TY - GEN
T1 - GAN Based Data Augmentation for Indoor Localization Using Labeled and Unlabeled Data
AU - Njima, Wafa
AU - Chafii, Marwa
AU - Shubair, Raed M.
N1 - Funding Information:
This work was supported in part by CY Initiative of Excellence (grant "Investissements d’Avenir" ANR-16-IDEX-0008) and by the project DELICATE funded by CNRS/INS2I.
Publisher Copyright:
© 2021 IEEE.
PY - 2021/9/20
Y1 - 2021/9/20
N2 - 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.
AB - 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.
KW - Indoor localization
KW - deep neural network (DNN)
KW - generative adversarial network (GAN)
KW - received signal strength indicator (RSSI)
KW - semi-supervised learning
UR - http://www.scopus.com/inward/record.url?scp=85119450943&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85119450943&partnerID=8YFLogxK
U2 - 10.1109/BalkanCom53780.2021.9593240
DO - 10.1109/BalkanCom53780.2021.9593240
M3 - Conference contribution
AN - SCOPUS:85119450943
T3 - 2021 International Balkan Conference on Communications and Networking, BalkanCom 2021
SP - 36
EP - 39
BT - 2021 International Balkan Conference on Communications and Networking, BalkanCom 2021
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 4th International Balkan Conference on Communications and Networking, BalkanCom 2021
Y2 - 20 September 2021 through 22 September 2021
ER -