Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 54
Encontrada(s) 1 página(s)

RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

An Adaptive LoRa-Based Edge Architecture for Data Sensing and Collection in Natural Parks

  • Cecilia-Canales, José María|||0000-0001-5648-214X
  • Arratia-Uribe, Benjamín Andrés|||0000-0001-7869-053X
  • Rosas-Olivos, Erika Susana
  • Martín Furones, Ángel Esteban|||0000-0001-9379-0694
  • Perles, Angel|||0000-0002-5782-4284
  • Posadas-Yagüe, Juan-Luis|||0000-0002-5017-8689
  • Manzoni, Pietro|||0000-0003-3753-0403
[EN] This article introduces the design of a flexible IoT/Edge architecture to overcome the challenges of deploying advanced sensors in remote settings such as natural parks. These environments demand reliable communication and considerable computational resources to manage the extensive real-time data from IoT devices like sensors and cameras. Our approach combines two LoRa-based protocols to efficiently handle large data blocks and ensure long-range communication, conserving energy and maintaining data integrity crucial for integrating sophisticated sensors with conventional IoT devices. The architecture offers edge computing within a containerbased gateway, simplifying on-site data processing and minimizing data traffic complexities. The MQTT protocol supports interoperability among distributed services, enhancing adaptability and efficiency in processing data locally or via cloud services like digital twins. We demonstrate this system¿s effectiveness through two case studies in natural parks: visitor counting using Time of Flight technology and water level measurement with GNSS data. These cases highlight the system¿s ability to handle frequent small and less frequent large data transmissions efficiently, This work has been supported by the MCSA-SE REMARKABLE grant ID: 101086387; Research project CIPROM/2023/29, funded by Direccio General de Ciencia ` i Investigacio Generalitat Valenciana - SPAIN; EU s Horizon ¿ 2020 research and innovation program No 101017861, by project Ramon y Cajal Grant RYC2018-025580-I, funded by ¿ MCIN/AEI/ 10.13039/501100011033 and ESF Investing in your future, GVA GRISOLIAP/2021/103 and Grant TED2021- 130890B funded by MCIN/AEI and by EU NextGenerationEU/PRTR.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Edge-enabled GNSS-IR for efficient water level monitoring in harsh environments

  • Rosas-Olivos, Erika Susana
  • Arratia-Uribe, Benjamín Andrés|||0000-0001-7869-053X
  • Martín Furones, Ángel Esteban|||0000-0001-9379-0694
  • Prades, Javier|||0000-0003-3349-2200
  • Manzoni, Pietro|||0000-0003-3753-0403
  • Cecilia-Canales, José María|||0000-0001-5648-214X
[EN] Accurate water level monitoring in remote and harsh environments is critical for managing water resources, assessing climate impacts, and anticipating flood risks. Traditional in situ sensors often fail in these contexts due to corrosion, biofouling, or limited access for maintenance. Global Navigation Satellite System Interferometric Reflectometry (GNSS-IR) offers a passive, low-cost alternative by extracting water level information from multipath reflections of GNSS signals. However, using multi-constellation GNSS-IR for near real-time monitoring is challenging due to its high computational and communication demands, especially in low-power, low-connectivity areas. This paper presents a novel edge computing-based GNSS-IR system designed for deployment in harsh environments. The system, validated in the highly saline La Mata-Torrevieja Natural Park (Spain), integrates a low-cost GNSS receiver and a modular gateway that executes the GNSS-IR processing locally. To efficiently transmit results over long distances, it uses the AlLoRa protocol, an advanced LPWAN solution optimized for high-throughput, low-power communication. By eliminating the need for raw data transmission and enabling local analytics, the system reduces bandwidth, enhances responsiveness, and supports continuous operation in constrained conditions. Experimental validation demonstrates the system's effectiveness in achieving near real-time water level estimation with minimal infrastructure., This work was partially supported by the research project Morellino (CIPROM/2023/29), funded by "Direccio General de Ciencia i Investigacio" Generalitat Valenciana-SPAIN and by the European Union's Horizon Europe project REMARKABLE under the MSCA-SE grant ID: 101086387, and the projects TED2021-130890B and CPP2021-008722 funded by MCIN/AEI/10.13039/501100011033 and by the European Union NextGenerationEU/PRTR.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Model-Driven Development of Web Augmenters for Facilitating Environmental Open Data Consumption

  • González-Martínez, Paula
  • González-Mora, Cesar
  • Garrigós, Irene
  • Mazón, Jose-Norberto
  • Cecilia-Canales, José María|||0000-0001-5648-214X
[EN] Citizens must consume open data published by public institutions to be aware of environmental issues of SDGs (Sustainable Development Goals). However, the existence of many related heterogeneous open data sets hampers citizens to access and consume them to raise environmental awareness. To overcome this scenario, in this paper, we introduce a model-driven development approach to automatically generate maps as web augmenters to allow citizens to surf the Web while they 1) homogeneously access environmental open data, and 2) easily visualize this data on the map. To show the feasibility of our approach, we focus on a case study of biodiversity maps, which are related to SDG 14 (life below water), and 15 (life on land). Through this case study, a web augmenter applied to Wikipedia is automatically generated from environmental open data related to "Mar Menor" coastal lagoon; a highly anthropized ecosystem located in Southeast Spain. A focus group is conducted to validate that our generated web augmenter is easy to use and useful for environmental open data consumption., This research has been supported by projects TED2021-130890B funded by the Ministerio de Ciencia, Innovacibn y Universidades (MCIN)/Agencia Estatal de Investigacibn (AEI)/10.13039/501100011033 and by the European Union NextGenerationEU/Plan de Recuperacibn, Transformacibn y Resiliencia (PRTR), CIAICO/2022/019 funded by Generalitat Valenciana, and by REMARKABLE project (HORIZON-Marie Sklodowska-Curie Actions (MSCA)-2021-SE-0 action number: 101086387). Also, this work has been supported by the European Union's Horizon 2020 research and innovation programme under grant agreement No 101017861. Authors are especially grateful to FauNatura for their support in validating the results of this research.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Assessment of oceanographic services for the monitoring of highly anthropised coastal lagoons: The Mar Menor case study

  • Gimenez-Manuel, Jose Gines|||0000-0002-2624-1481
  • Cecilia-Canales, José María|||0000-0001-5648-214X
  • Granero, Alberto
  • Senent-Aparicio, Javier
  • Gómez-Jakobsen, Francisco
  • Mercado, Jesus M.
  • Blanco-Gómez, Pablo
  • Ruiz, Juan M.
[EN] Ocean monitoring systems are designed for continuous monitoring of the seas and oceans to track their evolution and thus anticipate environmental issues. However, they are often based on Internet of Things (IoT) systems that are expensive, hard to maintain, and offer little spatial coverage. An emerging alternative is Satellite Remote Sensing (SRS) systems that offer good geographical coverage but, as a reliable and real-time monitoring system, they also face several challenges such as environmental conditions, spatio-temporal granularity, terrain oleography, etc. This paper introduces an easy-to-use software tool to crawl water-quality data from up to 6 satellite instruments (i.e. Sentinel 3A, Sentinel-3B, NOAA VIIRS, SNPP VIIRS, Aqua MODIS, Terra MODIS) of the European Space Agency's (ESA) Coopernicus system and NASA's Marine Environmental Monitoring Service. We also provide an in-depth analysis in terms of reliability and data coverage for the chlorophyll-a (Chl-a) in a highly anthropised local/regional context like the Mar Menor lagoon (Murcia, Spain), where serious socioenvironmental issues are arising due to the eutrophication process. Our results show a good linear correlation between in situ data, obtained by several Spanish public institutions since 2016, and data generated by the IRTMNN (Inverse Radiative Transfer Model-Neural Network) algorithm of Sentinel 3 in general, reaching coefficient correlation values close to 0.9. They also show that organic matter inputs from ephemeral streams are relevant in determining Chl-a concentrations. Moreover, the temporal coverage using a single instrument is rather limited, as no data were recorded for 80% of the days studied. This figure decreases to 30% when data from the 6 satellite instruments are combined, increasing the temporal granularity of the measurements from approximately 5 to 1.5 days, suggesting the need for a combination of these systems for a robust SRS system., This work has been supported by the European Union's Horizon 2020 research and innovation programme under grant agreement No 101017861 as well as the Ramon y Cajal Grant RYC2018-025580-I, funded by MCIN/AEI/10.13039/501100011033, "FSE invest in your future" and "ERDF A way of making Europe" and the TED2021-130890B research project funded by MCIN/AEI/10.13039/501100011033 and European Union NextGenerationEU/PRTR. The authors acknowledge the Comunidad Autonoma de la Region de Murcia (CARM) for the data provided through the Mar Menor information service website (Canal Mar Menor) . The chlorophyll monitoring of the IEO-CSIC was funded from DMMEM project from the Spanish Institute of Oceanography.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

AI*LoRa: Enabling Efficient Long-Range Communication with Machine Learning at the Edge

  • Arratia-Uribe, Benjamín Andrés|||0000-0001-7869-053X
  • Rosas-Olivos, Erika Susana
  • Cecilia-Canales, José María|||0000-0001-5648-214X
  • Manzoni, Pietro|||0000-0003-3753-0403
  • Pietrosemoli, Ermanno
  • Zennaro, Marco
[EN] Efficient long-range communication is critical for environmental monitoring, especially when dealing with large data transfers in remote areas. We present an AI-driven dynamic RF configuration mode, which combines the advanced capabilities of a novel AI*LoRa model with an enhanced RF configuration request mechanism. By leveraging TinyML, AI*LoRa dynamically adjusts key parameters of the physical layer, based on real-time environmental data, ensuring robust and energy-efficient communication. We conducted extensive real-world testing across distances ranging from a few meters to over 100 kilometers to collect the dataset necessary for training our model. The results demonstrate that our approach achieved over 90% accuracy in predicting optimal settings, leading to an average improvement of over 170% in communication efficiency. These findings underscore AI*LoRa's significant potential to enhance long-range IoT deployments., This work has been supported by the MCSA-SE REMARKABLE grant ID: 101086387 and SMARTLAGOON grant No 101017861, by project Ramón y Cajal Grant RYC2018-025580-I, funded by MCIN/AEI/ 10.13039/501100011033 and ESF Investing in your future, GVA GRISOLIAP/2021/103 and Grant TED2021-130890B funded by MCIN/AEI and by EU NextGenerationEU/PRTR.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Tesis doctoral (DoctoralThesis)

Optimizing Machine Learning Algorithm Execution on IoT Infrastructures

  • Arratia-Uribe, Benjamín Andrés|||0000-0001-7869-053X
[ES] Los desafíos ambientales globales, como el cambio climático, la contaminación y la pérdida de biodiversidad, exigen enfoques innovadores y sostenibles para monitorear y gestionar eficazmente ecosistemas vulnerables. La inteligencia ambiental (EI) surge como un paradigma clave, integrando diversas fuentes de datos y modelos dinámicos para posibilitar la toma de decisiones en tiempo real, basada en datos, en contextos socioambientales complejos. Esta tesis presenta el diseño e implementación de infraestructuras IoT in situ con capacidades de computación en el borde, adaptadas a entornos desafiantes como lagunas costeras y regiones semiáridas. En el núcleo de este trabajo se encuentran dos aportes principales: el protocolo AlLoRa y el sistema BODOQUE. AlLoRa optimiza la transmisión de grandes volúmenes de datos a larga distancia y bajo consumo, admitiendo tanto redes punto a punto como en malla. Probado con éxito a más de 100 kilómetros, AlLoRa demostró un rendimiento superior en velocidad de transmisión y eficiencia energética frente a soluciones existentes, mostrando su capacidad de adaptación en aplicaciones de monitoreo a gran escala y condiciones ambientales variadas. Al integrar sensores avanzados -como estimadores del nivel del agua basados en GNSS y boyas oceanográficas que capturan parámetros de calidad del agua en tiempo real- AlLoRa facilita la integración fluida de flujos de datos heterogéneos en una arquitectura flexible y unificada. El sistema BODOQUE combina TinyML y visión por computador para monitorear corrientes efímeras, fundamentales para comprender los aportes de nutrientes en ecosistemas sensible, como El Mar Menor, en España. Al procesar los datos localmente en el borde, BODOQUE minimiza el uso de energía y permite la detección en tiempo real de eventos hidrológicos de corta duración. Un modelo TinyML, desplegado en un microcontrolador con cámara, distingue con precisión imágenes con presencia de agua de aquellas sin, asegurando que los módulos de alto rendimiento se active sólo cuando sea necesario. Una evaluación de un año de duración, utilizando datos de la ``Rambla del Albujón'', confirmó ahorros energéticos sustanciales en comparación con sistemas de monitoreo continuo, destacando la utilidad de BODOQUE para regiones con recursos energéticos muy limitados. Las pruebas de campo resaltan mejoras notables en eficiencia energética, fiabilidad de la comunicación y precisión de los datos, impulsando prácticas de gestión ambiental más ágiles y sostenibles. Este trabajo pone de manifiesto el potencial de las infraestructuras IoT y la computación inteligente en el borde para transformar la monitorización ambiental, alineándose con los esfuerzos globales para mitigar el cambio climático, conservar la biodiversidad y promover la gestión sostenible de los recursos. Al abordar tanto desafíos tecnológicos como ecológicos, esta investigación contribuye significativamente al avance del campo de la inteligencia ambiental., [CA] Els desafiaments ambientals globals, com el canvi climàtic, la contaminació i la pèrdua de biodiversitat, requereixen enfocaments innovadors i sostenibles per tal de monitoritzar i gestionar eficaçment ecosistemes vulnerables. La intel·ligència ambiental (EI) es presenta com un paradigma clau, integrant fonts de dades diverses i models dinàmics per possibilitar la presa de decisions en temps real, basada en dades, en contextos socioambientals complexos. Aquesta tesi presenta el disseny i la implementació d'infraestructures IoT in situ amb capacitats de computació a l'extrem, adaptades a entorns exigents com les llacunes costaneres i les regions semiàrides. Al nucli d'aquest treball es troben dues contribucions principals: el protocol AlLoRa i el sistema BODOQUE. AlLoRa optimitza la transmissió de grans volums de dades a llarga distància i baix consum energètic, admetent tant xarxes punt a punt com en malla. Provada amb èxit a més de 100 quilòmetres, AlLoRa va demostrar un rendiment superior pel que fa a la velocitat de transmissió i l'eficiència energètica, evidenciant la seua capacitat d'adaptació en aplicacions de monitorització a gran escala i en condicions ambientals diverses. En integrar sensors avançats -com els estimadors del nivell de l'aigua basats en GNSS i boies oceanogràfiques que capten paràmetres de qualitat de l'aigua en temps real- AlLoRa facilita la integració fluida de fluxos de dades heterogenis dins una arquitectura flexible i unificada. El sistema BODOQUE combina TinyML i visió per computador per monitoritzar corrents efímers, fonamentals per comprendre els aportaments de nutrients en ecosistemes sensibles, com el del Mar Menor, a Espanya. En processar les dades localment a l'extrem, BODOQUE minimitza l'ús d'energia i permet la detecció en temps real d'esdeveniments hidrològics de curta durada. Un model TinyML, desplegat en un microcontrolador amb càmera, va distingir amb precisió imatges amb presència d'aigua d'aquelles sense, assegurant que els mòduls d'alt rendiment s'activen només quan és necessari. Una avaluació de tot un any, utilitzant dades de la ``Rambla del Albujón'', va confirmar importants estalvis energètics en comparació amb sistemes de monitorització contínua, destacant la idoneïtat de BODOQUE per a regions amb recursos energètics molt limitats. Les proves de camp ressalten millores notables en eficiència energètica, fiabilitat de la comunicació i precisió de les dades, impulsant pràctiques de gestió ambiental més àgils i sostenibles. Aquest treball posa en relleu el potencial de les infraestructures IoT i la computació intel·ligent a l'extrem per transformar la monitorització ambiental, alineant-se amb els esforços globals per mitigar el canvi climàtic, conservar la biodiversitat i promoure la gestió sostenible dels recursos. En abordar tant els reptes tecnològics com els ecològics, aquesta investigació contribueix significativament a l'avenç del camp de la intel·ligència ambiental., [EN] Global environmental challenges such as climate change, pollution, and biodiversity loss demand innovative and sustainable approaches to effectively monitor and manage vulnerable ecosystems. Environmental intelligence (EI) emerges as a key paradigm, integrating diverse data sources and dynamic models to enable real-time, data-driven decision-making in complex socio-environmental contexts. This thesis presents the design and implementation of in-situ IoT infrastructures with edge capabilities tailored for challenging environments like coastal lagoons and semi-arid regions. At the core of this work are two main contributions: the AlLoRa protocol and the BODOQUE system. AlLoRa optimizes long-range, low-power data transmission of large data volumes, supporting both point-to-point and mesh networking. Successfully tested over a 100-kilometer range, AlLoRa demonstrated superior throughput and energy efficiency compared to existing solutions, proving its adaptability for large-scale monitoring applications and diverse environmental conditions. By integrating advanced sensors-such as GNSS-based water level estimators and oceanographic buoys capturing real-time water quality metrics-AlLoRa facilitates the seamless integration of heterogeneous data streams under a unified, flexible architecture. The BODOQUE system combines TinyML and computer vision to monitor ephemeral streams, critical for understanding nutrient inflows into sensitive ecosystems, like the Mar Menor coastal lagoon, located in Spain. By processing data locally at the edge, BODOQUE minimizes energy use and enables real-time detection of short-lived hydrological events. A TinyML model, deployed on a camera-enabled microcontroller, accurately distinguishes images with water from those without, ensuring that high-performance edge modules activate only when necessary. A year-long evaluation using data from the ``Rambla del Albujón'' stream confirmed substantial energy savings compared to continuous monitoring systems, underscoring BODOQUE's suitability for remote regions with limited power resources. Field deployments highlight substantial improvements in energy efficiency, communication reliability, and data accuracy, advancing responsive and sustainable environmental management practices. This work underscores the potential of IoT infrastructures and intelligent edge computing to transform environmental monitoring, aligning with global efforts to mitigate climate change, conserve biodiversity, and promote sustainable resource management. By addressing both technological and ecological challenges, this research makes a significant contribution to the advancing field of environmental intelligence., I would like to thank Generalitat Valenciana and their Santiago Grisolía program, who supported me with the grant GVA GRISOLIAP/2021/103. To the SMARTLAGOON project, funded by grant No 101017861, that gave me the motivation and playground to develop and test technologies for real-life and relevant challenges. This work has also been supported by MCIN/AEI/ 10.13039/501100011033 and ESF Investing in your future, MCSA-SE REMARKABLE grant ID: 10108638, Grant TED2021-130890B funded by MCIN/AEI and by EU NextGenerationEU/PRTR and by project Ramón y Cajal Grant RYC2018-025580-I, funded by MCIN/AEI/ 10.13039/501100011033 and ESF Investing in your future.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Harnessing Social Sensing for Real-Time Flood Event Reconstruction: A Digital Autopsy of the 2024 Valencia DANA

