Poster Abstract: Link Quality Estimation—A Case Study for On-line Supervised Learning in Wireless Sensor Networks

  • Eduardo Feo-Flushing
  • Michal Kudelski
  • Jawad Nagi
  • Luca M. Gambardella
  • Gianni A. Di Caro
Conference paper

DOI: 10.1007/978-3-319-03071-5_12

Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 281)
Cite this paper as:
Feo-Flushing E., Kudelski M., Nagi J., Gambardella L.M., Di Caro G.A. (2014) Poster Abstract: Link Quality Estimation—A Case Study for On-line Supervised Learning in Wireless Sensor Networks. In: Langendoen K., Hu W., Ferrari F., Zimmerling M., Mottola L. (eds) Real-World Wireless Sensor Networks. Lecture Notes in Electrical Engineering, vol 281. Springer, Cham

Abstract

We focus on the implementation issues of on-line, batch supervised learning in computationally limited devices. As a case study, we consider the use of such techniques for link quality estimation. We compare three strategies for the on-line selection of the data samples to be kept in memory and used for learning. Results suggest that strategies that keep balanced the set of training samples in terms of ranges of target values provide better accuracy and faster convergence.

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Eduardo Feo-Flushing
    • 1
  • Michal Kudelski
    • 1
  • Jawad Nagi
    • 1
  • Luca M. Gambardella
    • 1
  • Gianni A. Di Caro
    • 1
  1. 1.Dalle Molle Institute for Artificial Intelligence (IDSIA)MannoSwitzerland

Personalised recommendations