Presentation | 2023-01-19 [Short Paper] An Empirical Study of Data Reduction Method for Point Cloud-based Link Quality Prediction Shoki Ohta, Takayuki Nishio, Riichi Kudo, Kahoko Takahashi, Hisashi Nagata, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | This study experimentally evaluates a tradeoff between prediction accuracy and the number of points on a millimeter-wave (mmWave) link quality prediction method using point clouds and machine learning. In high-frequency radio communications such as mmWave communications, link quality is greatly attenuated when the line-of-sight (LOS) communication path is blocked by a human body or a vehicle. A method using point clouds, which represent a set of points in a three-dimensional space, and machine learning has been proposed as a technique for predicting LOS blockage. While point clouds can accurately capture the 3D space with fewer privacy concerns, they require a large amount of data and computation. In this study, we applied random downsampling, a primitive but effective method for reducing the number of points, to point clouds acquired by LiDAR to reduce the data volume of point clouds, and evaluated the relationship between the reduction ratio and prediction accuracy. Experimental evaluation in an indoor environment showed that even when the number of points in the point cloud is reduced to about 1%, a large attenuation in mmWave throughput induced by human blockage can be predicted. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | link quality prediction / millimeter-wave communication / point cloud / machine learning / data reduction |
Paper # | SeMI2022-93 |
Date of Issue | 2023-01-12 (SeMI) |
Conference Information | |
Committee | SeMI |
---|---|
Conference Date | 2023/1/19(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Naruto grand hotel |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | Koji Yamamoto(Kyoto Univ.) |
Vice Chair | Kazuya Monden(Hitachi) / Yasunori Owada(NICT) / Shunsuke Saruwatari(Osaka Univ.) |
Secretary | Kazuya Monden(NTT DOCOMO) / Yasunori Owada(Tokyo Univ. of Agri. and Tech.) / Shunsuke Saruwatari(Osaka Univ.) |
Assistant | Yuki Matsuda(NAIST) / Akihito Taya(Aoyama Gakuin Univ.) / Takeshi Hirai(Osaka Univ.) |
Paper Information | |
Registration To | Technical Committee on Sensor Network and Mobile Intelligence |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | [Short Paper] An Empirical Study of Data Reduction Method for Point Cloud-based Link Quality Prediction |
Sub Title (in English) | |
Keyword(1) | link quality prediction |
Keyword(2) | millimeter-wave communication |
Keyword(3) | point cloud |
Keyword(4) | machine learning |
Keyword(5) | data reduction |
1st Author's Name | Shoki Ohta |
1st Author's Affiliation | Tokyo Institute of Technology(Tokyo Tech) |
2nd Author's Name | Takayuki Nishio |
2nd Author's Affiliation | Tokyo Institute of Technology(Tokyo Tech) |
3rd Author's Name | Riichi Kudo |
3rd Author's Affiliation | NTT(NTT) |
4th Author's Name | Kahoko Takahashi |
4th Author's Affiliation | NTT(NTT) |
5th Author's Name | Hisashi Nagata |
5th Author's Affiliation | NTT(NTT) |
Date | 2023-01-19 |
Paper # | SeMI2022-93 |
Volume (vol) | vol.122 |
Number (no) | SeMI-341 |
Page | pp.pp.96-100(SeMI), |
#Pages | 5 |
Date of Issue | 2023-01-12 (SeMI) |