Submit to this Journal Review for this Journal Propose a Special Issue

Article Menu

Share Help Cite Discuss in SciProfiles

Open AccessArticle

Peer-Review Record

AI-Driven Smart Transformation in Physical Education: Current Trends and Future Research Directions

Appl. Sci. 2024, 14(22), 10616; https://doi.org/10.3390/app142210616

by Zhengchun Hu¹, Zhaohe Liu¹ and Yushun Su^2,*

Reviewer 1: Anonymous

Reviewer 2:

Cristian Mihail Rus

Reviewer 3: Anonymous

Appl. Sci. 2024, 14(22), 10616; https://doi.org/10.3390/app142210616

Submission received: 10 October 2024 / Revised: 12 November 2024 / Accepted: 13 November 2024 / Published: 18 November 2024

(This article belongs to the Special Issue Applications of Digital Technology and AI in Educational Settings)

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors

Please find attatched.

Comments for author File: Comments.pdf

Author Response

Comment 1： Thank you for submitting your paper titled, 'AI-Driven Smart Transformation in Physical Education: Current Trends and Future Research Directions,' to Applied Sciences. I appreciated the opportunity to review your work. The topic addressed in this article is highly relevant, as the field of AI has expanded rapidly in recent years and holds significant potential to enhance teaching and learning processes. While this contribution is valuable, I have some concerns regarding the discourse adopted, which often emphasizes performance within the context of sports training. Given the fundamental pedagogical and didactic distinctions between sporting and educational settings, I believe it would be beneficial to include further clarifications on this matter. The references cited are mostly recent publications; however, there are some formatting inconsistencies that should be addressed. Please accept my comments in the respectfully constructive spirit in which they are intended.

Response 1: Thank you for your suggestions. Indeed, there has been some confusion between the concepts of physical education and sports training in both previous articles and this one. However, most of the articles related to the subjects of this study do not intentionally differentiate between these two concepts, unless a specific article aims to examine the distinctions between physical education and sports training(Dong Haiyang, 2017). We have re-checked and revised the citation format, making adjustments to the formatting of citations throughout the entire text.Nonetheless, we have made substantial additions and clarifications to the relevant content in the text. The specific adjustments are as follows:

1.Introduction

With the continuous advancement of technology, artificial intelligence (AI) has found increasingly deep applications across various fields, particularly in education, where it demonstrates tremendous potential. As a tool capable of optimizing resource allocation, improving teaching quality, and promoting personalized learning, AI equips educators with new resources and offers students a more efficient learning experience. In the field of physical education, traditional teaching methods often overlook individual differences among students, resulting in standardized training methods with limited personalized feedback [1]. To address this issue, it is essential to recognize the importance of a pedagogical approach that prioritizes the holistic development of students. Physical education should not merely focus on performance metrics but also foster cognitive, personal, and social skills, ensuring that all aspects of student growth are considered[2]. Physical education should not only focus on performance indicators but also promote the development of cognitive, personal, and social skills, ensuring attention is given to all aspects of student growth[3]. By designing personalized learning paths and conducting targeted training data analysis, AI can better address individual needs, enhancing the overall effectiveness of physical education. Through data-driven decision-making, AI provides teachers with precise insights to optimize their teaching strategies, allowing them to create more personalized plans based on each student’s abilities and performance, thereby improving the specificity and effectiveness of instruction [4].

With the rapid advancement of artificial intelligence technology, its application in the field of education, especially in physical education, is increasingly expanding and deepening[5]. This study focuses on the intersection of physical education and artifi-cial intelligence, exploring in depth how AI can significantly promote the comprehen-sive development of students from a unique educational perspective. At the same time, we utilize advanced techniques from computer science, particularly the LDA topic model, to accurately identify and analyze the main research directions of AI applica-tions in physical education.

As an important branch of education, physical education not only aims to enhance students' physical fitness but also emphasizes holistic development across cognitive, social, and other dimensions[6]. Artificial intelligence, as a core area of computer science, provides us with powerful data analysis and processing tools, making person-alized learning, precise teaching, and in-depth analysis of movement behavior possi-ble[7].

To effectively explore the application of AI in physical education, we need to clearly distinguish between physical education and sports training. These two areas have significant differences in teaching goals, methods, and target audiences. Physical education aims to promote students' overall development and lifelong participation in sports, whereas sports training emphasizes skill enhancement and optimization of competitive performance[2]. This difference requires us to consider not only the en-hancement of training performance when discussing AI applications but also the im-portance of learning outcomes and student engagement in the educational process.

Physical education operates within a dynamic and often unpredictable environ-ment, influenced by uncertainties such as pandemics and weather conditions [8]. AI technology addresses many of these previously insurmountable challenges by over-coming time and space limitations. Through the effective use of fragmented time and space, AI enables more intelligent and convenient scientific physical training [9].

As societal interest in sports continues to grow, the types and methods of associ-ated products are becoming increasingly diverse. Integrating artificial intelligence (AI) with physical education represents a significant step in educational innovation [8]. This combination improves teaching efficiency and enables personalized education, effectively stimulating students' interest and motivation in learning [1]. At the same time, the incorporation of artificial intelligence technology can enhance the effective-ness of personalized learning to a certain extent, providing students with differentiat-ed learning paths and specific content with targeted feedback. This approach meets the diverse needs of different students, thereby improving the overall teaching effective-ness[10]. Moreover, AI-driven wearable devices positively monitor physical conditions and enhance instruction safety [4]. Machine vision technology provides more precise feedback in sports training, thus improving training outcomes [11]. Additionally, 3D motion teaching localization technology positively correlates with training levels and performance [12].

There are many applications of artificial intelligence in physical education, such as the currently popular wearable devices. These devices effectively integrate wearable technology into physical education, allowing the system to track students' conditions and enhance interaction between students and teachers. Additionally, they can create tailored learning plans for students and provide instant feedback [13].

In the post-pandemic world, changes in people's habits due to prolonged preven-tive measures, along with the rapid development of AI technology [14], have acceler-ated the integration of physical education with AI, making it a new interdisciplinary application. This trend drives transformation in traditional physical education meth-ods and brings more innovation and opportunities to the sports industry. Wu and Ji [15] emphasize that traditional sports venues should actively embrace AI technology to promote technological application, service innovation, improved management effi-ciency, and comprehensive functional integration. This fusion can significantly en-hance athletes' training outcomes and propel the sports industry toward greater intel-ligence and modernization.

