English  |  正體中文  |  简体中文  |  Items with full text/Total items : 888/888 (100%)
Visitors : 10671908      Online Users : 790
RC Version 7.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
Scope Tips:
  • please add "double quotation mark" for query phrases to get precise results
  • please goto advance search for comprehansive author search
  • Adv. Search
    HomeLoginUploadHelpAboutAdminister Goto mobile version
    Please use this identifier to cite or link to this item: http://ccur.lib.ccu.edu.tw/handle/A095B0000Q/528


    Title: 基於數學規劃法檢測相互重疊之社群結構問題上;Modularity Optimization via Mathematical Programming for Overlapping Community Detection
    Authors: 林展慶;Lin, Jan-Ching
    Contributors: 資訊工程研究所
    Keywords: 模塊化;重疊社群;資料探勘;檢測社群;Modularity;Overlapping Communities;Data Mining;Community Detection
    Date: 2016
    Issue Date: 2019-07-17
    Publisher: 資訊工程研究所
    Abstract: 利用線性規劃求解模塊最大化問題時,由於得出的解答無法有效判定重疊社群結構,故我們透過放寬線性規劃的條件改變為二次規劃式,增加重疊節點在模塊化上的權重,藉此在最大化求解時可以經由得出的解答有效而準確地推估一個重疊社群結構。當節點數量過多時,二次規劃式求解所需時間甚長,針對大型社群網路架構,提出一個植基於我們的二次規劃式的整合切割計算流程,我們的構想主要是計算社群成員間相互變動的模塊化增益,透過模塊化增益的結果將社群網路切割成許多子圖,再將子圖通過二次規劃式檢測出疑似的重疊節點,最後使用疑似是重疊節點的外部度過濾掉子圖在通過二次規劃式時所產生過度分割的重疊節點。在人工合成的社群網路中,我們檢測重疊節點的方法結果與真實結果的比較,平均準確度高達五成,此外,在實際社群網路中,我們使用多種擴展模塊化評估分群結果的方法與其他檢測重疊社群結構的算法比較,主要對象有( 1 )基於團塊( Clique )在圖形上找尋團塊社群並分析團塊社群之間關係的方法;( 2 )基於模糊模塊化( Fuzzy modularity )使用基因演算法( Genetic Algorithm )檢測重疊節點的方法,在結果上我們所提出的方法都優此兩種檢測重疊社群結構的算法。
    Since the weight distribution of the modularization maximization in Linear Programming can not get the structure of overlapping community, we define this problem as the Weight Allocation of Community Structure problem. By relaxing the conditions of the Linear Programming, the modularity of the overlapping community is increased and the structure of the overlapping community can be obtained when the modularization is maximized.Quadratic Programming in a large network to detect overlapping community structure takes a long time. To overcome this problem, we propose an algorithm. This algorithm means that the social network is cut into many subgraphs. Then the sub-graph is used to detect overlapping nodes by Quadratic Programming. Finally, Quadratic Programming will produce over-partition, thus using the filter overlapping nodes outside degrees.In experiments, our method is applied on both synthetic and real networks. The results show that our method can detect the heavily overlapping nodes.
    Appears in Collections:[資訊工程學系] 學位論文

    Files in This Item:

    File Description SizeFormat
    index.html0KbHTML200View/Open


    All items in CCUR are protected by copyright, with all rights reserved.


    版權聲明 © 國立中正大學圖書館網頁內容著作權屬國立中正大學圖書館

    隱私權及資訊安全政策

    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - Feedback