  • Giner-Pérez de Lucía, José
  • López-Ballesteros, Adrián|||0000-0001-6350-5653
  • Fernández-Pedauyé, Julio José
  • Cecilia-Canales, José María|||0000-0001-5648-214X
  • Senent-Aparicio, Javier
[EN] Extreme rainfall and flash-flood events in the Western Mediterranean pose persistent challenges for real-time monitoring and emergency response. Traditional hydrometeorological networks often provide limited spatiotemporal coverage during rapidly evolving events, leading to localized blind spots. This study reconstructs the impacts of the October 2024 catastrophic floods in Valencia using more than 156{,}000 geolocated messages from X (formerly Twitter) as a form of social sensing. These citizen-generated data were integrated with hydrological and hydraulic modeling to contextualize reported flood dynamics and response gaps. Advanced Natural Language Processing (NLP) techniques were applied to extract spatiotemporal patterns of public perception, emergency reactions, and infrastructure disruptions. In addition, a Retrieval-Augmented Generation (RAG) system was implemented to transform unstructured messages into structured event summaries, providing actionable insights during the disaster window. The analysis revealed a clear temporal alignment between social media activity and flood progression, with online reporting peaking shortly after critical impact thresholds. Cross-validation with hydrological simulations confirmed the potential of social sensing to detect localized effects often missed by conventional monitoring, while also exposing the limitations of relying solely on proxy digital traces. Overall, the Valencia case demonstrates the feasibility of integrating human-sensed information with physically based models to enhance situational awareness and support adaptive, data-driven disaster risk reduction in urban environments., This research has been supported by projects TED2021-130890B funded by MCIN/AEI/10.13039/501100011033, and AM-DS (INREED/2024/1), funded by the European Union - NextGenerationEU. José Giner Pérez de Lucia acknowledges the financial support by the Spanish State Research Agency (Agencia Estatal de Investigación, AEI) through the Industrial PhD Grant within the Training of Doctors in Companies (Industrial PhDs) program, under the State Plan for Scientific, Technical and Innovation Research (DIN2024-014116-2). Finally, Adrián López-Ballesteros acknowledges the financial support received from the Juan de la Cierva Postdoc Spanish Program (JDC2023-050965-I).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

A Review of Service Selection Strategies in Mobile IoT Networks

  • Mohammed Hadjkouider, Abdessalam
  • Kerrache, Chaker Abdelaziz
  • Korichi, Ahmed
  • Sahraoui, Yesin
  • Dhelim, Sahraoui
  • Adnane, Asma
  • Tavares De Araujo Cesariny Calafate, Carlos Miguel|||0000-0001-5729-3041
[EN] With the proliferation of service-oriented architectures, the ubiquity of mobile networks, and an expanding spectrum of services available to users, the service selection process has become paramount in designing and implementing contemporary applications. Service selection strategies in mobile networks involve choosing the optimal services from many available options based on QoS (quality of service), bandwidth, and mobility, ultimately augmenting network efficiency and user experience. Nonetheless, particular challenges can impact the efficacy of these strategies. This paper presents a comprehensive survey of service selection strategies in mobile networks, transitioning from traditional approaches to emerging techniques, while also introducing a taxonomy classifying service selection methods based on criteria including mobile devices as service providers, architectural perspectives, computing devices allocation, evaluation metrics, and service selection methods. Additionally, We offer insights into the latest QoS-aware and energy-centric service selection methodologies, while addressing challenges related to battery life and energy efficiency, Quality of Service (QoS), security and privacy, as well as scalability and resource management. Additionally, we discuss prospective trajectories and future direction., This work was supported in part by MCIN/AEI/10.13039/501100011033 under Project TED2021-130890B-C22 and Project PID2021-122580NB-100; in part by the European Union NextGenerationEU/PRTR; and in part by the ERDF A way of making Europe.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

AlLoRa: Empowering environmental intelligence through an advanced LoRa-based IoT solution

  • Arratia-Uribe, Benjamín Andrés|||0000-0001-7869-053X
  • Rosas-Olivos, Erika Susana
  • Tavares De Araujo Cesariny Calafate, Carlos Miguel|||0000-0001-5729-3041
  • Cano, Juan-Carlos|||0000-0002-0038-0539
  • Cecilia-Canales, José María|||0000-0001-5648-214X
  • Manzoni, Pietro|||0000-0003-3753-0403
[EN] Environmental intelligence aims to improve the decision-making process for high social and environmental value ecosystems. To this end, data are collected using different sensors to allow monitoring of different variables of interest. Typically, these ecosystems cover a large geographical area, with spots of low or no connectivity, preventing their monitoring in real time. In this work, we propose \allora{} (Advanced Layer LoRa), a modular, low-power, long-range communication protocol based on LoRa, that allows monitoring of remote natural areas. \allora{} has been evaluated and tested in an operational oceanographic buoy that has been deployed to address the specific environmental crisis of the Mar Menor lagoon in southeastern Spain - a region spanning 135 Km currently undergoing severe eutrophication process. Our results reveal that \allora{} offers good performance regarding transfer time, power consumption, and range. The throughput ranged from around 2 kbps with SF7 to approximately 300 bps with SF11; the power consumption per kilobyte transmitted varied from $395 \mu Wh$ to $428 \mu Wh$ depending on the specific device used. The Mesh mode test successfully maintained communication between nodes over 20.33 km. Further tests in various configurations under challenging conditions validated the mesh forwarding approach. Despite tripling the distance, the system maintained reliable data transfer, improving speeds from the original point-to-point setup., This work has been supported by the European Union s Horizon 2020 research and innovation program under grant agreement No 101017861 and also by the project Ramon y Cajal Grant RYC2018-025580-I, funded by MCIN/AEI/ 10.13039/501100011033 and ESF Investing in your future, GVA GRISOLIAP/2021/103 and Grant TED2021-130890B funded by MCIN/AEI and by European Union NextGenerationEU/PRTR.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

BODOQUE: An Energy-Efficient Flow Monitoring System for Ephemeral Streams

  • Arratia-Uribe, Benjamín Andrés|||0000-0001-7869-053X
  • Prades, Javier|||0000-0003-3349-2200
  • Cecilia-Canales, José María|||0000-0001-5648-214X
  • Manzoni, Pietro|||0000-0003-3753-0403
  • Peña-Haro, Salvador
[EN] Effective environmental monitoring is crucial for managing global environmental challenges and providing the necessary data for Environmental Intelligence (EI). This discipline involves the integration of data from various sources to gain a comprehensive understanding of specific regions or processes. In this paper, we introduce BODOQUE, a hardware-software infrastructure to monitor water flows in ephemeral streams where the water rarely flows with great force. BODOQUE uses a low-power TinyML-based camera to detect the presence of water, activating a more complex system to measure flow only when the water flows, thereby optimizing energy consumption. This device is being deployed in the Segura basin, Murcia, Spain. This region is grappling with severe environmental issues that affect the Mar Menor, a unique saltwater lagoon. This paper focuses on the power-saving capabilities of BODOQUE, comparing the energy consumption of different edge devices running the code that measures water flow in the streams. Our goal is to determine the optimal hardware setup for the system based on our experiments, which involve performance and energy consumption tests. The results provide valuable information for future environmental monitoring systems, considering the best balance among the device's cost, performance, and energy consumption., This work has been supported by the European Union s Horizon 2020 program (No 101017861), the Ramon y Cajal Grant RYC2018-025580-I funded by MCIN/AEI/10.13039/501100011033 and FSE, and the Project TED2021-130890B backed by MCIN/AEI and the European Union s NextGenerationEU/ PRTR.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Towards efficient stream monitoring: A systematic approach for model selection and continuous improvement in Tiny Machine Learning applications

  • Arratia-Uribe, Benjamín Andrés|||0000-0001-7869-053X
  • Rosas-Olivos, Erika Susana
  • Prades, Javier|||0000-0003-3349-2200
  • Cecilia-Canales, José María|||0000-0001-5648-214X
  • Manzoni, Pietro|||0000-0003-3753-0403
  • Peña-Haro, Salvador
[EN] Measuring ephemeral stream flows is essential for ecological and hydrological studies. However, their intermittent nature and remote locations pose challenges for conventional monitoring methods, which often consume excessive energy to capture rare events. We address this with BODOQUE (Bimodal Observational Device for Optimizing Quantification of Ephemeral streams), a dual-mode system that leverages Tiny Machine Learning (TinyML) on low-power microcontrollers. The system remains in an energy-saving sensing state and activates high-precision measurements only when water flow is detected. We present a model selection methodology that balances detection accuracy with inference cost, enabling reliable operation within hardware constraints. To enhance adaptability in diverse environments, we developed a specialized component that facilitates dataset expansion through new field samples. This supports ongoing retraining to maintain model performance under changing conditions. A comprehensive evaluation using real-world data demonstrates that our system can achieve up to 97% annual energy savings compared to traditional continuous monitoring approaches., This work has been supported by the European Union s Horizon 2020 research and innovation program under grant agreement No. 101017861 and by the MCSA-SE REMARKABLE grant ID: 101086387. Additionally, it has received funding from the Ramón y Cajal Grant RYC2018-025580-I, supported by MCIN/AEI/10.13039/501100011 033 and ESF Investing in Your Future, as well as from GVA GRISOLIAP/ 2021/103 and Grant TED2021-130890B, funded by MCIN/AEI and the European Union NextGenerationEU/PRTR. This work was also partially supported by the research project CIPROM/2023/29, funded by the Direcció General de Ciència i Investigació of the Generalitat Valenciana, Spain.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Proyecto fin de carrera (BachelorThesis)

Análisis y predicción de avistamientos de aves para el turismo inteligente en la Comunidad Valenciana, Analysis and prediction of bird sightings for smart tourism in the Valencian Community, Anàlisi i predicció dels albiraments d&apos, ocells per al turisme intel·ligent a la Comunitat Valenciana

