{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T10:09:39Z","timestamp":1784023779302,"version":"3.55.0"},"reference-count":49,"publisher":"MDPI AG","issue":"23","license":[{"start":{"date-parts":[[2021,11,24]],"date-time":"2021-11-24T00:00:00Z","timestamp":1637712000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000780","name":"European Union","doi-asserted-by":"publisher","award":["883297"],"award-info":[{"award-number":["883297"]}],"id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Human stress is intricately linked with mental processes such as decision making. Public protection practitioners, including Law Enforcement Agents (LEAs), are forced to make difficult decisions during high-pressure operations, under strenuous circumstances. In this respect, systems and applications that assist such practitioners to take decisions, are increasingly incorporating user stress level information for their development, adaptation, and evaluation. To that end, our goal is to accurately detect and classify the level of acute, short-term stress, in real time, for the development of personalized, context-aware solutions for LEAs. Deep Neural Networks (DNNs), and in particular Convolutional Neural Networks (CNNs), have been gaining traction in the field of stress analysis, exhibiting promising results. Furthermore, the electrocardiogram (ECG) signals, have also been widely adopted for estimating levels of stress. In this work, we propose two CNN architectures for the stress detection and 3-level (low, moderate, high) stress classification tasks, using ultra short-term raw ECG signals (3 s). One architecture is simple and with a low memory footprint, suitable for running in wearable edge-computing nodes, and the other is able to learn more complex features, having more trainable parameters. The models were trained on the two publicly available stress classification datasets, after applying pre-processing techniques, such as data pruning, down-sampling, and data augmentation, using a sliding window approach. After hyperparameter tuning, using 4-fold cross-validation, the evaluation on the test set demonstrated state-of-the-art accuracy both on the 3- and 2-level stress classification task using the DriveDB dataset, reporting an accuracy of 83.55% and 98.77% respectively.<\/jats:p>","DOI":"10.3390\/s21237802","type":"journal-article","created":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T01:45:02Z","timestamp":1638323102000},"page":"7802","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":33,"title":["Real-Time Stress Level Feedback from Raw Ecg Signals for Personalised, Context-Aware Applications Using Lightweight Convolutional Neural Network Architectures"],"prefix":"10.3390","volume":"21","author":[{"given":"Konstantinos","family":"Tzevelekakis","sequence":"first","affiliation":[{"name":"Foundation for Research and Technology\u2014Hellas (FORTH), Institute of Computer Science, GR-70013 Heraklion, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zinovia","family":"Stefanidi","sequence":"additional","affiliation":[{"name":"Foundation for Research and Technology\u2014Hellas (FORTH), Institute of Computer Science, GR-70013 Heraklion, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9101-6301","authenticated-orcid":false,"given":"George","family":"Margetis","sequence":"additional","affiliation":[{"name":"Foundation for Research and Technology\u2014Hellas (FORTH), Institute of Computer Science, GR-70013 Heraklion, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2021,11,24]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Apostolakis, K., Dimitriou, N., Margetis, G., Ntoa, S., Tzovaras, D., and Stephanidis, C. (2021). DARLENE Improving situational awareness of European law enforcement agents through a combination of augmented reality and artificial intelligence solutions [version 1; peer review: Awaiting peer review]. Open Res. Eur., 1.","DOI":"10.12688\/openreseurope.13715.1"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1002\/gps.1660","article-title":"High score on the Relative Stress Scale, a marker of possible psychiatric disorder in family carers of patients with dementia","volume":"22","author":"Ulstein","year":"2007","journal-title":"Int. J. Geriatr. Psychiatry"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1016\/0146-6402(84)90001-8","article-title":"Phobic dimensions: I. Reliability and generalizability across samples, gender and nations: The fear survey schedule (FSS-III) and the fear questionnaire (FQ)","volume":"6","author":"Arrindell","year":"1984","journal-title":"Adv. Behav. Res. Ther."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1097\/00006842-198901000-00005","article-title":"The Cook-Medley hostility scale: Item content and ability to predict survival","volume":"51","author":"Barefoot","year":"1989","journal-title":"Psychosom. Med."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1097\/00006842-198901000-00004","article-title":"Hostility and cardiovascular reactivity to stress in women and men","volume":"51","author":"Weidner","year":"1989","journal-title":"Psychosom. Med."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"92","DOI":"10.1177\/1099800402238334","article-title":"Stress hormones: How do they measure up?","volume":"4","author":"King","year":"2002","journal-title":"Biol. Res. Nurs."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1016\/0301-0511(92)90018-P","article-title":"Assessing pilot workload. Why measure heart rate, HRV and respiration?","volume":"34","author":"Roscoe","year":"1992","journal-title":"Biol. Psychol."