{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T10:04:46Z","timestamp":1775037886593,"version":"3.50.1"},"reference-count":30,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2022,12,22]],"date-time":"2022-12-22T00:00:00Z","timestamp":1671667200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61771299, 62071286"],"award-info":[{"award-number":["61771299, 62071286"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Comput. Neurosci."],"abstract":"<jats:p>Recent RNN models deal with various dimensions of MTS as independent channels, which may lead to the loss of dependencies between different dimensions or the loss of associated information between each dimension and the global. To process MTS in a holistic way without losing the inter-relationship among dimensions, this paper proposes a novel Long-and Short-term Time-series network based on geometric algebra (GA), dubbed GA-LSTNet. Specifically, taking advantage of GA, multi-dimensional data at each time point of MTS is represented as GA multi-vectors to capture the inherent structures and preserve the correlation of those dimensions. In particular, traditional real-valued RNN, real-valued LSTM, and the back-propagation through time are extended to the GA domain. We evaluate the performance of the proposed GA-LSTNet model in prediction tasks on four well-known MTS datasets, and compared the prediction performance with other six methods. The experimental results indicate that our GA-LSTNet model outperforms traditional real-valued LSTNet with higher prediction accuracy, providing a more accurate solution for the existing shortcomings of MTS prediction models.<\/jats:p>","DOI":"10.3389\/fncom.2022.1078150","type":"journal-article","created":{"date-parts":[[2022,12,22]],"date-time":"2022-12-22T07:19:30Z","timestamp":1671693570000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Geometric algebra based recurrent neural network for multi-dimensional time-series prediction"],"prefix":"10.3389","volume":"16","author":[{"given":"Yanping","family":"Li","sequence":"first","affiliation":[]},{"given":"Yi","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Yue","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Chunhua","family":"Qian","sequence":"additional","affiliation":[]},{"given":"Rui","family":"Wang","sequence":"additional","affiliation":[]}],"member":"1965","published-online":{"date-parts":[[2022,12,22]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1703.07015","article-title":"Modeling long- and short-term temporal patterns with deep neural networks","author":"Ai","year":"2017","journal-title":"arXiv:1703.07015 [cs.LG]"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1803.01271","article-title":"An empirical evaluation of generic convolutional and recurrent networks for sequence modeling","author":"Bai","year":"2018","journal-title":"arXiv:1803.01271 [cs.LG]"},{"key":"B3","doi-asserted-by":"publisher","first-page":"1506","DOI":"10.1109\/TNN.2003.820556","article-title":"Support vector machine with adaptive parameters in financial time series forecasting","volume":"14","author":"Cao","year":"2003","journal-title":"IEEE Trans. Neural Netw"},{"key":"B4","doi-asserted-by":"publisher","first-page":"539","DOI":"10.1016\/j.jeconom.2020.07.015","article-title":"Autoregressive models for matrix-valued time series","volume":"222","author":"Chen","year":"2021","journal-title":"J. Econometr"},{"key":"B5","doi-asserted-by":"crossref","first-page":"103","DOI":"10.3115\/v1\/W14-4012","article-title":"\u201cOn the properties of neural machine translation: encoder-decoder approaches,\u201d","author":"Cho","year":"2014","journal-title":"Proceedings of SSST-8, Eighth Workshop on Syntax, Semantics and Structure in Statistical Translation"},{"key":"B6","unstructured":"\u201cLanguage modeling with gated convolutional networks,\u201d933941\n            DauphinY. N.\n            FanA.\n            AuliM.\n          35740899Proceedings of the 34th International Conference on Machine Learning, Volume 70 of ICML'172017"},{"key":"B7","doi-asserted-by":"publisher","first-page":"2102","DOI":"10.14778\/3229863.3229878","article-title":"Forecasting big time series: old and new","volume":"11","author":"Faloutsos","year":"2018","journal-title":"Proc. VLDB Endowment"},{"key":"B8","doi-asserted-by":"publisher","first-page":"817","DOI":"10.1109\/TSP.2017.2775589","article-title":"A time-vertex signal processing framework: scalable processing and meaningful representations for time-series on graphs","volume":"66","author":"Grassi","year":"2018","journal-title":"IEEE Trans. Signal Process"},{"key":"B9","doi-asserted-by":"publisher","first-page":"197","DOI":"10.2307\/2281054","article-title":"Hypothesis testing in time series analysis","volume":"49","author":"Gurland","year":"1951","journal-title":"J. Am. Stat. Assoc"},{"key":"B10","doi-asserted-by":"publisher","first-page":"3115","DOI":"10.48550\/arXiv.1307.0293","article-title":"A direct estimation of high dimensional stationary vector autoregressions","volume":"16","author":"Han","year":"2015","journal-title":"J. Mach. Learn. Res"},{"key":"B11","doi-asserted-by":"crossref","DOI":"10.1007\/978-94-009-4802-0","author":"Hestenes","year":"1986","journal-title":"New Foundations for Classical Mechanics"},{"key":"B12","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput"},{"key":"B13","first-page":"847","article-title":"\u201cTemporal regularized matrix factorization for