{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,16]],"date-time":"2026-11-16T16:43:09Z","timestamp":1794847389857,"version":"4.9.1"},"reference-count":43,"publisher":"MDPI AG","issue":"10","license":[{"start":{"date-parts":[[2024,5,11]],"date-time":"2024-05-11T00:00:00Z","timestamp":1715385600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Open Access Publishing Fund of Leipzig University","id":[{"id":"https:\/\/ror.org\/03s7gtk40","id-type":"ROR","asserted-by":"crossref"}]},{"name":"Federal Ministry of Education and Research of Germany","id":[{"id":"https:\/\/ror.org\/04pz7b180","id-type":"ROR","asserted-by":"crossref"}]},{"name":"S\u00e4chsische Staatsministerium f\u00fcr Wissenschaft Kultur und Tourismus in the Center of Excellence for AI-research program"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Smartwatch health sensor data are increasingly utilized in smart health applications and patient monitoring, including stress detection. However, such medical data often comprise sensitive personal information and are resource-intensive to acquire for research purposes. In response to this challenge, we introduce the privacy-aware synthetization of multi-sensor smartwatch health readings related to moments of stress, employing Generative Adversarial Networks (GANs) and Differential Privacy (DP) safeguards. Our method not only protects patient information but also enhances data availability for research. To ensure its usefulness, we test synthetic data from multiple GANs and employ different data enhancement strategies on an actual stress detection task. Our GAN-based augmentation methods demonstrate significant improvements in model performance, with private DP training scenarios observing an 11.90\u201315.48% increase in F1-score, while non-private training scenarios still see a 0.45% boost. These results underline the potential of differentially private synthetic data in optimizing utility\u2013privacy trade-offs, especially with the limited availability of real training samples. Through rigorous quality assessments, we confirm the integrity and plausibility of our synthetic data, which, however, are significantly impacted when increasing privacy requirements.<\/jats:p>","DOI":"10.3390\/s24103052","type":"journal-article","created":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T11:18:17Z","timestamp":1715599097000},"page":"3052","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":26,"title":["Generating Synthetic Health Sensor Data for Privacy-Preserving Wearable Stress Detection"],"prefix":"10.3390","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6745-0845","authenticated-orcid":false,"given":"Lucas","family":"Lange","sequence":"first","affiliation":[{"name":"ScaDS.AI Dresden\/Leipzig, Leipzig University, Augustusplatz 10, 04109 Leipzig, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nils","family":"Wenzlitschke","sequence":"additional","affiliation":[{"name":"ScaDS.AI Dresden\/Leipzig, Leipzig University, Augustusplatz 10, 04109 Leipzig, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2665-1114","authenticated-orcid":false,"given":"Erhard","family":"Rahm","sequence":"additional","affiliation":[{"name":"ScaDS.AI Dresden\/Leipzig, Leipzig University, Augustusplatz 10, 04109 Leipzig, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2024,5,11]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"440","DOI":"10.1109\/TAFFC.2019.2927337","article-title":"Review on psychological stress detection using biosignals","volume":"13","author":"Giannakakis","year":"2019","journal-title":"IEEE Trans. Affect. Comput."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Schmidt, P., Reiss, A., D\u00fcrichen, R., and Van Laerhoven, K. (2019). Wearable-based affect recognition\u2014A review. Sensors, 19.","DOI":"10.3390\/s19194079"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"444","DOI":"10.1016\/j.bbe.2019.01.004","article-title":"A survey of machine learning techniques in physiology based mental stress detection systems","volume":"39","author":"Panicker","year":"2019","journal-title":"Biocybern. Biomed. Eng."},{"key":"ref_4","unstructured":"Perez, E., and Abdel-Ghaffar, S. (2024, May 08). (Google\/Fitbit). How We Trained Fitbit\u2019s Body Response Feature to Detect Stress. Available online: https:\/\/blog.google\/products\/fitbit\/how-we-trained-fitbits-body-response-feature-to-detect-stress\/."},{"key":"ref_5","unstructured":"Garmin Technology (2024, May 08). Stress Tracking. Available online: https:\/\/www.garmin.com\/en-US\/garmin-technology\/health-science\/stress-tracking\/."