{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T12:06:26Z","timestamp":1784203586376,"version":"3.55.0"},"reference-count":117,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100016152","name":"Yayasan UTP","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100016152","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005710","name":"Universiti Teknologi Petronas","doi-asserted-by":"publisher","award":["015LC0\\u2013487"],"award-info":[{"award-number":["015LC0\\u2013487"]}],"id":[{"id":"10.13039\/501100005710","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.neucom.2026.134095","type":"journal-article","created":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T07:04:20Z","timestamp":1779951860000},"page":"134095","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["A systematic literature review and taxonomy of normalization techniques in training DNNs for time-series data"],"prefix":"10.1016","volume":"696","author":[{"given":"Mujaheed","family":"Abdullahi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hitham","family":"Alhussian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Norshakirah","family":"Aziz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Said Jadid","family":"Abdulkadir","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2845-5675","authenticated-orcid":false,"given":"Sallam O.F.","family":"Khairy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1178-2522","authenticated-orcid":false,"given":"Abubakar","family":"Bala","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shamsuddeen","family":"Adamu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rabiu Bashir","family":"Yunus","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neucom.2026.134095_bib1","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2020.113868","article-title":"Clustering and classification of time series using topological data analysis with applications to finance","volume":"162","author":"Majumdar","year":"2020","journal-title":"Expert. Syst. Appl."},{"key":"10.1016\/j.neucom.2026.134095_bib2","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1016\/j.shpsa.2022.05.006","article-title":"Variety of evidence in multimessenger astronomy","volume":"94","author":"Abelson","year":"2022","journal-title":"Stud. Hist. Philos. Sci."},{"key":"10.1016\/j.neucom.2026.134095_bib3","doi-asserted-by":"crossref","DOI":"10.1016\/j.bspc.2023.104753","article-title":"A prediction model for healthcare time-series data with a mixture of deep mixed effect models using Gaussian processes","volume":"84","author":"Hong","year":"2023","journal-title":"Biomed. Signal. Process. Control."},{"key":"10.1016\/j.neucom.2026.134095_bib4","doi-asserted-by":"crossref","DOI":"10.1016\/j.oceaneng.2022.113032","article-title":"On limiting the influence of serial correlation in metocean data for prediction of extreme return levels and environmental contours","volume":"266","author":"Coe","year":"2022","journal-title":"Ocean. Eng."},{"key":"10.1016\/j.neucom.2026.134095_bib5","series-title":"Proceedings of the 27th ACM SIGKDD conference on knowledge discovery & data mining","first-page":"269","article-title":"\u201cSt-norm: Spatial and temporal normalization for multi-variate time series forecasting,\u201d","author":"Deng","year":"2021"},{"issue":"3","key":"10.1016\/j.neucom.2026.134095_bib6","doi-asserted-by":"crossref","first-page":"629","DOI":"10.1111\/rssb.12370","article-title":"Testing relevant hypotheses in functional time series via self-normalization","volume":"82","author":"Dette","year":"2020","journal-title":"J. R. Stat. Soc. Ser. B Stat. Methodol."},{"key":"10.1016\/j.neucom.2026.134095_bib7","series-title":"Digital Interaction and Machine Intelligence","first-page":"88","article-title":"Normalization and Bias in Time Series Data","author":"Asesh","year":"2022"},{"key":"10.1016\/j.neucom.2026.134095_bib8","author":"Bhanja","year":"2018","journal-title":"Impact Data Norm. Deep. Neural Netw. Time Ser. Forecast."},{"issue":"7","key":"10.1016\/j.neucom.2026.134095_bib9","doi-asserted-by":"crossref","first-page":"2262","DOI":"10.1021\/ac0519312","article-title":"Scaling and Normalization Effects in NMR Spectroscopic Metabonomic Data Sets","volume":"78","author":"Craig","year":"2006","journal-title":"Anal. Chem."