{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,26]],"date-time":"2026-10-26T19:47:12Z","timestamp":1793044032269,"version":"4.5.0"},"reference-count":42,"publisher":"Public Library of Science (PLoS)","issue":"10","license":[{"start":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T00:00:00Z","timestamp":1761868800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62577027"],"award-info":[{"award-number":["62577027"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62177022"],"award-info":[{"award-number":["62177022"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61901165"],"award-info":[{"award-number":["61901165"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Self-determined Research Funds of CCNU from the Colleges\u2019 Basic Research and Operation of MOE","award":["CCNU25ai011"],"award-info":[{"award-number":["CCNU25ai011"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>As affective computing becomes increasingly crucial in health monitoring and psychological intervention, accurately identifying affective states is a key challenge. While traditional machine learning models have achieved some success in affective computation, their ability to handle complex, multimodal physiological signals is limited. Most affective computing tasks still rely heavily on traditional methods, with few deep learning models applied, particularly in multimodal signal processing. Given the importance of stress monitoring for mental health, developing a highly reliable and accurate affective computing model is essential. In this context, we propose a novel model\u2014PhysioFormer, for affective state prediction using physiological signals. PhysioFormer model integrates individual attributes and multimodal physiological data to address inter-individual variability, enhancing its reliability and generalization across different individuals. By incorporating feature embedding and affective representation modules, PhysioFormer model captures dynamic changes in time-series data and multimodal signal features, significantly improving accuracy. The model also includes an explainability model that uses symbolic regression to extract laws linking physiological signals to affective states, increasing transparency and explainability. Experiments conducted on the Wrist and Chest subsets of the WESAD dataset confirmed the model\u2019s superior performance, achieving over 99% accuracy, outperforming existing SOTA models. Sensitivity and ablation experiments further demonstrated PhysioFormer\u2019s reliability, validating the contribution of its individual components. The integration of symbolic regression not only enhanced model explainability but also highlighted the complex relationships between physiological signals and affective states. Future work will focus on optimizing the model for larger datasets and real-time applications, particularly in more complex environments. Additionally, further exploration of physiological signals and environmental factors will help build a more comprehensive affective computing system, advancing its use in health monitoring and psychological intervention.<\/jats:p>","DOI":"10.1371\/journal.pone.0335221","type":"journal-article","created":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T18:01:01Z","timestamp":1761933661000},"page":"e0335221","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":7,"title":["PhysioFormer: Integrating multimodal physiological signals and symbolic regression for explainable affective state prediction"],"prefix":"10.1371","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6960-509X","authenticated-orcid":true,"given":"Zhifeng","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wanxuan","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chunyan","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jialiang","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2025,10,31]]},"reference":[{"key":"pone.0335221.ref001","unstructured":"Dattani S, Rod\u00e9s-Guirao L, Ritchie H, Roser M. Mental Health. Our World in Data; 2023."},{"key":"pone.0335221.ref002","doi-asserted-by":"crossref","first-page":"17180","DOI":"10.1073\/pnas.1121254109","article-title":"Brain on stress: how the social environment gets under the skin","volume":"109","author":"BS McEwen","year":"2012","journal-title":"Proc Natl Acad Sci U S A."