Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2511.19891 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914170136428544 |
|---|---|
| author | Stefanakis, Pantelis Shen, Ming |
| author_facet | Stefanakis, Pantelis Shen, Ming |
| contents | Phase-Based Ranging (PBR) offers several advantages for estimating distances between wirelessly connected devices, including high accuracy over large distances and the removal of the need for antenna arrays at each transceiver. This study investigates the use of Neural Network (NN)-based models for accurate PBR in three distinct environments: Openfield, Office, and Near Buildings, comparing their performance with established non-NN methods. A novel 2NN Model is proposed, integrating two neural networks: one to classify the environment and another to predict distances. Performance was evaluated over 20 trials for each method and dataset using root mean square error (RMSE) and maximum prediction error.
Results show that the 2NN Model consistently outperformed other methods, frequently ranking among the top methods in minimizing both RMSE and maximum error. In addition, the 2NN Model achieved the best average RMSE and the lowest maximum error. To assess the effect of environment misclassification, filtered versions of the NN models were evaluated by omitting misclassified measurements prior to RMSE calculation. Although unsuitable for production use, the filtered models revealed that misclassifications in the 2NN Model had a significant impact. Its filtered variant achieved the lowest RMSE and maximum error across all datasets, and ranked first in the frequency of attaining the lowest maximum error over 20 trials.
Overall, the findings show that NN models deliver robust, high-accuracy ranging across diverse environments, outperforming non-NN methods and reinforcing their potential as universal PBR solutions when trained on comprehensive distance datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_19891 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Joint Classification and Regression Deep Learning Model for Universal Phase-based Ranging in Multiple Environments Stefanakis, Pantelis Shen, Ming Signal Processing Phase-Based Ranging (PBR) offers several advantages for estimating distances between wirelessly connected devices, including high accuracy over large distances and the removal of the need for antenna arrays at each transceiver. This study investigates the use of Neural Network (NN)-based models for accurate PBR in three distinct environments: Openfield, Office, and Near Buildings, comparing their performance with established non-NN methods. A novel 2NN Model is proposed, integrating two neural networks: one to classify the environment and another to predict distances. Performance was evaluated over 20 trials for each method and dataset using root mean square error (RMSE) and maximum prediction error. Results show that the 2NN Model consistently outperformed other methods, frequently ranking among the top methods in minimizing both RMSE and maximum error. In addition, the 2NN Model achieved the best average RMSE and the lowest maximum error. To assess the effect of environment misclassification, filtered versions of the NN models were evaluated by omitting misclassified measurements prior to RMSE calculation. Although unsuitable for production use, the filtered models revealed that misclassifications in the 2NN Model had a significant impact. Its filtered variant achieved the lowest RMSE and maximum error across all datasets, and ranked first in the frequency of attaining the lowest maximum error over 20 trials. Overall, the findings show that NN models deliver robust, high-accuracy ranging across diverse environments, outperforming non-NN methods and reinforcing their potential as universal PBR solutions when trained on comprehensive distance datasets. |
| title | Joint Classification and Regression Deep Learning Model for Universal Phase-based Ranging in Multiple Environments |
| topic | Signal Processing |
| url | https://arxiv.org/abs/2511.19891 |