期刊論文
| 學年 | 113 |
|---|---|
| 學期 | 2 |
| 出版（發表）日期 | 2025-05-01 |
| 作品名稱 | Indoor Localization Using 6G Time-Domain Feature and Deep Learning |
| 作品名稱（其他語言） | |
| 著者 | Chien-Ching Chiu；Hung-Yu Wu；Po-Hsiang Chen；Chen-En Chao；Eng Hock Lim |
| 單位 | |
| 出版者 | |
| 著錄名稱、卷期、頁數 | Electronics 14(9), p. 1870 |
| 摘要 | Accurate indoor localization is essential for Internet of Things (IoT) systems and autonomous navigation in the 6G communication system. However, achieving precision in environments affected by signal multipath effects and interference remains a challenge for 6G communication systems. We employ a Residual Neural Network (ResNet) augmented with channel and spatial attention mechanisms to enhance indoor localization performance using time-domain data. Through extensive experimentation, our models, when equipped with an attention mechanism, can achieve accurate location under 20% interference. Numerical results show that the ResNet with a Channel Local Attention Block (CLAB) can reduce the localization error by about 12% even when the interference is high. Similarly, the ResNet with a Spatial Local Attention Block (SLAB) can also improve the localization accuracy. While a ResNet combining both CLAB and SLAB can reduce the position error to about 7 cm. |
| 關鍵字 | residual neural network; 6G communication system; channel local attention block; spatial local attention block; indoor localization |
| 語言 | en_US |
| ISSN | |
| 期刊性質 | 國外 |
| 收錄於 | SCI |
| 產學合作 | |
| 通訊作者 | |
| 審稿制度 | 是 |
| 國別 | USA |
| 公開徵稿 | |
| 出版型式 | ,電子版 |
| 相關連結 |
機構典藏連結 ( http://tkuir.lib.tku.edu.tw:8080/dspace/handle/987654321/127755 ) |