AI Article Synopsis
- The authors developed a new indoor visible light positioning (VLP) design tool by transforming existing lighting design software.
- The tool effectively integrates various deep learning techniques, potentially minimizing the need for extensive training data collection.
- Experimental results indicate that the accuracy of the VLP models is comparable whether trained on real-world data or data generated by the software, demonstrating reduced training workload.
Article Abstract
We put forward and transform the commercially available lighting design software into an indoor visible light positioning (VLP) design tool. The proposed scheme can work well with different deep learning methods for reducing the loading of training data set collection. The indoor VLP models under evaluation include second order regression, fully-connected neural-network (FC-NN), and convolutional neural-network (CNN). Experimental results show that the similar positioning accuracy can be obtained when the indoor VLP models are trained with experimentally acquired data set or trained with software obtained data set. Hence, the proposed method can reduce the training loading for the indoor VLP.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1364/OE.459942 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!