Presentation 2022-01-21
A Study on Bayesian Receiver Design via Deep Unfolding-Aided Bilinear Inference for Correlated Large MIMO
Ryota Tamaki, Kenta Ito, Takumi Takahashi, Shinsuke Ibi, Seiichi Sampei,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper proposes a joint channel and data estimation (JCDE) scheme via deep unfolding (DU)-aided bilinear generalized approximate message passing (BiGAMP) for large multi-user multi-input multi-output (MU-MIMO) systems. BiGAMP is one of the promising JCDE schemes to achieve highly accurate multi-user detection (MUD) with low computational cost, which separates high dimensional signals based on matched filters (MFs). However, it is designed based on the large systems assuming independent and identically distributed (i.i.d.) observations with mean zero; therefore, the estimation capability is severely degraded in the presence of spatial fading correlation. To tackle this issue, we design a novel trainable BiGAMP (T-BiGAMP) that incorporates trainable internal parameters into the iterative process of the JCDE based on BiGAMP. By optimizing the parameters via textit{data-driven} tuning techniques, the JCDE algorithm based on T-BiGAMP achieves high estimation performance even in practical MIMO configurations that differ from the ideal operating conditions. Computer simulations demonstrate the validity of our proposed method in terms of bit error rate (BER) performance.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Correlated large MIMO detection / deep unfolding / BiGAMP / data-drive tuning
Paper # IT2021-65,SIP2021-73,RCS2021-233
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 JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A Study on Bayesian Receiver Design via Deep Unfolding-Aided Bilinear Inference for Correlated Large MIMO
Sub Title (in English)
Keyword(1) Correlated large MIMO detection
Keyword(2) deep unfolding
Keyword(3) BiGAMP
Keyword(4) data-drive tuning
1st Author's Name Ryota Tamaki
1st Author's Affiliation Osaka University(Osaka Univ.)
2nd Author's Name Kenta Ito
2nd Author's Affiliation Osaka University(Osaka Univ.)
3rd Author's Name Takumi Takahashi
3rd Author's Affiliation Osaka University(Osaka Univ.)
4th Author's Name Shinsuke Ibi
4th Author's Affiliation Doshisha University(Doshisha Univ.)
5th Author's Name Seiichi Sampei
5th Author's Affiliation Osaka University(Osaka Univ.)
Date 2022-01-21
Paper # IT2021-65,SIP2021-73,RCS2021-233
Volume (vol) vol.121
Number (no) IT-327,SIP-328,RCS-329
Page pp.pp.207-212(IT), pp.207-212(SIP), pp.207-212(RCS),
#Pages 6
Date of Issue 2022-01-13 (IT, SIP, RCS)