Transfer learning improves indoor localization accuracy and energy use
A Transfer Learning-Driven Methodology for Efficient and Sustainable Indoor Localization Using VLC
Machine Learning
Summary
Indoor localization helps track devices inside buildings, which is important for factories and automation. Traditional methods need lots of data and energy, and they don't work well when lighting or obstacles change. The authors propose using transfer learning, a technique that reuses knowledge from one setting to help another, making localization more accurate and energy efficient. They tested their method in a real factory and found big improvements in accuracy and energy use compared to older methods.
What this means in practice
- •For industrial automation teams: Improve device tracking inside factories with less energy and better accuracy despite changing environments using visible light signals.
- •For smart building operators: Deploy energy-saving indoor location services that adapt to lighting changes and physical obstacles for better asset monitoring.
Authors
Masood Jan, Wafa Njima, Xun Zhang, Alexander Artemenko
Abstract
The rapid expansion of the Internet of Things enables seamless collaboration among connected devices, making indoor localization a critical component of industrial automation. However, conventional localization techniques struggle in dynamic environments. These methods depend on extensive, frequent data collection and environment-specific calibration, limiting scalability, interoperability, and effective use of prior research while imposing significant energy penalties that hinder practical deployment. To address these challenges, we propose an energy-efficient transfer learning (TL) based approach for visible light communication based indoor localization. Our method leverages TL to tackle environmental variability, including lighting fluctuations and physical obstacles that typically degrade localization performance, while simultaneously reducing computational overhead and energy consumption compared to conventional approaches. We also introduce a novel model efficiency (ME) metric, designed to integrate localization accuracy, energy efficiency, data efficiency, and transfer gain into a single evaluative measure for comprehensive optimization. Evaluations on a real-world dataset collected from a BOSCH factory demonstrate that our model achieves a 47% improvement in localization accuracy compared to a conventional model that does not utilize TL, and achieves up to 67.5% ME with TL models, compared to only 10.4% in conventional models under high-noise conditions. These results underscore the potential of our approach to deliver a highly efficient and scalable indoor localization system suitable for energy-constrained industrial applications.