},{"key":"ref_6","unstructured":"Samsung Electronics (2024, May 08). Measure Your Stress Level with Samsung Health. Available online: https:\/\/www.samsung.com\/us\/support\/answer\/ANS00080574\/."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Narayanan, A., and Shmatikov, V. (2008, January 18\u201322). Robust de-anonymization of large sparse datasets. Proceedings of the 2008 IEEE Symposium on Security and Privacy (SP), Oakland, CA, USA.","DOI":"10.1109\/SP.2008.33"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1109\/MITP.2017.265105905","article-title":"Privacy issues and solutions for consumer wearables","volume":"20","author":"Perez","year":"2017","journal-title":"Professional"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Jafarlou, S., Rahmani, A.M., Dutt, N., and Mousavi, S.R. (2008, January 18\u201322). ECG Biosignal Deidentification Using Conditional Generative Adversarial Networks. Proceedings of the 2022 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), Oakland, CA, USA.","DOI":"10.1109\/EMBC48229.2022.9872015"},{"key":"ref_10","unstructured":"Lange, L., Schreieder, T., Christen, V., and Rahm, E. (2023). Privacy at Risk: Exploiting Similarities in Health Data for Identity Inference. arXiv."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Saleheen, N., Ullah, M.A., Chakraborty, S., Ones, D.S., Srivastava, M., and Kumar, S. (2021, January 15\u201319). Wristprint: Characterizing user re-identification risks from wrist-worn accelerometry data. Proceedings of the 2021 ACM SIGSAC Conference on Computer and Communications Security, Virtual Event.","DOI":"10.1145\/3460120.3484799"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"El Emam, K., Jonker, E., Arbuckle, L., and Malin, B. (2011). A systematic review of re-identification attacks on health data. PLoS ONE, 6.","DOI":"10.1371\/journal.pone.0028071"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"e239","DOI":"10.1016\/S2589-7500(22)00234-5","article-title":"Does deidentification of data from wearable devices give us a false sense of security? A systematic review","volume":"5","author":"Chikwetu","year":"2023","journal-title":"Lancet Digit. Health"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"e000167","DOI":"10.1136\/bmjmed-2022-000167","article-title":"Synthetic data in medical research","volume":"1","author":"Kokosi","year":"2022","journal-title":"BMJ Med."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"16233","DOI":"10.1109\/ACCESS.2023.3340884","article-title":"Ethical Frameworks for Machine Learning in Sensitive Healthcare Applications","volume":"12","author":"Javed","year":"2023","journal-title":"IEEE Access"},{"key":"ref_16","unstructured":"Dwork, C. (2006). International Colloquium on Automata, Languages, and Programming, Springer."},{"key":"ref_17","first-page":"139","article-title":"Generative adversarial nets","volume":"27","author":"Goodfellow","year":"2014","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_18","unstructured":"Xie, L., Lin, K., Wang, S., Wang, F., and Zhou, J. (2018). Differentially private generative adversarial network. arXiv."},{"key":"ref_19","unstructured":"Lange, L., Degenkolb, B., and Rahm, E. (2023, January 26\u201329). Privacy-Preserving Stress Detection Using Smartwatch Health Data. Proceedings of the 4. Interdisciplinary Privacy & Security at Large Workshop, INFORMATIK 2023, Berlin, Germany."},{"key":"ref_20","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_21","doi-asserted-by":"crossref","unstructured":"Siirtola, P. (2019, January 9\u201313). Continuous stress detection using the sensors of commercial smartwatch. Proceedings of the 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, London, UK.","DOI":"10.1145\/3341162.3344831"},{"key":"ref_22","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_23","unstructured":"Empatica Incorporated (2024, May 08). E4 Wristband. Available online: http:\/\/www.empatica.com\/research\/e4\/."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Nasr, M., Songi, S., Thakurta, A., Papernot, N., and Carlin, N. (2021, January 24\u201327). Adversary instantiation: Lower bounds for differentially private machine learning. Proceedings of the 2021 IEEE Symposium on Security and Privacy (SP), San Francisco, CA, USA.","DOI":"10.1109\/SP40001.2021.00069"},{"key":"ref_25","unstructured":"Carlini, N., Liu, C., Erlingsson, \u00da., Kos, J., and Song, D. (2019, January 14\u201316). The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks. Proceedings of the 28th USENIX Security Symposium (USENIX Security 19), Santa Clara, CA, USA."