A robust operators’ cognitive workload recognition method based on denoising masked autoencoder
Identifying the cognitive workload of operators is crucial in complex human-automation collaboration systems. An excessive workload can lead to fatigue or accidents, while an insufficient workload may diminish situational awareness and efficiency. However, existing supervised learning-based methods...
Saved in:
| Published in: | Knowledge-based systems Vol. 301; p. 112370 |
|---|---|
| Main Authors: | , |
| Format: | Journal Article |
| Language: | English |
| Published: |
Elsevier B.V
09.10.2024
|
| Subjects: | |
| ISSN: | 0950-7051 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | Identifying the cognitive workload of operators is crucial in complex human-automation collaboration systems. An excessive workload can lead to fatigue or accidents, while an insufficient workload may diminish situational awareness and efficiency. However, existing supervised learning-based methods for workload recognition are ineffective when dealing with imperfect input data, such as missing or noisy data, which is not practical in real applications. This study introduces a robust Electroencephalogram (EEG)-enabled cognitive workload recognition model using self-supervised learning. The proposed method, DMAEEG, combines the training strategies of denoising autoencoders and masked autoencoders, demonstrating strong robustness against noisy and incomplete data. More specifically, we adopt the temporal convolutional network and multi-head self-attention mechanisms as the backbone, effectively capturing both the temporal and spatial features from EEG. Extensive experiments are conducted to verify the effectiveness and robustness of the proposed method on an open dataset and a self-collected dataset. The results indicate that DMAEEG performs superior to other state-of-the-art across various evaluation metrics. Moreover, DMAEEG maintains high accuracy in workload inference even when EEG signals are corrupted with a high masking ratio or strong noises. This signifies its superiority in capturing robust intrinsic patterns from imperfect EEG data. The proposed method significantly contributes to decoding EEG signals for workload recognition in real-world applications, thereby enhancing the safety and reliability of human-automation interactions.
•A robust cognitive workload recognition approach is proposed.•Self-supervised learning is used to train the model and acquire robust features.•The training strategies of denoising and masked autoencoder are incorporated.•The proposed model performs superior to state-of-the-art baselines.•The accuracy of the model remains high with both sound and corrupted EEG signals. |
|---|---|
| AbstractList | Identifying the cognitive workload of operators is crucial in complex human-automation collaboration systems. An excessive workload can lead to fatigue or accidents, while an insufficient workload may diminish situational awareness and efficiency. However, existing supervised learning-based methods for workload recognition are ineffective when dealing with imperfect input data, such as missing or noisy data, which is not practical in real applications. This study introduces a robust Electroencephalogram (EEG)-enabled cognitive workload recognition model using self-supervised learning. The proposed method, DMAEEG, combines the training strategies of denoising autoencoders and masked autoencoders, demonstrating strong robustness against noisy and incomplete data. More specifically, we adopt the temporal convolutional network and multi-head self-attention mechanisms as the backbone, effectively capturing both the temporal and spatial features from EEG. Extensive experiments are conducted to verify the effectiveness and robustness of the proposed method on an open dataset and a self-collected dataset. The results indicate that DMAEEG performs superior to other state-of-the-art across various evaluation metrics. Moreover, DMAEEG maintains high accuracy in workload inference even when EEG signals are corrupted with a high masking ratio or strong noises. This signifies its superiority in capturing robust intrinsic patterns from imperfect EEG data. The proposed method significantly contributes to decoding EEG signals for workload recognition in real-world applications, thereby enhancing the safety and reliability of human-automation interactions.
•A robust cognitive workload recognition approach is proposed.•Self-supervised learning is used to train the model and acquire robust features.•The training strategies of denoising and masked autoencoder are incorporated.•The proposed model performs superior to state-of-the-art baselines.•The accuracy of the model remains high with both sound and corrupted EEG signals. |
| ArticleNumber | 112370 |
| Author | Chen, Chun-Hsien Yu, Xiaoqing |
| Author_xml | – sequence: 1 givenname: Xiaoqing orcidid: 0009-0006-7451-6204 surname: Yu fullname: Yu, Xiaoqing email: XIAOQING003@e.ntu.edu.sg – sequence: 2 givenname: Chun-Hsien orcidid: 0000-0003-2193-5270 surname: Chen fullname: Chen, Chun-Hsien email: mchchen@ntu.edu.sg |
