Comparison of Random Forest and Extreme Gradient Boosting Fingerprints to Enhance an indoor Wifi Localization System

Machine Learning framework adds a new dimension to the localization estimation problem. It tries to find the most likely position using processed features in a radio map. This paper compares the performance of two machine learning tools, Random Forest (RF) and Extreme Gradient Boosting (XGBoost), in exploiting the multipath information for Indoor localization problem. The investigation was carried out in a noisy indoor scenario, where Non-Line-Of-Sight (NLOS) between target and sensors may affect the location of Wi-Fi Access point strongly. It is possible to improve the position system performance by using fingerprints techniques that employ multipath information in a Machine Learning framework, which operates a dataset generated by real time. Usually, real measurements produce the fingerprints localization features, and there is mismatching with the simulated data. Another drawback of NLOS features extraction is the noise level that occurs in position processing. Random Forest algorithm uses fully grown decision trees to classify possible emitter position, trying to achieve error mitigation by reducing variance. On the other hand, XGBoost approach uses weak learners, defined by high bias and low variance. The results of the simulation show that XGBoost reaches a Mean Square Error (MSE) of 1.77m while RF has 1.83m, as shown in Fig. (4). In real time analysis, 40 points were used for testing. RF has an MSE 1.85m and XGBoost has 1.82m. The results are compared to the state of the art and recently published papers.