Transfer learning improves indoor location using visible light signals
Cross-Area Transfer Learning for VLC-based Indoor Localization with a Transfer Efficiency Score
Machine Learning
Summary
Indoor systems that find exact locations using visible light signals can struggle when they move to new rooms or areas because the environment changes. The authors show that by training a smart computer program on data from one area, then adjusting it with only some data from a new area, it can learn to locate things almost as well as if it had full data for that new spot. They also create a score that helps pick the best initial model to adapt for new places without trying them all. This method saves time and effort while keeping location accuracy high in different factory settings.
What this means in practice
- •For industrial automation teams: Improve indoor tracking systems by reusing previous visible light models, reducing data needs when deploying localization in new factory zones.
- •For smart building integrators: Deploy visible light localization that adapts quickly to different rooms with limited new measurements, enhancing position accuracy and system efficiency.
Authors
Masood Jan, Wafa Njima, Xun Zhang, Alexander Artemenko
Abstract
Indoor localization systems are critical for Industry-4.0 applications. Visible Light Communication (VLC)-based systems offer advantages such as immunity to electromagnetic interference, high accuracy, and energy efficiency, but their performance is hindered by environmental variability across deployment areas. This paper presents a transfer learning (TL) framework for VLC-based indoor localization that enhances cross-area robustness while reducing data requirements. Using real-world measurements from four distinct areas of a Bosch manufacturing facility, we show that fine-tuning a deep neural network (DNN) pre-trained on source area data with only 40% of target-area measurements recovers 97% of full-data performance, thereby reducing the amount of target data needed. We further introduce the Transfer Efficiency Score (TES), a composite metric that identifies the most effective source models for transfer without exhaustive evaluation. Guided by TES, the framework selects the best source model, yielding localization errors as low as 40.9 cm with success rates above 86%. Validation on an unseen area confirms its generalization capability, with a 3.28 cm mean error achieved using the TES-selected source model. Overall, the proposed framework provides a scalable and data-efficient pathway for industrial VLC localization, substantially reducing deployment costs and computational burden while maintaining high accuracy in diverse and dynamic environments.