Early weak anomaly detection and uncertainty quantification of equipment based on multi-task and multi-domain temporal memory autoencoder
To avoid severe malfunctions of industrial equipment, it is necessary to perform accurate detection in the early stages of abnormal occurrences. However, early anomalies are usually weak, difficult to model anomalous features, and affected by data uncertainty and training uncertainty. To address the...
Uložené v:
| Vydané v: | Engineering applications of artificial intelligence Ročník 162; s. 112735 |
|---|---|
| Hlavní autori: | , |
| Médium: | Journal Article |
| Jazyk: | English |
| Vydavateľské údaje: |
Elsevier Ltd
26.12.2025
|
| Predmet: | |
| ISSN: | 0952-1976 |
| On-line prístup: | Získať plný text |
| Tagy: |
Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
|
| Abstract | To avoid severe malfunctions of industrial equipment, it is necessary to perform accurate detection in the early stages of abnormal occurrences. However, early anomalies are usually weak, difficult to model anomalous features, and affected by data uncertainty and training uncertainty. To address these limitations, we propose a multi-task and multi-domain temporal memory autoencoder (MTMAE). In the encoding stage, we design a temporal feature learning convolutional encoder and a frequency-aware temporal block to fuse time-domain and frequency-domain anomalous features, thereby creating a cloud-enhancement feature modeling (CEFM) approach based on cloud model theory to mitigate uncertainty in the data. After obtaining the latent features of the encoder, the reconstruction task uses the deconvolution network to recover the data, forming an encoder–decoder adaptive matching. The encoding memory task uses an external attention memory unit scorer to memorize potential patterns in the data. In addition, we design an optimized regularization uncertainty weighting (UW) method to balance the two tasks and penalize training uncertainty. The experimental results of five public datasets demonstrate the superiority of MTMAE in anomaly detection, with an average F1 score of 0.871 and an area under the precision–recall curve of 0.887. In the actual anomaly detection of private marine diesel engine data, MTMAE can detect early weak anomalies fastest and has the lowest false alarm rate. In addition, we also demonstrated the contribution of CEFM and UW methods to the model’s resistance to uncertainty through noise set detection and model-independent detection experiments.
•We propose a multi-domain autoencoder to enhance time series modeling.•We design a memory scorer based on external attention to score anomalies.•Multi-task learning with uncertainty minimizes reconstruction error and score.•We use cloud model theory to quantify data uncertainty and assist the encoder.•We design noise set and model independent tests to evaluate model robustness. |
|---|---|
| AbstractList | To avoid severe malfunctions of industrial equipment, it is necessary to perform accurate detection in the early stages of abnormal occurrences. However, early anomalies are usually weak, difficult to model anomalous features, and affected by data uncertainty and training uncertainty. To address these limitations, we propose a multi-task and multi-domain temporal memory autoencoder (MTMAE). In the encoding stage, we design a temporal feature learning convolutional encoder and a frequency-aware temporal block to fuse time-domain and frequency-domain anomalous features, thereby creating a cloud-enhancement feature modeling (CEFM) approach based on cloud model theory to mitigate uncertainty in the data. After obtaining the latent features of the encoder, the reconstruction task uses the deconvolution network to recover the data, forming an encoder–decoder adaptive matching. The encoding memory task uses an external attention memory unit scorer to memorize potential patterns in the data. In addition, we design an optimized regularization uncertainty weighting (UW) method to balance the two tasks and penalize training uncertainty. The experimental results of five public datasets demonstrate the superiority of MTMAE in anomaly detection, with an average F1 score of 0.871 and an area under the precision–recall curve of 0.887. In the actual anomaly detection of private marine diesel engine data, MTMAE can detect early weak anomalies fastest and has the lowest false alarm rate. In addition, we also demonstrated the contribution of CEFM and UW methods to the model’s resistance to uncertainty through noise set detection and model-independent detection experiments.
