Research on Small Sample Radio Signal Analysis Based on the VSGGTD Algorithm

DOI

10.2991/tlicsc-18.2018.11How to use a DOI?

Keywords

Small sample data; feature extraction; virtual sample; underfitting.

Abstract

The current feature extraction methods for small sample signals focus on improving the performance. How to build a virtual sample set with strong rationality and high accuracy based on the original sample is one of the challenges in realizing small sample signal analysis. In line with the radio service feature in the time domain and the frequency domain of signals, this paper proposes a virtual sample generation method based on an improved Gaussian algorithm, the VSGGTD algorithm, and proves its rationality from mathematics. In the experiment, feature extraction was carried out for the sample set before and after expansion, and the different extraction results were compared. Experimental results show that this algorithm can improve the underfitting phenomenon caused by small sample size.

Copyright

© 2018, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Kai Zhou
AU  - Kaiyu Qin
AU  - Yuqi Zeng
AU  - Xueling Zhang
PY  - 2018/12
DA  - 2018/12
TI  - Research on Small Sample Radio Signal Analysis Based on the VSGGTD Algorithm
BT  - Proceedings of the 2018 International Conference on Transportation & Logistics, Information & Communication, Smart City (TLICSC 2018)
PB  - Atlantis Press
SP  - 70
EP  - 74
SN  - 1951-6851
UR  - https://doi.org/10.2991/tlicsc-18.2018.11
DO  - 10.2991/tlicsc-18.2018.11
ID  - Zhou2018/12
ER  -