以聚合式階層分群演算法應用於超聲波FMCW雷達系統;Agglomerative Hierarchical Clustering on Ultrasonic FMCW Radar System

NCUIR > College of Electrical Engineering & Computer Science > Graduate Institute of Communication Engineering > Electronic Thesis & Dissertation > Item 987654321/89650

Please use this identifier to cite or link to this item: http://ir.lib.ncu.edu.tw/handle/987654321/89650

Title:	以聚合式階層分群演算法應用於超聲波FMCW雷達系統;Agglomerative Hierarchical Clustering on Ultrasonic FMCW Radar System
Authors:	邱照嚴;Chiu, Chao-Yen
Contributors:	通訊工程學系
Keywords:	調頻連續波;非監督式學習;分群演算法;階層式分群法;FMCW;unsupervised learning;clustering algorithm;hierarchical clustering
Date:	2022-07-15
Issue Date:	2022-10-04 11:50:56 (UTC+8)
Publisher:	國立中央大學
Abstract:	本論文將使用階層分群法（Hierarchical Clustering），來對由調頻連續波雷達（FMCW radar, Frequency Modulated Continuous Waveform radar）量測出的結果進行模擬及分析。首先會先介紹FMCW雷達系統在測量距離上之應用，再來使用階層式分群法來對收集到的資料進行分群（cluster），以提升FMCW雷達系統分辨物體準確度。調頻連續波雷達，是指發射頻率受特定信號調製的連續波雷達，在掃頻週期內發送頻率變化的連續波，被物體反射之後的回波與發射信號有一定的頻率差，通過測量頻率差可以獲得目標與雷達之間的距離階層式分群法是透過一種階層架構的方式，將資料反覆進行分裂或聚合以產生樹狀圖（dendrogram），常見的方法有聚合式（agglomerative）和分裂式（divisible）兩種，由於不同情景、距離皆會使蒐集到的資料性不同，本文採用前者中的單一鏈結（Single Linkage）算法、完整鏈結（Complete Linkage）算法、平均鏈結（Average Linkage）算法及沃德法（Ward’s Method），並且比較各種算法適用於各種場景之資料分群效果。 ;This paper will use Hierarchical Clustering to simulate and analyze the results measured by Frequency Modulated Continuous Waveform radar. First, the application of the FMCW radar system in measuring distance will be introduced, and then the collected data will be clustered using the hierarchical clustering method to improve the accuracy of the FMCW radar system in measuring objects. FMCW radar refers to a continuous wave radar whose emission frequency is modulated by a specific signal. It transmits a continuous wave whose frequency changes during the frequency sweep period. The echo reflected by the object has a certain frequency difference with the transmitted signal. By measuring the frequency difference, the distance between the target and the radar can be obtained. The Hierarchical Clustering method agglomerates and divides data repeatedly to generate a dendrogram, called agglomerative clustering and divisible clustering. Afterward, according to different situations and distances, the collected data will be different, we compared the Single Linkage , Complete Linkage, Average Linkage and Ward′s Method are applicable to the clustering results of various scenarios.
Appears in Collections:	[Graduate Institute of Communication Engineering] Electronic Thesis & Dissertation

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	90	View/Open

社群 sharing

Loading...