{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T08:47:01Z","timestamp":1777106821195,"version":"3.51.4"},"reference-count":49,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100010418","name":"Institute for Information and Communications Technology Promotion","doi-asserted-by":"publisher","award":["IITP-2024-RS-2023-00254529"],"award-info":[{"award-number":["IITP-2024-RS-2023-00254529"]}],"id":[{"id":"10.13039\/501100010418","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100015098","name":"Seoul Metropolitan Government Seoul National University Boramae Medical Center","doi-asserted-by":"publisher","award":["2025-RISE-01-019-04"],"award-info":[{"award-number":["2025-RISE-01-019-04"]}],"id":[{"id":"10.13039\/501100015098","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100014188","name":"Ministry of Science and ICT, South Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100014188","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002701","name":"Ministry of Education","doi-asserted-by":"publisher","award":["2020R1A6A1A03038540"],"award-info":[{"award-number":["2020R1A6A1A03038540"]}],"id":[{"id":"10.13039\/501100002701","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Information Sciences"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.ins.2026.123385","type":"journal-article","created":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T08:33:28Z","timestamp":1773909208000},"page":"123385","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Adaptive multimodal emotion detection for mental health monitoring using deep learning"],"prefix":"10.1016","volume":"744","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-8732-6626","authenticated-orcid":false,"given":"Gul E.","family":"Arzu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Muhammad","family":"Umar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Asma","family":"Khan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8986-3173","authenticated-orcid":false,"given":"Usman","family":"Ali","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"L.Minh","family":"Dang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7668-3838","authenticated-orcid":false,"given":"Hyeonjoon","family":"Moon","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"issue":"6","key":"10.1016\/j.ins.2026.123385_bib0010","doi-asserted-by":"crossref","first-page":"8065","DOI":"10.1109\/TITS.2025.3558085","article-title":"Human-factors-in-aviation-loop: multimodal deep learning for pilot situation awareness analysis using gaze position and flight control data","volume":"26","author":"Xu","year":"2025","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.ins.2026.123385_bib0015","doi-asserted-by":"crossref","DOI":"10.3389\/fnbot.2021.697634","article-title":"Multi-modal fusion emotion recognition method of speech expression based on deep learning","volume":"15","author":"Liu","year":"2021","journal-title":"Front. Neurorobot."},{"key":"10.1016\/j.ins.2026.123385_bib0020","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2023.121692","article-title":"Deep learning-based multimodal emotion recognition from audio, visual, and text modalities: a systematic review of recent advancements and future prospects","volume":"237","author":"Zhang","year":"2024","journal-title":"Expert Syst. Appl."},{"issue":"2","key":"10.1016\/j.ins.2026.123385_bib0025","doi-asserted-by":"crossref","first-page":"423","DOI":"10.1109\/TPAMI.2018.2798607","article-title":"Multimodal machine learning: a survey and taxonomy","volume":"41","author":"Baltru\u0161aitis","year":"2019","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"9","key":"10.1016\/j.ins.2026.123385_bib0030","doi-asserted-by":"crossref","first-page":"4682","DOI":"10.1109\/TVCG.2024.3409568","article-title":"Talkingstyle: personalized speech-driven 3D facial animation with style preservation","volume":"31","author":"Song","year":"2024","journal-title":"IEEE Trans. Vis. Comput. Graph."},{"key":"10.1016\/j.ins.2026.123385_bib0035","series-title":"Adaptive Computation and Machine Learning","article-title":"Reinforcement learning: an introduction","author":"Andrew","year":"2018"},{"issue":"4","key":"10.1016\/j.ins.2026.123385_bib0040","doi-asserted-by":"crossref","first-page":"3177","DOI":"10.1109\/TAFFC.2023.3253859","article-title":"Recognizing, fast and slow: Complex emotion recognition with facial expression detection and remote physiological measurement","volume":"14","author":"Wu","year":"2023","journal-title":"IEEE Trans. Affect. Comput."},{"key":"10.1016\/j.ins.2026.123385_bib0045","first-page":"1","article-title":"Facial expression and action unit recognition augmented by their dependencies on graph convolutional networks","author":"He","year":"2021","journal-title":"J. Multimodal User Interfaces"},{"key":"10.1016\/j.ins.2026.123385_bib0050","series-title":"IEEE Winter Conference on Applications of Computer Vision (WACV)","first-page":"1","article-title":"Going deeper in facial expression recognition using deep neural networks","author":"Mollahosseini","year":"2016"},{"key":"10.1016\/j.ins.2026.123385_bib0055","doi-asserted-by":"crossref","first-page":"149","DOI":"10.1007\/s40846-019-00505-7","article-title":"Emotion recognition from multimodal physiological signals for emotion aware healthcare systems","volume":"40","author":"Ayata","year":"2020","journal-title":"J. Med. Biol. Eng."