Trilateration-based target localization using received signal strengths (RSS) within wireless sensor networks (WSN) often results in inaccurate location estimates due to the considerable fluctuations in RSS measurements encountered in indoor environments. Enhancing the precision of RSS-based localization systems has been a primary area of interest in extensive research efforts. This study introduces two range-free algorithms, Ensemble Learning (EL) and EL+KF, which leverage RSS measurements for localization. In contrast to trilateration, the EL- based localization approach enables the direct estimation of target locations based on field measurements, eliminating the need for distance calculations. Notably, unlike other cutting-edge localization and tracking (L&T) scheme like the support vector regression (SVR), the LSBoost (Least Squares Boosting) EL based localization architecture can be trained very quickly using RSS measurements to determine the mobile target's position. Furthermore, the proposed EL-based localization scheme incorporates the Kalman filter (KF) to achieve additional refinement in target location estimates. To assess the localization effectiveness of these proposed algorithms in the presence of noisy RF channels and dynamic target motion models, rigorous simulations were conducted. Thanks to the robust generalization capabilities of EL, the simulation results reveal that the presented EL-based localization algorithms exhibit superior performance compared to trilateration and the SVR-based localization scheme, particularly in terms of indoor localization accuracy.
Read full abstract