| BookMark | eNqFkE1OwzAQhb0oEi1wAxa-QIIncZqGBVJV8SdVYgNry8lMivtjV7Zb1B3X4HqchFTpigWsRvOk9_TeN2ID6ywxdg0iBQHjm2W6si4cQpqJTKYAWV6KARuKqhBJKQo4Z6MQlkKILIPJkOkp967ehcjdlryOzofvzy_euIU10eyJfzi_WjuN3NNJdJZvKL475LUOhLz7kawzwdgF3-iw6jS9i45s45D8JTtr9TrQ1elesLeH-9fZUzJ_eXyeTedJ0zWJSQlSA9albEi3OQJKmckxQt1WgGUt87LNCyxQTAopkYjynCaAUDVQFRXJ_ILd9rmNdyF4alVjoj7WjV6btQKhjoDUUvWA1BGQ6gF1ZvnLvPVmo_3hP9tdb6Nu2N6QV6Ex3W5C0-GKCp35O-AHlZ2J_A |
| CitedBy_id | crossref_primary_10_1016_j_neucom_2025_130418 crossref_primary_10_1016_j_aei_2024_102784 crossref_primary_10_1016_j_aei_2024_102971 crossref_primary_10_1016_j_aei_2025_103506 crossref_primary_10_1016_j_eswa_2025_127418 crossref_primary_10_1080_09544828_2025_2509056 crossref_primary_10_1016_j_aei_2024_103065 crossref_primary_10_1049_bme2_7626919 crossref_primary_10_1016_j_aei_2025_103259 crossref_primary_10_1145_3736574 |
| Cites_doi | 10.1088/1741-2552/abbd50 10.1145/3422622 10.1088/1741-2552/ac2bf8 10.1016/j.aei.2023.102123 10.1016/j.neucom.2014.08.092 10.1109/TITS.2023.3316203 10.1016/j.bspc.2011.02.001 10.1080/00207543.2023.2172473 10.1109/TIM.2017.2759398 10.1016/j.bspc.2021.103070 10.1109/TNSRE.2022.3140456 10.1016/j.bspc.2021.103094 10.1109/TNSRE.2022.3201197 10.1007/s10111-018-0464-4 10.1080/00140139.2021.2016998 10.1016/j.knosys.2024.112086 10.3390/s21155019 10.1109/THMS.2014.2366914 10.1016/j.patcog.2017.12.002 10.1016/j.neucom.2020.04.029 10.1016/j.bspc.2024.106046 10.1016/j.neucom.2019.05.108 10.1016/j.neuroimage.2022.119586 10.1145/3503161.3548243 10.1016/j.knosys.2024.111523 10.1109/TNSRE.2019.2913400 10.1016/j.bspc.2021.103292 10.1109/TCDS.2021.3114162 10.1109/CVPR52688.2022.01553 10.1109/TNSRE.2017.2701002 10.1016/j.bspc.2024.106131 10.1145/3577190.3614113 10.1177/00187208221077804 10.1016/j.rcim.2023.102659 10.1109/TNSRE.2022.3174821 10.1109/TPAMI.2023.3314762 10.1109/TNSRE.2018.2872924 10.1109/TCDS.2021.3090217 10.1109/TIE.2023.3288182 10.1145/3582272 10.1016/j.knosys.2022.110179 |
| ContentType | Journal Article |
| Copyright | 2024 Elsevier B.V. |
| Copyright_xml | – notice: 2024 Elsevier B.V. |
| DBID | AAYXX CITATION |
| DOI | 10.1016/j.knosys.2024.112370 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| ExternalDocumentID | 10_1016_j_knosys_2024_112370 S0950705124010049 |
| GroupedDBID | --K --M .DC .~1 0R~ 1B1 1~. 1~5 4.4 457 4G. 5VS 7-5 71M 77K 8P~ 9JN AACTN AAEDT AAEDW AAIKJ AAKOC AALRI AAOAW AAQFI AAXKI AAXUO AAYFN ABAOU ABBOA ABIVO ABJNI ABMAC ACDAQ ACGFS ACRLP ACZNC ADBBV ADEZE ADGUI ADTZH AEBSH AECPX AEKER AENEX AFKWA AFTJW AGHFR AGUBO AGYEJ AHHHB AHJVU AHZHX AIALX AIEXJ AIKHN AITUG AJOXV AKRWK ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOUOD ARUGR AXJTR BJAXD BKOJK BLXMC CS3 DU5 EBS EFJIC EO8 EO9 EP2 EP3 FDB FIRID FNPLU FYGXN G-Q GBLVA GBOLZ IHE J1W JJJVA KOM MHUIS MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. PQQKQ Q38 RIG ROL RPZ SDF SDG SDP SES SEW SPC SPCBC SST SSV SSW SSZ T5K WH7 XPP ZMT ~02 ~G- 29L 77I 9DU AAQXK AATTM AAYWO AAYXX ABDPE ABWVN ABXDB ACLOT ACNNM ACRPL ACVFH ADCNI ADJOM ADMUD ADNMO AEIPS AEUPX AFJKZ AFPUW AGQPQ AIGII AIIUN AKBMS AKYEP ANKPU APXCP ASPBG AVWKF AZFZN CITATION EFKBS EFLBG EJD FEDTE FGOYB G-2 HLZ HVGLF HZ~ LG9 LY7 M41 R2- SBC SET UHS WUQ ~HD |
| ID | FETCH-LOGICAL-c221t-714a1db74ceaf3d1d44246d1bf91d7b437f35d5d08544deee33e81d19c1959e43 |
| ISSN | 0950-7051 |
| IngestDate | Sat Nov 29 01:33:42 EST 2025 Tue Nov 18 21:24:39 EST 2025 Sat Sep 07 15:51:21 EDT 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Robustness Masked autoencoder Cognitive workload EEG Self-supervised learning |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c221t-714a1db74ceaf3d1d44246d1bf91d7b437f35d5d08544deee33e81d19c1959e43 |
| ORCID | 0009-0006-7451-6204 0000-0003-2193-5270 |
| ParticipantIDs | crossref_citationtrail_10_1016_j_knosys_2024_112370 crossref_primary_10_1016_j_knosys_2024_112370 elsevier_sciencedirect_doi_10_1016_j_knosys_2024_112370 |
| PublicationCentury | 2000 |
| PublicationDate | 2024-10-09 |
| PublicationDateYYYYMMDD | 2024-10-09 |
| PublicationDate_xml | – month: 10 year: 2024 text: 2024-10-09 day: 09 |
| PublicationDecade | 2020 |
| PublicationTitle | Knowledge-based systems |
| PublicationYear | 2024 |
| Publisher | Elsevier B.V |
| Publisher_xml | – name: Elsevier B.V |
| References | Wu, Zhou, Yang, Huang, Lv (b43) 2023; 45 Tan, Gui, Qiu (b45) 2024; 290 Zhang, Wang, Chen, You, Zhang (b56) 2019; 27 Li, Ng, Simon, Yiu, Lyu (b9) 2023; 260 D. Pulver, P. Angkan, P. Hungler, A. Etemad, EEG-based Cognitive Load Classification using Feature Masked Autoencoding and Emotion Transfer Learning, in: Proceedings of the 25th International Conference on Multimodal Interaction, 2023, pp. 190–197. Zhou, Xu, Niu, Wang, Wen, Wu, Zhang (b21) 2022; 30 Makowski, Pham, Lau, Brammer, Lespinasse, Pham, Schölzel, Chen (b50) 2021 Li, Struzik, Zhang, Cichocki (b38) 2015; 165 C. Lee, F. Imrie, M. van der Schaar, Self-supervision enhanced feature selection with correlated gates, in: International Conference on Learning Representations, 2022. Chuang, Chang, Huang, Jung (b13) 2022; 263 Zhang, Yin, Wang (b22) 2014; 45 Pagnotta, Jacobs, de Frutos, Rodríguez, Ibáñez-Gijón, Travieso (b54) 2022; 65 Huang, Liu, Peng (b28) 2022; 71 Wu, Ye, Gu, Zhang, Wang, He (b49) 2022 Yu, Chen, Yang (b7) 2023; 57 K. He, X. Chen, S. Xie, Y. Li, P. Dollár, R. Girshick, Masked autoencoders are scalable vision learners, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 16000–16009. Cheema, Samima, Sarma, Samanta (b23) 2018 Panagou, Neumann, Fruggiero (b1) 2024; 62 Wang, Han, Peng, Zhao, Fan, Meng, Xu, Niu, Cheng, Liu (b30) 2024; 92 Stergiadis, Kostaridou, Klados (b12) 2022; 72 Fu, Chen, Huang, Chen, Duan, Li, Wu, Jiang, Gao, Gu (b34) 2022; 30 R. Li, Y. Wang, W.