Multi-Classification of UWB Signal Propagation Channels Based on One-Dimensional Wavelet Packet Analysis and CNN

Wang, Jin; Yu, Kegen; Bu, Jinwei; Lin, Yiruo; Han, Songtao

doi:10.1109/tvt.2022.3172863

Cited by 20 publications

(4 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Refs. [18,19] proposed a method that converts onedimensional CIR data into two-dimensional images and uses deep learning networks for identification. Its accuracy is affected by image size and inefficient operation.…”

Section: Related Workmentioning

confidence: 99%

Research on None-Line-of-Sight/Line-of-Sight Identification Method Based on Convolutional Neural Network-Channel Attention Module

Zhang,

Yi,

Huang

et al. 2023

Sensors

View full text Add to dashboard Cite

None-Line-of-Sight (NLOS) propagation of Ultra-Wideband (UWB) signals leads to a decrease in the reliability of positioning accuracy. Therefore, it is essential to identify the channel environment prior to localization to preserve the high-accuracy Line-of-Sight (LOS) ranging results and correct or reject the NLOS ranging results with positive bias. Aiming at the problem of the low accuracy and poor generalization ability of NLOS/LOS identification methods based on Channel Impulse Response (CIR) at present, the multilayer Convolutional Neural Networks (CNN) combined with Channel Attention Module (CAM) for NLOS/LOS identification method is proposed. Firstly, the CAM is embedded in the multilayer CNN to extract the time-domain data features of the original CIR. Then, the global average pooling layer is used to replace the fully connected layer for feature integration and classification output. In addition, the public dataset from the European Horizon 2020 Programme project eWINE is used to perform comparative experiments with different structural models and different identification methods. The results show that the proposed CNN-CAM model has a LOS recall of 92.29%, NLOS recall of 87.71%, accuracy of 90.00%, and F1-score of 90.22%. Compared with the current relatively advanced technology, it has better performance advantages.

show abstract

Section: Related Workmentioning

confidence: 99%

Research on None-Line-of-Sight/Line-of-Sight Identification Method Based on Convolutional Neural Network-Channel Attention Module

Zhang,

Yi,

Huang

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…In [9], three various classifiers, including SVM, multilayer perceptron, and random forest, were employed for the identification of both NLOS and multi-path conditions based on twelve features extracted from UWB. In [10][11], wavelet analysis was employed for extracting UWB information and the classifier called CNN was utilized to recognize the NLOS environment. However, the channel-based method is not applicable in practical engineering due to the high computational complexity and the need for pre-training of classifiers.…”

Section: Introductionmentioning

confidence: 99%

Study on the indoor mobile robot localization based on multi-sensor fusion

He,

2024

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

In recent years, mobile robots have found extensive application across diverse sectors including industry, agriculture, healthcare, and defense. However, relying solely on a single sensor for mobile robot localization presents several challenges, such as limited accuracy, divergence of localization errors over time, and susceptibility to obstruction from obstacles. This paper proposes an indoor mobile robot localization algorithm assisted by Ultra-Wideband (UWB). The algorithm begins by calculating the credibility of the Line-of-Sight (LOS) environment using UWB ranging measurements and predicted distances, enabling the identification of the Non-Line-of-Sight (NLOS) environment. Subsequently, ranging measurements affected by NLOS errors are compensated by using a complementary filter. Finally, these measurements are utilized for Extended Kalman Filter updates to achieve the best estimation of the mobile robot’s position. Field tests are conducted on a wheeled robot to validate the effectiveness and performance of the developed approach. Results show that the localization approach reduces the maximum localization error from 41 cm to 19 cm compared to UWB trilateration, achieving a 53.7% improvement. Even under a prolonged NLOS environment, the algorithm ensures that the localization error remains below 25 cm. The proposed method is of significant merit in solving the challenge of indoor mobile robot localization.

show abstract

“…In addition, when evaluating the accuracy of the machine learning algorithms, the test set and training set used in existing literatures are measured at the same position without testing the performance through data independent of the training set [6,7,[10][11][12][13][14][15] which is not practical because the scope of test set is always much larger than that of training set, and UWB mobile nodes may distribute in any corner of the room.…”

Section: Introductionmentioning

confidence: 99%

Dataset collecting for UWB NLOS identification based on machine learning

Zhang,

Liu,

Hao

2023

Sixth International Conference on Computer Information Science and Application Technology (CISAT 2023)

View full text Add to dashboard Cite

The Non-Line-of-Sight (NLOS) environment significantly reduces the accuracy of Ultra-Wideband (UWB) ranging and positioning in the UWB positioning system based on time of arrival. The mainstream method is to identify the Line-of-Sight (LOS) and NLOS environment through machine learning and make corresponding corrections to improve the accuracy of the positioning system. However, the existing research and application of machine learning methods do not fully consider the situation that the test set exceeds the training set, which is inconsistent with the actual scenario. Firstly, in this paper, we show through experimental results that when the test set and the training set are independent, different training set acquisition methods will directly affect the accuracy of machine learning. The denser the training set, the higher the precision and the greater the workload. Therefore, aiming at how to choose the training set collection scheme, we put forward an evaluation index to determine the best training set collection scheme. Commonly used machine learning algorithms, such as Random Forest (RF), and XGBoost, are used here to explore the parameter configuration of this index. The research results show that when using machine learning method to identify ultra-wideband NLOS scenes, the acquisition step size of training set is 1.6 meters, which can make the identification accuracy high and the acquisition workload small.

show abstract

Multi-Classification of UWB Signal Propagation Channels Based on One-Dimensional Wavelet Packet Analysis and CNN

Cited by 20 publications

References 49 publications

Research on None-Line-of-Sight/Line-of-Sight Identification Method Based on Convolutional Neural Network-Channel Attention Module

Research on None-Line-of-Sight/Line-of-Sight Identification Method Based on Convolutional Neural Network-Channel Attention Module

Study on the indoor mobile robot localization based on multi-sensor fusion

Dataset collecting for UWB NLOS identification based on machine learning

Contact Info

Product

Resources

About