QuickLoc: Adaptive Deep-Learning for Fast Indoor Localization with Mobile Devices

TL;DR

QuickLoc introduces an adaptive deep learning approach for indoor localization on mobile devices, significantly reducing prediction latency and energy consumption while maintaining high accuracy, enabling practical deployment in smart city environments.

Contribution

The paper presents a novel adaptive deep learning framework that reduces computational complexity and energy use in indoor localization without sacrificing accuracy.

Findings

Up to 42% reduction in prediction latency.

Up to 45% reduction in prediction energy.

Validated across multiple smartphones.

Abstract

Indoor localization services are a crucial aspect for the realization of smart cyber-physical systems within cities of the future. Such services are poised to reinvent the process of navigation and tracking of people and assets in a variety of indoor and subterranean environments. The growing ownership of computationally capable smartphones has laid the foundations of portable fingerprinting-based indoor localization through deep learning. However, as the demand for accurate localization increases, the computational complexity of the associated deep learning models increases as well. We present an approach for reducing the computational requirements of a deep learning-based indoor localization framework while maintaining localization accuracy targets. Our proposed methodology is deployed and validated across multiple smartphones and is shown to deliver up to 42% reduction in prediction latency and 45% reduction in prediction energy as compared to the best-known baseline deep learning-based indoor localization model.