Transfer Learning for Convolutional Indoor Positioning Systems

Tutkimustuotos: KonferenssiartikkeliScientificvertaisarvioitu

20 Lataukset (Pure)

Abstrakti

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.
AlkuperäiskieliEnglanti
Otsikko2021 International Conference on Indoor Positioning and Indoor Navigation (IPIN)
KustantajaIEEE
Sivumäärä8
ISBN (elektroninen)978-1-6654-0402-0
DOI - pysyväislinkit
TilaJulkaistu - 2021
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisussa
TapahtumaInternational Conference on Indoor Positioning and Indoor Navigation - , Espanja
Kesto: 29 marrask. 20212 jouluk. 2021

Julkaisusarja

NimiInternational Conference on Indoor Positioning and Indoor Navigation
ISSN (elektroninen)2471-917X

Conference

ConferenceInternational Conference on Indoor Positioning and Indoor Navigation
Maa/AlueEspanja
Ajanjakso29/11/212/12/21

Julkaisufoorumi-taso

  • Jufo-taso 1

Sormenjälki

Sukella tutkimusaiheisiin 'Transfer Learning for Convolutional Indoor Positioning Systems'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.

Siteeraa tätä