Presentation | 2021-06-24 A Study on Deep Unfolding-Aided Belief Propagation for Error Correction Decoding of CRC Code Qilin Zhang, Shinsuke Ibi, Takumi Takahashi, Hisato Iwai, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Internet of things (IoT), which plays an important role in the next-generation wireless communication infrastructure, tends to use small packet size. Therefore, even if an error correction code designed for long code length such as low-density parity-check (LDPC) code is utilized for IoT, high error correction capability cannot be expected. This is why some configurations which deliberately do not use error-correcting codes are sometimes used in a standards, such as bluetooth low energy (BLE) 4.0. However, even in such configurations, the cyclic redundancy check (CRC) code is usually used to detect errors in the packets. Since a parity bit of about 24 bits is added to the information bit sequence of the CRC code, the coding rate will be higher when the information bit sequence length is very long. So, in general, the CRC code is not used as an error correction code. However, on the premise that IoT has a small packet size, it is possible to use error detecting code as error correction code. As the decoding method, belief propagation (BP) can be considered. Unfortunately, the parity check matrix contains many short cycles, so its decoding performance is not good. In this paper, we apply deep unfolding (DU), which is a kind of deep learning techniques, to BP based on the analogy between the belief propagation and the structure of the deep neural network, and clarify the improvement of decoding performance of DU-aided BP. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | CRC code / belief propagation / deep learning / deep unfolding / data-driven tuning |
Paper # | RCS2021-55 |
Date of Issue | 2021-06-16 (RCS) |
Conference Information | |
Committee | RCS |
---|---|
Conference Date | 2021/6/23(3days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Online |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | First Presentation in IEICE Technical Committee, Resource Control, Scheduling, Wireless Communications, etc. |
Chair | Eiji Okamoto(Nagoya Inst. of Tech.) |
Vice Chair | Fumihide Kojima(NICT) / Toshihiko Nishimura(Hokkaido Univ.) / Tomoya Tandai(Toshiba) |
Secretary | Fumihide Kojima(Panasonic) / Toshihiko Nishimura(NEC) / Tomoya Tandai |
Assistant | Koichi Adachi(Univ. of Electro-Comm.) / Osamu Nakamura(Sharp) / Manabu Sakai(Mitsubishi Electric) / Masashi Iwabuchi(NTT) / Tatsuki Okuyama(NTT DOCOMO) |
Paper Information | |
Registration To | Technical Committee on Radio Communication Systems |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | A Study on Deep Unfolding-Aided Belief Propagation for Error Correction Decoding of CRC Code |
Sub Title (in English) | |
Keyword(1) | CRC code |
Keyword(2) | belief propagation |
Keyword(3) | deep learning |
Keyword(4) | deep unfolding |
Keyword(5) | data-driven tuning |
1st Author's Name | Qilin Zhang |
1st Author's Affiliation | Doshisha University(Doshisha Univ.) |
2nd Author's Name | Shinsuke Ibi |
2nd Author's Affiliation | Doshisha University(Doshisha Univ.) |
3rd Author's Name | Takumi Takahashi |
3rd Author's Affiliation | Osaka University(Osaka Univ.) |
4th Author's Name | Hisato Iwai |
4th Author's Affiliation | Doshisha University(Doshisha Univ.) |
Date | 2021-06-24 |
Paper # | RCS2021-55 |
Volume (vol) | vol.121 |
Number (no) | RCS-72 |
Page | pp.pp.157-162(RCS), |
#Pages | 6 |
Date of Issue | 2021-06-16 (RCS) |