Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 12
Encontrada(s) 1 página(s)

Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

Effects of data time lag in a decision-making system using machine learning for pork price prediction

  • Suaza-Medina, Mario E.
  • Zarazaga-Soria, F. Javier
  • Pinilla-Lopez, Jorge
  • Lopez-Pellicer, Francisco J.
  • Lacasta, Javier
Spain is the third-largest producer of pork meat in the world, and many farms in several regions depend on the evolution of this market. However, the current pricing system is unfair, as some actors have better market information than others. In this context, historical pricing is an easy-to-find and affordable data source that can help all agents to be better informed. However, the time lag in data acquisition can affect their pricing decisions. In this paper, we study the effect that data acquisition delay has on a price prediction system using multiple prediction algorithms. We describe the integration of the best proposal into a decision support system prototype and test it in a real-case scenario. Specifically, we use public data from the most important regional pork meat markets in Spain published by the Ministry of Agriculture with a two-week delay and subscription-based data of the same markets obtained on the same day. The results show that the error difference between the best public and data subscription models is 0.6 Euro cents in favour of the data without delay. The market dimension makes these differences significant in the supply chain, giving pricing agents a better tool to negotiate market prices.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

Providing a Common Approach to Designing Dataset-Based Learning Activities Based on a Literature Review

  • Díaz-Pérez, Lucía
  • Lopez-Pellicer, Francisco J.
  • Brufau, Pilar
  • Lacasta, Javier
  • Trillo-Lado, Raquel
  • Yagüe-Fabra, José A.
  • Zarazaga-Soria, Francisco Javier
While there are references available in the literature regarding learning experiences with Dataset-Based Learning (DBL) approaches, there is a noticeable absence of a standardized model for designing DBL activities. This gap was identified in this work after performing a systematic literature review (SLR). In contrast to other active learning methodologies, the lack of a common framework for the DBL methodology makes it challenging to compare different DBL approaches. This paper highlights the knowledge gap in the methodology for designing DBL activities and aims to provide a common approach for sharing the view and details about what DBL entails in higher education and how to design a DBL activity. Additionally, we illustrate these concepts with three case studies in different engineering fields. Based on the SLR results and the review of additional literature, this work defines DBL as an active teaching methodology that focuses on using datasets to promote the learning and understanding of specific concepts and skills. These datasets should contain real data presented in different formats. As a common starting point, in a DBL lesson, the dataset not only provides information and context in the activity statement but also serves as the material to work with, and the solution to the activity is entirely extracted from the information contained in the dataset.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

Identifying the Evolution of Open Government Data Initiatives and Their User Engagement

  • Aziz, Abdul
  • Herrera-Murillo, Dagoberto José
  • Nogueras-Iso, Javier
  • Lacasta, Javier
  • Lopez-Pellicer, Francisco J.
Over the last decade, many Open Data initiatives have been launched by public administrations to promote transparency and reuse of data. However, it is not easy to assess the impact of data availability from the perspective of user communities. Although some Open Data portals provide mechanisms for user feedback through dedicated discussion forums or web forms, and some of the user experiences are reported directly in the portals, there is no consistent way to compare user feedback in different data initiatives. To overcome the difficulty of assessing user impact, this paper examines the activity generated by Open Data initiatives through the social network X (formerly Twitter): a forum used by all types of stakeholders and publicly available for consistent analysis. This work proposes a methodology for analysing the evolution of Open Government Data initiatives and their user engagement along a temporal period. First, a set of variables are collected to describe the main features of Open Data initiatives and their associated social network activity. Then, to analyse these collected data from a multidimensional and temporal perspective, we apply the well-known technique of self-organizing maps to find hidden correlations between the status of different initiatives in the analysed period. Finally, as the number of map nodes is still too big to identify clear levels of maturity, a clustering algorithm is applied to group initiatives with a similar evolution status. The feasibility of this methodology has been tested by analysing 27 European Open Government Data portals between 2017 and 2021.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

