Using Synthetic Data to Enhance the Accuracy of Fingerprint-Based Localization: A Deep Learning Approach

Article


Nabati, M., Navidan, H., Shahbazian, R., Ghorashi, S. A. and Windridge, D. 2020. Using Synthetic Data to Enhance the Accuracy of Fingerprint-Based Localization: A Deep Learning Approach. IEEE Sensors Letters. 4 (Art. 6000204). https://doi.org/10.1109/LSENS.2020.2971555
AuthorsNabati, M., Navidan, H., Shahbazian, R., Ghorashi, S. A. and Windridge, D.
Abstract

Human-centered data collection is typically costly and implicates issues of privacy. Various solutions have been proposed in the literature to reduce this cost, such as crowd-sourced data collection, or the use of semisupervised algorithms. However, semisupervised algorithms require a source of unlabeled data, and crowd-sourcing methods require numbers of active participants. An alternative passive data collection modality is fingerprint-based localization. Such methods use received signal strength or channel state information in wireless sensor networks to localize users in indoor/outdoor environments. In this letter, we introduce a novel approach to reduce training data collection costs in fingerprint-based localization by using synthetic data. Generative adversarial networks (GANs) are used to learn the distribution of a limited sample of collected data and, following this, to produce synthetic data that can be used to augment the real collected data in order to increase overall positioning accuracy. Experimental results on a benchmark dataset show that by applying the proposed method and using a combination of 10% collected data and 90% synthetic data, we can obtain essentially similar positioning accuracy to that which would be obtained by using the full set of collected data. This means that by employing GAN-generated synthetic data, we can use 90% less real data, thereby reducing data-collection costs while achieving acceptable accuracy.

KeywordsSensor applications; deep learning; fingerprint localization; generative adversarial networks (GANs); synthetic data; wireless sensor networks
JournalIEEE Sensors Letters
Journal citation4 (Art. 6000204)
ISSN2475-1472
Year2020
PublisherIEEE
Accepted author manuscript
License
File Access Level
Anyone
Digital Object Identifier (DOI)https://doi.org/10.1109/LSENS.2020.2971555
Web address (URL)https://doi.org/10.1109/LSENS.2020.2971555
Publication dates
Print04 Feb 2020
Publication process dates
Accepted20 Jan 2020
Deposited01 Jun 2020
Copyright holder© 2020 IEEE
Copyright informationPersonal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Permalink -

https://repository.uel.ac.uk/item/880wz

Download files

Accepted author manuscript
Ghorashi - IEEE Sensors Letter - 2020-2-1.pdf
License: All rights reserved
File access level: Anyone

  • 34
    total views
  • 23
    total downloads
  • 6
    views this month
  • 6
    downloads this month

Export as

Related outputs

Resource Allocation in Full-Duplex UAV Enabled Multi Small Cell Networks
Hajihoseini Gazestani, A., Ghorashi, S. A., Yang, Z. and Shikh-Bahaei, M 2020. Resource Allocation in Full-Duplex UAV Enabled Multi Small Cell Networks. IEEE Transactions on Mobile Computing. https://doi.org/10.1109/TMC.2020.3017137
Privacy preserving in indoor fingerprint localization and radio map expansion
Ghorashi, S. A., Sazdar, A. M., Alikhani, N. and Khonsari, A. 2020. Privacy preserving in indoor fingerprint localization and radio map expansion. Peer-to-Peer Networking and Applications. https://doi.org/10.1007/s12083-020-00950-1
A Low-complexity trajectory privacy preservation approach for indoor fingerprinting positioning systems
Sazdar, A. M., Ghorashi, S. A., Moghtadaiee, V., Khonsari, A. and Windridge, D. 2020. A Low-complexity trajectory privacy preservation approach for indoor fingerprinting positioning systems. Journal of Information Security and Applications. 53 (Art. 102515). https://doi.org/10.1016/j.jisa.2020.102515
Power Allocation for D2D Communications Using Max-Min Message-Passing Algorithm
Kazemi Rashed, S, Asvadi, R., Rajabi, S., Ghorashi, S. A. and Martini, M. G. 2020. Power Allocation for D2D Communications Using Max-Min Message-Passing Algorithm. IEEE Transactions on Vehicular Technology. https://doi.org/10.1109/TVT.2020.2995534
Throughput Improvement by Mode Selection in Hybrid Duplex Wireless Networks
Mousavinasab, B., Gazestani, A. H., Ghorashi, S. A. and Shikh-Bahaei, M. 2020. Throughput Improvement by Mode Selection in Hybrid Duplex Wireless Networks. Wireless Networks. 26, p. 3687–3699. https://doi.org/10.1007/s11276-020-02286-3
New Reconstructed Database for Cost Reduction in Indoor Fingerprinting Localization
Moghatdaiee, V., Ghorashi, S. and Ghavami, G. 2019. New Reconstructed Database for Cost Reduction in Indoor Fingerprinting Localization. IEEE Access. 7, pp. 104462-104477. https://doi.org/10.1109/ACCESS.2019.2932024