Online Data Stream Mining on Interactive Trajectories in Soccer Games
Online Data Stream Mining on Interactive Trajectories in Soccer Games
复制标题
足球比赛中交互轨迹的在线数据流挖掘
DOI：
--
复制
发表时间：
2010
期刊：
影响因子：
--
通讯作者：
Thorsten Edelhäußer
中科院分区：
文献类型：
--
作者：
Christopher Mutschler;G. Kókai;Thorsten Edelhäußer
在体育运动中，特别是足球和其他球类运动中，运动员轨迹之间的相互作用在比赛分析中起着重要作用。现有的方法遵循时空、序列或空间模式的挖掘方式，但没有考虑多个交互轨迹之间的交互。本文提出了一种在线数据挖掘方法，能够识别轨迹运动的重复模式，而不管它们是如何缩放，旋转艾德或翻译。其结果是一个高效的数据流挖掘应用程序，它提供了当前游戏中有意义的信息。该框架是以模块化的方式设计的，以方便增强功能。对算法的评价证明了所提概念的有效性。
In sports, especially soccer and other ball-sports, the interaction between trajectories of players take a major role in purposes of game analysis. Existing approaches follow th e way of mining spatio-temporal, sequential patterns or spat ial patterns, but do not incorporate interactions between mult iple, interactive trajectories. This paper proposes an online da ta mining method that is able to recognize repeating patterns o f trajectory movements regardless of how they are scaled, rot a ed or translated. The result is an efficient data stream mining application, which provides meaningful information within the current game. The framework is designed in a modular manner in order to enhance the capabilities easily. The evaluationof the algorithms proves the efficiency of the provided concepts.