},{"key":"pone.0335221.ref003","doi-asserted-by":"crossref","unstructured":"Ertin E, Stohs N, Kumar S, Raij A, al\u2019Absi M, Shah S. AutoSense. In: Proceedings of the 9th ACM Conference on Embedded Networked Sensor Systems. 2011. p. 274\u201387. https:\/\/doi.org\/10.1145\/2070942.2070970","DOI":"10.1145\/2070942.2070970"},{"key":"pone.0335221.ref004","doi-asserted-by":"crossref","unstructured":"De Nadai S, D\u2019Inca M, Parodi F, Benza M, Trotta A, Zero E, et al. Enhancing safety of transport by road by on-line monitoring of driver emotions. In: 2016 11th System of Systems Engineering Conference (SoSE). 2016. https:\/\/doi.org\/10.1109\/sysose.2016.7542941","DOI":"10.1109\/SYSOSE.2016.7542941"},{"key":"pone.0335221.ref005","doi-asserted-by":"crossref","unstructured":"Hosseini E, Fang R, Zhang R, Rafatirad S, Homayoun H. Emotion and stress recognition utilizing galvanic skin response and wearable technology: a real-time approach for mental health care. In: 2023 IEEE International Conference on Bioinformatics and Biomedicine (BIBM). 2023. p. 1125\u201331. https:\/\/doi.org\/10.1109\/bibm58861.2023.10386049","DOI":"10.1109\/BIBM58861.2023.10386049"},{"issue":"8","key":"pone.0335221.ref006","doi-asserted-by":"crossref","first-page":"3287","DOI":"10.3390\/ijerph8083287","article-title":"Perceived stress scale: reliability and validity study in Greece","volume":"8","author":"E Andreou","year":"2011","journal-title":"Int J Environ Res Public Health."},{"key":"pone.0335221.ref007","doi-asserted-by":"crossref","unstructured":"Mei H, Xu X. EEG-based emotion classification using convolutional neural network. In: 2017 International Conference on Security, Pattern Analysis, and Cybernetics (SPAC). 2017. p. 130\u20135. https:\/\/doi.org\/10.1109\/spac.2017.8304263","DOI":"10.1109\/SPAC.2017.8304263"},{"issue":"3","key":"pone.0335221.ref008","doi-asserted-by":"crossref","first-page":"532","DOI":"10.1109\/TAFFC.2018.2817622","article-title":"EEG emotion recognition using dynamical graph convolutional neural networks","volume":"11","author":"T Song","year":"2020","journal-title":"IEEE Trans Affective Comput."},{"key":"pone.0335221.ref009","doi-asserted-by":"crossref","unstructured":"Ashwin VH, Jegan R, Rajalakshmy P. Stress detection using wearable physiological sensors and machine learning algorithm. In: 2022 6th International Conference on Electronics, Communication and Aerospace Technology. 2022. p. 972\u20137. https:\/\/doi.org\/10.1109\/iceca55336.2022.10009326","DOI":"10.1109\/ICECA55336.2022.10009326"},{"issue":"16","key":"pone.0335221.ref010","article-title":"AI Feynman: a physics-inspired method for symbolic regression","volume":"6","author":"S-M Udrescu","year":"2020","journal-title":"Sci Adv."},{"issue":"16","key":"pone.0335221.ref011","doi-asserted-by":"crossref","first-page":"7165","DOI":"10.3390\/app14167165","article-title":"A systematic literature review of modalities, trends, and limitations in emotion recognition, affective computing, and sentiment analysis","volume":"14","author":"RA Garc\u00eda-Hern\u00e1ndez","year":"2024","journal-title":"Applied Sciences."},{"key":"pone.0335221.ref012","article-title":"Decision support with text-based emotion recognition: deep learning for affective computing","author":"B Kratzwald","year":"2018","journal-title":"CoRR."},{"issue":"8","key":"pone.0335221.ref013","doi-asserted-by":"crossref","first-page":"758","DOI":"10.1111\/psyp.12058","article-title":"The imaging Maastricht Acute Stress Test (iMAST): a neuroimaging compatible psychophysiological stressor","volume":"50","author":"CWEM Quaedflieg","year":"2013","journal-title":"Psychophysiology."},{"issue":"5","key":"pone.0335221.ref014","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1139\/jpn.0541","article-title":"The Montreal Imaging Stress Task: using functional imaging to investigate the effects of perceiving and processing psychosocial stress in the human brain","volume":"30","author":"K Dedovic","year":"2005","journal-title":"J Psychiatry Neurosci."},{"issue":"3","key":"pone.0335221.ref015","doi-asserted-by":"crossref","first-page":"1541","DOI":"10.1109\/TAFFC.2020.3014842","article-title":"Self-supervised ECG representation learning for emotion recognition","volume":"13","author":"P Sarkar","year":"2022","journal-title":"IEEE Trans Affective Comput."