利用迴歸分析於探勘使用者移動模式

Abstract

本研究計畫的目的在於利用通聯紀錄(call detail records)，以期能夠在不增加行動通訊系統額外之儲存空間，探勘使用者的移動行為模式。在此計畫中，我們提出一系列之演算法，用以探勘使用者移動行為模式。首先，通聯記錄需轉換為移動序列。我們提出演算法LS用以精確地決定相類似的移動序列。利用空間-時間區域性(亦即在相近的時間內使用者的位置不會相距太遠)的特性，演算法TC將時間上相臨近的通聯記錄予以分群，使得同一群之通聯記錄具有空間-時間區域之特性。利用迴歸分析的概念，我們研發演算法MF用以推導出使用者移動行為模式函數。為了驗證所提出探勘機制正確性，我們建構行動計算系統模擬環境，對此一機制進行效能分析。模擬實驗結果顯示所提出的機制能有效的探勘使用者的移動行為模式且利用現有之通聯紀錄便可逼近使用者真實的移動行為模式。

In this thesis, by exploiting the log of call detail records, we present a solution procedure of mining user moving patterns in a mobile computing system. Specifically, we propose algorithm LS to accurately determine similar moving sequences from the log of call detail records so as to obtain moving behavior of users. By exploring the feature of spatial-temporal locality, which refers to the feature that if the time interval among consecutive calls of a mobile user is small, the mobile user is likely to move nearby, we develop algorithm TC to cluster those call detail records whose time intevals are very close. In light of the concept of regression, we devise algorithm MF to derive moving functions of moving behavior. Performance of the proposed solution procedure is analyzed and sensitivity analysis on several design parameters is conducted. It is shown by our simulation results that user moving patterns obtained by our solution procedure are of very high quality and in fact very close to real user moving behavior.