{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T16:58:06Z","timestamp":1762361886636,"version":"build-2065373602"},"reference-count":53,"publisher":"Institution of Engineering and Technology (IET)","issue":"1","license":[{"start":{"date-parts":[[2024,7,24]],"date-time":"2024-07-24T00:00:00Z","timestamp":1721779200000},"content-version":"vor","delay-in-days":205,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62071242","62171232"],"award-info":[{"award-number":["62071242","62171232"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["ietresearch.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["IET Signal Processing"],"published-print":{"date-parts":[[2024,1]]},"abstract":"<jats:p>As an essential part of intelligent transportation system (ITS), traffic forecasting has provided crucial role for traffic management and risk assessment. However, complex spatial\u2013temporal dependencies, heterogeneity, dynamicity, and periodicity of traffic data influence the traffic forecasting performance. Consequently, we propose a novel effective gated spatial\u2013temporal merged transformer (GSTMT) inspired by multimask and dual branch for accurate traffic forecasting in this paper. Specifically, we first conduct a concatenation of gated spatial static mask transformer (GSSMT) and gated spatial dynamic mask transformer (GSDMT) with residual network. The GSSMT and GSDMT evolve from the traditional transformer by making preferable modifications that include gated linear unit (GLU), multimask mechanism including static mask matrix (SMM) and dynamic mask matrix (DMM), and spatial attention (SA). Among them, GLU is to promote the performance of capturing spatial dependency, dynamicity, and heterogeneity due to advanced performance for controlling information flow through layers. Additionally, by developing multimask mechanism including two novel SMM and DMM, the proposed GSTMT can precisely model the static and dynamic spatial structure for effectively highlighting static dependency and dynamicity. And SA is injected for enhancing the ability of capturing spatial dependency of GSSMT and GSDMT. Secondly, we develop a dual\u2010branch gated temporal transformer (DBGTT) for capturing temporal dependency, heterogeneity, dynamicity, and periodicity via incorporating the GLU and mixed time series decomposition (MTD) into traditional transformer. Similarly, we also introduce the GLU for empowering DBGTT with capability of capturing temporal dependency, dynamicity, and heterogeneity. In addition, MTD, which brings dual\u2010branch mechanism, can enhance the DBGTT for capturing more detailed temporal information via exploiting global and periodic profile of traffic data. At last, some experiments, which are performed on several real\u2010world traffic datasets, demonstrate the better results over classic traffic forecasting methods.<\/jats:p>","DOI":"10.1049\/2024\/8639981","type":"journal-article","created":{"date-parts":[[2024,7,24]],"date-time":"2024-07-24T06:54:01Z","timestamp":1721804041000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Gated Spatial\u2013Temporal Merged Transformer Inspired by Multimask and Dual Branch for Traffic Forecasting"],"prefix":"10.1049","volume":"2024","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3992-2814","authenticated-orcid":false,"given":"Yongpeng","family":"Yang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5763-2768","authenticated-orcid":false,"given":"Zhenzhen","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Zhen","family":"Yang","sequence":"additional","affiliation":[]}],"member":"265","published-online":{"date-parts":[[2024,7,24]]},"reference":[{"key":"e_1_2_10_1_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2020.107484"},{"key":"e_1_2_10_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3008612"},{"key":"e_1_2_10_3_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.aap.2020.105711"},{"key":"e_1_2_10_4_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2023.109062"},{"key":"e_1_2_10_5_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109670"},{"key":"e_1_2_10_6_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.117921"},{"key":"e_1_2_10_7_2","doi-asserted-by":"publisher","DOI":"10.3390\/ijgi12030100"},{"key":"e_1_2_10_8_2","first-page":"1","article-title":"Urban traffic flow prediction techniques: a review, sustainable computing","volume":"35","author":"Medina B.","year":"2022","journal-title":"Informatics and Systems"},{"key":"e_1_2_10_9_2","unstructured":"YuG.andZhangC. Switching ARIMA model based forecasting for traffic flow 2004 IEEE International Conference on Acoustics Speech and Signal Processing May 2004 Montreal Que Canada IEEE 429\u2013432."