Weighted Naive Bayes Approach for Imbalanced Indoor Positioning System Using UWB

Che, Fuhu; Abbas, Waqas Bin; Ahmed, Qasim Zeeshan; Amjad, Bisma; Khan, Faheem A.; Lazaridis, Pavlos I.

doi:10.1109/blackseacom54372.2022.9858257

Cited by 12 publications

(4 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…NLOS classification research was put forward by Ziyu Lu et.al [], who detected non-direct paths using machine learning and artificial neural networks. Meanwhile, Fuhu Ce carries out NLOS classification by performing feature selection and classification using Weighted Naïve Bayes [190]. Deep learning was proposed by Alijca Olejniczac to classify LOS/NLOS using total power and first path power parameters [191].…”

Section: Discussionmentioning

confidence: 99%

Future Research and Trends in Ultra-Wideband Indoor Tag Localization

Hapsari,

Munadi,

Erfianto

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Indoor tag localization technology is one area of research applied to positioning, tracking, and navigation. UWB is a signal that is widely used for indoor tag localization with the consideration of having higher accuracy, wide bandwidth, and low power consumption. The diversity and breadth of research in the field of indoor tag localization can be confusing for new researchers to find out how this research has progressed until this day. The use of other sensors besides UWB in indoor tag localization is an alternative solution offered, thus obscuring the trend of UWB research on indoor tag localization. The way to find out whether indoor tag localization research using UWB still has a good trend and has research opportunities is to read paper reviews from previous researchers. However, until now no one has reviewed the previous paper review using the SMS and SLR methods. The SMS method is quantitative which directs the paper collection to the intended research area so it can be mapped properly. SMS is the process of identifying, categorizing, and analyzing existing literature that is relevant to a certain research topic. Meanwhile, the SLR method is qualitative which makes paper discussions sharper and more focused. SLR is the process of collecting and critically analyzing multiple research studies or papers through a systematic process. It aims to synthesize the findings of the studies and conclude the state of the art on the topic. This paper describes the literacy results of the paper using the SMS and SLR methods to thoroughly discuss research developments on UWB indoor tag localization. The discussion includes research developments and topic areas of indoor tag localization from 2017-2022, trends in the use of UWB in indoor tag localization research, issues and metrics that are carried out in indoor tag localization research, and opportunities for future research. Literacy results show that machine learning, filtering, and sensor fusion are topic areas that are currently being researched on UWB indoor tag localization. In general, every research optimizes performance metrics, namely accuracy, scalability, energy efficiency, latency, cost, and complexity. Each optimized metric related to different issues will be represented in the form of a taxonomy for easy understanding and explained in detail in this paper. Several future promising research opportunities are described in this paper to provide insight to other researchers to dig deeper into this research field.

show abstract

Section: Discussionmentioning

confidence: 99%

Future Research and Trends in Ultra-Wideband Indoor Tag Localization

Hapsari,

Munadi,

Erfianto

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…From the collected dataset, we randomly select 100 NLoS and 1000 LoS signals to generate data imbalance. We consider two more features in addition to the 10 features of [23]: i) the index of the detected first-path (F P index) and ii) the power ratio between the estimated received power and first-path power. The features and the correlation between them are illustrated in Fig.…”

Section: Experimental Setup and Data Collectionmentioning

confidence: 99%

Novel Fine-Tuned Attribute Weighted Naïve Bayes NLoS Classifier for UWB Positioning

et al. 2023

Self Cite

View full text Add to dashboard Cite

In this paper, we propose a novel Fine-Tuned attribute Weighted Naïve Bayes (FT-WNB) classifier to identify the Line-of-Sight (LoS) and Non-Line-of-Sight (NLoS) for UltraWide Bandwidth (UWB) signals in an Indoor Positioning System (IPS).The FT-WNB classifier assigns each signal feature a specific weight and fine-tunes its probabilities to address the mismatch between the predicted and actual class. The performance of the FT-WNB classifier is compared with the state-of-the-art Machine Learning (ML) classifiers such as minimum Redundancy Maximum Relevance (mRMR)-k-Nearest Neighbour (KNN), Support Vector Machine (SVM), Decision Tree (DT), Naïve Bayes (NB), and Neural Network (NN). It is demonstrated that the proposed classifier outperforms other algorithms by achieving a high NLoS classification accuracy of 99.7% with imbalanced data and 99.8% with balanced data. The experimental results indicate that our proposed FT-WNB classifier significantly outperforms the existing state-of-the-art ML methods for LoS and NLoS signals in IPS in the considered scenario.

show abstract

“…A UWB positioning system based on RF is proposed in Reference [16], the RF algorithm is innovatively applied to Kalman filter measurement update, and the Taylor algorithm is adopted to improve the estimation accuracy. To address the performance degradation caused by the disproportionate number of LOS and NLOS signals, Che et al [17] proposed the Weighted Naive Bayes algorithm to reduce the impact of the limited number of NLOS components on the train the model. The recognition effect of the method based on machine learning largely depends on offline data collecting and labeling, and selection of channel statistical characteristics.…”

Section: Related Work a Nlos Identificationmentioning

confidence: 99%

NLOS Identification for UWB Positioning Based on IDBO and Convolutional Neural Networks

Kong

2023

IEEE Access

View full text Add to dashboard Cite

Ultra-wideband (UWB) is regarded as the technology with the most potential for precise indoor location due to its centimeter-level ranging capabilities, good time resolution, and low power consumption. However, Because of the presence of non-line-of-sight (NLOS) error, the accuracy of UWB localization deteriorates significantly in harsh and volatile indoor conditions. Therefore, identifying NLOS conditions is crucial to enhancing the accuracy of UWB location. This paper proposes a convolutional neural network (CNN) classification method based on an improved Dung Beetle Optimizer (DBO). Firstly, based on the standard DBO, the Circle chaotic mapping, non-uniform Gaussian variational strategy, and multi-stage perturbation strategy are used to optimize the exploration capability and enhance the performance of original DBO method, the superiority-seeking ability of IDBO is demonstrated by testing 23 benchmark functions. In addition, based on the IDBO algorithm, we propose an IDBO-CNN classification model, with the help of IDBO, the accuracy of NLOS identification is improved by adjusting the hyperparameters of CNN to be closer to the optimal solution. Experiments conducted on the open-source dataset demonstrate that IDBO-CNN is capable of achieve the desired effect. In comparison to the conventional CNN approach, the F1-score achieved by IDBO-CNN is enhanced by 3.31%, which demonstrates that IDBO-CNN has superior identification accuracy.

show abstract

Weighted Naive Bayes Approach for Imbalanced Indoor Positioning System Using UWB

Cited by 12 publications

References 27 publications

Future Research and Trends in Ultra-Wideband Indoor Tag Localization

Future Research and Trends in Ultra-Wideband Indoor Tag Localization

Novel Fine-Tuned Attribute Weighted Naïve Bayes NLoS Classifier for UWB Positioning

NLOS Identification for UWB Positioning Based on IDBO and Convolutional Neural Networks

Contact Info

Product

Resources

About