An empirical study of the limitations of minimum bounding boxes for defining the extent of geospatial resources: the use of DGGS and other alternatives for improving the performance of spatial searches

  • Martín-Segura, S.
  • López-Pellicer, F. J.
  • Béjar, R.
  • Nogueras-Iso, J.
  • Zarazaga-Soria, F. J
A Minimum Bounding Box (MBB) is a rectangle which bounds a geographic feature or dataset. It is commonly used in spatial information systems as a simplified way of describing the spatial extent of a resource. MBBs are typically indexed for searching and discovering resources relevant to a given geographic area of interest. However, this simplification leads to a loss of precision in the description of the extent and can affect the overall precision of the search results. We propose an alternative technique for describing the spatial extent based on the use of DGGS tiles. To measure the precision improvements offered by our method, we designed and implemented an empirical method for evaluating the average precision, and applied it to three different systems: one based on MBB, another on Convex Hull, and ours based on DGGS. The three methods were evaluated with the same test collection obtained from some of the main European geospatial data catalogues compliant with the INSPIRE directive. The results showed that our method outperformed the other two. Where the catalogue average precision of the MBB search scenarios is between 73% and 97%, the DGGS is between 96% and 99%. Additionally, we propose a realistic method of transitioning from the current technologies to the technology we are proposing, considering the current state of the spatial data infrastructures.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

First steps towards a platform for the analysis of civil law documentary heritage = Primeros pasos hacia una plataforma para el análisis del patrimonio documental de derecho civil

  • Neji, Hala
  • Nogueras-Iso, Javier
  • García-Marco, Francisco Javier
  • Bayod López, María del Carmen
The documentary heritage about civil law is an important asset whose study allows us to learn about the political, social and cultural context of the period referred in historical documents. This paper presents the design of a prototype platform to sup-port researchers in the analysis of civil law docu-mentary heritage. Our platform involves creating an online version of these materials, making them more accessible. The platform provides automatic assistants for the transcription, translation and extraction of specific information items associated to civil law concepts (voices) such as citations to external sources and named entities (locations, persons, and organizations) to identify better their context. The feasibility of this platform has been tested with the processing of a doctrinal work writ-ten by Miguel del Molino, a well-known civil law expert in XV century in the Aragon kingdom. El patrimonio documental sobre derecho civil es un importante activo cuyo estudio permite conocer el contexto político, social y cultural de la época a la que se refieren los documentos históricos. Este trabajo presenta el diseño de un prototipo de plataforma para apoyar a los investigadores en el análisis del patrimonio documental sobre derecho civil. Nuestra plataforma consiste en crear una versión en línea de estos materiales, haciéndolos más accesibles. La plataforma proporciona asistentes automáticos para la transcripción, traducción y extracción de elementos de información específicos asociados a conceptos de derecho civil (voces) como citas a fuentes externas y entidades con nombre (lugares, personas y organizaciones) para identificar mejor su contexto. La viabilidad de esta plataforma se ha puesto a prueba con el tratamiento de una obra doctrinal escrita por Miguel del Molino, un conocido experto en derecho civil del siglo XV en el reino de Aragón.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

Detection of changes in the heat emissions signature of buildings related to indoor activity using publicly available satellite data