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"84045","DOI":"10.1109\/ACCESS.2021.3085502","article-title":"A Review on Mental Stress Detection Using Wearable Sensors and Machine Learning Techniques","volume":"9","author":"Gedam","year":"2021","journal-title":"IEEE Access"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"34746","DOI":"10.1109\/ACCESS.2018.2849870","article-title":"Evolution, Current Challenges, and Future Possibilities in ECG Biometrics","volume":"6","author":"Cardoso","year":"2018","journal-title":"IEEE Access"},{"key":"ref_10","first-page":"121","article-title":"Heart rate variability, trait anxiety, and perceived stress among physically fit men and women","volume":"37","author":"Dishman","year":"2000","journal-title":"Int. J. Psychophysiol. Off. J. Int. Organ. Psychophysiol."},{"key":"ref_11","first-page":"1128","article-title":"Electrodermal Activity Is Sensitive to Cognitive Stress under Water","volume":"8","author":"Florian","year":"2017","journal-title":"Front. Physiol."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Ahn, J.W., Ku, Y., and Kim, H.C. (2019). A Novel Wearable EEG and ECG Recording System for Stress Assessment. Sensors, 19.","DOI":"10.3390\/s19091991"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1287","DOI":"10.1016\/j.cmpb.2012.07.003","article-title":"Objective measures, sensors and computational techniques for stress recognition and classification: A survey","volume":"108","author":"Sharma","year":"2012","journal-title":"Comput. Methods Prog. Biomed."},{"key":"ref_14","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_15","unstructured":"Conover, M.B. (2002). Understanding Electrocardiography, Elsevier Health Sciences."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Giannakakis, G., Trivizakis, E., Tsiknakis, M., and Marias, K. (2019, January 3\u20136). A novel multi-kernel 1D convolutional neural network for stress recognition from ECG. Proceedings of the 2019 8th International Conference on Affective Computing and Intelligent Interaction Workshops and Demos (ACIIW), Cambridge, UK.","DOI":"10.1109\/ACIIW.2019.8925020"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"213","DOI":"10.3389\/fpsyg.2017.00213","article-title":"Heart Rate Variability and Cardiac Vagal Tone in Psychophysiological Research\u2014Recommendations for Experiment Planning, Data Analysis, and Data Reporting","volume":"8","author":"Laborde","year":"2017","journal-title":"Front. Psychol."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"623","DOI":"10.1111\/j.1469-8986.1997.tb02140.x","article-title":"Heart rate variability: Origins, methods, and interpretive caveats","volume":"34","author":"Berntson","year":"1997","journal-title":"Psychophysiology"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1007\/BF01819000","article-title":"Time and frequency domain assessment of heart rate variability: A theoretical and clinical appreciation","volume":"3","author":"Spiers","year":"1993","journal-title":"Clin. Auton. Res."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Ihmig, F.R., H, A.G., Neurohr-Parakenings, F., Sch\u00e4fer, S.K., Lass-Hennemann, J., and Michael, T. (2020). On-line anxiety level detection from biosignals: Machine learning based on a randomized controlled trial with spider-fearful individuals. PLoS ONE, 15.","DOI":"10.1371\/journal.pone.0231517"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Keshan, N., Parimi, P.V., and Bichindaritz, I. (November, January 29). Machine learning for stress detection from ECG signals in automobile drivers. Proceedings of the 2015 IEEE International Conference on Big Data (Big Data), Santa Clara, CA, USA.","DOI":"10.1109\/BigData.2015.7364066"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Serino, S., Matic, A., Giakoumis, D., Lopez, G., and Cipresso, P. (2016). Comparison of Machine Learning Techniques for Psychophysiological Stress Detection. Pervasive Computing Paradigms for Mental Health, Springer International Publishing. Communications in Computer and Information Science.","DOI":"10.1007\/978-3-319-32270-4"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"252","DOI":"10.1016\/j.bspc.2010.07.006","article-title":"Classification of electrocardiogram signals with support vector machines and genetic algorithms using power spectral features","volume":"5","author":"Khazaee","year":"2010","journal-title":"Biomed. Signal Process. Control"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"e8860841","DOI":"10.1155\/2020\/8860841","article-title":"Modified Support Vector Machine for Detecting Stress Level Using EEG Signals","volume":"2020","author":"Gupta","year":"2020","journal-title":"Comput. Intell. Neurosci."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1989","DOI":"10.1016\/j.procs.2020.04.213","article-title":"Assessment of Anxiety, Depression and Stress using Machine Learning Models","volume":"171","author":"Kumar","year":"2020","journal-title":"Procedia Comput. Sci."},{"key":"ref_26","unstructured":"Gris, M., and Yang, G. (2012). Activity-Aware Mental Stress Detection Using Physiological Sensors. Mobile Computing, Applications, and Services, Springer. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Munla, N., Khalil, M., Shahin, A., and Mourad, A. (2015, January 16\u201318). Driver stress level detection using HRV analysis. Proceedings of the 2015 International Conference on Advances in Biomedical Engineering (ICABME), Beirut, Lebanon.","DOI":"10.1109\/ICABME.2015.7323251"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"436","DOI":"10.7326\/0003-4819-118-6-199303150-00008","article-title":"Heart Rate Variability","volume":"118","author":"Kollee","year":"1993","journal-title":"Ann. Intern. Med."