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Lange, L., Schneider, M., Christen, P., and Rahm, E. (2023, January 10\u201312). Privacy in Practice: Private COVID-19 Detection in X-Ray Images. Proceedings of the 20th International Conference on Security and Cryptography (SECRYPT 2023). SciTePress, Rome, Italy.","DOI":"10.5220\/0012048100003555"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Abadi, M., Chu, A., Goodfellow, I., McMahan, H.B., Mironov, I., Talwar, K., and Zhang, L. (2016, January 24\u201328). Deep learning with differential privacy. Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security, Vienna, Austria.","DOI":"10.1145\/2976749.2978318"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Ehrhart, M., Resch, B., Havas, C., and Niederseer, D. (2022). A Conditional GAN for Generating Time Series Data for Stress Detection in Wearable Physiological Sensor Data. Sensors, 22.","DOI":"10.3390\/s22165969"},{"key":"ref_29","unstructured":"Stadler, T., Oprisanu, B., and Troncoso, C. (2022, January 10\u201312). Synthetic Data\u2014Anonymisation Groundhog Day. Proceedings of the 31st USENIX Security Symposium (USENIX Security 22), Boston, MA, USA."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Torkzadehmahani, R., Kairouz, P., and Paten, B. DP-CGAN: Differentially Private Synthetic Data and Label Generation. Proceedings of the 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Long Beach, CA, USA.","DOI":"10.1109\/CVPRW.2019.00018"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Dzie\u017cyc, M., Gjoreski, M., Kazienko, P., Saganowski, S., and Gams, M. (2020). Can we ditch feature engineering? end-to-end deep learning for affect recognition from physiological sensor data. Sensors, 20.","DOI":"10.3390\/s20226535"},{"key":"ref_32","first-page":"5508","article-title":"Time-series generative adversarial networks","volume":"32","author":"Yoon","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_33","unstructured":"Mirza, M., and Osindero, S. (2014). Conditional generative adversarial nets. arXiv."},{"key":"ref_34","unstructured":"Esteban, C., Hyland, S.L., and R\u00e4tsch, G. (2017). Real-valued (medical) time series generation with recurrent conditional gans. arXiv."},{"key":"ref_35","unstructured":"Wenzlitschke, N. (2023). Privacy-Preserving Smartwatch Health Data Generation For Stress Detection Using GANs. [Master\u2019s thesis, University Leipzig]."},{"key":"ref_36","unstructured":"Kingma, D.P., and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Lin, Z., Jain, A., Wang, C., Fanti, G., and Sekar, V. (2020, January 27\u201329). Using gans for sharing networked time series data: Challenges, initial promise, and open questions. Proceedings of the ACM Internet Measurement Conference, Virtual Event.","DOI":"10.1145\/3419394.3423643"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Liu, Y., Peng, J., James, J., and Wu, Y. (2019, January 4\u20136). PPGAN: Privacy-preserving generative adversarial network. Proceedings of the 2019 IEEE 25Th International Conference on Parallel and Distributed Systems (ICPADS), Tianjin, China.","DOI":"10.1109\/ICPADS47876.2019.00150"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1016\/0169-7439(87)80084-9","article-title":"Principal component analysis","volume":"2","author":"Wold","year":"1987","journal-title":"Chemom. Intell. Lab. Syst."},{"key":"ref_40","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Hinton","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"e4483","DOI":"10.1136\/bmj.e4483","article-title":"Pearson\u2019s correlation coefficient","volume":"345","author":"Sedgwick","year":"2012","journal-title":"BMJ"},{"key":"ref_42","first-page":"203","article-title":"P values: What they are and what they are not","volume":"50","author":"Schervish","year":"1996","journal-title":"Am. Stat."},{"key":"ref_43","unstructured":"Lopez-Paz, D., and Oquab, M. (2016). Revisiting classifier two-sample tests. arXiv."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/10\/3052\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T14:44:16Z","timestamp":1760107456000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/10\/3052"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,11]]},"references-count":43,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2024,5]]}},"alternative-id":["s24103052"],"URL":"https:\/\/doi.org\/10.3390\/s24103052","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5,11]]}}}