基於CSI 指紋庫之機器學習演算法做 帶缺陷訓練資料之室內定位;CSI-Based Fingerprints for Machine Learning Method with Indoor Localization of Incomplete Training Data

NCU Institutional Repository > 資訊電機學院 > 通訊工程研究所 > 博碩士論文 > Item 987654321/86462

jsp.display-item.identifier=請使用永久網址來引用或連結此文件: http://ir.lib.ncu.edu.tw/handle/987654321/86462

题名:	基於CSI 指紋庫之機器學習演算法做帶缺陷訓練資料之室內定位;CSI-Based Fingerprints for Machine Learning Method with Indoor Localization of Incomplete Training Data
作者:	許哲齊;Hsu, Che-Chi
贡献者:	通訊工程學系
关键词:	通道狀態資訊;K-近鄰演算法;XGBoost;多層感知器;Channel State Information;K-Nearest Neighbors;Extreme Gradient Boosting;Multi-Layer Perception
日期:	2021-10-21
上传时间:	2021-12-07 12:51:54 (UTC+8)
出版者:	國立中央大學
摘要:	室內定位(Indoor Localization) 是早於十餘年前就提出的技術，相較於全球定位系統(Global Positioning System, GPS) 的戶外定位系統(Location-Based Service, LBS)，由於衛星訊號無法穿透建材，故無法使用衛星進行定位。但室內定位的應用仍相當廣泛，且具有一定的商業價值，如醫療看護、倉儲、機場、百貨公司等，加上近年來科技技術的提升，使得室內定位搖身一變成為一個熱門的話題。本篇論文採用Wi-Fi 做為室內定位技術，以通道狀態資訊(Channel State Information, CSI) 作為定位方針，先敘述環境參數與設備，並說明各式演算法，從而討論利用各種演算法來進行基本室內定位的準確度，再延伸討論至若有些位置無法採集或不方便採集到通道資訊時，能以什麼樣的方式來進行克服，進而在資訊存有缺陷的情況下實現室內定位。;Indoor Localization has been being an attracting technology studied over ten years along with the Location-Based Service of Global Positioning System (GPS). Because satellite signals cannot enter building, it is impossible to use satellite signals for indoor localization. However, the application of indoor localization is still quite extensive, and it has some commercial values certainly, such as medical care, warehousing, airports, departments, etc. In recent years, due to the advancement of the computing technology, the issue of indoor localization become an attractive topic. This thesis adopts Wi-Fi as the technique of Indoor Localization and channel state information (CSI) as the localization fingerprint. First, we describe the problem formulation and the involved equipment. Second, we introduce some machine learning algorithms that are compared in this paper. Then we discuss the accuracy of indoor localization with different machine learning algorithms. In this paper, considering there is some missed information which cannot be collected or is inconvenient to be collected for machine training, we propose a method that can be used to deal with this kind of situation to achieve effective indoor localization.
显示于类别:	[通訊工程研究所] 博碩士論文

文件中的档案:

档案	描述	大小	格式	浏览次数
index.html		0Kb	HTML	129	检视/开启

在NCUIR中所有的数据项都受到原著作权保护.

社群 sharing

数据加载中.....