{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T22:51:22Z","timestamp":1775083882587,"version":"3.50.1"},"reference-count":58,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3613663","type":"journal-article","created":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T17:26:05Z","timestamp":1758648365000},"page":"168643-168653","source":"Crossref","is-referenced-by-count":2,"title":["TriP-LLM: A Tri-Branch Patch-Wise Large Language Model Framework for Time-Series Anomaly Detection"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-2862-4455","authenticated-orcid":false,"given":"Yuan-Cheng","family":"Yu","sequence":"first","affiliation":[{"name":"Department of Electrical Engineering, National Chung Hsing University, Taichung, Taiwan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4221-2787","authenticated-orcid":false,"given":"Yen-Chieh","family":"Ouyang","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, National Chung Hsing University, Taichung, Taiwan"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8874-6196","authenticated-orcid":false,"given":"Chun-An","family":"Lin","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, National Chung Hsing University, Taichung, Taiwan"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.14778\/3611540.3611570"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/UKSim.2014.67"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3182\/20130902-3-cn-3020.00044"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.2991\/jrnal.k.210521.010"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3063686"},{"key":"ref6","article-title":"Generative artificial intelligence for Internet of Things computing: A systematic survey","author":"Mangione","year":"2025","journal-title":"arXiv:2504.07635"},{"key":"ref7","article-title":"Tackling data heterogeneity in federated time series forecasting","author":"Yuan","year":"2024","journal-title":"arXiv:2411.15716"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/1541880.1541882"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3439950"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2916648"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3105827"},{"key":"ref12","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. Conf. North","volume":"1","author":"Devlin"},{"key":"ref13","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Brown"},{"key":"ref14","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learning Represent.","author":"Dosovitskiy"},{"key":"ref15","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref16","first-page":"34892","article-title":"Visual instruction tuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-30490-4_56"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467075"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2022.3164087"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/COMPSAC61105.2024.00106"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.14778\/3514061.3514067"},{"key":"ref22","article-title":"Anomaly transformer: Time series anomaly detection with association discrepancy","volume-title":"Proc. Int. Conf. Learning Represent. (ICLR)","author":"Xu"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599295"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.111507"},{"key":"ref25","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023","journal-title":"arXiv:2312.00752"},{"key":"ref26","article-title":"XLSTM: Extended long short-term memory","author":"Beck","year":"2024","journal-title":"arXiv:2405.04517"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/HPSR64165.2025.11038914"},{"key":"ref28","article-title":"XLSTMAD: A powerful xLSTM-based method for anomaly detection","author":"Faber","year":"2025","journal-title":"arXiv:2506.22837"},{"key":"ref29","article-title":"AnomalyBERT: Self-supervised transformer for time series anomaly detection using data degradation scheme","author":"Jeong","year":"2023","journal-title":"arXiv:2305.04468"},{"key":"ref30","article-title":"One fits all: Power general time series analysis by pretrained LM","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhou"},{"key":"ref31","article-title":"Multi-patch prediction: Adapting LLMs for time series representation learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bian"},{"key":"ref32","article-title":"Time-LLM: Time series forecasting by reprogramming large language models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Jin"},{"key":"ref33","first-page":"122154","article-title":"Autotimes: Autoregressive time series forecasters via large language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"37","author":"Liu"},{"key":"ref34","first-page":"19622","article-title":"Large language models are zero-shot time series forecasters","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Gruver"},{"key":"ref35","article-title":"Large language models can be zero-shot anomaly detectors for time series?","author":"Alnegheimish","year":"2024","journal-title":"arXiv:2405.14755"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330672"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CySWater.2016.7469060"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219845"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467174"},{"key":"ref40","article-title":"SWAN-SF [dataset], Harvard dataverse, V1","author":"Angryk","year":"2020"},{"key":"ref41","article-title":"Revisiting time series outlier detection: Definitions and benchmarks","volume-title":"Proc. NeurIPS Datasets and Benchmarks Track","author":"Lai"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539339"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671971"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.14778\/3551793.3551830"},{"issue":"8","key":"ref45","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403392"},{"key":"ref47","article-title":"TimesNet: Temporal 2D-variation modeling for general time series analysis","volume-title":"Proc. Int. Conf. Learning Represent.","author":"Wu"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3270293"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/tbdata.2025.3596745"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3393996"},{"key":"ref51","volume-title":"3.2: Revolutionizing Edge AI and Vision With Open, Customizable Models","year":"2024"},{"key":"ref52","article-title":"Gemma 3 technical report","volume-title":"arXiv:2503.19786","author":"Team","year":"2025"},{"key":"ref53","article-title":"Qwen3 technical report","volume-title":"arXiv:2505.09388","author":"Yang","year":"2025"},{"key":"ref54","first-page":"60162","article-title":"Are language models actually useful for time series forecasting?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Tan"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i9.26317"},{"key":"ref56","article-title":"A time series is worth 64 words: Long-term forecasting with transformers","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Nie"},{"key":"ref57","article-title":"PatchMixer: A patch-mixing architecture for long-term time series forecasting","author":"Gong","year":"2023","journal-title":"arXiv:2310.00655"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2025.3613663"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11175692.pdf?arnumber=11175692","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,2]],"date-time":"2025-10-02T17:40:48Z","timestamp":1759426848000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11175692\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3613663","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}