An Enhancement of Indoor Localization using PCA-aided LSTM Approach

This paper presents an approach that combines Principal Component Analysis (PCA) and Long Short-Term Memory (LSTM) to enhance the accuracy of indoor positioning systems. The proposed approach exploits the advantages of PCA in reducing data dimensionality, leading to reduced computational complexity while preserving essential data features. To evaluate the performance of our approach, we conducted experiments using a public dataset. The results demonstrate that our approach achieved a Root Mean Square Error (RMSE) of 1.95 meters and a distance error of 2.2 meters. These results surpass state-of-the-art studies on the same dataset, showcasing a significant improvement in accuracy with a reduction in distance error ranging from 12.0% to 18.5%. Moreover, our approach substantially reduces the time required for position prediction by half. These remarkable advancements confirm the effectiveness of our proposed approach.