Data Abstraction

Data Abstraction
复制标题

数据抽象

DOI:
10.1007/978-3-642-97479-3_3
复制
发表时间:
2021
期刊:
Game Data Science
影响因子:
--
通讯作者:
Anders Drachen
Anders Drachen
中科院分区:
--
文献类型:
--
作者:
M. S. El;Truong Huy Nguyen Dinh;Alessandro Canossa;Anders Drachen

文献摘要

被引文献

相似文献

本章介绍用于将数据从低级别数据抽象为可用于可视化和开发模型以通知不同利益相关者的功能的技术。这些技术包括:(a)知识工程,利用专家知识制定公式,从低级数据中计算各种衡量标准;(B)特征选择,从低级数据变量清单中选择特定的重要变量,因为这些变量可能被认为比其他变量更重要;(c)特征提取,通过结合低级数据中的各种衡量标准,以统计方式计算特征。本章还包括实验室,在那里,使用真实的游戏数据,你可以应用所讨论的技术。
This chapter introduces the techniques used to abstract the data from low-level data to features that can be used to visualize and develop models to inform the different stakeholders. These techniques range from (a) knowledge engineering, where expert knowledge is used to develop formulae to compute various measures from low-level data; (b) feature selection, where specific important variables are selected from the list of low-level data variables as they may be deemed more important than other; and (c) feature extraction, where features are computed statistically through combining various measures from low-level data. The chapter also includes labs where, using real game data, you get to apply the discussed techniques.