},{"key":"10.1016\/j.neucom.2026.134095_bib10","series-title":"2021 National Computing Colleges Conference (NCCC)","first-page":"1","article-title":"Evaluation of Artificial Neural Networks Performance Using Various Normalization Methods for Water Demand Forecasting","author":"Al-Ghamdi","year":"2021"},{"key":"10.1016\/j.neucom.2026.134095_bib11","first-page":"1","article-title":"Forecasting financial time series using robust deep adaptive input normalization","author":"Passalis","year":"2021","journal-title":"J. Signal. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134095_bib12","series-title":"2020 25th International Conference on Pattern Recognition (ICPR)","first-page":"7287","article-title":"Data normalization for bilinear structures in high-frequency financial time-series","author":"Tran","year":"2021"},{"issue":"512","key":"10.1016\/j.neucom.2026.134095_bib13","doi-asserted-by":"crossref","first-page":"1797","DOI":"10.1080\/01621459.2015.1050493","article-title":"Self-Normalization for Time Series: A Review of Recent Developments","volume":"110","author":"Shao","year":"2015","journal-title":"J. Am. Stat. Assoc."},{"key":"10.1016\/j.neucom.2026.134095_bib14","first-page":"1","article-title":"Adaptive Normalization: A novel data normalization approach for non-stationary time series","author":"Ogasawara","year":"2010","journal-title":"2010 Int. Jt. Conf. Neural Netw. (IJCNN)"},{"issue":"8","key":"10.1016\/j.neucom.2026.134095_bib15","doi-asserted-by":"crossref","first-page":"1798","DOI":"10.1109\/TPAMI.2013.50","article-title":"Representation Learning: A Review and New Perspectives","volume":"35","author":"Bengio","year":"2013","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.neucom.2026.134095_bib16","series-title":"Proceedings of International Conference on Frontiers in Computing and Systems","first-page":"267","article-title":"Deep Neural Network for Multivariate Time-Series Forecasting","author":"Bhanja","year":"2021"},{"issue":"7","key":"10.1016\/j.neucom.2026.134095_bib17","doi-asserted-by":"crossref","first-page":"951","DOI":"10.1080\/00295450.2019.1693215","article-title":"Comparison of Multilayer Perceptron and Long Short-Term Memory for Plant Parameter Trend Prediction","volume":"206","author":"Bae","year":"2020","journal-title":"Nucl. Technol."},{"issue":"1","key":"10.1016\/j.neucom.2026.134095_bib18","doi-asserted-by":"crossref","first-page":"453","DOI":"10.1016\/j.gsf.2020.04.011","article-title":"Machine learning for pore-water pressure time-series prediction: Application of recurrent neural networks","volume":"12","author":"Wei","year":"2021","journal-title":"Geosci. Front."},{"issue":"8","key":"10.1016\/j.neucom.2026.134095_bib19","doi-asserted-by":"crossref","first-page":"10173","DOI":"10.1109\/TPAMI.2023.3250241","article-title":"Normalization Techniques in Training DNNs: Methodology, Analysis and Application","volume":"45","author":"Huang","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.neucom.2026.134095_bib20","first-page":"357","article-title":"Impact of Data Normalization on Stock Index Forecasting","volume":"6","author":"Nayak","year":"2014"},{"key":"10.1016\/j.neucom.2026.134095_bib21","doi-asserted-by":"crossref","DOI":"10.1016\/j.asoc.2019.105524","article-title":"Investigating the impact of data normalization on classification performance","volume":"97","author":"Singh","year":"2020","journal-title":"Appl. Soft Comput."},{"key":"10.1016\/j.neucom.2026.134095_bib22","series-title":"Introduction to statistical pattern recognition","author":"Fukunaga","year":"2013"},{"key":"10.1016\/j.neucom.2026.134095_bib23","doi-asserted-by":"crossref","first-page":"170","DOI":"10.21449\/ijate.479404","article-title":"The Effect of the Normalization Method Used in Different Sample Sizes on the Success of Artificial Neural Network Model","volume":"6","author":"Aksu","year":"2019","journal-title":"Int. J. Assess. Tools Educ."},{"key":"10.1016\/j.neucom.2026.134095_bib24","series-title":"Data mining: concepts and techniques","author":"Han","year":"2022"},{"key":"10.1016\/j.neucom.2026.134095_bib25","doi-asserted-by":"crossref","first-page":"183680","DOI":"10.1109\/ACCESS.2019.2959789","article-title":"Mixture of Activation Functions with Extended Min-Max Normalization for Forex Market Prediction","volume":"7","author":"Munkhdalai","year":"2019","journal-title":"IEEE Access."