{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T01:26:02Z","timestamp":1788917162846,"version":"build-2803163510"},"reference-count":33,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2022,12,21]],"date-time":"2022-12-21T00:00:00Z","timestamp":1671580800000},"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":["61472095"],"award-info":[{"award-number":["61472095"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["LH2020F023"],"award-info":[{"award-number":["LH2020F023"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005046","name":"Natural Science Foundation of Heilongjiang Province","doi-asserted-by":"publisher","award":["61472095"],"award-info":[{"award-number":["61472095"]}],"id":[{"id":"10.13039\/501100005046","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005046","name":"Natural Science Foundation of Heilongjiang Province","doi-asserted-by":"publisher","award":["LH2020F023"],"award-info":[{"award-number":["LH2020F023"]}],"id":[{"id":"10.13039\/501100005046","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Entropy"],"abstract":"<jats:p>Multivariate time series prediction models perform the required operation on a specific window length of a given input. However, capturing complex and nonlinear interdependencies in each temporal window remains challenging. The typical attention mechanisms assign a weight for a variable at the same time or the features of each previous time step to capture spatio-temporal correlations. However, it fails to directly extract each time step\u2019s relevant features that affect future values to learn the spatio-temporal pattern from a global perspective. To this end, a temporal window attention-based window-dependent long short-term memory network (TWA-WDLSTM) is proposed to enhance the temporal dependencies, which exploits the encoder\u2013decoder framework. In the encoder, we design a temporal window attention mechanism to select relevant exogenous series in a temporal window. Furthermore, we introduce a window-dependent long short-term memory network (WDLSTM) to encode the input sequences in a temporal window into a feature representation and capture very long term dependencies. In the decoder, we use WDLSTM to generate the prediction values. We applied our model to four real-world datasets in comparison to a variety of state-of-the-art models. The experimental results suggest that TWA-WDLSTM can outperform comparison models. In addition, the temporal window attention mechanism has good interpretability. We can observe which variable contributes to the future value.<\/jats:p>","DOI":"10.3390\/e25010010","type":"journal-article","created":{"date-parts":[[2022,12,22]],"date-time":"2022-12-22T01:33:12Z","timestamp":1671672792000},"page":"10","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["A Temporal Window Attention-Based Window-Dependent Long Short-Term Memory Network for Multivariate Time Series Prediction"],"prefix":"10.3390","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9712-7678","authenticated-orcid":false,"given":"Shuang","family":"Han","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, Harbin Engineering University, Harbin 150001, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongbin","family":"Dong","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Harbin Engineering University, Harbin 150001, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2022,12,21]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"162","DOI":"10.1016\/j.neucom.2022.06.014","article-title":"Temporal self-attention-based Conv-LSTM network for multivariate time series prediction","volume":"501","author":"Fu","year":"2022","journal-title":"Neurocomputing"},{"key":"ref_2","unstructured":"Kamarthi, H., Rodr\u00edguez, A., and Prakash, B.A. (2022, January 25\u201329). Back2Future: Leveraging Backfill Dynamics for Improving Real-time Predictions in Future. Proceedings of the Tenth International Conference on Learning Representations, Virtual."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"107416","DOI":"10.1016\/j.knosys.2021.107416","article-title":"Spatio-attention embedded recurrent neural network for air quality prediction","volume":"233","author":"Huang","year":"2021","journal-title":"Knowl. Based Syst."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"117011","DOI":"10.1016\/j.eswa.2022.117011","article-title":"Multi-scale temporal features extraction based graph convolutional network with attention for multivariate time series prediction","volume":"200","author":"Chen","year":"2022","journal-title":"Expert Syst. Appl."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1421","DOI":"10.1007\/s10994-019-05815-0","article-title":"Temporal pattern attention for multivariate time series forecasting","volume":"108","author":"Shih","year":"2019","journal-title":"Mach. Learn."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"300","DOI":"10.1016\/j.isatra.2021.07.013","article-title":"Modeling the stochastic mechanism of sensor using a hybrid method based on seasonal autoregressive integrated moving average time series and generalized estimating equations","volume":"125","author":"Mahmoudi","year":"2022","journal-title":"ISA Trans."},{"key":"ref_7","first-page":"1","article-title":"Do confidence indicators lead Greek economic activity ?","volume":"8","author":"Dimitrios","year":"2021","journal-title":"Bull. Appl. Econ."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"118791","DOI":"10.1016\/j.energy.2020.118791","article-title":"Forecast of electricity consumption in the Cameroonian residential sector by Grey and vector autoregressive models","volume":"214","author":"Guefano","year":"2021","journal-title":"Energy"},{"key":"ref_9","first-page":"1","article-title":"A Hidden Markov Model-based fuzzy modeling of multivariate time series","volume":"6","author":"Li","year":"2022","journal-title":"Soft Comput."},{"key":"ref_10","doi-asserted-by":"crossref","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":"ref_11","doi-asserted-by":"crossref","first-page":"102906","DOI":"10.1016\/j.resourpol.2022.102906","article-title":"Medium- to long-term nickel price forecasting using LSTM and GRU networks","volume":"78","author":"Ozdemir","year":"2022","journal-title":"Resour. Policy"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"107377","DOI":"10.1016\/j.asoc.2021.107377","article-title":"Correlational graph attention-based Long Short-Term Memory network for multivariate time series prediction","volume":"106","author":"Han","year":"2021","journal-title":"Appl. Soft Comput."