Neural Network Localization With TOA Measurements Based on Error Learning and Matching

Wu, Shixun; Zhang, Shengjun; Xu, Kai; Huang, Darong

doi:10.1109/access.2019.2897153

Cited by 18 publications

(16 citation statements)

References 38 publications

(40 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Specifically, for our evaluation in MLP, the misclassification rate of MP as LOS increased from 2.2% to 7.7%, while MP as NLOS increased from 1.1% to 5.9% ( Figure 10). In fact, the predicted accuracy of both LOS and NLOS also declined in the MLP classifier, i.e., from 30 Figure 10. Comparison of the multi-class classification results for the MLP classifier using confusion matrices in two scenarios: (a) the test dataset obtained from the same conditions as the training phase; (b) the test dataset collected in a different condition from the training.…”

Section: Comparative Analysis Of the Two Test Scenarios For The Mlp Cmentioning

confidence: 96%

“…This paper is solely focused on the former case. In fact, there exists a method that bypasses the identification process and directly mitigates the ranging error using channel statistics and SVM as an ML-based classifier [18,30]. However, this method restricts the flexibility to choose different positioning algorithms in the latter case since the mitigation technique is limited to a few compatible algorithms.…”

Section: Related Workmentioning

confidence: 99%

“…The common approach is to detect the non-direct path signal (i.e., NLOS and/or MP) and use the detected information to modify the location algorithm in order to mitigate the biases caused by the NLOS and/or MP conditions [9,10,17,18,20,21,30]. In this manuscript, we divided the related works into two subsections: (i) conventional approaches without using ML techniques (Section 3.1) and (ii) ML-based approaches (Section 3.2).…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Identification of NLOS and Multi-Path Conditions in UWB Localization Using Machine Learning Methods

et al. 2020

View full text Add to dashboard Cite

In ultra-wideband (UWB)-based wireless ranging or distance measurement, differentiation between line-of-sight (LOS), non-line-of-sight (NLOS), and multi-path (MP) conditions is important for precise indoor localization. This is because the accuracy of the reported measured distance in UWB ranging systems is directly affected by the measurement conditions (LOS, NLOS, or MP). However, the major contributions in the literature only address the binary classification between LOS and NLOS in UWB ranging systems. The MP condition is usually ignored. In fact, the MP condition also has a significant impact on the ranging errors of the UWB compared to the direct LOS measurement results. However, the magnitudes of the error contained in MP conditions are generally lower than completely blocked NLOS scenarios. This paper addresses machine learning techniques for identification of the three mentioned classes (LOS, NLOS, and MP) in the UWB indoor localization system using an experimental dataset. The dataset was collected in different conditions in different scenarios in indoor environments. Using the collected real measurement data, we compared three machine learning (ML) classifiers, i.e., support vector machine (SVM), random forest (RF) based on an ensemble learning method, and multilayer perceptron (MLP) based on a deep artificial neural network, in terms of their performance. The results showed that applying ML methods in UWB ranging systems was effective in the identification of the above-three mentioned classes. Specifically, the overall accuracy reached up to 91.9% in the best-case scenario and 72.9% in the worst-case scenario. Regarding the F1-score, it was 0.92 in the best-case and 0.69 in the worst-case scenario. For reproducible results and further exploration, we provide the publicly accessible experimental research data discussed in this paper at PUB (Publications at Bielefeld University). The evaluations of the three classifiers are conducted using the open-source Python machine learning library scikit-learn.

show abstract

Section: Comparative Analysis Of the Two Test Scenarios For The Mlp Cmentioning

confidence: 96%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Identification of NLOS and Multi-Path Conditions in UWB Localization Using Machine Learning Methods

et al. 2020

View full text Add to dashboard Cite

show abstract

“…This paper is solely focused on the former case. In fact, there exists a method that by-pass the identification process and directly mitigate the ranging error using channel statistics and SVM as a ML-based classifier [16,27]. However, this method restricts the flexibility to choose different positioning algorithms in the later case since the mitigation technique is limited to a few compatible algorithms.…”

Section: Related Workmentioning

confidence: 99%

Identification of NLOS and Multi-Path Conditions in UWB Localization Using Machine Learning Methods

Sang¹,

Steinhagen²,

Homburg³

et al. 2020

Preprint

View full text Add to dashboard Cite

In Ultra-wideband (UWB)-based wireless ranging or distance measurement, differentiation between line-of-sight~(LOS), non-line-of-sight~(NLOS), and multi-path (MP) conditions are important for precise indoor localization. This is because the accuracy of the reported measured distance in UWB ranging systems is directly affected by the measurement conditions (LOS, NLOS or MP). However, the major contributions in literature only address the binary classification between LOS and NLOS in UWB ranging systems. The MP condition is usually ignored. In fact, the MP condition also has a significant impact on the ranging errors of the UWB compared to the direct LOS measurement results. Though, the magnitudes of the error contained in MP conditions are generally lower than completely blocked NLOS scenarios. This paper addresses machine learning techniques for identification of the mentioned three classes (LOS, NLOS, and MP) in the UWB indoor localization system using an experimental data-set. The data-set was collected in different conditions at different scenarios in indoor environments. Using the collected real measurement data, we compare three machine learning (ML) classifiers, i.e., support vector machine (SVM), random forest (RF) based on an ensemble learning method, and multilayer perceptron (MLP) based on a deep artificial neural network, in terms of their performance. The results show that applying ML methods in UWB ranging systems are effective in identification of the above-mentioned three classes. In specific, the overall accuracy reaches up to 91.9% in the best-case scenario and 72.9% in the worst-case scenario. Regarding the F1-score, it is 0.92 in the best-case and 0.69 in the worst-case scenario. For reproducible results and further exploration, we (will) provide the publicly accessible experimental research data discussed in this paper at PUB - Publications at Bielefeld University. The evaluations of the three classifiers are conducted using the open-source python machine learning library scikit-learn.

show abstract

“…It realizes comparable performance to the current methods with significantly higher effectiveness. To deal with multiple types of errors, the artificial neural network (ANN) and radial basis function (RBF) neural network are introduced to alleviate the accuracy loss due to the measurement error, non-line of sight (NLOS) error, and synchronization error [29].…”

Section: Introductionmentioning

confidence: 99%

Refinement of TOA Localization with Sensor Position Uncertainty in Closed-Form

Gan¹,

Cong²,

Sun

2020

Sensors

View full text Add to dashboard Cite

The subject of localization has received great deal attention in the past decades. Although it is perhaps a well-studied problem, there is still room for improvement. Traditional localization methods usually assume the number of sensors is sufficient for providing desired performance. However, this assumption is not always satisfied in practice. This paper studies the time of arrival (TOA)-based source positioning in the presence of sensor position errors. An error refined solution is developed for reducing the mean-squared-error (MSE) and bias in small sensor network (the number of sensors is fewer) when the noise or error level is relatively large. The MSE performance is analyzed theoretically and validated by simulations. Analytical and numerical results show the proposed method attains the Cramér-Rao lower bound (CRLB). It outperforms the existing closed-form methods with slightly raising computation complexity, especially in the larger noise/error case.

show abstract

Neural Network Localization With TOA Measurements Based on Error Learning and Matching

Cited by 18 publications

References 38 publications

Identification of NLOS and Multi-Path Conditions in UWB Localization Using Machine Learning Methods

Identification of NLOS and Multi-Path Conditions in UWB Localization Using Machine Learning Methods

Identification of NLOS and Multi-Path Conditions in UWB Localization Using Machine Learning Methods

Refinement of TOA Localization with Sensor Position Uncertainty in Closed-Form

Contact Info

Product

Resources

About