  • Suaza-Medina, Mario E.
  • Lacasta, Javier
  • López-Pellicer, Francisco J.
  • Béjar, Rubén
  • Zarazaga-Soria, F. Javier
Monitoring human activities in remote areas presents significant challenges due to lacking communication networks and infrastructure. In this context, using publicly available satellite imagery offers a cost-effective solution, as it enables the identification of changes in these areas. However, specific scenarios make detection more complicated. One such scenario is detecting indoor activity within buildings in remote areas. Walls and roofs create barriers for most sensors. Nevertheless, activities inside buildings can be associated with heat emissions, which specific remote sensors can detect. Unfortunately, publicly available satellite data does not include information from such sensors. In light of this limitation, this study investigates the opportunity of using machine learning models to interpret public-available data. Specifically, we trained four machine learning models (XGBoost, LGBM, DNN, and CNN) using images from Sentinel-2 Band 12 (the sensor with the frequency range closest to the heat emission peak) and meteorological data (temperature). Our results show that these models can identify farm-building activity, with the XGBoost model achieving the highest accuracy of 0.96 by integrating satellite data and temperature information; the findings suggest that leveraging public satellite sensors can effectively detect human heat emissions and improve surveillance in remote areas, overcoming some limitations of traditional methods.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

A platform to support the fast development of digital twins for agricultural holdings

  • Laguna, Jorge
  • Suaza-Medina, Mario E.
  • Béjar, Rubén
  • Lacasta, Javier
  • Zarazaga-Soria, F. Javier
Industry 4.0 has advanced in agriculture through Smart Agriculture initiatives, yet open-field farming lags in the adoption of digital twins. Although digital twins have transformed manufacturing since 2011, their application in open-field farming remains limited by environmental variability, data scarcity, and financial constraints. This paper addresses four gaps: the lack of affordable platforms for small farms that dominate European agriculture; the need to manage agricultural complexity through data-driven models rather than the physical modelling approaches prevalent in non-agricultural sectors; the absence of open sources solutions adapted to agriculture’s slower innovation pace; the breach between technology and farmers. The platform features innovations in data workflow integration, open data incorporation, a cost-effective shared warehouse, and scalable data pipelines. To validate the proposed platform, a case study with two example digital twins mirroring two fields is conducted. This implementation ran efficiently on modest hardware (2 vCPUs, 4GB RAM). It achieved an average CPU usage of 60%, RAM usage of 2.5 GB, and a deployment time of around one minute. This helps lowering adoption barriers for small holdings and bridging the gap between basic monitoring and complex future systems.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

A framework for the acceptance testing of geospatial search engines

  • Herrera-Murillo, Dagoberto José
  • Nogueras-Iso, Javier
  • Abad-Power, Paloma
  • Latre, Miguel Á.
  • Lopez-Pellicer, Francisco J.
Geospatial search engines are an essential component of spatial data infrastructures and enable a broad spectrum of environmental applications. The back-end implementation of these search engines has evolved from traditional text-based information retrieval systems into more specialised search engines. However, to assess the actual improvement brought by this evolution, thorough testing is needed. The aim of this work is to propose a framework for the acceptance testing of geospatial search engines that assesses their functionality, effectiveness, and user-friendliness. For each quality attribute, the framework proposes different testing design techniques and guidelines for their practical implementation. To demonstrate its feasibility, it has been applied to the evaluation of a geospatial semantic search engine of the Spanish National Geographic Institute. The evaluated search engine showed a sufficient level of functionality and effectiveness. However, the usability results were barely satisfactory due to perceived problems associated with complexity, inconsistency, and low learnability.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

Collective Intelligence in Humanitarian Voluntary Geographic Information: The Case of the HOT Tasking Manager

  • Herrera-Murillo, Dagoberto José
  • Ochoa-Ortiz, Héctor
  • Ahmed, Umair
  • Lopez-Pellicer, Francisco J.
  • Re, Barbara
  • Polini, Andrea
  • Nogueras-Iso, Javier
Voluntary Geographic Information initiatives are transforming the disaster response landscape. Our research provides insights into how the concept of collective intelligence is accomplished in humanitarian mapping initiatives. The main source originates from the data obtained in 746 mapping projects organised by the Humanitarian OpenStreetMap Team between December 2021 and November 2023, where 38,893 contributors completed 312,289 mapping tasks. These data include detailed attributes of the contributors and the states the tasks go through. The methodology adopts a quantitative approach, including descriptive and inferential statistics, and standard process mining techniques. Our results indicate that, in general terms, in humanitarian mapping, a group of contributors from outside the area of interest perform straightforward mapping tasks with limited collaboration among them. The ‘wisdom’ of advanced contributors is the cornerstone that sustains the system. The discussion section elaborates on (1) how these findings suggest that humanitarian mapping projects effectively meet their short-term mapping objectives but fall short if more sustainable mapping objectives are sought and (2) possible strategies for better harnessing the collective intelligence of these efforts.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

