Novel Fine-Tuned Attribute Weighted Naïve Bayes NLoS Classifier for UWB Positioning
This work addresses the challenge of accurate signal classification for indoor positioning systems, which is incremental as it builds on existing Naïve Bayes methods with fine-tuning and weighting.
The paper tackles the problem of classifying Line-of-Sight (LoS) and Non-Line-of-Sight (NLoS) signals in UltraWide Bandwidth (UWB) indoor positioning by proposing a Fine-Tuned attribute Weighted Naïve Bayes (FT-WNB) classifier, which achieves NLoS classification accuracies of 99.7% with imbalanced data and 99.8% with balanced data, outperforming state-of-the-art machine learning methods.
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.