文化大學機構典藏 CCUR:Item 987654321/39407
English  |  正體中文  |  简体中文  |  Items with full text/Total items : 46962/50828 (92%)
Visitors : 12451370      Online Users : 606
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


    Please use this identifier to cite or link to this item: https://irlib.pccu.edu.tw/handle/987654321/39407


    Title: 運用時空資料分析探索美國大聯盟職業棒球數據資料
    Space-Time Analysis of Mlb Baseball Data
    Authors: 陳致元
    Contributors: 地理系
    Keywords: 美國職棒大聯盟
    職業棒球
    時空分析
    資料探索
    棒球
    機器學習
    Major League Baseball
    space-time analysis
    data mining
    machine learning
    Date: 2018-01
    Issue Date: 2018-03-02 10:57:24 (UTC+8)
    Abstract: 棒球成為職業運動已有一百多年的歷史,在七〇年代興起的「賽伯計量學」帶起了整個棒球界的計量革命,發展出棒球進階數據的觀念。然而目前棒球相關進階數據分析的研究,卻鮮少以時空分析的角度切入。例如: 如何定義棒球場上的時間與空間? 時空間因子如何影響球員的表現? 不同球員或是球隊在不同的比賽時空情境下,是否有不同的時空間決策? 本研究將以美國職棒大聯盟先進媒體公司(MLB Adavancd Media) 所提供之PITCHf/x 投球歷史資料庫,以及相關網站所提供之比賽公開資料為研究題材,利用時空分析方法進行資料探索及分析,來定義以及回應以上問題。本研究主要的研究焦點如下: 一、棒球場上的時空間範疇定義; 二、在這些時間與空間的範疇下,棒球場上的教練以及球員所採用的時間與空間決策行為。本計畫期望透過兩年期的資料收集與分析,架構出棒球數據資料的時空探索架構。而在方法上,本研究將探索:一、不同時空分析方法,應用在棒球數據分析的可能性; 二、棒球時空間進階數據的應用; 三、針對棒球場上會發生的不同情境,以選手及教練的角度來進行時空探索分析及整理,並將結果以時空視覺化的方法呈現。
    Sabermetrics has changed the history of baseball. It has changed not only the ways how people learn the statistics of players, but also the game plans that teams use to win the games. With the advent of new technologies now we have an enormous amount of play-by-play baseball data with accurate spatial and temporal information, which people can never image before. Those data have both spatial and temporal components in terms of batting, pitching, fielding, and strategies planning. Hidden behind the data, there are plenty of baseball knowledge and strategic thinking which can lead teams to win the ball games. However, the space-time analysis of baseball data remains a challenging task due to the lack of the paradigms to analyze baseball data from multiple dimensions including space, time, and others. For example, how to define the major categories of space and time in baseball? How to apply space-time analysis methods to discovery the hidden patterns in baseball data? How the players and coaches changed their space-time decisions or strategies under different situations of offense and defense? To fill those gaps in both theoretical and practical aspects, this research project plans to conduct a two-year study for the baseball data collection and space-time analysis. The pitch-by-pitch Data from the Major League Baseball Advanced Media PITCHf/x database and other open-sourced data with space and time information will be the major targets to be collected in this project. Accordingly, we introduce a framework applies space-time analysis to explore the spatiotemporal patterns of baseball data. First, we define the space and time units in baseball based on pre-knowledge of baseball rules and strategies, the situations of offense and defense, and other none spatiotemporal attributes related to players and games. Then, different approaches of space-time analysis methods are applied to discovery the hidden patterns
    Appears in Collections:[Department of Geography & Graduate Institute of Earth Science / Geography ] project

    Files in This Item:

    File Description SizeFormat
    index.html0KbHTML497View/Open


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


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