Repository logo
  • English
  • Čeština
  • Deutsch
  • Español
  • Français
  • Gàidhlig
  • Latviešu
  • Magyar
  • Nederlands
  • Português
  • Português do Brasil
  • Suomi
  • Svenska
  • Türkçe
  • Қазақ
  • বাংলা
  • हिंदी
  • Ελληνικά
  • Log In
    New user? Click here to register.
Repository logo

Repositorio Institucional de la Universidad de Murcia

Repository logoRepository logo
  • Communities & Collections
  • All of DSpace
  • menu.section.collectors
  • menu.section.acerca
  • English
  • Čeština
  • Deutsch
  • Español
  • Français
  • Gàidhlig
  • Latviešu
  • Magyar
  • Nederlands
  • Português
  • Português do Brasil
  • Suomi
  • Svenska
  • Türkçe
  • Қазақ
  • বাংলা
  • हिंदी
  • Ελληνικά
  • Log In
    New user? Click here to register.
  1. Home
  2. Browse by Subject

Browsing by Subject "Artificial neural networks"

Now showing 1 - 2 of 2
Results Per Page
Sort Options
  • Loading...
    Thumbnail Image
    Publication
    Open Access
    A circularity accounting network : CO2 measurement along supply chains using machine learning
    (Universidad de Murcia, Servicio de publicaciones, 2023) Fabian Jesse, Forrest; Antonini, Carla; Luque Vilchez, Mercedes
    This paper proposes to use a type of machine learning network called artificial neural networks to design a circularity accounting network. The network is composed of human and non-human actors and accounts for the impact of products CO2emissions and sequestration along global supply chains. The network serves to connect people and other actors that share a CO2 indicator and allows users to visualize the level of (un-)circularity of different products through specific diagrams calculated by a CO2estimator drawing on insights from actor-network theory. Unlike most previous circular economy accounting studies that develop sometype of framework or indicator that represent measurements at micro, meso or macro levels, the circularity accounting network is not confined to a particular level of analysis but is designed to build relationships between multiple users at different levels (e.g., government, corporate or consumer actors). The paper presents the conceptual design and a preliminary test of the network using real data, helping to advancethe under explored potential of artificial intelligence in the field of circular economy accounting. The main contribution of this network is that data provided by the indicator: (i) is derived from the network itselflearning from open sources, the network (ii) is not static but keeps flowing as new relationships are builtwithin the network, moving toward self-regulating, (iii) contemplates both emissions and sequestrations along supply chains.
  • Loading...
    Thumbnail Image
    Publication
    Open Access
    Algoritmos de clasificación y redes neuronales en la observación automatizada de registros
    (Murcia: Servicio de Publicaciones de la Universidad de Murcia, 2015) González Ruiz, Sergio Luis; Gómez-Gallego, I.; Pastrana Brincones, José Luis; Hernández-Mendo, Antonio
    El objetivo del presente estudio es analizar los datos obtenidos a través de una plataforma on-line, mediante diferentes técnicas de clasificación y aprendizaje orientadas al descubrimiento del conocimiento. Se aplican técnicas de minería de datos para obtener relaciones de fiabilidad que informen del interés de los usuarios por cumplimentar de manera rigurosa el cuestionario on-line atendiendo al modo de realizar el mismo. Aunque existen técnicas que nos permiten observar el comportamiento de los usuarios mientras realizan el cuestionario, en este caso se emplean Redes Neuronales Artificiales para predecir el comportamiento de aquellos, atendiendo a variables obtenidas al realizar el cuestionario. La muestra consta de 1.636 participantes de diferentes zonas geográficas y rangos de edad, obtenida al contestar de manera anónima o identificada al cuestionario Inventario Psicológico para el Seguimiento de Talentos Deportivos (IPSETA). Los resultados obtenidos mediante las diferentes técnicas de análisis informan que el género femenino pre#ere realizar el registro en la plataforma para cumplimentar el cuestionario, alcanzando un alto porcentaje de fiabilidad (70%).

DSpace software copyright © 2002-2025 LYRASIS

  • Cookie settings
  • Accessibility
  • Send Feedback