English  |  正體中文  |  简体中文  |  Items with full text/Total items : 90453/105672 (86%)
Visitors : 14946007      Online Users : 281
RC Version 6.0 © 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
    ASIA unversity > 資訊學院 > 資訊工程學系 > 期刊論文 >  Item 310904400/111754

    Please use this identifier to cite or link to this item: http://asiair.asia.edu.tw/ir/handle/310904400/111754

    Title: Visual Exploration Using Improved Moving Average Methods for Time Series Datasets
    Authors: 莊政宏;Chuang, Cheng-Hung;呂威甫;Lu, Wei-Fu;陳瑞奇;Chen, Jui-Chi;*
    Contributors: 資訊工程學系
    Date: 2018-07
    Issue Date: 2018-12-25 16:12:09 (UTC+8)
    Abstract: Recently, Taiwan government has voluntarily opened up various data sets to provide the public for analysis and application in order to find potential problems and help solve some public issues. A common way of using the data sets to initially explore potential issues is to visualize the miscellaneous data and present useful information represented by readily available statistical charts. In this process, the most often encountered problem is the fluctuations of the data changes in the time series of the statistical chart, so it is not easy to visually compare the trends of the source data among different factors. Therefore, we use the concept of moving average to smooth short-term fluctuations. The moving average can clearly show the difference or impact of the data on different factors. However, when using some of the traditional moving average methods to draw charts, we found that the moving averages lag behind the values of the source data, making the data visual delay in comparison. To solve this problem, this study proposes two improved moving average methods, which are compared with the traditional moving average methods in terms of smoothness and lag results to see if we can find a better one, which can more accurately analyze time series datasets to determine the trends of the past problems and the possible future trends, and then lead the follow-up study.
    Relation: International Journal of Electronics and Information Engineering
    Appears in Collections:[資訊工程學系] 期刊論文

    Files in This Item:

    File SizeFormat

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

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