Although some studies have explored the integration of artificial intelligence (AI) with physical education through bibliometric methods [16] , most focus primarily on quantitative statistical data analysis and lack systematic exploration of key themes within the textual content. LDA can extract core themes from complex literature data, providing strong support for a deeper understanding of the critical areas of current research. Therefore, this study employs the LDA topic model to analyze existing liter-ature, aiming to systematically identify the main research directions of AI integration in physical education from a broader literature pool, thereby deepening the under-standing of the current status of AI applications in physical education. By revealing the primary themes and trends in current research, we hope to provide educators and researchers with a structured understanding that promotes the intelligent develop-ment of physical education.

Comment 2：ABSTRACT :Page 1, Line 10: The acronym must be written in full as it is its first use.

KEYWORDS

Page 1, Line 24: Replace 'physical education' with a relevant keyword that

accurately represents your work and enhances searchability, while avoiding the repetition of words already present in the title.

Response 2: Thank you for your suggestions. We have made corresponding adjustments to the abstract and optimized the content throughout. There may be some confusion between the concepts of physical education and sports training in this article. However, most of the articles related to the subjects of this study do not intentionally differentiate between these two concepts, unless a specific article aims to examine the distinctions between physical education and sports training (Dong Haiyang, 2017). To avoid potential controversy, we have changed the keywords to "Physical Education and Training." The specific adjustments are as follows:

Abstract: In recent years, the application of Artificial Intelligence (AI) in physical education has garnered increasing attention. This study is based on data from the Web of Science Core Collection and employs a systematic literature screening process, utilizing the LDA topic model for in-depth analysis of relevant literature to reveal the current status and trends of AI technology in physical education. The findings indicate that AI applications in this field primarily focus on three areas: “AI and data-driven optimization of physical education and training,” “computer vision and AI-based movement behavior recognition and training optimization,” and “AI and virtual technology-driven innovation and assessment in physical education.” An in-depth analysis of existing research shows that the intelligentization of physical education, particularly in school and athletic training contexts, not only promotes sustainable development in the field but also significantly enhances teaching quality and safety, allowing educators to utilize data more precisely to optimize teaching strategies. However, current research remains relatively broad and lacks more precise and robust data support. Therefore, this study critically examines the limitations of current research in the field and proposes key research directions for further advancing the intelligent transformation of physical education, providing a solid theoretical framework and guidance for future research.

Keywords: Physical education and training; Latent Dirichlet Allocation; physical education; Artificial Intelligence:；

Comment 3.：INTRODUCTION

The rationale presented throughout the introduction is not always clear. Even though some connections between the different themes are perceived, there are theoretical foundations that must be developed, strengthened and better clarified. Given that the context used is Physical Education, which encompasses the education and training of children, adolescents, and young adults, certain aspects of the teaching-learning process must be carefully considered, particularly at the pedagogical and didactic levels. Student learning should always guide the teacher's actions, without losing sight of the individual behind the student. The aim is not to reduce performance and motor development to mere data points, but rather to consider the student's holistic development. Physical Education, while fostering motor skills, should also focus on developing abilities in cognitive, personal, and social domains.

It is crucial that the authors highlight the importance of holistic student development across multiple domains, and demonstrate the potential of AI in the educational context without limiting its focus exclusively to the motor domain or quantitative assessments. Although motor skill development forms the basis of Physical Education, it is not confined to this domain, nor is it solely about processing training data. While improving student performance is a valid goal, 'performance' as an objective aligns more with sports training contexts than with educational settings. Therefore, I recommend that the introduction, discussion, and limitations sections of the study provide a comprehensive framework addressing this perspective.

Throughout the introduction, I notice a focus on the discourse associated with sports training, especially when they point out the benefits in the results of athlete training and the contribution to the development of the sports industry. Since the article focuses on the educational context, on Physical Education, it is important to understand the differences in its objectives. Thus, the discourse adopted must be based on the educational context and not the sporting context, or in order to realize that it is a way of highlighting what has been investigated, even if the focus is to increase research in a context with some similarities, but still distinct.

Response 3: Thank you for your suggestions. We have added supplementary information to the Introduction section, with specific adjustments as follows:

1.Introduction

To effectively explore the application of AI in physical education, we need to clearly distinguish between physical education and sports training. These two areas have significant differences in teaching goals, methods, and target audiences. Physical education aims to promote students' overall development and lifelong participation in sports, whereas sports training emphasizes skill enhancement and optimization of competitive performance [2]. This difference requires us to consider not only the en-hancement of training performance when discussing AI applications but also the im-portance of learning outcomes and student engagement in the educational process.

As societal interest in sports continues to grow, the types and methods of associated products are becoming increasingly diverse. Integrating artificial intelligence (AI) with physical education represents a significant step in educational innovation [8]. This combination improves teaching efficiency and enables personalized education, effectively stimulating students' interest and motivation in learning [1]. At the same time, the incorporation of artificial intelligence technology can enhance the effective-ness of personalized learning to a certain extent, providing students with differentiat-ed learning paths and specific content with targeted feedback. This approach meets the diverse needs of different students, thereby improving the overall teaching effective-ness[10]. Moreover, AI-driven wearable devices positively monitor physical conditions and enhance instruction safety [4]. Machine vision technology provides more precise feedback in sports training, thus improving training outcomes [11]. Additionally, 3D motion teaching localization technology positively correlates with training levels and performance [12].

In the post-pandemic world, changes in people's habits due to prolonged preven-tive measures, along with the rapid development of AI technology [14], have acceler-ated the integration of physical education with AI, making it a new interdisciplinary application. This trend drives transformation in traditional physical education meth-ods and brings more innovation and opportunities to the sports industry. Wu and Ji [15] emphasize that traditional sports venues should actively embrace AI technology to promote technological application, service innovation, improved management efficiency, and comprehensive functional integration. This fusion can significantly en-hance athletes' training outcomes and propel the sports industry toward greater intel-ligence and modernization.

