Examinando por Autor "Montejo, Arturo"

Mostrando 1 - 2 de 2

A new soil quality index based on morpho-pedological indicators as a site-specific web service applied to olive groves in the Province of Jaen (South Spain)
(Elsevier, 2018-03) Calero-González, Julio; Aranda-Sanjuán, Víctor; Montejo, Arturo; Martín-García, Juan Manuel
Soil quality has become a fundamental concept in soil science and agriculture, but it can be difficult to apply its theoretical and experimental approaches to poorly surveyed zones where precision techniques are far from being applied. In this paper, we propose a new technique that enables little-used qualitative morpho-pedological data to be managed and integrated into a single Field Soil Quality Index (FSQI). Nonlinear Principal Component Analysis (NLPCA), a technique able to handle categorical data, is applied here to deal with morpho-pedological indicators. When categorical values are transformed, they can be properly analyzed and interpreted. This procedure requires less expert knowledge, so it can help soil quality assessments by non-experts. We applied the FSQI protocol to soils in the most important olive-growing area in the world, Jaen Province (Southern Spain), which has serious problems with soil degradation and erosion. First, a soil database for the study area was compiled, including 18 morphological attributes for 131 surface horizons belonging to eight Land Use Types. Secondly, the NLPCA provides optimal scalings and attribute weights that transform and integrate morphological indicators into a simple weighted additive index (FSQI). Thirdly, the scaling functions and weights found were applied to the same attributes of an evaluation set comparing two soil management types (conventional vs. organic) in olive groves. The FSQI means for the first (conventional) were significantly lower than in the organic groves (0.278 vs. 0.463, P < .05), which supports the validity of the index. A site-specific FSQI web service has been created to assist in decision-making in the study area, whose methodology can be generalized to other zones and crops.
Identification of Complex Words in the Academic Domain in Spanish
(2025-03-12) Ortíz-Zambrano, Jenny Alexandra; Montejo, Arturo; Universidad de Jaén. Departamento de Informática
Esta tesis doctoral aborda la identificación de palabras complejas en textos académicos en español, clave para mejorar la comprensión lectora, especialmente para no nativos o personas con dificultades de lectura. El objetivo principal es desarrollar y evaluar metodologías avanzadas que identifiquen y predigan la complejidad léxica. Se integran características lingüísticas (morfológicas, sintácticas, semánticas) en algoritmos de aprendizaje automático clásico (SVM, árboles de decisión, Random Forests) y redes neuronales profundas (modelos Transformer). Además, se exploran técnicas no supervisadas, como modelos generativos autoregresivos, para la predicción de complejidad. Los experimentos, realizados en español e inglés, muestran que la combinación de características lingüísticas con modelos de deep learning mejora la precisión en la identificación de palabras complejas. Asimismo, se desarrollan nuevos corpus de referencia en español, proporcionando recursos valiosos para futuras investigaciones. La tesis ofrece un enfoque integral que favorece la accesibilidad y comprensión en contextos académicos multilingües This doctoral thesis addresses the identification of complex words in academic texts in Spanish, crucial for improving reading comprehension, especially for non-native speakers or individuals with reading difficulties. The main objective is to develop and evaluate advanced methodologies to identify and predict lexical complexity. Linguistic features (morphological, syntactic, semantic) are integrated into classical machine learning algorithms (SVM, decision trees, Random Forests) and deep neural networks (Transformer models). Additionally, unsupervised techniques, such as generative autoregressive models, are explored for complexity prediction. Experiments conducted in both Spanish and English show that combining linguistic features with deep learning models enhances accuracy in identifying complex words. Furthermore, new reference corpora in Spanish are developed, providing valuable resources for future research. The thesis offers a comprehensive approach that improves accessibility and comprehension in multilingual academic contexts

RUJA: Repositorio Institucional de Producción Científica

Examinando por Autor "Montejo, Arturo"