Comunicaciones y ponencias de congresos DEIM - EIMS Biltzarretako komunikazioak eta txostenak

Permanent URI for this collection

http://hdl.handle.net/2454/29491

Browse

Now showing 1 - 20 of 92

Open Access
Mid-air contactless haptics to augment VR experiences
(Association for Computing Machinery, 2023) Ezcurdia Aguirre, Íñigo Fermín; Fernández Ortega, Unai Javier; Olaz Moratinos, Xabier; Marzo Pérez, Asier; Estadística, Informática y Matemáticas; Estatistika, Informatika eta Matematika; Institute of Smart Cities - ISC
We present four technologies to deliver contactless haptic stimuli for enriching Virtual Reality (VR) experiences. The technologies are electrostatic piloerection, focused light-induced heat, electric plasma, and ultrasound; the user does not require to wear or touch any device. We describe the working principle behind each technology and how these technologies can provide new exciting sensations in VR experiences. Additionally, we showcase a VR demo experience gathering all four remote haptic stimuli along a circuit for the users to experiment with these new sensations.
Open Access
A linearly implicit splitting method for solving time dependent semilinear reaction-diffusion systems
(Springer, 2020) Clavero, Carmelo; Jorge Ulecia, Juan Carlos; Estadística, Informática y Matemáticas; Estatistika, Informatika eta Matematika; Institute of Smart Cities - ISC
In this paper we deal with the efficient resolution of a coupled system of two one dimensional, time dependent, semilinear parabolic singularly perturbed partial differential equations of reaction-diffusion type, with distinct diffusion parameters which may have different orders of magnitude. The numerical method is based on a linearized version of the fractional implicit Euler method, which avoids the use of iterative methods, and a splitting by components to discretize in time; so, only tridiagonal linear systems are involved in the time integration process. Consequently, the computational cost of the proposed method is lower than classical schemes used for the same type of problems. The solution of this singularly perturbed problem features layers, what are resolved on an appropriate piecewise uniform mesh of Shishkin type. We show that the method is uniformly convergent of first order in time and of almost second order in space. Numerical results are presented to corroborate the theoretical results.
Open Access
Women, Science and Technology Chair—Promoting women’s careers in stem fields
(IEEE, 2023) Pérez Artieda, Miren Gurutze; Gómez Fernández, Marisol; Aranguren Garacochea, Patricia; Barrenechea Tartas, Edurne; Catalán Ros, Leyre; Díaz Lucas, Silvia; Jurío Munárriz, Aránzazu; Martínez Ramírez, Alicia; Millor Muruzábal, Nora; Ortiz Nicolás, Amalia; San Martín Biurrun, Idoia; Estadística, Informática y Matemáticas; Ingeniería; Ingeniería Eléctrica, Electrónica y de Comunicación; Estatistika, Informatika eta Matematika; Ingeniaritza; Ingeniaritza Elektrikoa, Elektronikoaren eta Telekomunikazio Ingeniaritzaren
The Chair of Women, Science and Technology of the Universidad Pública de Navarra (UPNA) aims to increase the participation of women in the fields of science and technology. Scientific culture and dissemination are the main focus of the different actions of the Chair. These activities include: the theatrical performance "Yo quiero ser científica", experimental workshops and conferences and exhibitions for all audiences and ages. More than 6.000 people have seen the play, more than 1.500 secondary school students have participated in the workshops and the audiovisual material has received more than 20.000 visits.
Open Access
Fuzzy integrals for edge detection
(Springer, 2023) Marco Detchart, Cedric; Lucca, Giancarlo; Pereira Dimuro, Graçaliz; Da Cruz Asmus, Tiago; López Molina, Carlos; Borges, Eduardo N.; Rincon, J. A.; Julian, Vicente; Bustince Sola, Humberto; Estadística, Informática y Matemáticas; Estatistika, Informatika eta Matematika
In this work, we compare different families of fuzzy integrals in the context of feature aggregation for edge detection. We analyze the behaviour of the Sugeno and Choquet integral and some of its generalizations. In addition, we study the influence of the fuzzy measure over the extracted image features. For testing purposes, we follow the Bezdek Breakdown Structure for edge detection and compare the different fuzzy integrals with some classical feature aggregation methods in the literature. The results of these experiments are analyzed and discussed in detail, providing insights into the strengths and weaknesses of each approach. The overall conclusion is that the configuration of the fuzzy measure does have a paramount effect on the results by the Sugeno integral, but also that satisfactory results can be obtained by sensibly tuning such parameter. The obtained results provide valuable guidance in choosing the appropriate family of fuzzy integrals and settings for specific applications. Overall, the proposed method shows promising results for edge detection and could be applied to other image-processing tasks.