-L. Zheng, B.-L. Lu, A multi-view spectral-spatial-temporal masked autoencoder for decoding emotions with self-supervised learning, in: Proceedings of the 30th ACM International Conference on Multimedia, 2022, pp. 6–14. Huang, Liu, Peng (b58) 2022; 71 Goodfellow, Pouget-Abadie, Mirza, Xu, Warde-Farley, Ozair, Courville, Bengio (b33) 2020; 63 Amadori, Fischer, Wang, Demiris (b57) 2022; 14 Klados, Papadelis, Braun, Bamidis (b11) 2011; 6 Ji, Tang, Wang, Xie, Liu, Yin (b29) 2023; 230 Sun, Su, Wu, Wu (b15) 2020; 404 Li, Wu, Xia, He, Jin (b8) 2020; 17 Yang, Wu, Hu, Lv (b27) 2024; 71 Zhang, Zhong, Liu (b36) 2022 Dimitrakopoulos, Kakkos, Dai, Lim, deSouza, Bezerianos, Sun (b20) 2017; 25 van de Merwe, Mallam, Nazir (b5) 2024; 66 Nagar, Kumar (b40) 2022; 30 Jiao, Deng, Luo, Lu (b35) 2020; 408 Paszke, Gross, Massa, Lerer, Bradbury, Chanan, Killeen, Lin, Gimelshein, Antiga (b55) 2019; 32 Liu, Zhang, Hou, Mian, Wang, Zhang, Tang (b31) 2021; 35 Leite, Pereira, Gurjao, Veloso (b41) 2018 Kosch, Karolus, Zagermann, Reiterer, Schmidt, Woźniak (b6) 2023; 55 Chen, Xu, Liu, McKeown, Wang (b10) 2017; 67 Rafiei, Gauthier, Adeli, Takabi (b37) 2022 Padhmashree, Bhattacharyya (b18) 2022; 238 Vaswani, Shazeer, Parmar, Uszkoreit, Jones, Gomez, Kaiser, Polosukhin (b51) 2017; 30 Yang, Liu, Hu, Nguyen, Guerra, Lv (b3) 2024; 25 Lyu, Li, Lee, Chen (b2) 2024 Zhou, Huang, Xu, Wang, Wu, Zhang (b17) 2021; 14 Jiao, Gao, Wang, Li, Xu (b24) 2018; 76 Chakladar, Dey, Roy, Dogra (b26) 2020; 60 Weng, Gu, Guo, Ma, Yang, Liu, Chen (b32) 2024 Zhang, Zhao, Wei, Mantini, Li, Liu (b14) 2021; 18 Laybidi, Rasoulzadeh, Dianat, Samavati, Jafarabadi, Nazari (b19) 2022; 252 Zhang, Ding, Hui, Liu, Guo, Wang (b4) 2024; 86 Lim, Sourina, Wang (b52) 2018; 26 Cai, Zeng (b39) 2024; 94 Gupta, Taori, Ladekar, Manthalkar, Gajre, Joshi (b25) 2021; 70 Chien, Goh, Sandino, Cheng (b46) 2022 Friedrich, Biermann, Gontar, Biella, Bengler (b53) 2018; 20 Chen, Chen, Chen, Wu (b42) 2021; 21 Chakladar (10.1016/j.knosys.2024.112370_b26) 2020; 60 Kosch (10.1016/j.knosys.2024.112370_b6) 2023; 55 10.1016/j.knosys.2024.112370_b44 Vaswani (10.1016/j.knosys.2024.112370_b51) 2017; 30 Sun (10.1016/j.knosys.2024.112370_b15) 2020; 404 Zhang (10.1016/j.knosys.2024.112370_b22) 2014; 45 Goodfellow (10.1016/j.knosys.2024.112370_b33) 2020; 63 Zhou (10.1016/j.knosys.2024.112370_b17) 2021; 14 Li (10.1016/j.knosys.2024.112370_b38) 2015; 165 Gupta (10.1016/j.knosys.2024.112370_b25) 2021; 70 Pagnotta (10.1016/j.knosys.2024.112370_b54) 2022; 65 Padhmashree (10.1016/j.knosys.2024.112370_b18) 2022; 238 Yu (10.1016/j.knosys.2024.112370_b7) 2023; 57 Panagou (10.1016/j.knosys.2024.112370_b1) 2024; 62 Nagar (10.1016/j.knosys.2024.112370_b40) 2022; 30 Wang (10.1016/j.knosys.2024.112370_b30) 2024; 92 Klados (10.1016/j.knosys.2024.112370_b11) 2011; 6 Huang (10.1016/j.knosys.2024.112370_b28) 2022; 71 Wu (10.1016/j.knosys.2024.112370_b49) 2022 Liu (10.1016/j.knosys.2024.112370_b31) 2021; 35 Yang (10.1016/j.knosys.2024.112370_b27) 2024; 71 Chien (10.1016/j.knosys.2024.112370_b46) 2022 Weng (10.1016/j.knosys.2024.112370_b32) 2024 Stergiadis (10.1016/j.knosys.2024.112370_b12) 2022; 72 Zhang (10.1016/j.knosys.2024.112370_b56) 2019; 27 Leite (10.1016/j.knosys.2024.112370_b41) 2018 10.1016/j.knosys.2024.112370_b48 Tan (10.1016/j.knosys.2024.112370_b45) 2024; 290 10.1016/j.knosys.2024.112370_b47 Laybidi (10.1016/j.knosys.2024.112370_b19) 2022; 252 Friedrich (10.1016/j.knosys.2024.112370_b53) 2018; 20 Paszke (10.1016/j.knosys.2024.112370_b55) 2019; 32 Lyu (10.1016/j.knosys.2024.112370_b2) 2024 Wu (10.1016/j.knosys.2024.112370_b43) 2023; 45 Zhou (10.1016/j.knosys.2024.112370_b21) 2022; 30 Dimitrakopoulos (10.1016/j.knosys.2024.112370_b20) 2017; 25 Cheema (10.1016/j.knosys.2024.112370_b23) 2018 Zhang (10.1016/j.knosys.2024.112370_b4) 2024; 86 Amadori (10.1016/j.knosys.2024.112370_b57) 2022; 14 Zhang (10.1016/j.knosys.2024.112370_b14) 2021; 18 Zhang (10.1016/j.knosys.2024.112370_b36) 2022 Li (10.1016/j.knosys.2024.112370_b8) 2020; 17 10.1016/j.knosys.2024.112370_b16 Chuang (10.1016/j.knosys.2024.112370_b13) 2022; 263 Makowski (10.1016/j.knosys.2024.112370_b50) 2021 Fu (10.1016/j.knosys.2024.112370_b34) 2022; 30 Yang (10.1016/j.knosys.2024.112370_b3) 2024; 25 Rafiei (10.1016/j.knosys.2024.112370_b37) 2022 Chen (10.1016/j.knosys.2024.112370_b42) 2021; 21 Li (10.1016/j.knosys.2024.112370_b9) 2023; 260 Jiao (10.1016/j.knosys.2024.112370_b35) 2020; 408 Huang (10.1016/j.knosys.2024.112370_b58) 2022; 71 van de Merwe (10.1016/j.knosys.2024.112370_b5) 2024; 66 Jiao (10.1016/j.knosys.2024.112370_b24) 2018; 76 Ji (10.1016/j.knosys.2024.112370_b29) 2023; 230 Lim (10.1016/j.knosys.2024.112370_b52) 2018; 26 Chen (10.1016/j.knosys.2024.112370_b10) 2017; 67 Cai (10.1016/j.knosys.2024.112370_b39) 2024; 94 |
