| Presentation | 2022-01-20 Signature Code Designed by Binarized Neural Networks Lantian Wei, Shan Lu, Hiroshi Kamabe, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In multi-user communication systems, user identification and channel estimation scheme depending on signature code are interesting to many researchers. In previous works, to improve the performance of the signature code, various high-performance decoding methods have been proposed. These studies mostly use a randomly generated signature matrix. The performance of the signature code is largely dependent on the signature matrix. In this study, we use binarized neural networks with an autoencoder structure to generate the binary signature matrix. Our simulation results show that the performance of the signature matrix generated by the neural networks is better than that of the signature matrix generated randomly, and the neural networks generated matrix is suitable for various existing decoding methods. Finally, we discuss the reason why the performance of the matrix has improved. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | |
| Paper # | IT2021-34,SIP2021-42,RCS2021-202 |
| Date of Issue | 2022-01-13 (IT, SIP, RCS) |
| Conference Information | |
| Committee | RCS / SIP / IT |
|---|---|
| Conference Date | 2022/1/20(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Online |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Eiji Okamoto(Nagoya Inst. of Tech.) / Yukihiro Bandou(NTT) / Tadashi Wadayama(Nagoya Inst. of Tech.) |
| Vice Chair | Toshihiko Nishimura(Hokkaido Univ.) / Tomoya Tandai(Toshiba) / Fumihide Kojima(NICT) / Toshihisa Tanaka(Tokyo Univ. Agri.&Tech.) / Takayuki Nakachi(Ryukyu Univ.) / Tetsuya Kojima(Tokyo Kosen) |
| Secretary | Toshihiko Nishimura(NEC) / Tomoya Tandai(Panasonic) / Fumihide Kojima(Xiaomi) / Toshihisa Tanaka(Takushoku Univ.) / Takayuki Nakachi(Tokyo Univ. Agri.&Tech.) / Tetsuya Kojima(Saitamai Univ.) |
| Assistant | Koichi Adachi(Univ. of Electro-Comm.) / Osamu Nakamura(Sharp) / Manabu Sakai(Mitsubishi Electric) / Masashi Iwabuchi(NTT) / Tatsuki Okuyama(NTT DOCOMO) / Taichi Yoshida(UEC) / Seisuke Kyochi(Univ. of Kitakyushu) / Masanori Hirotomo(Saga Univ.) |
| Paper Information | |
| Registration To | Technical Committee on Radio Communication Systems / Technical Committee on Signal Processing / Technical Committee on Information Theory |
|---|---|
| Language | ENG |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Signature Code Designed by Binarized Neural Networks |
| Sub Title (in English) | |
| Keyword(1) | |
| Keyword(2) | |
| Keyword(3) | |
| Keyword(4) | |
| Keyword(5) | |
| 1st Author's Name | Lantian Wei |
| 1st Author's Affiliation | Gifu University(Gifu Univ.) |
| 2nd Author's Name | Shan Lu |
| 2nd Author's Affiliation | Gifu University(Gifu Univ.) |
| 3rd Author's Name | Hiroshi Kamabe |
| 3rd Author's Affiliation | Gifu University(Gifu Univ.) |
| Date | 2022-01-20 |
| Paper # | IT2021-34,SIP2021-42,RCS2021-202 |
| Volume (vol) | vol.121 |
| Number (no) | IT-327,SIP-328,RCS-329 |
| Page | pp.pp.34-39(IT), pp.34-39(SIP), pp.34-39(RCS), |
| #Pages | 6 |
| Date of Issue | 2022-01-13 (IT, SIP, RCS) |