Open Access
LevPet: a magnetic levitating spherical pet with affective reactions
(ACM, 2022) Sorbet Molina, Josune; Elizondo Martínez, Sonia; Iriarte Cárdenas, Naroa; Ortiz Nicolás, Amalia; Marzo Pérez, Asier; Estadística, Informática y Matemáticas; Estatistika, Informatika eta Matematika
LevPet combines affective computing and magnetic levitation to create an artificial levitating pet with affective responses and novel ways of moving to express emotions. Our interactive pet can recognise the user's emotional status using computer vision, and respond to it with a low-level empathy system based on mirroring behaviour. For example, if you approach it with a happy face, the pet will greet you and move in a nimble way. A repulsive magnetic levitator is attached to a mechanical stage controlled by a computer system. On top of it, there is the pet playground, where a house, a ping-pong ball,a xylophone and other accessories are placed. Two cameras allow to capture the user's face and the objects placed on the playground, so that the pet can interact with them. LevPet is an exploration of how to communicate internal state with only a levitating sphere; it is a platform for experimentation and an interactive demo that brings together an outer-worldly levitating metallic sphere with familiar things like emotions and a playground made of traditional items.
Open Access
On construction methods of (interval-valued) general grouping functions
(Springer, 2022) Pereira Dimuro, Graçaliz; Da Cruz Asmus, Tiago; Pinheiro, Jocivania; Santos, Helida; Borges, Eduardo N.; Lucca, Giancarlo; Rodríguez Martínez, Iosu; Mesiar, Radko; Bustince Sola, Humberto; Estadística, Informática y Matemáticas; Estatistika, Informatika eta Matematika
Recently, several theoretical and applied studies on grouping functions and overlap functions appeared in the literature, mainly because of their flexibility when comparing them with the popular aggregation operators t-conorms and t-norms, respectively. Additionally, they constitute richer classes of disjunction/conjunction operations than t-norms and t-conorms. In particular, grouping functions have been applied as the disjunction operator in several problems, like decision making based on fuzzy preference relations. In this case, when performing pairwise comparisons, grouping functions allow one to evaluate the measure of the amount of evidence in favor of either of two given alternatives. However, grouping functions are not associative. Then, in order to allow them to be applied in n-dimensional problems, such as the pooling layer of neural networks, some generalizations were introduced, namely, n-dimensional grouping functions and the more flexible general grouping functions, the latter for enlarging the scope of applications. Then, in order to h andle uncertainty on the definition of the membership functions in real-life problems, n-dimensional and general interval-valued grouping functions were proposed. This paper aims at providing new constructions methods of general (interval-valued) grouping functions, also providing some examples.
Open Access
Application and comparison of CC-integrals in business group decision making
(Springer, 2022) Wieczynski, Jonata; Lucca, Giancarlo; Borges, Eduardo N.; Pereira Dimuro, Graçaliz; Lourenzutti, Rodolfo; Bustince Sola, Humberto; Estadística, Informática y Matemáticas; Estatistika, Informatika eta Matematika
Optimized decisions is required by businesses (analysts) if they want to stay open. Even thought some of these are from the knowhow of the managers/executives, most of them can be described mathematically and solved (semi)-optimally by computers. The Group Modular Choquet Random Technique for Order of Preference by Similarity to Ideal Solution (GMC-RTOPSIS) is a Multi-Criteria Decision Making (MCDM) that was developed as a method to optimize the later types of problems, by being able to work with multiple heterogeneous data types and interaction among different criteria. On the other hand the Choquet integral is widely used in various fields, such as brain-computer interfaces and classification problems. With the introduction of the CC-integrals, this study presents the GMC-RTOPSIS method with CC-integrals. We applied 30 different CC-integrals in the method and analyzed its results using 3 different methods. We found that by modifying the decisionmaking method we allow for more flexibility and certainty in the choosing process.
Open Access
Content-aware image smoothing based on fuzzy clustering
(Springer, 2022) Antunes dos Santos, Felipe; López Molina, Carlos; Mir Fuentes, Arnau; Mendióroz Iriarte, Maite; Baets, Bernard de; Estadística, Informática y Matemáticas; Estatistika, Informatika eta Matematika
Literature contains a large variety of content-aware smoothing methods. As opposed to classical smoothing methods, content-aware ones intend to regularize the image while avoiding the loss of relevant visual information. In this work, we propose a novel approach to contentaware image smoothing based on fuzzy clustering, specifically the Spatial Fuzzy c-Means (SFCM) algorithm. We develop the proposal and put it to the test in the context of automatic analysis of immunohistochemistry imagery for neural tissue analysis.