| References_xml | – volume: 76 start-page: 582 year: 2018 end-page: 595 ident: b24 article-title: Deep convolutional neural networks for mental load classification based on EEG data publication-title: Pattern Recognit. – volume: 26 start-page: 2106 year: 2018 end-page: 2114 ident: b52 article-title: STEW: Simultaneous task EEG workload data set publication-title: IEEE Trans. Neural Syst. Rehabil. Eng. – volume: 290 year: 2024 ident: b45 article-title: GAEFS: Self-supervised graph auto-encoder enhanced feature selection publication-title: Knowl.-Based Syst. – volume: 72 year: 2022 ident: b12 article-title: Which BSS method separates better the EEG signals? A comparison of five different algorithms publication-title: Biomed. Signal Process. Control – year: 2022 ident: b37 article-title: Self-supervised learning for electroencephalography publication-title: IEEE Trans. Neural Netw. Learn. Syst. – volume: 71 year: 2022 ident: b58 article-title: Recognition of driver’s mental workload based on physiological signals, a comparative study publication-title: Biomed. Signal Process. Control – volume: 238 year: 2022 ident: b18 article-title: Human emotion recognition based on time–frequency analysis of multivariate EEG signal publication-title: Knowl.-Based Syst. – volume: 30 start-page: 50 year: 2022 end-page: 60 ident: b21 article-title: Cross-task cognitive workload recognition based on EEG and domain adaptation publication-title: IEEE Trans. Neural Syst. Rehabil. Eng. – reference: R. Li, Y. Wang, W.-L. Zheng, B.-L. Lu, A multi-view spectral-spatial-temporal masked autoencoder for decoding emotions with self-supervised learning, in: Proceedings of the 30th ACM International Conference on Multimedia, 2022, pp. 6–14. – volume: 25 start-page: 1940 year: 2017 end-page: 1949 ident: b20 article-title: Task-independent mental workload classification based upon common multiband EEG cortical connectivity publication-title: IEEE Trans. Neural Syst. Rehabil. Eng. – volume: 67 start-page: 359 year: 2017 end-page: 370 ident: b10 article-title: The use of multivariate EMD and CCA for denoising muscle artifacts from few-channel EEG recordings publication-title: IEEE Trans. Instrum. Meas. – volume: 60 year: 2020 ident: b26 article-title: EEG-based mental workload estimation using deep BLSTM-LSTM network and evolutionary algorithm publication-title: Biomed. Signal Process. Control – volume: 71 start-page: 4999 year: 2024 end-page: 5009 ident: b27 article-title: Real-time driver cognitive workload recognition: Attention-enabled learning with multimodal information fusion publication-title: IEEE Trans. Ind. Electron. – volume: 6 start-page: 291 year: 2011 end-page: 300 ident: b11 article-title: REG-ICA: a hybrid methodology combining blind source separation and regression techniques for the rejection of ocular artifacts publication-title: Biomed. Signal Process. Control – volume: 62 start-page: 974 year: 2024 end-page: 990 ident: b1 article-title: A scoping review of human robot interaction research towards industry 5.0 human-centric workplaces publication-title: Int. J. Prod. Res. – volume: 27 start-page: 1149 year: 2019 end-page: 1159 ident: b56 article-title: Spectral and temporal feature learning with two-stream neural networks for mental workload assessment publication-title: IEEE Trans. Neural Syst. Rehabil. Eng. – volume: 70 year: 2021 ident: b25 article-title: Classification of cross task cognitive workload using deep recurrent network with modelling of temporal dynamics publication-title: Biomed. Signal Process. Control – volume: 230 year: 2023 ident: b29 article-title: Cross-task cognitive workload recognition using a dynamic residual network with attention mechanism based on neurophysiological signals publication-title: Biomed. Signal Process. Control – volume: 21 start-page: 5019 year: 2021 ident: b42 article-title: Denoising autoencoder-based feature extraction to robust SSVEP-based BCIs publication-title: Sensors – volume: 25 start-page: 2034 year: 2024 end-page: 2045 ident: b3 article-title: Quantitative identification of driver distraction: A weakly supervised contrastive learning approach publication-title: IEEE Trans. Intell. Transp. Syst. – volume: 32 year: 2019 ident: b55 article-title: Pytorch: An imperative style, high-performance deep learning library publication-title: Adv. Neural Inf. Process. Syst. – volume: 260 year: 2023 ident: b9 article-title: Recognising situation awareness associated with different workloads using EEG and eye-tracking features in air traffic control tasks publication-title: Knowl.-Based Syst. – volume: 57 year: 2023 ident: b7 article-title: Air traffic controllers’ mental fatigue recognition: A multi-sensor information fusion-based deep learning approach publication-title: Adv. Eng. Inform. – volume: 20 start-page: 205 year: 2018 end-page: 217 ident: b53 article-title: The influence of task load on situation awareness and control strategy in the ATC tower environment publication-title: Cogn. Technol. Work – year: 2024 ident: b32 article-title: Self-supervised learning for electroencephalogram: A systematic survey – start-page: 1 year: 2021 end-page: 8 ident: b50 article-title: NeuroKit2: A python toolbox for neurophysiological signal processing publication-title: Behav. Res. Methods – volume: 30 start-page: 2474 year: 2022 end-page: 2485 ident: b40 article-title: Orthogonal features based EEG signals denoising using fractional and compressed one-dimensional CNN AutoEncoder publication-title: IEEE Trans. Neural Syst. Rehabil. Eng. – reference: D. Pulver, P. Angkan, P. Hungler, A. Etemad, EEG-based Cognitive Load Classification using Feature Masked Autoencoding and Emotion Transfer Learning, in: Proceedings of the 25th International