},{"key":"pone.0335221.ref016","doi-asserted-by":"crossref","unstructured":"Akre S, Cohen ZD, Welborn A, Zbozinek TD, Balliu B, Flint J, et al. Detection of symptoms of depression using data from the iPhone and Apple Watch. In: 2023 IEEE International Conference on Bioinformatics and Biomedicine (BIBM). 2023. p. 1818\u201323. https:\/\/doi.org\/10.1109\/bibm58861.2023.10385797","DOI":"10.1109\/BIBM58861.2023.10385797"},{"key":"pone.0335221.ref017","doi-asserted-by":"crossref","unstructured":"Koldijk S, Sappelli M, Verberne S, Neerincx MA, Kraaij W. The SWELL knowledge work dataset for stress and user modeling research. In: Proceedings of the 16th International Conference on Multimodal Interaction, 2014. p. 291\u20138. https:\/\/doi.org\/10.1145\/2663204.2663257","DOI":"10.1145\/2663204.2663257"},{"key":"pone.0335221.ref018","article-title":"Utilizing deep learning towards multi-modal bio-sensing and vision-based affective computing","author":"Siddharth","year":"2019","journal-title":"CoRR."},{"issue":"15","key":"pone.0335221.ref019","doi-asserted-by":"crossref","first-page":"3932","DOI":"10.1073\/pnas.1517384113","article-title":"Discovering governing equations from data by sparse identification of nonlinear dynamical systems","volume":"113","author":"SL Brunton","year":"2016","journal-title":"Proc Natl Acad Sci U S A."},{"key":"pone.0335221.ref020","doi-asserted-by":"crossref","first-page":"120580","DOI":"10.1016\/j.ces.2024.120580","article-title":"Integrating knowledge-guided symbolic regression and model-based design of experiments to automate process flow diagram development","volume":"300","author":"AW Rogers","year":"2024","journal-title":"Chemical Engineering Science."},{"key":"pone.0335221.ref021","doi-asserted-by":"crossref","first-page":"1039438","DOI":"10.3389\/frai.2023.1039438","article-title":"Application of the symbolic regression program AI-Feynman to psychology","volume":"6","author":"M Miyazaki","year":"2023","journal-title":"Front Artif Intell."},{"issue":"5","key":"pone.0335221.ref022","doi-asserted-by":"crossref","first-page":"334","DOI":"10.1038\/s43588-024-00629-0","article-title":"Automated discovery of symbolic laws governing skill acquisition from naturally occurring data","volume":"4","author":"S Liu","year":"2024","journal-title":"Nat Comput Sci."},{"issue":"2","key":"pone.0335221.ref023","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1109\/5.18626","article-title":"A tutorial on hidden Markov models and selected applications in speech recognition","volume":"77","author":"LR Rabiner","year":"1989","journal-title":"Proc IEEE."},{"key":"pone.0335221.ref024","unstructured":"Lafferty JD, McCallum A, Pereira FCN. Conditional random fields: probabilistic models for segmenting and labeling sequence data. In: Proceedings of the Eighteenth International Conference on Machine Learning. 2001. p. 282\u20139."},{"key":"pone.0335221.ref025","doi-asserted-by":"crossref","unstructured":"Mikolov T, Karafi\u00e1t M, Burget L, \u010cernock\u00fd J, Khudanpur S. Recurrent neural network based language model. In: Interspeech 2010 . 2010. p. 1045\u20138.","DOI":"10.21437\/Interspeech.2010-343"},{"key":"pone.0335221.ref026","unstructured":"Frinken V, Zamora-Mart\u00ednez F, Espa\u00f1a-Boquera S, Castro-Bleda MJ, Fischer A, Bunke H. Long-short term memory neural networks language modeling for handwriting recognition. In: Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012). 2012. p. 701\u20134."},{"key":"pone.0335221.ref027","doi-asserted-by":"crossref","unstructured":"Dhavale M, Bhandari ProfS. Speech Emotion Recognition Using CNN and LSTM. In: 2022 6th International Conference on Computing, Communication, Control And Automation (ICCUBEA). 2022. p. 1\u20133. https:\/\/doi.org\/10.1109\/iccubea54992.2022.10010751","DOI":"10.1109\/ICCUBEA54992.2022.10010751"},{"key":"pone.0335221.ref028","doi-asserted-by":"crossref","unstructured":"Sateesh SK, S BK, U D. Decoding human emotions: Analyzing multi-channel EEG data using LSTM networks. 2024. https:\/\/arxiv.org\/abs\/2408.10328","DOI":"10.1007\/978-981-96-2179-8_38"},{"key":"pone.0335221.ref029","doi-asserted-by":"crossref","first-page":"108339","DOI":"10.1016\/j.engappai.2024.108339","article-title":"Using transformers for multimodal emotion recognition: taxonomies and state of the art review","volume":"133","author":"S Hazmoune","year":"2024","journal-title":"Engineering Applications of Artificial Intelligence."