Open Access
A framework for active contour initialization with application to liver segmentation in MRI
(Springer, 2022) Mir Torres, Arnau; Antunes dos Santos, Felipe; Fernández Fernández, Francisco Javier; López Molina, Carlos; Estadística, Informática y Matemáticas; Estatistika, Informatika eta Matematika
Object segmentation is a prominent low-level task in image processing and computer vision. A technique of special relevance within segmentation algorithms is active contour modeling. An active contour is a closed contour on an image which can be evolved to progressively fit the silhouette of certain area or object. Active contours shall be initialized as a closed contour at some position of the image, further evolving to precisely fit to the silhouette of the object of interest. While the evolution of the contour has been deeply studied in literature [5, 11], the study of strategies to define the initial location of the contour is rather absent from it. Typically, such contour is created as a small closed curve around an inner position in the object. However, literature contains no general-purpose algorithms to determine those inner positions, or to quantify their fitness. In fact, such points are frequently set manually by human experts, hence turning the segmentation process into a semi-supervised one. In this work, we present a method to find inner points in relevant object using spatial-tonal fuzzy clustering. Our proposal intends to detect dominant clusters of bright pixels, which are further used to identify candidate points or regions around which active contours can be initialized.
Open Access
Fuzzy clustering to encode contextual information in artistic image classification
(Springer, 2022) Fumanal Idocin, Javier; Takáč, Zdenko; Horanská, Lubomíra; Bustince Sola, Humberto; Cordón, Óscar; Estadística, Informática y Matemáticas; Estatistika, Informatika eta Matematika
Automatic art analysis comprises of utilizing diverse processing methods to classify and categorize works of art. When working with this kind of pictures, we have to take under consideration different considerations compared to classical picture handling, since works of art alter definitely depending on the creator, the scene delineated or their aesthetic fashion. This extra data improves the visual signals gotten from the images and can lead to better performance. However, this information needs to be modeled and embed alongside the visual features of the image. This is often performed utilizing deep learning models, but they are expensive to train. In this paper we utilize the Fuzzy C-Means algorithm to create a embedding strategy based on fuzzy memberships to extract relevant information from the clusters present in the contextual information. We extend an existing state-of-the-art art classification system utilizing this strategy to get a new version that presents similar results without training additional deep learning models.
Open Access
Verification system based on long-range iris and Graph Siamese Neural Networks
(ACM, 2022) Zola, Francesco; Fernandez-Carrasco, José Álvaro; Bruse, Jan Lukas; Galar Idoate, Mikel; Geradts, Zeno; Estadística, Informática y Matemáticas; Estatistika, Informatika eta Matematika; Institute of Smart Cities - ISC
Biometric systems represent valid solutions in tasks like user authentication and verification, since they are able to analyze physical and behavioural features with high precision. However, especially when physical biometrics are used, as is the case of iris recognition, they require specific hardware such as retina scanners, sensors, or HD cameras to achieve relevant results. At the same time, they require the users to be very close to the camera to extract high-resolution information. For this reason, in this work, we propose a novel approach that uses long-range (LR) distance images for implementing an iris verification system. More specifically, we present a novel methodology for converting LR iris images into graphs and then use Graph Siamese Neural Networks (GSNN) to predict whether two graphs belong to the same person. In this study, we not only describe this methodology but also evaluate how the spectral components of these images can be used for improving the graph extraction and the final classification task. Results demonstrate the suitability of this approach, encouraging the community to explore graph application in biometric systems.
Open Access
Space-time parallel methods for evolutionary reaction-diffusion problems
(Springer, 2023) Arrarás Ventura, Andrés; Gaspar, F. J.; Portero Egea, Laura; Rodrigo, C.; Estadística, Informática y Matemáticas; Estatistika, Informatika eta Matematika; Institute for Advanced Materials and Mathematics - INAMAT2
In recent years, the gradual saturation of parallelization in space has been a strongmotivation for the design and analysis of new parallel-in-time algorithms. Amongthese methods, the parareal algorithm, first introduced by Lions, Maday and Turinici[9], has received significant attention.
