Improving UWB Indoor Localization Accuracy Using Sparse Fingerprinting and Transfer Learning

Adamkiewicz, Krzysztof; Koch, Piotr; Morawska, Barbara; Lipiński, Piotr; Lichy, Krzysztof; Leplawy, Marcin

doi:10.1007/978-3-030-77980-1_23

Cited by 7 publications

(4 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [44]- [46], the authors proposed TL based on the fingerprinting samples. The authors in [44] proposed a NN to learn precise fingerprinting of UWB access points in an environment, then apply TL by updating the NN in a new environment. Only 7% of fingerprinting samples is needed for a new environment.…”

Section: Tl Based On Fingerprintingmentioning

confidence: 99%

Transfer Learning for UWB Error Correction and (N)LOS Classification in Multiple Environments

Fontaine

Che

Shahid

et al. 2024

IEEE Internet Things J.

View full text Add to dashboard Cite

Ultra Wideband (UWB) is a popular technology to address the need for high precision indoor positioning systems in challenging industry 4.0 use cases. In line-of-sight (LOS) environments, UWB positioning errors in the order of 1 − 10 cm can be achieved. However, in non-line-of-sight (NLOS) conditions, this precision drops significantly, with errors typically > 30 cm. Machine learning has been proposed to improve the precision in such NLOS conditions, but is typically environmentspecific and lacks generalization to new environments and UWB configurations. As such, it is necessary to collect large datasets to train a neural network for each new environment or UWB configuration. To remedy this, this paper proposes automatic optimizations for transfer learning (TL) deep neural networks towards new environments and UWB configurations. We analyze error correction and (non)-line-of-sight ((N)LOS) classification models, using either feature-or channel impulse response-based (CIR) input data. Our TL solutions show a 50% error improvement and 15% (N)LOS classification accuracy improvement (for both feature-and CIR-based approaches) compared to a model trained in a different environment. We also analyze the impact on TL using a limited number of samples (25 to 400 samples). The highest accuracy is typically achieved by the CIR-based approach, where with only 50 samples from the new mixed (N)LOS environment, we show ±10 cm precision after error correction with 93% (N)LOS detection. The presented results demonstrate high precision UWB localization (from 643 mm to 245 mm) through ML with minimal data collection effort in challenging NLOS environments.

show abstract

Section: Tl Based On Fingerprintingmentioning

confidence: 99%

Transfer Learning for UWB Error Correction and (N)LOS Classification in Multiple Environments

Fontaine

Che

Shahid

et al. 2024

IEEE Internet Things J.

View full text Add to dashboard Cite

show abstract

“…In recent years, there has been a growing interest in localization and positioning technologies. Researchers and practitioners have proposed various technologies, such as using UWB [5,6], augmented reality (AR) [7,8], and wireless IoT through cross-platform development engine [9,10], to address the challenges of indoor localization. This paper reviews the most recent popular localization technologies, as well as localization within UWB technology, which address the challenges of indoor localization and navigation.…”

Section: Literature Reviewmentioning

confidence: 99%

Indoor Positioning System Based on UWB Rapid Integration with Unity Cross Platform Development Engine through IoT

Zikrul Hakiem Ishak,

Sallehuddin Mohamed Haris

2023

JAIT

View full text Add to dashboard Cite

The changes in time have made divergences of endless possibilities in localization technology. Localization in an indoor environment is surely a concerning matter as several shortcomings always arise when dealing with indoor localization. To optimize localization in an indoor environment, tracking a subject’s position in real-time is a certainly vital interest. Challenges in obtaining an accurate position in precise millimetre accuracy whilst the subject perceive visual information rendered in real-time is somewhat always a matter in hand to address in an indoor environment. The main objective of this research is to implement a positioning method in an indoor environment base on ultra-wideband (UWB) technology to obtain position accuracy in millimetres by rapidly integrating with Unity three-dimensional (3D) engine hence obtaining a detailed inertial measurement unit (IMU) data via wireless Message Queuing Telemetry Transport (MQTT) network protocol. The key results of this research should ensure an establishment of an indoor positioning system based on providing the finest selection of positioning and UWB parameters. These fine selections are an important design choice impacting the system’s performance in obtaining an accurate position within the range of 0.15mm to 115mm. The technological benefits involve the innovation of wireless communication based on the internet of things (IoT) concept relevant to the Industrial Revolution 4.0 (IR 4.0) enabling participants to move freely in an indoor environment whilst obtaining accurate and precise positioning coordinates. Future recommendations comprise of real-time two-dimensional (2D) Pozyx Creator Controller integrated with Unity 3D user graphical user interface (GUI) purposes intended for mobile mapping navigations.

show abstract

“…The only variables that affect the running average E[t] at time step t are the previous average and the current gradient (9). By substituting the descending mean on the previous squared gradients for the diagonal matrix (G[t]), in terms of parameter update vector ∆𝜃 𝑡 (10).…”

Section: Adaptive Delta (Adadelta)mentioning

confidence: 99%

“…In which, there are some applied studies in improving the accuracy of Transfer learning models from input data, or combining algorithms. For the improvement of input data, these studies can be mentioned: A Stacked Denoising Autoencoder [9], Sparse Fingerprinting [10], converting High-Resource to Low-Resource Language [11], time series data augmentation [12], combine images [13], …. For the algorithm, there are studies such as Vector Segmentation [14], Kidney Segmentation [15], SURF features [16], etc.…”

Section: Introductionmentioning

confidence: 99%

Evaluation of the Efficiency of the Optimization Algorithms for Transfer Learning on the Rice Leaf Disease Dataset

Quach¹,

Quoc²,

Quynh³

et al. 2022

IJACSA

View full text Add to dashboard Cite

To improve the model's efficiency, people use many different methods, including the Transfer Learning algorithm, to improve the efficiency of recognition and classification of image data. The study was carried out to combine optimization algorithms with the Transfer Learning model with MobileNet, MobileNetV2, InceptionV3, Xception, ResNet50V2, DenseNet201 models. Then, testing on rice disease data set with 13.186 images, background removed. The result obtained with high accuracy is the RMSprop algorithm, with an accuracy of 88% when combined with the Xception model, similar to the F1, Xception model, and ResNet50V2 score of 87% when combined with the Adam algorithm. This shows the effect of gradients on the Transition learning model. Research, evaluate and draw the optimal model to build a website to identify diseases on rice leaves, with the main functions including images and recording of disease identification points for better management purposes on diseased areas of rice.

show abstract

Improving UWB Indoor Localization Accuracy Using Sparse Fingerprinting and Transfer Learning

Cited by 7 publications

References 18 publications

Transfer Learning for UWB Error Correction and (N)LOS Classification in Multiple Environments

Transfer Learning for UWB Error Correction and (N)LOS Classification in Multiple Environments

Indoor Positioning System Based on UWB Rapid Integration with Unity Cross Platform Development Engine through IoT

Evaluation of the Efficiency of the Optimization Algorithms for Transfer Learning on the Rice Leaf Disease Dataset

Contact Info

Product

Resources

About