{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T16:49:00Z","timestamp":1782233340120,"version":"3.54.5"},"reference-count":51,"publisher":"Oxford University Press (OUP)","license":[{"start":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T00:00:00Z","timestamp":1782172800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["DMS-2515104"],"award-info":[{"award-number":["DMS-2515104"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"NIH","doi-asserted-by":"publisher","award":["UG3NS140730"],"award-info":[{"award-number":["UG3NS140730"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"NIH","doi-asserted-by":"publisher","award":["R01AG080043"],"award-info":[{"award-number":["R01AG080043"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Time series classification is crucial for numerous scientific and engineering applications. In this article, we present a numerically efficient, practically competitive, and theoretically rigorous classification method for distinguishing between two classes of locally stationary time series based on their time-domain, second-order characteristics. Our approach builds on the autoregressive approximation for locally stationary time series, imposes no requirement on the training sample size, and is shown to achieve zero misclassification error rate asymptotically when the underlying time series differ only mildly in their second-order characteristics. The new method is demonstrated to outperform a variety of state-of-the-art solutions, including wavelet-based, tree-based, convolution-based methods, as well as modern deep learning methods, through intensive numerical simulations and a real electroencephalography data analysis for epilepsy classification.<\/jats:p>","DOI":"10.1093\/jrsssb\/qkag083","type":"journal-article","created":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T11:48:02Z","timestamp":1781092082000},"source":"Crossref","is-referenced-by-count":0,"title":["Structural classification of locally stationary time series based on second-order characteristics"],"prefix":"10.1093","author":[{"given":"Chen","family":"Qian","sequence":"first","affiliation":[{"name":"University of California at Davis Department of Statistics, , Davis, CA ,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiucai","family":"Ding","sequence":"additional","affiliation":[{"name":"University of California at Davis Department of Statistics, , Davis, CA ,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2962-1989","authenticated-orcid":false,"given":"Lexin","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Biostatistics and Epidemiology, University of California at Berkeley , Berkeley, CA ,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,6,23]]},"reference":[{"issue":"2","key":"2026062310483694900_qkag083-B1","doi-asserted-by":"publisher","first-page":"476","DOI":"10.1007\/s10618-015-0425-y","article-title":"Time series representation and similarity based on local autopatterns","volume":"30","author":"Baydogan","year":"2016","journal-title":"Data Mining and Knowledge Discovery"},{"issue":"11","key":"2026062310483694900_qkag083-B2","doi-asserted-by":"publisher","first-page":"2796","DOI":"10.1109\/TPAMI.2013.72","article-title":"A bag-of-features framework to classify time series","volume":"35","author":"Baydogan","year":"2013","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2026062310483694900_qkag083-B3","volume-title":"Pattern recognition and machine learning","author":"Bishop","year":"2006"},{"key":"2026062310483694900_qkag083-B4","author":"Cabello","year":"2020"},{"issue":"473","key":"2026062310483694900_qkag083-B5","doi-asserted-by":"publisher","first-page":"240","DOI":"10.1198\/016214505000000899","article-title":"Discrimination of locally stationary time series based on the excess mass functional","volume":"101","author":"Chandler","year":"2006","journal-title":"Journal of the American Statistical Association"},{"key":"2026062310483694900_qkag083-B6","doi-asserted-by":"publisher","first-page":"5549","DOI":"10.1016\/S1573-4412(07)06076-X","article-title":"Large sample sieve estimation of semi-nonparametric models","volume":"6","author":"Chen","year":"2007","journal-title":"Handbook of Econometrics"},{"issue":"6","key":"2026062310483694900_qkag083-B7","doi-asserted-by":"publisher","first-page":"2994","DOI":"10.1214\/13-AOS1182","article-title":"Covariance and precision matrix estimation for high-dimensional time series","volume":"41","author":"Chen","year":"2013","journal-title":"Annals of Statistics"},{"key":"2026062310483694900_qkag083-B8","first-page":"351","volume-title":"Locally stationary processes","author":"Dahlhaus","year":"2012"},{"issue":"2","key":"2026062310483694900_qkag083-B9","doi-asserted-by":"publisher","first-page":"1013","DOI":"10.3150\/17-BEJ1011","article-title":"Towards