Ryota Takamido , Chiharu Suzuki , Jun Ota , Hiroki Nakamoto
{"title":"使用神经格兰杰因果关系作为可解释的人工智能来理解两个玩家之间的全身人际动态","authors":"Ryota Takamido , Chiharu Suzuki , Jun Ota , Hiroki Nakamoto","doi":"10.1016/j.humov.2025.103366","DOIUrl":null,"url":null,"abstract":"<div><div>Understanding the dynamics of complex, whole-body interpersonal coordination behavior in humans is an important subject in behavioral science. However, due to the challenges of analyzing complex causal relationships among multiple body components with conventional techniques, this area remains underexplored. To address this issue, this study proposes a new analytical framework that attempts to understand the underlying causal structures behind each joint movement of individual players using neural Granger causality (NGC) as the explainable artificial intelligence (XAI). In the NGC analysis, causal relationships were defined as the size of the weight parameters of the first layer of a machine-learning model trained to predict the future state of a specific time-series variable. To verify this approach practically, we conducted an experiment with 16 pairs of expert baseball pitchers and batters, and input datasets with 27 joint resultant velocity (13 pitchers' and 14 batters' joints) were generated and used for model training. The results revealed that significant causal relations exist among intra- and inter-individual body components, such as “the batter's hands have a causal effect from pitcher's throwing arm.” Although the causality from the batters to the pitcher's body is significantly lower than that from the pitchers to the batter's body, it exhibits a significant correlation with the performance outcomes of batters (R<sup>2</sup> = 0.69). These results suggest the effectiveness of the NGC analysis for understanding whole-body inter-personal coordination dynamics and, more broadly, the XAI technique as a new approach for analyzing complex human behavior from a perspective different from conventional techniques.</div></div>","PeriodicalId":55046,"journal":{"name":"Human Movement Science","volume":"101 ","pages":"Article 103366"},"PeriodicalIF":1.9000,"publicationDate":"2025-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Understanding whole-body inter-personal dynamics between two players using neural granger causality as the explainable artificial intelligence\",\"authors\":\"Ryota Takamido , Chiharu Suzuki , Jun Ota , Hiroki Nakamoto\",\"doi\":\"10.1016/j.humov.2025.103366\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>Understanding the dynamics of complex, whole-body interpersonal coordination behavior in humans is an important subject in behavioral science. However, due to the challenges of analyzing complex causal relationships among multiple body components with conventional techniques, this area remains underexplored. To address this issue, this study proposes a new analytical framework that attempts to understand the underlying causal structures behind each joint movement of individual players using neural Granger causality (NGC) as the explainable artificial intelligence (XAI). In the NGC analysis, causal relationships were defined as the size of the weight parameters of the first layer of a machine-learning model trained to predict the future state of a specific time-series variable. To verify this approach practically, we conducted an experiment with 16 pairs of expert baseball pitchers and batters, and input datasets with 27 joint resultant velocity (13 pitchers' and 14 batters' joints) were generated and used for model training. The results revealed that significant causal relations exist among intra- and inter-individual body components, such as “the batter's hands have a causal effect from pitcher's throwing arm.” Although the causality from the batters to the pitcher's body is significantly lower than that from the pitchers to the batter's body, it exhibits a significant correlation with the performance outcomes of batters (R<sup>2</sup> = 0.69). These results suggest the effectiveness of the NGC analysis for understanding whole-body inter-personal coordination dynamics and, more broadly, the XAI technique as a new approach for analyzing complex human behavior from a perspective different from conventional techniques.</div></div>\",\"PeriodicalId\":55046,\"journal\":{\"name\":\"Human Movement Science\",\"volume\":\"101 \",\"pages\":\"Article 103366\"},\"PeriodicalIF\":1.9000,\"publicationDate\":\"2025-05-30\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Human Movement Science\",\"FirstCategoryId\":\"102\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S016794572500048X\",\"RegionNum\":3,\"RegionCategory\":\"心理学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"NEUROSCIENCES\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Human Movement Science","FirstCategoryId":"102","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S016794572500048X","RegionNum":3,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"NEUROSCIENCES","Score":null,"Total":0}
Understanding whole-body inter-personal dynamics between two players using neural granger causality as the explainable artificial intelligence
Understanding the dynamics of complex, whole-body interpersonal coordination behavior in humans is an important subject in behavioral science. However, due to the challenges of analyzing complex causal relationships among multiple body components with conventional techniques, this area remains underexplored. To address this issue, this study proposes a new analytical framework that attempts to understand the underlying causal structures behind each joint movement of individual players using neural Granger causality (NGC) as the explainable artificial intelligence (XAI). In the NGC analysis, causal relationships were defined as the size of the weight parameters of the first layer of a machine-learning model trained to predict the future state of a specific time-series variable. To verify this approach practically, we conducted an experiment with 16 pairs of expert baseball pitchers and batters, and input datasets with 27 joint resultant velocity (13 pitchers' and 14 batters' joints) were generated and used for model training. The results revealed that significant causal relations exist among intra- and inter-individual body components, such as “the batter's hands have a causal effect from pitcher's throwing arm.” Although the causality from the batters to the pitcher's body is significantly lower than that from the pitchers to the batter's body, it exhibits a significant correlation with the performance outcomes of batters (R2 = 0.69). These results suggest the effectiveness of the NGC analysis for understanding whole-body inter-personal coordination dynamics and, more broadly, the XAI technique as a new approach for analyzing complex human behavior from a perspective different from conventional techniques.
期刊介绍:
Human Movement Science provides a medium for publishing disciplinary and multidisciplinary studies on human movement. It brings together psychological, biomechanical and neurophysiological research on the control, organization and learning of human movement, including the perceptual support of movement. The overarching goal of the journal is to publish articles that help advance theoretical understanding of the control and organization of human movement, as well as changes therein as a function of development, learning and rehabilitation. The nature of the research reported may vary from fundamental theoretical or empirical studies to more applied studies in the fields of, for example, sport, dance and rehabilitation with the proviso that all studies have a distinct theoretical bearing. Also, reviews and meta-studies advancing the understanding of human movement are welcome.
These aims and scope imply that purely descriptive studies are not acceptable, while methodological articles are only acceptable if the methodology in question opens up new vistas in understanding the control and organization of human movement. The same holds for articles on exercise physiology, which in general are not supported, unless they speak to the control and organization of human movement. In general, it is required that the theoretical message of articles published in Human Movement Science is, to a certain extent, innovative and not dismissible as just "more of the same."