Skip to main content

SMART-DASCI: MODELOS DE CIENCIA DE DATOS E INTELIGENCIA COMPUTACIONAL: TENDIENDO EL PUENTE ENTRE BIG DATA Y SMART DATA

TIN2017-89517-P

•
Funding agency name Agencia Estatal de Investigación
Funding agency acronym AEI
Program Programa Estatal de Fomento de la Investigación Científica y Técnica de Excelencia
Subprogram Subprograma Estatal de Generación de Conocimiento
Call Proyectos de I+D (Excelencia / Generación de Conocimiento)
Call year 2017
State Plan 2017-2020 Plan Estatal de Investigación Científica y Técnica y de Innovación
Beneficiary centre UNIVERSIDAD DE GRANADA

Resultados relacionados

Resultados totales (Incluyendo duplicados): 7
Encontrada(s) 1 página(s)

RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Irony Detection in Twitter with Imbalanced Class Distributions

  • Hernandez-Farias, Delia Irazu
  • Prati, Ronaldo
  • Herrera, Francisco
  • Rosso, Paolo|||0000-0002-8922-1242
[EN] Irony detection is a not trivial problem and can help to improve natural language processing tasks as sentiment analysis. When dealing with social media data in real scenarios, an important issue to address is data skew, i.e. the imbalance between available ironic and non-ironic samples available. In this work, the main objective is to address irony detection in Twitter considering various degrees of imbalanced distribution between classes. We rely on the emotIDM irony detection model. We evaluated it against both benchmark corpora and skewed Twitter datasets collected to simulate a realistic distribution of ironic tweets. We carry out a set of classification experiments aimed to determine the impact of class imbalance on detecting irony, and we evaluate the performance of irony detection when different scenarios are considered. We experiment with a set of classifiers applying class imbalance techniques to compensate class distribution. Our results indicate that by using such techniques, it is possible to improve the performance of irony detection in imbalanced class scenarios., The first author was funded by CONACYT project FC-2016/2410. Ronaldo Prati was supported by the São Paulo State (Brazil) research council FAPESP under project 2015/20606-6. Francisco Herrera was partially supported by the Spanish National Research Project TIN2017-89517-P. The work of Paolo Rosso was partially supported by the Spanish MICINN under the research project MISMIS (PGC2018-096212- B-C31) and by the Generalitat Valenciana under the grant PROMETEO/2019/121.
RUA. Repositorio Institucional de la Universidad de Alicante
Publication Otros (Other)

TimeSpec4LULC: a global multispectral time series database for training LULC mapping models with machine learning

  • Khaldi, Rohaifa
  • Alcaraz-Segura, Domingo
  • Guirado, Emilio
  • Benhammou, Yassir
  • El Afia, Abdellatif
  • Herrera, Francisco
  • Tabik, Siham
Land use and land cover (LULC) mapping are of paramount importance to monitor and understand the structure and dynamics of the Earth system. One of the most promising ways to create accurate global LULC maps is by building good quality state-of-the-art machine learning models. Building such models requires large and global datasets of annotated time series of satellite images, which are not available yet. This paper presents TimeSpec4LULC (https://doi.org/10.5281/zenodo.5913554; Khaldi et al., 2022), a smart open-source global dataset of multispectral time series for 29 LULC classes ready to train machine learning models. TimeSpec4LULC was built based on the seven spectral bands of the MODIS sensors at 500 m resolution, from 2000 to 2021, and was annotated using spatial–temporal agreement across the 15 global LULC products available in Google Earth Engine (GEE). The 22-year monthly time series of the seven bands were created globally by (1) applying different spatial–temporal quality assessment filters on MODIS Terra and Aqua satellites; (2) aggregating their original 8 d temporal granularity into monthly composites; (3) merging Terra + Aqua data into a combined time series; and (4) extracting, at the pixel level, 6 076 531 time series of size 262 for the seven bands along with a set of metadata: geographic coordinates, country and departmental divisions, spatial–temporal consistency across LULC products, temporal data availability, and the global human modification index. A balanced subset of the original dataset was also provided by selecting 1000 evenly distributed samples from each class such that they are representative of the entire globe. To assess the annotation quality of the dataset, a sample of pixels, evenly distributed around the world from each LULC class, was selected and validated by experts using very high resolution images from both Google Earth and Bing Maps imagery. This smartly, pre-processed, and annotated dataset is targeted towards scientific users interested in developing various machine learning models, including deep learning networks, to perform global LULC mapping.
RUA. Repositorio Institucional de la Universidad de Alicante
Publication Otros (Other)

