Transfer Learning for Convolutional Indoor Positioning Systems

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

42 Downloads (Pure)


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 for fingerprinting positioning purposes can greatly improve the prediction speed compared to the k-NN approach, but requires a voluminous training dataset to achieve comparable performance. In many indoor positioning datasets, the number of samples is only at a level of hundreds, which results in poor performance of the neural network solution. In this work, we develop a novel algorithm based on a transfer learning approach, which combines samples from 15 different Wi-Fi RSS indoor positioning datasets, to train a single convolutional neural network model, which learns the common patterns in the combined data. The proposed model is then fine-tuned to optimally fit the individual databases. We show that the proposed solution reduces the positioning error by up to 25% compared to the benchmark model while reducing the number of outlier predictions.
Original languageEnglish
Title of host publication2021 International Conference on Indoor Positioning and Indoor Navigation (IPIN)
Number of pages8
ISBN (Electronic)978-1-6654-0402-0
Publication statusPublished - 2021
Publication typeA4 Article in conference proceedings
EventInternational Conference on Indoor Positioning and Indoor Navigation - , Spain
Duration: 29 Nov 20212 Dec 2021

Publication series

NameInternational Conference on Indoor Positioning and Indoor Navigation
ISSN (Electronic)2471-917X


ConferenceInternational Conference on Indoor Positioning and Indoor Navigation


  • Artificial neural network
  • Convolutional neural network
  • Deep learning
  • Fingerprinting
  • Indoor positioning
  • Machine learning
  • Transfer learning
  • WLAN

Publication forum classification

  • Publication forum level 1


Dive into the research topics of 'Transfer Learning for Convolutional Indoor Positioning Systems'. Together they form a unique fingerprint.

Cite this