},{"key":"e_1_2_10_10_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijforecast.2006.03.005"},{"key":"e_1_2_10_11_2","doi-asserted-by":"publisher","DOI":"10.1080\/15472450902858368"},{"key":"e_1_2_10_12_2","doi-asserted-by":"crossref","unstructured":"MayM. HeckerD. KornerC. ScheiderS. andSchulzD. A vector-geometry based spatial KNN-algorithm for traffic frequency predictions IEEE International Conference on Data Mining Workshops ICDM Workshops 2008 December 2008 Pisa Italy IEEE 442\u2013447.","DOI":"10.1109\/ICDMW.2008.35"},{"key":"e_1_2_10_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2004.837813"},{"key":"e_1_2_10_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/TST.5971803"},{"key":"e_1_2_10_15_2","doi-asserted-by":"crossref","unstructured":"DingZ. ZhaoR. ZhangJ. GaoT. andHuangT. Spatio-temporal recurrent networks for event-based optical flow estimation 36th AAAI Conference on Artificial Intelligence AAAI 2022 February 2022 AAAI 525\u2013533.","DOI":"10.1609\/aaai.v36i1.19931"},{"key":"e_1_2_10_16_2","doi-asserted-by":"publisher","DOI":"10.3390\/s17071501"},{"key":"e_1_2_10_17_2","doi-asserted-by":"crossref","unstructured":"LvZ. XuJ. ZhengK. andYinH. LC-RNN: a deep learning model for traffic speed prediction 27th International Joint Conference on Artificial Intelligence IJCAI 2018 July 2018 Stockholm Sweden Morgan Kaufmann 3470\u20133476.","DOI":"10.24963\/ijcai.2018\/482"},{"key":"e_1_2_10_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/TII.9424"},{"key":"e_1_2_10_19_2","unstructured":"LiY. YuR. ShahabiC. andLiuY. Diffusion convolutional recurrent neural network: data-driven traffic forecasting 6th International Conference on Learning Representations ICLR 2018 April 2018 Vancouver BC Canada ICLR 1\u201316."},{"key":"e_1_2_10_20_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2022.108506"},{"key":"e_1_2_10_21_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2023.109133"},{"key":"e_1_2_10_22_2","unstructured":"KipfT.andWellingM. Semi-supervised classification with graph convolutional networks 2017 International Conference on Learning Representation July 2017 Sydney Australia ACM 1\u201314."},{"key":"e_1_2_10_23_2","unstructured":"XuK. HuW. LeskovecJ. andJegelkaS. How powerful are graph neural networks 7th International Conference on Learning Representations ICLR 2019 May 2019 New Orleans LA United States ACM 1\u201317."},{"key":"e_1_2_10_24_2","unstructured":"VelickovicP. CucurullG. CasanovaA. RomeroA. LioP. andBengioY. Graph attention networks 6th International Conference on Learning Representations ICLR 2018 April 2018 Vancouver BC Canada ICLR 1\u201312."},{"key":"e_1_2_10_25_2","unstructured":"LiuX. JinW. MaY. LiY. LiuH. WangY. YanM. andTangJ. Elastic graph neural networks 2021 International Conference on Machine Learning July 2021 ACM 6861\u20136871."},{"key":"e_1_2_10_26_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109867"},{"key":"e_1_2_10_27_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2023.108950"},{"key":"e_1_2_10_28_2","doi-asserted-by":"crossref","unstructured":"YuB. YinH. andZhuZ. Spatio-temporal graph convolutional networks: a deep learning framework for traffic forecasting 27th International Joint Conference on Artificial Intelligence IJCAI 2018 July 2018 Stockholm Sweden Morgan Kaufmann 3634\u20133640.","DOI":"10.24963\/ijcai.2018\/505"},{"key":"e_1_2_10_29_2","unstructured":"WolfT. DebutL. SanhV. ChaumondJ. andRushA. Transformers: state-of-the-art natural language processing 2020 System Demonstrations of the 2020 Conference on Empirical Methods in Natural Language Processing EMNLP 2020 November 2020 ACL 38\u201345."},{"key":"e_1_2_10_30_2","doi-asserted-by":"crossref","unstructured":"WuZ. PanS. LongG. JiangJ. andZhangC. Graph wavenet for deep spatial-temporal graph modeling 28th International Joint Conference on Artificial Intelligence IJCAI 2019 August 2019 Macao China Morgan Kaufmann 1907\u20131913.","DOI":"10.24963\/ijcai.2019\/264"},{"key":"e_1_2_10_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2022.3156366"},{"key":"e_1_2_10_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3532611"},{"key":"e_1_2_10_33_2","doi-asserted-by":"crossref","unstructured":"ZhengC. FanX. WangC. andQiJ. GMAN: a graph multi-attention network for traffic prediction 34th AAAI Conference on Artificial Intelligence AAAI 2020 February 2020 New York NY United States AAAI 1234\u20131241.","DOI":"10.1609\/aaai.v34i01.5477"},{"key":"e_1_2_10_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3179646"},{"key":"e_1_2_10_35_2","doi-asserted-by":"crossref","unstructured":"GuoS. LinY. FengN. SongC. andWanH. Attention based spatial-temporal graph convolutional networks for traffic flow forecasting 33rd AAAI Conference on Artificial Intelligence AAAI 2019 January 2019 Honolulu HI United States AAAI 922\u2013929.","DOI":"10.1609\/aaai.v33i01.3301922"},{"key":"e_1_2_10_36_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2023.104156"},{"key":"e_1_2_10_37_2","doi-asserted-by":"crossref","unstructured":"JiangJ. HanC. ZhaoW. andWangJ. PDFormer: propagation delay-aware dynamic long-range transformer for traffic flow prediction 37th AAAI Conference on Artificial Intelligence AAAI 2023 February 2023 Washington DC United States AAAI 1\u20139.","DOI":"10.1609\/aaai.v37i4.25556"},{"key":"e_1_2_10_38_2","doi-asserted-by":"crossref","unstructured":"ZhouH. ZhangS. PengJ. ZhangS. andZhangW. Informer: beyond efficient transformer for long sequence time-series forecasting 35th AAAI Conference on Artificial Intelligence AAAI 2021 February 2021 AAAI 1\u201314.","DOI":"10.1609\/aaai.v35i12.17325"},{"key":"e_1_2_10_39_2","unstructured":"KitaevN. KaiserL. andLevskayaA. Reformer: the efficient transformer 8th International Conference on Learning Representations ICLR 2020 2020 Addis Ababa Ethiopia ICLR 1\u201312."