查詢結果分析
來源資料
頁籤選單縮合
題 名 | 模糊時間數列之探討--以臺灣景氣對策信號為例=The Study of Fuzzy Time Series in Taiwan Monitor Index |
---|---|
作 者 | 廖敏治; | 書刊名 | 正修學報 |
卷 期 | 13 2000.12[民89.12] |
頁 次 | 頁191-208 |
分類號 | 550.19 |
關鍵詞 | 模糊時間數列; 階次認定; 模糊自相似度; 隸屬度函數; 模糊趨勢; Fuzzy time series; Order identification; Fuzzy auto-similarity; Membership function; Fuzzy trend; |
語 文 | 中文(Chinese) |
中文摘要 | 本文乃將模糊時間數列的觀念,應用到時間數列分析上。研究重點包括模糊自相似度的定義與度量,模糊時間數列自迴歸模型探討、模糊自相似度對自迴歸階次認定、及模糊時間數列模式建構與預測等。首先,吾人給定模糊時間數列模式的概念與重要性質。接著,提出模糊自相似度的定義與度量,以及模式建構的流程。並且使用模糊關係方程找出合適的模糊時間數列模式。然後,利用本文提出的模式建構方法對臺灣景氣對策信號建立模糊時間數列模式。最後,使用所建構的模糊時間數列模式對未來進行預測,以驗證所建構的模糊時間數列模式的效率性與實用性。 |
英文摘要 | This paper is to apply the concept of fuzzy theory to time series analysis. The study contains the definitions and measures of fuzzy auto-similarity (FAS), the type of fuzzy auto-regression (FAR) time series, the order identification of fuzzy time series, and fuzzy time series constructing and forecasting techniques. First, I'll provide the concept of fuzzy time series and important properties. Second, I'll propose the definitions and measures of fuzzy auto-similarity. Third, I'll show the models of fuzzy time series to be applied for this purpose. In this section, order detection process for fuzzy time series is presented. Last, I'll use the model construction process to construct the model and forecast the future for Taiwan Monitor Index, and to prove the efficiency and practicality of this method. |
本系統中英文摘要資訊取自各篇刊載內容。