},{"issue":"2","key":"10.1016\/j.neucom.2026.134095_bib26","first-page":"354","article-title":"Evaluation of Normalization Techniques on Neural Networks for the Prediction of 305-Day Milk Yield","volume":"1","author":"AsliAk\u0131ll\u0131","year":"2020","journal-title":"Journal"},{"key":"10.1016\/j.neucom.2026.134095_bib27","doi-asserted-by":"crossref","first-page":"48392","DOI":"10.1109\/ACCESS.2023.3276439","article-title":"Personalized Adaptive Learning Technologies Based on Machine Learning Techniques to Identify Learning Styles: A Systematic Literature Review","volume":"11","author":"Essa","year":"2023","journal-title":"IEEE Access."},{"key":"10.1016\/j.neucom.2026.134095_bib28","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"4822","article-title":"Latent multi-task architecture learning","author":"Ruder","year":"2019"},{"issue":"16","key":"10.1016\/j.neucom.2026.134095_bib29","doi-asserted-by":"crossref","first-page":"13319","DOI":"10.1007\/s00521-022-07143-2","article-title":"A convolutional neural network based approach to financial time series prediction","volume":"34","author":"Durairaj","year":"2022","journal-title":"Neural Comput. Appl."},{"issue":"21","key":"10.1016\/j.neucom.2026.134095_bib30","doi-asserted-by":"crossref","DOI":"10.1002\/cpe.7141","article-title":"Weather parameters forecasting with time series using deep hybrid neural networks","volume":"34","author":"Yal\u00e7\u0131n","year":"2022","journal-title":"Concurr. Comput."},{"key":"10.1016\/j.neucom.2026.134095_bib31","unstructured":"Y. Wang, H. Wu, J. Dong, Y. Liu, M. Long, and J. Wang, Deep Time Series Models: A Comprehensive Survey and Benchmark, arXiv preprint arXiv:2407.13278, 2024."},{"issue":"6","key":"10.1016\/j.neucom.2026.134095_bib32","doi-asserted-by":"crossref","DOI":"10.1145\/3533382","article-title":"Deep Learning for Time Series Forecasting: Tutorial and Literature Survey","volume":"55","author":"Benidis","year":"2022","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.neucom.2026.134095_bib33","doi-asserted-by":"crossref","first-page":"120043","DOI":"10.1109\/ACCESS.2021.3107975","article-title":"Deep Learning for Anomaly Detection in Time-Series Data: Review, Analysis, and Guidelines","volume":"9","author":"Choi","year":"2021","journal-title":"IEEE Access."},{"issue":"11","key":"10.1016\/j.neucom.2026.134095_bib34","doi-asserted-by":"crossref","first-page":"7327","DOI":"10.1109\/TPAMI.2021.3116668","article-title":"Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Models","volume":"44","author":"Bond-Taylor","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.neucom.2026.134095_bib35","doi-asserted-by":"crossref","DOI":"10.1016\/j.asoc.2020.106181","article-title":"\u201cFinancial time series forecasting with deep learning: A systematic literature review: 2005\u20132019,\u201d","volume":"90","author":"Sezer","year":"2020","journal-title":"Appl. Soft Comput."},{"issue":"6","key":"10.1016\/j.neucom.2026.134095_bib36","doi-asserted-by":"crossref","first-page":"7833","DOI":"10.1109\/JSEN.2019.2923982","article-title":"A Review of Deep Learning Models for Time Series Prediction","volume":"21","author":"Han","year":"2021","journal-title":"IEEE Sens. J."},{"issue":"23","key":"10.1016\/j.neucom.2026.134095_bib37","doi-asserted-by":"crossref","first-page":"5227","DOI":"10.3390\/s19235227","article-title":"Estimating biomechanical time-series with wearable sensors: A systematic review of machine learning techniques","volume":"19","author":"Gurchiek","year":"2019","journal-title":"Sensors"},{"key":"10.1016\/j.neucom.2026.134095_bib38","doi-asserted-by":"crossref","first-page":"709","DOI":"10.1016\/j.energy.2018.09.144","article-title":"Forecasting energy consumption time series using machine learning techniques based on usage patterns of residential householders","volume":"165","author":"Chou","year":"2018","journal-title":"Energy"},{"issue":"11","key":"10.1016\/j.neucom.2026.134095_bib39","doi-asserted-by":"crossref","first-page":"100","DOI":"10.5539\/ijef.v9n11p100","article-title":"Stock market prediction performance of neural networks: A literature review","volume":"9","author":"Ican","year":"2017","journal-title":"Int. J. Econ. Financ."},{"issue":"2","key":"10.1016\/j.neucom.2026.134095_bib40","doi-asserted-by":"crossref","first-page":"1340","DOI":"10.1016\/j.rser.2011.10.015","article-title":"Applications of artificial neural networks for refrigeration, air-conditioning and heat pump systems\u2014A review","volume":"16","author":"Mohanraj","year":"2012","journal-title":"Renew. Sustain. Energy Rev."