  • Wu, Tingting
[ES] Los sistemas tradicionales de seguimiento ornitológico enfrentan restricciones presupuestarias y de personal que limitan su capacidad de documentar la avifauna a escalas espaciotemporales amplias. Las plataformas participativas emergen como alternativa prometedora, aunque requieren validación científica rigurosa antes de su adopción en programas oficiales de conservación. Este estudio examina la fiabilidad y utilidad de eBird para el seguimiento de aves en ecosistemas mediterráneos, evaluando simultáneamente su potencial para informar estrategias de turismo de naturaleza basado en datos. La investigación procesó más de 1,4 millones de observaciones ciudadanas de fauna ornitológica valenciana recopiladas desde 2021 hasta principios de 2025, integrando datos meteorológicos sincronizados y aplicando técnicas de análisis temporal, geoespacial y modelado predictivo. Las metodologías incluyeron corrección específica de sesgos participativos mediante análisis de autocorrelación, descomposición de series temporales y validación cruzada espacialmente explícita. El conjunto documenta 434 especies con diversidad alfa comparable a inventarios profesionales (Shannon = 4,90). La distribución espacial muestra concentración efectiva en áreas protegidas (88 % de cobertura) e identifica vacíos funcionales en paisajes agrícolas periurbanos. Los patrones fenológicos replican ciclos migratorios documentados, con máximos primaverales y otoñales separados por depresiones estivales del 60 %. El análisis cuantifica sesgos sistemáticos: incrementos del 70 % durante fines de semana y reducción del 17 % bajo condiciones meteorológicas adversas. Los modelos predictivos demuestran capacidad útil para planificación turística (errores del 24-30 % períodos estables) aunque con degradación durante eventos migratorios excepcionales, indicando predominancia de factores comportamentales humanos sobre señales ecológicas directas. Los resultados confirman que las plataformas de ciencia ciudadana constituyen fuentes válidas para monitoreo regional cuando se aplican protocolos rigurosos. El estudio establece metodologías transferibles y proporciona fundamentos empíricos para herramientas de gestión territorial y turismo de naturaleza basadas en participación ciudadana., [EN] Traditional ornithological monitoring systems face budgetary and personnel constraints that limit their capacity to document avifauna at broad spatiotemporal scales. Participatory platforms emerge as a promising alternative, although they require rigorous scientific validation before their adoption in official conservation programs. This study examines the reliability and utility of eBird for bird monitoring in Mediterranean ecosystems, simultaneously evaluating its potential to inform data-driven nature tourism strategies. The research processed over 1.4 million citizen observations of Valencian ornithological fauna collected from 2021 to early 2025, integrating synchronized meteorological data and applying temporal, geospatial analysis and predictive modeling techniques. Methodologies included specific correction of participatory biases through autocorrelation analysis, time series decomposition, and spatially explicit cross-validation. The dataset documents 434 species with alpha diversity comparable to professional inventories (Shannon = 4.90). Spatial distribution shows effective concentration in protected areas (88% coverage) and identifies functional gaps in periurban agricultural landscapes. Phenological patterns replicate documented migratory cycles, with spring and autumn maxima separated by 60% summer depressions. Analysis quantifies systematic biases: 70% increases during weekends and 17% reduction under adverse meteorological conditions. Predictive models demonstrate useful capacity for tourism planning (24-30% errors in stable periods) although with degradation during exceptional migratory events, indicating predominance of human behavioral factors over direct ecological signals. Results confirm that citizen science platforms constitute valid sources for regional monitoring when rigorous protocols are applied. The study establishes transferable methodologies and provides empirical foundations for territorial management tools and nature tourism based on citizen participation., [CA] Els sistemes tradicionals de seguiment ornitològic s’enfronten a restriccions pressupostàries i de personal que limiten la seua capacitat de documentar l’avifauna a escales espaciotemporals àmplies. Les plataformes participatives emergixen com alternativa prometedora, encara que requerixen validació científica rigorosa abans de la seua adopció en programes oficials de conservació. Aquest estudi examina la fiabilitat i utilitat d’eBird per al seguiment d’aus en ecosistemes mediterranis, avaluant simultàniament el seu potencial per informar estratègies de turisme de natura basat en dades. La investigació processà més d’1,4 milions d’observacions ciutadanes de fauna ornitològica valenciana recopilades des del 2021 fins a principis del 2025, integrant dades meteorològiques sincronitzades i aplicant tècniques d’anàlisi temporal, geoespacial i modelatge predictiu. Les metodologies inclogueren correcció específica de biaixos participatius mitjançant anàlisi d’autocorrelació, descomposició de sèries temporals i validació encreuada espacialment explícita. El conjunt documenta 434 espècies amb diversitat alfa comparable a inventaris professionals (Shannon = 4,90). La distribució espacial mostra concentració efectiva en àrees protegides (88% de cobertura) i identifica buits funcionals en paisatges agrícoles periurbans. Els patrons fenològics repliquen cicles migratoris documentats, amb màxims primaverencs i tardorencs separats per depressions estivals del 60%. L’anàlisi quantifica biaixos sistemàtics: increments del 70% durant caps de setmana i reducció del 17% sota condicions meteorològiques adverses. Els models predictius demostren capacitat útil per a planificació turística (errors 24-30% períodes estables) encara que amb degradació durant esdeveniments migratoris excepcionals, indicant predominança de factors comportamentals humans sobre senyals ecològics directes. Els resultats confirmen que les plataformes de ciència ciutadana constituïxen fonts vàlides per al monitoratge regional quan s’apliquen protocols rigorosos. L’estudi establix metodologies transferibles i proporciona fonaments empírics per a eines de gestió territorial i turisme de natura basades en participació ciutadana.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Methodology for Measuring Individual Affective Polarization Using Sentiment Analysis in Social Networks

  • Martínez-España, Raquel
  • Rojo-Martínez, Jose Miguel
  • Bakdid-Albane, Kaoutar
  • García-Escribano, Juan José
  • Fernández-Pedauyé, Julio José
  • Giner-Pérez de Lucía, José
[EN] Affective polarization has important consequences for societies and institutions. At the institutional level, it hinders agreement among political actors, which damages the stability of the system. At the social level, it increases tensions and conflicts between people, damaging coexistence. Until now, affective polarization has been studied essentially through surveys, which are generally very costly if large and representative samples are to be obtained and in which the answers of the interviewees may not be totally sincere. Through this article, we apply sentiment analysis techniques to measure affective polarization without resorting to surveys, simply by monitoring the non-self-reported behavior of individuals in social networks. To do that, a novel methodology and a new indicator of affective polarization has been proposed using data from social networks. The proposed methodology and new indicator have been applied to the real case study of the regional elections in Spain, specifically to the autonomous Region of Murcia. The application of the methodology has been satisfactory, as well as that of the new indicator of affective polarization, providing a cost-effective way of calculating polarization. The results show that all political groups are polarized to a greater or lesser extent. Furthermore, the results conclude that the winning ideology in the elections, i.e., the right, was the one whose supporters behaved differently from the supporters of other ideologies., This work was supported by the Science and Technology Agency of the Region of Murcia under Grant 21876/PI/2022. The work of Jose Miguel Rojo-Martinez and Kaoutar Bakdid-Albane was supported by the Ministry of Universities of the Spanish Government through the FPU under Grant FPU20/01033 and Grant FPU21/04363. The work of Jose Giner-Perez de Lucia was supported in part by the CIN/AEI/10.13039/501100011033 under Grant TED2021-130890B, and in part by the European Union NextGeneration EU/PRTR.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Advancing smart tourism destinations: A case study using bidirectional encoder representations from transformers-based occupancy predictions in Torrevieja (Spain)

  • Gimenez-Manuel, Jose Gines|||0000-0002-2624-1481
  • Giner-Pérez de Lucía, José
  • Cano, Juan-Carlos|||0000-0002-0038-0539
  • Cecilia-Canales, José María|||0000-0001-5648-214X
  • Celdrán Bernabeu, Marco
  • Mazón López, Jose Norberto
[EN] Tourism represents a crucial socio¿economic pillar globally, yet the multifaceted chal-lenges it poses necessitate innovative management approaches. The paradigm of smarttourism harnesses advanced data analytics tools to promote both profitability and sus-tainability in tourist destinations, leading to new levels of destination smartness. Accuratetourist occupancy prediction, particularly in areas dominated by second¿home accom-modations where traditional hospitality data may be insufficient, plays a key role inoptimising tourism management. To address this data gap, our prior research employedARIMA modelling on Airbnb booking time series and analysed tourism¿related Twitterconversations to forecast occupancy levels in Torrevieja (Alicante); a prominent second¿home tourism destination in Southeastern Spain. In this extended study, we delve deeperinto the realm of social sensing by utilising bidirectional encoder representations fromtransformers (BERT) for topic modelling. Our methodology involves the processing andanalysis of Twitter data to identify prominent themes related to Torrevieja. The findingsnot only reveal nuanced perceptions and discussions about the destination but also un-derscore the effectiveness of BERT in capturing intricate topic dynamics. Importantly,this work highlights how the alignment of specific topics with booking patterns canfurther enhance predictive accuracy for tourist occupancy, presenting a robust toolkit forstakeholders in the tourism sector., This work has been supported by the projects TED2021-130890B, funded by MCIN/AEI/10.13039/501100011033 and by the European Union NextGenerationEU/PRTR, and Ramon y Cajal Grant RYC2018-025580-I, funded by MCIN/ AEI/10.13039/501100011033, FSE invest in your future and ERDF A way of making Europe .
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

TorreviejaSensing: A Social Sensing Approach for Real-Time Sustainable Tourism Monitoring in Coastal Cities

  • Giner-Pérez de Lucía, José
  • Cecilia-Canales, José María|||0000-0001-5648-214X
  • Fernández-Pedauyé, Julio
  • Celdrán-Bernabeu, Marco
  • Mazón, Jose Norberto
[EN] Tourism places increasing pressure on coastal cities, where seasonal congestion, fragmented urban development and changing citizen expectations challenge the sustainability of services and governance. To address these issues, we present TorreviejaSensing, a social sensing framework that transforms user-generated content into actionable evidence for policy and planning. The system combines multilingual natural language processing over X (Twitter) posts and Google Maps reviews, a policy-aware mapping of social signals to municipal strategic axes, and a Retrieval-Augmented Generation (RAG) chatbot that provides transparent, evidence-grounded answers to policy queries. Applied to Torrevieja (Spain), the framework enables real-time tracking of mobility and cleanliness complaints, early detection of seasonal pain points, and alignment of digital discourse with institutional strategies. A mixed-methods evaluation¿including manual annotation of NLP outputs, baseline comparison, and a pilot human assessment of chatbot responses¿demonstrates both robustness and practical utility. Findings reveal strong seasonal dynamics, recurrent topic clusters consistent with known governance challenges, and improved transparency of the RAG assistant compared to keyword-only approaches. Beyond the Torrevieja case, the framework is low-cost, transferable, and provides a replicable model for integrating citizen discourse into sustainable urban tourism governance., This research has been supported by projects TED2021‐130890B funded by MCIN/AEI/10.13039/501100011033 and by the European Union NextGenerationEU/PRTR, CIAICO/2022/019 funded by Generalitat Valenciana, and by REMARKABLE project (HORIZON‐MSCA‐2021‐SE‐0 action number: 101086387). Also, this work has been supported by the European Union's Horizon 2020 research and innovation programme under grant agreement No 101017861.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

From Research on Data-Intensive Software to Innovation in Data Spaces: A Search Service for Tabular Data

  • Berenguer, Alberto
  • Alcaraz, Olimpia
  • Tomás, David
  • Mazón, Jose-Norberto
  • Mazón, Jose-Norberto|||/items/31f8766d-f389-4889-ba06-adeb367a0753
  • Tomás, David|||/items/cf031fc3-3c30-454b-a6df-3762c29cc296
  • Berenguer, Alberto|||/items/6bc5210d-69fb-4751-bc6d-634368d65349
  • Alcaraz, Olimpia|||/items/35c2fc12-3ffa-42c2-b0ac-09c1090f33a6
Within research on data-intensive software development, a significant opportunity is emerging around data spaces. The main challenge is enabling researchers to create spin-offs that transfer research results within data spaces, beyond traditional approaches such as licensing or patenting. To address this challenge, we have combined the renowned Lean Startup approach with the Last Research Mile methodology in a novel technology transfer process. Finally, our journey in creating InferIA, a spin-off from the Science Park of the University of Alicante, is outlined to provide lessons learned when research results on tabular data search are transferred as innovative services within a data space context.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

The underestimated role of carrion in vertebrates' diet studies

  • Sebastián-González, Esther
  • Morant, Jon
  • Moleón, Marcos
  • Redondo-Gómez, Daniel
  • Morales-Reyes, Zebensui
  • Pascual-Rico, Roberto
  • Pérez-García, Juan M.
  • Arrondo, Eneko
  • Morant, Jon|||/items/f5c63ce0-a69a-483c-b591-c2e7b22a83f8
  • Sebastián-González, Esther|||/items/c53fd431-7978-4887-bee5-296d259dab12
Aim: Despite the increasing scientific evidence on the importance of carrion in the ecology and evolution of many vertebrates, scavenging is still barely considered in diet studies. Here, we draw attention to how scientific literature has underestimated the role of vertebrates as scavengers, identifying the ecological traits that characterize those species whose role as scavengers could have gone especially unnoticed. Location: Global. Time Period: 1938–2022. Major Taxa Studied: Terrestrial vertebrate scavengers. Methods: We analysed and compared (a) the largest database available on scavenging patterns by carrion-consuming vertebrates, (b) 908 diet studies about 156 scavenger species and (c) one of the most complete databases on bird and mammal diets (Elton Traits database). For each of these 156 species, we calculated their scavenging degree (i.e. proportion of carcases where the species is detected consuming carrion) as a proxy for carrion consumption, and related their ecological traits with the probability of being identified as scavengers in diet studies and in the Elton Traits database. Results: More than half of the species identified as scavengers at monitored carcasses were not assigned carrion as food source in their diet studies nor in the Elton Traits database. Using a subset of study sites, we found a direct relationship between a species' scavenging degree and its rate of carrion biomass removal. In addition, scavenger species, which were classified as non-predators and mammals had a lower probability of being identified as scavengers in diet studies and in the Elton Traits database, respectively. Main Conclusions: Our results clearly indicate an underestimation of the role of scavenging in vertebrate food webs. Given that detritus recycling is fundamental to ecosystem functioning, we encourage further recognition and investigation of the role of carrion as a food resource for vertebrates, especially for non-predator species and mammals with higher scavenging degree.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Vertebrate scavenger assemblages and their functioning differ between artificial and natural wetlands: Implications for ecosystem management

  • Orihuela-Torres, Adrian
  • Pérez-García, Juan M.
  • Arrondo, Eneko
  • Pessano-Serrat, Tatiana
  • Green, Andy J.
  • Naves-Alegre, Lara
  • Botella, Francisco
  • Selva, Nuria
  • Sánchez-Zapata, José A.
  • Sebastián-González, Esther
  • Orihuela-Torres, Adrian|||/items/88c3e834-f7ed-4ec8-b727-7506929b6eee
  • Sebastián-González, Esther|||/items/c53fd431-7978-4887-bee5-296d259dab12
Natural wetlands perform essential ecological functions, but their area has dramatically decreased. Partly to counteract this loss, artificial wetlands have been created. While studies comparing animal communities between artificial and natural wetlands abound, research on their comparative ecological functions is scarce. In particular, vertebrate scavengers in aquatic ecosystems have been little studied despite their critical role in nutrient cycling. This study compared vertebrate scavenger assemblages and their consumption patterns in natural and artificial wetlands in Doñana, Spain, to evaluate the effects of wetland management (natural vs. artificial hydrology) across different seasons. We placed 120 carcasses (carp and chicken) in natural and artificial wetlands. We recorded 22 vertebrate scavenger species efficiently consuming 100 % of carrion in an average of less than two days, highlighting their role in nutrient recycling. Carrion of aquatic-origin was consumed faster and by a greater variety of species than that of terrestrial-origin, facilitating the transport of essential nutrients from water to land. Artificial wetlands exhibited higher efficiency in carrion removal (twice as fast as natural wetlands). However, they hosted less diverse assemblages, dominated by opportunistic and non-native species. This suggests that artificial wetlands are not replacing natural wetlands in terms of biodiversity, despite sustaining water levels and functions. Importantly, ‘kidnapping’ water for irrigation reduces the ability of natural wetlands to maintain ecological functions provided by scavengers. Urgent regulation of water abstraction from aquifers, especially for crop irrigation, is necessary to maintain minimum groundwater levels, preserving the functionality and ecological processes of this critical wetland complex.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Simultaneous, vision-based fish instance segmentation, species classification and size regression

