GAN Based Data Augmentation for Indoor Localization Using Labeled and Unlabeled Data

Wafa Njima (1) , Marwa Chafii (2) , Raed M Shubair (2)

1 ETIS - UMR 8051 - Equipes Traitement de l'Information et Systèmes
2 New York University [Abu Dhabi]

Machine learning techniques allow accurate indoor localization with low online complexity. However, a large amount of collected data samples is needed to properly train a deep neural network (DNN) model used for localization. In this paper, we propose to generate fake fingerprints using generative adversarial networks (GANs) based on a small amount of collected data samples. We consider an indoor scenario where collected labeled data samples are rare and insufficient to generate fake samples of a good multitude and diversity in order to provide a good localization accuracy. Thus, both labeled and unlabeled fingerprints are provided to the GAN so that more realistic fake data samples are generated. Then, a DNN model is trained on mixed dataset comprising real collected labeled and pseudo-labeled fingerprints as well as fake generated pseudo-labeled fingerprints. The data augmentation based on real measurements leads to a mean localization accuracy improvement of 9.66% in comparison to the conventional semi-supervised localization algorithm.

Mots clés: Indoor localization; deep neural network (DNN); generative adversarial network (GAN); received signal strength indicator (RSSI); semi-supervised learning

Domaines: Réseau de neurones [cs.NE]

Wafa Njima, Marwa Chafii, Raed M Shubair. GAN Based Data Augmentation for Indoor Localization Using Labeled and Unlabeled Data. Fourth International Balkan Conference on Communications and Networking (BalkanCom 2021), Sep 2021, Novi Sad, Serbia. ⟨hal-03347456⟩