},{"key":"10.1016\/j.neucom.2026.134095_bib41","series-title":"Proceedings of the thirteenth international conference on artificial intelligence and statistics, JMLR Workshop and Conference Proceedings","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"Glorot","year":"2010"},{"issue":"12","key":"10.1016\/j.neucom.2026.134095_bib42","doi-asserted-by":"crossref","first-page":"2270","DOI":"10.1016\/j.patcog.2005.01.012","article-title":"Score normalization in multimodal biometric systems","volume":"38","author":"Jain","year":"2005","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.neucom.2026.134095_bib43","article-title":"The PRISMA 2020 statement: an updated guideline for reporting systematic reviews","volume":"372","author":"Page","year":"2021","journal-title":"BMJ"},{"issue":"2","key":"10.1016\/j.neucom.2026.134095_bib44","article-title":"PRISMA2020: An R package and Shiny app for producing PRISMA 2020-compliant flow diagrams, with interactivity for optimised digital transparency and Open Synthesis","volume":"18","author":"Haddaway","year":"2022","journal-title":"Campbell Syst. Rev."},{"key":"10.1016\/j.neucom.2026.134095_bib45","unstructured":"B. Kitchenham and S. Charters, Guidelines for performing systematic literature reviews in software engineering, 2007, UK."},{"key":"10.1016\/j.neucom.2026.134095_bib46","doi-asserted-by":"crossref","first-page":"57815","DOI":"10.1109\/ACCESS.2024.3386826","article-title":"A Comprehensive Systematic Review of YOLO for Medical Object Detection (2018\u20132023)","volume":"12","author":"Ragab","year":"2024","journal-title":"IEEE Access."},{"issue":"5","key":"10.1016\/j.neucom.2026.134095_bib47","doi-asserted-by":"crossref","DOI":"10.1016\/j.jksuci.2024.102068","article-title":"RNN-LSTM: From applications to modeling techniques and beyond\u2014Systematic review","volume":"36","author":"Al-Selwi","year":"2024","journal-title":"J. King Saud. Univ. - Comput. Inf. Sci."},{"key":"10.1016\/j.neucom.2026.134095_bib48","series-title":"Detecting Cybersecurity Attacks in Internet of Things Using Artificial Intelligence Methods: A Systematic Literature Review","author":"Abdullahi","year":"2022"},{"issue":"1","key":"10.1016\/j.neucom.2026.134095_bib49","doi-asserted-by":"crossref","first-page":"7292","DOI":"10.1038\/s41598-026-38136-z","article-title":"Application of swarm-based deep neural networks and ensemble models for reconstruction of specific conductance data","volume":"16","author":"Mahdavi-Meymand","year":"2026","journal-title":"Sci. Rep."},{"issue":"1","key":"10.1016\/j.neucom.2026.134095_bib50","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0341003","article-title":"A deep state-space analysis framework for cancer patient latent state estimation and classification from EHR time-series data","volume":"21","author":"Okamoto","year":"2026","journal-title":"PLoS. One"},{"key":"10.1016\/j.neucom.2026.134095_bib51","doi-asserted-by":"crossref","first-page":"7627","DOI":"10.1109\/JSTARS.2026.3655410","article-title":"High Performance Distributed Data Processing Architecture for AI-Based Multivariate Arctic Geospatial Predictive Weather Modeling","volume":"19","author":"Moradi","year":"2026","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote. Sens."},{"key":"10.1016\/j.neucom.2026.134095_bib52","doi-asserted-by":"crossref","first-page":"113343","DOI":"10.1109\/ACCESS.2025.3584251","article-title":"Pattern-Based Feature Extraction for Improved Deep Learning in Financial Time Series Classification","volume":"13","author":"Hosseini","year":"2025","journal-title":"IEEE Access."},{"key":"10.1016\/j.neucom.2026.134095_bib53","article-title":"A Survey on Spatio-Temporal Prediction: From Transformers to Foundation Models","author":"Mao","year":"2025","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.neucom.2026.134095_bib54","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2025.107399","article-title":"Decomposition-based multi-scale transformer framework for time series anomaly detection","volume":"187","author":"Zhang","year":"2025","journal-title":"Neural Netw."},{"key":"10.1016\/j.neucom.2026.134095_bib55","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2024.108184","article-title":"Variable scale multilayer perceptron for helicopter transmission system vibration data abnormity beyond efficient recovery","volume":"133","author":"Fan","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.neucom.2026.134095_bib56","doi-asserted-by":"crossref","DOI":"10.1016\/j.jbiomech.2024.112116","article-title":"The effect of time normalization and biomechanical signal processing techniques of ground reaction force curves on deep-learning model performance,\u201d","volume":"168","author":"Jlassi","year":"2024","journal-title":"J. Biomech."