{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T09:11:07Z","timestamp":1778749867351,"version":"3.51.4"},"reference-count":37,"publisher":"Wiley","issue":"6","license":[{"start":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T00:00:00Z","timestamp":1778198400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T00:00:00Z","timestamp":1778198400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["42201465"],"award-info":[{"award-number":["42201465"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Expert Systems"],"published-print":{"date-parts":[[2026,6]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>Multivariate time series anomaly detection (MTSAD) is widely applied in domains such as industrial monitoring and financial risk management. Although unsupervised deep learning models have made notable progress in capturing normal behaviour patterns, they still face a trade\u2010off between modelling capacity and computational efficiency. Transformer\u2010based methods possess strong representational power but are computationally intensive, while lightweight models are more efficient but often struggle to capture fine\u2010grained anomalies such as periodic perturbations and frequency shifts. To address this issue, we propose a unified, lightweight, and highly discriminative framework, Dual\u2010Path Adaptive Convolution and Frequency\u2010Aware Transformer (DPAC\u2010FAT), which jointly models local disturbances and frequency\u2010domain anomalies. Specifically, a Structure\u2010Aware Temporal Encoder (SATE) is introduced to efficiently model nonlinear short\u2010term dynamics, while a Frequency\u2010Informed Contextual AutoEncoder (FICA) is employed to enhance the recognition of periodic structures and frequency\u2010specific variations. Considering that the temporal and frequency branches should exhibit consistent representations under normal conditions, we further design a Dual\u2010Branch Alignment Loss (DBAL) based on cosine similarity to encourage both pathways to learn coherent backbone representations, thereby improving model robustness and cross\u2010view discriminability. Experimental results on five real\u2010world datasets demonstrate that DPAC\u2010FAT achieves a 5.41% improvement in average F1 score over 11 representative state\u2010of\u2010the\u2010art methods, while significantly reducing training costs.<\/jats:p>","DOI":"10.1111\/exsy.70287","type":"journal-article","created":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T14:10:33Z","timestamp":1778249433000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["<scp>DPAC<\/scp>\n                    \u2010\n                    <scp>FAT<\/scp>\n                    : A Lightweight Dual\u2010Path Adaptive Convolution and Frequency\u2010Aware Transformer for Multivariate Time Series Anomaly Detection"],"prefix":"10.1111","volume":"43","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-6539-2012","authenticated-orcid":false,"given":"Yanqing","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Software Henan University  Kaifeng Henan China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiang","family":"Yin","sequence":"additional","affiliation":[{"name":"School of Software Henan University  Kaifeng Henan China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2026,5,8]]},"reference":[{"key":"e_1_2_10_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403392"},{"key":"e_1_2_10_3_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TIM.2023.3315420","article-title":"Crossfun: Multiview Joint Cross\u2010Fusion Network for Time\u2010Series Anomaly Detection","volume":"72","author":"Bai Y.","year":"2023","journal-title":"IEEE Transactions on Instrumentation and Measurement"},{"key":"e_1_2_10_4_1","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1970.10481180"},{"key":"e_1_2_10_5_1","article-title":"Vista: Unsupervised 2d Temporal Dependency Representations for Time Series Anomaly Detection","author":"Chin S.","year":"2025","journal-title":"arXiv Preprint"},{"key":"e_1_2_10_6_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i5.16523"},{"key":"e_1_2_10_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE55515.2023.00046"},{"key":"e_1_2_10_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2785792"},{"key":"e_1_2_10_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2013.184"},{"key":"e_1_2_10_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2004.1334558"},{"key":"e_1_2_10_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-024-05575-y"},{"key":"e_1_2_10_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219845"},{"key":"e_1_2_10_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3711896.3736977"},{"key":"e_1_2_10_14_1","article-title":"Adam: A Method for Stochastic Optimization","author":"Kingma D. P.","year":"2014","journal-title":"arXiv Preprint"},{"key":"e_1_2_10_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2025.104315"},{"key":"e_1_2_10_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-30490-4_56"},{"key":"e_1_2_10_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467075"},{"key":"e_1_2_10_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CySWater.2016.7469060"},{"key":"e_1_2_10_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/51.932724"},{"key":"e_1_2_10_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM50108.2020.00147"},{"key":"e_1_2_10_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3439950"},{"key":"e_1_2_10_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671928"},{"key":"e_1_2_10_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/342009.335437"},{"key":"e_1_2_10_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICICIS46948.2019.9014697"},{"key":"e_1_2_10_25_1","first-page":"865","volume-title":"Future of Information and Communication Conference","author":"Shaukat K.","year":"2021"},{"key":"e_1_2_10_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098144"},{"key":"e_1_2_10_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330672"},{"key":"e_1_2_10_28_1","doi-asserted-by":"publisher","DOI":"10.1023\/B:MACH.0000008084.60811.49"},{"key":"e_1_2_10_29_1","article-title":"Tranad: Deep Transformer Networks for Anomaly Detection in Multivariate Time Series Data","author":"Tuli S.","year":"2022","journal-title":"arXiv Preprint"},{"key":"e_1_2_10_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2025.112775"},{"key":"e_1_2_10_31_1","article-title":"Catch: Channel\u2010Aware Multivariate Time Series Anomaly Detection Via Frequency Patching","author":"Wu X.","year":"2024","journal-title":"arXiv Preprint"},{"key":"e_1_2_10_32_1","first-page":"697","article-title":"Multivariate Time Series Anomaly Detection by Capturing Coarse\u2010Grained Intra\u2010and Inter\u2010Variate Dependencies","volume":"2025","author":"Xie Y.","year":"2025","journal-title":"Proceedings of the ACM on Web Conference"},{"key":"e_1_2_10_33_1","article-title":"Anomaly Transformer: Time Series Anomaly Detection With Association Discrepancy","author":"Xu J.","year":"2021","journal-title":"arXiv Preprint"},{"key":"e_1_2_10_34_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.111849"},{"key":"e_1_2_10_35_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33011409"},{"issue":"2","key":"e_1_2_10_36_1","first-page":"2118","article-title":"Unsupervised Deep Anomaly Detection for Multi\u2010Sensor Time\u2010Series Signals","volume":"35","author":"Zhang Y.","year":"2021","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"e_1_2_10_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2025.3596745"},{"key":"e_1_2_10_38_1","volume-title":"International Conference on Learning Representations","author":"Zong B.","year":"2018"}],"container-title":["Expert Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/exsy.70287","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/exsy.70287","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/exsy.70287","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T08:26:49Z","timestamp":1778747209000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/exsy.70287"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,8]]},"references-count":37,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2026,6]]}},"alternative-id":["10.1111\/exsy.70287"],"URL":"https:\/\/doi.org\/10.1111\/exsy.70287","archive":["Portico"],"relation":{},"ISSN":["0266-4720","1468-0394"],"issn-type":[{"value":"0266-4720","type":"print"},{"value":"1468-0394","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,8]]},"assertion":[{"value":"2025-10-21","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-04-28","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-05-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70287"}}