Conference on Multimodal Interaction, 2023, pp. 190–197. – start-page: 2605 year: 2018 end-page: 2612 ident: b41 article-title: Deep convolutional autoencoder for EEG noise filtering publication-title: 2018 IEEE International Conference on Bioinformatics and Biomedicine – start-page: 265 year: 2018 end-page: 284 ident: b23 article-title: Mental workload estimation from EEG signals using machine learning algorithms publication-title: Engineering Psychology and Cognitive Ergonomics: 15th International Conference, EPCE 2018, Held As Part of HCI International 2018, Las Vegas, NV, USA, July 15-20, 2018, Proceedings 15 – volume: 55 start-page: 1 year: 2023 end-page: 39 ident: b6 article-title: A survey on measuring cognitive workload in human-computer interaction publication-title: ACM Comput. Surv. – volume: 18 year: 2021 ident: b14 article-title: EeGdenoiseNet: A benchmark dataset for deep learning solutions of EEG denoising publication-title: J. Neural Eng. – volume: 14 start-page: 1474 year: 2022 end-page: 1485 ident: b57 article-title: Predicting secondary task performance: A directly actionable metric for cognitive overload detection publication-title: IEEE Trans. Cogn. Dev. Syst. – volume: 92 year: 2024 ident: b30 article-title: LGNet: Learning local–global EEG representations for cognitive workload classification in simulated flights publication-title: Biomed. Signal Process. Control – reference: K. He, X. Chen, S. Xie, Y. Li, P. Dollár, R. Girshick, Masked autoencoders are scalable vision learners, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 16000–16009. – year: 2022 ident: b49 article-title: Denoising masked autoencoders help robust classification – volume: 63 start-page: 139 year: 2020 end-page: 144 ident: b33 article-title: Generative adversarial networks publication-title: Commun. ACM. – volume: 252 year: 2022 ident: b19 article-title: Cognitive performance and electroencephalographic variations in air traffic controllers under various mental workload and time of day publication-title: Physiol. Behav. – volume: 45 start-page: 14745 year: 2023 end-page: 14759 ident: b43 article-title: Human-guided reinforcement learning with sim-to-real transfer for autonomous navigation publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – volume: 86 year: 2024 ident: b4 article-title: Skeleton-RGB integrated highly similar human action prediction in human–robot collaborative assembly publication-title: Robot. Comput.-Integr. Manuf. – volume: 17 year: 2020 ident: b8 article-title: Review of semi-dry electrodes for EEG recording publication-title: J. Neural Eng. – reference: C. Lee, F. Imrie, M. van der Schaar, Self-supervision enhanced feature selection with correlated gates, in: International Conference on Learning Representations, 2022. – volume: 66 start-page: 180 year: 2024 end-page: 208 ident: b5 article-title: Agent transparency, situation awareness, mental workload, and operator performance: A systematic literature review publication-title: Hum. Factors – volume: 30 start-page: 1384 year: 2022 end-page: 1400 ident: b34 article-title: Symmetric convolutional and adversarial neural network enables improved mental stress classification from EEG publication-title: IEEE Trans. Neural Syst. Rehabil. Eng. – volume: 94 year: 2024 ident: b39 article-title: MAE-EEG-transformer: A transformer-based approach combining masked autoencoder and cross-individual data augmentation pre-training for EEG classification publication-title: Biomed. Signal Process. Control – volume: 14 start-page: 799 year: 2021 end-page: 818 ident: b17 article-title: Cognitive workload recognition using EEG signals and machine learning: A review publication-title: IEEE Trans. Cogn. Dev. Syst. – volume: 71 year: 2022 ident: b28 article-title: Recognition of driver’s mental workload based on physiological signals, a comparative study publication-title: Biomed. Signal Process. Control – volume: 165 start-page: 23 year: 2015 end-page: 31 ident: b38 article-title: Feature learning from incomplete EEG with denoising autoencoder publication-title: Neurocomputing – volume: 263 year: 2022 ident: b13 article-title: IC-U-Net: a U-net-based denoising autoencoder using mixtures of independent components for automatic EEG artifact removal publication-title: NeuroImage – volume: 45 start-page: 200 year: 2014 end-page: 214 ident: b22 article-title: Recognition of mental workload levels under complex human–machine collaboration by using physiological features and adaptive support vector machines publication-title: IEEE Trans. Hum.-Mach. Syst. – volume: 30 year: 2017 ident: b51 article-title: Attention is all you need publication-title: Adv. Neural Inf. Process. Syst. – volume: 408 start-page: 100 year: 2020 end-page: 111 ident: b35 article-title: Driver sleepiness detection from EEG and EOG signals using GAN and LSTM networks publication-title: Neurocomputing – volume: 404 start-page: 108 year: 2020 end-page: 121 ident: b15 article-title: A novel end-to-end 1D-ResCNN model to remove artifact from EEG signals publication-title: Neurocomputing – year: 2022 ident: b46 article-title: Maeeg: Masked auto-encoder for eeg representation learning – year: 2024 ident: b2 article-title: VALIO: Visual attention-based linear temporal logic method for explainable out-of-the-loop identification publication-title: Knowl.