English

CHISEL: Compression-Aware High-Accuracy Embedded Indoor Localization with Deep Learning

Machine Learning 2021-07-05 v1 Artificial Intelligence

Abstract

GPS technology has revolutionized the way we localize and navigate outdoors. However, the poor reception of GPS signals in buildings makes it unsuitable for indoor localization. WiFi fingerprinting-based indoor localization is one of the most promising ways to meet this demand. Unfortunately, most work in the domain fails to resolve challenges associated with deployability on resource-limited embedded devices. In this work, we propose a compression-aware and high-accuracy deep learning framework called CHISEL that outperforms the best-known works in the area while maintaining localization robustness on embedded devices.

Keywords

Cite

@article{arxiv.2107.01192,
  title  = {CHISEL: Compression-Aware High-Accuracy Embedded Indoor Localization with Deep Learning},
  author = {Liping Wang and Saideep Tiku and Sudeep Pasricha},
  journal= {arXiv preprint arXiv:2107.01192},
  year   = {2021}
}
R2 v1 2026-06-24T03:51:07.147Z