GAMES Webinar 2021 – 170期(可视化专题) | Gennady and Natalia Andrienko (Fraunhofer IAIS & City, University of London)
【GAMES Webinar 2021-170期】(可视化专题)
报告嘉宾：Gennady and Natalia Andrienko (Fraunhofer IAIS & City, University of London)
报告题目：A theory of data patterns and visual analytics of football
A fundamental goal of data analysis is to derive general, high-level knowledge from elementary data items, for example, derive understanding of the tactics of football teams from trajectories of the players and the ball. We consider knowledge to be a mental model of a piece of real world, which is the subject of analysis. A model represents overall relationships between different aspects or components of the analysis subject, such as space, time, groups of moving entities, and sets of actions and events. Data items describe elementary connections between individual elements of the subject components: spatial positions, time moments, entities, and so on. To derive understanding of overall relationships from elementary connections, we need to apply abstraction, in which multiple connections are considered together as a unified whole. The unification can be done with the help of relationships existing between elements within subject components, such as relationships of distance and direction between spatial locations and relationships of ordering and distance between time moments. We introduce a working definition of a data pattern as a combination of relationships between connected elements of two or more data components that can be considered and represented holistically as a single object, as, for example, a cluster, a trend, or a correlation. We discuss the roles of different types of relationships in forming data patterns. We illustrate the theoretical concepts using examples of football data. In the second part of our talk, we describe the process of designing an analytical workflow for finding tactical patterns in behaviours of teams in a football game.
Gennady and Natalia Andrienko are lead scientists at Fraunhofer Institute IAIS and professors at City, University of London. They published two monographs: “Exploratory analysis of spatial and temporal data. A systematic approach” (Springer, 2005) and “Visual analytics of movement” (Springer, 2013) and a textbook entitled “Visual analytics for data scientists” (Springer, 2020). They co-authored numerous papers addressing theoretical aspects and practical applications of visual analytics approaches. Natalia and Gennady Andrienko received test of time award at IEEE VAST 2018, best paper awards at AGILE 2006, IEEE VAST 2011 and 2012, and EuroVis 2015 conferences and EuroVA 2018 and 2019 workshops, honorable mention awards at IEEE VAST 2010 and EuroVis 2017 conferences, VAST challenge awards 2008 and 2014, and best poster awards at AGILE 2007 and 2018, ACM GIS 2011 and IEEE VAST 2016 conferences.
李杰，天津大学智能与计算学部副教授，研究兴趣为大数据交互探索，人监督机器学习、智能可视分析。在IEEEVIS、TVCG等期刊和会议发表论文30余篇。曾获4次学术奖，包含IEEEVIS 2019 最佳海报奖、EuroVA 2018最佳论文奖等。担任VINCI 2016-2017大会宣传主席和程序委员会主席，ChinaVIS 2019-2020 Fastforward主席，PacificVIS2020宣传主席、JVLC客座编辑等。担任IEEEVIS、EuroVIS、PacificVIS, TVCG、软件学报、CAD学报等多个期刊和会议审稿人。入选北洋青年骨干教师。
GAMES主页的“使用教程”中有 “如何观看GAMES Webinar直播？”及“如何加入GAMES微信群？”的信息；