Summary
International Conference on Emerging Technologies for Communications
2020
Session Number:H2
Session:
Number:H2-3
Indoor Experiments on Transfer Learning-Based Received Power Prediction
Masahiro Iwasaki, Takayuki Nishio, Masahiro Morikura, Koji Yamamoto, Riichi Kudo, Kahoko Takahashi, Tomoaki Ogawa,
pp.-
Publication Date:2020/12/2
Online ISSN:2188-5079
DOI:10.34385/proc.63.H2-3
PDF download
Summary:
This paper proposes a method to predict received power in indoor environments deterministically, which can learn a prediction model from small amount of measurement data by a simulation-aided transfer learning and data augmentation. Recent development in machine learning such as artificial neural network (ANN) enables us to predict radio propagation and path loss accurately. However, training a high-performance ANN model requires a significant number of data, which are difficult to obtain in real environments. The main motivation for this work was to facilitate accurate prediction using small amount of measurement data. To this end, we propose a transfer learning-based prediction method with data augmentation. The proposed method pre-trains a prediction model using data generated from ray-tracing simulations, increases the number of data using simulation-assisted data augmentation, and then fine-tunes a model using the augmented data to fit the target environment. Experiments using Wi-Fi devices were conducted, and we demonstrated that the feasibility of received power prediction in indoor environments.