{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T20:29:00Z","timestamp":1787257740001,"version":"build-2736575974"},"reference-count":52,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62476250"],"award-info":[{"award-number":["62476250"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Expert Systems with Applications"],"published-print":{"date-parts":[[2027,1]]},"DOI":"10.1016\/j.eswa.2026.133986","type":"journal-article","created":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T23:30:15Z","timestamp":1786663815000},"page":"133986","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PC","title":["CQMTformer: Channel query enhanced Mamba-transformer fusion architecture for multivariate time series forecasting"],"prefix":"10.1016","volume":"333","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-1854-9728","authenticated-orcid":false,"given":"Junyu","family":"Jin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-3075-2684","authenticated-orcid":false,"given":"Bensheng","family":"Yun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-5344-2754","authenticated-orcid":false,"given":"Zhenyu","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9968-4894","authenticated-orcid":false,"given":"Xiaofeng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.eswa.2026.133986_bib0001","unstructured":"Bai, S., Kolter, J. Z., & Koltun, V. (2018). An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv preprint arXiv: 1803.01271."},{"key":"10.1016\/j.eswa.2026.133986_sbref0002","doi-asserted-by":"crossref","first-page":"107547","DOI":"10.52202\/079017-3417","article-title":"XLSTM: Extended long short-term memory","volume":"37","author":"Beck","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.133986_bib0003","unstructured":"Cai, X., Zhu, Y., Wang, X., & Yao, Y. (2024). MambaTS: Improved selective state space models for long-term time series forecasting. arXiv preprint arXiv: 2405.16440."},{"key":"10.1016\/j.eswa.2026.133986_sbref0025","doi-asserted-by":"crossref","first-page":"72","DOI":"10.1016\/j.knosys.2019.03.011","article-title":"An intelligent hybridization of ARIMA with machine learning models for time series forecasting","volume":"175","author":"de O. Santos","year":"2019","journal-title":"Knowledge-Based Systems"},{"key":"10.1016\/j.eswa.2026.133986_sbref0004","series-title":"Proceedings of the 33rd ACM international conference on information and knowledge management","first-page":"446","article-title":"Drformer:Multi-scale transformer utilizing diverse receptive fields for long time-series forecasting","author":"Ding","year":"2024"},{"key":"10.1016\/j.eswa.2026.133986_sbref0005","series-title":"First conference on language modeling","article-title":"Mamba:Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2024"},{"key":"10.1016\/j.eswa.2026.133986_sbref0006","doi-asserted-by":"crossref","DOI":"10.1016\/j.physa.2026.131363","article-title":"Self-attention vector output similarities reveal how machines pay attention","author":"Halevi","year":"2026","journal-title":"Physica A: Statistical Mechanics and its Applications"},{"key":"10.1016\/j.eswa.2026.133986_bib0008","doi-asserted-by":"crossref","unstructured":"Hankemeier, V., & Hankemeier, M. (2026). Stochastic parroting in temporal attention\u2013regulating the diagonal sink. arXiv preprint arXiv: 2602.10956.","DOI":"10.14428\/esann\/2026.ES2026-150"},{"key":"10.1016\/j.eswa.2026.133986_bib0009","unstructured":"Hu, Y., Zhang, G., Liu, P., Lan, D., Li, N., Cheng, D., Dai, T., Xia, S.-T., & Pan, S. (2025). TimeFilter: Patch-specific spatial-temporal graph filtration for time series forecasting. arXiv preprint arXiv: 2501.13041."