  • Climent-Pérez, Pau
  • Galán Cuenca, Alejandro
  • García-D'Urso, Nahuel
  • Saval-Calvo, Marcelo
  • Azorin-Lopez, Jorge
  • Fuster-Guilló, Andrés
  • Azorin-Lopez, Jorge|||/items/d43d029b-14bf-4dac-9bda-ed08e213bb1d
  • Climent-Pérez, Pau|||/items/ff360266-4bb6-48b2-9801-4faea00aebd3
  • Fuster-Guilló, Andrés|||/items/0d96ca87-a50d-4788-b5d3-456c44f8a6b6
  • Galán Cuenca, Alejandro|||/items/d81019ac-5845-4e4f-8af5-9c00dc6d1467
  • Saval-Calvo, Marcelo|||/items/403da831-5e9a-4111-8bed-6b60076f8101
  • García-D'Urso, Nahuel|||/items/2996c123-43e6-424d-b407-225d39a29839
Overexploitation of fisheries is a worldwide problem, which is leading to a large loss of diversity, and affects human communities indirectly through the loss of traditional jobs, cultural heritage, etc. To address this issue, governments have started accumulating data on fishing activities, to determine biomass extraction rates, and fisheries status. However, these data are often estimated from small samplings, which can lead to partially inaccurate assessments. Fishing can also benefit of the digitization process that many industries are undergoing. Wholesale fish markets, where vessels disembark, can be the point of contact to retrieve valuable information on biomass extraction rates, and can do so automatically. Fine-grained knowledge about the fish species, quantities, sizes, etc. that are caught can be therefore very valuable to all stakeholders, and particularly decision-makers regarding fisheries conservation, sustainable, and long-term exploitation. In this regard, this article presents a full workflow for fish instance segmentation, species classification, and size estimation from uncalibrated images of fish trays at the fish market, in order to automate information extraction that can be helpful in such scenarios. Our results on fish instance segmentation and species classification show an overall mean average precision (mAP) at 50% intersection-over-union (IoU) of 70.42%, while fish size estimation shows a mean average error (MAE) of only 1.27 cm.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Optimizing IoT Video Data: Dimensionality Reduction for Efficient Deep Learning on Edge Computing

  • Ortiz Pérez, David
  • Ruiz Ponce, Pablo
  • Mulero Pérez, David
  • Benavent-Lledó, Manuel
  • Rodríguez Juan, Javier
  • Hernandez-Lopez, Hugo
  • Iarovikov, Anatoli
  • Krco, Srdjan
  • Nedić, Daliborka
  • Vukobratović, Dejan
  • Garcia-Rodriguez, Jose
  • Benavent-Lledó, Manuel|||/items/0d1bda20-de83-4080-97c9-1820faf481da
  • Garcia-Rodriguez, Jose|||/items/d5bc18f8-44db-4723-b291-5849321e9e69
  • Mulero Pérez, David|||/items/e3a342d3-f8d6-4010-bf87-a509394c0d36
  • Ortiz Pérez, David|||/items/e77e67d5-78fc-4170-a005-b6d3fd3ca79e
  • Ruiz Ponce, Pablo|||/items/bf90946b-d388-45f2-bbc1-53d580a02453
  • Rodríguez Juan, Javier|||/items/4f464549-7f4d-4a47-9602-a42f7e1b5975
The rapid loss of biodiversity significantly impacts birds’ environments and behaviors, highlighting the importance of analyzing bird behavior for ecological insights. With the growing adoption of Machine Learning (ML) algorithms in the Internet of Things (IoT) domain, edge computing has become essential to ensure data privacy and enable real-time predictions by processing high-dimensional data, such as video streams, efficiently. This paper introduces a set of dimensionality reduction techniques tailored for video sequences based on cutting-edge methods for this data representation. These methods drastically compress video data, reducing bandwidth and storage requirements while enabling the creation of compact ML models with faster inference speeds. Comprehensive experiments on bird behavior classification in rural environments demonstrate the effectiveness of the proposed techniques. The experiments incorporate state-of-the-art deep learning techniques, including pre-trained video vision models, Autoencoders, and single-frame feature extraction. These methods demonstrated superior performance to the baseline, achieving up to a 6000-fold reduction in data size while reaching a classification accuracy of 60.7% on the Visual WetlandBirds Dataset and obtaining state-of-the-art performance on this dataset. These findings underline the potential of using dimensionality reduction to enhance the scalability and efficiency of bird behavior analysis.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Automated Generation of Clinical Reports Using Sensing Technologies with Deep Learning Techniques

  • Cabello Collado, Celia
  • Rodríguez Juan, Javier
  • Ortiz Pérez, David
  • Garcia-Rodriguez, Jose
  • Tomás, David
  • Vizcaya-Moreno, M. Flores
  • Cabello Collado, Celia|||/items/48c4b3ac-9631-4f88-9d2a-0b7a320ba50b
  • Garcia-Rodriguez, Jose|||/items/d5bc18f8-44db-4723-b291-5849321e9e69
  • Ortiz Pérez, David|||/items/e77e67d5-78fc-4170-a005-b6d3fd3ca79e
  • Rodríguez Juan, Javier|||/items/4f464549-7f4d-4a47-9602-a42f7e1b5975
  • Tomás, David|||/items/cf031fc3-3c30-454b-a6df-3762c29cc296
  • Vizcaya-Moreno, M. Flores|||/items/47df53a0-4d4d-48fe-8f29-471e90417a09
This study presents a pioneering approach that leverages advanced sensing technologies and data processing techniques to enhance the process of clinical documentation generation during medical consultations. By employing sophisticated sensors to capture and interpret various cues such as speech patterns, intonations, or pauses, the system aims to accurately perceive and understand patient–doctor interactions in real time. This sensing capability allows for the automation of transcription and summarization tasks, facilitating the creation of concise and informative clinical documents. Through the integration of automatic speech recognition sensors, spoken dialogue is seamlessly converted into text, enabling efficient data capture. Additionally, deep models such as Transformer models are utilized to extract and analyze crucial information from the dialogue, ensuring that the generated summaries encapsulate the essence of the consultations accurately. Despite encountering challenges during development, experimentation with these sensing technologies has yielded promising results. The system achieved a maximum ROUGE-1 metric score of 0.57, demonstrating its effectiveness in summarizing complex medical discussions. This sensor-based approach aims to alleviate the administrative burden on healthcare professionals by automating documentation tasks and safeguarding important patient information. Ultimately, by enhancing the efficiency and reliability of clinical documentation, this innovative method contributes to improving overall healthcare outcomes.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Model-Driven Development of Web Augmenters for Facilitating Environmental Open Data Consumption

  • González Martínez, Paula
  • González Mora, César
  • Garrigós, Irene
  • Mazón, Jose-Norberto
  • Cecilia, José M.
  • Garrigós, Irene|||/items/50e21847-f541-4051-8e6d-4064e0e80ea3
  • González Mora, César|||/items/bffa7ade-023b-4e37-893a-cf0aa181e2d4
  • Mazón, Jose-Norberto|||/items/31f8766d-f389-4889-ba06-adeb367a0753
Citizens must consume open data published by public institutions to be aware of environmental issues of SDGs (Sustainable Development Goals). However, the existence of many related heterogeneous open data sets hampers citizens to access and consume them to raise environmental awareness. To overcome this scenario, in this paper, we introduce a model-driven development approach to automatically generate maps as web augmenters to allowcitizens to surf theWeb while they (i) homogeneously access environmental open data, and (ii) easily visualize this data on the map. To show the feasibility of our approach, we focus on a case study of biodiversity maps, which are related to SDG 14 (life below water), and 15 (life on land). Through this case study, a web augmenter applied to Wikipedia is automatically generated from environmental open data related to “Mar Menor” coastal lagoon; a highly anthropized ecosystem located in Southeast Spain. A focus group is conducted to validate that our generated web augmenter is easy to use and useful for environmental open data consumption.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

El papel de los carroñeros vertebrados terrestres en el aprovechamiento de restos de caza de aves acuáticas en un humedal Mediterráneo, The role of terrestrial vertebrate scavengers in the utilization of waterfowl hunting carcasses in a Mediterranean wetland

  • Pessano-Serrat, Tatiana
  • Sebastián-González, Esther
  • Orihuela-Torres, Adrian
  • Orihuela-Torres, Adrian|||/items/88c3e834-f7ed-4ec8-b727-7506929b6eee
  • Sebastián-González, Esther|||/items/c53fd431-7978-4887-bee5-296d259dab12
Los carroñeros vertebrados son esenciales en los ecosistemas, estabilizando las cadenas tróficas, acelerando el reciclaje de nutrientes y eliminando posibles focos de enfermedades. En el Parque Natural de El Hondo, un humedal de importancia internacional para las aves (sudeste de España), se producen eventos periódicos de mortalidad, como la caza de aves acuáticas. Los restos no recuperados de la caza generan pulsos predecibles de carroña que diversas especies de carroñeros aprovechan. Este estudio describe la comunidad de carroñeros vertebrados terrestres y sus patrones de consumo de carroñas que simulan eventos de caza en El Hondo. Se colocaron 39 carroñas de aves acuáticas tras eventos de caza en tres áreas adyacentes a cotos y se monitoreó su consumo con cámaras trampa. Registramos siete especies de carroñeros destacando el zorro rojo (Vulpes vulpes) y la rata parda (Rattus norvegicus) como principales consumidores de carroña, aunque esta última mostró menor eficiencia, aumentando el tiempo de permanencia de las carroñas en el ecosistema. También identificamos otras especies de vertebrados, como aves insectívoras, que consumieron invertebrados atraídos por las carroñas. Los resultados mostraron que los restos de la caza de aves acuáticas son aprovechados por una diversa comunidad de vertebrados en los humedales. Además, nuestros resultados sugieren que la caza en áreas protegidas puede favorecer la presencia de especies invasoras, como la rata parda. Esto subraya la necesidad de gestionar las interacciones entre las actividades humanas y las comunidades de carroñeros, crucial para la conservación efectiva de ecosistemas amenazados y esenciales para la biodiversidad, como los humedales.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Model-Driven Approach for Making Citizen Science Data FAIR

  • Alvarez Luna, Reynaldo
  • Garrigós, Irene
  • Zubcoff, Jose
  • González Mora, César
  • Garrigós, Irene|||/items/50e21847-f541-4051-8e6d-4064e0e80ea3
  • González Mora, César|||/items/bffa7ade-023b-4e37-893a-cf0aa181e2d4
  • Zubcoff, Jose|||/items/c8d086dc-e561-4ce4-9d9b-2db5c48a75f5
Citizen Science (CS) initiatives have proliferated in different scientific and social fields, producing vast amounts of data. Existing CS projects usually adopt PPSR Core as a data and metadata standard. However, these projects are still not FAIR (Findable, Accessible, Interoperable and Reusable)-compliant. We propose to use DCAT as a data and metadata standard since it helps to improve the interoperability of CS data catalogs and all the FAIR features. For this purpose, in this paper we present a model-driven approach to make CS data FAIR. Our approach has the following contributions: (i) the definition of a metamodel based on PPSR Core, (ii) the definition of a DCAT profile for CS, (iii) a definition of set of automated transformations from PPSR Core to DCAT. Finally, the implementation of the model-driven process has been validated by evaluating several FAIR metrics. The results show that our proposal has significantly improved the FAIR quality of CS projects.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Multivariate Deep Learning for Bird Species Sighting Forecasting: A Case Study in Las Lagunas de la Mata y Torrevieja Natural Park

  • Morales-García, Juan
  • García-Tapia-Mateo, Paula
  • Melgarejo-Hernández, José
  • Garrigós, Irene
  • Mazón, Jose-Norberto
  • Morales-García, Juan|||/items/392294ef-1f4d-46ea-acdd-b1c285f28bea
  • García-Tapia-Mateo, Paula|||/items/1df5b3ce-4fd2-463b-8f82-68e9b5376d8f
  • Melgarejo-Hernández, José|||/items/3f8fa674-9e56-41ad-bc1d-0daef6e2828b
  • Garrigós, Irene|||/items/50e21847-f541-4051-8e6d-4064e0e80ea3
  • Mazón, Jose-Norberto|||/items/31f8766d-f389-4889-ba06-adeb367a0753
Accurate prediction of bird species sightings is vital for enhancing tourism planning and supporting biodiversity management, allowing visitors to natural parks to optimize their schedules for birdwatching experiences. This study focuses on the Natural Park of Las Lagunas de la Mata y Torrevieja (Alicante, Spain), where advanced artificial intelligence (AI) models were developed to forecast the presence of multiple bird species simultaneously through a multivariate modeling strategy that integrates shared temporal dynamics and interspecific predictive relationships among species. The analysis revealed that data granularity significantly impacts the performance of predictive models. High-frequency datasets exhibited substantial noise and a high proportion of zero-valued observations, making daily forecasting particularly challenging. In contrast, aggregated datasets with weekly or monthly intervals exhibited clearer seasonal patterns and reduced noise, favoring recurrent architectures such as LSTM and CNNLSTM, whose relative performance varied depending on the temporal granularity and evaluation metric. The final configurations were evaluated through recursive multi-step forecasts from multiple temporal origins and random seeds, and a target-only comparison showed that using all selected species as input reduced RMSE and MAE compared with models trained only on the target species. Additionally, a web augmenterwas implemented to enhance theWikipedia page for this natural park, offering interactive visualizations such as dynamic maps displaying species-specific bird sighting predictions. This approach facilitates tourism planning and illustrates the potential of integrating AI-driven multivariate forecasting with web augmentation technologies to support biodiversity monitoring and public engagement.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Exploring Content-Based Catalogs for Enhanced Discovery Services in Data Spaces

