Predicting a User's Next Cell With Supervised Learning Based on Channel States - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2013

Predicting a User's Next Cell With Supervised Learning Based on Channel States

Xu Chen
  • Fonction : Auteur
  • PersonId : 941200
François Mériaux
  • Fonction : Auteur
  • PersonId : 936101
Stefan Valentin
  • Fonction : Auteur
  • PersonId : 941201

Résumé

Knowing a user's next cell allows more efficient resource allocation and enables new location-aware services. To anticipate the cell a user will hand-over to, we introduce a new machine learning based prediction system. Therein, we formulate the prediction as a classification problem based on information that is readily available in cellular networks. Using only Channel State Information (CSI) and handover history, we perform classification by embedding Support Vector Machines (SVMs) into an efficient pre-processing structure. Simulation results from a Manhattan Grid scenario and from a realistic radio map of downtown Frankfurt show that our system provides timely prediction at high accuracy.
Fichier principal
Vignette du fichier
csi_ml_fingerprinting.pdf (930.45 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-00821207 , version 1 (13-05-2013)

Identifiants

Citer

Xu Chen, François Mériaux, Stefan Valentin. Predicting a User's Next Cell With Supervised Learning Based on Channel States. IEEE 14th Workshop on Signal Processing Advances in Wireless Communications (SPAWC 2013), Jun 2013, Darmstadt, Germany. pp.1-5, ⟨10.1109/spawc.2013.6612007⟩. ⟨hal-00821207⟩
512 Consultations
153 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More