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

Njima, Wafa; Chafii, Marwa; Shubair, Raed M.

doi:10.1109/balkancom53780.2021.9593240

Cited by 14 publications

(21 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[60] constructed CSI fingerprint data at each location point as amplitude images and then generated additional images to extend the fingerprint dataset by AC-GAN, which can generate pseudo-fingerprint data without limitation and efficiently utilizes computational resources and real fingerprint data. [61] generated pseudofingerprint data at different locations based on CGAN using real collected RSS data. [62] proposed a generative adversarial network for RSSI data enhancement, which generates virtual RSSI data based on a small amount of collected marker data and selects the generated data to reduce data generation errors, with an average localization error of up to 0.83m in a 20m × 20m localization environment.…”

Section: A Methods Based On Generative Adversarial Networkmentioning

confidence: 99%

Low-Cost Indoor Wireless Fingerprint Location Database Construction Methods: A Review

et al. 2023

View full text Add to dashboard Cite

The fingerprint positioning has achieved remarkable results in indoor localization tasks, but the method usually relies on a large amount of fingerprint data to build a fingerprint database, and the amount and diversity of fingerprint data will directly affect the effectiveness of fingerprint positioning. Since fingerprint acquisition is limited and disturbed by space and time, it consumes a lot of labor and time costs to collect fingerprint data in the localization environment, and wireless fingerprint data is time-sensitive and environment-dependent, and changes in the localization environment will reduce the usability of the existing fingerprint database. The complex and repetitive fingerprint acquisition work seriously affects the feasibility of practical deployment of fingerprint positioning systems in the positioning environment. Therefore, the study of low-cost wireless fingerprint database construction methods has become an inevitable part of promoting the widespread deployment of indoor fingerprint positioning systems. In this paper, we introduce the traditional data augmentation-based approach and the advanced machine learning model-based approach, systematically presenting the underlying models and algorithms of both. The former reviews the application of two traditional data enhancement methods, namely channel propagation models and interpolation or regression, to the construction of low-cost wireless fingerprint databases, while the latter taps into techniques for reducing the cost of fingerprint database construction by combining generative adversarial networks and small-sample learning models with the indoor localization domain. Finally, we discuss the current challenges and future research directions for achieving high-performance indoor localization based on low-cost wireless fingerprint databases, and suggest some useful research guidelines.

show abstract

Section: A Methods Based On Generative Adversarial Networkmentioning

confidence: 99%

Low-Cost Indoor Wireless Fingerprint Location Database Construction Methods: A Review

et al. 2023

View full text Add to dashboard Cite

show abstract

“…in [31], [35], and we do not assume having sufficient collected data in some regions as in [34]. Moreover, we do not use GANs to further diversify signal measurements at known positions, as considered in [32], [33].…”

Section: B Contributionsmentioning

confidence: 99%

DNN-Based Indoor Localization Under Limited Dataset Using GANs and Semi-Supervised Learning

2022

Self Cite

View full text Add to dashboard Cite

Indoor localization techniques based on supervised learning deliver great performance accuracy while maintaining low online complexity. However, such systems require massive amounts of data for offline training, which necessitates costly measurements. The essence of this paper is twofold with the purpose of providing solutions to missing data of different nature: available unlabeled data and missing unlabeled data. In both cases, we rely on a few labeled available data, which is costly yet insufficient to achieve a high localization accuracy. To address the problem of available unlabeled data, a weighted semisupervised DNN-based indoor localization approach leveraging pseudo-labeling methods in combination with real labeled samples and inexpensive pseudo-labeled samples is proposed in order to boost localization accuracy, while overcoming the high cost of collecting additional labeled data. As for the extreme case of unavailable unlabeled data, we propose an alternative localization system generating fake fingerprints based on generative adversarial networks (GANs) named 'Weighted GAN based indoor localization'. Furthermore, a deep neural network is trained on a mixed dataset containing both real collected and fake produced data samples using a similar weighting technique in order to improve location prediction performance and avoids overfitting. In terms of localization accuracy, our proposed localization approaches outperform conventional supervised localization schemes utilizing the same collection of real labeled samples. For experimental evaluations, we have tested our proposed methods on both simulated data and experimental data from the publicly available UJIndoorLoc database, which is built to test indoor positioning systems relying on Wi-Fi fingerprints. Results based on experimental data provide the localization accuracy increase compared to the classical supervised learning method using the same set of labeled collected data when using the weighted semi-supervised and the weighted-GAN approaches by 10.11 % and 8.53 %, respectively.

show abstract

“…Explicit density is a generating function that draws a sample from the actual input distribution. Some preliminary works on GAN for indoor localisation are in [9]- [11]. Especially for the work in [12], we cite this publication as our primary reference.…”

Section: Introductionmentioning

confidence: 99%

Synthesis of a Small Fingerprint Database through a Deep Generative Model for Indoor Localisation

Suroso

Cherntanomwong

Sooraksa

2023

ELEKTRON ELEKTROTECH

View full text Add to dashboard Cite

In deep learning (DL), the deep generative model is helpful for data augmentation objectives to tackle the lack of datasets that have a significant impact on learning performance. Data augmentation or synthesis is expected to solve the issue in a small/sparse database. The problem of databasing also exists in the fingerprint-based indoor localisation system. The dense offline fingerprint database must be constructed with the accuracy requirement. However, this will affect the high cost, massive laborious work, and increase the complexity of the system. Therefore, this paper proposes to address these issues by generating synthetic data via a deep generative model. The generative adversarial network (GAN) is selected to generate the synthetic fingerprint database for indoor localisation. Our database consideration consists of power-based parameters, i.e., the received signal strength indicator (RSSI) from Wi-Fi devices obtained from the actual measurement campaign. Some of the literature mainly discusses how GAN works in a vast and complex dataset. Here, we consider applying GAN in a relatively small dataset and for a simple setup. Our results show that by only using the 20 % fraction of actual RSSI data combined with the synthetic RSSI, the accuracy validation performance is slightly higher than when using all actual data usage. Moreover, in only 60 % of actual data usage and in combination with 625 samples of synthetic data, the accuracy performance is improved to 0.73 (1.37 times higher than the use of all actual data, 0.53). Thus, this result proves that the challenges of offline fingerprint databases can be alleviated by data synthesis through GAN by using only a small dataset.

show abstract

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

Cited by 14 publications

References 7 publications

Low-Cost Indoor Wireless Fingerprint Location Database Construction Methods: A Review

Low-Cost Indoor Wireless Fingerprint Location Database Construction Methods: A Review

DNN-Based Indoor Localization Under Limited Dataset Using GANs and Semi-Supervised Learning

Synthesis of a Small Fingerprint Database through a Deep Generative Model for Indoor Localisation

Contact Info

Product

Resources

About