a general theory for nonlinear locally stationary processes","volume":"25","author":"Dahlhaus","year":"2019","journal-title":"Bernoulli"},{"issue":"5","key":"2026062310483694900_qkag083-B10","doi-asserted-by":"publisher","first-page":"1454","DOI":"10.1007\/s10618-020-00701-z","article-title":"ROCKET: Exceptionally fast and accurate time series classification using random convolutional kernels","volume":"34","author":"Dempster","year":"2020","journal-title":"Data Mining and Knowledge Discovery"},{"issue":"5","key":"2026062310483694900_qkag083-B11","doi-asserted-by":"publisher","first-page":"1779","DOI":"10.1007\/s10618-023-00939-3","article-title":"Hydra: Competing convolutional kernels for fast and accurate time series classification","volume":"37","author":"Dempster","year":"2023","journal-title":"Data Mining and Knowledge Discovery"},{"key":"2026062310483694900_qkag083-B12","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1016\/j.ins.2013.02.030","article-title":"A time series forest for classification and feature extraction","volume":"239","author":"Deng","year":"2013","journal-title":"Information Sciences"},{"issue":"495","key":"2026062310483694900_qkag083-B13","doi-asserted-by":"publisher","first-page":"1113","DOI":"10.1198\/jasa.2011.tm10811","article-title":"A measure of stationarity in locally stationary processes with applications to testing","volume":"106","author":"Dette","year":"2011","journal-title":"Journal of the American Statistical Association"},{"issue":"1","key":"2026062310483694900_qkag083-B14","doi-asserted-by":"publisher","first-page":"370","DOI":"10.1080\/07350015.2020.1819296","article-title":"Prediction in locally stationary time series","volume":"40","author":"Dette","year":"2022","journal-title":"Journal of Business & Economic Statistics"},{"issue":"4","key":"2026062310483694900_qkag083-B15","doi-asserted-by":"publisher","first-page":"2455","DOI":"10.1214\/19-AOS1894","article-title":"Estimation and inference for precision matrices of nonstationary time series","volume":"48","author":"Ding","year":"2020","journal-title":"Annals of Statistics"},{"issue":"3","key":"2026062310483694900_qkag083-B16","doi-asserted-by":"publisher","first-page":"1207","DOI":"10.1214\/23-AOS2288","article-title":"Autoregressive approximations to nonstationary time series with inference and applications","volume":"51","author":"Ding","year":"2023","journal-title":"Annals of Statistics"},{"issue":"2","key":"2026062310483694900_qkag083-B17","doi-asserted-by":"publisher","first-page":"asaf016","DOI":"10.1093\/biomet\/asaf016","article-title":"On the partial autocorrelation function for locally stationary time series: Characterization, estimation and inference","volume":"112","author":"Ding","year":"2025","journal-title":"Biometrika"},{"issue":"3","key":"2026062310483694900_qkag083-B18","doi-asserted-by":"publisher","first-page":"962","DOI":"10.1214\/009053604000000265","article-title":"Higher criticism for detecting sparse heterogeneous mixtures","volume":"32","author":"Donoho","year":"2004","journal-title":"Annals of Statistics"},{"issue":"4","key":"2026062310483694900_qkag083-B19","doi-asserted-by":"publisher","first-page":"611","DOI":"10.1111\/j.1467-9868.2006.00558.x","article-title":"Haar\u2013Fisz estimation of evolutionary wavelet spectra","volume":"68","author":"Fryzlewicz","year":"2006","journal-title":"Journal of the Royal Statistical Society: Series B, Statistical Methodology"},{"issue":"485","key":"2026062310483694900_qkag083-B20","doi-asserted-by":"publisher","first-page":"299","DOI":"10.1198\/jasa.2009.0110","article-title":"Consistent classification of nonstationary time series using stochastic wavelet representations","volume":"104","author":"Fryzlewicz","year":"2009","journal-title":"Journal of the American Statistical Association"},{"issue":"2","key":"2026062310483694900_qkag083-B21","doi-asserted-by":"publisher","first-page":"310","DOI":"10.1007\/s10618-012-0251-4","article-title":"Using derivatives in time series classification","volume":"26","author":"G\u00f3recki","year":"2013","journal-title":"Data Mining and Knowledge Discovery"},{"issue":"4","key":"2026062310483694900_qkag083-B22","doi-asserted-by":"publisher","first-page":"851","DOI":"10.1007\/s10618-013-0322-1","article-title":"Classification of time series by shapelet transformation","volume":"28","author":"Hills","year":"2014","journal-title":"Data Mining and Knowledge Discovery"},{"issue":"467","key":"2026062310483694900_qkag083-B23","doi-asserted-by":"publisher","first-page":"763","DOI":"10.1198\/016214504000001105","article-title":"Discrimination and classification of nonstationary time series using the SLEX model","volume":"99","author":"Huang","year":"2004","journal-title":"Journal of the American Statistical