  • Morejón, Adriana
  • Berenguer, Alberto
  • Espona, Lucía de
  • Tomás, David
  • Mazón, Jose-Norberto
  • Espona, Lucía de|||/items/8fcc5d80-ab24-4d59-b540-ece3a6278503
  • Mazón, Jose-Norberto|||/items/31f8766d-f389-4889-ba06-adeb367a0753
  • Tomás, David|||/items/cf031fc3-3c30-454b-a6df-3762c29cc296
  • Berenguer, Alberto|||/items/6bc5210d-69fb-4751-bc6d-634368d65349
  • Morejón, Adriana|||/items/9d2a15c0-e2f1-4731-a508-bd26af966fdd
In the realm of data sharing, effective data discovery is critical for fostering collaboration and innovation across organizations. Data spaces merge the interoperability and secure sharing features of data ecosystems with the transactional and economic aspects of data markets, enabling seamless data exchange among data providers and consumers while preserving data sovereignty. Central to this paradigm is the data catalog, an entity that handles metadata and provides it for data discovery services. However, traditional data catalogs rely heavily on metadata related to high-level representation of data, as well as the overall features of datasets (e.g., dataset name, license or keywords, following standards such as DCAT). This limitation hampers data discovery, as these metadata alone may not effectively describe datasets to fully convey the relevance of datasets. To address this challenge, this paper proposes content-based catalogs to enhance data discovery within data spaces. Our approach for content-based catalogs incorporates three key assets for data consumers to discover relevant datasets and evaluate their utility before accessing them: (i) high-quality structural metadata for datasets; (ii) representative data samples from the dataset; and (iii) a discovery service for searching relevant datasets. Our novel content-based catalog reduces the risk of unintended exposure while still showcasing the value of data, thus preserving the interests of both data providers and consumers within data spaces.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Carrion ecology in inland aquatic ecosystems: a systematic review

  • Orihuela-Torres, Adrian
  • Morales-Reyes, Zebensui
  • Hermoso, Virgilio
  • Picazo Mota, Félix
  • Sánchez Fernández, David
  • Pérez-García, Juan M.
  • Botella, Francisco
  • Sánchez-Zapata, José A.
  • Sebastián-González, Esther
  • Orihuela-Torres, Adrian|||/items/88c3e834-f7ed-4ec8-b727-7506929b6eee
  • Sebastián-González, Esther|||/items/c53fd431-7978-4887-bee5-296d259dab12
Carrion ecology, i.e. the decomposition and recycling of dead animals, has traditionally been neglected as a key process in ecosystem functioning. Similarly, despite the large threats that inland aquatic ecosystems (hereafter, aquatic ecosystems) face, the scientific literature is still largely biased towards terrestrial ecosystems. However, there has been an increasing number of studies on carrion ecology in aquatic ecosystems in the last two decades, highlighting their key role in nutrient recirculation and disease control. Thus, a global assessment of the ecological role of scavengers and carrion in aquatic ecosystems is timely. Here, we systematically reviewed scientific articles on carrion ecology in aquatic ecosystems to describe current knowledge, identify research gaps, and promote future studies that will deepen our understanding in this field. We found 206 relevant studies, which were highly biased towards North America, especially in lotic ecosystems, covering short time periods, and overlooking seasonality, a crucial factor in scavenging dynamics. Despite the low number of studies on scavenger assemblages, we recorded 55 orders of invertebrates from 179 families, with Diptera and Coleoptera being the most frequent orders. For vertebrates, we recorded 114 species from 40 families, with birds and mammals being the most common. Our results emphasise the significance of scavengers in stabilising food webs and facilitating nutrient cycling within aquatic ecosystems. Studies were strongly biased towards the assessment of the ecosystem effects of carrion, particularly of salmon carcasses in North America. The second most common research topic was the foraging ecology of vertebrates, which was mostly evaluated through sporadic observations of carrion in the diet. Articles assessing scavenger assemblages were scarce, and only a limited number of these studies evaluated carrion consumption patterns, which serve as a proxy for the role of scavengers in the ecosystem. The ecological functions performed by carrion and scavengers in aquatic ecosystems were diverse. The main ecological functions were carrion as food source and the role of scavengers in nutrient cycling, which appeared in 52.4% (N = 108) and 46.1% (N = 95) of publications, respectively. Ecosystem threats associated with carrion ecology were also identified, the most common being water eutrophication and carrion as source of pathogens (2.4%; N = 5 each). Regarding the effects of carrion on ecosystems, we found studies spanning all ecosystem components (N = 85), from soil or the water column to terrestrial vertebrates, with a particular focus on aquatic invertebrates and fish. Most of these articles found positive effects of carrion on ecosystems (e.g. higher species richness, abundance or fitness; 84.7%; N = 72), while a minority found negative effects, changes in community composition, or even no effects. Enhancing our understanding of scavengers and carrion in aquatic ecosystems is crucial to assessing their current and future roles amidst global change, mainly for water–land nutrient transport, due to changes in the amount and speed of nutrient movement, and for disease control and impact mitigation, due to the predicted increase in occurrence and magnitude of mortality events in aquatic ecosystems.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Contextual word embeddings for tabular data search and integration

  • Pilaluisa, José
  • Tomás, David
  • Navarro Colorado, Borja
  • Mazón, Jose-Norberto
  • Mazón, Jose-Norberto|||/items/31f8766d-f389-4889-ba06-adeb367a0753
  • Navarro Colorado, Borja|||/items/e3aa6827-9508-46f7-833a-2f084cd5e24a
  • Tomás, David|||/items/cf031fc3-3c30-454b-a6df-3762c29cc296
This paper presents a new approach to retrieve and further integrate tabular datasets (collections of rows and columns) using union and join operations. In this work, both processes were carried out using a similarity measure based on contextual word embeddings, which allows finding semantically similar tables and overcome the recall problem of lexical approaches based on string similarity. This work is the first attempt to use contextual word embeddings in the whole pipeline of table search and integration, including for the first time their use in the join operation. A comprehensive analysis of their performance was carried out on both retrieving and integrating tabular datasets, comparing them with context-free models. Column headings and cell values were used as contextual information and their impact on each task was evaluated. The results revealed that contextual models significantly outperform context-free models and a traditional weighting schema in ad hoc table retrieval. In the data integration task, contextual models also improved the results on union operation compared to context-free approaches.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Tabular open government data search for data spaces based on word embeddings

  • Berenguer, Alberto
  • Tomás, David
  • Mazón, Jose-Norberto
  • Mazón, Jose-Norberto|||/items/31f8766d-f389-4889-ba06-adeb367a0753
  • Tomás, David|||/items/cf031fc3-3c30-454b-a6df-3762c29cc296
  • Berenguer, Alberto|||/items/6bc5210d-69fb-4751-bc6d-634368d65349
Nowadays, data spaces are envisioned as a prominent mechanism for data sharing, boosting growth and creating value. Open government data providers should be considered as important participants in data space reference infrastructures, since open data portal initiatives are adopted by most of the governments to supply their public sector information. However, open data is mostly published in the form of tabular data such as spreadsheets or CSV files. Therefore, reusing open data in data space is challenging due to the friction that may occur when combining the use of data shared in data spaces and the use of tabular data published in open government portals. To alleviate this situation, tabular open data search engines can be a promising solution. Actually, most open data portals allow reusers to retrieve and federate tabular open data by means of a keyword-based search engine over metadata. Unfortunately, these search engines rely on the (not so often good enough) metadata quality, which must be complete, descriptive, and representative of the content. Moreover, keyword-based search is not always an adequate solution for retrieving open data, since it does not consider their tabular nature and search results can be useless for reusers (e.g., when they attempt to find data useful for extending rows or columns of a given tabular dataset). To overcome these problems, this paper presents an approach that uses word embeddings for tabular open data search based on unionability and joinability. Our approach could be seamlessly integrated in a data space infrastructure. A prototype of our approach has been developed. Finally, both, an intrinsic and an extrinsic evaluation with end users, have been carried out.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

POSEIDON: A Data Augmentation Tool for Small Object Detection Datasets in Maritime Environments

  • Ruiz Ponce, Pablo
  • Ortiz Pérez, David
  • Garcia-Rodriguez, Jose
  • Kiefer, Benjamin
  • Garcia-Rodriguez, Jose|||/items/d5bc18f8-44db-4723-b291-5849321e9e69
  • Ortiz Pérez, David|||/items/e77e67d5-78fc-4170-a005-b6d3fd3ca79e
  • Ruiz Ponce, Pablo|||/items/bf90946b-d388-45f2-bbc1-53d580a02453
Certain fields present significant challenges when attempting to train complex Deep Learning architectures, particularly when the available datasets are limited and imbalanced. Real-time object detection in maritime environments using aerial images is a notable example. Although SeaDronesSee is the most extensive and complete dataset for this task, it suffers from significant class imbalance. To address this issue, we present POSEIDON, a data augmentation tool specifically designed for object detection datasets. Our approach generates new training samples by combining objects and samples from the original training set while utilizing the image metadata to make informed decisions. We evaluate our method using YOLOv5 and YOLOv8 and demonstrate its superiority over other balancing techniques, such as error weighting, by an overall improvement of 2.33% and 4.6%, respectively.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Shot Boundary Detection with 3D Depthwise Convolutions and Visual Attention

  • Esteve Brotons, Miguel José
  • Lucendo, Francisco Javier
  • Rodríguez Juan, Javier
  • Garcia-Rodriguez, Jose
  • Garcia-Rodriguez, Jose|||/items/d5bc18f8-44db-4723-b291-5849321e9e69
  • Rodríguez Juan, Javier|||/items/4f464549-7f4d-4a47-9602-a42f7e1b5975
Shot boundary detection is the process of identifying and locating the boundaries between individual shots in a video sequence. A shot is a continuous sequence of frames that are captured by a single camera, without any cuts or edits. Recent investigations have shown the effectiveness of the use of 3D convolutional networks to solve this task due to its high capacity to extract spatiotemporal features of the video and determine in which frame a transition or shot change occurs. When this task is used as part of a scene segmentation use case with the aim of improving the experience of viewing content from streaming platforms, the speed of segmentation is very important for live and near-live use cases such as start-over. The problem with models based on 3D convolutions is the large number of parameters that they entail. Standard 3D convolutions impose much higher CPU and memory requirements than do the same 2D operations. In this paper, we rely on depthwise separable convolutions to address the problem but with a scheme that significantly reduces the number of parameters. To compensate for the slight loss of performance, we analyze and propose the use of visual self-attention as a mechanism of improvement.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Face Recognition Bias Assessment through Quality Estimation Models

  • López Payá, Luis
  • Cordoba, Pedro
  • Sánchez Pérez, Ángela
  • Barrachina, Javier
  • Benavent-Lledó, Manuel
  • Mulero Pérez, David
  • Garcia-Rodriguez, Jose
  • Benavent-Lledó, Manuel|||/items/0d1bda20-de83-4080-97c9-1820faf481da
  • Garcia-Rodriguez, Jose|||/items/d5bc18f8-44db-4723-b291-5849321e9e69
  • Mulero Pérez, David|||/items/e3a342d3-f8d6-4010-bf87-a509394c0d36
Recent advances in facial recognition technology have achieved outstanding performance, but unconstrained face recognition remains an ongoing issue. Facial-image-quality-evaluation algorithms evaluate the quality of the input samples, providing crucial information about the accuracy of recognition decisions. By doing so, this can lead to improved results in challenging scenarios. In recent years, significant progress has been made in assessing the quality of facial images. The computation of quality scores has become highly precise and closely correlated with the model results. In this paper, we reviewed and analyzed the existing biases of cutting-edge quality-estimation techniques for face recognition. Our experimentation focused on the quality estimators developed by MagFace, FaceQNet, and SER-FIQ and were evaluated on the CelebA reference dataset. A study of bias in the face-recognition model was conducted by analyzing the quality scores presented in each article. This allowed for an examination of existing biases within both the quality estimators and the face-recognition models.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Servibirds: Quantitative Assessment of the Ecosystem Services Provided by Native Birds in Spain, Servibirds: Evaluación cuantitativa de los servicios ecosistémicos proporcionados por las aves nativas en España

  • Sebastián-González, Esther
  • Carrión Jaén, Susana
  • Pérez-Granados, Cristian
  • López Iborra, Germán M.
  • Botella, Francisco
  • Pérez, Claudia
  • Rocher, Gloria
  • Pérez-García, Juan M.
  • García-Rodríguez, José
  • Sánchez-Zapata, José A.
  • Orihuela-Torres, Adrian
  • Sebastián-González, Esther|||/items/c53fd431-7978-4887-bee5-296d259dab12
  • López Iborra, Germán M.|||/items/3559b8a1-fa00-454a-8392-d36b796af5b9
  • Orihuela-Torres, Adrian|||/items/88c3e834-f7ed-4ec8-b727-7506929b6eee
Birds are key ecosystem service providers given the wide range of services in which they are involved, their outstanding mobility and large population sizes. However, we lack a comprehensive framework to evaluate the ecosystem services (ES) provided by bird species at large spatial scales. Here, we introduce ServiBirds, an innovative database meticulously designed to quantify the ES delivered by bird species, using Spain, a species-rich country, as our study model. The database describes the species-level values in 12 different provisioning, supporting/regulating and cultural ES for 378 bird species from 73 families. For each species, the supporting/regulating services were weighted by its field metabolic rate and its population size in Spain, to enable a more precise view of the current role of the species in such services. In addition, birds provide diverse other ES, especially aesthetic, ecotouristic, as pest controllers and as seed dispersers. The most important providers of supporting/regulating services in Spain included some, such as the Eurasian Magpie Pica pica and the Common Blackbird Turdus merula, that provide several services and specialists, such as the Griffon Vulture Gyps fulvus, that provide a single service. For cultural services, the top species were those, such as the Red-legged Partridge Alectoris rufa, Golden Eagle Aquila chrysaetos or European Goldfinch Carduelis carduelis, that provide multiple services. Our study underlines the important role that birds play in ecosystem conservation and for human wellbeing. Moreover, the proposed framework can be adapted to other regions, and even taxonomic groups. We hope this study acts as a catalyst to better understand and evaluate the ES provided by birds, thereby serving as a tool for bird conservation and ecosystem management.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Análisis y caracterización de los potenciales visitantes de un espacio natural protegido litoral: el caso del Parque Natural de las Lagunas de la Mata y Torrevieja (Alicante), Analysis and characterisation of potential visitors to a protected coastal natural area: the case of the Lagunas de la Mata y Torrevieja Natural Park (Alicante)