},{"issue":"4","key":"10.1016\/j.neucom.2026.134095_bib57","doi-asserted-by":"crossref","first-page":"1538","DOI":"10.1093\/comjnl\/bxad080","article-title":"\u201cCDNM: Clustering-Based Data Normalization Method For Automated Vulnerability Detection,\u201d","volume":"67","author":"Wu","year":"2024","journal-title":"Comput. J."},{"key":"10.1016\/j.neucom.2026.134095_bib58","doi-asserted-by":"crossref","first-page":"478","DOI":"10.1016\/j.neunet.2023.11.047","article-title":"A filter-augmented auto-encoder with learnable normalization for robust multivariate time series anomaly detection","volume":"170","author":"Yu","year":"2024","journal-title":"Neural Netw."},{"key":"10.1016\/j.neucom.2026.134095_bib59","series-title":"Proceedings of the 2023 13th International Conference on Communication and Network Security","first-page":"265","article-title":"Nonstationary Network Traffic Prediction With RevIN-based LSTM","author":"Liu","year":"2023"},{"issue":"5","key":"10.1016\/j.neucom.2026.134095_bib60","doi-asserted-by":"crossref","first-page":"1606","DOI":"10.1177\/0309524X221093908","article-title":"\u201cAdaptive wind data normalization to improve the performance of forecasting models,\u201d","volume":"46","author":"Patil","year":"2022","journal-title":"Wind. Eng."},{"key":"10.1016\/j.neucom.2026.134095_bib61","series-title":"2022 1st International Conference on Sustainable Technology for Power and Energy Systems (STPES)","first-page":"1","article-title":"Forecasting Nonstationary Wind Data Using Adaptive Min-Max Normalization","author":"Patel","year":"2022"},{"key":"10.1016\/j.neucom.2026.134095_bib62","doi-asserted-by":"crossref","first-page":"413","DOI":"10.1016\/j.patrec.2021.11.004","article-title":"\u201cDeep adaptive group-based input normalization for financial trading,\u201d","volume":"152","author":"Nalmpantis","year":"2021","journal-title":"Pattern Recognit. Lett."},{"key":"10.1016\/j.neucom.2026.134095_bib63","article-title":"Self-normalizing neural networks","volume":"30","author":"Klambauer","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134095_bib64","series-title":"2017 International Joint Conference on Neural Networks (IJCNN)","first-page":"1578","article-title":"Time series classification from scratch with deep neural networks: A strong baseline","author":"Wang","year":"2017"},{"key":"10.1016\/j.neucom.2026.134095_bib65","unstructured":"T. Cooijmans, N. Ballas, C. Laurent, \u00c7. G\u00fcl\u00e7ehre, and A. Courville, \u201cRecurrent batch normalization,\u201d arXiv preprint arXiv:1603.09025, 2016."},{"key":"10.1016\/j.neucom.2026.134095_bib66","doi-asserted-by":"crossref","DOI":"10.1016\/j.bdr.2023.100407","article-title":"A Large Comparison of Normalization Methods on Time Series","volume":"34","author":"Lima","year":"2023","journal-title":"Big Data Res."},{"issue":"11","key":"10.1016\/j.neucom.2026.134095_bib67","doi-asserted-by":"crossref","DOI":"10.3390\/fi12110194","article-title":"Homogeneous Data Normalization and Deep Learning: A Case Study in Human Activity Classification","volume":"12","author":"Pires","year":"2020","journal-title":"Future Internet"},{"key":"10.1016\/j.neucom.2026.134095_bib68","unstructured":"S. Ioffe, \u201cBatch normalization: Accelerating deep network training by reducing internal covariate shift,\u201d arXiv preprint arXiv:1502.03167, 2015."},{"issue":"1","key":"10.1016\/j.neucom.2026.134095_bib69","doi-asserted-by":"crossref","first-page":"5909","DOI":"10.1038\/s41598-022-09910-6","article-title":"A note on factor normalization for deep neural network models","volume":"12","author":"Qi","year":"2022","journal-title":"Sci. Rep."},{"issue":"8","key":"10.1016\/j.neucom.2026.134095_bib70","article-title":"Multivariate Temporal Convolutional Network: A Deep Neural Networks Approach for Multivariate Time Series Forecasting","volume":"8","author":"Wan","year":"2019","journal-title":"Electron. (Basel)"},{"key":"10.1016\/j.neucom.2026.134095_bib71","series-title":"2018 IEEE 5th International Conference on Data Science and Advanced Analytics (DSAA)","first-page":"90","article-title":"\u201cMultivariate Time Series Early Classification Using Multi-Domain Deep Neural Network,\u201d","author":"Huang","year":"2018"},{"key":"10.1016\/j.neucom.2026.134095_bib72","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1016\/j.egyr.2019.11.009","article-title":"Comparison of deep learning models for multivariate prediction of time series wind power generation and temperature","volume":"6","author":"Mishra","year":"2020","journal-title":"Energy Rep."