-Based Syst. – volume: 65 start-page: 1095 year: 2022 end-page: 1118 ident: b54 article-title: Task difficulty and physiological measures of mental workload in air traffic control: a scoping review publication-title: Ergonomics – volume: 35 start-page: 857 year: 2021 end-page: 876 ident: b31 article-title: Self-supervised learning: Generative or contrastive publication-title: IEEE Trans. Knowl. Data Eng. – year: 2022 ident: b36 article-title: GANSER: A self-supervised data augmentation framework for EEG-based emotion recognition publication-title: IEEE Trans. Affect Comput. – volume: 17 issue: 5 year: 2020 ident: 10.1016/j.knosys.2024.112370_b8 article-title: Review of semi-dry electrodes for EEG recording publication-title: J. Neural Eng. doi: 10.1088/1741-2552/abbd50 – volume: 63 start-page: 139 issue: 11 year: 2020 ident: 10.1016/j.knosys.2024.112370_b33 article-title: Generative adversarial networks publication-title: Commun. ACM. doi: 10.1145/3422622 – volume: 18 issue: 5 year: 2021 ident: 10.1016/j.knosys.2024.112370_b14 article-title: EeGdenoiseNet: A benchmark dataset for deep learning solutions of EEG denoising publication-title: J. Neural Eng. doi: 10.1088/1741-2552/ac2bf8 – volume: 57 year: 2023 ident: 10.1016/j.knosys.2024.112370_b7 article-title: Air traffic controllers’ mental fatigue recognition: A multi-sensor information fusion-based deep learning approach publication-title: Adv. Eng. Inform. doi: 10.1016/j.aei.2023.102123 – year: 2022 ident: 10.1016/j.knosys.2024.112370_b46 – volume: 165 start-page: 23 year: 2015 ident: 10.1016/j.knosys.2024.112370_b38 article-title: Feature learning from incomplete EEG with denoising autoencoder publication-title: Neurocomputing doi: 10.1016/j.neucom.2014.08.092 – volume: 25 start-page: 2034 issue: 2 year: 2024 ident: 10.1016/j.knosys.2024.112370_b3 article-title: Quantitative identification of driver distraction: A weakly supervised contrastive learning approach publication-title: IEEE Trans. Intell. Transp. Syst. doi: 10.1109/TITS.2023.3316203 – year: 2024 ident: 10.1016/j.knosys.2024.112370_b32 – start-page: 2605 year: 2018 ident: 10.1016/j.knosys.2024.112370_b41 article-title: Deep convolutional autoencoder for EEG noise filtering – volume: 6 start-page: 291 issue: 3 year: 2011 ident: 10.1016/j.knosys.2024.112370_b11 article-title: REG-ICA: a hybrid methodology combining blind source separation and regression techniques for the rejection of ocular artifacts publication-title: Biomed. Signal Process. Control doi: 10.1016/j.bspc.2011.02.001 – volume: 62 start-page: 974 issue: 3 year: 2024 ident: 10.1016/j.knosys.2024.112370_b1 article-title: A scoping review of human robot interaction research towards industry 5.0 human-centric workplaces publication-title: Int. J. Prod. Res. doi: 10.1080/00207543.2023.2172473 – volume: 67 start-page: 359 issue: 2 year: 2017 ident: 10.1016/j.knosys.2024.112370_b10 article-title: The use of multivariate EMD and CCA for denoising muscle artifacts from few-channel EEG recordings publication-title: IEEE Trans. Instrum. Meas. doi: 10.1109/TIM.2017.2759398 – volume: 70 year: 2021 ident: 10.1016/j.knosys.2024.112370_b25 article-title: Classification of cross task cognitive workload using deep recurrent network with modelling of temporal dynamics publication-title: Biomed. Signal Process. Control doi: 10.1016/j.bspc.2021.103070 – volume: 30 year: 2017 ident: 10.1016/j.knosys.2024.112370_b51 article-title: Attention is all you need publication-title: Adv. Neural Inf. Process. Syst. – volume: 30 start-page: 50 year: 2022 ident: 10.1016/j.knosys.2024.112370_b21 article-title: Cross-task cognitive workload recognition based on EEG and domain adaptation publication-title: IEEE Trans. Neural Syst. Rehabil. Eng. doi: 10.1109/TNSRE.2022.3140456 – volume: 71 year: 2022 ident: 10.1016/j.knosys.2024.112370_b58 article-title: Recognition of driver’s mental workload based on physiological signals, a comparative study publication-title: Biomed. Signal Process. Control doi: 10.1016/j.bspc.2021.103094 – year: 2022 ident: 10.1016/j.knosys.2024.112370_b36 article-title: GANSER: A self-supervised data augmentation framework for EEG-based emotion recognition publication-title: IEEE Trans. Affect Comput. – volume: 252 year: 2022 ident: 10.1016/j.knosys.2024.112370_b19 article-title: Cognitive performance and electroencephalographic variations in air traffic controllers under various mental workload and time of day publication-title: Physiol. Behav. – year: 2022 ident: 10.1016/j.knosys.2024.112370_b49 – volume: 230 year: 2023 ident: 10.1016/j.knosys.2024.112370_b29 article-title: Cross-task cognitive workload recognition using a dynamic residual network with attention mechanism based on neurophysiological signals publication-title: Biomed. Signal Process. Control – start-page: 265 year: 2018 ident: 10.1016/j.knosys.2024.112370_b23 article-title: Mental workload estimation from EEG signals using machine learning algorithms – ident: 10.1016/j.knosys.2024.112370_b44 – volume: 30 start-page: 2474 year: 2022 ident: 10.1016/j.knosys.2024.112370_b40 article-title: Orthogonal features based EEG signals denoising using fractional and compressed one-dimensional CNN AutoEncoder publication-title: IEEE Trans. Neural Syst. Rehabil. Eng. doi: 10.1109/TNSRE.2022.3201197 – volume: 60 year: 2020 ident: 