•We propose a multi-domain autoencoder to enhance time series modeling.•We design a memory scorer based on external attention to score anomalies.•Multi-task learning with uncertainty minimizes reconstruction error and score.•We use cloud model theory to quantify data uncertainty and assist the encoder.•We design noise set and model independent tests to evaluate model robustness. |
| ArticleNumber | 112735 |
| Author | Ma, Liyong Li, Chuanrui |
| Author_xml | – sequence: 1 givenname: Chuanrui orcidid: 0009-0001-2097-1299 surname: Li fullname: Li, Chuanrui organization: School of Information Science and Engineering, Harbin Institute of Technology, WeiHai, 264209, China – sequence: 2 givenname: Liyong surname: Ma fullname: Ma, Liyong email: maliyong@hit.edu.cn organization: School of Information Science and Engineering, Harbin Institute of Technology, WeiHai, 264209, China |
| BookMark | eNqFkM1OwzAQhH0oEm3hFZBfIMV2Gie5garyI1XiAmdra6-R28ZOHQeUR-CtSSmcOa1mVjMafTMy8cEjITecLTjj8na3QP8ObQtuIZgoFpyLMi8mZMrqQmS8LuUlmXXdjjGWV0s5JV9riIeBfiLsKfjQwCgMJtTJBT86hvZeY0zgfBrosQefnHUaft7BUjz2rm3QJ7qFDg0d3aY_JJcl6PY_-bM0Y7XzNGHThggH2mAT4kChTwG9DgbjFbmwcOjw-vfOydvD-nX1lG1eHp9X95tMC8lTxoGVJS4lEwZyaXO0mldbVm_50pa11qK2qA1shcwLjqIwVS0lx7qyUljLqnxO5LlXx9B1Ea1qo2sgDoozdYKoduoPojpBVGeIY_DuHMRx3YfDqDrtxvFoXBx5KRPcfxXfqWCGvA |
| Cites_doi | 10.1109/LRA.2018.2801475 10.1145/3292500.3330672 10.1016/j.ins.2024.120605 10.1109/TIP.2022.3219228 10.1016/j.ress.2021.107791 10.1109/TBME.2024.3447058 10.1109/TNNLS.2021.3086137 10.1109/TSG.2020.2995313 10.1109/TIP.2023.3293772 10.1016/j.engappai.2023.106173 10.1016/j.patrec.2021.04.020 10.1016/j.inffus.2021.05.008 10.1038/s41746-024-01418-9 10.1007/s00158-022-03348-0 10.1109/JBHI.2021.3123936 10.1016/j.ins.2023.119610 10.1109/TASLP.2017.2759338 10.1016/j.ins.2022.11.011 10.1109/ACCESS.2020.2977671 10.1109/JSEN.2024.3370965 10.3390/math11122746 10.1007/s10489-024-05575-y 10.1016/j.ress.2022.108949 10.1016/j.future.2017.07.036 10.1016/j.ins.2023.118989 10.1016/j.aei.2020.101105 10.1007/s10845-022-02034-8 10.1109/TII.2020.2967556 10.1109/CVPR.2018.00781 10.1109/MCOM.001.2200294 10.1109/TCSVT.2022.3211839 10.1016/j.engappai.2022.104729 10.1016/j.eswa.2023.120284 10.1016/j.rcim.2022.102441 10.1016/j.engfailanal.2025.109315 10.1109/TII.2024.3378834 10.1016/j.ipm.2021.102844 10.1016/j.inffus.2022.12.027 |
| ContentType | Journal Article |
| Copyright | 2025 Elsevier Ltd |
| Copyright_xml | – notice: 2025 Elsevier Ltd |
| DBID | AAYXX CITATION |
| DOI | 10.1016/j.engappai.2025.112735 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Applied Sciences Computer Science |
| ExternalDocumentID | 10_1016_j_engappai_2025_112735 S0952197625027666 |
| GroupedDBID | --K --M .DC .~1 0R~ 1B1 1~. 1~5 4.4 457 4G. 5GY 5VS 7-5 71M 8P~ 9JN AABNK AAEDT AAEDW AAIKJ AAKOC AALRI AAOAW AAQFI AATTM AAXKI AAXUO AAYFN AAYWO ABBOA ABJNI ABMAC ACDAQ ACGFS ACLOT ACRLP ACVFH ACZNC ADBBV ADCNI ADEZE ADTZH AEBSH AECPX AEIPS AEKER AENEX AEUPX AFJKZ AFPUW AFTJW AGHFR AGUBO AGYEJ AHHHB AHJVU AHZHX AIALX AIEXJ AIGII AIIUN AIKHN AITUG AKBMS AKRWK AKYEP ALMA_UNASSIGNED_HOLDINGS AMRAJ ANKPU AOUOD APXCP AXJTR BJAXD BKOJK BLXMC CS3 DU5 EBS EFJIC EFKBS EFLBG EO8 EO9 EP2 EP3 F5P FDB FIRID FNPLU FYGXN G-Q GBLVA GBOLZ IHE J1W JJJVA KOM LG9 LY7 M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 ROL RPZ SDF SDG SDP SES SEW SPC SPCBC SST SSV SSZ T5K TN5 ~G- ~HD 29G 9DU AAQXK AAYXX ABWVN ABXDB ACNNM ACRPL ADJOM ADMUD ADNMO AGQPQ ASPBG AVWKF AZFZN CITATION EJD FEDTE FGOYB G-2 HLZ HVGLF HZ~ R2- SBC SET UHS WUQ ZMT |
| ID | FETCH-LOGICAL-c261t-1a077e4602da36f3efc18b09b14f79cc29fecdab26351e25d89661e98f62ff083 |
| ISICitedReferencesCount | 0 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001601106800002&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0952-1976 |
| IngestDate | Sat Nov 29 06:49:51 EST 2025 Sat Nov 29 17:09:10 EST 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Early weak anomaly detection Uncertainty Autoencoder Multi-task learning |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c261t-1a077e4602da36f3efc18b09b14f79cc29fecdab26351e25d89661e98f62ff083 |
| ORCID | 0009-0001-2097-1299 |
| ParticipantIDs | crossref_primary_10_1016_j_engappai_2025_112735 elsevier_sciencedirect_doi_10_1016_j_engappai_2025_112735 |
| PublicationCentury | 2000 |
| PublicationDate | 2025-12-26 |
| PublicationDateYYYYMMDD | 2025-12-26 |
| PublicationDate_xml | – month: 12 year: 2025 text: 2025-12-26 day: 26 |
| PublicationDecade | 2020 |
| PublicationTitle | Engineering applications of artificial intelligence |
| PublicationYear | 2025 |
| Publisher | Elsevier Ltd |
| Publisher_xml | – name: Elsevier Ltd |