Although some studies have explored the integration of artificial intelligence (AI) with physical education through bibliometric methods [16] , most focus primarily on quantitative statistical data analysis and lack systematic exploration of key themes within the textual content. LDA can extract core themes from complex literature data, providing strong support for a deeper understanding of the critical areas of current research. Therefore, this study employs the LDA topic model to analyze existing literature, aiming to systematically identify the main research directions of AI integration in physical education from a broader literature pool, thereby deepening the under-standing of the current status of AI applications in physical education. By revealing the primary themes and trends in current research, we hope to provide educators and researchers with a structured understanding that promotes the intelligent development of physical education.

Comment 4.：MATERIALS AND METHODS The materials and methods used are rigorous. The design aligns well with the main objective of the study.

DATA RESULTS AND ANALYSIS The results are appropriately presented, and there are no objections. However, I recommend that the authors take into account the various concerns previously highlighted in the introduction when analyzing and reflecting on the results obtained.

Response 4: Thank you for your suggestions. We have further enriched the content related to the research methods in the MATERIALS AND METHODS section, with specific adjustments as follows:

2.1. Data sources and research methods

This study aims to analyze the current achievements, future development directions, and potential challenges in the integration of "artificial intelligence and physical education." We selected journal articles from the Social Sciences Citation Index (SSCI) and Science Citation Index (SCI) in the Web of Science (WOS) Core Collection as the data sources, reflecting a focus on rigor and credibility [21,22]. Our search query was constructed as TS=(("Artificial intelligence" OR "Artificial neural network" OR "case-based reasoning" OR "cognitive computing" OR "cognitive science" OR "computer vision" OR "data mining" OR "data science" OR "deep learning" OR "expert system" OR "fuzzy linguistic modelling" OR "fuzzy logic" OR "genetic algorithm" OR "image recognition" OR "k-means" OR "knowledge-based system" OR "logic programming" OR "machine learning" OR "machine vision" OR "natural language processing" OR "neural network" OR "pattern recognition" OR "recommendation system" OR "recommender system" OR "semantic network" OR "speech recognition" OR "support vector machine" OR "SVM" OR "text mining") AND ("physical education" OR "sports education" OR "fitness education" OR "sports training")). Although the search strategy includes various interdisciplinary keywords, this study has rigorously screened the data to ensure that all selected literature is directly related to the application of artificial intelligence in physical education. The keywords "cognitive computing" and "communication codes" have practical applications in personalized feedback and learning analytics within physical education. By incorporating these keywords, we are able to comprehensively capture the diverse application scenarios and technological needs in the intelligent transformation of physical education[20].This search covered the period from January 1, 2003, to August 1, 2024. We chose this timeframe because, since 2003, the field of AI integration with physical education has seen a significant increase in attention. This period allows us to observe the development of technology, policy support, and emerging trends and challenges in practice. The cutoff date for the search was August 1, 2024, when we conducted the final literature search and data collection. The search strategy was designed to cover all potentially relevant literature on the research topic. However, despite the broad scope, the search may include some articles that are less relevant to the topic. The framework of Data sources and research methods is shown in Figure 1.

Figure 1. Data Sources and Retrieval Strategies

2.2. LDA topic model

Latent Dirichlet Allocation (LDA) is a probabilistic Bayesian model for analyzing discrete data and is one of the most effective techniques in text mining. It is widely used for data mining, uncovering latent data, and identifying relationships between data and text documents [20]. The core feature of the traditional LDA model is its unsupervised nature, which enables it to autonomously execute multiple analysis steps with minimal human intervention, even achieving automatic labeling functionality. [24].

The LDA topic model is one of the most effective techniques in text mining and has been applied in numerous disciplines and industries. For instance, significant results related to LDA have been achieved in fields such as biomedical research, communication studies, and maritime target detection[20,25,26].

In this study, we employed the LDA topic model based on Dirichlet distribution because of its superior performance in handling large volumes of documents and interpreting identified latent themes, compared to several other algorithms [27]. This approach effectively addresses the challenges posed by co-occurrence and keyword analysis in traditional bibliometric studies. In many cases, documents may not explicitly list keywords, or the keywords are merely selected from a predefined list, which significantly limits their accuracy and affects the true and comprehensive representation of the document's content. [28].

Topic modeling infers latent themes from textual data and automatically identifies topics within articles, showing their distribution across different documents. This method does not rely on predefined keywords or co-citation relationships but instead extracts information directly from the text, enabling a more accurate capture of the document’s meaning [29].

Figure 3 illustrates the generative process of the Latent Dirichlet Allocation (LDA) model [24], which assumes that each document is a mixture of several topics, and each topic is a distribution over multiple words. In this model, α and β control two Dirichlet distributions. The parameter α randomly generates the topic multinomial distribution θ for each document, θ then randomly generates a topic z, and β randomly generates the word multinomial distribution φ for the corresponding topic. Combining the topic z and the corresponding word distribution φ generates a word w. This process continues until a document with m words is generated, ultimately leading to n documents under k topics[25]. Through this model, we obtain the document-topic and topic-word distributions related to the integration of artificial intelligence and physical education.

The document-topic distribution helps analyze the directions and focus areas of AI integration with physical education. By comparing the topic distributions θm of different documents, we can identify which topics are frequently associated with integrating AI and physical education. Analyzing the document-topic distribution also helps uncover new research directions and unexplored areas[20]. Researchers can determine new research avenues and propose recommendations by identifying topics that appear less frequently in existing documents.

Similarly, the topic-word distribution provides a deeper understanding of the research content in the AI and physical education domain. By comparing the word distributions within different topics, we can identify φk and recognize which words frequently associate with AI and physical education integration [25].This analysis not only helps determine future research directions but also provides new suggestions for policymakers, highlighting their crucial role in shaping the future of AI in physical education[20].

Comment 5： DATA RESULTS AND ANALYSIS The results are appropriately presented, and there are no objections. However, I recommend that the authors take into account the various concerns previously highlighted in the introduction when analyzing and reflecting on the results obtained. INFORMED CONSENT STATEMENT Please clarify the rationale for seeking consent and identify from whom it was obtained, given that the study does not involve human subjects as participants.