},{"key":"e_1_2_10_40_2","first-page":"22419","article-title":"Autoformer: decomposition transformers with auto-correlation for long-term series forecasting","volume":"34","author":"Wu H.","year":"2021","journal-title":"Neural Information Processing Systems"},{"key":"e_1_2_10_41_2","unstructured":"ZhouT. MaZ. WenQ. WangX. SunL. andJinR. FEDformer: frequency enhanced decomposed transformer for long-term series forecasting 39th International Conference on Machine Learning ICML 2022 July 2022 Baltimore MD United States ACM 1\u201319."},{"key":"e_1_2_10_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3019893"},{"key":"e_1_2_10_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3245407"},{"key":"e_1_2_10_44_2","doi-asserted-by":"crossref","unstructured":"LaiJ. YangS. WuW. WuT. JiangG. WangX. LiuJ. GaoB. andZhangW. SpatialFormer: semantic and target aware attentions for few-shot learning 37th AAAI Conference on Artificial Intelligence AAAI 2023 February 2023 Washington DC United States AAAI 8430\u20138437.","DOI":"10.1609\/aaai.v37i7.26016"},{"key":"e_1_2_10_45_2","unstructured":"BrodyS. AlonU. andYahavE. How attentive are graph attention networks? 10th International Conference on Learning Representations ICLR 2022 April 2022 ICLR 1\u201326."},{"key":"e_1_2_10_46_2","doi-asserted-by":"crossref","unstructured":"LiuZ. LinY. CaoY. HuH. WeiY. ZhangZ. LinS. andGuoB. Swin transformer: hierarchical vision transformer using shifted windows 18th IEEE\/CVF International Conference on Computer Vision ICCV 2021 October 2021 Canada IEEE 10012\u201310022.","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_2_10_47_2","doi-asserted-by":"crossref","unstructured":"HochreiterS.andSchmidhuberJ. Long short-term memory Neural Computation 1997 9 no. 8 1735\u20131780.","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_2_10_48_2","unstructured":"DauphinY. FanA. AuliM. andGrangierD. Language modeling with gated convolutional networks 34th International Conference on Machine Learning ICML 2017 2017 Sydney NSW Australia ACM 933\u2013941."},{"key":"e_1_2_10_49_2","first-page":"1","article-title":"STR: a seasonal-trend decomposition procedure based on regression","volume":"13","author":"Dokumentov A.","year":"2015","journal-title":"Monash Econometrics and Business Statistics Working Papers"},{"key":"e_1_2_10_50_2","first-page":"22419","article-title":"Autoformer: decomposition transformers with auto-correlation for long-term series forecasting","volume":"34","author":"Wu H.","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_10_51_2","doi-asserted-by":"crossref","unstructured":"ZengA. ChenM. ZhangL. andXuQ. Are transformers effective for time series forecasting? 37th AAAI Conference on Artificial Intelligence AAAI 2023 February 2023 Washington DC United States AAAI 11121\u201311128.","DOI":"10.1609\/aaai.v37i9.26317"},{"key":"e_1_2_10_52_2","unstructured":"YunC. BhojanapalliS. RawatA. ReddiS. andKumarS. Are transformers universal approximators of sequence-to-sequence functions? 8th International Conference on Learning Representations ICLR 2020 April 2020 Addis Ababa Ethiopia 1\u201323."},{"key":"e_1_2_10_53_2","doi-asserted-by":"crossref","unstructured":"ChengB. MisraI. SchwingA. KirillovA. andGirdharR. Masked-attention mask transformer for universal image segmentation 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition CVPR 2022 June 2022 New Orleans LA United States IEEE 1290\u20131299.","DOI":"10.1109\/CVPR52688.2022.00135"}],"container-title":["IET Signal Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/2024\/8639981","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T16:54:27Z","timestamp":1762361667000},"score":1,"resource":{"primary":{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/10.1049\/2024\/8639981"}},"subtitle":[],"editor":[{"given":"Qinghe","family":"Zheng","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2024,1]]},"references-count":53,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,1]]}},"alternative-id":["10.1049\/2024\/8639981"],"URL":"https:\/\/doi.org\/10.1049\/2024\/8639981","archive":["Portico"],"relation":{},"ISSN":["1751-9675","1751-9683"],"issn-type":[{"type":"print","value":"1751-9675"},{"type":"electronic","value":"1751-9683"}],"subject":[],"published":{"date-parts":[[2024,1]]},"assertion":[{"value":"2024-02-07","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-06-27","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-07-24","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"8639981"}}