Multivariate integration of time series with ML for corn price forecasting in Colombia

  • Beltran, Adelaida Ojeda
  • Suaza-Medina, Mario E.
  • Zarazaga-Soria, F. Javier
  • De-La-Hoz-Franco, Emiro
  • Escorcia-Gutierrez, José
The volatility of corn prices poses a significant challenge for both producers and policymakers. This study proposes a hybrid model that combines Extreme Gradient Boosting (XGBoost) and Light Gradient Boosting Machine (LightGBM), optimized through Particle Swarm Optimization with Cuckoo Search (PSO-CS), for accurate corn price forecasting. The approach integrates multivariate time series data, including local prices from the Atlántico market and international futures prices from the Chicago Board of Trade (CBOT). Empirical Mode Decomposition (EMD) is applied to enhance signal clarity and improve model performance. Model performance is assessed through sensitivity analysis and statistical comparison using the Diebold-Mariano (DM) test. The results demonstrate that the proposed ensemble outperforms both individual models and neural network combinations, achieving a Mean Absolute Percentage Error (MAPE) of 2.06.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

Applicability of process mining in usability tests: a case study for identifying user mental models in geospatial search engines

  • Herrera-Murillo, Dagoberto José
  • Abad-Power, Paloma
  • López-Pellicer, Francisco J.
  • Baldassarri, Sandra
  • Nogueras-Iso, Javier
A fundamental challenge in digital product design is ensuring that actual mental models of users align with the intended functionality of the system. When discrepancies arise, usability can suffer, leading to inefficient interactions and reduced adoption. Usability testing lets development teams identify design problems in digital products by collecting qualitative and quantitative information. However, this technique is often not able to provide a panoramic view of the interaction with the system, especially when dealing with complex interfaces such as those used in geospatial search engines and we need to analyse the quantitative data compiled during testing. This work proposes to actively incorporate process mining into usability testing. We discuss the implications of process mining on usability testing using a case study performed at the National Geographic Institute of Spain, where a new geospatial search engine was under development. Twenty-one participants, ranging from novice to expert users, were recruited to perform a search task using the new geospatial search engine. The findings reveal that the mental model of users leans towards the archetype of a regular search engine rather than fully utilising the geographic functionalities provided by the platform, as intended by its designers.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

Quality Issues in Crowdsourced Mapping: Microtask Aggregation in the Humanitarian OpenStreetMap Team Tasking Manager

  • Ochoa-Ortiz, Héctor
  • Herrera-Murillo, Dagoberto José
  • Re, Barbara
  • Lopez-Pellicer, Francisco J.
  • Nogueras-Iso, Javier
In crowdsourcing, dividing work into narrowly defined microtasks may affect the quality of the final product. This study examines this problem in the con text of humanitarian mapping initiatives coordinated using the Humanitarian OpenStreetMap Team Tasking Manager, analyzing 4619 projects and over 1.4 million microtasks. Using a combination of spatial statistical techniques and expert visual inspection, we identify two main issues derived from microtask aggregation: edge‐based and task‐wide distortions. Our findings reveal that the current microtasking model hinders the emergence of spatial collective intelligence, resulting in fragmented and inconsistent outputs that reduce the quality of the final data. Edge‐based issues are identified by observing differences in event distribution between edge and interior areas. Task‐wide issues are examined by computing the spatial autocorrelation of geometries within microtask areas. We propose actionable strategies to address these issues, including overlapping task boundaries and fostering implicit coordination among contributors.