},{"key":"10.1016\/j.neucom.2026.134095_bib73","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2022.108945","article-title":"Do deep neural networks contribute to multivariate time series anomaly detection?","volume":"132","author":"Audibert","year":"2022","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.neucom.2026.134095_bib74","doi-asserted-by":"crossref","first-page":"149","DOI":"10.1016\/j.patcog.2016.10.003","article-title":"Hierarchical deep neural network for multivariate regression","volume":"63","author":"Du","year":"2017","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.neucom.2026.134095_bib75","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2022.118260","article-title":"Real-time Change-Point Detection: A deep neural network-based adaptive approach for detecting changes in multivariate time series data","volume":"209","author":"Gupta","year":"2022","journal-title":"Expert. Syst. Appl."},{"key":"10.1016\/j.neucom.2026.134095_bib76","series-title":"International conference on web-age information management","first-page":"298","article-title":"Time series classification using multi-channels deep convolutional neural networks","author":"Zheng","year":"2014"},{"key":"10.1016\/j.neucom.2026.134095_bib77","unstructured":"K. Rasul, A.-S. Sheikh, I. Schuster, U. Bergmann, and R. Vollgraf, Multivariate probabilistic time series forecasting via conditioned normalizing flows, arXiv preprint arXiv:2002.06103, 2020."},{"key":"10.1016\/j.neucom.2026.134095_bib78","doi-asserted-by":"crossref","DOI":"10.1016\/j.apenergy.2023.121370","article-title":"Multivariate probabilistic forecasting of intraday electricity prices using normalizing flows","volume":"346","author":"Cramer","year":"2023","journal-title":"Appl. Energy"},{"issue":"1","key":"10.1016\/j.neucom.2026.134095_bib79","doi-asserted-by":"crossref","first-page":"19038","DOI":"10.1038\/s41598-019-55320-6","article-title":"Unsupervised Pre-training of a Deep LSTM-based Stacked Autoencoder for Multivariate Time Series Forecasting Problems","volume":"9","author":"Sagheer","year":"2019","journal-title":"Sci. Rep."},{"key":"10.1016\/j.neucom.2026.134095_bib80","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"1409","article-title":"A deep neural network for unsupervised anomaly detection and diagnosis in multivariate time series data","author":"Zhang","year":"2019"},{"key":"10.1016\/j.neucom.2026.134095_bib81","series-title":"Proceedings of the 27th ACM SIGKDD conference on knowledge discovery & data mining","first-page":"2114","article-title":"\u201cA transformer-based framework for multivariate time series representation learning,\u201d","author":"Zerveas","year":"2021"},{"key":"10.1016\/j.neucom.2026.134095_bib82","doi-asserted-by":"crossref","first-page":"1598","DOI":"10.1109\/BigData.2018.8621889","article-title":"Scalable Classification of Univariate and Multivariate Time Series","author":"Karimi-Bidhendi","year":"2018","journal-title":"2018 IEEE Int. Conf. Big Data (Big Data)"},{"issue":"2","key":"10.1016\/j.neucom.2026.134095_bib83","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0054201","article-title":"\u201cA Method for Comparing Multivariate Time Series with Different Dimensions,\u201d","volume":"8","author":"Tapinos","year":"2013","journal-title":"PLoS. One"},{"issue":"9","key":"10.1016\/j.neucom.2026.134095_bib84","first-page":"1239","article-title":"Discrete processes dynamics neural network simulation based on multivariate time series analysis with significant factors delayed influence consideration","volume":"23","author":"Barabanov","year":"2013","journal-title":"World Appl. Sci. J."},{"key":"10.1016\/j.neucom.2026.134095_bib85","doi-asserted-by":"crossref","first-page":"1105","DOI":"10.1016\/j.asoc.2014.08.020","article-title":"Training of support vector machine with the use of multivariate normalization","volume":"24","author":"Mart\u00ednez L\u00f3pez","year":"2014","journal-title":"Appl. Soft Comput."},{"key":"10.1016\/j.neucom.2026.134095_bib86","series-title":"2016 First IEEE International Conference on Computer Communication and the Internet (ICCCI)","first-page":"196","article-title":"Sensor time series association rule discovery based on modified discretization method","author":"Xue","year":"2016"},{"key":"10.1016\/j.neucom.2026.134095_bib87","article-title":"Multi-scale attention flow for probabilistic time series forecasting","author":"Feng","year":"2023","journal-title":"IEEE Trans. Knowl. Data Eng."