},{"key":"ref_29","unstructured":"Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning, MIT Press. Available online: http:\/\/www.deeplearningbook.org."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"107398","DOI":"10.1016\/j.ymssp.2020.107398","article-title":"1D convolutional neural networks and applications: A survey","volume":"151","author":"Kiranyaz","year":"2021","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"42710","DOI":"10.1109\/ACCESS.2019.2907076","article-title":"Real-Time Detection of Acute Cognitive Stress Using a Convolutional Neural Network From Electrocardiographic Signal","volume":"7","author":"He","year":"2019","journal-title":"IEEE Access"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"753","DOI":"10.1089\/tmj.2017.0250","article-title":"Deep ECGNet: An Optimal Deep Learning Framework for Monitoring Mental Stress Using Ultra Short-Term ECG Signals","volume":"24","author":"Hwang","year":"2018","journal-title":"Telemed. J. E-Heal. Off. J. Am. Telemed. Assoc."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Seo, W., Kim, N., Kim, S., Lee, C., and Park, S.M. (2019). Deep ECG-Respiration Network (DeepER Net) for Recognizing Mental Stress. Sensors, 19.","DOI":"10.3390\/s19133021"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Huang, J., Luo, X., and Peng, X. (2020). A Novel Classification Method for a Driver\u2019s Cognitive Stress Level by Transferring Interbeat Intervals of the ECG Signal to Pictures. Sensors, 20.","DOI":"10.3390\/s20051340"},{"key":"ref_35","unstructured":"Nain, N., Vipparthi, S.K., and Raman, B. (2020). Psychological Stress Detection Using Deep Convolutional Neural Networks, Springer. Computer Vision and Image Processing; Communications in Computer and Information Science."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"9951905","DOI":"10.1155\/2021\/9951905","article-title":"Classification of Mental Stress Using CNN-LSTM Algorithms with Electrocardiogram Signals","volume":"2021","author":"Kang","year":"2021","journal-title":"J. Healthc. Eng."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"E215","DOI":"10.1161\/01.CIR.101.23.e215","article-title":"PhysioBank, PhysioToolkit, and PhysioNet: Components of a new research resource for complex physiologic signals","volume":"101","author":"Goldberger","year":"2000","journal-title":"Circulation"},{"key":"ref_38","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, Boulder, CO, USA.","DOI":"10.1145\/3242969.3242985"},{"key":"ref_39","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 \u201914), Istanbul, Turkey.","DOI":"10.1145\/2663204.2663257"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1038\/s41592-019-0686-2","article-title":"SciPy 1.0: Fundamental Algorithms for Scientific Computing in Python","volume":"17","author":"Virtanen","year":"2020","journal-title":"Nat. Methods"},{"key":"ref_41","first-page":"430","article-title":"Evaluation of the physiological data indicating the dynamic stress level of drivers","volume":"6","year":"2011","journal-title":"SRE"},{"key":"ref_42","unstructured":"Healey, J.A. (2000). Wearable and Automotive Systems for Affect Recognition from Physiology. [Ph.D. Thesis, Massachusetts Institute of Technology]."},{"key":"ref_43","unstructured":"Simonyan, K., and Zisserman, A. (2015). Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"112793","DOI":"10.1016\/j.eswa.2019.07.010","article-title":"Automatic driver stress level classification using multimodal deep learning","volume":"138","author":"Rastgoo","year":"2019","journal-title":"Expert Syst. Appl."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"103810","DOI":"10.1016\/j.compbiomed.2020.103810","article-title":"Proposing a convolutional neural network for stress assessment by means of derived heart rate from functional near infrared spectroscopy","volume":"121","author":"Hakimi","year":"2020","journal-title":"Comput. Biol. Med."},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Lee, J., Lee, H., and Shin, M. (2021). Driving Stress Detection Using Multimodal Convolutional Neural Networks with Nonlinear Representation of Short-Term Physiological Signals. Sensors, 21.","DOI":"10.3390\/s21072381"},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Cho, H.M., Park, H., Dong, S.Y., and Youn, I. (2019). Ambulatory and Laboratory Stress Detection Based on Raw Electrocardiogram Signals Using a Convolutional Neural Network. Sensors, 19.","DOI":"10.3390\/s19204408"},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Zhang, P., Li, F., Zhao, R., Zhou, R., Du, L., Zhao, Z., Chen, X., and Fang, Z. (2021). Real-Time Psychological Stress Detection According to ECG Using Deep Learning. Appl. Sci., 11.","DOI":"10.3390\/app11093838"},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Ahmad, Z., and Khan, N. (2020). Multi-level Stress Assessment Using Multi-domain Fusion of ECG Signal. arXiv.","DOI":"10.1109\/EMBC44109.2020.9176590"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/23\/7802\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T07:34:57Z","timestamp":1760168097000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/23\/7802"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,11,24]]},"references-count":49,"journal-issue":{"issue":"23","published-online":{"date-parts":[[2021,12]]}},"alternative-id":["s21237802"],"URL":"https:\/\/doi.org\/10.3390\/s21237802","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,11,24]]}}}