{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T13:20:14Z","timestamp":1774444814485,"version":"3.50.1"},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,5,7]],"date-time":"2025-05-07T00:00:00Z","timestamp":1746576000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,5,7]],"date-time":"2025-05-07T00:00:00Z","timestamp":1746576000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Discov Computing"],"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>Neural architecture search (NAS) has emerged as a promising approach for automating deep learning model design. However, its application in sports analytics faces unique challenges due to the complex interplay between biomechanical patterns, physiological adaptations, and coaching expertise. Traditional NAS methods need help to effectively capture the multifaceted nature of athletic performance, often failing to integrate qualitative coaching insights with quantitative measurements. We introduce ChampionNet, a framework incorporating NAS and large language models to enhance accuracy in predicting athletic performance and tailoring training regimens. Our approach offers three primary contributions: integrating hyperdimensional embedding to capture fine-grained biomechanical features and physiological parameters with exceptional detail, a structure-preserving graph encoding leverages to maintain crucial spatiotemporal relationships in athletic movements, and the novel comprehensiveness of the training graph that models forward performance prediction and backward physiological adaptation pathways. Our experiments on various sports demonstrate that ChampionNet outperforms other models by 2.5% in accuracy and over 61.9% in computational cost. Further insights illustrate the framework's performance with complex patterns and multi-modal data, especially for sports with advanced biomechanical needs. These findings support ChampionNet's effectiveness as an integrative athletic performance optimization solution, highlighting the need for automated architecture search tailored to sports.<\/jats:p>","DOI":"10.1007\/s10791-025-09560-y","type":"journal-article","created":{"date-parts":[[2025,5,7]],"date-time":"2025-05-07T16:58:27Z","timestamp":1746637107000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["ChampionNet: a transformer-enhanced neural architecture search framework for athletic performance prediction and training optimization"],"prefix":"10.1007","volume":"28","author":[{"given":"Lei","family":"Chang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shalli","family":"Rani","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Muhammad Azeem","family":"Akbar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,5,7]]},"reference":[{"issue":"5","key":"9560_CR1","doi-asserted-by":"publisher","first-page":"1400","DOI":"10.1109\/TC.2024.3365949","volume":"73","author":"LB Ma","year":"2024","unstructured":"Ma LB, Kang HD, Yu G, Li Q, He Q. Single-domain generalized predictor for neural architecture search system. IEEE Trans Comput. 2024;73(5):1400\u201313.","journal-title":"IEEE Trans Comput"},{"issue":"9","key":"9560_CR2","doi-asserted-by":"publisher","first-page":"260","DOI":"10.1007\/s10462-024-10888-y","volume":"57","author":"P Kumar","year":"2024","unstructured":"Kumar P. Large language models (LLMs): survey, technical frameworks, and future challenges. Artif Intell Rev. 2024;57(9):260.","journal-title":"Artif Intell Rev"},{"issue":"5","key":"9560_CR3","doi-asserted-by":"publisher","first-page":"e264","DOI":"10.1519\/JSC.0000000000004727","volume":"38","author":"JR Harry","year":"2024","unstructured":"Harry JR, Hurwitz J, Agnew C, Bishop C. Statistical tests for sports science practitioners: identifying performance gains in individual athletes. J Strength Cond Res. 2024;38(5):e264\u201372.","journal-title":"J Strength Cond Res"},{"key":"9560_CR4","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2025.3530416","author":"N Li","year":"2025","unstructured":"Li N, Xue B, Ma LB. Automatic fuzzy architecture design for defect detection via classifier-assisted multiobjective optimization approach. IEEE Trans Evol Comput. 