},{"issue":"4","key":"10.1016\/j.neucom.2026.134095_bib88","doi-asserted-by":"crossref","first-page":"3832","DOI":"10.1109\/TKDE.2021.3128770","article-title":"Enhanced Bayesian Factorization With Variant Scale Partitioning for Multivariate Time Series Analysis","volume":"35","author":"Tang","year":"2023","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"10.1016\/j.neucom.2026.134095_bib89","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1016\/j.is.2015.04.007","article-title":"Time-series clustering - A decade review","volume":"53","author":"Aghabozorgi","year":"2015","journal-title":"Inf. Syst."},{"key":"10.1016\/j.neucom.2026.134095_bib90","doi-asserted-by":"crossref","first-page":"272","DOI":"10.1016\/j.inffus.2014.03.006","article-title":"Fault detection in multi-sensor networks based on multivariate time-series models and orthogonal transformations","volume":"20","author":"Serdio","year":"2014","journal-title":"Inf. Fusion."},{"key":"10.1016\/j.neucom.2026.134095_bib91","series-title":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, in KDD \u201919","first-page":"2828","article-title":"Robust Anomaly Detection for Multivariate Time Series through Stochastic Recurrent Neural Network","author":"Su","year":"2019"},{"issue":"1","key":"10.1016\/j.neucom.2026.134095_bib92","doi-asserted-by":"crossref","first-page":"6085","DOI":"10.1038\/s41598-018-24271-9","article-title":"Recurrent Neural Networks for Multivariate Time Series with Missing Values","volume":"8","author":"Che","year":"2018","journal-title":"Sci. Rep."},{"issue":"7","key":"10.1016\/j.neucom.2026.134095_bib93","first-page":"1","article-title":"An empirical survey of data augmentation for time series classification with neural networks","volume":"16","author":"Iwana Brian Kenji","year":"2021","journal-title":"PLoS. One"},{"issue":"8","key":"10.1016\/j.neucom.2026.134095_bib94","doi-asserted-by":"crossref","first-page":"852","DOI":"10.1002\/for.2543","article-title":"Benchmark dataset for mid-price forecasting of limit order book data with machine learning methods","volume":"37","author":"Ntakaris","year":"2018","journal-title":"J. Forecast."},{"key":"10.1016\/j.neucom.2026.134095_bib95","unstructured":"\u201cHeart Failure Clinical Records [Dataset] - UCI Machine Learning Repository.\u201d Accessed: Sep. 15, 2025. [Online]. Available: \u3008https:\/\/archive.ics.uci.edu\/dataset\/519\/heart+failure+clinical+records\u3009."},{"key":"10.1016\/j.neucom.2026.134095_bib96","doi-asserted-by":"crossref","first-page":"108490","DOI":"10.52202\/079017-3444","article-title":"DDN: Dual-domain dynamic normalization for non-stationary time series forecasting","volume":"37","author":"Dai","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"13","key":"10.1016\/j.neucom.2026.134095_bib97","doi-asserted-by":"crossref","DOI":"10.3390\/s22135005","article-title":"Sliding-Window Normalization to Improve the Performance of Machine-Learning Models for Real-Time Motion Prediction Using Electromyography","volume":"22","author":"Tanaka","year":"2022","journal-title":"Sensors"},{"key":"10.1016\/j.neucom.2026.134095_bib98","doi-asserted-by":"crossref","DOI":"10.1016\/j.is.2024.102515","article-title":"Adaptive sliding window normalization","volume":"129","author":"Papageorgiou","year":"2025","journal-title":"Inf. Syst."},{"key":"10.1016\/j.neucom.2026.134095_bib99","series-title":"International conference on learning representations","article-title":"Reversible instance normalization for accurate time-series forecasting against distribution shift","author":"Kim","year":"2021"},{"issue":"1","key":"10.1016\/j.neucom.2026.134095_bib100","doi-asserted-by":"crossref","first-page":"7200","DOI":"10.1038\/s41598-025-91219-1","article-title":"Using tide for rainfall runoff simulation with feature projection and reversible instance normalization","volume":"15","author":"Fang","year":"2025","journal-title":"Sci. Rep."