Person:
García González, María

Profile Picture
Name
García González, María
publication.page.department
Universidad de Murcia. Departamento de Información y Documentación
Repository logoRepository logoRepository logoRepository logoRepository logoRepository logoRepository logo

Filters

2018 - 201912020 - 20252
3
3
Reset filters

Settings

Search Results

Now showing 1 - 3 of 3
  • Thumbnail Image
    Publication
    Open Access
    A Multi-Agent Deep Reinforcement Learning System for Governmental Interoperability
    (MDPI, 2025-03-13) Azanu Mirolgn Mequanenit; Eyerusalem Alebachew Nibret; Pilar Herrero-Martín; García González, María; Martínez Béjar, Rodrigo; Información y Documentación; Facultades de la UMU::Facultad de Comunicación y Documentación
    This study explores the integration of the JADE (Java Agent Development Framework) platform with deep reinforcement learning (DRL) to enhance governmental interoperability and optimize administrative workflows in municipal settings. The proposed approach combines the JADE’s robust multi-agent system (MAS) capabilities with the adaptive decision-making power of DRL to address prevalent challenges faced by government agencies, such as fragmented operations, incompatible data formats, and rigid communication protocols. By enabling seamless communication between agents across departments such as the Treasury, the Event Management department, and the Public Safety department, the hybrid system fosters real-time collaboration and supports efficient, data-driven decision making. Agents leverage historical and real-time data to adapt to environmental changes and make optimized decisions that align with overarching governmental objectives, such as resource allocation and emergency response. The result is a system capable of managing intricate administrative duties using structured agent communication and the integration of DRL-driven learning models, improving governmental interoperability. Key performance indicators highlight the system’s effectiveness, achieving a task completion rate of 95%, decision accuracy of 96%, and a communication latency of just 120 ms. Additionally, the framework’s flexibility ensures seamless scalability, accommodating complex and large-scale tasks across multiple governmental units. This research presents a scalable, automated, and resilient framework for optimizing governmental processes, offering a pathway to more efficient, transparent, and adaptive public sector operations.
  • Thumbnail Image
    Publication
    Restricted
    A modelling approach to privacy and safety issues in cyber-physical systems
    (IGI Global, 2023) Martínez Béjar, Rodrigo; García González, María; Scalera, Lorenzo; Gasparetto, Alessandro; Información y Documentación; Mateus Coelho, Nuno; Cruz Cunha, Manuela
    Safety issues are relevant in the interaction of human and robotic systems, as these might be a risk for humans’ physical integrity. Robotic systems in the armies are a good example of such risk, since these systems are highly dependent on the software integrity that governs their behaviour. But in civil society there are examples of such issues as well. For example, manufacturing systems are connected to each other and/or to communication networks systems, so these being potentially targets of hijacking. Also, medical applications are usually designed to be very accurate/precise, for instance, in surgery. If that accuracy/precision is threatened due to a cyberattack -as some of those robots are connected to communication networks- the patient could even die. In this work, we describe a modelling approach that categorizes the most relevant cybersecurity threats to robots from different analytical viewpoints (e.g., type of human interrelation with robots, industrial sector, etc.). To illustrate the usefulness of this model, the main characteristics of a model addressing the cybersecurity threats to manufacturing robotic systems is shown in this work. Such model has been implemented into a machine-understandable software by using standard knowledge representation methods.
  • Thumbnail Image
    Publication
    Restricted
    e-Administración: realidad encontrada tras la aplicación de un método descriptivo de gestión de procesos administrativos en entidades locales españolas.
    (Congreso de los Diputados: Dirección de Estudios, Análisis y Publicaciones, 2018) García González, María; Información y Documentación
    La implementación de recomendaciones dadas por normativas y directrices tanto europeas como nacionales, se están dejando en el camino varias fases definidas e identificadas que deberían solucionarse previamente a la hora de implantar la Administración Electrónica en entidades locales de mediano, pequeño nivel. Esta realidad conduce a la adopción de un enfoque por procesos, donde por un lado, se diseña y aplica un modelo de descripción de procesos institucionales que vierte una estructura conceptual de un proceso real para un entorno electrónico y, por otro, un modelo de metadatos que comprende una estructura lógica para describir esa conceptualización, siendo el principal objeto de estudio un expediente administrativo real. Los resultados obtenidos tras la aplicación metodológica conducen a fundamentar, plantear y solucionar algunas de las muchas cuestiones que figuran en esta monografía, tales como: ¿cómo se solucionará el problema de la Interoperabilidad Organizativa y Semántica?; ¿es necesario adoptar otro posicionamiento respecto a la redacción de un nuevo marco legislativo para la gestión de los procesos tramitados de forma electrónica?, etc...
Ir a Estadísticas