2025. https:\/\/doi.org\/10.1109\/TEVC.2025.3530416.","journal-title":"IEEE Trans Evol Comput"},{"issue":"11","key":"9560_CR5","doi-asserted-by":"publisher","first-page":"1583","DOI":"10.1123\/ijspp.2022-0105","volume":"17","author":"F Dobler","year":"2022","unstructured":"Dobler F, Bachl P, Stoggl T, Andersson EP. Physiological responses and performance during a 3-minute cycle time trial: standard paced versus all-out paced. Int J Sports Physiol Perform. 2022;17(11):1583\u20139.","journal-title":"Int J Sports Physiol Perform"},{"key":"9560_CR6","doi-asserted-by":"publisher","DOI":"10.1016\/j.ypmed.2023.107582","volume":"173","author":"ZW Liu","year":"2023","unstructured":"Liu ZW, Wang XF. Action recognition for sports combined training based on wearable sensor technology and SVM prediction. Prev Med. 2023;173: 107582.","journal-title":"Prev Med"},{"key":"9560_CR7","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102780","volume":"115","author":"JH Lv","year":"2024","unstructured":"Lv JH, Kim BG, Parameshachari BD, Slowik A, Li KQ. Large model-driven hyperscale healthcare data fusion analysis in complex multi-sensors. Inf Fusion. 2024;115: 102780.","journal-title":"Inf Fusion"},{"key":"9560_CR8","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2023.119642","volume":"649","author":"GT Pereira","year":"2023","unstructured":"Pereira GT, Santos IBA, Garcia LPF, Urruty T, Visani M, de Carvalho ACPLF. Neural architecture search with interpretable meta-features and fast predictors. Inf Sci. 2023;649: 119642.","journal-title":"Inf Sci"},{"issue":"4","key":"9560_CR9","doi-asserted-by":"publisher","first-page":"769","DOI":"10.26599\/TST.2022.9010042","volume":"28","author":"Y Jin","year":"2023","unstructured":"Jin Y, Zhang Y, Zhang Y. Neighbor library-aware graph neural network for third party library recommendation. Tsinghua Sci Technol. 2023;28(4):769\u201385.","journal-title":"Tsinghua Sci Technol"},{"issue":"7","key":"9560_CR10","doi-asserted-by":"publisher","first-page":"640","DOI":"10.23736\/S0022-4707.24.15786-6","volume":"64","author":"B Lim","year":"2024","unstructured":"Lim B, Song WK. Exploring CrossFit performance prediction and analysis via extensive data and machine learning. J Sports Med Phys Fitness. 2024;64(7):640\u20139.","journal-title":"J Sports Med Phys Fitness"},{"issue":"12","key":"9560_CR11","doi-asserted-by":"publisher","first-page":"1853","DOI":"10.3390\/math12121853","volume":"12","author":"M White","year":"2024","unstructured":"White M, De Lazzari B, Bezodis N, Camomilla V. Wearable sensors for athletic performance: a comparison of discrete and continuous feature-extraction methods for prediction models. Mathematics. 2024;12(12):1853.","journal-title":"Mathematics"},{"issue":"6","key":"9560_CR12","doi-asserted-by":"publisher","first-page":"2585","DOI":"10.1007\/s11036-022-02074-7","volume":"27","author":"DK Jiang","year":"2022","unstructured":"Jiang DK, Gadekallu TR. Research on a mobile prediction platform for dynamic changes in athletic performance based on screening factors. Mob Netw Appl. 2022;27(6):2585\u201395.","journal-title":"Mob Netw Appl"},{"issue":"4","key":"9560_CR13","doi-asserted-by":"publisher","first-page":"786","DOI":"10.26599\/TST.2022.9010050","volume":"28","author":"D Ma","year":"2023","unstructured":"Ma D, Wang Y, Ma J, Jin Q. SGNR: A social graph neural network based interactive recommendation scheme for e-commerce. Tsinghua Sci Technol. 2023;28(4):786\u201398.","journal-title":"Tsinghua Sci Technol"},{"key":"9560_CR14","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2024.3470323","author":"ZH Liu","year":"2024","unstructured":"Liu ZH, Quan Y, Lyu XH, Alenazi MJF. Enhancing clinical accuracy of medical chatbots with large language models. IEEE J Biomed Health Inform. 