| Presentation | 2021-06-25 Experimental Evaluation of Frequency-domain Feature Selection for CSI-based Object Detection in Wireless LAN Systems Kazuki Noguchi, Osamu Muta, Tomoki Murakami, Shinya Otsuki, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Various object detection schemes utilizing channel state information (CSI) in wireless local area network(WLAN) systems have been investigated recently. To obtain further detection performance improvement, adoptinga proper feature selection technique is important. The authors have proposed interleaved subcarrier selectionmethods for an object detection system utilizing CSI in WLAN systems, where two subcarrier selection methods, Interleaved sampling(IS) and Interleaved clustering and sampling(ICS), are investigated. The IS method selectssome subcarriers in an interleaved manner and reduces the data size while maintaining the object detection accuracy. In the ISC method, all subcarriers are divided into multiple clusters in an interleaved manner, and the resultsof machine learning decisions for each cluster are integrated for object detection. In this article, we demonstratethe effectiveness of the proposed approach through real-time experimental evaluations in an indoor environmentscenario. Experimental results show that the ISC method improves the object detection accuracy compared to thecase without cluster division. We also show the IS method achieve the same detection accuracy while reducing thedata size. Furthermore, we show the detection accuracy is improved by distributing the antennas. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Object detection / channel state information / subcarrier selection / wireless LAN |
| Paper # | RCS2021-64 |
| 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) | Experimental Evaluation of Frequency-domain Feature Selection for CSI-based Object Detection in Wireless LAN Systems |
| Sub Title (in English) | |
| Keyword(1) | Object detection |
| Keyword(2) | channel state information |
| Keyword(3) | subcarrier selection |
| Keyword(4) | wireless LAN |
| 1st Author's Name | Kazuki Noguchi |
| 1st Author's Affiliation | Kyushu University(Kyushu Univ.) |
| 2nd Author's Name | Osamu Muta |
| 2nd Author's Affiliation | Kyushu University(Kyushu Univ.) |
| 3rd Author's Name | Tomoki Murakami |
| 3rd Author's Affiliation | NTT Corporation(former NTT) |
| 4th Author's Name | Shinya Otsuki |
| 4th Author's Affiliation | NTT Corporation(former NTT) |
| Date | 2021-06-25 |
| Paper # | RCS2021-64 |
| Volume (vol) | vol.121 |
| Number (no) | RCS-72 |
| Page | pp.pp.202-207(RCS), |
| #Pages | 6 |
| Date of Issue | 2021-06-16 (RCS) |