IEICE Communications Express
Online ISSN : 2187-0136
ISSN-L : 2187-0136

この記事には本公開記事があります。本公開記事を参照してください。
引用する場合も本公開記事を引用してください。

A formulation-aid transfer learning-based framework in received power prediction
Khanh N. NguyenKenichi Takizawa
著者情報
ジャーナル フリー 早期公開

論文ID: 2022XBL0143

この記事には本公開記事があります。
詳細
抄録

This study is motivated by the demand for an efficient deep learning-based model that helps us predict the future link quality for intelligent decision-making systems. In this letter, we propose a transfer learning-based approach to predict millimeter-wave future received power in an indoor environment. The model is pre-trained using formulation-aid generated data and fine-tuned using measured data. The proposed framework reduces more than 30% in root-mean-square error and 6.5% in accuracy with high training speed compared to the baseline training from scratch.

著者関連情報
© 2022 The Institute of Electronics, Information and Communication Engineers
feedback
Top