high-dimensional time series prediction,\u201d","author":"Hsiang","year":"2016","journal-title":"NIPS'16: Proceedings of the 30th International Conference on Neural Information Processing Systems, NIPS'16"},{"key":"B14","doi-asserted-by":"publisher","first-page":"4870","DOI":"10.1109\/TSP.2019.2929930","article-title":"Forecasting time series with varma recursions on graphs","volume":"67","author":"Isufi","year":"2019","journal-title":"IEEE Trans. Signal Process"},{"key":"B15","doi-asserted-by":"publisher","first-page":"271","DOI":"10.1614\/0043-1745(2003)051[0271:KNAATE]2.0.CO;2","article-title":"Knowledge networks: an avenue to ecological management of invasive weeds","volume":"51","author":"Jordan","year":"2003","journal-title":"Weed Sci"},{"key":"B16","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1145\/3209978.3210006","article-title":"\u201cModeling long- and short-term temporal patterns with deep neural networks,\u201d","author":"Lai","year":"2018","journal-title":"SIGIR '18: The 41st International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR '18"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1707.01926","article-title":"Diffusion convolutional recurrent neural network: data-driven traffic forecasting","author":"Li","year":"2017","journal-title":"arXiv:1707.01926 [cs.LG]"},{"key":"B18","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1145\/3231541.3231544","article-title":"A brief overview of machine learning methods for short-term traffic forecasting and future directions","volume":"10","author":"Li","year":"2018","journal-title":"SIGSPATIAL Special"},{"key":"B19","doi-asserted-by":"publisher","first-page":"1045","DOI":"10.1007\/s00006-015-0589-y","article-title":"Geometric entities voting schemes in the conformal geometric algebra framework","volume":"26","author":"L\u00f3pez-Gonz\u00e1lez","year":"2016","journal-title":"Adv. Appl. Clifford Algebras"},{"key":"B20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13634-019-0631-7","article-title":"Stationary time-vertex signal processing","volume":"36","author":"Loukas","year":"2019","journal-title":"EURASIP J. Adv. Signal Process"},{"key":"B21","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1016\/j.still.2018.12.023","article-title":"A reliable linear stochastic daily soil temperature forecast model","volume":"189","author":"Mohammad","year":"2019","journal-title":"Soil Tillage Res"},{"key":"B22","doi-asserted-by":"crossref","first-page":"8519","DOI":"10.1109\/ICASSP.2019.8683583","article-title":"\u201cBidirectional quaternion long-short term memory recurrent neural networks for speech recognition,\u201d","author":"Parcollet","year":"2019","journal-title":"ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"},{"key":"B23","author":"Rafal","year":"2004","journal-title":"Lectures on Clifford (Geometric) Algebras and Applications"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1098\/rsta.2011.0550","article-title":"Gaussian processes for time-series modelling","author":"Roberts","year":"2012","journal-title":"Philos. Trans"},{"key":"B25","doi-asserted-by":"publisher","first-page":"277","DOI":"10.1109\/LGRS.2019.2918719","article-title":"Hybridsn: exploring 3-d-2-d cnn feature hierarchy for hyperspectral image classification","volume":"17","author":"Roy","year":"2020","journal-title":"IEEE Geosci. Remote Sens. Lett"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1905.03806","article-title":"Think globally, act locally: a deep neural network approach to high-dimensional time series forecasting","author":"Sen","year":"2019","journal-title":"arXiv:1905.03806 [stat.ML]"},{"key":"B27","first-page":"7796","article-title":"\u201cDeep state space models for time series forecasting,\u201d","author":"Syama","year":"2018","journal-title":"NIPS'18: Proceedings of the 32nd International Conference on Neural Information Processing Systems, NIPS'18"},{"key":"B28","first-page":"1907","article-title":"\u201cGraph wavenet for deep spatial-temporal graph modeling,\u201d","author":"Wu","year":"2019","journal-title":"IJCAI'19: Proceedings of the 28th International Joint Conference on Artificial Intelligence, IJCAI'19"},{"key":"B29","first-page":"3634","article-title":"\u201cSpatio-temporal graph convolutional networks: a deep learning framework for traffic forecasting,\u201d","author":"Yu","year":"2018","journal-title":"IJCAI'18: Proceedings of the 27th International Joint Conference on Artificial Intelligence, IJCAI'18"},{"key":"B30","doi-asserted-by":"crossref","first-page":"2141","DOI":"10.1145\/3097983.3098117","article-title":"\u201cStock price prediction via discovering multi-frequency trading patterns,\u201d","author":"Zhang","year":"2017","journal-title":"KDD '17: Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD '17"}],"container-title":["Frontiers in Computational Neuroscience"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fncom.2022.1078150\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,22]],"date-time":"2022-12-22T07:19:43Z","timestamp":1671693583000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fncom.2022.1078150\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,22]]},"references-count":30,"alternative-id":["10.3389\/fncom.2022.1078150"],"URL":"https:\/\/doi.org\/10.3389\/fncom.2022.1078150","relation":{},"ISSN":["1662-5188"],"issn-type":[{"value":"1662-5188","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,12,22]]},"article-number":"1078150"}}