Model-based Behavioral Causality Analysis of Handball with Delayed Transfer Entropy

Kota Itoda, Norifumi Watanabe, Yoshiyasu Takefuji

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

In goal-type ball games, such as handball, basketball, hockey or soccer, teammates and opponents share the same field. They switch dynamically their behaviors and relationships based on other players' behaviors or intentions. Interactions between players are highly complicated and hard to comprehend, but recent technological developments have enabled us to acquire positions or velocities of their behaviors. We focus on handball as an example of goal-type ball games and analyze causality between teammates' behaviors from tracking data with Hidden Semi-Markov Model (HSMM) and delayed Transfer Entropy (dTE). Although 'off-the-ball' behaviors are a crucial component of cooperation, most research tends to focus on 'on-the-ball' behaviors, and relations of behaviors are only known as tacit knowledge of coaches or players. In contrast, our approach quantitatively reveals player's relationships of 'off-the-ball' behaviors. The extracted causal models are compared to the corresponding video scenes, and we claim that our approach extracts causal relationships between teammates' behaviors or intentions and clarifies roles of the players in both attacking and defending phase.

Original languageEnglish
Title of host publicationProcedia Computer Science
PublisherElsevier
Pages85-91
Number of pages7
Volume71
DOIs
Publication statusPublished - 2015
Event6th Annual International Conference on Biologically Inspired Cognitive Architectures, BICA 2015 - Lyon, France
Duration: 2015 Nov 62015 Nov 8

Other

Other6th Annual International Conference on Biologically Inspired Cognitive Architectures, BICA 2015
CountryFrance
CityLyon
Period15/11/615/11/8

Fingerprint

Entropy
Switches

Keywords

  • Causality Analysis
  • delayed Transfer Entropy
  • Goal-type Ball Game
  • Group Behavior
  • Handball
  • Hidden Semi-Markov Model

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

Itoda, K., Watanabe, N., & Takefuji, Y. (2015). Model-based Behavioral Causality Analysis of Handball with Delayed Transfer Entropy. In Procedia Computer Science (Vol. 71, pp. 85-91). Elsevier. https://doi.org/10.1016/j.procs.2015.12.210

Model-based Behavioral Causality Analysis of Handball with Delayed Transfer Entropy. / Itoda, Kota; Watanabe, Norifumi; Takefuji, Yoshiyasu.

Procedia Computer Science. Vol. 71 Elsevier, 2015. p. 85-91.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Itoda, K, Watanabe, N & Takefuji, Y 2015, Model-based Behavioral Causality Analysis of Handball with Delayed Transfer Entropy. in Procedia Computer Science. vol. 71, Elsevier, pp. 85-91, 6th Annual International Conference on Biologically Inspired Cognitive Architectures, BICA 2015, Lyon, France, 15/11/6. https://doi.org/10.1016/j.procs.2015.12.210
Itoda, Kota ; Watanabe, Norifumi ; Takefuji, Yoshiyasu. / Model-based Behavioral Causality Analysis of Handball with Delayed Transfer Entropy. Procedia Computer Science. Vol. 71 Elsevier, 2015. pp. 85-91
@inproceedings{97e7cd38ed1c46088608a7f1a9dac218,
title = "Model-based Behavioral Causality Analysis of Handball with Delayed Transfer Entropy",
abstract = "In goal-type ball games, such as handball, basketball, hockey or soccer, teammates and opponents share the same field. They switch dynamically their behaviors and relationships based on other players' behaviors or intentions. Interactions between players are highly complicated and hard to comprehend, but recent technological developments have enabled us to acquire positions or velocities of their behaviors. We focus on handball as an example of goal-type ball games and analyze causality between teammates' behaviors from tracking data with Hidden Semi-Markov Model (HSMM) and delayed Transfer Entropy (dTE). Although 'off-the-ball' behaviors are a crucial component of cooperation, most research tends to focus on 'on-the-ball' behaviors, and relations of behaviors are only known as tacit knowledge of coaches or players. In contrast, our approach quantitatively reveals player's relationships of 'off-the-ball' behaviors. The extracted causal models are compared to the corresponding video scenes, and we claim that our approach extracts causal relationships between teammates' behaviors or intentions and clarifies roles of the players in both attacking and defending phase.",
keywords = "Causality Analysis, delayed Transfer Entropy, Goal-type Ball Game, Group Behavior, Handball, Hidden Semi-Markov Model",
author = "Kota Itoda and Norifumi Watanabe and Yoshiyasu Takefuji",
year = "2015",
doi = "10.1016/j.procs.2015.12.210",
language = "English",
volume = "71",
pages = "85--91",
booktitle = "Procedia Computer Science",
publisher = "Elsevier",

}

TY - GEN

T1 - Model-based Behavioral Causality Analysis of Handball with Delayed Transfer Entropy

AU - Itoda, Kota

AU - Watanabe, Norifumi

AU - Takefuji, Yoshiyasu

PY - 2015

Y1 - 2015

N2 - In goal-type ball games, such as handball, basketball, hockey or soccer, teammates and opponents share the same field. They switch dynamically their behaviors and relationships based on other players' behaviors or intentions. Interactions between players are highly complicated and hard to comprehend, but recent technological developments have enabled us to acquire positions or velocities of their behaviors. We focus on handball as an example of goal-type ball games and analyze causality between teammates' behaviors from tracking data with Hidden Semi-Markov Model (HSMM) and delayed Transfer Entropy (dTE). Although 'off-the-ball' behaviors are a crucial component of cooperation, most research tends to focus on 'on-the-ball' behaviors, and relations of behaviors are only known as tacit knowledge of coaches or players. In contrast, our approach quantitatively reveals player's relationships of 'off-the-ball' behaviors. The extracted causal models are compared to the corresponding video scenes, and we claim that our approach extracts causal relationships between teammates' behaviors or intentions and clarifies roles of the players in both attacking and defending phase.

AB - In goal-type ball games, such as handball, basketball, hockey or soccer, teammates and opponents share the same field. They switch dynamically their behaviors and relationships based on other players' behaviors or intentions. Interactions between players are highly complicated and hard to comprehend, but recent technological developments have enabled us to acquire positions or velocities of their behaviors. We focus on handball as an example of goal-type ball games and analyze causality between teammates' behaviors from tracking data with Hidden Semi-Markov Model (HSMM) and delayed Transfer Entropy (dTE). Although 'off-the-ball' behaviors are a crucial component of cooperation, most research tends to focus on 'on-the-ball' behaviors, and relations of behaviors are only known as tacit knowledge of coaches or players. In contrast, our approach quantitatively reveals player's relationships of 'off-the-ball' behaviors. The extracted causal models are compared to the corresponding video scenes, and we claim that our approach extracts causal relationships between teammates' behaviors or intentions and clarifies roles of the players in both attacking and defending phase.

KW - Causality Analysis

KW - delayed Transfer Entropy

KW - Goal-type Ball Game

KW - Group Behavior

KW - Handball

KW - Hidden Semi-Markov Model

UR - http://www.scopus.com/inward/record.url?scp=84962740866&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84962740866&partnerID=8YFLogxK

U2 - 10.1016/j.procs.2015.12.210

DO - 10.1016/j.procs.2015.12.210

M3 - Conference contribution

AN - SCOPUS:84962740866

VL - 71

SP - 85

EP - 91

BT - Procedia Computer Science

PB - Elsevier

ER -