Open Access
Gender stereotyping impact in facial expression recognition
(Springer, 2023) Domínguez Catena, Iris; Paternain Dallo, Daniel; Galar Idoate, Mikel; Estadística, Informática y Matemáticas; Estatistika, Informatika eta Matematika; Institute of Smart Cities - ISC; Universidad Pública de Navarra / Nafarroako Unibertsitate Publikoa
Facial Expression Recognition (FER) uses images of faces to identify the emotional state of users, allowing for a closer interaction between humans and autonomous systems. Unfortunately, as the images naturally integrate some demographic information, such as apparent age, gender, and race of the subject, these systems are prone to demographic bias issues. In recent years, machine learning-based models have become the most popular approach to FER. These models require training on large datasets of facial expression images, and their generalization capabilities are strongly related to the characteristics of the dataset. In publicly available FER datasets, apparent gender representation is usually mostly balanced, but their representation in the individual label is not, embedding social stereotypes into the datasets and generating a potential for harm. Although this type of bias has been overlooked so far, it is important to understand the impact it may have in the context of FER. To do so, we use a popular FER dataset, FER+, to generate derivative datasets with different amounts of stereotypical bias by altering the gender proportions of certain labels. We then proceed to measure the discrepancy between the performance of the models trained on these datasets for the apparent gender groups. We observe a discrepancy in the recognition of certain emotions between genders of up to 29 % under the worst bias conditions. Our results also suggest a safety range for stereotypical bias in a dataset that does not appear to produce stereotypical bias in the resulting model. Our findings support the need for a thorough bias analysis of public datasets in problems like FER, where a global balance of demographic representation can still hide other types of bias that harm certain demographic groups.
Open Access
Avatarians: playing with your friends' data
(ACM, 2012) Marzo Pérez, Asier; Ardaiz Villanueva, Óscar; Estadística, Informática y Matemáticas; Estatistika, Informatika eta Matematika; Gobierno de Navarra / Nafarroako Gobernua
This article describes a new game mechanic called Game Entity Social Mapping (GESM) based on using social networking data fetched from a remote site about the player and his contacts to create characters, items or scenarios. A preliminary evaluation consisting of applying this mechanic to three different games was conducted. A small number of users tested those games to measure the enjoyment and learning about their contacts information.
Open Access
Analyzing the determinant characteristics for a good performance at enade brazilian exam stratified by teaching modality: face-to-face versus online
(SciTePress, 2022) Gondran, Eric; Lucca, Giancarlo; Berri, Rafael A.; Santos, Helida; Borges, Eduardo N.; Estadística, Informática y Matemáticas; Estatistika, Informatika eta Matematika
The National Student Performance Exam (ENADE) annually evaluates different Brazilian higher education courses. This exam considers both face-to-face and distance learning courses. Distance learning is growing increasingly, especially during the coronavirus (COVID-19) pandemic. This study applies different techniques for selecting ENADE 2018 database characteristics, like information gain, gain rate, symmetric uncertainty, Pearson correlation, and relief F. The objective of the work is to discover which personal and socioeconomic characteristics are decisive for the student's performance at ENADE, whether the student is in the context of Distance Education or face-to-face. It can be concluded, among other results, that: the father's level of education directly influences performance; the higher the income, the better the performance; and white students have better performance than black and brown-skinned ones. Thus, the results obtained in this study may initiate analyzes of public policies towards improving performance at ENADE.
Open Access
TipTrap: a co-located direct manipulation technique for acoustically levitated content
(ACM, 2022) Jankauskis, Eimontas; Elizondo Martínez, Sonia; Montano Murillo, Roberto; Marzo Pérez, Asier; Martinez Plasencia, Diego; Estadística, Informática y Matemáticas; Estatistika, Informatika eta Matematika
Acoustic levitation has emerged as a promising approach for mid-air displays, by using multiple levitated particles as 3D voxels, cloth and thread props, or high-speed tracer particles, under the promise of creating 3D displays that users can see, hear and feel with their bare eyes, ears and hands. However, interaction with this mid-air content always occurred at a distance, since external objects in the display volume (e.g. user’s hands) can disturb the acoustic fields and make the particles fall. This paper proposes TipTrap, a co-located direct manipulation technique for acoustically levitated particles. TipTrap leverages the reflection of ultrasound on the users’ skin and employs a closed-loop system to create functional acoustic traps 2.1 mm below the fingertips, and addresses its 3 basic stages: selection, manipulation and deselection. We use Finite-Differences Time Domain (FDTD) simulations to explain the principles enabling TipTrap, and explore how finger reflections and user strategies influence the quality of the traps (e.g. approaching direction, orientation and tracking errors), and use these results to design our technique. We then implement the technique, characterizing its performance with a robotic hand setup and finish with an exploration of the ability of TipTrap to manipulate different types of levitated content.