10.1016/j.knosys.2024.112370_b26 article-title: EEG-based mental workload estimation using deep BLSTM-LSTM network and evolutionary algorithm publication-title: Biomed. Signal Process. Control – volume: 20 start-page: 205 year: 2018 ident: 10.1016/j.knosys.2024.112370_b53 article-title: The influence of task load on situation awareness and control strategy in the ATC tower environment publication-title: Cogn. Technol. Work doi: 10.1007/s10111-018-0464-4 – volume: 65 start-page: 1095 issue: 8 year: 2022 ident: 10.1016/j.knosys.2024.112370_b54 article-title: Task difficulty and physiological measures of mental workload in air traffic control: a scoping review publication-title: Ergonomics doi: 10.1080/00140139.2021.2016998 – year: 2024 ident: 10.1016/j.knosys.2024.112370_b2 article-title: VALIO: Visual attention-based linear temporal logic method for explainable out-of-the-loop identification publication-title: Knowl.-Based Syst. doi: 10.1016/j.knosys.2024.112086 – volume: 21 start-page: 5019 issue: 15 year: 2021 ident: 10.1016/j.knosys.2024.112370_b42 article-title: Denoising autoencoder-based feature extraction to robust SSVEP-based BCIs publication-title: Sensors doi: 10.3390/s21155019 – volume: 45 start-page: 200 issue: 2 year: 2014 ident: 10.1016/j.knosys.2024.112370_b22 article-title: Recognition of mental workload levels under complex human–machine collaboration by using physiological features and adaptive support vector machines publication-title: IEEE Trans. Hum.-Mach. Syst. doi: 10.1109/THMS.2014.2366914 – volume: 76 start-page: 582 year: 2018 ident: 10.1016/j.knosys.2024.112370_b24 article-title: Deep convolutional neural networks for mental load classification based on EEG data publication-title: Pattern Recognit. doi: 10.1016/j.patcog.2017.12.002 – volume: 404 start-page: 108 year: 2020 ident: 10.1016/j.knosys.2024.112370_b15 article-title: A novel end-to-end 1D-ResCNN model to remove artifact from EEG signals publication-title: Neurocomputing doi: 10.1016/j.neucom.2020.04.029 – volume: 92 year: 2024 ident: 10.1016/j.knosys.2024.112370_b30 article-title: LGNet: Learning local–global EEG representations for cognitive workload classification in simulated flights publication-title: Biomed. Signal Process. Control doi: 10.1016/j.bspc.2024.106046 – volume: 408 start-page: 100 year: 2020 ident: 10.1016/j.knosys.2024.112370_b35 article-title: Driver sleepiness detection from EEG and EOG signals using GAN and LSTM networks publication-title: Neurocomputing doi: 10.1016/j.neucom.2019.05.108 – volume: 35 start-page: 857 issue: 1 year: 2021 ident: 10.1016/j.knosys.2024.112370_b31 article-title: Self-supervised learning: Generative or contrastive publication-title: IEEE Trans. Knowl. Data Eng. – volume: 263 year: 2022 ident: 10.1016/j.knosys.2024.112370_b13 article-title: IC-U-Net: a U-net-based denoising autoencoder using mixtures of independent components for automatic EEG artifact removal publication-title: NeuroImage doi: 10.1016/j.neuroimage.2022.119586 – ident: 10.1016/j.knosys.2024.112370_b47 doi: 10.1145/3503161.3548243 – volume: 32 year: 2019 ident: 10.1016/j.knosys.2024.112370_b55 article-title: Pytorch: An imperative style, high-performance deep learning library publication-title: Adv. Neural Inf. Process. Syst. – volume: 290 year: 2024 ident: 10.1016/j.knosys.2024.112370_b45 article-title: GAEFS: Self-supervised graph auto-encoder enhanced feature selection publication-title: Knowl.-Based Syst. doi: 10.1016/j.knosys.2024.111523 – start-page: 1 year: 2021 ident: 10.1016/j.knosys.2024.112370_b50 article-title: NeuroKit2: A python toolbox for neurophysiological signal processing publication-title: Behav. Res. Methods – volume: 27 start-page: 1149 issue: 6 year: 2019 ident: 10.1016/j.knosys.2024.112370_b56 article-title: Spectral and temporal feature learning with two-stream neural networks for mental workload assessment publication-title: IEEE Trans. Neural Syst. Rehabil. Eng. doi: 10.1109/TNSRE.2019.2913400 – volume: 72 year: 2022 ident: 10.1016/j.knosys.2024.112370_b12 article-title: Which BSS method separates better the EEG signals? A comparison of five different algorithms publication-title: Biomed. Signal Process. Control doi: 10.1016/j.bspc.2021.103292 – volume: 238 year: 2022 ident: 10.1016/j.knosys.2024.112370_b18 article-title: Human emotion recognition based on time–frequency analysis of multivariate EEG signal publication-title: Knowl.-Based Syst. – volume: 14 start-page: 1474 issue: 4 year: 2022 ident: 10.1016/j.knosys.2024.112370_b57 article-title: Predicting secondary task performance: A directly actionable metric for cognitive overload detection publication-title: IEEE Trans. Cogn. Dev. Syst. doi: 10.1109/TCDS.2021.3114162 – ident: 10.1016/j.knosys.2024.112370_b16 doi: 10.1109/CVPR52688.2022.01553 – volume: 25 start-page: 1940 issue: 11 year: 2017 ident: 10.1016/j.knosys.2024.112370_b20 article-title: Task-independent mental workload classification based upon common multiband EEG cortical connectivity publication-title: IEEE Trans. Neural Syst. Rehabil. Eng. doi: 10.1109/TNSRE.2017.2701002 – year: 2022 ident: 10.1016/j.knosys.2024.112370_b37 article-title: Self-supervised learning for electroencephalography publication-title: IEEE Trans. Neural Netw. Learn. Syst. – volume: 94 year: 2024 ident: 10.1016/j.knosys.2024.112370_b39 article-title: