we show its effect on the performance of the system. Finally, we make a profound study of how to make the final decision in the system. We propose the usage of both up to six types of different classifiers and a wide range of aggregation functions (including classical aggregations, Choquet and Sugeno integrals and their extensions and overlap functions) to fuse the information given by the considered classifiers. We have tested this new system on a dataset of 20 volunteers performing motor imagery-based braincomputer interface experiments. On this dataset, the new system achieved a 88.80% of accuracy. We also propose an optimized version of our system that is able to obtain up to 90, 76%. Furthermore, we find that the pair Choquet/Sugeno integrals and overlap functions are the ones providing the best results.