Response 5: Thank you for your suggestions. We have made content modifications to the introduction and conclusion sections to strengthen the connection within the article, with specific changes as follows:

Introduction

In the post-pandemic world, changes in people's habits due to prolonged preven-tive measures, along with the rapid development of AI technology [14], have acceler-ated the integration of physical education with AI, making it a new interdisciplinary application. This trend drives transformation in traditional physical education meth-ods and brings more innovation and opportunities to the sports industry. Wu and Ji [8] emphasize that traditional sports venues should actively embrace AI technology to promote technological application, service innovation, improved management effi-ciency, and comprehensive functional integration. This fusion can significantly en-hance athletes' training outcomes and propel the sports industry toward greater intel-ligence and modernization [15].

Comment 6：INFORMED CONSENT STATEMENT Please clarify the rationale for seeking consent and identify from whom it was obtained, given that the study does not involve human subjects as participants.

DATA AVAILABILITY STATEMENT According to the journal's guidelines, this section must be completed.

REFERENCES The cited references are appropriate and, for the most part, consist of recent publications. It is recommended to standardize the formatting of the references, as some entries contain capitalized text while others do not.

Response 6: Thank you for your suggestions. We have made content revisions in the requested areas, All data were obtained from the WOS Core Collection, and there are no legal issues. Additionally, I conducted a thorough check on the citation format standards and ultimately standardized the formatting of references [15], [16], [21], and [22].with specific adjustments as follows:

Informed consent statement: Not applicable.

Data Availability Statement: The original contributions presented in the study are included in the article material; further inquiries can be directed to the corresponding author.

Author Response File: Author Response.pdf

Reviewer 2 Report

Comments and Suggestions for Authors

A relevant and current study that follows the current trend of the realities in which we live.

• What is the main question addressed by the research?

The proposed study is an analysis for a number of publications that have the same common denominator AI. The use of the LDA (Latent Dirichlet Allocation) model for text analysis is only a reference system proposed by others for a basis to be provided by the Social Sciences Citation Index (SSCI) and the Science Citation Index (SCI) of the Web of Science (WOS) Core Collection .

• Do you consider the topic original or relevant to the field? Does it address a specific gap in the field? Please also explain why this is/is not the case.

The topic is a bit forced and mixes different topics from the perspective of communication codes, lines 96-107, from cognitive computing (99) to sports education (106), but this can be a great advantage for other researchers with a niche approach.

• What does it add to the subject area compared to other published material?

It presents a crystallized perspective of a volume of articles already published, a fact that can positively favor future researchers in approaches to this subject.

• What specific methodological improvements should the authors consider? What additional checks should be considered?

To this question, my answer is that: the vision of the authors must be respected as it is and my recommendations would seem nothing more than unacceptable misrepresentations.

• Are the conclusions consistent with the evidence and arguments presented and do they address the main question posed? Please also explain why this is/is not the case.

I come back and emphasize, the conclusions are ok from the research perspective, but the authors make confusion regarding the notions of physical education (299) and sports activities (401), a fact that induces, from the perspective of the field of Physical Education and Sport, some ambiguities, but this fact does not decrease with nothing worth this study.

• Are references adequate?

The references are carefully chosen and eloquent!

• Any additional comments on tables and figures.

These are well founded and self-explanatory.

Author Response

Reviewer 2:

Comment 1：What is the main question addressed by the research?

Response 1: Thank you for your suggestions. We have added supplementary information to the Introduction section, with specific adjustments as follows:

Introduction

The structure of the remainder of this article is as follows: Section 2 describes the process, methods, and results of determining the research topic; Section 3 discusses the current status of the research topic and provides a summary of each aspect; Section 4 outlines the contributions of this study and looks ahead to the future development of the integration of artificial intelligence and physical education.

Comment 2：Do you consider the topic original or relevant to the field? Does it address a specific gap in the field? Please also explain why this is/is not the case.

Response 2: Thank you for your suggestions. We have made adjustments to the 2.1. Data Sources and Research Methods section, adding further explanations regarding the composition of the search strategy. This includes detailing the rationale for using various interdisciplinary keywords included in the search strategy, as well as supplementing the literature. The specific content adjustments are as follows:

2.1. Data sources and research methods

Figure 1. Data Sources and Retrieval Strategies

Comment 3：What does it add to the subject area compared to other published material?

It presents a crystallized perspective of a volume of articles already published, a fact that can positively favor future researchers in approaches to this subject.

Response 3: Thank you for your suggestion. We have further supplemented the introduction and Chapter Four with summaries of the research questions and research contributions, with specific content adjustments as follows:

4.1. Research Contributions

This study systematically identifies three main application directions of artificial intelligence in physical education through LDA topic analysis. This thematic classification not only provides a structured framework for the field but also offers a clear direction for future research. Secondly, the study delves into the groundbreaking contributions of AI technology in automated movement behavior recognition and personalized feedback, highlighting the important role of AI in enhancing the scientific nature of sports training and the accuracy of feedback. Thirdly, the study presents the practical application value of integrating AI with virtual reality technology in physical education classrooms, providing data support for improving student engagement and the precision of teaching assessments. Finally, the research proposes future research directions from the perspectives of sustainability and personalization, emphasizing the potential of intelligent physical education in resource utilization, educational equity, and social benefits. Through these contributions, this study provides theoretical support and practical guidance for academic exploration and practical development in intelligent physical education.

Comment 4：What specific methodological improvements should the authors consider? What additional checks should be considered?

To this question, my answer is that: the vision of the authors must be respected as it is and my recommendations would seem nothing more than unacceptable misrepresentations.

Response 4: Thank you for your suggestion. In Section 4.2, Future Research Outlook, of Chapter Four, we have added suggestions for improving research methods based on different perspectives for future studies, such as the dynamic topic model. The specific adjustments are as follows:

4.3. Future Research Outlook

Physical education has its unique characteristics, with each sport requiring specific skills, rules, and underlying values, which place particular demands on educational methods and approaches. While technological advancements have driven the smartification of physical education, this evolution presents both opportunities and challenges. Future research can focus on addressing these challenges.

