| Presentation | 2020-11-18 Automatic Modulation Recognition Method Using Two-Stage Deep Learning Kaoru Kishimoto, Kiyohiko Takahashi, Taichi Ohtsuji, Toshiki Takeuchi, Shigeyuki Kurahashi, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Automatic modulation recognition method could be applied to dynamic spectrum sharing, estimating communication method of the primary users or the other secondary users．In addition to classical methods such as statistical analysis of the phase and amplitude components of IQ signals, deep-learning-based methods have been studied in recent years. Deep-learning-based methods could estimate modulation scheme using learned model in a short time. However, when there is a difference between center frequency of the training data and that of the estimation data, there is a problem that the estimation performance significantly decreases. Therefore, we propose a two-stage estimation method; the first stage estimates the gap frequency between zero and center frequency of the target signals, and shifts the center frequency with the estimated gap, then the second stage estimates the modulation scheme of the shifted signals. Experimental results demonstrate that the average estimation accuracy of the proposed method is about 9 pt higher than that of the conventional method in 0 to 10-dB conditions. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Automatic Modulation Recognition / Deep Learning / Two-stage estimation |
| Paper # | SR2020-24 |
| Date of Issue | 2020-11-11 (SR) |
| Conference Information | |
| Committee | SR |
|---|---|
| Conference Date | 2020/11/18(3days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Online |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Software Radio, Cognitive Radio, Spectrum Sharing, etc. |
| Chair | Masayuki Ariyoshi(NEC) |
| Vice Chair | Suguru Kameda(Tohoku Univ.) / Osamu Takyu(Shinshu Univ.) / Kentaro Ishidu(NICT) |
| Secretary | Suguru Kameda(ATR) / Osamu Takyu(Univ. of Electro-Comm.) / Kentaro Ishidu(Mie Univ.) |
| Assistant | Mai Ohta(Fukuoka Univ.) / Teppei Oyama(Fujitsu Lab.) / Kentaro Kobayashi(Nagoya Univ.) |
| Paper Information | |
| Registration To | Technical Committee on Smart Radio |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Automatic Modulation Recognition Method Using Two-Stage Deep Learning |
| Sub Title (in English) | |
| Keyword(1) | Automatic Modulation Recognition |
| Keyword(2) | Deep Learning |
| Keyword(3) | Two-stage estimation |
| 1st Author's Name | Kaoru Kishimoto |
| 1st Author's Affiliation | NEC Corporation(NEC) |
| 2nd Author's Name | Kiyohiko Takahashi |
| 2nd Author's Affiliation | NEC Corporation(NEC) |
| 3rd Author's Name | Taichi Ohtsuji |
| 3rd Author's Affiliation | NEC Corporation(NEC) |
| 4th Author's Name | Toshiki Takeuchi |
| 4th Author's Affiliation | NEC Corporation(NEC) |
| 5th Author's Name | Shigeyuki Kurahashi |
| 5th Author's Affiliation | NEC Corporation(NEC) |
| Date | 2020-11-18 |
| Paper # | SR2020-24 |
| Volume (vol) | vol.120 |
| Number (no) | SR-238 |
| Page | pp.pp.10-16(SR), |
| #Pages | 7 |
| Date of Issue | 2020-11-11 (SR) |