中大機構典藏-NCU Institutional Repository-提供博碩士論文、考古題、期刊論文、研究計畫等下載:Item 987654321/89650
English  |  正體中文  |  简体中文  |  全文笔数/总笔数 : 80990/80990 (100%)
造访人次 : 43434966      在线人数 : 1244
RC Version 7.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
搜寻范围 查询小技巧:
  • 您可在西文检索词汇前后加上"双引号",以获取较精准的检索结果
  • 若欲以作者姓名搜寻,建议至进阶搜寻限定作者字段,可获得较完整数据
  • 进阶搜寻


    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/987654321/89650


    题名: 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
    作者: 邱照嚴;Chiu, Chao-Yen
    贡献者: 通訊工程學系
    关键词: 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
    日期: 2022-07-15
    上传时间: 2022-10-04 11:50:56 (UTC+8)
    出版者: 國立中央大學
    摘要: 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.
    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.html0KbHTML73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

    ::: Copyright National Central University. | 國立中央大學圖書館版權所有 | 收藏本站 | 設為首頁 | 最佳瀏覽畫面: 1024*768 | 建站日期:8-24-2009 :::
    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - 隱私權政策聲明