},{"issue":"7","key":"10.1016\/j.eswa.2026.133986_sbref0009","doi-asserted-by":"crossref","first-page":"216","DOI":"10.1007\/s10462-025-11223-9","article-title":"A comprehensive survey of deep learning for time series forecasting: Architectural diversity and open challenges","volume":"58","author":"Kim","year":"2025","journal-title":"Artificial Intelligence Review"},{"key":"10.1016\/j.eswa.2026.133986_sbref0010","series-title":"International conference on learning representations","article-title":"Reversible instance normalization for accurate time-series forecasting against distribution shift","author":"Kim","year":"2021"},{"key":"10.1016\/j.eswa.2026.133986_bib0012","unstructured":"Kitaev, N., Kaiser, \u0141., & Levskaya, A. (2020). Reformer: The efficient transformer. arXiv preprint arXiv: 2001.04451."},{"key":"10.1016\/j.eswa.2026.133986_sbref0012","series-title":"The 41st international ACM SIGIR conference on research & development in information retrieval","first-page":"95","article-title":"Modeling long-and short-term temporal patterns with deep neural networks","author":"Lai","year":"2018"},{"key":"10.1016\/j.eswa.2026.133986_bib0014","doi-asserted-by":"crossref","unstructured":"Lee, M., Yoon, H., & Kang, M. (2025). Casa: CNN autoencoder-based score attention for efficient multivariate long-term time-series forecasting. arXiv preprint arXiv: 2505.02011.","DOI":"10.24963\/ijcai.2025\/619"},{"key":"10.1016\/j.eswa.2026.133986_bib0015","unstructured":"Li, C., Li, M., & Diao, R. (2025). TVNet: A novel time series analysis method based on dynamic convolution and 3D-variation. arXiv preprint arXiv: 2503.07674."},{"key":"10.1016\/j.eswa.2026.133986_bib0016","unstructured":"Liang, A., Jiang, X., Sun, Y., Shi, X., & Li, K. (2024). Bi-Mamba+: Bidirectional Mamba for time series forecasting. arXiv preprint arXiv: 2404.15772."},{"key":"10.1016\/j.eswa.2026.133986_bib0017","unstructured":"Liang, Z., Zhu, J., & Sun, W. (2025). Why attention fails: The degeneration of transformers into mlps in time series forecasting. arXiv preprint arXiv: 2509.20942."},{"key":"10.1016\/j.eswa.2026.133986_bib0018","unstructured":"Lin, S., Chen, H., Wu, H., Qiu, C., & Lin, W. (2025). Temporal query network for efficient multivariate time series forecasting. arXiv preprint arXiv: 2505.12917."},{"key":"10.1016\/j.eswa.2026.133986_sbref0018","doi-asserted-by":"crossref","first-page":"106315","DOI":"10.52202\/079017-3373","article-title":"CycleNet: Enhancing time series forecasting through modeling periodic patterns","volume":"37","author":"Lin","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.133986_sbref0019","series-title":"International conference on learning representations","article-title":"Pyraformer: Low-complexity pyramidal attention for long-range time series modeling and forecasting","author":"Liu","year":"2021"},{"key":"10.1016\/j.eswa.2026.133986_bib0021","unstructured":"Liu, Y., Hu, T., Zhang, H., Wu, H., Wang, S., Ma, L., & Long, M. (2023). Inverted transformers are effective for time series forecasting. arXiv preprint arXiv: 2310.06625https:\/\/openreview.net\/forum?id=JePfAI8fah&utm_source=www.turingpost.com&utm_medium=referral&utm_campaign=a-list-of-time-series-foundation-models."},{"key":"10.1016\/j.eswa.2026.133986_sbref0021","doi-asserted-by":"crossref","first-page":"9881","DOI":"10.52202\/068431-0718","article-title":"non-stationary transformers: Exploring the stationarity in time series forecasting","volume":"35","author":"Liu","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.133986_bib0023","unstructured":"Liu, Z., Wang, Y., Vaidya, S., Ruehle, F., Halverson, J., Solja\u010di\u0107, M., Hou, T. Y., & Tegmark, M. (2024). KAN: Kolmogorov-Arnold networks. arXiv preprint arXiv: 2404.19756."},{"key":"10.1016\/j.eswa.2026.133986_sbref0023","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111499","article-title":"Multimodal urban traffic flow prediction based on multi-scale time series imaging","volume":"164","author":"Lv","year":"2025","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.eswa.2026.133986_bib0025","unstructured":"Nie, Y., Nguyen, N. H., Sinthong, P., & Kalagnanam, J. (2022). A time series is worth 64 words: Long-term forecasting with transformers. arXiv preprint arXiv: 2211.14730."