The personalized application of AI in physical education still holds significant potential for development [16]. Future studies should focus on developing more refined personalized teaching plans, utilizing deep learning technologies to optimize and tailor content based on multidimensional data, such as students' physical fitness and athletic performance [30]. This approach aims to significantly enhance teaching quality and guide the evolution of physical education toward a more advanced level of intelligence and personalization.

The deeper integration of virtual reality (VR) and AI is a key research direction for the future. Although VR technology has been preliminarily applied in physical education, its close integration with AI remains to be further explored [47]. A critical research question is how to combine virtual training environments with AI-driven data analysis to enable real-time adjustments to teaching content, offering students an immersive and personalized training experience.

The sustainability of smart physical education also warrants more attention. It is essential to explore how the widespread application of AI in physical education can promote long-term educational equity and efficiency while minimizing environmental resource consumption. The application prospects of AI technology in physical education are vast, extending beyond just improving training outcomes to enhancing students' learning experiences and educational equity. Future research directions should focus on how to effectively integrate AI technology into the educational system to promote the holistic develop-ment of students.

Comment 5：Are the conclusions consistent with the evidence and arguments presented and do they address the main question posed? Please also explain why this is/is not the case.

Response 5: Thank you for your suggestion. We have made further content adjustments throughout the paper regarding the mentioned aspects. "Physical education" refers to a systematic and structured teaching process, while "sports activities" pertains to the actual sports or activity experiences in which students participate. We have revised the relevant sections accordingly, with specific adjustments as follows:

Introduction

With the continuous advancement of technology, artificial intelligence (AI) has found increasingly deep applications across various fields, particularly in education, where it demonstrates tremendous potential. As a tool capable of optimizing resource allocation, improving teaching quality, and promoting personalized learning, AI equips educators with new resources and offers students a more efficient learning ex-perience. In the field of physical education, traditional teaching methods often over-look individual differences among students, resulting in standardized training meth-ods with limited personalized feedback [1]. To address this issue, it is essential to rec-ognize the importance of a pedagogical approach that prioritizes the holistic devel-opment of students. Physical education should not merely focus on performance met-rics but also foster cognitive, personal, and social skills, ensuring that all aspects of student growth are considered[2]. Physical education should not only focus on per-formance indicators but also promote the development of cognitive, personal, and so-cial skills, ensuring attention is given to all aspects of student growth[3]. By designing personalized learning paths and conducting targeted training data analysis, AI can better address individual needs, enhancing the overall effectiveness of physical educa-tion. Through data-driven decision-making, AI provides teachers with precise insights to optimize their teaching strategies, allowing them to create more personalized plans based on each student’s abilities and performance, thereby improving the specificity and effectiveness of instruction [4].

In the post-pandemic world, changes in people's habits due to prolonged preven-tive measures, along with the rapid development of AI technology [14], have acceler-ated the integration of physical education with AI, making it a new interdisciplinary application. This trend drives transformation in traditional physical education meth-ods and brings more innovation and opportunities to the sports industry. Wu and Ji [8] emphasize that traditional sports venues should actively embrace AI technology to promote technological application, service innovation, improved management effi-ciency, and comprehensive functional integration. This fusion can significantly en-hance athletes' training outcomes and propel the sports industry toward greater intel-ligence and modernization .

2.2. LDA topic model

Comment 6：Are references adequate?

The references are carefully chosen and eloquent!

Any additional comments on tables and figures.

These are well founded and self-explanatory.

Reponse 6: Thank you for your suggestion. All the references in our study come from the WOS Core Collection, and during the process of adjusting the content throughout the research, we added several additional references to enrich the study. To enrich the research content and make it more comprehensive, we have added additional figures, with specific adjustments as follows:

2.1. Data sources and research methods

This study aims to analyze the current achievements, future development direc-tions, and potential challenges in the integration of "artificial intelligence and physical education." We selected journal articles from the Social Sciences Citation Index (SSCI) and Science Citation Index (SCI) in the Web of Science (WOS) Core Collection as the data sources, reflecting a focus on rigor and credibility [21,22]. Our search query was constructed as TS=(("Artificial intelligence" OR "Artificial neural network" OR "case-based reasoning" OR "cognitive computing" OR "cognitive science" OR "computer vision" OR "data mining" OR "data science" OR "deep learning" OR "expert system" OR "fuzzy linguistic modelling" OR "fuzzy logic" OR "genetic algorithm" OR "image recog-nition" OR "k-means" OR "knowledge-based system" OR "logic programming" OR "ma-chine learning" OR "machine vision" OR "natural language processing" OR "neural network" OR "pattern recognition" OR "recommendation system" OR "recommender system" OR "semantic network" OR "speech recognition" OR "support vector machine" OR "SVM" OR "text mining") AND ("physical education" OR "sports education" OR "fitness education" OR "sports training")). Although the search strategy includes vari-ous interdisciplinary keywords, this study has rigorously screened the data to ensure that all selected literature is directly related to the application of artificial intelligence in physical education. The keywords "cognitive computing" and "communication codes" have practical applications in personalized feedback and learning analytics within physical education. By incorporating these keywords, we are able to compre-hensively capture the diverse application scenarios and technological needs in the in-telligent transformation of physical education[20].This search covered the period from January 1, 2003, to August 1, 2024. We chose this timeframe because, since 2003, the field of AI integration with physical education has seen a significant increase in atten-tion. This period allows us to observe the development of technology, policy support, and emerging trends and challenges in practice. The cutoff date for the search was August 1, 2024, when we conducted the final literature search and data collection. The search strategy was designed to cover all potentially relevant literature on the research topic. However, despite the broad scope, the search may include some articles that are less relevant to the topic. The framework of Data sources and research methods is shown in Figure 1.

Figure 1. Data Sources and Retrieval Strategies

Author Response File: Author Response.pdf

Reviewer 3 Report

Comments and Suggestions for Authors

The Abstract is well written, however it could include more information – in brief -about the research design and context used. The Introduction could include more information about the discipline used along with a short overview of the rest of the article in the last paragraph. The first paragraph of the Data Sources and Research Methods could be presented in a table as an alternative mode of representation. Author could include references in the stages/steps of the method used, so as to justify it. The LDA section presents in a clear and brief manner the model used along with justification, which however could be more extensive. Section 3.2.1 needs more justification in literature. The paper could be enriched with a more representative sample of data sets, derived from the LDA model as well as it would be useful to provide more information on the use of AI in physical education, targeted at physical education and its context. This is a good approach which however could be enriched at specific sections.

