Detecting and Controlling Smart Lights with LiTalk

TL;DR

This paper introduces a machine learning-based Visible Light Communication approach to automate the mapping of smart light identifiers to their physical locations, improving accuracy and reducing manual effort.

Contribution

It presents a novel method combining VLC and machine learning to automate smart light location mapping, outperforming existing techniques.

Findings

Enhanced location-mapping accuracy over traditional methods

Reduced manual effort in smart light deployment

Effective automation for non-stationary lights

Abstract

The rapid increase in demand for wireless controlled Smart Lighting has created a need to automate the mapping between the identifiers for individual light sources and their physical locations. To control Smart Lights, their IDs and physical locations relative to each other must be determined. Nowadays, skilled technicians perform this process manually, which requires a lot of effort, is time-consuming, and incurs high costs, particularly with non-stationary lights. Visible Light Communication has been presented as a possible solution to this problem. This paper presents an approach based on Visible Light Communication that leverages Machine Learning to automate the mapping process between the identifiers and the relative physical location of Smart Lights. We show that our approach provides a better location-mapping performance compared to existing methods.