},{"key":"10.1016\/j.eswa.2026.133986_sbref0026","doi-asserted-by":"crossref","DOI":"10.1016\/j.health.2026.100447","article-title":"An analytics framework for graph-based anomaly detection in healthcare time series","author":"Okano","year":"2026","journal-title":"Healthcare Analytics"},{"key":"10.1016\/j.eswa.2026.133986_sbref0027","doi-asserted-by":"crossref","first-page":"397","DOI":"10.1016\/j.future.2023.12.021","article-title":"Pattern sequence-based algorithm for multivariate big data time series forecasting: Application to electricity consumption","volume":"154","author":"P\u00e9rez-Chac\u00f3n","year":"2024","journal-title":"Future Generation Computer Systems"},{"issue":"3","key":"10.1016\/j.eswa.2026.133986_sbref0028","doi-asserted-by":"crossref","first-page":"705","DOI":"10.1016\/j.ijforecast.2021.11.001","article-title":"Forecasting: Theory and practice","volume":"38","author":"Petropoulos","year":"2022","journal-title":"International Journal of Forecasting"},{"key":"10.1016\/j.eswa.2026.133986_sbref0029","series-title":"Proceedings of the 30th ACM SIGKDD conference on knowledge discovery and data mining","first-page":"2400","article-title":"Fredformer: Frequency debiased transformer for time series forecasting","author":"Piao","year":"2024"},{"key":"10.1016\/j.eswa.2026.133986_sbref0030","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"12640","article-title":"Unlocking the power of patch: Patch-based mlp for long-term time series forecasting","volume":"vol. 39","author":"Tang","year":"2025"},{"key":"10.1016\/j.eswa.2026.133986_sbref0031","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.133986_bib0032","unstructured":"Vasylenko, P., Pitorro, H., Martins, A. F. T., & Treviso, M. (2025). Long-context generalization with sparse attention. arXiv preprint arXiv: 2506.16640."},{"key":"10.1016\/j.eswa.2026.133986_sbref0033","series-title":"The eleventh international conference on learning representations","article-title":"MICN: Multi-scale local and global context modeling for long-term series forecasting","author":"Wang","year":"2023"},{"key":"10.1016\/j.eswa.2026.133986_bib0034","unstructured":"Wang, S., Li, J., Shi, X., Ye, Z., Mo, B., Lin, W., Ju, S., Chu, Z., & Jin, M. (2024a). TimeMixer++: A general time series pattern machine for universal predictive analysis. arXiv preprint arXiv: 2410.16032."},{"key":"10.1016\/j.eswa.2026.133986_bib0035","unstructured":"Wang, S., Wu, H., Shi, X., Hu, T., Luo, H., Ma, L., Zhang, J. Y., & Zhou, J. (2024b). TimeMixer: Decomposable multiscale mixing for time series forecasting. arXiv preprint arXiv: 2405.14616."},{"issue":"3","key":"10.1016\/j.eswa.2026.133986_sbref0036","doi-asserted-by":"crossref","first-page":"1163","DOI":"10.1016\/j.ijforecast.2022.05.001","article-title":"Distributed ARIMA models for ultra-long time series","volume":"39","author":"Wang","year":"2023","journal-title":"International Journal of Forecasting"},{"key":"10.1016\/j.eswa.2026.133986_sbref0037","doi-asserted-by":"crossref","first-page":"469","DOI":"10.52202\/079017-0015","article-title":"Timexer: Empowering transformers for time series forecasting with exogenous variables","volume":"37","author":"Wang","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.133986_sbref0038","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.129178","article-title":"Is Mamba effective for time series forecasting?","volume":"619","author":"Wang","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.eswa.2026.133986_bib0039","unstructured":"Wu, H., Hu, T., Liu, Y., Zhou, H., Wang, J., & Long, M. (2022). TimesNet: Temporal 2CD-variation modeling for general time series analysis. arXiv preprint arXiv: 2210.02186."},{"key":"10.1016\/j.eswa.2026.133986_sbref0040","first-page":"22419","article-title":"Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting","volume":"34","author":"Wu","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"23","key":"10.1016\/j.eswa.2026.133986_sbref0041","doi-asserted-by":"crossref","first-page":"7837","DOI":"10.3390\/s24237837","article-title":"Spatiotemporal multivariate weather prediction network based on CNN-transformer","volume":"24","author":"Wu","year":"2024","journal-title":"Sensors"},{"key":"10.1016\/j.eswa.2026.133986_bib0042","unstructured":"Xu, X., Liang, Y., Huang, B., Lan, Z., & Shu, K. (2024). Integrating mamba and transformer for long-short range time series forecasting. 