{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T07:10:51Z","timestamp":1777965051637,"version":"3.51.4"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T00:00:00Z","timestamp":1777939200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T00:00:00Z","timestamp":1777939200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"The Science and Technology Projects of Guangzhou","award":["2025A04J3386"],"award-info":[{"award-number":["2025A04J3386"]}]},{"name":"The Guangxi Natural Science Foundation","award":["2025GXNSFAA069842"],"award-info":[{"award-number":["2025GXNSFAA069842"]}]},{"DOI":"10.13039\/501100001809","name":"The National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["11801105"],"award-info":[{"award-number":["11801105"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Data Sci Anal"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1007\/s41060-026-01118-5","type":"journal-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T06:12:21Z","timestamp":1777961541000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Component number selection in partial least squares based on SPlit algorithm"],"prefix":"10.1007","volume":"22","author":[{"given":"Zhixi","family":"Yi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuxuan","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiangong","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Youwu","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,5,5]]},"reference":[{"key":"1118_CR1","doi-asserted-by":"publisher","first-page":"286","DOI":"10.1007\/BFb0062108","volume-title":"Matrix Pencils","author":"S Wold","year":"1983","unstructured":"Wold, S., Martens, H., Wold, H.: The multivariate calibration problem in chemistry solved by the PLS method. In: Matrix Pencils, pp. 286\u2013293. Springer, Berlin, Heidelberg (1983)"},{"issue":"2","key":"1118_CR2","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1016\/S0169-7439(01)00155-1","volume":"58","author":"S Wold","year":"2001","unstructured":"Wold, S., Sj\u00f6str\u00f6m, M., Eriksson, L.: PLS-regression: a basic tool of chemometrics. Chemom. Intell. Lab. Syst. 58(2), 109\u2013130 (2001)","journal-title":"Chemom. Intell. Lab. Syst."},{"issue":"2","key":"1118_CR3","doi-asserted-by":"publisher","first-page":"455","DOI":"10.1016\/j.neuroimage.2010.07.034","volume":"56","author":"A Krishnan","year":"2011","unstructured":"Krishnan, A., Williams, L.J., McIntosh, A.R., Abdi, H.: Partial least squares (PLS) methods for neuroimaging: a tutorial and review. Neuroimage 56(2), 455\u2013475 (2011)","journal-title":"Neuroimage"},{"issue":"1","key":"1118_CR4","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1111\/j.1467-9868.2009.00723.x","volume":"72","author":"H Chun","year":"2010","unstructured":"Chun, H., Kele\u015f, S.: Sparse partial least squares regression for simultaneous dimension reduction and variable selection. J. R. Stat. Soc. B Stat. Methodol. 72(1), 3\u201325 (2010)","journal-title":"J. R. Stat. Soc. B Stat. Methodol."},{"issue":"1","key":"1118_CR5","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1002\/cem.2762","volume":"30","author":"T Mehmood","year":"2016","unstructured":"Mehmood, T., Ahmed, B.: The diversity in the applications of partial least squares: an overview. J. Chemom. 30(1), 4\u201317 (2016)","journal-title":"J. Chemom."},{"issue":"9","key":"1118_CR6","doi-asserted-by":"publisher","DOI":"10.1002\/cem.3044","volume":"32","author":"IS Helland","year":"2018","unstructured":"Helland, I.S., S\u00e6b\u00f8, S., Alm\u00f8y, T., Rimal, R.: Model and estimators for partial least squares regression. J. Chemom. 32(9), e3044 (2018)","journal-title":"J. Chemom."},{"issue":"5","key":"1118_CR7","doi-asserted-by":"publisher","DOI":"10.1590\/0103-8478cr20201072","volume":"52","author":"RA Ferreira","year":"2021","unstructured":"Ferreira, R.A., Teixeira, G., Peternelli, L.A.: Kennard-Stone method outperforms the random sampling in the selection of calibration samples in SNPs and NIR data. Cienc. Rural 52(5), e20201072 (2021)","journal-title":"Cienc. Rural"},{"issue":"4","key":"1118_CR8","doi-asserted-by":"publisher","first-page":"736","DOI":"10.1016\/j.talanta.2005.03.025","volume":"67","author":"RKH Galvao","year":"2005","unstructured":"Galvao, R.K.H., Araujo, M.C.U., Jos\u00e9, G.E., Pontes, M.J.C., Silva, E.C., Saldanha, T.C.B.: A method for calibration and validation subset partitioning. Talanta 67(4), 736\u2013740 (2005)","journal-title":"Talanta"},{"issue":"1-2","key":"1118_CR9","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1016\/S0169-7439(03)00083-2","volume":"68","author":"S Amato","year":"2003","unstructured":"Amato, S., Vinzi, V.E.: Bootstrap-based Q\u0302kh2 for the selection of components and variables in PLS regression. Chemom. Intell. Lab. Syst. 68(1\u20132), 5\u201316 (2003)","journal-title":"Chemom. Intell. Lab. Syst."