  • Pinar Pinar, Jennifer
  • Celdrán-Bernabéu, Marco Antonio
  • Sebastián-González, Esther
  • Orihuela-Torres, Adrian
  • Celdrán-Bernabéu, Marco Antonio|||/items/8e8f46aa-40c7-4d5c-829c-d50dc85757eb
  • Sebastián-González, Esther|||/items/c53fd431-7978-4887-bee5-296d259dab12
  • Orihuela-Torres, Adrian|||/items/88c3e834-f7ed-4ec8-b727-7506929b6eee
El presente trabajo de investigación trata de aproximarse al nivel de conocimiento y atracción del Parque Natural de las Lagunas de La Mata y Torrevieja (Alicante), así como profundizar en los factores determinantes de su visita. Todo en el marco evolutivo de los destinos de sol y playa, y la necesidad de establecer nuevas líneas de trabajo orientadas a la cualificación y diversificación del turismo litoral, gracias a la puesta en valor de recursos infravalorados que promuevan productos y servicios sostenibles. Para ello, esta investigación utiliza una metodología combinada sustentada en la revisión de la literatura científica relacionada con los espacios naturales protegidos y su potencialidad para diversificar, diferenciar y cualificar destinos turísticos. Además, se utilizan técnicas cuantitativas y cualitativas, concretamente el desarrollo de un cuestionario estructurado dirigido a potenciales visitantes de este espacio natural protegido del sureste español, así como entrevistas en profundidad a los agentes directamente relacionados con la gestión y promoción de este espacio natural. Como principales resultados, este trabajo subraya la importancia de tener en cuenta las motivaciones turísticas y resalta la relevancia de aprovechar el atractivo de las aves como un recurso turístico de primer nivel.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Visual WetlandBirds Dataset: Bird Species Identification and Behavior Recognition in Videos

  • Rodríguez Juan, Javier
  • Ortiz Pérez, David
  • Benavent-Lledó, Manuel
  • Mulero Pérez, David
  • Ruiz Ponce, Pablo
  • Orihuela-Torres, Adrian
  • Garcia-Rodriguez, Jose
  • Sebastián-González, Esther
  • Benavent-Lledó, Manuel|||/items/0d1bda20-de83-4080-97c9-1820faf481da
  • Garcia-Rodriguez, Jose|||/items/d5bc18f8-44db-4723-b291-5849321e9e69
  • Mulero Pérez, David|||/items/e3a342d3-f8d6-4010-bf87-a509394c0d36
  • Orihuela-Torres, Adrian|||/items/88c3e834-f7ed-4ec8-b727-7506929b6eee
  • Ortiz Pérez, David|||/items/e77e67d5-78fc-4170-a005-b6d3fd3ca79e
  • Rodríguez Juan, Javier|||/items/4f464549-7f4d-4a47-9602-a42f7e1b5975
  • Ruiz Ponce, Pablo|||/items/bf90946b-d388-45f2-bbc1-53d580a02453
  • Sebastián-González, Esther|||/items/c53fd431-7978-4887-bee5-296d259dab12
The current biodiversity loss crisis makes animal monitoring a relevant field of study. In light of this, data collected through monitoring can provide essential insights, and information for decision-making aimed at preserving global biodiversity. Despite the importance of such data, there is a notable scarcity of datasets featuring videos of birds, and none of the existing datasets offer detailed annotations of bird behaviors in video format. In response to this gap, our study introduces the first fine-grained video dataset specifically designed for bird behavior detection and species classification. This dataset addresses the need for comprehensive bird video datasets and provides detailed data on bird actions, facilitating the development of deep learning models to recognize these, similar to the advancements made in human action recognition. The proposed dataset comprises 178 videos recorded in Spanish wetlands, capturing 13 different bird species performing 7 distinct behavior classes. In addition, we also present baseline results using state of the art models on two tasks: bird behavior recognition and species classification.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

A global assessment of BirdNET performance: Differences among continents, biomes, and species

  • Funosas, David
  • Sebastián-González, Esther
  • Morant, Jon
  • Marín Gómez, Oscar H.
  • Mendoza, Irene
  • Mohedano-Munoz, Miguel A.
  • Santamaría, Eduardo
  • Bastianelli, Giulia
  • Márquez-Rodríguez, Alba
  • Budka, Michał
  • Bota, Gerard
  • Alonso-Moya, Cristina D.
  • De la Peña-Rubio, José M.
  • García de la Morena, Eladio L.
  • Santa-Cruz, Manu
  • De la Nava, Pablo
  • Fernández-Tizón, Mario
  • Sánchez-Mateos, Hugo
  • Barrero, Adrián
  • Traba, Juan
  • Osiejuk, Tomasz
  • Hart, Patrick J.
  • Navine, Amanda K.
  • Montoya Muñoz, Andrés F.
  • De Araújo, Carlos B.
  • Rosa, Gabriel L.M.
  • Torres, Ingrid M.D.
  • Catalano, Ana L.C.
  • Simões, Cassio Rachid
  • Llusia, Diego
  • Morales, Manuel B.
  • Acebes, Pablo
  • Medina, Juan A.
  • Brown, Nicholas
  • Astaras, Christos
  • Karmiris, Ilias
  • Navarrete, Elizabeth
  • Cauchoix, Maxime
  • Barbaro, Luc
  • Arend, Dominik
  • Müeller, Sandra
  • González-García, Fernando
  • González-Romero, Alberto
  • Mammides, Christos
  • Pontikis, Michaelangelo
  • Jacuzzi, Giordano
  • Olden, Julian D.
  • Bombaci, Sara P.
  • Marcacci, Gabriel
  • Jacot, Alain
  • Zurano, Juan P.
  • Gangenova, Elena
  • Varela, Diego
  • Di Sallo, Facundo
  • Zurita, Gustavo A.
  • Atemasov, Andrey
  • Tremblay, Junior A.
  • Lamarre, Vincent
  • Hutschenreiter, Anja
  • Monroy-Ojeda, Alan
  • Díaz-Vallejo, Mauricio
  • Chaparro-Herrera, Sergio
  • Briers, Robert A.
  • Sousa-Lima, Renata
  • Pinheiro, Thiago
  • da Silva, Wigna C.
  • Calvente, Alice
  • Paz, Raiane V.
  • Salustio-Gomes, Carlos
  • Oliveira-Júnior, Dorgival Diógenes
  • Lima-Santos, Cicero S.
  • Pichorim, Mauro
  • Dal Molin, Anamaria
  • Antonelli, Alexandre
  • Gogoleva, Svetlana
  • Palko, Igor
  • Trong, Hiếu V.
  • Duarte, Marina H.L.
  • Saturnino, Natalia dos Santos
  • Silva, Samuel R.
  • Rainho, Ana
  • Lopes, Paula
  • Schuchmann, Karl-L.
  • Marques, Marinêz I.
  • Tissiani, Ana S. de Oliverira
  • Littlewood, Nick A.
  • Tuanmu, Mao-Ning
  • Kepfer-Rojas, Sebastian
  • Aguilera, Andrea L.
  • Brotons, Lluís
  • Feldman, Mariano J.
  • Imbeau, Louis
  • Panwar, Pooja
  • Weed, Aaron S.
  • Dehwal, Anant
  • Attisano, Alfredo
  • Theuerkauf, Jörn
  • Goodale, Eben
  • Darras, Kevin F.A.
  • Pérez-Granados, Cristian
  • Sebastián-González, Esther|||/items/c53fd431-7978-4887-bee5-296d259dab12
  • Morant, Jon|||/items/f5c63ce0-a69a-483c-b591-c2e7b22a83f8
Recent advances in machine learning have accelerated automated species detection across diverse ecological domains, enabling large-scale, non-invasive monitoring of biodiversity. In ornithological research, the combination of passive acoustic monitoring (PAM) and rapidly-developing novel identification tools such as BirdNET—a deep learning–based sound recognition algorithm—offers new opportunities for surveying vocally active bird communities. Here, we present the first worldwide evaluation of BirdNET using 4224 one-minute recordings from 67 sites across all continents annotated by local experts. More specifically, we assessed the capacity of BirdNET to accurately identify individual vocalizations and characterize bird communities based on the automated analysis of passively collected soundscapes. We further analyzed how its performance varies across continents, biomes, species, and minimum confidence thresholds. The proportion of correct BirdNET predictions (precision) was generally high and consistent across continents (range: 0.57–0.71) and biomes (range: 0.55–0.76). In contrast, the proportion of vocalizations successfully detected (recall) was generally lower and more heterogeneous across continents (range: 0.24–0.52) and biomes (range: 0.34–0.72), reflecting differences in species coverage and local ecological context. BirdNET predictive power, as measured by the Precision-Recall Area Under the Curve (PR AUC; higher values indicating better performance), was highest in North America, Oceania, and Europe (range: 0.16–0.23), moderate in Central/South America (0.13), and lowest in Africa and Asia (range: 0.03–0.04). Species-specific analyses revealed substantial heterogeneity in detection accuracy, with optimal confidence thresholds varying widely by species and analytical goal. Our results establish a global reference point for BirdNET reliability and highlight where algorithmic refinement and expanded acoustic sampling are most needed.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Leveraging Large Language Models for Sensor Data Retrieval

  • Berenguer, Alberto
  • Morejón, Adriana
  • Tomás, David
  • Mazón, Jose-Norberto
  • Mazón, Jose-Norberto|||/items/31f8766d-f389-4889-ba06-adeb367a0753
  • Tomás, David|||/items/cf031fc3-3c30-454b-a6df-3762c29cc296
  • Berenguer, Alberto|||/items/6bc5210d-69fb-4751-bc6d-634368d65349
  • Morejón, Adriana|||/items/9d2a15c0-e2f1-4731-a508-bd26af966fdd
The growing significance of sensor data in the development of information technology services finds obstacles due to disparate data presentations and non-adherence to FAIR principles. This paper introduces a novel approach for sensor data gathering and retrieval. The proposal leverages large language models to convert sensor data into FAIR-compliant formats and to provide word embedding representations of tabular data for subsequent exploration, enabling semantic comparison. The proposed system comprises two primary components. The first focuses on gathering data from sensors and converting it into a reusable structured format, while the second component aims to identify the most relevant sensor data to augment a given user-provided dataset. The evaluation of the proposed approach involved comparing the performance of various large language models in generating representative word embeddings for each table to retrieve related sensor data. The results show promising performance in terms of precision and MRR (0.90 and 0.94 for the best-performing model, respectively), indicating the system’s ability to retrieve pertinent sensor data that fulfil user requirements.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Detecting and locating trending places using multimodal social network data

  • Lucas, Luis
  • Tomás, David
  • Garcia-Rodriguez, Jose
  • Garcia-Rodriguez, Jose|||/items/d5bc18f8-44db-4723-b291-5849321e9e69
  • Lucas, Luis|||/items/3c17c0cd-e8e4-4860-8a08-3ba5fb81b36b
  • Tomás, David|||/items/cf031fc3-3c30-454b-a6df-3762c29cc296
This paper presents a machine learning-based classifier for detecting points of interest through the combined use of images and text from social networks. This model exploits the transfer learning capabilities of the neural network architecture CLIP (Contrastive Language-Image Pre-Training) in multimodal environments using image and text. Different methodologies based on multimodal information are explored for the geolocation of the places detected. To this end, pre-trained neural network models are used for the classification of images and their associated texts. The result is a system that allows creating new synergies between images and texts in order to detect and geolocate trending places that has not been previously tagged by any other means, providing potentially relevant information for tasks such as cataloging specific types of places in a city for the tourism industry. The experiments carried out reveal that, in general, textual information is more accurate and relevant than visual cues in this multimodal setting.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Using Large Language Models to Enhance the Reusability of Sensor Data

  • Berenguer, Alberto
  • Morejón, Adriana
  • Tomás, David
  • Mazón, Jose-Norberto
  • Mazón, Jose-Norberto|||/items/31f8766d-f389-4889-ba06-adeb367a0753
  • Tomás, David|||/items/cf031fc3-3c30-454b-a6df-3762c29cc296
  • Berenguer, Alberto|||/items/6bc5210d-69fb-4751-bc6d-634368d65349
  • Morejón, Adriana|||/items/9d2a15c0-e2f1-4731-a508-bd26af966fdd
The Internet of Things generates vast data volumes via diverse sensors, yet its potential remains unexploited for innovative data-driven products and services. Limitations arise from sensor-dependent data handling by manufacturers and user companies, hindering third-party access and comprehension. Initiatives like the European Data Act aim to enable high-quality access to sensor-generated data by regulating accuracy, completeness, and relevance while respecting intellectual property rights. Despite data availability, interoperability challenges impede sensor data reusability. For instance, sensor data shared in HTML formats requires an intricate, time-consuming processing to attain reusable formats like JSON or XML. This study introduces a methodology aimed at converting raw sensor data extracted from web portals into structured formats, thereby enhancing data reusability. The approach utilises large language models to derive structured formats from sensor data initially presented in non-interoperable formats. The effectiveness of these language models was assessed through quantitative and qualitative evaluations in a use case involving meteorological data. In the proposed experiments, GPT-4, the best performing LLM tested, demonstrated the feasibility of this methodology, achieving a precision of 93.51% and a recall of 85.33% in converting HTML to JSON/XML, thus confirming its potential in obtaining reusable sensor data.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Word embeddings for retrieving tabular data from research publications

  • Berenguer, Alberto
  • Mazón, Jose-Norberto
  • Tomás, David
  • Mazón, Jose-Norberto|||/items/31f8766d-f389-4889-ba06-adeb367a0753
  • Tomás, David|||/items/cf031fc3-3c30-454b-a6df-3762c29cc296
  • Berenguer, Alberto|||/items/6bc5210d-69fb-4751-bc6d-634368d65349
Scientists face challenges when finding datasets related to their research problems due to the limitations of current dataset search engines. Existing tools for searching research datasets rely on publication content or metadata, do not considering the data contained in the publication in the form of tables. Moreover, scientists require more elaborate inputs and functionalities to retrieve different parts of an article, such as data presented in tables, based on their search purposes. Therefore, this paper proposes a novel approach to retrieve relevant tabular datasets from publications. The input of our system is a research problem stated as an abstract from a scientific paper, and the output is a set of relevant tables from publications that are related to the research problem. This approach aims to provide a better solution for scientists to find useful datasets that support them in addressing their research problems. To validate this approach, experiments were conducted using word embedding from different language models to calculate the semantic similarity between abstracts and tables. The results showed that contextual models significantly outperformed non-contextual models, especially when pre-trained with scientific data. Furthermore, the importance of context was found to be crucial for improving the results.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Are cats more equal than dogs?