2024. https:\/\/doi.org\/10.1109\/JBHI.2024.3470323.","journal-title":"IEEE J Biomed Health Inform"},{"issue":"8","key":"9560_CR15","doi-asserted-by":"publisher","first-page":"1143","DOI":"10.1631\/FITEE.2300041","volume":"24","author":"LN Zhou","year":"2023","unstructured":"Zhou LN, Lu ZG, You WK, Fang XF. Reversible data hiding using a transformer predictor and an adaptive embedding strategy. Front Inf Technol Electron Eng. 2023;24(8):1143\u201355.","journal-title":"Front Inf Technol Electron Eng"},{"issue":"11","key":"9560_CR16","doi-asserted-by":"publisher","first-page":"4975","DOI":"10.1109\/TCAD.2022.3148202","volume":"41","author":"S Hassantabar","year":"2022","unstructured":"Hassantabar S, Dai XL, Jha NK. CURIOUS: efficient neural architecture search based on a performance predictor and evolutionary search. IEEE Trans Comput-Aided Des Integr Circuits Syst. 2022;41(11):4975\u201390.","journal-title":"IEEE Trans Comput-Aided Des Integr Circuits Syst."},{"key":"9560_CR17","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1613\/jair.1.13942","volume":"77","author":"S Tuli","year":"2023","unstructured":"Tuli S, Dedhia B, Tuli S, Jha NK. FlexiBERT: are current transformer architectures too homogeneous and rigid? J Artif Intell Res. 2023;77:39\u201370.","journal-title":"J Artif Intell Res"},{"key":"9560_CR18","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2024.106539","volume":"179","author":"CC Xiao","year":"2024","unstructured":"Xiao CC, Cao Q, Zhong YJ, Lan L, Zhang X, Luo ZG, Tao DC. MotionTrack: learning motion predictor for multiple object tracking. Neural Netw. 2024;179: 106539.","journal-title":"Neural Netw"},{"key":"9560_CR19","doi-asserted-by":"publisher","first-page":"548","DOI":"10.1016\/j.neunet.2023.10.055","volume":"170","author":"HY Cai","year":"2024","unstructured":"Cai HY, Lan L, Zhang J, Zhang X, Zhan YB, Luo ZG. IoUformer: pseudo-IoU prediction with transformer for visual tracking. Neural Netw. 2024;170:548\u201363.","journal-title":"Neural Netw"},{"key":"9560_CR20","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.123716","volume":"249","author":"J Wang","year":"2024","unstructured":"Wang J, Yang S, Wang YY, Yang G. PPTtrack: Pyramid pooling based Transformer backbone for visual tracking. Expert Syst Appl. 2024;249: 123716.","journal-title":"Expert Syst Appl"},{"key":"9560_CR21","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110301","volume":"150","author":"MSS Raj","year":"2024","unstructured":"Raj MSS, George SN, Raja K. Leveraging spatio-temporal features using graph neural networks for human activity recognition. Pattern Recognit. 2024;150: 110301.","journal-title":"Pattern Recognit"},{"key":"9560_CR22","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2024.101694","volume":"89","author":"JW Zhang","year":"2025","unstructured":"Zhang JW, Han DL, Han S, Li H, Lam WK, Zhang MY. ChatMatch: exploring the potential of hybrid vision-language deep learning approach for the intelligent analysis and inference of racket sports. Comput Speech Lang. 2025;89: 101694.","journal-title":"Comput Speech Lang"},{"issue":"6","key":"9560_CR23","doi-asserted-by":"publisher","first-page":"1079","DOI":"10.1007\/s41095-023-0392-y","volume":"10","author":"ZZ Feng","year":"2024","unstructured":"Feng ZZ, Zhu F, Wang HJ, Hao JN, Yang SH, Zeng W, Qu HM. HoLens: a visual analytics design for higher-order movement modeling and visualization. Comput Vis Media. 2024;10(6):1079\u2013100.","journal-title":"Comput Vis Media"},{"issue":"1","key":"9560_CR24","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1109\/TEVC.2022.3178299","volume":"27","author":"AA Bidgoli","year":"2022","unstructured":"Bidgoli AA, Rahnamayan S, Dehkharghanian T, Riasatian A, Tizhoosh HR. Evolutionary computation in action: hyperdimensional deep embedding spaces of gigapixel pathology images. IEEE Trans Evol Comput. 