| References | Zhang, Li, Wang, Wang, Lai, Zhang (b42) 2023; 93 Essien, Giannetti (b8) 2020; 16 Cordoni, Bacchiega, Bondani, Radu, Muradore (b5) 2022; 110 Ullah, Hussain, Ullah, Lee, Baik (b31) 2023; 123 Li, Zheng, Tang, Zhu, Huang (b19) 2023; 649 Xu, Wu, Wang, Long (b37) 2021 Deng, Xu, Zhang, Fruehholz, Schuller (b7) 2018; 26 Yan, Shao, Xiao, Liu, Wan (b38) 2023; 79 Huang, Liu, Jin, Xu, Yao (b15) 2024; 24 Deng, Hooi (b6) 2021; vol. 35 Chen, Su, Deng, Huang, Wu, Peng (b3) 2021; vol. 11605 Han, Jhaveri, Wang, Qiao, Du (b12) 2023; 27 Friedman, Khurshid, Venn, Wang, Diamant, Di Achille, Weng, Choi, Reeder, Pirruccello, Singh, Lau, Philippakis, Anderson, Maddah, Batra, Ellinor, Ho, Lubitz (b9) 2025; 8 Souto (b27) 2024; 255 Gelli, Govindarasu (b10) 2024; 15 Su, Y., Zhao, Y., Niu, C., Liu, R., Sun, W., Pei, D., 2019. Robust Anomaly Detection for Multivariate Time Series through Stochastic Recurrent Neural Network. In: KDD’19: Proceedings of the 25TH ACM SIGKDD International Conferencce on Knowledge Discovery and Data Mining. pp. 2828–2837. Zhou, Song, Zhang, Liu, Zhu, Liu (b45) 2022; 33 Chow, Su, Wu, Tan, Mao, Wang (b4) 2020; 45 An, Wang, Zhang (b2) 2022; 59 Kumar, Kumar, Aloqaily, Aljuhani (b18) 2023; 61 Abdar, Pourpanah, Hussain, Rezazadegan, Liu, Ghavamzadeh, Fieguth, Cao, Khosravi, Acharya, Makarenkov, Nahavandi (b1) 2021; 76 Liu, Gong, Chen, Zhou (b22) 2023; 11 Yang, Zhang, Chen, Hu, Gao, Liu, Ping, Song (b39) 2024; 35 Wu, Zhu, Shi, Wang, Wu (b32) 2023; 33 Xiao, Li, Zhu (b34) 2024; 20 Xu, Ding, Li, Dai, Zheng, Yu, Sui (b36) 2022; 618 Trirat, Lee (b30) 2024 Kendall, A., Gal, Y., Cipolla, R., 2018. Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. CVPR, pp. 7482–7491. Zang, Ren, Zhang, Liu (b40) 2018; 81 Li, Zhu, Van Leeuwen (b20) 2023; 18 Liu, Wang, Wang, Xue, Wang, Gao (b24) 2025; 170 Park, Hoshi, Kemp (b25) 2018; 3 Zou, Yang, Kui, Liu, Liao, Zhao (b47) 2023; 638 Huang, Chen, Deng, Huang (b13) 2024; 54 Xie, Dong, Chen, Peng, Li (b35) 2021; 215 Zhu, Yang, Jiang (b46) 2023; 230 Szegedy, Ioffe, Vanhoucke, Alemi (b29) 2017 Guo, Zhou, Chen, Ying, Zhang, Zhou (b11) 2020; 8 Liang, Zhang, Zhao, Wu, Liu, Pan (b21) 2023; 32 Sanguineti, Morerio, Del Bue, Murino (b26) 2022; 31 Kim, Choi, Kim (b17) 2022; 65 Xiang, Ali, Zhang, Jung, Zhou (b33) 2024; 129 Huang, Liu, Cui, Zhang, Li, Zhang, Zhang, Zhang (b14) 2024; 669 Zhang, Shi, Lin, Cao, Guo, Zhang, Li, Yang, Xu (b43) 2025; 72 Zhang, Zhang, Cao, Bian, Yi, Zheng, Li (b44) 2022 Liu, Liu, Zheng, Wang, Mao, Qiu, Ling (b23) 2023; 228 Zhang, Deng (b41) 2021; 148 Li (10.1016/j.engappai.2025.112735_b19) 2023; 649 Zhang (10.1016/j.engappai.2025.112735_b41) 2021; 148 Huang (10.1016/j.engappai.2025.112735_b15) 2024; 24 Liang (10.1016/j.engappai.2025.112735_b21) 2023; 32 Liu (10.1016/j.engappai.2025.112735_b23) 2023; 228 Deng (10.1016/j.engappai.2025.112735_b6) 2021; vol. 35 Yan (10.1016/j.engappai.2025.112735_b38) 2023; 79 Wu (10.1016/j.engappai.2025.112735_b32) 2023; 33 Guo (10.1016/j.engappai.2025.112735_b11) 2020; 8 Xu (10.1016/j.engappai.2025.112735_b36) 2022; 618 Cordoni (10.1016/j.engappai.2025.112735_b5) 2022; 110 Essien (10.1016/j.engappai.2025.112735_b8) 2020; 16 Kim (10.1016/j.engappai.2025.112735_b17) 2022; 65 Zhu (10.1016/j.engappai.2025.112735_b46) 2023; 230 Han (10.1016/j.engappai.2025.112735_b12) 2023; 27 Liu (10.1016/j.engappai.2025.112735_b24) 2025; 170 Yang (10.1016/j.engappai.2025.112735_b39) 2024; 35 Friedman (10.1016/j.engappai.2025.112735_b9) 2025; 8 Zhou (10.1016/j.engappai.2025.112735_b45) 2022; 33 Zhang (10.1016/j.engappai.2025.112735_b44) 2022 Zang (10.1016/j.engappai.2025.112735_b40) 2018; 81 10.1016/j.engappai.2025.112735_b16 Huang (10.1016/j.engappai.2025.112735_b13) 2024; 54 Xiang (10.1016/j.engappai.2025.112735_b33) 2024; 129 Trirat (10.1016/j.engappai.2025.112735_b30) 2024 Chen (10.1016/j.engappai.2025.112735_b3) 2021; vol. 11605 Xu (10.1016/j.engappai.2025.112735_b37) 2021 Huang (10.1016/j.engappai.2025.112735_b14) 2024; 669 Ullah (10.1016/j.engappai.2025.112735_b31) 2023; 123 Chow (10.1016/j.engappai.2025.112735_b4) 2020; 45 Deng (10.1016/j.engappai.2025.112735_b7) 2018; 26 Souto (10.1016/j.engappai.2025.112735_b27) 2024; 255 Li (10.1016/j.engappai.2025.112735_b20) 2023; 18 Liu (10.1016/j.engappai.2025.112735_b22) 2023; 11 Zhang (10.1016/j.engappai.2025.112735_b42) 2023; 93 Gelli (10.1016/j.engappai.2025.112735_b10) 2024; 15 Szegedy (10.1016/j.engappai.2025.112735_b29) 2017 Zhang (10.1016/j.engappai.2025.112735_b43) 2025; 72 Xiao (10.1016/j.engappai.2025.112735_b34) 2024; 20 Abdar (10.1016/j.engappai.2025.112735_b1) 2021; 76 Park (10.1016/j.engappai.2025.112735_b25) 2018; 3 Zou (10.1016/j.engappai.2025.112735_b47) 2023; 638 Xie (10.1016/j.engappai.2025.112735_b35) 2021; 215 Sanguineti (10.1016/j.engappai.2025.112735_b26) 2022; 31 10.1016/j.engappai.2025.112735_b28 An (10.1016/j.engappai.2025.112735_b2) 2022; 59 Kumar (10.1016/j.engappai.2025.112735_b18) 2023; 61 |