Association"},{"issue":"4","key":"2026062310483694900_qkag083-B24","doi-asserted-by":"publisher","first-page":"917","DOI":"10.1007\/s10618-019-00619-1","article-title":"Deep learning for time series classification: A review","volume":"33","author":"Ismail Fawaz","year":"2019","journal-title":"Data Mining and Knowledge Discovery"},{"issue":"4","key":"2026062310483694900_qkag083-B25","doi-asserted-by":"publisher","first-page":"969","DOI":"10.1111\/rssc.12563","article-title":"Analysing cycling sensors data through ordinal logistic regression with functional covariates","volume":"71","author":"Jacques","year":"2022","journal-title":"Journal of the Royal Statistical Society Series: Applied Statistics"},{"issue":"9","key":"2026062310483694900_qkag083-B26","doi-asserted-by":"publisher","first-page":"2231","DOI":"10.1016\/j.patcog.2010.09.022","article-title":"Weighted dynamic time warping for time series classification","volume":"44","author":"Jeong","year":"2011","journal-title":"Pattern Recognition"},{"issue":"17","key":"2026062310483694900_qkag083-B27","doi-asserted-by":"publisher","first-page":"e1750","DOI":"10.1212\/WNL.0000000000207127","article-title":"Development of expert-level classification of seizures and rhythmic and periodic patterns during eeg interpretation","volume":"100","author":"Jing","year":"2023","journal-title":"Neurology"},{"issue":"2","key":"2026062310483694900_qkag083-B28","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1007\/s10618-015-0418-x","article-title":"Using dynamic time warping distances as features for improved time series classification","volume":"30","author":"Kate","year":"2016","journal-title":"Data Mining and Knowledge Discovery"},{"key":"2026062310483694900_qkag083-B29","doi-asserted-by":"publisher","first-page":"108681","DOI":"10.1016\/j.compbiomed.2024.108681","article-title":"Reaching the ceiling? Empirical scaling behaviour for deep eeg pathology classification","volume":"178","author":"Kiessner","year":"2024","journal-title":"Computers in Biology and Medicine"},{"issue":"2","key":"2026062310483694900_qkag083-B30","doi-asserted-by":"publisher","first-page":"3710","DOI":"10.1214\/19-EJS1606","article-title":"Predictive, finite-sample model choice for time series under stationarity and non-stationarity","volume":"13","author":"Kley","year":"2019","journal-title":"Electronic Journal of Statistics"},{"issue":"4","key":"2026062310483694900_qkag083-B31","doi-asserted-by":"publisher","first-page":"435","DOI":"10.1111\/jtsa.12166","article-title":"Discriminant analysis of time series in the presence of within-group spectral variability","volume":"37","author":"Krafty","year":"2016","journal-title":"Journal of Time Series Analysis"},{"issue":"1","key":"2026062310483694900_qkag083-B32","doi-asserted-by":"publisher","first-page":"144","DOI":"10.1002\/sta4.51","article-title":"Classification of non-stationary time series","volume":"3","author":"Krzemieniewska","year":"2014","journal-title":"Stat"},{"issue":"3","key":"2026062310483694900_qkag083-B33","doi-asserted-by":"publisher","first-page":"565","DOI":"10.1007\/s10618-014-0361-2","article-title":"Time series classification with ensembles of elastic distance measures","volume":"29","author":"Lines","year":"2015","journal-title":"Data Mining and Knowledge Discovery"},{"key":"2026062310483694900_qkag083-B34","first-page":"289","volume-title":"Proceedings of the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","author":"Lines","year":"2012"},{"issue":"2","key":"2026062310483694900_qkag083-B35","doi-asserted-by":"publisher","first-page":"879","DOI":"10.1016\/j.csda.2007.05.010","article-title":"Discrimination of locally stationary time series using wavelets","volume":"52","author":"Maharaj","year":"2007","journal-title":"Computational Statistics & Data Analysis"},{"key":"2026062310483694900_qkag083-B36","doi-asserted-by":"crossref","DOI":"10.1201\/9780429058264","volume-title":"Time series clustering and classification","author":"Maharaj","year":"2019"},{"issue":"2","key":"2026062310483694900_qkag083-B37","doi-asserted-by":"publisher","first-page":"306","DOI":"10.1109\/TPAMI.2008.76","article-title":"Time warp edit distance with stiffness adjustment for time series matching","volume":"31","author":"Marteau","year":"2008","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"5","key":"2026062310483694900_qkag083-B38","doi-asserted-by":"publisher","first-page":"879","DOI":"10.1111\/rssb.12015","article-title":"A test for second-order stationarity and approximate confidence intervals for localized autocovariances for locally stationary time series","volume":"75","author":"Nason","year":"2013","journal-title":"Journal of the Royal Statistical Society: Series B, Statistical