},{"key":"10.1016\/j.ins.2026.123385_bib0060","first-page":"192","article-title":"A deep learning-based strategy for identifying positive emotions from EEG signals","volume":"386","author":"Tran","year":"2020","journal-title":"Neurocomputing"},{"issue":"3","key":"10.1016\/j.ins.2026.123385_bib0065","first-page":"2156","article-title":"Self-attention fusion for multimodal emotion recognition","volume":"14","author":"Li","year":"2021","journal-title":"IEEE Trans. Affect. Comput."},{"key":"10.1016\/j.ins.2026.123385_bib0070","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.inffus.2023.02.012","article-title":"Multimodal emotion recognition via gated cross-attention transformer","volume":"94","author":"Xu","year":"2023","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.ins.2026.123385_bib0075","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.112499","article-title":"Cenn: capsule-enhanced neural network with innovative metrics for robust speech emotion recognition","volume":"304","author":"Zhang","year":"2024","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.ins.2026.123385_bib0080","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2025.110060","article-title":"Sparse temporal-aware capsule network for robust speech emotion recognition","volume":"144","author":"Zhang","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.ins.2026.123385_bib0085","author":"Waligora"},{"key":"10.1016\/j.ins.2026.123385_bib0090","series-title":"Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (ACL)","first-page":"1234","article-title":"Cmath: cross-modality augmented transformer with hierarchical variational distillation","author":"Zhu","year":"2024"},{"key":"10.1016\/j.ins.2026.123385_bib0095","first-page":"128","article-title":"Emotionrl: reinforcement learning framework for emotion-aware dialogue","volume":"536","author":"Zhou","year":"2023","journal-title":"Neurocomputing"},{"issue":"35","key":"10.1016\/j.ins.2026.123385_bib0100","doi-asserted-by":"crossref","DOI":"10.31449\/inf.v49i35.10316","article-title":"Reinforcement learning-based framework for dynamic strategy generation in personalized psychological counseling using deep q-networks","volume":"49","author":"Chen","year":"2025","journal-title":"Informatica"},{"key":"10.1016\/j.ins.2026.123385_bib0105","author":"Chhua"},{"key":"10.1016\/j.ins.2026.123385_bib0110","author":"Rizvi"},{"issue":"16","key":"10.1016\/j.ins.2026.123385_bib0115","first-page":"3217","article-title":"Rs-xception: a lightweight network for facial expression recognition","volume":"13","author":"Lee","year":"2025","journal-title":"Electronics"},{"issue":"8","key":"10.1016\/j.ins.2026.123385_bib0120","doi-asserted-by":"crossref","first-page":"2375","DOI":"10.1049\/ipr2.12798","article-title":"A lightweight method for face expression recognition based on improved mobilenetv3","volume":"17","author":"Liang","year":"2023","journal-title":"IET Image Process."},{"key":"10.1016\/j.ins.2026.123385_bib0125","article-title":"Reproducible and generalizable speech emotion recognition via an intelligent fusion network","volume":"109","author":"Jia","year":"2025","journal-title":"Biomed. Signal Process. Control."},{"key":"10.1016\/j.ins.2026.123385_bib0130","author":"Dhanith P R"},{"key":"10.1016\/j.ins.2026.123385_bib0135","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2023.127109","article-title":"A multi-message passing framework based on heterogeneous graphs in conversational emotion recognition","volume":"569","author":"Meng","year":"2024","journal-title":"Neurocomputing"},{"key":"10.1016\/j.ins.2026.123385_bib0140","series-title":"Proceedings of the 26th International Conference on Pattern Recognition (ICPR)","first-page":"1456","article-title":"Patt-Lite: lightweight patch and attention mobilenet for facial expression recognition","author":"Ngwe","year":"2023"},{"issue":"7","key":"10.1016\/j.ins.2026.123385_bib0145","doi-asserted-by":"crossref","first-page":"2538","DOI":"10.3390\/s22072538","article-title":"Datasets for automated affect and emotion recognition from cardiovascular signals using artificial intelligence\u2014a systematic review","volume":"22","author":"Jemio\u0142o","year":"2022","journal-title":"Sensors"},{"key":"10.1016\/j.ins.2026.123385_bib0150","series-title":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing","first-page":"3687","article-title":"Carer: contextualized affect representations for emotion recognition","author":"Saravia","year":"2018"},{"key":"10.1016\/j.ins.2026.123385_bib0155","article-title":"Context-aware emotion recognition via multimodal transformer with dynamic fusion","author":"Zhang","year":"2023","journal-title":"IEEE Trans. Affect. Comput."},{"issue":"9","key":"10.1016\/j.ins.2026.123385_bib0160","doi-asserted-by":"crossref","first-page":"5643","DOI":"10.1002\/int.22805","article-title":"A multiturn complementary generative framework for conversational emotion recognition","volume":"37","author":"Wang","year":"2022","journal-title":"Int. J. Intell. Syst."},{"issue":"3","key":"10.1016\/j.ins.2026.123385_bib0165","doi-asserted-by":"crossref","first-page":"2033","DOI":"10.1109\/TAFFC.2025.3551330","article-title":"Identifying stable EEG patterns in manipulation task for negative emotion recognition","volume":"16","author":"Pei","year":"2025","journal-title":"IEEE Trans. Affect. Comput."