2022;27(1):52\u201366.","journal-title":"IEEE Trans Evol Comput"},{"key":"9560_CR25","doi-asserted-by":"publisher","first-page":"150","DOI":"10.1016\/j.patrec.2021.06.012","volume":"149","author":"Y Shi","year":"2021","unstructured":"Shi Y, Xiao Y, Quan P, Lei ML, Niu LF. Document-level relation extraction via graph transformer networks and temporal convolutional networks. Pattern Recognit Lett. 2021;149:150\u20131566.","journal-title":"Pattern Recognit Lett"},{"issue":"20","key":"9560_CR26","doi-asserted-by":"publisher","first-page":"29459","DOI":"10.1007\/s11042-022-12831-1","volume":"81","author":"XH Wang","year":"2022","unstructured":"Wang XH, Hu SH. Visual gait recognition based on convolutional block attention network. Multimed Tools Appl. 2022;81(20):29459\u201376.","journal-title":"Multimed Tools Appl"},{"issue":"3","key":"9560_CR27","doi-asserted-by":"publisher","first-page":"416","DOI":"10.1109\/TCBB.2024.3366545","volume":"21","author":"W Wang","year":"2024","unstructured":"Wang W, Sun ZX, Liu D, Zhang HJ, Li JT, Wang XF, Zhou Y. MAHyNet: parallel hybrid network for RNA-protein binding sites prediction based on multi-head attention and expectation pooling. IEEE\/ACM Trans Comput Biol Bioinform. 2024;21(3):416\u201327.","journal-title":"IEEE\/ACM Trans Comput Biol Bioinform"},{"issue":"1","key":"9560_CR28","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1016\/j.icte.2019.06.001","volume":"6","author":"MS Hanif","year":"2020","unstructured":"Hanif MS, Bilal M. Competitive residual neural network for image classification. ICT Express. 2020;6(1):28\u201337.","journal-title":"ICT Express"},{"issue":"17","key":"9560_CR29","doi-asserted-by":"publisher","first-page":"5696","DOI":"10.3390\/s24175696","volume":"24","author":"AA Sharifi","year":"2024","unstructured":"Sharifi AA, Zoljodi A, Daneshtalab M. TrajectoryNAS: a neural architecture search for trajectory prediction. Sensor. 2024;24(17):5696.","journal-title":"Sensor"},{"issue":"4","key":"9560_CR30","doi-asserted-by":"publisher","first-page":"1081","DOI":"10.1109\/TC.2022.3188175","volume":"72","author":"XZ Luo","year":"2023","unstructured":"Luo XZ, Liu D, Kong H, Huai S, Chen H, Liu WC. SurgeNAS: a comprehensive surgery on hardware-aware differentiable neural architecture search. IEEE Trans Comput. 2023;72(4):1081\u201394.","journal-title":"IEEE Trans Comput"},{"issue":"2","key":"9560_CR31","doi-asserted-by":"publisher","first-page":"444","DOI":"10.1109\/TETC.2023.3270181","volume":"12","author":"JL Gao","year":"2024","unstructured":"Gao JL, Chen JM, Oloulade BM, Al-Sabri R, Lyu T, Zhang J, Li Z. CommGNAS: unsupervised graph neural architecture search for community detection. IEEE Trans Emerg Top Comput. 2024;12(2):444\u201354.","journal-title":"IEEE Trans Emerg Top Comput"},{"key":"9560_CR32","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2024.109030","volume":"136","author":"C Termritthikun","year":"2024","unstructured":"Termritthikun C, Umer A, Suwanwimolkul S, Xia F, Lee IV. SalNAS: efficient Saliency-prediction Neural Architecture Search with self-knowledge distillation. Eng Appl Artif Intell. 2024;136: 109030.","journal-title":"Eng Appl Artif Intell"},{"issue":"7","key":"9560_CR33","doi-asserted-by":"publisher","first-page":"5868","DOI":"10.1109\/TCSVT.2023.3287684","volume":"34","author":"BC Guo","year":"2024","unstructured":"Guo BC, Xu LL, Chen T, Ye P, He SB, Liu HY, Chen JM. Latency-aware neural architecture performance predictor with query-to-tier technique. IEEE Trans Circuits Syst Video Technol. 2024;34(7):5868\u201383.","journal-title":"IEEE Trans Circuits Syst Video Technol"}],"container-title":["Discover Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10791-025-09560-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10791-025-09560-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10791-025-09560-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,7]],"date-time":"2025-05-07T16:58:27Z","timestamp":1746637107000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10791-025-09560-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,7]]},"references-count":33,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["9560"],"URL":"https:\/\/doi.org\/10.1007\/s10791-025-09560-y","relation":{},"ISSN":["2948-2992"],"issn-type":[{"value":"2948-2992","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,7]]},"assertion":[{"value":"16 January 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 April 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 May 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"71"}}