},{"key":"10.1016\/j.neucom.2026.134095_bib101","doi-asserted-by":"crossref","unstructured":"J. Yang, TOKON: TOKenization-Optimized Normalization for time series analysis with a large language model, arXiv preprint arXiv:2502.05701, 2025.","DOI":"10.1109\/ECTI-CON64996.2025.11100774"},{"key":"10.1016\/j.neucom.2026.134095_bib102","series-title":"Findings of the Association for Computational Linguistics: EMNLP 2020","first-page":"1341","article-title":"Optimizing word segmentation for downstream task","author":"Hiraoka","year":"2020"},{"issue":"1","key":"10.1016\/j.neucom.2026.134095_bib103","doi-asserted-by":"crossref","first-page":"465","DOI":"10.1109\/TPAMI.2023.3319005","article-title":"Re-Thinking the Effectiveness of Batch Normalization and Beyond","volume":"46","author":"Peng","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.neucom.2026.134095_bib104","doi-asserted-by":"crossref","unstructured":"W. Ye, S. Deng, Q. Zou, and N. Gui, Frequency Adaptive Normalization For Non-stationary Time Series Forecasting, arXiv preprint arXiv:2409.20371, 2024.","DOI":"10.52202\/079017-0985"},{"key":"10.1016\/j.neucom.2026.134095_bib105","series-title":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"2657","article-title":"Batch normalized recurrent neural networks","author":"Laurent","year":"2016"},{"key":"10.1016\/j.neucom.2026.134095_bib106","unstructured":"J.L. Ba, J.R. Kiros, and G.E. Hinton, Layer normalization, arXiv preprint arXiv:1607.06450, 2016."},{"key":"10.1016\/j.neucom.2026.134095_bib107","series-title":"International Conference on Machine Learning","first-page":"5806","article-title":"Stabilizing gradients for deep neural networks via efficient svd parameterization","author":"Zhang","year":"2018"},{"key":"10.1016\/j.neucom.2026.134095_bib108","series-title":"Advances in Neural Information Processing Systems","article-title":"Understanding and Improving Layer Normalization","author":"Xu","year":"2019"},{"key":"10.1016\/j.neucom.2026.134095_bib109","first-page":"1","article-title":"Switchable Normalization for Learning-to-Normalize Deep Representation","author":"Luo","year":"2019","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.neucom.2026.134095_bib110","unstructured":"K. Xu, L. Chen, and S. Wang, Are KAN Effective for Identifying and Tracking Concept Drift in Time Series?, arXiv preprint arXiv:2410.10041, 2024."},{"issue":"12","key":"10.1016\/j.neucom.2026.134095_bib111","first-page":"2346","article-title":"Learning under concept drift: A review","volume":"31","author":"Lu","year":"2018","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"10.1016\/j.neucom.2026.134095_bib112","unstructured":"L. Zhao and Y. Shen, Proactive Model Adaptation Against Concept Drift for Online Time Series Forecasting, arXiv preprint arXiv:2412.08435, 2024."},{"key":"10.1016\/j.neucom.2026.134095_bib113","unstructured":"Y. Liu, G. Qin, X. Huang, J. Wang, and M. Long, Timer-XL: Long-Context Transformers for Unified Time Series Forecasting, arXiv preprint arXiv:2410.04803, 2024."},{"key":"10.1016\/j.neucom.2026.134095_bib114","unstructured":"J. Liu et al., Large language models can deliver accurate and interpretable time series anomaly detection, arXiv preprint arXiv:2405.15370, 2024."},{"key":"10.1016\/j.neucom.2026.134095_bib115","doi-asserted-by":"crossref","first-page":"58118","DOI":"10.52202\/079017-1853","article-title":"From news to forecast: Integrating event analysis in llm-based time series forecasting with reflection","volume":"37","author":"Wang","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"2","key":"10.1016\/j.neucom.2026.134095_bib116","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1145\/3715073.3715083","article-title":"Time series forecasting with llms: Understanding and enhancing model capabilities","volume":"26","author":"Tang","year":"2025","journal-title":"ACM SIGKDD Explor. Newsl."},{"issue":"10","key":"10.1016\/j.neucom.2026.134095_bib117","doi-asserted-by":"crossref","DOI":"10.3390\/math12101504","article-title":"Deep Time Series Forecasting Models: A Comprehensive Survey","volume":"12","author":"Liu","year":"2024","journal-title":"Mathematics"}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226014931?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226014931?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T11:41:47Z","timestamp":1784202107000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231226014931"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":117,"alternative-id":["S0925231226014931"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134095","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"A systematic literature review and taxonomy of normalization techniques in training DNNs for time-series data","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134095","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"134095"}}