  • Durá-Alemañ, Carlos Javier
  • Almarcha, Francisco
  • Sánchez-Zapata, José A.
  • Sebastián-González, Esther
  • Martínez Camacho, Elvira
  • Trouwborst, Arie
  • Sebastián-González, Esther|||/items/c53fd431-7978-4887-bee5-296d259dab12
The impact of cats and dogs on biodiversity has been the focus of intense debate. Here, we review the scientific literature on the impacts themselves and discuss societal perception of cats and dogs from a cultural point of view. This includes varying feelings of fear and appreciation, related to differences in risks posed to people, animal size, difficulty in handling, and behavior. We then analyze existing international rules on the management of cats and dogs, particularly international treaties and European Union legislation. The documented adverse biodiversity impacts of cats appear to be significantly greater than those of dogs, but in many countries dogs are prevented from roaming free, whereas cats are often allowed to roam freely on a massive scale. This appears to run counter to many legal obligations. A mismatch thus appears to exist between science on the one hand and law on the other hand, which may partly be explained by differing social perceptions. The results of our analysis justify a more homogeneous legal treatment for dogs and cats with regard to their freedom of movement, through a tightening of the rules that affect cats.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Advancing smart tourism destinations: A case study using bidirectional encoder representations from transformers-based occupancy predictions in Torrevieja (Spain)

  • Giménez Manuel, José Ginés
  • Giner Pérez de Lucia, José
  • Celdrán-Bernabéu, Marco Antonio
  • Mazón, Jose-Norberto
  • Cano Escribá, Juan Carlos
  • Cecilia Canales, José María
  • Celdrán-Bernabéu, Marco Antonio|||/items/8e8f46aa-40c7-4d5c-829c-d50dc85757eb
  • Mazón, Jose-Norberto|||/items/31f8766d-f389-4889-ba06-adeb367a0753
Tourism represents a crucial socio-economic pillar globally, yet the multifaceted challenges it poses necessitate innovative management approaches. The paradigm of smart tourism harnesses advanced data analytics tools to promote both profitability and sustainability in tourist destinations, leading to new levels of destination smartness. Accurate tourist occupancy prediction, particularly in areas dominated by second-home accommodations where traditional hospitality data may be insufficient, plays a key role in optimising tourism management. To address this data gap, our prior research employed ARIMA modelling on Airbnb booking time series and analysed tourism-related Twitter conversations to forecast occupancy levels in Torrevieja (Alicante); a prominent second-home tourism destination in Southeastern Spain. In this extended study, we delve deeper into the realm of social sensing by utilising bidirectional encoder representations from transformers (BERT) for topic modelling. Our methodology involves the processing and analysis of Twitter data to identify prominent themes related to Torrevieja. The findings not only reveal nuanced perceptions and discussions about the destination but also underscore the effectiveness of BERT in capturing intricate topic dynamics. Importantly, this work highlights how the alignment of specific topics with booking patterns can further enhance predictive accuracy for tourist occupancy, presenting a robust toolkit for stakeholders in the tourism sector.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

A Video Mosaicing-Based Sensing Method for Chicken Behavior Recognition on Edge Computing Devices

  • Teterja, Dmitrij
  • Garcia-Rodriguez, Jose
  • Azorin-Lopez, Jorge
  • Sebastián-González, Esther
  • Nedić, Daliborka
  • Leković, Dalibor
  • Knežević, Petar
  • Drajić, Dejan
  • Vukobratović, Dejan
  • Azorin-Lopez, Jorge|||/items/d43d029b-14bf-4dac-9bda-ed08e213bb1d
  • Garcia-Rodriguez, Jose|||/items/d5bc18f8-44db-4723-b291-5849321e9e69
  • Sebastián-González, Esther|||/items/c53fd431-7978-4887-bee5-296d259dab12
Chicken behavior recognition is crucial for a number of reasons, including promoting animal welfare, ensuring the early detection of health issues, optimizing farm management practices, and contributing to more sustainable and ethical poultry farming. In this paper, we introduce a technique for recognizing chicken behavior on edge computing devices based on video sensing mosaicing. Our method combines video sensing mosaicing with deep learning to accurately identify specific chicken behaviors from videos. It attains remarkable accuracy, achieving 79.61% with MobileNetV2 for chickens demonstrating three types of behavior. These findings underscore the efficacy and promise of our approach in chicken behavior recognition on edge computing devices, making it adaptable for diverse applications. The ongoing exploration and identification of various behavioral patterns will contribute to a more comprehensive understanding of chicken behavior, enhancing the scope and accuracy of behavior analysis within diverse contexts.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

A Comprehensive Study on Pain Assessment from Multimodal Sensor Data

  • Benavent-Lledó, Manuel
  • Mulero Pérez, David
  • Ortiz Pérez, David
  • Rodríguez Juan, Javier
  • Berenguer-Agullo, Adrian
  • Psarrou, Alexandra
  • Garcia-Rodriguez, Jose
  • Benavent-Lledó, Manuel|||/items/0d1bda20-de83-4080-97c9-1820faf481da
  • Garcia-Rodriguez, Jose|||/items/d5bc18f8-44db-4723-b291-5849321e9e69
  • Mulero Pérez, David|||/items/e3a342d3-f8d6-4010-bf87-a509394c0d36
  • Ortiz Pérez, David|||/items/e77e67d5-78fc-4170-a005-b6d3fd3ca79e
  • Rodríguez Juan, Javier|||/items/4f464549-7f4d-4a47-9602-a42f7e1b5975
Pain assessment is a critical aspect of healthcare, influencing timely interventions and patient well-being. Traditional pain evaluation methods often rely on subjective patient reports, leading to inaccuracies and disparities in treatment, especially for patients who present difficulties to communicate due to cognitive impairments. Our contributions are three-fold. Firstly, we analyze the correlations of the data extracted from biomedical sensors. Then, we use state-of-the-art computer vision techniques to analyze videos focusing on the facial expressions of the patients, both per-frame and using the temporal context. We compare them and provide a baseline for pain assessment methods using two popular benchmarks: UNBC-McMaster Shoulder Pain Expression Archive Database and BioVid Heat Pain Database. We achieved an accuracy of over 96% and over 94% for the F1 Score, recall and precision metrics in pain estimation using single frames with the UNBC-McMaster dataset, employing state-of-the-art computer vision techniques such as Transformer-based architectures for vision tasks. In addition, from the conclusions drawn from the study, future lines of work in this area are discussed.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

A Federated Learning Architecture for Bird Species Classification in Wetlands

  • Mulero Pérez, David
  • Rodríguez Juan, Javier
  • Ramírez, Tamai
  • Benavent-Lledó, Manuel
  • Ruiz Ponce, Pablo
  • Ortiz Pérez, David
  • Garcia-Rodriguez, Jose
  • Sebastián-González, Esther
  • Benavent-Lledó, Manuel|||/items/0d1bda20-de83-4080-97c9-1820faf481da
  • Garcia-Rodriguez, Jose|||/items/d5bc18f8-44db-4723-b291-5849321e9e69
  • Mulero Pérez, David|||/items/e3a342d3-f8d6-4010-bf87-a509394c0d36
  • Ortiz Pérez, David|||/items/e77e67d5-78fc-4170-a005-b6d3fd3ca79e
  • Rodríguez Juan, Javier|||/items/4f464549-7f4d-4a47-9602-a42f7e1b5975
  • Ruiz Ponce, Pablo|||/items/bf90946b-d388-45f2-bbc1-53d580a02453
  • Sebastián-González, Esther|||/items/c53fd431-7978-4887-bee5-296d259dab12
  • Ramírez, Tamai|||/items/893d04e3-ff41-417a-8deb-db50429d715a
Federated learning allows models to be trained on edge devices with local data, eliminating the need to share data with a central server. This significantly reduces the amount of data transferred from edge devices to central servers, which is particularly important in rural areas with limited bandwidth resources. Despite the potential of federated learning to fine-tune deep learning models using data collected from edge devices in low-resource environments, its application in the field of bird monitoring remains underexplored. This study proposes a federated learning pipeline tailored for bird species classification in wetlands. The proposed approach is based on lightweight convolutional neural networks optimized for use on resource-constrained devices. Since the performance of federated learning is strongly influenced by the models used and the experimental setting, this study conducts a comprehensive comparison of well-known lightweight models such as WideResNet, EfficientNetV2, MNASNet, GoogLeNet and ResNet in different training settings. The results demonstrate the importance of the training setting in federated learning architectures and the suitability of the different models for bird species recognition. This work contributes to the wider application of federated learning in ecological monitoring and highlights its potential to overcome challenges such as bandwidth limitations.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

TorreviejaSensing: A Social Sensing Approach for Real‐ Time Sustainable Tourism Monitoring in Coastal Cities

  • Giner Pérez de Lucia, José
  • Fernández Pedauyé, Julio
  • Celdrán-Bernabéu, Marco Antonio
  • Mazón, Jose-Norberto
  • Cecilia
  • Mazón, Jose-Norberto|||/items/31f8766d-f389-4889-ba06-adeb367a0753
  • Celdrán-Bernabéu, Marco Antonio|||/items/8e8f46aa-40c7-4d5c-829c-d50dc85757eb
Tourism places increasing pressure on coastal cities, where seasonal congestion, fragmented urban development and changing citizen expectations challenge the sustainability of services and governance. To address these issues, we present TorreviejaSensing, a social sensing framework that transforms user-generated content into actionable evidence for policy and planning. The system combines multilingual natural language processing over X (Twitter) posts and Google Maps reviews, a policy-aware mapping of social signals to municipal strategic axes and a retrieval-augmented generation (RAG) chatbot that provides transparent evidence-grounded answers to policy queries. Applied to Torrevieja (Spain), the framework enables real-time tracking of mobility and cleanliness complaints, early detection of seasonal pain points and alignment of digital discourse with institutional strategies. A mixed-methods evaluation—including manual annotation of NLP outputs, baseline comparison and a pilot human assessment of chatbot responses—demonstrates both robustness and practical utility. Findings reveal strong seasonal dynamics, recurrent topic clusters consistent with known governance challenges and improved transparency of the RAG assistant compared to keyword-only approaches. Beyond the Torrevieja case, the framework is low-cost, transferable and provides a replicable model for integrating citizen discourse into sustainable urban tourism governance.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Understanding bird diversity in seasonally dry tropical forests: The role of landscape anthropization and chronic disturbance

  • Orihuela-Torres, Adrian
  • Tinoco, Boris A.
  • Sebastián-González, Esther
  • Jara-Guerrero, Andrea
  • Espinosa, Carlos Iván
  • Orihuela-Torres, Adrian|||/items/88c3e834-f7ed-4ec8-b727-7506929b6eee
  • Sebastián-González, Esther|||/items/c53fd431-7978-4887-bee5-296d259dab12
Understanding how species respond to human-induced habitat modification is essential for effective conservation and management. Among these modifications, forest chronic disturbance and landscape anthropization are key drivers threatening biodiversity. While these alterations are often associated with biodiversity loss, their effects are not always direct; rather, they frequently operate through indirect pathways, such as changes in vegetation structure. We used the bird community of seasonally dry tropical forest (SDTF) as a model system to evaluate both direct and indirect effects of these habitat modifications on biodiversity. SDTF provide an ideal context for this research, as they are simultaneously impacted by chronic degradation and landscape anthropization. Bird surveys were conducted across 51 point-counts, each visited nine times between February 2018 and March 2019, in Zapotillo, southwestern Ecuador. A total of 11,012 birds from 110 species, 39 families, and 18 orders were recorded. Our results reveal that landscape anthropization was the primary driver, influencing species richness and evenness, while chronic disturbance enhanced taxonomic distinctness. At the feeding guild level, chronic disturbance influenced the guilds in contrasting ways, both directly and indirectly, through changes in vegetation, such as reductions in canopy height and structural complexity. Our results underscore the importance of conserving well-preserved forest patches within heterogeneous mosaic of anthropized landscapes to support greater bird diversity and abundance while maintaining essential ecosystem services of different functional bird feeding guilds. This study underscores the need for tailored management strategies in SDTFs to address increasing anthropogenic pressures and ensure the long-term resilience of these unique ecosystems.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Soaring over open waters: horizontal winds provide lift to soaring migrants in weak thermal conditions

  • Škrábal, Jan
  • Krejčí, Šimon
  • Raab, Rainer
  • Sebastián-González, Esther
  • Literák, Ivan
  • Sebastián-González, Esther|||/items/c53fd431-7978-4887-bee5-296d259dab12
Background For soaring birds, the ability to benefit from variable airflow dynamics is crucial, especially while crossing natural barriers such as vast water bodies during migration. Soaring birds also take advantage of warm rising air, so-called thermals, that allow birds to ascend passively to higher altitudes with reduced energy costs. Although it is well known that soaring migrants generally benefit from supportive winds and thermals, the potential of uplifts and other weather factors enabling soaring behavior remains unsolved. Methods In this study, we GPS-tracked 19 Red Kites, Milvus milvus, from the Central European population that crossed the Adriatic Sea on their autumn migration. Migratory tracks were annotated with weather data (wind support, side wind, temperature difference between air and surface—proxy for thermal uplift, cloud cover, and precipitation) to assess their effect on Red Kites' decisions and soaring performance along their migration across the Adriatic Sea and land. Results Wind support affected the timing of crossing over the Adriatic Sea. We found that temperature differences and horizontal winds positively affected soaring sea movement by providing lift support in otherwise weak thermals. Furthermore, we found that the soaring patterns of tracked raptors were affected by the strength and direction of prevailing winds. Conclusion Thanks to modern GPS–GSM telemetry devices and available data from online databases, we explored the effect of different weather variables on the occurrence of soaring behavior and soaring patterns of migratory raptors. We revealed how wind affected the soaring pattern and that tracked birds could soar in weak thermals by utilizing horizontal winds, thus reducing energy costs of active flapping flight over vast water bodies.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Leveraging Artificial Intelligence to Forecast Bird Sightings and Its Visualization with Augmented Web Technologies

  • Morales-García, Juan
  • González Martínez, Paula
  • Melgarejo-Hernández, José
  • García-Tapia-Mateo, Paula
  • Garrigós, Irene
  • Mazón, Jose-Norberto
  • Garrigós, Irene|||/items/50e21847-f541-4051-8e6d-4064e0e80ea3
  • Mazón, Jose-Norberto|||/items/31f8766d-f389-4889-ba06-adeb367a0753
  • Morales-García, Juan|||/items/392294ef-1f4d-46ea-acdd-b1c285f28bea
  • García-Tapia-Mateo, Paula|||/items/1df5b3ce-4fd2-463b-8f82-68e9b5376d8f
  • Melgarejo-Hernández, José|||/items/3f8fa674-9e56-41ad-bc1d-0daef6e2828b
Accurate bird sighting predictions enhance tourism planning, helping visitors optimize birdwatching in natural parks. This study focuses on the Natural Park of Las Lagunas de la Mata y Torrevieja (Alicante, Spain), where AI models were developed for bird sightings forecasts. The analysis showed that data granularity affects model performance: high-frequency datasets with noise are harder to predict due to the lack of clear seasonal patterns, whereas aggregated datasets with weekly or monthly intervals reveal more structured trends with reduced noise. In all scenarios, the hybrid CNNLSTM model consistently outperformed the other studied models. Additionally, a web augmenter was implemented to enhance the Wikipedia page for the park, offering interactive visualizations, including dynamic maps with daily bird sighting predictions, aiding tourists in planning their visits.
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