2(7). arXiv preprint arXiv: 2404.14757."},{"key":"10.1016\/j.eswa.2026.133986_sbref0043","doi-asserted-by":"crossref","first-page":"31350","DOI":"10.52202\/079017-0985","article-title":"Frequency adaptive normalization for non-stationary time series forecasting","volume":"37","author":"Ye","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.133986_sbref0044","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"11121","article-title":"Are transformers effective for time series forecasting?","volume":"vol. 37","author":"Zeng","year":"2023"},{"key":"10.1016\/j.eswa.2026.133986_sbref0045","series-title":"International conference on machine learning","first-page":"40770","article-title":"Stabilizing transformer training by preventing attention entropy collapse","author":"Zhai","year":"2023"},{"key":"10.1016\/j.eswa.2026.133986_bib0046","unstructured":"Zhang, X., Jin, X., Gopalswamy, K., Gupta, G., Park, Y., Shi, X., Wang, H., Maddix, D. C., & Wang, Y. (2022). First de-trend then attend: Rethinking attention for time-series forecasting. arXiv preprint arXiv: 2212.08151."},{"key":"10.1016\/j.eswa.2026.133986_sbref0047","article-title":"Mamba in speech: Towards an alternative to self-attention","author":"Zhang","year":"2025","journal-title":"IEEE Transactions on Audio, Speech and Language Processing"},{"key":"10.1016\/j.eswa.2026.133986_sbref0048","series-title":"The eleventh international conference on learning representations","article-title":"Crossformer: Transformer utilizing cross-dimension dependency for multivariate time series forecasting","author":"Zhang","year":"2023"},{"key":"10.1016\/j.eswa.2026.133986_sbref0049","series-title":"Proceedings of the 63rd annual meeting of the association for computational linguistics (volume 1: Long papers)","first-page":"9840","article-title":"Attention entropy is a key factor: An analysis of parallel context encoding with full-attention-based pre-trained language models","author":"Zhang","year":"2025"},{"key":"10.1016\/j.eswa.2026.133986_sbref0050","series-title":"The thirteenth international conference on learning representations","article-title":"multi-resolution decomposable diffusion model for non-stationary time series anomaly detection","author":"Zhong","year":"2025"},{"key":"10.1016\/j.eswa.2026.133986_sbref0051","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"11106","article-title":"Informer: Beyond efficient transformer for long sequence time-series forecasting","volume":"vol. 35","author":"Zhou","year":"2021"},{"key":"10.1016\/j.eswa.2026.133986_sbref0052","series-title":"International conference on machine learning","first-page":"27268","article-title":"Fedformer: Frequency enhanced decomposed transformer for long-term series forecasting","author":"Zhou","year":"2022"}],"container-title":["Expert Systems with Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426028927?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426028927?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T20:04:34Z","timestamp":1787256274000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0957417426028927"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2027,1]]},"references-count":52,"alternative-id":["S0957417426028927"],"URL":"https:\/\/doi.org\/10.1016\/j.eswa.2026.133986","relation":{},"ISSN":["0957-4174"],"issn-type":[{"value":"0957-4174","type":"print"}],"subject":[],"published":{"date-parts":[[2027,1]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"CQMTformer: Channel query enhanced Mamba-transformer fusion architecture for multivariate time series forecasting","name":"articletitle","label":"Article Title"},{"value":"Expert Systems with Applications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.eswa.2026.133986","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"133986"}}