| References_xml | – volume: 65 year: 2022 ident: b17 article-title: Data-driven prognostics with low-fidelity physical information for digital twin: physics-informed neural network publication-title: Struct. Multidiscip. Optim. – volume: 76 start-page: 243 year: 2021 end-page: 297 ident: b1 article-title: A review of uncertainty quantification in deep learning: Techniques, applications and challenges publication-title: Inf. Fusion – volume: 123 year: 2023 ident: b31 article-title: Transcnn: Hybrid CNN and transformer mechanism for surveillance anomaly detection publication-title: Eng. Appl. Artif. Intell. – volume: 45 year: 2020 ident: b4 article-title: Anomaly detection of defects on concrete structures with the convolutional autoencoder publication-title: Adv. Eng. Inform. – volume: 8 start-page: 1 year: 2025 end-page: 13 ident: b9 article-title: Unsupervised deep learning of electrocardiograms enables scalable human disease profiling publication-title: Npj Digital Med. – volume: 32 start-page: 4327 year: 2023 end-page: 4340 ident: b21 article-title: Omni-frequency channel-selection representations for unsupervised anomaly detection publication-title: IEEE Trans. Image Process. – volume: 11 year: 2023 ident: b22 article-title: Multi-step-ahead wind speed forecast method based on outlier correction, optimized decomposition, and dlinear model publication-title: Mathematics – year: 2024 ident: b30 article-title: PASTA: Neural architecture search for anomaly detection in multivariate time series publication-title: IEEE Trans. Emerg. Topics Comput. Intell. – volume: 93 start-page: 192 year: 2023 end-page: 208 ident: b42 article-title: A multi-source information fusion model for outlier detection publication-title: Inf. Fusion – volume: 8 start-page: 43992 year: 2020 end-page: 44005 ident: b11 article-title: Variational autoencoder with optimizing Gaussian mixture model priors publication-title: IEEE Access – volume: 54 start-page: 7636 year: 2024 end-page: 7658 ident: b13 article-title: Multivariate time series anomaly detection via dynamic graph attention network and informer publication-title: Appl. Intell. – volume: 35 start-page: 95 year: 2024 end-page: 113 ident: b39 article-title: Surface defect detection method for air rudder based on positive samples publication-title: J. Intell. Manuf. – volume: 170 year: 2025 ident: b24 article-title: Method for predicting remaining useful life of rolling bearings based on dynamic complexity characteristic entropy and quantum neural networks publication-title: Eng. Fail. Anal. – volume: 228 year: 2023 ident: b23 article-title: Anomaly-GAN: A data augmentation method for train surface anomaly detection publication-title: Expert Syst. Appl. – volume: 129 year: 2024 ident: b33 article-title: Pixel-associated autoencoder for hyperspectral anomaly detection publication-title: Int. J. Appl. Earth Obs. Geoinf. – year: 2022 ident: b44 article-title: Less is more: Fast multivariate time series forecasting with light sampling-oriented MLP structures – volume: 18 start-page: 1 year: 2023 end-page: 54 ident: b20 article-title: A survey on explainable anomaly detection publication-title: ACM Trans. Knowl. Discov. Data – volume: 31 start-page: 7102 year: 2022 end-page: 7115 ident: b26 article-title: Unsupervised synthetic acoustic image generation for audio-visual scene understanding publication-title: IEEE Trans. Image Process. – volume: 26 start-page: 31 year: 2018 end-page: 43 ident: b7 article-title: Semisupervised autoencoders for speech emotion recognition publication-title: IEEE-ACM Trans. Audio Speech Lang. Process. – volume: 20 start-page: 9320 year: 2024 end-page: 9329 ident: b34 article-title: Seq publication-title: IEEE Trans. Ind. Inform. – volume: 24 start-page: 12770 year: 2024 end-page: 12781 ident: b15 article-title: Improved autoencoder model with memory module for anomaly detection publication-title: IEEE Sens. J. – volume: vol. 35 start-page: 4027 year: 2021 end-page: 4035 ident: b6 article-title: Graph neural network-based anomaly detection in multivariate time series publication-title: Proceedings of the AAAI Conference on Artificial Intelligence – volume: 15 start-page: 5939 year: 2024 end-page: 5951 ident: b10 article-title: Anomaly detection and mitigation for wide-area damping control using machine learning publication-title: IEEE Trans. Smart Grid – volume: 255 year: 2024 ident: b27 article-title: Charting new avenues in financial forecasting with TimesNet: The impact of intraperiod and interperiod variations on realized volatility prediction publication-title: Expert Syst. Appl. – volume: 27 start-page: 804 year: 2023 end-page: 813 ident: b12 article-title: Application of robust zero-watermarking scheme based on federated learning for securing the healthcare data publication-title: IEEE J. Biomed. Health Inform. – reference: Kendall, A., Gal, Y., Cipolla, R., 2018. Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. CVPR, pp. 7482–7491. – volume: 3 start-page: 1544 year: 2018 end-page: 1551 ident: b25 article-title: A multimodal anomaly detector for robot-assisted feeding using an LSTM-based variational autoencoder publication-title: IEEE Robot. Autom. Lett. – volume: 16 start-page: 6069 year: 2020 end-page: 6078 ident: b8 article-title: A deep learning model for smart manufacturing using convolutional LSTM neural network autoencoders publication-title: IEEE Trans. Ind. Inform. – volume: 649 year: 2023 ident: b19 article-title: Few-shot time-series anomaly detection with unsupervised domain adaptation publication-title: Inf. Sci. – year: 2021 ident: b37 article-title: Anomaly transformer: Time series anomaly detection with association discrepancy – volume: 618 start-page: 336 year: 2022 end-page: 355 ident: b36 article-title: A new Bayesian network model for risk assessment based on cloud model, interval type-2 fuzzy sets and improved D-S evidence theory publication-title: Inf. Sci. – volume: 669 year: 2024 ident: b14 article-title: MEAformer: An all-MLP transformer with temporal external attention for long-term time series forecasting publication-title: Inform. Sci. – reference: Su, Y., Zhao, Y., Niu, C., Liu, R., Sun, W., Pei, D., 2019. Robust Anomaly Detection for Multivariate Time Series through Stochastic Recurrent Neural Network. In: KDD’19: Proceedings of the 25TH ACM SIGKDD International Conferencce on Knowledge Discovery and Data Mining. pp. 2828–2837. – volume: 230 year: 2023 ident: b46 article-title: Identifying crucial deficiency categories influencing ship detention: A method of combining cloud model and prospect theory publication-title: Reliab. Eng. Syst. Saf. – start-page: 4278 year: 2017 end-page: 4284 ident: b29 article-title: Inception-v4, inception-ResNet and the impact of residual connections on learning publication-title: Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence (AAAI-17) – volume: 148 start-page: 1 year: 2021 end-page: 6 ident: b41 article-title: Anomaly detection using improved deep SVDD model with data structure preservation publication-title: Pattern Recognit. Lett. – volume: 215 year: 2021 ident: b35 article-title: A novel risk evaluation method for fire and explosion accidents in oil depots using bow-tie analysis and risk matrix analysis method based on cloud model theory publication-title: Reliab. Eng. Syst. Saf. – volume: vol. 11605 start-page: 42 year: 2021 end-page: 48 ident: b3 article-title: Weak anomaly-reinforced autoencoder for unsupervised anomaly detection publication-title: Thirteenth International Conference on Machine Vision – volume: 79 year: 2023 ident: b38 article-title: Hybrid robust convolutional autoencoder for unsupervised anomaly detection of machine tools under noises publication-title: Robotics Computer-Integrated Manuf. – volume: 33 start-page: 2454 year: 2022 end-page: 2465 ident: b45 article-title: Feature encoding with autoencoders for weakly supervised anomaly detection publication-title: IEEE Trans. Neural Netw. Learn. Syst. – volume: 61 start-page: 96 year: 2023 end-page: 102 ident: b18 article-title: Deep-learning-based blockchain for secure zero touch networks publication-title: IEEE Commun. Mag. – volume: 59 year: 2022 ident: b2 article-title: Ensemble unsupervised autoencoders and Gaussian mixture model for cyberattack detection publication-title: Inf. Process. Manag. – volume: 33 start-page: 1374 year: 2023 end-page: 1385 ident: b32 article-title: Self-attention memory-augmented wavelet-CNN for anomaly detection publication-title: IEEE Trans. Circuits Syst. Video Technol. – volume: 81 start-page: 465 year: 2018 end-page: 477 ident: b40 article-title: A cloud model based DNA genetic algorithm for numerical optimization problems publication-title: Future Gener. Comput. Syst.