MAE-EEG-transformer: A transformer-based approach combining masked autoencoder and cross-individual data augmentation pre-training for EEG classification publication-title: Biomed. Signal Process. Control doi: 10.1016/j.bspc.2024.106131 – ident: 10.1016/j.knosys.2024.112370_b48 doi: 10.1145/3577190.3614113 – volume: 66 start-page: 180 issue: 1 year: 2024 ident: 10.1016/j.knosys.2024.112370_b5 article-title: Agent transparency, situation awareness, mental workload, and operator performance: A systematic literature review publication-title: Hum. Factors doi: 10.1177/00187208221077804 – volume: 86 year: 2024 ident: 10.1016/j.knosys.2024.112370_b4 article-title: Skeleton-RGB integrated highly similar human action prediction in human–robot collaborative assembly publication-title: Robot. Comput.-Integr. Manuf. doi: 10.1016/j.rcim.2023.102659 – volume: 71 year: 2022 ident: 10.1016/j.knosys.2024.112370_b28 article-title: Recognition of driver’s mental workload based on physiological signals, a comparative study publication-title: Biomed. Signal Process. Control doi: 10.1016/j.bspc.2021.103094 – volume: 30 start-page: 1384 year: 2022 ident: 10.1016/j.knosys.2024.112370_b34 article-title: Symmetric convolutional and adversarial neural network enables improved mental stress classification from EEG publication-title: IEEE Trans. Neural Syst. Rehabil. Eng. doi: 10.1109/TNSRE.2022.3174821 – volume: 45 start-page: 14745 issue: 12 year: 2023 ident: 10.1016/j.knosys.2024.112370_b43 article-title: Human-guided reinforcement learning with sim-to-real transfer for autonomous navigation publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2023.3314762 – volume: 26 start-page: 2106 issue: 11 year: 2018 ident: 10.1016/j.knosys.2024.112370_b52 article-title: STEW: Simultaneous task EEG workload data set publication-title: IEEE Trans. Neural Syst. Rehabil. Eng. doi: 10.1109/TNSRE.2018.2872924 – volume: 14 start-page: 799 issue: 3 year: 2021 ident: 10.1016/j.knosys.2024.112370_b17 article-title: Cognitive workload recognition using EEG signals and machine learning: A review publication-title: IEEE Trans. Cogn. Dev. Syst. doi: 10.1109/TCDS.2021.3090217 – volume: 71 start-page: 4999 issue: 5 year: 2024 ident: 10.1016/j.knosys.2024.112370_b27 article-title: Real-time driver cognitive workload recognition: Attention-enabled learning with multimodal information fusion publication-title: IEEE Trans. Ind. Electron. doi: 10.1109/TIE.2023.3288182 – volume: 55 start-page: 1 issue: 13s year: 2023 ident: 10.1016/j.knosys.2024.112370_b6 article-title: A survey on measuring cognitive workload in human-computer interaction publication-title: ACM Comput. Surv. doi: 10.1145/3582272 – volume: 260 year: 2023 ident: 10.1016/j.knosys.2024.112370_b9 article-title: Recognising situation awareness associated with different workloads using EEG and eye-tracking features in air traffic control tasks publication-title: Knowl.-Based Syst. doi: 10.1016/j.knosys.2022.110179 |
| SSID | ssj0002218 |
| Score | 2.4116104 |
| Snippet | Identifying the cognitive workload of operators is crucial in complex human-automation collaboration systems. An excessive workload can lead to fatigue or... |
| SourceID | crossref elsevier |
| SourceType | Enrichment Source Index Database Publisher |
| StartPage | 112370 |
| SubjectTerms | Cognitive workload EEG Masked autoencoder Robustness Self-supervised learning |
| Title | A robust operators’ cognitive workload recognition method based on denoising masked autoencoder |
| URI | https://dx.doi.org/10.1016/j.knosys.2024.112370 |
| Volume | 301 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVESC databaseName: Elsevier SD Freedom Collection Journals 2021 issn: 0950-7051 databaseCode: AIEXJ dateStart: 19950201 customDbUrl: isFulltext: true dateEnd: 99991231 titleUrlDefault: https://www.sciencedirect.com omitProxy: false ssIdentifier: ssj0002218 providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3JbtswECVSp4de0qQLmm7goTeDhiTSpnQ0ihRpCgQ9JIBvAjcBTlLJteQgx_xGfq9f0uEmO02QNodeBIsQKcrvaTgazoLQpwqUVGUqRagcZwRIkVtDE7zuihkprdBMlCs2wY-P89ms-B5CCFpXToDXdX51VSz-K9TQBmDb0NlHwN0PCg3wG0CHI8AOx38CfjpcNnLVdsNmYdweehsdGorh2lnI-mNdNMLGroRGoIEvJz20K5u2uwggk5q5Myb8EO05tIlV19jMlzr49Aat9ls0zBHftd1Ig-6KflkgZ3PR_IwLpXMoMGHDf1WTw3YeYtKCBSJjzpetuGVKTAhPQuLYIFVpsFF4uQhaHfUFQu6IbG89OBud1w3MbmRvMFpffjtD9h8rV-9PGF3Vzko_SmlHKf0oT9B2xsdFPkDb068Hs6N-nc4yZ_3tZx8DK533393Z3K-4bCgjJ7toJ3xF4KlHfw9tmfoFeh4rdOAgsF8iMcWeDLgnw6_rG9zTAEca4A0aYE8D7LDEcN7TAHsa4A0avEKnXw5OPh-SUFSDKHjgjvCUiVRLzpQRFdWpZixjE53Kqkg1l4zyio71WIMqzpg2xlBq4JsmLZRNQ2QYfY0GdVObNwizSTVRVcK5ymDQROY2rlsoLVOuJnki9hGN_1ipQsZ5W_jkonwIr31E-l4Ln3HlL9fzCEYZtEavDZbAsAd7vn3knd6hZ2v6v0eDbrkyH9BTddnN2-XHQK_fvJCTzA |
| 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=A+robust+operators%E2%80%99+cognitive+workload+recognition+method+based+on+denoising+masked+autoencoder&rft.jtitle=Knowledge-based+systems&rft.au=Yu%2C+Xiaoqing&rft.au=Chen%2C+Chun-Hsien&rft.date=2024-10-09&rft.issn=0950-7051&rft.volume=301&rft.spage=112370&rft_id=info:doi/10.1016%2Fj.knosys.2024.112370&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_knosys_2024_112370 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0950-7051&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0950-7051&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0950-7051&client=summon |