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Qin, Y., Song, D., Cheng, H., Cheng, W., Jiang, G., and Cottrell, G.W. (2017). A dual-stage attention-based recurrent neural network for time series prediction. IJCAI Int. Jt. Conf. Artif. Intell., 2627\u20132633.","DOI":"10.24963\/ijcai.2017\/366"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"122","DOI":"10.1016\/j.neucom.2019.11.060","article-title":"Multistage attention network for multivariate time series prediction","volume":"383","author":"Hu","year":"2020","journal-title":"Neurocomputing"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"121360","DOI":"10.1016\/j.energy.2021.121360","article-title":"State-of-charge estimation of lithium-ion battery based on clockwork recurrent neural network","volume":"236","author":"Feng","year":"2021","journal-title":"Energy"},{"key":"ref_16","unstructured":"Zhang, Y., Peng, N., Dai, M., Zhang, J., and Wang, H. (2021, January 2\u20139). Memory-Gated Recurrent Networks. Proceedings of the AAAI Conference on Artificial Intelligence, Virtual."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Ma, Q., Lin, Z., Chen, E., and Cottrell, G.W. (2020, January 7\u201312). Temporal pyramid recurrent neural network. Proceedings of the 34th AAAI Conference on Artificial Intelligence, New York, NY, USA.","DOI":"10.1609\/aaai.v34i04.5947"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"96","DOI":"10.1038\/s41597-019-0103-9","article-title":"Multitask learning and benchmarking with clinical time series data","volume":"6","author":"Harutyunyan","year":"2019","journal-title":"Sci. Data"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Zhang, C., Fiore, M., Murray, I., and Patras, P. (2021, January 2\u20139). CloudLSTM: A Recurrent Neural Model for Spatiotemporal Point-cloud Stream Forecasting. Proceedings of the 35th AAAI Conference on Artificial Intelligence, Virtual.","DOI":"10.1609\/aaai.v35i12.17296"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"e196972","DOI":"10.1001\/jamanetworkopen.2019.6972","article-title":"Development and Validation of a Deep Learning Algorithm for Mortality Prediction in Selecting Patients with Dementia for Earlier Palliative Care Interventions","volume":"2","author":"Wang","year":"2019","journal-title":"JAMA Netw. Open"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"113082","DOI":"10.1016\/j.eswa.2019.113082","article-title":"DSTP-RNN: A dual-stage two-phase attention-based recurrent neural networks for long-term and multivariate time series prediction","volume":"143","author":"Liu","year":"2020","journal-title":"Expert Syst. Appl."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Liang, Y., Ke, S., Zhang, J., Yi, X., and Zheng, Y. (2018, January 13\u201319). Geoman: Multi-level attention networks for geo-sensory time series prediction. Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, Stockholm, Sweden.","DOI":"10.24963\/ijcai.2018\/476"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Deng, A., and Hooi, B. (2021, January 2\u20139). Graph Neural Network-Based Anomaly Detection in Multivariate Time Series. Proceedings of the 35th AAAI Conference on Artificial Intelligence, Virtual.","DOI":"10.1609\/aaai.v35i5.16523"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"109317","DOI":"10.1016\/j.asoc.2022.109317","article-title":"A dual-stage advanced deep learning algorithm for long-term and long-sequence prediction for multivariate financial time series","volume":"126","author":"Preeti","year":"2022","journal-title":"Appl. Soft Comput."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1016\/j.neucom.2019.05.023","article-title":"Multiple convolutional neural networks for multivariate time series prediction","volume":"360","author":"Wang","year":"2019","journal-title":"Neurocomputing"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Wu, Z., Pan, S., Long, G., Jiang, J., Chang, X., and Zhang, C. (2020, January 6\u201310). Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks. Proceedings of the 26th ACM SIGKDD international conference on knowledge discovery & data mining, Virtual.","DOI":"10.1145\/3394486.3403118"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Lai, G., Chang, W.C., Yang, Y., and Liu, H. (2018, January 8\u201312). Modeling long- and short-term temporal patterns with deep neural networks. Proceedings of the 41st international ACM SIGIR conference on research & development in information retrieval, SIGIR 2018, Ann Arbor, MI, USA.","DOI":"10.1145\/3209978.3210006"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1016\/j.ins.2022.07.125","article-title":"A spatio-temporal sequence-to-sequence network for traffic flow prediction","volume":"610","author":"Cao","year":"2022","journal-title":"Inf. Sci."},{"key":"ref_29","unstructured":"De Br\u00e9bisson, A., and Vincent, P. (2015). An exploration of softmax alternatives belonging to the spherical loss family. 4th Int. Conf. Learn. Represent. arXiv."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Siami-Namini, S., Tavakoli, N., and Namin, A.S. (2018, January 17\u201320). A Comparison of ARIMA and LSTM in Forecasting Time Series. Proceedings of the 17th IEEE International Conference on Machine Learning and Applications (ICMLA), Orlando, FL, USA.","DOI":"10.1109\/ICMLA.2018.00227"},{"key":"ref_31","unstructured":"Gers, F. Long Short-Term Memory in Recurrent Neural Networks. Volume 2366."},{"key":"ref_32","unstructured":"Chang, Y.-Y., Sun, F.-Y., Wu, Y.-H., and Lin, S.-D. (2018). A Memory-Network Based Solution for Multivariate Time-Series Forecasting. arXiv."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"2036","DOI":"10.1002\/int.22370","article-title":"A dual-stage attention-based Conv-LSTM network for spatio-temporal correlation and multivariate time series prediction","volume":"36","author":"Xiao","year":"2021","journal-title":"Int. J. Intell. Syst."}],"container-title":["Entropy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1099-4300\/25\/1\/10\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T01:45:31Z","timestamp":1760147131000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1099-4300\/25\/1\/10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,21]]},"references-count":33,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,1]]}},"alternative-id":["e25010010"],"URL":"https:\/\/doi.org\/10.3390\/e25010010","relation":{},"ISSN":["1099-4300"],"issn-type":[{"value":"1099-4300","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,12,21]]}}}