| Presentation | 2022-12-15 Efficient Beam Prediction for Intelligent Reflecting Surface-Assisted mmWave Systems based on Memory Driven Simple Transformer Deep Learning Model Taisei Urakami, Haohui Jia, Na Chen, Minoru Okada, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In this paper, we propose a memory driven simple transformer (MDST) deep learning (DL) model with the autoregressive module and spatial attention method, and channel matrix compression method to realize the high accuracy with small data collecting and low training overhead for intelligent reflecting surface (IRS)-assisted millimeter wave (mmWave) wireless communication system. Specifically, in the channel matrix compression, we convert the channel state information (CSI) into the sparse angular-delay domain, then the data size is significantly compressed in the delay domain. In the MDST-DL model, first, compressed CSI is input to the gated recurrent unit (GRU) to extract the frequency features. After that, these frequency features are input to the simple spatial attention to obtain the global features based on the frequency features extracted from each element. As the results show, in the case of compressed channel, the MDST-DL model can achieve the sufficient average accuracy of 80.0% with 17min 12s in comparison with the average accuracy of original channel of 85.7% with 22min 10s. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | mmWaveintelligent reflecting surfacebeam predictiondeep learning |
| Paper # | RCS2022-185 |
| Date of Issue | 2022-12-08 (RCS) |
| Conference Information | |
| Committee | RCS / NS |
|---|---|
| Conference Date | 2022/12/15(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Nagoya Institute of Technology, and Online |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Multi-hop/Relay/Cooperation, Disaster-resistant wireless network, Sensor/Mesh network, Ad-hoc network, D2D/M2M, Wireless network coding, Handover/AP switching/Connected cell control/Load balancing among base stations/Mobile network dynamic reconfiguration, QoS/QoE assurance, Wireless VoIP, IoT, Edge computing, etc. |
| Chair | Kenichi Higuchi(Tokyo Univ. of Science) / Tetsuya Oishi(NTT) |
| Vice Chair | Tomoya Tandai(Toshiba) / Fumihide Kojima(NICT) / Osamu Muta(Kyushu Univ.) / Takumi Miyoshi(Shibaura Insti of Tech.) |
| Secretary | Tomoya Tandai(Panasonic) / Fumihide Kojima(Univ. of Electro-Comm) / Osamu Muta(Sharp) / Takumi Miyoshi(NTT) |
| Assistant | Manabu Sakai(Mitsubishi Electric) / Masashi Iwabuchi(NTT) / Issei Kanno(KDDI Research) / Yuyuan Chang(Tokyo Inst. of Tech) / Kazuki Maruta(Tokyo Univ. of Science) / Kotaro Mihara(NTT) |
| Paper Information | |
| Registration To | Technical Committee on Radio Communication Systems / Technical Committee on Network Systems |
|---|---|
| Language | ENG |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Efficient Beam Prediction for Intelligent Reflecting Surface-Assisted mmWave Systems based on Memory Driven Simple Transformer Deep Learning Model |
| Sub Title (in English) | |
| Keyword(1) | mmWaveintelligent reflecting surfacebeam predictiondeep learning |
| 1st Author's Name | Taisei Urakami |
| 1st Author's Affiliation | Nara Institute of Science and Technology(NAIST) |
| 2nd Author's Name | Haohui Jia |
| 2nd Author's Affiliation | Nara Institute of Science and Technology(NAIST) |
| 3rd Author's Name | Na Chen |
| 3rd Author's Affiliation | Nara Institute of Science and Technology(NAIST) |
| 4th Author's Name | Minoru Okada |
| 4th Author's Affiliation | Nara Institute of Science and Technology(NAIST) |
| Date | 2022-12-15 |
| Paper # | RCS2022-185 |
| Volume (vol) | vol.122 |
| Number (no) | RCS-311 |
| Page | pp.pp.1-6(RCS), |
| #Pages | 6 |
| Date of Issue | 2022-12-08 (RCS) |