},{"issue":"02","key":"pone.0335221.ref030","doi-asserted-by":"crossref","first-page":"1359","DOI":"10.1609\/aaai.v34i02.5492","article-title":"M3ER: multiplicative multimodal emotion recognition using facial, textual, and speech cues","volume":"34","author":"T Mittal","year":"2020","journal-title":"AAAI."},{"key":"pone.0335221.ref031","doi-asserted-by":"crossref","unstructured":"Kumar CSA, Maharana AD, Krishnan SM, Hanuma SSS, Lal GJ, Ravi V. Speech emotion recognition using CNN-LSTM and vision transformer. In: Abraham A, Bajaj A, Gandhi N, Madureira AM, Kahraman C, editors. Innovations in Bio-Inspired Computing and Applications. Cham: Springer; 2023. p. 86\u201397.","DOI":"10.1007\/978-3-031-27499-2_8"},{"issue":"2","key":"pone.0335221.ref032","doi-asserted-by":"crossref","first-page":"410","DOI":"10.1109\/TITB.2009.2036164","article-title":"Discriminating stress from cognitive load using a wearable EDA device","volume":"14","author":"C Setz","year":"2010","journal-title":"IEEE Trans Inform Technol Biomed."},{"key":"pone.0335221.ref033","unstructured":"Bianchi G, Sorrentino R. Electronic Filter Simulation & Design. McGraw-Hill Education; 2007."},{"issue":"4","key":"pone.0335221.ref034","first-page":"797","article-title":"cvxEDA: a convex optimization approach to electrodermal activity processing","volume":"63","author":"A Greco","year":"2016","journal-title":"IEEE Trans Biomed Eng."},{"issue":"4","key":"pone.0335221.ref035","doi-asserted-by":"crossref","first-page":"1689","DOI":"10.3758\/s13428-020-01516-y","article-title":"NeuroKit2: a python toolbox for neurophysiological signal processing","volume":"53","author":"D Makowski","year":"2021","journal-title":"Behav Res Methods."},{"key":"pone.0335221.ref036","unstructured":"Liu Y, Li C, Wang J, Long M. Koopa: learning non-stationary time series dynamics with koopman predictors. In: NIPS, Red Hook, NY, USA, 2024. p. 1\u20139."},{"key":"pone.0335221.ref037","unstructured":"Sundararajan M, Taly A, Yan Q. Axiomatic attribution for deep networks. In: Proceedings of the 34th International Conference on Machine Learning. 2017. p. 3319\u201328."},{"key":"pone.0335221.ref038","doi-asserted-by":"crossref","unstructured":"Schmidt P, Reiss A, Duerichen R, Marberger C, Van Laerhoven K. Introducing WESAD, a multimodal dataset for wearable stress and affect detection. In: Proceedings of the 20th ACM International Conference on Multimodal Interaction. 2018. p. 400\u20138. https:\/\/doi.org\/10.1145\/3242969.3242985","DOI":"10.1145\/3242969.3242985"},{"key":"pone.0335221.ref039","doi-asserted-by":"crossref","unstructured":"Bobade P, Vani M. Stress detection with machine learning and deep learning using multimodal physiological data. In: 2020 Second International Conference on Inventive Research in Computing Applications (ICIRCA), Coimbatore, India. 2020. p. 51\u20137.","DOI":"10.1109\/ICIRCA48905.2020.9183244"},{"key":"pone.0335221.ref040","doi-asserted-by":"crossref","unstructured":"Siirtola P. Continuous stress detection using the sensors of commercial smartwatch. In: Adjunct Proceedings of the 2019 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2019 ACM International Symposium on Wearable Computers, 2019. p. 1198\u2013201. https:\/\/doi.org\/10.1145\/3341162.3344831","DOI":"10.1145\/3341162.3344831"},{"key":"pone.0335221.ref041","first-page":"19","article-title":"Emotion recognition using cvxEDA-based features","volume":"10","author":"H Ferdinando","year":"2018","journal-title":"Journal of Telecommunication, Electronic and Computer Engineering (JTEC)."},{"issue":"4","key":"pone.0335221.ref042","doi-asserted-by":"crossref","first-page":"212","DOI":"10.3390\/info11040212","article-title":"A systematic exploration of deep neural networks for EDA-based emotion recognition","volume":"11","author":"D Yu","year":"2020","journal-title":"Information."}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0335221","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T18:01:10Z","timestamp":1761933670000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0335221"}},"subtitle":[],"editor":[{"given":"Amgad","family":"Muneer","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2025,10,31]]},"references-count":42,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2025,10,31]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0335221","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,31]]}}}