},{"issue":"6","key":"10.1016\/j.ins.2026.123385_bib0170","doi-asserted-by":"crossref","first-page":"4469","DOI":"10.1109\/TCSS.2025.3555607","article-title":"Intervening in negative emotion contagion on social networks using reinforcement learning","volume":"12","author":"Deng","year":"2025","journal-title":"IEEE Trans. Comput. Soc. Syst."},{"key":"10.1016\/j.ins.2026.123385_bib0175","series-title":"International Symposium on Music Information Retrieval","first-page":"1","article-title":"Mel frequency cepstral coefficients for music modeling","author":"Logan","year":"2000"},{"issue":"1\u20133","key":"10.1016\/j.ins.2026.123385_bib0180","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1016\/S0167-6393(98)00033-8","article-title":"Cepstral domain segmental feature vector normalization for noise robust speech recognition","volume":"25","author":"Viikki","year":"1998","journal-title":"Speech Commun."},{"key":"10.1016\/j.ins.2026.123385_bib0185","series-title":"Neural Information Processing: 20th International Conference, ICONIP 2013, Daegu, Korea, November 3\u20137, 2013. Proceedings, Part III 20","first-page":"117","article-title":"Challenges in representation learning: a report on three machine learning contests","author":"Goodfellow","year":"2013"},{"key":"10.1016\/j.ins.2026.123385_bib0190","series-title":"Comprehensive Database for Facial Expression Analysis","author":"Kanade","year":"2000"},{"key":"10.1016\/j.ins.2026.123385_bib0195","series-title":"Interspeech","first-page":"1517","article-title":"A database of German emotional speech","volume":"vol. 5","author":"Burkhardt","year":"2005"},{"issue":"3","key":"10.1016\/j.ins.2026.123385_bib0200","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1007\/s00138-022-01294-x","article-title":"Convolutional neural network-based cross-corpus speech emotion recognition with data augmentation and features fusion","volume":"33","author":"Jahangir","year":"2022","journal-title":"Mach. Vis. Appl."},{"issue":"1","key":"10.1016\/j.ins.2026.123385_bib0205","article-title":"Tpro-Net: an EEG-based emotion recognition method reflecting subtle changes in emotion","volume":"14","author":"Zhang","year":"2024","journal-title":"Sci. Rep."},{"key":"10.1016\/j.ins.2026.123385_bib0210","series-title":"Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"5200","article-title":"Adieu features? End-to-end speech emotion recognition using a deep convolutional recurrent network","author":"Trigeorgis","year":"2016"},{"issue":"8","key":"10.1016\/j.ins.2026.123385_bib0215","doi-asserted-by":"crossref","first-page":"1301","DOI":"10.1109\/JSTSP.2017.2764438","article-title":"End-to-end multimodal emotion recognition using deep neural networks","volume":"11","author":"Tzirakis","year":"2017","journal-title":"IEEE J. Sel. Top. Signal Process."},{"key":"10.1016\/j.ins.2026.123385_bib0220","series-title":"Proceedings of the 19th ACM International Conference on Multimodal Interaction","first-page":"577","article-title":"Audio-visual emotion recognition using deep transfer learning and multiple temporal models","author":"Ouyang","year":"2017"},{"key":"10.1016\/j.ins.2026.123385_bib0225","doi-asserted-by":"crossref","first-page":"98","DOI":"10.1016\/j.inffus.2017.02.003","article-title":"A review of affective computing: from unimodal analysis to multimodal fusion","volume":"37","author":"Poria","year":"2017","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.ins.2026.123385_bib0230","series-title":"Proceedings of the 28th ACM International Conference on Multimedia","first-page":"2532","article-title":"Ch-Sims: a large-scale Chinese multimodal sentiment analysis dataset","author":"Li","year":"2020"},{"key":"10.1016\/j.ins.2026.123385_bib0235","series-title":"Proceedings of the Conference. Association for Computational Linguistics. Meeting","first-page":"6558","article-title":"Multimodal transformer for unaligned multimodal language sequences","volume":"vol. 2019","author":"Tsai","year":"2019"},{"key":"10.1016\/j.ins.2026.123385_bib0240","series-title":"ICASSP","article-title":"Multimodal emotion recognition with hierarchical attention fusion network","author":"Li","year":"2021"},{"key":"10.1016\/j.ins.2026.123385_bib0245","series-title":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (ACL)","first-page":"1","article-title":"Ernie-Vil: knowledge enhanced vision-language representations through scene graph","author":"Yu","year":"2022"},{"key":"10.1016\/j.ins.2026.123385_bib0250","series-title":"Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"1","article-title":"Multimodal emotion recognition based on deep temporal features using cross-modal transformer and self-attention","author":"Maji","year":"2023"}],"container-title":["Information Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0020025526003166?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0020025526003166?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T08:17:43Z","timestamp":1777105063000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0020025526003166"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":49,"alternative-id":["S0020025526003166"],"URL":"https:\/\/doi.org\/10.1016\/j.ins.2026.123385","relation":{},"ISSN":["0020-0255"],"issn-type":[{"value":"0020-0255","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Adaptive multimodal emotion detection for mental health monitoring using deep learning","name":"articletitle","label":"Article Title"},{"value":"Information Sciences","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.ins.2026.123385","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"123385"}}