{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T18:08:27Z","timestamp":1780078107407,"version":"3.54.0"},"reference-count":23,"publisher":"MDPI AG","issue":"11","license":[{"start":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T00:00:00Z","timestamp":1780012800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Accurate stress monitoring is critical for high-risk professions like firefighting, yet existing wearable solutions face challenges balancing accuracy with practical usability. While electrodermal activity (EDA) offers a non-invasive, single-sensor approach, current automated feature extraction methods fail to capture stress-discriminative patterns effectively. We developed a hybrid stress detection pipeline combining 20 hand-crafted physiological features with 32 deep-learned features from a supervised convolutional autoencoder. Unlike traditional unsupervised approaches optimized solely for signal reconstruction, our architecture employs a dual-head design with weighted classification loss to guide feature learning toward stress discrimination. The system was validated on the WESAD dataset (15 subjects) using rigorous leave-one-subject-out (LOSO) cross-validation, along with comprehensive preprocessing, including cvxEDA decomposition, adaptive artifact detection, and physiological peak validation. Our optimized K-Nearest Neighbors classifier achieved 98.62% accuracy, surpassing the industry-standard PyEDA benchmark (97.0%) by 1.62 percentage points. The model demonstrated 97.58% sensitivity (true positive rate) and 98.92% specificity (true negative rate), with only 2.42% false negatives\u2014critical for safety-critical applications. Ablation studies revealed that unsupervised autoencoder features alone achieved only 55% accuracy, increasing to 89% with supervised learning and 98.62% with the hybrid approach, representing a 43.62-percentage-point improvement. This work demonstrates that combining domain-specific physiological knowledge with label-aware deep learning produces more discriminative features than either approach alone. The resulting system successfully translates complex probabilistic outputs into an interpretable 1\u201310 stress score, providing a practical foundation for real-time stress monitoring in wearable devices for first responders.<\/jats:p>","DOI":"10.3390\/s26113451","type":"journal-article","created":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T17:36:18Z","timestamp":1780076178000},"page":"3451","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Hybrid Feature Learning for Wearable Stress Detection: Combining Domain Knowledge with Supervised Deep Learning"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-4021-1386","authenticated-orcid":false,"given":"Dennis","family":"Birkenmaier","sequence":"first","affiliation":[{"name":"FZI Research Center for Information Technology, 76131 Karlsruhe, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shanthan Rao","family":"Kanuganti","sequence":"additional","affiliation":[{"name":"FZI Research Center for Information Technology, 76131 Karlsruhe, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wilhelm","family":"Stork","sequence":"additional","affiliation":[{"name":"Institute for Information Processing Technologies, Karlsruhe Institute of Technology KIT, 76131 Karlsruhe, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,5,29]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Kyriakou, K., Resch, B., Sagl, G., Petutschnig, A., Werner, C., Niederseer, D., Liedlgruber, M., Wilhelm, F.H., Osborne, T., and Pykett, J. (2019). Detecting Moments of Stress from Measurements of Wearable Physiological Sensors. Sensors, 19.","DOI":"10.3390\/s19173805"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"2155","DOI":"10.1109\/JBHI.2023.3239305","article-title":"Stress Detection Through Wrist-Based Electrodermal Activity Monitoring and Machine Learning","volume":"27","author":"Zhu","year":"2023","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Hosseini, E., Fang, R., Zhang, R., Rafatirad, S., and Homayoun, H. (2023, January 5\u20138). Emotion and Stress Recognition Utilizing Galvanic Skin Response and Wearable Technology: A Real-time Approach for Mental Health Care. Proceedings of the 2023 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), Istanbul, Turkiye.","DOI":"10.1109\/BIBM58861.2023.10386049"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Hosseini, E., Fang, R., Zhang, R., Parenteau, A., Hang, S., Rafatirad, S., Hostinar, C., Orooji, M., and Homayoun, H. (2022, January 6\u20138). A Low Cost EDA-based Stress Detection Using Machine Learning. Proceedings of the 2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), Las Vegas, NV, USA.","DOI":"10.1109\/BIBM55620.2022.9995093"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Schmidt, P., Reiss, A., Duerichen, R., Marberger, C., and Van Laerhoven, K. (2018, January 16\u201320). Introducing WESAD, a Multimodal Dataset for Wearable Stress and Affect Detection. Proceedings of the 20th ACM International Conference on Multimodal Interaction (ICMI), Boulder, CO, USA.","DOI":"10.1145\/3242969.3242985"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Di Flumeri, G., Ronca, V., Giorgi, A., Vozzi, A., Aric\u00f2, P., Sciaraffa, N., Zeng, H., Dai, G., Kong, W., and Babiloni, F. (2023). Wrist-Worn Sensor Validation for Heart Rate Variability and Electrodermal Activity Detection in a Stressful Driving Environment. Sensors, 