},{"issue":"4","key":"1118_CR10","doi-asserted-by":"publisher","DOI":"10.1002\/cem.2993","volume":"32","author":"OM Kvalheim","year":"2018","unstructured":"Kvalheim, O.M., Arneberg, R., Grung, B., Rajalahti, T.: Determination of optimum number of components in partial least squares regression from distributions of the root\u2010mean\u2010squared error obtained by Monte Carlo resampling. J. Chemom. 32(4), e2993 (2018)","journal-title":"J. Chemom."},{"issue":"6A","key":"1118_CR11","doi-asserted-by":"publisher","first-page":"2562","DOI":"10.1214\/17-AOS1629","volume":"46","author":"S Mak","year":"2018","unstructured":"Mak, S., Joseph, V.R.: Support points. Ann. Stat. 46(6A), 2562\u20132592 (2018)","journal-title":"Ann. Stat."},{"issue":"2","key":"1118_CR12","doi-asserted-by":"publisher","first-page":"166","DOI":"10.1080\/00401706.2021.1921037","volume":"64","author":"VR Joseph","year":"2022","unstructured":"Joseph, V.R., Vakayil, A.: SPlit: an optimal method for data splitting. Technometrics 64(2), 166\u2013176 (2022)","journal-title":"Technometrics"},{"key":"1118_CR13","doi-asserted-by":"publisher","DOI":"10.1016\/j.measurement.2021.110131","volume":"186","author":"NM Kebonye","year":"2021","unstructured":"Kebonye, N.M.: Exploring the novel support points-based split method on a soil dataset. Measurement 186, 110131 (2021)","journal-title":"Measurement"},{"key":"1118_CR14","doi-asserted-by":"publisher","DOI":"10.1016\/j.csda.2023.107780","volume":"186","author":"OD Agboola","year":"2023","unstructured":"Agboola, O.D., Yu, H.: Neighborhood-based cross fitting approach to treatment effects with high-dimensional data. Comput. Stat. Data Anal. 186, 107780 (2023)","journal-title":"Comput. Stat. Data Anal."},{"issue":"1","key":"1118_CR15","volume":"2023","author":"S Krishnan","year":"2023","unstructured":"Krishnan, S., Aruna, S.K., Kanagarathinam, K., Venugopal, E.: Identification of dry bean varieties based on multiple attributes using catboost machine learning algorithm. Sci. Program. 2023(1), 2556066 (2023)","journal-title":"Sci. Program."},{"key":"1118_CR16","unstructured":"Wold H:. Estimation of principal components and related models by iterative least squares. Multivariate Analysis. 391\u2013420 (1966)"},{"issue":"5","key":"1118_CR17","doi-asserted-by":"publisher","first-page":"477","DOI":"10.1016\/0892-0362(89)90025-1","volume":"11","author":"PD Sampson","year":"1989","unstructured":"Sampson, P.D., Streissguth, A.P., Barr, H.M., Bookstein, F.L.: Neurobehavioral effects of prenatal alcohol: part ii. partial least squares analysis. Neurotoxicol. Teratol. 11(5), 477\u2013491 (1989)","journal-title":"Neurotoxicol. Teratol."},{"issue":"3","key":"1118_CR18","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1002\/cem.1180020306","volume":"2","author":"A H\u00f6skuldsson","year":"1988","unstructured":"H\u00f6skuldsson, A.: PLS regression methods. J. Chemom. 2(3), 211\u2013228 (1988)","journal-title":"J. Chemom."},{"issue":"3","key":"1118_CR19","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1002\/cem.605","volume":"15","author":"QS Xu","year":"2001","unstructured":"Xu, Q.S., Liang, Y.Z., Shen, H.L.: Generalized PLS regression. J. Chemom. 15(3), 135\u2013148 (2001)","journal-title":"J. Chemom."},{"issue":"3","key":"1118_CR20","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1016\/0169-7439(93)85002-X","volume":"18","author":"S De Jong","year":"1993","unstructured":"De Jong, S.: SIMPLS: an alternative approach to partial least squares regression. Chemom. Intell. Lab. Syst. 18(3), 251\u2013263 (1993)","journal-title":"Chemom. Intell. Lab. Syst."},{"issue":"12","key":"1118_CR21","doi-asserted-by":"publisher","DOI":"10.1002\/cem.3457","volume":"36","author":"YW Lin","year":"2022","unstructured":"Lin, Y.W., Xu, C.C., Zhou, Z.J., Shen, L., Huang, S.: Distribution\u2010free predictive inference for partial least squares regression with applications to molecular descriptors datasets. J. Chemom. 