| Presentation | 2023-05-12 [Invited Talk] Federated Learning-Inspired Gaussian Process Regression: Low Latency Design and Its Application to Radio Map Construction Koya Sato, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Gaussian process regression (GPR) is a non-parametric method that optimizes regression analysis for Gaussian process data. There has been a wide range of applications, such as environmental monitoring and robotics. However, GPR has drawbacks regarding computational complexity and communication cost for collecting sensing data; it will be significant in the massive-dataset analysis. This presentation gives recent progress in distributed GPR over wireless networks toward low latency and accurate regression analysis. It is also shown that the distributed GPR can be applied for radio map construction tasks, an application of GPR in wireless communications. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Gaussian process regression / distributed machine learning / over-the-air computation / radio map |
| Paper # | SR2023-20 |
| Date of Issue | 2023-05-04 (SR) |
| Conference Information | |
| Committee | SR |
|---|---|
| Conference Date | 2023/5/11(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Center of lifelong learning Kiran (Higashi Muroran) |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Software Defined Radio, Cognitive Radio, Spectrum Sharing, Machine Learning, etc. |
| Chair | Suguru Kameda(Hiroshima Univ.) |
| Vice Chair | Osamu Takyu(Shinshu Univ.) / Kentaro Ishidu(NICT) / Kazuto Yano(ATR) |
| Secretary | Osamu Takyu(Mie Univ.) / Kentaro Ishidu(Tokai Univ.) / Kazuto Yano(NTT) |
| Assistant | Taichi Ohtsuji(NEC) / WANG Xiaoyan(Ibaraki Univ.) / Akemi Tanaka(MathWorks) / Katsuya Suto(Univ. of Electro-Comm) |
| 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) | [Invited Talk] Federated Learning-Inspired Gaussian Process Regression: Low Latency Design and Its Application to Radio Map Construction |
| Sub Title (in English) | |
| Keyword(1) | Gaussian process regression |
| Keyword(2) | distributed machine learning |
| Keyword(3) | over-the-air computation |
| Keyword(4) | radio map |
| 1st Author's Name | Koya Sato |
| 1st Author's Affiliation | The University of Electro-Communications(UEC) |
| Date | 2023-05-12 |
| Paper # | SR2023-20 |
| Volume (vol) | vol.123 |
| Number (no) | SR-19 |
| Page | pp.pp.91-91(SR), |
| #Pages | 1 |
| Date of Issue | 2023-05-04 (SR) |