Open Access
Comparison of experiment and simulation of ultrasonic mid-air haptic forces
(IEEE, 2022) Morales González, Rafael; Georgiou, Orestis; Marzo Pérez, Asier; Frier, William; Estadística, Informática y Matemáticas; Estatistika, Informatika eta Matematika; Institute of Smart Cities - ISC
Ultrasound mid-air haptics is an emerging technology with many applications in human-computer interactions. Despite great advances in related hardware and software, physics models that predict the resulting forces on a surface (e.g., someone's hand) are either too simple (inaccurate) or too complex (computationally expensive). In this paper, we show that simple models are not sufficient when predicting the force on an experimental setup involving two prototype devices and a precision scale. Specifically, we demonstrate that our experimental measurements cannot be accurately predicted using a linear acoustic model.
Open Access
Multi-temporal data augmentation for high frequency satellite imagery: a case study in Sentinel-1 and Sentinel-2 building and road segmentation
(ISPRS, 2022) Ayala Lauroba, Christian; Aranda Magallón, Coral; Galar Idoate, Mikel; Estadística, Informática y Matemáticas; Estatistika, Informatika eta Matematika; Institute of Smart Cities - ISC
Semantic segmentation of remote sensing images has many practical applications such as urban planning or disaster assessment. Deep learning-based approaches have shown their usefulness in automatically segmenting large remote sensing images, helping to automatize these tasks. However, deep learning models require large amounts of labeled data to generalize well to unseen scenarios. The generation of global-scale remote sensing datasets with high intraclass variability presents a major challenge. For this reason, data augmentation techniques have been widely applied to artificially increase the size of the datasets. Among them, photometric data augmentation techniques such as random brightness, contrast, saturation, and hue have been traditionally applied aiming at improving the generalization against color spectrum variations, but they can have a negative effect on the model due to their synthetic nature. To solve this issue, sensors with high revisit times such as Sentinel-1 and Sentinel-2 can be exploited to realistically augment the dataset. Accordingly, this paper sets out a novel realistic multi-temporal color data augmentation technique. The proposed methodology has been evaluated in the building and road semantic segmentation tasks, considering a dataset composed of 38 Spanish cities. As a result, the experimental study shows the usefulness of the proposed multi-temporal data augmentation technique, which can be further improved with traditional photometric transformations.
Open Access
Analysing capacity challenges in the Multi-Airport System of Mexico City
(Dime University of Genoa, 2022) Mújica Mota, Miguel; Izco Berastegui, Irene; Faulín Fajardo, Javier; Estadística, Informática y Matemáticas; Estatistika, Informatika eta Matematika; Institute of Smart Cities - ISC
The relentless growth in Mexico City’s aviation traffic has inevitably strained capacity development of its airport, raising the dilemma between the possible solutions. In the present study, Mexico’s Multi-Airport System is subjected to analysis by means of multi-model simulation, focusing on the capacity-demand problem of the system. The methodology combines phases of modelling, data collection, simulation, experimental design, and analysis. Drawing a distinction from previous works involving two-airport systems. It also explores the challenges raised by the Covid-19 pandemic in Mexico City airport operations, with a discrete-event simulation model of a multi-airport system composed by three airports (MEX, TLC, and the new airport NLU). The study is including the latest data of flights, infrastructures, and layout collected in 2021. Therefore, the paper aims to answer to the question of whether the system will be able to cope with the expected demand in a short-, medium-, and long term by simulating three future scenarios based on aviation forecasts. The study reveals potential limitations of the system as time evolves and the feasibility of a joint operation to absorb the demand in such a big region like Mexico City
Open Access
Application of the Sugeno integral in fuzzy rule-based classification
(Springer, 2022) Wieczynski, Jonata; Lucca, Giancarlo; Borges, Eduardo N.; Pereira Dimuro, Graçaliz; Estadística, Informática y Matemáticas; Estatistika, Informatika eta Matematika
Fuzzy Rule-Based Classification System (FRBCS) is a well known technique to deal with classification problems. Recent studies have considered the usage of the Choquet integral and its generalizations to enhance the quality of such systems. Precisely, it was applied to the Fuzzy Reasoning Method (FRM) to aggregate the fired fuzzy rules when classify new data. On the other side, the Sugeno integral, another well known aggregation operator, obtained good results when applied to brain-computer interfaces. Those facts led to the present study in which we consider the Sugeno integral in classification problems. That is, the Sugeno integral is applied in the FRM of a widely used FRBCS and its performance is analyzed over 33 different datasets from the literature. In order to show the efficiency of this new approach, the obtained results are also compared to past studies involving the application of different aggregation functions. Finally, we perform a statistical analysis of the application.