23.","DOI":"10.3390\/s23208423"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Borrego, A., Latorre, J., Alca\u00f1iz, M., and Llorens, R. (2019, January 21\u201324). Reliability of the Empatica E4 wristband to measure electrodermal activity to emotional stimuli. Proceedings of the International Conference on Virtual Rehabilitation (ICVR), Tel Aviv, Israel.","DOI":"10.1109\/ICVR46560.2019.8994546"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Boucsein, W. (2012). Electrodermal Activity, Springer. [2nd ed.].","DOI":"10.1007\/978-1-4614-1126-0"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Cacioppo, J.T., Tassinary, L.G., and Berntson, G.G. (2017). The Electrodermal System. Handbook of Psychophysiology, Cambridge University Press. [4th ed.].","DOI":"10.1017\/9781107415782"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1017","DOI":"10.1111\/j.1469-8986.2012.01384.x","article-title":"Society for Psychophysiological Research Ad Hoc Committee on Electrodermal Measures. Publication recommendations for electrodermal measurements","volume":"49","author":"Boucsein","year":"2012","journal-title":"Psychophysiology"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"490","DOI":"10.1016\/j.biopsycho.2013.09.010","article-title":"An improved algorithm for model-based analysis of evoked skin conductance responses","volume":"94","author":"Bach","year":"2013","journal-title":"Biol. Psychol."},{"key":"ref_12","unstructured":"BIOPAC Systems, Inc. (2026, March 25). How Do I Compute Phasic Skin Conductance from Tonic EDA? AcqKnowledge Knowledge Base. Available online: https:\/\/www.biopac.com\/knowledge-base\/phasic-eda-issue\/."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"764","DOI":"10.1016\/j.jesp.2013.03.013","article-title":"Detecting outliers: Do not use standard deviation around the mean, use absolute deviation around the median","volume":"49","author":"Leys","year":"2013","journal-title":"J. Exp. Soc. Psychol."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Taylor, S., Jaques, N., Chen, W., Fedor, S., Sano, A., and Picard, R. (2015, January 25\u201329). Automatic Identification of Artifacts in Electrodermal Activity Data. Proceedings of the 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Milan, Italy.","DOI":"10.1109\/EMBC.2015.7318762"},{"key":"ref_15","first-page":"797","article-title":"cvxEDA: A Convex Optimization Approach to Electrodermal Activity Processing","volume":"63","author":"Greco","year":"2016","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"394","DOI":"10.1016\/j.biopsycho.2010.03.010","article-title":"Autonomic nervous system activity in emotion: A review","volume":"84","author":"Kreibig","year":"2010","journal-title":"Biol. Psychol."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1016\/j.procs.2021.03.021","article-title":"pyEDA: An Open-Source Python Toolkit for Pre-processing and Feature Extraction of Electrodermal Activity","volume":"184","author":"Aqajari","year":"2021","journal-title":"Procedia Comput. Sci."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Bobade, P., and Vani, M. (2020, January 15\u201317). Stress Detection with Machine Learning and Deep Learning using Multimodal Physiological Data. Proceedings of the Second International Conference on Inventive Research in Computing Applications (ICIRCA), Coimbatore, India.","DOI":"10.1109\/ICIRCA48905.2020.9183244"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1109\/MAES.2021.3115198","article-title":"Human stress detection with wearable sensors using convolutional neural networks","volume":"37","author":"Mateos","year":"2022","journal-title":"IEEE Aerosp. Electron. Syst. Mag."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Koldijk, S., Sappelli, M., Verberne, S., Neerincx, M.A., and Kraaij, W. (2014, January 12\u201316). The SWELL Knowledge Work Dataset for Stress and User Modeling Research. Proceedings of the 16th International Conference on Multimodal Interaction (ICMI), Istanbul, Turkey.","DOI":"10.1145\/2663204.2663257"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"156","DOI":"10.1109\/TITS.2005.848368","article-title":"Detecting stress during real-world driving tasks using physiological sensors","volume":"6","author":"Healey","year":"2005","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_22","unstructured":"Chaptoukaev, H., Strizhkova, V., Panariello, M., D\u2019Alpaos, B., Reka, A., Manera, V., Th\u00fcmmler, S., Ismailova, E., Evans, N., and Bremond, F. (2023, January 10\u201316). StressID: A Multimodal Dataset for Stress Identification. Proceedings of the Advances in Neural Information Processing Systems 36 (NeurIPS 2023) Datasets and Benchmarks Track, New Orleans, LA, USA."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1109\/T-AFFC.2011.15","article-title":"DEAP: A Database for Emotion Analysis Using Physiological Signals","volume":"3","author":"Koelstra","year":"2012","journal-title":"IEEE Trans. Affect. Comput."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/11\/3451\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T17:40:19Z","timestamp":1780076419000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/11\/3451"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,29]]},"references-count":23,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2026,6]]}},"alternative-id":["s26113451"],"URL":"https:\/\/doi.org\/10.3390\/s26113451","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,29]]}}}