The underestimated role of carrion in vertebrates' diet studies

  • Sebastián-González, Esther
  • Morant, Jon
  • Moleón, Marcos
  • Redondo-Gómez, Daniel
  • Morales-Reyes, Zebensui
  • Pascual Rico, Roberto
  • Pérez-García, Juan M.
  • Arrondo, Eneko
[Aim] Despite the increasing scientific evidence on the importance of carrion in the ecology and evolution of many vertebrates, scavenging is still barely considered in diet studies. Here, we draw attention to how scientific literature has underestimated the role of vertebrates as scavengers, identifying the ecological traits that characterize those species whose role as scavengers could have gone especially unnoticed., [Location] Global., [Time Period] 1938–2022., [Major Taxa Studied] Terrestrial vertebrate scavengers., [Methods] We analysed and compared (a) the largest database available on scavenging patterns by carrion-consuming vertebrates, (b) 908 diet studies about 156 scavenger species and (c) one of the most complete databases on bird and mammal diets (Elton Traits database). For each of these 156 species, we calculated their scavenging degree (i.e. proportion of carcases where the species is detected consuming carrion) as a proxy for carrion consumption, and related their ecological traits with the probability of being identified as scavengers in diet studies and in the Elton Traits database., [Results] More than half of the species identified as scavengers at monitored carcasses were not assigned carrion as food source in their diet studies nor in the Elton Traits database. Using a subset of study sites, we found a direct relationship between a species' scavenging degree and its rate of carrion biomass removal. In addition, scavenger species, which were classified as non-predators and mammals had a lower probability of being identified as scavengers in diet studies and in the Elton Traits database, respectively., [Main Conclusions] Our results clearly indicate an underestimation of the role of scavenging in vertebrate food webs. Given that detritus recycling is fundamental to ecosystem functioning, we encourage further recognition and investigation of the role of carrion as a food resource for vertebrates, especially for non-predator species and mammals with higher scavenging degree., Consejería de Economía, Innovación, Ciencia y Empleo, Junta de Andalucía, Grant/Award Number: POSTDOC_21_00353 and PREDOC_00262; Eusko Jaurlaritza, Grant/Award Number: PRE_2018_2_0112; Generalitat Valenciana, Grant/Award Number: ACIF/2019/056, APOSTD/2019/016 and APOSTD/2021/028; HORIZON EUROPE Marie Sklodowska-Curie Actions, Grant/Award Number: 101086387; Ministerio de Ciencia e Innovación, Grant/Award Number: IJC-2019- 038968, PID2021- 1 2 8 9 5 2 N B - I 0 0 , R YC - 2 0 1 5 - 19 2 3 1 , RYC- 2019- 027216-I and TED2021- 130890B-C21, Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

Assessment of oceanographic services for the monitoring of highly anthropised coastal lagoons: The Mar Menor case study

  • Giménez, José G.
  • Granero, Alberto
  • Senent-Aparicio, Javier
  • Gómez-Jakobsen, Francisco José
  • Mercado, Jesús M.
  • Blanco-Gómez, Pablo
  • Ruiz, Juan M.
  • Cecilia, José M.
Ocean monitoring systems are designed for continuous monitoring of the seas and oceans to track their evolution and thus anticipate environmental issues. However, they are often based on Internet of Things (IoT) systems that are expensive, hard to maintain, and offer little spatial coverage. An emerging alternative is Satellite Remote Sensing (SRS) systems that offer good geographical coverage but, as a reliable and real-time monitoring system, they also face several challenges such as environmental conditions, spatio-temporal granularity, terrain oleography, etc. This paper introduces an easy-to-use software tool to crawl water-quality data from up to 6 satellite instruments (i.e. Sentinel 3A, Sentinel-3B, NOAA VIIRS, SNPP VIIRS, Aqua MODIS, Terra MODIS) of the European Space Agency's (ESA) Coopernicus system and NASA's Marine Environmental Monitoring Service. We also provide an in-depth analysis in terms of reliability and data coverage for the chlorophyll-a (Chl-a) in a highly anthropised local/regional context like the Mar Menor lagoon (Murcia, Spain), where serious socio-environmental issues are arising due to the eutrophication process. Our results show a good linear correlation between in situ data, obtained by several Spanish public institutions since 2016, and data generated by the IRTM-NN (Inverse Radiative Transfer Model-Neural Network) algorithm of Sentinel 3 in general, reaching coefficient correlation values close to 0.9. They also show that organic matter inputs from ephemeral streams are relevant in determining Chl-a concentrations. Moreover, the temporal coverage using a single instrument is rather limited, as no data were recorded for 80% of the days studied. This figure decreases to 30% when data from the 6 satellite instruments are combined, increasing the temporal granularity of the measurements from approximately 5 to 1.5 days, suggesting the need for a combination of these systems for a robust SRS system., This work has been supported by the European Union's Horizon 2020 research and innovation programme under grant agreement No 101017861 as well as the Ramon y Cajal Grant RYC2018-025580-I, funded by MCIN/AEI/10.13039/501100011033, “FSE invest in your future” and “ERDF A way of making Europe” and the TED2021-130890B research project funded by MCIN/AEI /10.13039/501100011033 and European Union NextGenerationEU/ PRTR. The authors acknowledge the Comunidad Autonoma de la Región de Murcia (CARM) for the data provided through the Mar Menor information service website (Canal Mar Menor). The chlorophyll monitoring of the IEO-CSIC was funded from DMMEM project from the Spanish Institute of Oceanography., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

Vertebrate scavenger assemblages and their functioning differ between artificial and natural wetlands: Implications for ecosystem management

  • Orihuela-Torres, Adrián
  • Pérez-García, Juan M.
  • Arrondo, Eneko
  • Pessano Serrat, Tatiana
  • Green, Andy J.
  • Naves-Alegre, Lara
  • Botella, Francisco
  • Selva, Nuria
  • Sánchez-Zapata, José A.
  • Sebastián-González, Esther
Natural wetlands perform essential ecological functions, but their area has dramatically decreased. Partly to counteract this loss, artificial wetlands have been created. While studies comparing animal communities between artificial and natural wetlands abound, research on their comparative ecological functions is scarce. In particular, vertebrate scavengers in aquatic ecosystems have been little studied despite their critical role in nutrient cycling. This study compared vertebrate scavenger assemblages and their consumption patterns in natural and artificial wetlands in Doñana, Spain, to evaluate the effects of wetland management (natural vs. artificial hydrology) across different seasons. We placed 120 carcasses (carp and chicken) in natural and artificial wetlands. We recorded 22 vertebrate scavenger species efficiently consuming 100 % of carrion in an average of less than two days, highlighting their role in nutrient recycling. Carrion of aquatic-origin was consumed faster and by a greater variety of species than that of terrestrial-origin, facilitating the transport of essential nutrients from water to land. Artificial wetlands exhibited higher efficiency in carrion removal (twice as fast as natural wetlands). However, they hosted less diverse assemblages, dominated by opportunistic and non-native species. This suggests that artificial wetlands are not replacing natural wetlands in terms of biodiversity, despite sustaining water levels and functions. Importantly, ‘kidnapping’ water for irrigation reduces the ability of natural wetlands to maintain ecological functions provided by scavengers. Urgent regulation of water abstraction from aquifers, especially for crop irrigation, is necessary to maintain minimum groundwater levels, preserving the functionality and ecological processes of this critical wetland complex., AJG was supported by Ministerio de Ciencia e Innovación Project PID2020-112774GB-I00/AEI/10.13039/501100011033. ESG was partially supported by the “European Union NextGenerationEU/PRTR”, by MCIN/AEI/10.13039/501100011033 and by “ESF Investing in your future”, under the CHAN-TWIN project (TED2021-130890B-C21) and the RYC-2019-027216-I. TPS was supported by Spanish Ministry of Education and Vocational Training (22CO1/000897)., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

A global assessment of BirdNET performance: Differences among continents, biomes, and species

  • Funosas, David
  • Sebastián-González, Esther
  • Morant, Jon
  • Marín Gómez, Oscar H.
  • Mendoza, Irene
  • Mohedano Muñoz, Miguel A.
  • Santamaría García, Eduardo
  • Bastianelli, Giulia
  • Márquez Rodríguez, Alba
  • Budka, Michał
  • Bota, Gerard
  • Alonso-Moya, Cristina D.
  • Peña-Rubio, José M. de la
  • García de la Morena, Eladio L.
  • Santa-Cruz, Manu
  • Nava, Pablo de la
  • Fernández-Tizón, Mario
  • Sánchez-Mateos, Hugo
  • Barrero, Adrián
  • Traba, Juan
  • Osiejuk, Tomasz S.
  • Hart, Patrick J.
  • Navine, Amanda K.
  • Montoya Muñoz, Andrés F.
  • Araújo, Carlos B. de
  • Rosa, Gabriel L. M.
  • Torres, Ingrid M. D.
  • Catalano, Ana L. C.
  • Simões, Cassio Rachid
  • Llusia, Diego
  • Morales, Manuel B.
  • Acebes, Pablo
  • Medina, Juan A.
  • Brown, Nicholas
  • Astaras, Christos
  • Karmiris, Ilias
  • Navarrete, Elizabeth
  • Cauchoix, Maxime
  • Barbaro, Luc
  • Arend, Dominik
  • Müeller, Sandra
  • González-García, Fernando
  • González-Romero, Alberto
  • Mammides, Christos
  • Pontikis, Michaelangelo
  • Jacuzzi, Giordano
  • Olden, Julian D.
  • Bombaci, Sara P.
  • Marcacci, Gabriel
  • Jacot, Alain
  • Zurano, Juan P.
  • Gangenova, Elena
  • Varela, Diego
  • Di Sallo, Facundo
  • Zurita, Gustavo A.
  • Atemasov, Andrey
  • Tremblay, Junior A.
  • Lamarre, Vincent
  • Hutschenreiter, Anja
  • Monroy-Ojeda, Alan
  • Díaz-Vallejo, Mauricio
  • Chaparro-Herrera, Sergio
  • Briers, Robert A.
  • Sousa-Lima, Renata
  • Pinheiro, Thiago
  • Da Silva, Wigna C.
  • Calvente, Alice
  • Paz, Raiane V.
  • Salustio-Gomes, Carlos
  • Oliveira-Júnior, Dorgival D.
  • Lima-Santos, Cicero S.
  • Pichorim, Mauro
  • Molin, Anamaria Dal
  • Antonelli, Alexandre
  • Gogoleva, Svetlana
  • Palko, Igor
  • Trong, Hiếu V.
  • Duarte, Marina H. L.
  • Dos Santos Saturnino, Natalia
  • Silva, Samuel R.
  • Rainho, Ana
  • Lopes, Paula
  • Schuchmann, Karl L.
  • Marques, Marinêz I.
  • De Oliverira Tissiani, Ana S.
  • Littlewood, Nick A.
  • Tuanmu, Mao Ning
  • Kepfer-Rojas, Sebastian
  • Aguilera, Andrea L.
  • Brotons, Lluís
  • Feldman, Mariano J.
  • Imbeau, Louis
  • Panwar, Pooja
  • Weed, Aaron S.
  • Dehwal, Anant
  • Attisano, Alfredo
  • Theuerkauf, Jörn
  • Goodale, Eben
  • Darras, Kevin F. A.
  • Pérez-Granados, Cristian
Recent advances in machine learning have accelerated automated species detection across diverse ecological domains, enabling large-scale, non-invasive monitoring of biodiversity. In ornithological research, the combination of passive acoustic monitoring (PAM) and rapidly-developing novel identification tools such as BirdNET—a deep learning–based sound recognition algorithm—offers new opportunities for surveying vocally active bird communities. Here, we present the first worldwide evaluation of BirdNET using 4224 one-minute recordings from 67 sites across all continents annotated by local experts. More specifically, we assessed the capacity of BirdNET to accurately identify individual vocalizations and characterize bird communities based on the automated analysis of passively collected soundscapes. We further analyzed how its performance varies across continents, biomes, species, and minimum confidence thresholds. The proportion of correct BirdNET predictions (precision) was generally high and consistent across continents (range: 0.57–0.71) and biomes (range: 0.55–0.76). In contrast, the proportion of vocalizations successfully detected (recall) was generally lower and more heterogeneous across continents (range: 0.24–0.52) and biomes (range: 0.34–0.72), reflecting differences in species coverage and local ecological context. BirdNET predictive power, as measured by the Precision-Recall Area Under the Curve (PR AUC; higher values indicating better performance), was highest in North America, Oceania, and Europe (range: 0.16–0.23), moderate in Central/South America (0.13), and lowest in Africa and Asia (range: 0.03–0.04). Species-specific analyses revealed substantial heterogeneity in detection accuracy, with optimal confidence thresholds varying widely by species and analytical goal. Our results establish a global reference point for BirdNET reliability and highlight where algorithmic refinement and expanded acoustic sampling are most needed., DF was funded by the University of Toulouse; CP-G was funded by Departament de Recerca i Universitats de la Generalitat de Catalunya through the 2021-SGR 00302 project; and ES-G was funded by the Spanish Ministry of Science, Innovation and Universities (MCIN/AEI/10.13039/501100011033), NextGenerationEU/PRTR, ESF Investing in your future (TED2021-130890B-C21 and RYC2019-027216-I), and HORIZONMSCA-2021-SE-0 (action number: 101086387)., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

Harnessing social sensing for real-time flood event reconstruction: A digital autopsy of the 2024 Valencia DANA

  • Giner Pérez de Lucia, José
  • López-Ballesteros, Adrián
  • Fernández-Pedauyé, Julio
  • Senent-Aparicio, Javier
  • Cecilia, José M.
Extreme rainfall and flash-flood events in the Western Mediterranean pose persistent challenges for real-time monitoring and emergency response. Traditional hydrometeorological networks often provide limited spatiotemporal coverage during rapidly evolving events, leading to localized blind spots. This study reconstructs the impacts of the October 2024 catastrophic floods in Valencia using more than 156,000 geolocated messages from X (formerly Twitter) as a form of social sensing. These citizen-generated data were integrated with hydrological and hydraulic modeling to contextualize reported flood dynamics and response gaps. Advanced Natural Language Processing (NLP) techniques were applied to extract spatiotemporal patterns of public perception, emergency reactions, and infrastructure disruptions. In addition, a Retrieval-Augmented Generation (RAG) system was implemented to transform unstructured messages into structured event summaries, providing actionable insights during the disaster window. The analysis revealed a clear temporal alignment between social media activity and flood progression, with online reporting peaking shortly after critical impact thresholds. Cross-validation with hydrological simulations confirmed the potential of social sensing to detect localized effects often missed by conventional monitoring, while also exposing the limitations of relying solely on proxy digital traces. Overall, the Valencia case demonstrates the feasibility of integrating human-sensed information with physically based models to enhance situational awareness and support adaptive, data-driven disaster risk reduction in urban environments., This research has been supported by projects TED2021-130890B funded by MCIN/AEI/10.13039/501100011033, and AM-DS (INREED/2024/1), funded by the European Union - NextGenerationEU. José Giner Pérez de Lucia acknowledges the financial support by the Spanish State Research Agency (Agencia Estatal de Investigación, AEI) through the Industrial PhD Grant within the “Training of Doctors in Companies (Industrial PhDs)” program, under the State Plan for Scientific, Technical and Innovation Research (DIN2024-014116-2). Finally, Adrián López-Ballesteros acknowledges the financial support received from the Juan de la Cierva Postdoc Spanish Program (JDC2023-050965-I)., Peer reviewed