Deep Transfer Learning for WiFi Localization

TL;DR

This paper presents a deep transfer learning approach for WiFi indoor localization using CNNs on CSI data, demonstrating significant reductions in training time and data requirements while maintaining high accuracy across different environments.

Contribution

It introduces a transfer learning method for WiFi localization CNN models, enabling feature reuse and reducing training data and time needed.

Findings

Achieved localization accuracy of 46.55 cm in ideal conditions.

Transfer of feature extraction layers retains accuracy with less training data.

Reduced training parameters by 60% and training time by over 50%.

Abstract

This paper studies a WiFi indoor localisation technique based on using a deep learning model and its transfer strategies. We take CSI packets collected via the WiFi standard channel sounding as the training dataset and verify the CNN model on the subsets collected in three experimental environments. We achieve a localisation accuracy of 46.55 cm in an ideal $(6.5m \times 2.5m)$ office with no obstacles, 58.30 cm in an office with obstacles, and 102.8 cm in a sports hall $(40 \times 35m)$. Then, we evaluate the transfer ability of the proposed model to different environments. The experimental results show that, for a trained localisation model, feature extraction layers can be directly transferred to other models and only the fully connected layers need to be retrained to achieve the same baseline accuracy with non-transferred base models. This can save 60% of the training parameters and reduce the training time by more than half. Finally, an ablation study of the training dataset shows that, in both office and sport hall scenarios, after reusing the feature extraction layers of the base model, only 55% of the training data is required to obtain the models' accuracy similar to the base models.