Author Response

Comment 1：The Abstract is well written, however it could include more information – in brief -about the research design and context used. The Introduction could include more information about the discipline used along with a short overview of the rest of the article in the last paragraph. The first paragraph of the Data Sources and Research Methods could be presented in a table as an alternative mode of representation. Author could include references in the stages/steps of the method used, so as to justify it. The LDA section presents in a clear and brief manner the model used along with justification, which however could be more extensive. Section 3.2.1 needs more justification in literature. The paper could be enriched with a more representative sample of data sets, derived from the LDA model as well as it would be useful to provide more information on the use of AI in physical education, targeted at physical education and its context. This is a good approach which however could be enriched at specific sections.

Response 1: Thank you for your suggestion. I have reflected deeply on the suggestions above and made further optimizations to the relevant parts of the article. The specific changes are as follows:

(1)We have carefully checked and corrected the citation styles in our manuscript that did not comply with the literature standards. These corrections have been marked in the text.

(2)The articles you recommended are very important for the issue of sustainable employment. I have added these two articles to the 1. Introduction' section of the manuscript and highlighted them in yellow. The details are as follows:

Introduction

With the continuous advancement of technology, artificial intelligence (AI) has found increasingly deep applications across various fields, particularly in education, where it demonstrates tremendous potential. As a tool capable of optimizing resource allocation, improving teaching quality, and promoting personalized learning, AI equips educators with new resources and offers students a more efficient learning ex-perience. In the field of physical education, traditional teaching methods often over-look individual differences among students, resulting in standardized training meth-ods with limited personalized feedback [1]. To address this issue, it is essential to rec-ognize the importance of a pedagogical approach that prioritizes the holistic devel-opment of students. Physical education should not merely focus on performance met-rics but also foster cognitive, personal, and social skills, ensuring that all aspects of student growth are considered[2]. Physical education should not only focus on per-formance indicators but also promote the development of cognitive, personal, and so-cial skills, ensuring attention is given to all aspects of student growth[3]. By designing personalized learning paths and conducting targeted training data analysis, AI can better address individual needs, enhancing the overall effectiveness of physical educa-tion. Through data-driven decision-making, AI provides teachers with precise insights to optimize their teaching strategies, allowing them to create more personalized plans based on each student’s abilities and performance, thereby improving the specificity and effectiveness of instruction [4].

(3)We have transformed this section into a table and adjusted the wording of the content, enriching the references. The specific adjustments are as follows:

2.1. Data sources and research methods

Figure 1. Data Sources and Retrieval Strategies

(4)I have added more references to certain sections to strengthen the rationale behind the statements. The changes are as follows:

(5)We have further added references in this section and enriched the content to provide a more comprehensive introduction to the model. We have further supplemented this section to provide a more comprehensive description of the relevant research on the application of the model and added more information regarding the use of artificial intelligence in physical education and its related contexts. The specific changes are as follows:

2.2. LDA topic model

(6)I have added more references in this section to enhance the introduction of the topic and strengthen the rationale behind the arguments. The specific adjustments are as follows:

3.2.1. AI and Data-Driven Optimization of Physical Education and Training

With the rapid development of artificial intelligence (AI), various industries are actively seeking ways to integrate AI technologies and the field of physical education is no exception[34]. Increasingly, research is focusing on the application of AI in physical education, making exploring how AI can enhance teaching and training outcomes a prominent research area[8]. The advancement of AI technologies, particularly the application of neural networks, deep learning, and data mining, has profoundly impacted physical education and training[35,36]. In the simulation training results, high-probability keywords such as "network," "student," "college," and "mining" indicate that scholars in this research area tend to explore the integration of neural networks, deep learning, and data mining technologies within physical education and training. These studies go beyond a superficial understanding of the broad concept of AI, delving into the application and future development of data mining ("mining," "system") and deep learning ("deep") technologies in physical education and training. This research plays a critical role in unlocking the potential of current physical education and enhancing its sustainability[37].Data mining ("mining," "system") and deep learning technologies ("deep") provide better technical support for physical education, making them crucial for optimizing both teaching and training processes[36]. Hence, Topic 1 has been labeled "AI and Data-Driven Optimization of Physical Education and Training. As shown in Figure 6.

In recent years, many scholars have explored how AI technology can optimize physical education classes, analyze training data, and improve teaching outcomes through the application of neural network technologies. The studies by Li et al. [38] and Liu et al. [39] indicate that the integration of network technology ("network") with higher education physical education not only enhances teaching effectiveness, promotes the smartification of physical education, optimizes resource allocation, and boosts student participation, but also offers new perspectives and methods for research in the field of physical education. This integration not only helps improve the current state of physical education but also has a profound impact on its future development. Cao et al. [40] leveraged AI-based big data mining ("mining") to suggest that education should aim to stimulate student engagement, enhance physical fitness, and encourage students to adapt to diverse learning environments, including physical education. Their study shows that AI can not only compensate for the limitations of traditional education but also enhance students' overall competencies, allowing them to grasp key concepts in real-world settings. Wan [41] specifically highlighted the promising application of BP neural networks in sports training, demonstrating that BP neural networks can enhance students' physical functions, enabling them to perform at their best while showcasing the multiple benefits of physical exercise. Fu [42], through research on basketball, found that deep learning and BP neural networks could analyze athletes' performance, identify areas for improvement, and provide personalized training recommendations, supporting teachers in developing more efficient teaching strategies. Yang et al. [43] predicted that the integration of AI technology will lead to revolutionary changes in future physical education. The application of AI holds great potential, as it can provide precise, data-driven support for curriculum design and training evaluation in physical education. These studies provide a solid foundation for the integration of AI with physical education and clearly highlight the significant value of AI in this field.