- Int. J. Escience – volume: 72 start-page: 238 year: 2025 end-page: 248 ident: b43 article-title: Attenuation tomography using low-frequency ultrasound with variational autoencoder for thorax imaging: Experimental study publication-title: IEEE Trans. Biomed. Eng. – volume: 110 year: 2022 ident: b5 article-title: A multi-modal unsupervised fault detection system based on power signals and thermal imaging via deep AutoEncoder neural network publication-title: Eng. Appl. Artif. Intell. – volume: 638 year: 2023 ident: b47 article-title: Anomaly detection for streaming data based on grid-clustering and Gaussian distribution publication-title: Inf. Sci. – volume: 3 start-page: 1544 year: 2018 ident: 10.1016/j.engappai.2025.112735_b25 article-title: A multimodal anomaly detector for robot-assisted feeding using an LSTM-based variational autoencoder publication-title: IEEE Robot. Autom. Lett. doi: 10.1109/LRA.2018.2801475 – ident: 10.1016/j.engappai.2025.112735_b28 doi: 10.1145/3292500.3330672 – volume: 669 year: 2024 ident: 10.1016/j.engappai.2025.112735_b14 article-title: MEAformer: An all-MLP transformer with temporal external attention for long-term time series forecasting publication-title: Inform. Sci. doi: 10.1016/j.ins.2024.120605 – volume: 31 start-page: 7102 year: 2022 ident: 10.1016/j.engappai.2025.112735_b26 article-title: Unsupervised synthetic acoustic image generation for audio-visual scene understanding publication-title: IEEE Trans. Image Process. doi: 10.1109/TIP.2022.3219228 – volume: 215 year: 2021 ident: 10.1016/j.engappai.2025.112735_b35 article-title: A novel risk evaluation method for fire and explosion accidents in oil depots using bow-tie analysis and risk matrix analysis method based on cloud model theory publication-title: Reliab. Eng. Syst. Saf. doi: 10.1016/j.ress.2021.107791 – volume: 72 start-page: 238 year: 2025 ident: 10.1016/j.engappai.2025.112735_b43 article-title: Attenuation tomography using low-frequency ultrasound with variational autoencoder for thorax imaging: Experimental study publication-title: IEEE Trans. Biomed. Eng. doi: 10.1109/TBME.2024.3447058 – volume: 33 start-page: 2454 year: 2022 ident: 10.1016/j.engappai.2025.112735_b45 article-title: Feature encoding with autoencoders for weakly supervised anomaly detection publication-title: IEEE Trans. Neural Netw. Learn. Syst. doi: 10.1109/TNNLS.2021.3086137 – volume: 15 start-page: 5939 year: 2024 ident: 10.1016/j.engappai.2025.112735_b10 article-title: Anomaly detection and mitigation for wide-area damping control using machine learning publication-title: IEEE Trans. Smart Grid doi: 10.1109/TSG.2020.2995313 – volume: 32 start-page: 4327 year: 2023 ident: 10.1016/j.engappai.2025.112735_b21 article-title: Omni-frequency channel-selection representations for unsupervised anomaly detection publication-title: IEEE Trans. Image Process. doi: 10.1109/TIP.2023.3293772 – volume: 123 year: 2023 ident: 10.1016/j.engappai.2025.112735_b31 article-title: Transcnn: Hybrid CNN and transformer mechanism for surveillance anomaly detection publication-title: Eng. Appl. Artif. Intell. doi: 10.1016/j.engappai.2023.106173 – volume: 148 start-page: 1 year: 2021 ident: 10.1016/j.engappai.2025.112735_b41 article-title: Anomaly detection using improved deep SVDD model with data structure preservation publication-title: Pattern Recognit. Lett. doi: 10.1016/j.patrec.2021.04.020 – volume: 76 start-page: 243 year: 2021 ident: 10.1016/j.engappai.2025.112735_b1 article-title: A review of uncertainty quantification in deep learning: Techniques, applications and challenges publication-title: Inf. Fusion doi: 10.1016/j.inffus.2021.05.008 – volume: 8 start-page: 1 year: 2025 ident: 10.1016/j.engappai.2025.112735_b9 article-title: Unsupervised deep learning of electrocardiograms enables scalable human disease profiling publication-title: Npj Digital Med. doi: 10.1038/s41746-024-01418-9 – volume: 65 year: 2022 ident: 10.1016/j.engappai.2025.112735_b17 article-title: Data-driven prognostics with low-fidelity physical information for digital twin: physics-informed neural network publication-title: Struct. Multidiscip. Optim. doi: 10.1007/s00158-022-03348-0 – volume: 27 start-page: 804 year: 2023 ident: 10.1016/j.engappai.2025.112735_b12 article-title: Application of robust zero-watermarking scheme based on federated learning for securing the healthcare data publication-title: IEEE J. Biomed. Health Inform. doi: 10.1109/JBHI.2021.3123936 – volume: 129 year: 2024 ident: 10.1016/j.engappai.2025.112735_b33 article-title: Pixel-associated autoencoder for hyperspectral anomaly detection publication-title: Int. J. Appl. Earth Obs. Geoinf. – volume: 255 issue: D year: 2024 ident: 10.1016/j.engappai.2025.112735_b27 article-title: Charting new avenues in financial forecasting with TimesNet: The impact of intraperiod and interperiod variations on realized