Discrete Indoor Three-Dimensional Visible Light Communication Localization System Based on Machine Learning Algorithms

Abstract

3D indoor visible light communication (VLC) localization system, based on received signal strength (RSS) and several machine learning (ML) algorithms, are proposed. k nearest Neighbours (K-NN), random forest (RF), support vector machine (SVM), decision tree and neural network (NN) are the utilized models in this paper. Dataset gathering is determined from three grids of different points of RSSs. This dataset is used in the training phase. To verify the robustness of the proposed work, several evaluation metrics are utilized. Specifically, training time, testing time, classification accuracy (CA), area under curve (AUC), F1-score, precision, recall, logloss and specificity. The results of the proposed framework achieve 97.9 % for AUC, and 96.3 % for CA, precision, F1-score, and recall. The logloss and precision are 16 % and 98.2 %, respectively. Moreover, in order to ensure the robustness of the proposed framework, other several evaluation metric are utilized. Practically, mean square error (MSE), root mean square error RMSE, mean absolute error (MAE) and coefficient of determination (R2). The results of the superior model fulfils with RMSE equal <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\text{0. 0 0 1 ~ c m}$</tex>. And <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\text{1. 0 0 0}$</tex> for R2.