These studies summarize the multiple advantages of artificial intelligence and data-driven technologies in physical education, which not only have a positive impact on students and teachers but also promote the intelligent transformation of the entire education system, enhancing the efficiency and engagement of teaching. As algorithms continue to improve and the trend towards

smartification accelerates, the education system can leverage a variety of technologies and methods to promote sustainable development. These studies provide a theoretical foundation for the intelligent transformation of physical education and offer guidance for future educational reforms, particularly in improving the efficiency and effectiveness of physical education [37].

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

Comments and Suggestions for Authors

Considering that two of the previously provided suggestions were not implemented, likely due to being overlooked amidst other inputs, I would like to reiterate them here.

I kindly request that you consult the attached document to identify the specific suggestions.

Comments for author File: Comments.pdf

Author Response

Comment 1：The acronym (LDA) must be written in full as it is its first use

Response 1: Thank you for your suggestions. We have made modifications to the relevant content in the abstract, with the details of the revisions as follows:

Abstract: Although the rapid development of Artificial Intelligence (AI) in recent years has brought increasing academic attention to the intelligent transformation of physical education, the core knowledge structure of this field, such as its primary research topics, has yet to be systematically explored. The LDA (Latent Dirichlet Allocation) topic model can identify latent themes in large-scale textual data, helping researchers extract key research directions and development trends from extensive literature. This study is based on data from the Web of Science Core Collection and employs a systematic literature screening process, utilizing the LDA topic model for in-depth analysis of relevant literature to reveal the current status and trends of AI technology in physical education. The findings indicate that AI applications in this field primarily focus on three areas: “AI and data-driven optimization of physical education and training,” “computer vision and AI-based movement behavior recognition and training optimization,” and “AI and virtual technology-driven innovation and assessment in physical education.” An in-depth analysis of existing research shows that the intelligentization of physical education, particularly in school and athletic training contexts, not only promotes sustainable development in the field but also significantly enhances teaching quality and safety, allowing educators to utilize data more precisely to optimize teaching strategies. However, current research remains relatively broad and lacks more precise and robust data support. Therefore, this study critically examines the limitations of current research in the field and proposes key research directions for further advancing the intelligent transformation of physical education, providing a solid theoretical framework and guidance for future research.

Comment 2：Replace 'physical education' with a relevant keyword that accurately represents your work and enhances searchability, while avoiding the repetition of words already present in the title.

Response 2: Thank you for your suggestions. We replaced the keyword "physical education" with "Physical Development," which avoids conflict with the article title and effectively represents the focus of this study.

Author Response File: Author Response.docx

Reviewer 3 Report

Comments and Suggestions for Authors

The Abstract could include more information about the research design and context used, as well as brief presentation of preliminary data (in 2 rows). Τhe Introduction section includes important concepts which however could be analysed in a literature review section, especially since the topic of the paper is about AR and state of the art technology- a section as such is missing. The inclusion of Figures 6 and 7 seems not to have an added value to the quality of the paper- these word arts are no data sets, and presentation and analysis of more data could improve the quality of the paper and ensure the validity of the research design.

Author Response

Comment 1：The Abstract could include more information about the research design and context used, as well as brief presentation of preliminary data (in 2 rows). Τhe Introduction section includes important concepts which however could be analysed in a literature review section, especially since the topic of the paper is about AR and state of the art technology- a section as such is missing. The inclusion of Figures 6 and 7 seems not to have an added value to the quality of the paper- these word arts are no data sets, and presentation and analysis of more data could improve the quality of the paper and ensure the validity of the research design.

Response 1: Thank you for your suggestions. We have expanded the research background and methodology sections in the abstract, and presented our preliminary data. In addition to incorporating content on Augmented Reality (AR) and frontier technologies, we made substantial changes to the Introduction and added a literature review section as Chapter 2. We also removed the etymological diagrams from Figures 6 to 8, as detailed below:

Abstract: Although the rapid development of Artificial Intelligence (AI) in recent years has brought increasing academic attention to the intelligent transformation of physical education, the core knowledge structure of this field, such as its primary research topics, has yet to be systematically explored. The LDA (Latent Dirichlet Allocation) topic model can identify latent themes in large-scale textual data, helping researchers extract key research directions and development trends from extensive literature. This study is based on data from the Web of Science Core Collection and employs a systematic literature screening process, utilizing the LDA topic model for indepth analysis of relevant literature to reveal the current status and trends of AI technology in physical education. The findings indicate that AI applications in this field primarily focus on three areas: “AI and data-driven optimization of physical education and training,” “computer vision and AI-based movement behavior recognition and training optimization,” and “AI and virtual technology-driven innovation and assessment in physical education.” An in-depth analysis of existing research shows that the intelligentization of physical education, particularly in school and athletic training contexts, not only promotes sustainable development in the field but also significantly enhances teaching quality and safety, allowing educators to utilize data more precisely to optimize teaching strategies. However, current research remains relatively broad and lacks more precise and robust data support. Therefore, this study critically examines the limitations of current research in the field and proposes key research directions for further advancing the intelligent transformation of physical education, providing a solid theoretical framework and guidance for future research.

Introduction

With the continuous advancement of technology, artificial intelligence (AI) has found increasingly deep applications across various fields, particularly in education, where it demonstrates tremendous potential. As a tool capable of optimizing resource allocation, improving teaching quality, and promoting personalized learning, AI equips educators with new resources and offers students a more efficient learning experience. In the field of physical education, traditional teaching methods often overlook individual differences among students, resulting in standardized training methods with limited personalized feedback [1]. To address this issue, it is essential to recognize the importance of a pedagogical approach that prioritizes the holistic development of students. Physical education should not merely focus on performance metrics but also foster cognitive, personal, and social skills, ensuring that all aspects of student growth are considered [2]. Physical education should not only focus on performance indicators but also promote the development of cognitive, personal, and social skills, ensuring attention is given to all aspects of student growth [3]. By designing personalized learning paths and conducting targeted training data analysis, AI can better address individual needs, enhancing the overall effectiveness of physical education. Through data-driven decision-making, AI provides teachers with precise insights to optimize their teaching strategies, allowing them to create more personalized plans based on each student’s abilities and performance, thereby improving the specificity and effectiveness of instruction [4].