Tree Cover Estimation in Global Drylands from Space Using Deep Learning

  • Guirado, Emilio
  • Alcaraz-Segura, Domingo
  • Cabello, Javier
  • Puertas-Ruíz, Sergio
  • Herrera, Francisco
  • Tabik, Siham
Accurate tree cover mapping is of paramount importance in many fields, from biodiversity conservation to carbon stock estimation, ecohydrology, erosion control, or Earth system modelling. Despite this importance, there is still uncertainty about global forest cover, particularly in drylands. Recently, the Food and Agriculture Organization of the United Nations (FAO) conducted a costly global assessment of dryland forest cover through the visual interpretation of orthoimages using the Collect Earth software, involving hundreds of operators from around the world. Our study proposes a new automatic method for estimating tree cover using artificial intelligence and free orthoimages. Our results show that our tree cover classification model, based on convolutional neural networks (CNN), is 23% more accurate than the manual visual interpretation used by FAO, reaching up to 79% overall accuracy. The smallest differences between the two methods occurred in the driest regions, but disagreement increased with the percentage of tree cover. The application of CNNs could be used to improve and reduce the cost of tree cover maps from the local to the global scale, with broad implications for research and management.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publication Artículo científico (JournalArticle)

Experiencias y recursos TIC en la enseñanza y aprendizaje de la probabilidad

  • Beltrán-Pellicer, Pablo
  • Begué, Nuria
  • Roldán López de Hierro, Antonio Francisco
En este artículo se recopilan y analizan algunos de los recursos TIC existentes que pueden incorporarse a procesos de enseñanza y aprendizaje de la probabilidad. Se realiza una revisión bibliográfica a partir de la cual se exponen novedades que atañen a la cuestión tecnológica y que han propiciado la aparición de ciertos recursos que facilitan la negociación de significados en el aula. De esta manera, además de la potencia que ofrece la simulación para explorar sistemáticamente modelizaciones y extender el número de repeticiones de los experimentos, veremos que se pueden plantear secuencias didácticas que generan dinámicas de aula que favorecen el uso del lenguaje y que permiten poner en juego el razonamiento estocástico.
Academica-e. Repositorio Institucional de la Universidad Pública de Navarra
Publication Artículo científico (JournalArticle)

Extension of restricted equivalence functions and similarity measures for type-2 fuzzy sets

  • Miguel Turullols, Laura de
  • Santiago, Regivan
  • Wagner, Christian
  • Garibaldi, Jonathan M.
  • Takáč, Zdenko
  • Roldán López de Hierro, Antonio Francisco
  • Bustince Sola, Humberto
In this work we generalize the notion of restricted equivalence function for type-2 fuzzy sets, leading to the notion of extended restricted equivalence functions. We also study how under suitable conditions, these new functions recover the standard axioms for restricted equivalence functions in the real setting. Extended restricted equivalence functions allow us to compare any two general type-2 fuzzy sets and to generate a similarity measure for type-2 fuzzy sets. The result of this similarity is a fuzzy set on the same referential set (i.e., domain) as the considered type-2 fuzzy set. The latter is crucial for applications such as explainable AI and decision making, as it enables an intuitive interpretation of the similarity within the domain-specific context of the fuzzy sets. We show how this measure can be used to compare type-2 fuzzy sets with different membership functions in such a way that the uncertainty linked to type-2 fuzzy sets is not lost. This is achieved by generating a fuzzy set rather than a single numerical value. Furthermore, we also show how to obtain a numerical value for discrete referential sets., This work has been supported by the Research Services of Universidad Pública de Navarra as well as by the Projects PID2019-108392GBI00, financed by MCIN/AEI/10.13039/501100011033), TIN2017-89517-P, by grant VEGA 1/0267/21 and UK EPSRC grant EP/P011918/1.
Academica-e. Repositorio Institucional de la Universidad Pública de Navarra
Publication Artículo científico (JournalArticle)

