Basic Search / Detailed Display

Author: 楊承訓
Cheng-Hsun Yang
Thesis Title: 由社交網路的移動紀錄擷取社群網路資訊及其應用
Extraction of Social Communities from Real Mobility Traces and its Use as Input to a Mobile Social Network Trace Generator
Advisor: 陳秋華
Chyou-hwa Chen
Committee: 鄭欣明
none
金台齡
none
邱舉明
none
Degree: 碩士
Master
Department: 電資學院 - 資訊工程系
Department of Computer Science and Information Engineering
Thesis Publication Year: 2015
Graduation Academic Year: 103
Language: 中文
Pages: 37
Keywords (in Chinese): 人群關係分類模擬社群網路效能評估分群演算法時間性分析
Keywords (in other languages): Social Relationship, Simulations, Social Network, Effectiveness Evaluation, Communities Detection, Temporal Analysis
Reference times: Clicks: 368Downloads: 0
Share:
School Collection Retrieve National Library Collection Retrieve Error Report

如何判斷節點之間關係,人與人之間的互動。常見的方法是利用
三種特徵:累積的連線時間、連線的次數以及網路結構,來判斷兩節
點屬於何種關係。
但是這些特徵並不足以嚴格評斷兩節點之間的關係,例如:人類
的移動行為;兩人恰好某一天長時間待在同一處或網路拓樸結構恰好
重疊性高。單獨依靠某一兩個特徵並不能正確的判定兩人之關係;更
進一步說人類最重要的社群關係以及社群結構也完全無法正確的擷
取。
為了能找出正確的人群關係,並且能透過真實的社群關係資訊去
檢視其正確性,這是巨大挑戰,幸運的是研究領域上已經有許多完整
人類移動模型,以及相關人群關係分類方法。我們主要是改良已被提
出的人群關係分類方法,提出不同方法找出更近似於真實社群的,並
使得真實現象能完整重現。


How to identify the relationship between nodes and
interactions of two people are issues to be considered. It is
mainly using three characteristics including contact duration,
number of contact and network topological to identify social
relationship.
However, those evaluations are insufficient to determine
the social relationship of two nodes by strict. For instance,
the major moving method of people is through visiting the same
place with high frequency in a long time. By depending on the
three characteristics mentioned in the previous paragraph, we
cannot inspect the reality of the moving model. Furthermore,
the critical social relationship as well as social structure
cannot be reproduced correctly.

1. Introduction………………………………………………………………………1 2. Introduction Social Relationship and Temporal Communities and RECAST 2.1 Social Relationship 2.2 Temporal Communities 2.3 Stranger help friends to communicate 2.4 RECAST 3. Methodology and Datasets 3.1 Community Extraction Overview ………………………………………13 3.2 Community Extraction Flow Chart……………………………………13 3.3 Edge Classification – Frequency calculation ………………14 3.4 Edge Classification – Total duration …………………………15 3.5 Frequency and Total duration statistics ………………………16 3.6 Edge Classification – Classify ……………………………………17 3.7 Cluster Similarity ………………………………………………………18 3.8 Edge Clustering ……………………………………………………………19 3.9 Similarity measurement……………………………………………………19 3.10 Datasets describe………………………………………………………20 4. Performance Evaluation of Extracted Communities 4.1 Evaluation of overlap measurement……………………………………22 5. Extracted Communities as input to a Mobility Trace Generator Two Facets  Statistical characteristics Contact Time, Inter-Contact Time, Contact Duration, Number of Contacts.  Social characteristics Connected Components 5.1 Input to a Mobility Trace Generator………………………………27 5.2 Evaluation of Two Facets………………………………………………28 6. Conclusion and Future work 6.1 Conclusion…………………………………………………………………35 6.2 Future work………………………………………………………………35 7. Reference…………………………………………………………………………37

1. Anna Kaisa Pietiläinen, Christophe Diot: ”Dissemination in opportunistic
social networks: the role of temporal communities.” MobiHoc 2012:
165-174
2. Tracy Camp,Jeff Boleng,Vanessa Davies : “A Survey of Mobility Models
for Ad Hoc Network Research” 10 September 2002
3. Dmytro Karamshuk, Chiara Boldrini, Marco Conti, Andrea Passarella: ”An
arrival-based framework for human mobility modeling.” WOWMOM 2012:
1-9
4. Lecture Notes: Social Networks: Models, Algorithms, and Applications
Lecture 3: Jan 24, 2012 Scribes: Geoffrey Fairchild and Jason Fries
5. Pedro Olmo Vaz de Melo et al. “RECAST Telling Apart Social and
Random Relationships in Dynamic Networks”, ACM Int. Conf. Modeling,
Analysis and Simulation of Wireless and Mobile Systems (MSWiM'2013)
6. S. Gaito et al. “Strangers help friends to communicate in opportunistic
networks”, Computer Networks 55 (2011) 374–385
7. Endres and Schindelin, A new metric for probability distributions, IEEE
Trans. on Info. Thy., vol. 49, no. 3, Jul. 2003, pp. 1858-1860.
8. Pasquale De Meo, Emilio Ferrara, Giacomo Fiumara, Alessandro Provetti :
“Generalized Louvain method for community detection in large networks”,
arXiv:1108.1502 [cs.SI], Sat, 6 Aug 2011

無法下載圖示 Full text public date 2020/08/18 (Intranet public)
Full text public date This full text is not authorized to be published. (Internet public)
Full text public date 2025/08/18 (National library)
QR CODE