With the rapid advancement of artificial intelligence technology, its application in the field of education, especially in physical education, is increasingly expanding and deepening [5]. This study focuses on the intersection of physical education and AI, using the LDA topic model to systematically identify the main research directions in AI applications within physical education. By revealing the primary themes and trends in current research, this study aims to provide educators and researchers with structured insights that promote the intelligent development of physical education.

The remainder of this study is structured as follows: Section 2 reviews relevant research on AI in the field of physical education, providing a theoretical foundation for subsequent analysis. Section 3 describes the process, methods, and results of determining the research themes. Section 4 discusses the current status of the research themes and summarizes various aspects. Section 5 outlines the contributions of this study and provides an outlook on the future development of AI integration in physical education.

Literature Review

The application of artificial intelligence (AI) in physical education has become an important research topic, focusing primarily on how to improve and innovate educational approaches through technological means. Numerous studies have shown that AI has the potential to transform traditional educational methods by providing personalized feedback, optimizing teaching resources, and enhancing overall learning outcomes [5]. In physical education, AI is used to address the limitations of standardized teaching methods, particularly their inability to accommodate individual differences among students [1].

As an important branch of education, physical education not only aims to enhance students' physical fitness but also emphasizes holistic development across cognitive, social, and other dimensions [6]. Artificial intelligence, as a core area of computer science, provides us with powerful data analysis and processing tools, making personalized learning, precise teaching, and in-depth analysis of movement behavior possible [7].

In 1997, physical education was divided into four sub-disciplines: sports education training, sports humanities, kinesiology, and traditional national sports. Therefore, physical education is more comprehensive; it not only seeks to improve students' physical fitness but also involves various aspects of mental and physical development, while sports training focuses more on performance indicators and competitive results [2]. To effectively explore the application of AI in physical education, we need to clearly distinguish between physical education and sports training. These two areas have significant differences in teaching goals, methods, and target audiences. Physical education aims to promote students' overall development and lifelong participation in sports, whereas sports training emphasizes skill enhancement and optimization of competitive performance [2,8]. This difference requires us to consider not only the enhancement of training performance when discussing AI applications but also the importance of learning outcomes and student engagement in the educational process.

Physical education operates within a dynamic and often unpredictable environment, influenced by uncertainties such as pandemics and weather conditions [9]. AI technology addresses many of these previously insurmountable challenges by overcoming time and space limitations. Through the effective use of fragmented time and space, AI enables more intelligent and convenient scientific physical training [10].

As societal interest in sports continues to grow, the types and methods of associated products are becoming increasingly diverse. Integrating artificial intelligence (AI) with physical education represents a significant step in educational innovation [9]. This combination improves teaching efficiency and enables personalized education, effectively stimulating students' interest and motivation in learning [1]. The application of AR and cutting-edge technologies in physical education encompasses numerous aspects. AR can significantly enhance the effectiveness and quality of physical education, providing more refined instructional designs that stimulate students' interest and help achieve educational objectives [11]. At the same time, the incorporation of artificial intelligence technology can enhance the effectiveness of personalized learning to a certain extent, providing students with differentiated learning paths and specific content with targeted feedback. This approach meets the diverse needs of different students, thereby improving the overall teaching effectiveness[12]. Moreover, AI-driven wearable devices positively monitor physical conditions and enhance instruction safety [4]. Machine vision technology provides more precise feedback in sports training, thus improving training outcomes [13]. Additionally, 3D motion teaching localization technology positively correlates with training levels and performance [14].

There are many applications of artificial intelligence in physical education, and in recent years, the use of wearable devices, a cutting-edge technology, has significantly increased in this field [15]. These devices effectively integrate wearable technology into physical education, allowing the system to track students' conditions and enhance interaction between students and teachers. Additionally, they can create tailored learning plans for students and provide instant feedback [16]. These advanced technologies can effectively track students' participation in physical activities, enhance sports instruction and teacher-student interaction, and enable data-driven, intelligent, and visualized physical education. By tailoring exercise plans to students' strengths and preventing ineffective activities and injuries, these devices significantly improve teaching effectiveness [16].

In the post-pandemic world, changes in people's habits due to prolonged preventive measures, along with the rapid development of AI technology [17], have accelerated the integration of physical education with AI, making it a new interdisciplinary application. This trend drives transformation in traditional physical education methods and brings more innovation and opportunities to the sports industry. Wu and Ji [18] emphasize that traditional sports venues should actively embrace AI technology to promote technological application, service innovation, improved management efficiency, and comprehensive functional integration. This fusion can significantly enhance athletes' training outcomes and propel the sports industry toward greater intelligence and modernization.

As an advanced text analysis tool, the LDA topic model identifies latent themes in large-scale textual data, assisting researchers in extracting critical research directions and development trends from vast literature [19]. Compared to traditional qualitative literature reviews, the LDA model offers greater systematicity and objectivity, revealing hidden thematic structures in a data-driven manner. This advantage has led to its widespread application across multiple disciplines, especially in research requiring the analysis of large textual datasets, such as in communication studies, social sciences, and education [20]. For instance, Daniel Maier [21] and colleagues used the LDA model in communication studies to successfully distill core research themes, enhancing the transparency and interpretability of their results. Similarly, Hamed Jelodar [22] and others demonstrated the broad applicability of LDA in handling complex datasets, further proving the method’s effectiveness in education and other intricate fields.

Although some studies have explored the integration of artificial intelligence (AI) with physical education through bibliometric methods [23] , most focus primarily on quantitative statistical data analysis and lack systematic exploration of key themes within the textual content. LDA can extract core themes from complex literature data, providing strong support for a deeper understanding of key areas in current research. Therefore, this study applies the LDA topic model to analyze existing literature, aiming to systematically identify the main research directions in the integration of AI with physical education from a broader pool of studies. By revealing the primary themes and trends in current research, we hope this study can offer valuable theoretical support to educators, researchers, and policymakers, further advancing the intelligent development of physical education and inspiring more in-depth research on the application of AI in this field.

Author Response File: Author Response.pdf

Article Menu

AI-Driven Smart Transformation in Physical Education: Current Trends and Future Research Directions

Further Information

Guidelines

MDPI Initiatives

Follow MDPI