volatility prediction publication-title: Expert Syst. Appl. – volume: 649 year: 2023 ident: 10.1016/j.engappai.2025.112735_b19 article-title: Few-shot time-series anomaly detection with unsupervised domain adaptation publication-title: Inf. Sci. doi: 10.1016/j.ins.2023.119610 – volume: 26 start-page: 31 year: 2018 ident: 10.1016/j.engappai.2025.112735_b7 article-title: Semisupervised autoencoders for speech emotion recognition publication-title: IEEE-ACM Trans. Audio Speech Lang. Process. doi: 10.1109/TASLP.2017.2759338 – start-page: 4278 year: 2017 ident: 10.1016/j.engappai.2025.112735_b29 article-title: Inception-v4, inception-ResNet and the impact of residual connections on learning – volume: 618 start-page: 336 year: 2022 ident: 10.1016/j.engappai.2025.112735_b36 article-title: A new Bayesian network model for risk assessment based on cloud model, interval type-2 fuzzy sets and improved D-S evidence theory publication-title: Inf. Sci. doi: 10.1016/j.ins.2022.11.011 – volume: 8 start-page: 43992 year: 2020 ident: 10.1016/j.engappai.2025.112735_b11 article-title: Variational autoencoder with optimizing Gaussian mixture model priors publication-title: IEEE Access doi: 10.1109/ACCESS.2020.2977671 – volume: 24 start-page: 12770 year: 2024 ident: 10.1016/j.engappai.2025.112735_b15 article-title: Improved autoencoder model with memory module for anomaly detection publication-title: IEEE Sens. J. doi: 10.1109/JSEN.2024.3370965 – volume: 11 issue: 12 year: 2023 ident: 10.1016/j.engappai.2025.112735_b22 article-title: Multi-step-ahead wind speed forecast method based on outlier correction, optimized decomposition, and dlinear model publication-title: Mathematics doi: 10.3390/math11122746 – volume: 54 start-page: 7636 issue: 17 year: 2024 ident: 10.1016/j.engappai.2025.112735_b13 article-title: Multivariate time series anomaly detection via dynamic graph attention network and informer publication-title: Appl. Intell. doi: 10.1007/s10489-024-05575-y – volume: 230 year: 2023 ident: 10.1016/j.engappai.2025.112735_b46 article-title: Identifying crucial deficiency categories influencing ship detention: A method of combining cloud model and prospect theory publication-title: Reliab. Eng. Syst. Saf. doi: 10.1016/j.ress.2022.108949 – volume: 18 start-page: 1 issue: 1 year: 2023 ident: 10.1016/j.engappai.2025.112735_b20 article-title: A survey on explainable anomaly detection publication-title: ACM Trans. Knowl. Discov. Data – volume: 81 start-page: 465 year: 2018 ident: 10.1016/j.engappai.2025.112735_b40 article-title: A cloud model based DNA genetic algorithm for numerical optimization problems publication-title: Future Gener. Comput. Syst.- Int. J. Escience doi: 10.1016/j.future.2017.07.036 – year: 2021 ident: 10.1016/j.engappai.2025.112735_b37 – year: 2024 ident: 10.1016/j.engappai.2025.112735_b30 article-title: PASTA: Neural architecture search for anomaly detection in multivariate time series publication-title: IEEE Trans. Emerg. Topics Comput. Intell. – volume: 638 year: 2023 ident: 10.1016/j.engappai.2025.112735_b47 article-title: Anomaly detection for streaming data based on grid-clustering and Gaussian distribution publication-title: Inf. Sci. doi: 10.1016/j.ins.2023.118989 – volume: 45 year: 2020 ident: 10.1016/j.engappai.2025.112735_b4 article-title: Anomaly detection of defects on concrete structures with the convolutional autoencoder publication-title: Adv. Eng. Inform. doi: 10.1016/j.aei.2020.101105 – volume: 35 start-page: 95 year: 2024 ident: 10.1016/j.engappai.2025.112735_b39 article-title: Surface defect detection method for air rudder based on positive samples publication-title: J. Intell. Manuf. doi: 10.1007/s10845-022-02034-8 – year: 2022 ident: 10.1016/j.engappai.2025.112735_b44 – volume: 16 start-page: 6069 year: 2020 ident: 10.1016/j.engappai.2025.112735_b8 article-title: A deep learning model for smart manufacturing using convolutional LSTM neural network autoencoders publication-title: IEEE Trans. Ind. Inform. doi: 10.1109/TII.2020.2967556 – ident: 10.1016/j.engappai.2025.112735_b16 doi: 10.1109/CVPR.2018.00781 – volume: 61 start-page: 96 year: 2023 ident: 10.1016/j.engappai.2025.112735_b18 article-title: Deep-learning-based blockchain for secure zero touch networks publication-title: IEEE Commun. Mag. doi: 10.1109/MCOM.001.2200294 – volume: vol. 35 start-page: 4027 year: 2021 ident: 10.1016/j.engappai.2025.112735_b6 article-title: Graph neural network-based anomaly detection in multivariate time series – volume: 33 start-page: 1374 year: 2023 ident: 10.1016/j.engappai.2025.112735_b32 article-title: Self-attention memory-augmented wavelet-CNN for anomaly