Ayoub Asadi , Afkham Daneshfar , Mohammad R. Saeedpour-Parizi , Christopher A. Aiken , Ann Smiley
{"title":"Detecting optimal gaze behavior of successful basketball free throwing via machine learning system","authors":"Ayoub Asadi , Afkham Daneshfar , Mohammad R. Saeedpour-Parizi , Christopher A. Aiken , Ann Smiley","doi":"10.1016/j.humov.2025.103381","DOIUrl":null,"url":null,"abstract":"<div><div>Eye tracking in sport is an emerging field that explores the relationships between visual function and motor performance. However, research has shown that visual behaviors are distinct enough to detect superior performance; and serve as a suitable input for designing machine learning systems, few study has been tested yet the eye tracking machine learning in sport tasks. The current research investigated the eye movement behaviors for detecting successful performance using machine learning. The gaze behavior of 25 student basketball players during the hit and miss free- throwing's trials was collected and analyzed by statistical (JMP pro) and machine learning (Python) approaches. Results showed significant differences between saccade duration in hit and miss trials. In previous studies of free throwing, fixations were used as a measure of visual information processing, but our results showed that the metrics related to saccades were more important for successful performance than those related to fixations. These findings highlight the importance of eye tracking machine learning in sport domain and suggest that successful performance can be reliably predicted from performers' eye movement data. Our results provide primary insights as well as inspiration for future research focusing on developing eye-tracking machine learning systems to detect proficiency in motor skills.</div></div>","PeriodicalId":55046,"journal":{"name":"Human Movement Science","volume":"102 ","pages":"Article 103381"},"PeriodicalIF":1.9000,"publicationDate":"2025-06-13","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/S0167945725000636","RegionNum":3,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"NEUROSCIENCES","Score":null,"Total":0}
引用次数: 0
Abstract
Eye tracking in sport is an emerging field that explores the relationships between visual function and motor performance. However, research has shown that visual behaviors are distinct enough to detect superior performance; and serve as a suitable input for designing machine learning systems, few study has been tested yet the eye tracking machine learning in sport tasks. The current research investigated the eye movement behaviors for detecting successful performance using machine learning. The gaze behavior of 25 student basketball players during the hit and miss free- throwing's trials was collected and analyzed by statistical (JMP pro) and machine learning (Python) approaches. Results showed significant differences between saccade duration in hit and miss trials. In previous studies of free throwing, fixations were used as a measure of visual information processing, but our results showed that the metrics related to saccades were more important for successful performance than those related to fixations. These findings highlight the importance of eye tracking machine learning in sport domain and suggest that successful performance can be reliably predicted from performers' eye movement data. Our results provide primary insights as well as inspiration for future research focusing on developing eye-tracking machine learning systems to detect proficiency in motor skills.
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."