Broad Learning System for Indoor CSI Fingerprint Localization

被引：2

作者：

Yu, Chieh ^{[1
]}

Sheu, Jang-Ping ^{[2
]}

Kuo, Yung-Ching ^{[2
]}

机构：

[1] Natl Tsing Hua Univ, Intelligent Prod & Intelligent Mfg Master Program, Hsinchu, Taiwan

[2] Natl Tsing Hua Univ, Dept Comp Sci, Hsinchu, Taiwan

来源：

2023 IEEE WIRELESS COMMUNICATIONS AND NETWORKING CONFERENCE, WCNC | 2023年

关键词：

Channel State Information; Fingerprint; Indoor Localization; Broad Learning System;

D O I：

10.1109/WCNC55385.2023.10119111

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

With the development of the Internet of Things (IoT), the demand for location-based services in indoor environments proliferates. Channel State Information (CSI) based fingerprint localization has become a research hot spot. However, a compelling method to address this issue does not appear because of the hardship of processing CSI data. Meanwhile, many fingerprint localization algorithms have a time-consuming offline training phase. Therefore, we propose an indoor CSI fingerprint localization system based on the broad learning system (BLS). First, we filter the outliers, generate delegates of CSI by the data nugget algorithm, and use tensor decomposition to reconstruct the CSI delegates. Moreover, we utilize Isometric mapping (Isomap) to extract CSI features to reduce BLS's complexity. The experimental results show that our scheme outperforms several existing algorithms in two indoor environments.

引用

页数：6