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

TL;DR

CHISEL is a deep learning framework designed for high-accuracy indoor localization using WiFi fingerprinting, optimized for resource-limited embedded devices, outperforming existing methods in robustness and deployability.

Contribution

This work introduces CHISEL, a novel compression-aware deep learning approach that enhances indoor localization accuracy and robustness on embedded devices.

Findings

Outperforms existing WiFi fingerprinting methods in accuracy

Maintains robustness on resource-constrained embedded devices

Demonstrates effective compression for deployment

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.