Curve-based monotonicity: a generalization of directional monotonicity

  • Roldán López de Hierro, Antonio Francisco
  • Sesma Sara, Mikel
  • Špirková, Jana
  • Lafuente López, Julio
  • Pradera, Ana
  • Mesiar, Radko
  • Bustince Sola, Humberto
In this work we propose a generalization of the notion of directional monotonicity. Instead of considering increasingness or decreasingness along rays, we allow more general paths defined by curves in the n-dimensional space. These considerations lead us to the notion of α-monotonicity, where α is the corresponding curve. We study several theoretical properties of α-monotonicity and relate it to other notions of monotonicity, such as weak monotonicity and directional monotonicity., This work is supported by the research group FQM268 of Junta de Andalucía, by the projects TIN2017-89517-P and TIN2016-77356-P (AEI/FEDER, UE), by the the Slovak Scientic Grant Agency VEGA no. 1/0093/17 Identication of risk factors and their impact on products of the insurance and savings schemes, by Slovak grant APVV- 14-0013, and by Czech Project LQ1602 \IT4Innovations excellence in science.
Academica-e. Repositorio Institucional de la Universidad Pública de Navarra
Publication Artículo científico (JournalArticle)

Normal-weight obesity is associated with poorer cardiometabolic profile and lower physical fitness levels in children and adolescents

  • García Hermoso, Antonio
  • Agostinis-Sobrinho, César
  • Camargo Villalba, Gloria Eugenia
  • González Jiménez, Nubia Mercedes
  • Izquierdo Redín, Mikel
  • Correa Bautista, Jorge Enrique
  • Ramírez Vélez, Robinson
Normal-weight obesity (NWO) syndrome has been shown to be associated with cardiometabolic dysfunction. However, little is known regarding this potential relationship in Latin American children and adolescents. The aim of this study was two-fold: (i) to investigate whether Colombian youth with NWO syndrome have a poorer cardiometabolic profile and physical fitness performance than normal-weight lean (NWL) peers; and (ii) to determine if physical fitness levels are related to prevalence of normal-weight obesity in youth. This was an analytical cross-sectional study of 1919 youths (9–179 years old, 53.0% girls) in the capital area of Colombia. NWO was defined as a body mass index < 25 kg/m2 and a validated body fat percentage above the sex-age-specific 90th percentile for Colombian children and adolescents. Body fat was estimated using bioelectrical impedance analysis, cardiorespiratory fitness (CRF) was estimated using the 20-meter shuttle run test, and muscular fitness with the handgrip test. Biochemical profile blood samples were collected for cardiometabolic risk factors. After adjusting for chronological age, pubertal stage, and Mediterranean diet adherence, the NWO group (boys and girls) had significantly higher values for cardiometabolic risk factors, and waist circumference (WC) than the NWL group. The prevalence of NWO was lower in youth classified with healthy CRF (boys, odds ratio (OR) = 0.54, 95% confidence interval (CI) 0.37 to 0.78; girls, OR = 0.35, 95% CI 0.24 to 0.50), p < 0.001. Our findings indicate that using only body mass index for the assessment of cardiometabolic risk likely misrepresents true adiposity and suggest the need to include the assessment of body fat in the routine clinical evaluation of individuals during childhood and adolescence., A.G.-H. is a Miguel Servet Fellow (Instituto de Salud Carlos III-FSE—CP18/0150). R.R.-V. is funded in part by a postdoctotal fellowship grant ID 420/2019 from the Universidad Pública de Navarra, Spain. M.I. is funded in part by research grant PI17/01814 from the Ministerio de Economía, Industria y Competitividad de España (ISCIII, FEDER). The FUPRECOL Study was possible due to the financial support provided by the Instituto Colombiano para el Desarrollo de la Ciencia y la Tecnología 'Francisco José de Caldas' COLCIENCIAS (Contract No. 671-2014 Code 122265743978) and Universidad de Boyacá (Code N RECT 47).