36(12), e3457 (2022)","journal-title":"J. Chemom."},{"issue":"1","key":"1118_CR22","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1080\/00401706.1969.10490666","volume":"11","author":"RW Kennard","year":"1969","unstructured":"Kennard, R.W., Stone, L.A.: Computer aided design of experiments. Technometrics 11(1), 137\u2013148 (1969)","journal-title":"Technometrics"},{"issue":"1","key":"1118_CR23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1214\/aos\/1176344552","volume":"7","author":"B Efron","year":"1979","unstructured":"Efron, B.: Bootstrap methods: another look at the jackknife. Ann. Stat. 7(1), 1\u201326 (1979)","journal-title":"Ann. Stat."},{"issue":"4","key":"1118_CR24","doi-asserted-by":"publisher","first-page":"501","DOI":"10.1080\/07350015.1988.10509698","volume":"6","author":"NT Quan","year":"1988","unstructured":"Quan, N.T.: The prediction sum of squares as a general measure for regression diagnostics[J]. J. Bus. Econ. Stat. 6(4), 501\u2013504 (1988)","journal-title":"J. Bus. Econ. Stat."},{"issue":"2","key":"1118_CR25","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1016\/S0169-7439(97)00038-5","volume":"37","author":"JH Kalivas","year":"1997","unstructured":"Kalivas, J.H.: Two data sets of near infrared spectra. Chemom. Intell. Lab. Syst. 37(2), 255\u2013259 (1997)","journal-title":"Chemom. Intell. Lab. Syst."},{"issue":"2","key":"1118_CR26","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1016\/0169-7439(95)80023-3","volume":"27","author":"M Forina","year":"1995","unstructured":"Forina, M., Drava, G., Armanino, C., Boggia, R., Lanteri, S., Leardi, R., Corti, P., Conti, P., Giangiacomo, R., Galliena, C., Bigoni, R., Quartari, I., Serra, C., Ferri, D., Leoni, O., Lazzeri, L.: Transfer of calibration function in near-infrared spectroscopy. Chemom. Intell. Lab. Syst. 27(2), 189\u2013203 (1995)","journal-title":"Chemom. Intell. Lab. Syst."},{"issue":"3","key":"1118_CR27","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1007\/s41664-018-0068-2","volume":"2","author":"Y Xu","year":"2018","unstructured":"Xu, Y., Goodacre, R.: On splitting training and validation set: a comparative study of cross-validation, bootstrap and systematic sampling for estimating the generalization performance of supervised learning. J. Anal. Test. 2(3), 249\u2013262 (2018)","journal-title":"J. Anal. Test."},{"issue":"Suppl 2","key":"1118_CR28","doi-asserted-by":"publisher","first-page":"3069","DOI":"10.1007\/s10586-018-1877-9","volume":"22","author":"T Gao","year":"2019","unstructured":"Gao, T., Hu, L., Jia, Z., Xia, T., Fang, C., Li, H., Hu, L., Lu, Y., Li, H.: SPXYE: an improved method for partitioning training and validation sets. Clust. Comput. 22(Suppl 2), 3069\u20133078 (2019)","journal-title":"Clust. Comput."},{"issue":"3","key":"1118_CR29","doi-asserted-by":"publisher","DOI":"10.1007\/s11222-024-10417-5","volume":"34","author":"Y Lin","year":"2024","unstructured":"Lin, Y., Zeng, X., Wang, P., Huang, S., Teo, K.L.: Variable selection using axis-aligned random projections for partial least-squares regression. Stat. Comput. 34(3), 105 (2024)","journal-title":"Stat. Comput."}],"container-title":["International Journal of Data Science and Analytics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s41060-026-01118-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s41060-026-01118-5","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s41060-026-01118-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T06:12:22Z","timestamp":1777961542000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s41060-026-01118-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,5]]},"references-count":29,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,12]]}},"alternative-id":["1118"],"URL":"https:\/\/doi.org\/10.1007\/s41060-026-01118-5","relation":{},"ISSN":["2364-415X","2364-4168"],"issn-type":[{"value":"2364-415X","type":"print"},{"value":"2364-4168","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,5]]},"assertion":[{"value":"20 November 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 March 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 May 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that there is no conflict of interest regarding the publication of this paper.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"158"}}