Wi-Fi fingerprinting-based indoor localization is an emerging embedded application domain that leverages existing Wi-Fi access points (APs) in buildings to localize users with smartphones. Unfortunately, it has been demonstrated that the heterogeneity of wireless transceivers among various cellphones used by consumers reduces the accuracy and dependability of localization algorithms. In this chapter, we propose a novel framework based on vision transformer neural networks called VITAL that addresses this important challenge. Experiments indicate that VITAL can reduce the uncertainty created by smartphone heterogeneity while improving localization accuracy from 41% to 68% over the best-known prior works. We also demonstrate the generalizability of our approach and propose a data augmentation technique that can be integrated into most deep learning-based localization frameworks to improve accuracy.
CITATION STYLE
Gufran, D., Tiku, S., & Pasricha, S. (2023). Heterogeneous Device Resilient Indoor Localization Using Vision Transformer Neural Networks. In Machine Learning for Indoor Localization and Navigation (pp. 357–375). Springer International Publishing. https://doi.org/10.1007/978-3-031-26712-3_15
Mendeley helps you to discover research relevant for your work.