detection publication-title: IEEE Trans. Circuits Syst. Video Technol. doi: 10.1109/TCSVT.2022.3211839 – volume: 110 year: 2022 ident: 10.1016/j.engappai.2025.112735_b5 article-title: A multi-modal unsupervised fault detection system based on power signals and thermal imaging via deep AutoEncoder neural network publication-title: Eng. Appl. Artif. Intell. doi: 10.1016/j.engappai.2022.104729 – volume: 228 year: 2023 ident: 10.1016/j.engappai.2025.112735_b23 article-title: Anomaly-GAN: A data augmentation method for train surface anomaly detection publication-title: Expert Syst. Appl. doi: 10.1016/j.eswa.2023.120284 – volume: 79 year: 2023 ident: 10.1016/j.engappai.2025.112735_b38 article-title: Hybrid robust convolutional autoencoder for unsupervised anomaly detection of machine tools under noises publication-title: Robotics Computer-Integrated Manuf. doi: 10.1016/j.rcim.2022.102441 – volume: 170 year: 2025 ident: 10.1016/j.engappai.2025.112735_b24 article-title: Method for predicting remaining useful life of rolling bearings based on dynamic complexity characteristic entropy and quantum neural networks publication-title: Eng. Fail. Anal. doi: 10.1016/j.engfailanal.2025.109315 – volume: 20 start-page: 9320 year: 2024 ident: 10.1016/j.engappai.2025.112735_b34 article-title: Seqα GAN: Sign language sequence generation based on variational and adversarial learning publication-title: IEEE Trans. Ind. Inform. doi: 10.1109/TII.2024.3378834 – volume: vol. 11605 start-page: 42 year: 2021 ident: 10.1016/j.engappai.2025.112735_b3 article-title: Weak anomaly-reinforced autoencoder for unsupervised anomaly detection – volume: 59 year: 2022 ident: 10.1016/j.engappai.2025.112735_b2 article-title: Ensemble unsupervised autoencoders and Gaussian mixture model for cyberattack detection publication-title: Inf. Process. Manag. doi: 10.1016/j.ipm.2021.102844 – volume: 93 start-page: 192 year: 2023 ident: 10.1016/j.engappai.2025.112735_b42 article-title: A multi-source information fusion model for outlier detection publication-title: Inf. Fusion doi: 10.1016/j.inffus.2022.12.027 |
| SSID | ssj0003846 |
| Score | 2.444343 |
| Snippet | To avoid severe malfunctions of industrial equipment, it is necessary to perform accurate detection in the early stages of abnormal occurrences. However, early... |
| SourceID | crossref elsevier |
| SourceType | Index Database Publisher |
| StartPage | 112735 |
| SubjectTerms | Autoencoder Early weak anomaly detection Multi-task learning Uncertainty |
| Title | Early weak anomaly detection and uncertainty quantification of equipment based on multi-task and multi-domain temporal memory autoencoder |
| URI | https://dx.doi.org/10.1016/j.engappai.2025.112735 |
| Volume | 162 |
| WOSCitedRecordID | wos001601106800002&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVESC databaseName: ScienceDirect Freedom Collection - Elsevier issn: 0952-1976 databaseCode: AIEXJ dateStart: 19950201 customDbUrl: isFulltext: true dateEnd: 99991231 titleUrlDefault: https://www.sciencedirect.com omitProxy: false ssIdentifier: ssj0003846 providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Jb9QwFLaGKQcuUDa1bPKB2yjDOJPE9rFCRZRDxaFIc4uc2EZpadLOJKX8hP6B_l6etySFCuiBSzR5kh3PvG_elrcg9DaRYplmJY8SKQtwUBSLRMrTSBr9zs1sh0TaYRP08JCtVvzzZHIdamEuvtG6ZpeX_Oy_shpowGxTOnsHdvebAgE-A9PhCmyH6z8x3rUs_q7EyUzUzamAG6la5UeC13IGmszlAYD9fd4Jly3UW47qvKtsDtHMKDhpXibYpMOoFZsTu97dStja5Ei61lamBOXUvK4XXduY3pjSZ_2GoP_Q9nA2fmdu0xDW9gR2esioQWifKlS5tAA46bqrhgi6iyj8aLzq9ZGLODVZIK48vg9BxhHhbv5LL429cHbyFKxB6tqZ_CbqXdTheK7qr3BuUc3NI-bDgpu9tX_ReX0mYkhyO87DPrnZJ3f73ENbMU05m6KtvYP91adexy-ZKwEL32BUe377iW43e0amzNE2euh9ELznsPMYTVT9BD3y_gj20n4DpDDyI9CeoiuLLmzQhT26cI8uoEg8Qhe-iS7caNyjC1t0YaAO6LLrx-jCAV3YoQuP0PUMffmwf_T-Y-SneUQleOltRMSCUpVkixjEQ6aXSpeEFQtekERTXpYx16qUojDdkYiKU8nAEyeKM53FWoOn8BxN66ZWOwgnRJOSckULRUCckIIJ05YvU0Jr8JDlLnoXfuz8zDVtyf_M6F3EA09yb3o6kzIHuP1l7Ys7P-0lejD8H16habvu1Gt0v7xoq836jcfaT2cZsjU |
| linkProvider | Elsevier |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Early+weak+anomaly+detection+and+uncertainty+quantification+of+equipment+based+on+multi-task+and+multi-domain+temporal+memory+autoencoder&rft.jtitle=Engineering+applications+of+artificial+intelligence&rft.au=Li%2C+Chuanrui&rft.au=Ma%2C+Liyong&rft.date=2025-12-26&rft.issn=0952-1976&rft.volume=162&rft.spage=112735&rft_id=info:doi/10.1016%2Fj.engappai.2025.112735&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_engappai_2025_112735 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0952-1976&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0952-1976&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0952-1976&client=summon |