Methodology"},{"issue":"2","key":"2026062310483694900_qkag083-B39","doi-asserted-by":"publisher","first-page":"271","DOI":"10.1111\/1467-9868.00231","article-title":"Wavelet processes and adaptive estimation of the evolutionary wavelet spectrum","volume":"62","author":"Nason","year":"2000","journal-title":"Journal of the Royal Statistical Society: Series B, Statistical Methodology"},{"key":"2026062310483694900_qkag083-B40","doi-asserted-by":"publisher","first-page":"196","DOI":"10.3389\/fnins.2016.00196","article-title":"The temple university hospital EEG data corpus","volume":"1","author":"Obeid","year":"2016","journal-title":"Frontiers in Neuroscience"},{"issue":"2","key":"2026062310483694900_qkag083-B41","doi-asserted-by":"publisher","first-page":"1215","DOI":"10.30757\/ALEA.v15-45","article-title":"Prediction of weakly locally stationary processes by auto-regression","volume":"15","author":"Roueff","year":"2018","journal-title":"Latin American Journal of Probability and Mathematical Statistics"},{"issue":"2","key":"2026062310483694900_qkag083-B42","doi-asserted-by":"publisher","first-page":"282","DOI":"10.1016\/j.jmva.2003.08.002","article-title":"Discriminant analysis for locally stationary processes","volume":"90","author":"Sakiyama","year":"2004","journal-title":"Journal of Multivariate Analysis"},{"key":"2026062310483694900_qkag083-B43","doi-asserted-by":"publisher","first-page":"132306","DOI":"10.1016\/j.physd.2019.132306","article-title":"Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network","volume":"40","author":"Sherstinsky","year":"2020","journal-title":"Physica D: Nonlinear Phenomena"},{"key":"2026062310483694900_qkag083-B44","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-70584-7","volume-title":"Time series analysis and its applications","author":"Shumway","year":"2025"},{"issue":"5","key":"2026062310483694900_qkag083-B45","doi-asserted-by":"publisher","first-page":"1623","DOI":"10.1007\/s10618-022-00844-1","article-title":"MultiRocket: Multiple pooling operators and transformations for fast and effective time series classification","volume":"36","author":"Tan","year":"2022","journal-title":"Data Mining and Knowledge Discovery"},{"issue":"5","key":"2026062310483694900_qkag083-B46","doi-asserted-by":"publisher","first-page":"2601","DOI":"10.1214\/12-AOS1043","article-title":"Nonparametric regression for locally stationary time series","volume":"40","author":"Vogt","year":"2012","journal-title":"Annals of Statistics"},{"issue":"40","key":"2026062310483694900_qkag083-B47","doi-asserted-by":"publisher","first-page":"14150","DOI":"10.1073\/pnas.0506715102","article-title":"Nonlinear system theory: Another look at dependence","volume":"102","author":"Wu","year":"2005","journal-title":"Proceedings of the National Academy of Sciences"},{"key":"2026062310483694900_qkag083-B48","first-page":"2261","article-title":"High dimensional inverse covariance matrix estimation via linear programming","volume":"11(79)","author":"Yuan","year":"2010","journal-title":"Journal of Machine Learning Research"},{"issue":"502","key":"2026062310483694900_qkag083-B49","doi-asserted-by":"publisher","first-page":"726","DOI":"10.1080\/01621459.2013.787184","article-title":"Heteroscedasticity and autocorrelation robust structural change detection","volume":"108","author":"Zhou","year":"2013","journal-title":"Journal of the American Statistical Association"},{"issue":"4","key":"2026062310483694900_qkag083-B50","doi-asserted-by":"publisher","first-page":"508","DOI":"10.1111\/jtsa.12028","article-title":"Inference for non-stationary time-series autoregression","volume":"34","author":"Zhou","year":"2013","journal-title":"Journal of Time Series Analysis"},{"key":"2026062310483694900_qkag083-B51","doi-asserted-by":"publisher","first-page":"2696","DOI":"10.1214\/08-AOS636","article-title":"Local linear quantile estimation for non-stationary time series","volume":"3","author":"Zhou","year":"2009","journal-title":"Annals of Statistics"}],"container-title":["Journal of the Royal Statistical Society Series B: Statistical Methodology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jrsssb\/advance-article-pdf\/doi\/10.1093\/jrsssb\/qkag083\/68584361\/qkag083.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jrsssb\/advance-article-pdf\/doi\/10.1093\/jrsssb\/qkag083\/68584361\/qkag083.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T15:56:22Z","timestamp":1782230182000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jrsssb\/advance-article\/doi\/10.1093\/jrsssb\/qkag083\/8713844"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,23]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1093\/jrsssb\/qkag083","relation":{},"ISSN":["1369-7412","1467-9868"],"issn-type":[{"value":"1369-7412","type":"print"},{"value":"1467-9868","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,23]]},"article-number":"qkag083"}}