ListarINIT_Congressos i Informes por tema "machine learning"

Mostrando ítems 1-5 de 5

    • openAccess   Characterising Players of a Cube Puzzle Game with a Two-level Bag of Words 

      Anadón, Xavier; Sanahuja, Pablo; Traver, V. Javier; Lopez, Angeles; Ribelles, Jose Association for Computing Machinery (ACM) (2021-06)
      This work explores an unsupervised approach for modelling players of a 2D cube puzzle game with the ultimate goal of customising the game for particular players based solely on their interaction data. To that end, user ...

    • openAccess   Ensembling Multiple Radio Maps with Dynamic Noise in Fingerprint-based Indoor Positioning 

      Torres-Sospedra, Joaquín; Aranda Polo, Fernando Jesús; Álvarez, Fernando J.; Quezada Gaibor, Darwin; Silva, Ivo; Pendão, Cristiano; Moreira, Adriano Institute of Electrical and Electronics Engineers (2021-06-15)
      Fingerprint-based indoor positioning is widely used in many contexts, including pedestrian and autonomous vehicles navigation. Many approaches have used traditional Machine Learning models to deal with fingerprinting, ...

    • openAccess   Integrating Concepts of Artificial Intelligence in the EO4GEO Body of Knowledge 

      Lemmens, Rob; Lang, Stefan; Albrecht, Florian; Augustijn, E.; Granell, Carlos; Olijslagers, Marc; Pathe, C.; Dubois, C.; Stelmaszczuk-Górska, Martyna A. International Society for Photogrammetry and Remote Sensing (2022-06)
      The EO4GEO Body of Knowledge (BoK) forms a structure of concepts and relationships between them, describing the domain of Earth Observation and Geo-Information (EO/GI). Each concept carries a short description, a list of ...

    • closedAccess   Towards Accelerated Localization Performance Across Indoor Positioning Datasets 

      Klus, Lucie; Quezada Gaibor, Darwin; Torres-Sospedra, Joaquín; Lohan, Elena Simona; Granell, Carlos; Nurmi, Jari IEEE (2022)
      The localization speed and accuracy in the indoor scenario can greatly impact the Quality of Experience of the user. While many individual machine learning models can achieve comparable positioning performance, their ...

    • openAccess   Transfer Learning for Convolutional Indoor Positioning Systems 

      Klus, Roman; Klus, Lucie; Talvitie, Jukka; Pihlajasalo, Jaakko; Torres-Sospedra, Joaquín; Valkama, Mikko IEEE (2021-11-29)
      Fingerprinting is a widely used technique in indoor positioning, mainly due to its simplicity. Usually, this technique is used with the deterministic k - Nearest Neighbors (k-NN) algorithm. Utilizing a neural network model ...