{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T19:57:36Z","timestamp":1768420656184,"version":"3.49.0"},"reference-count":35,"publisher":"MDPI AG","issue":"19","license":[{"start":{"date-parts":[[2021,9,30]],"date-time":"2021-09-30T00:00:00Z","timestamp":1632960000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Internally funded","award":["000000"],"award-info":[{"award-number":["000000"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Frequent spontaneous facial self-touches, predominantly during outbreaks, have the theoretical potential to be a mechanism of contracting and transmitting diseases. Despite the recent advent of vaccines, behavioral approaches remain an integral part of reducing the spread of COVID-19 and other respiratory illnesses. The aim of this study was to utilize the functionality and the spread of smartwatches to develop a smartwatch application to identify motion signatures that are mapped accurately to face touching. Participants (n = 10, five women, aged 20\u201383) performed 10 physical activities classified into face touching (FT) and non-face touching (NFT) categories in a standardized laboratory setting. We developed a smartwatch application on Samsung Galaxy Watch to collect raw accelerometer data from participants. Data features were extracted from consecutive non-overlapping windows varying from 2 to 16 s. We examined the performance of state-of-the-art machine learning methods on face-touching movement recognition (FT vs. NFT) and individual activity recognition (IAR): logistic regression, support vector machine, decision trees, and random forest. While all machine learning models were accurate in recognizing FT categories, logistic regression achieved the best performance across all metrics (accuracy: 0.93 \u00b1 0.08, recall: 0.89 \u00b1 0.16, precision: 0.93 \u00b1 0.08, F1-score: 0.90 \u00b1 0.11, AUC: 0.95 \u00b1 0.07) at the window size of 5 s. IAR models resulted in lower performance, where the random forest classifier achieved the best performance across all metrics (accuracy: 0.70 \u00b1 0.14, recall: 0.70 \u00b1 0.14, precision: 0.70 \u00b1 0.16, F1-score: 0.67 \u00b1 0.15) at the window size of 9 s. In conclusion, wearable devices, powered by machine learning, are effective in detecting facial touches. This is highly significant during respiratory infection outbreaks as it has the potential to limit face touching as a transmission vector.<\/jats:p>","DOI":"10.3390\/s21196528","type":"journal-article","created":{"date-parts":[[2021,10,8]],"date-time":"2021-10-08T21:26:20Z","timestamp":1633728380000},"page":"6528","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["Using Smartwatches to Detect Face Touching"],"prefix":"10.3390","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0961-1927","authenticated-orcid":false,"given":"Chen","family":"Bai","sequence":"first","affiliation":[{"name":"Department of Health Outcomes and Biomedical Informatics, College of Medicine, University of Florida, Gainesville, FL 32610, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu-Peng","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Computer and Information Science and Engineering, University of Florida, Gainesville, FL 32611, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7626-6436","authenticated-orcid":false,"given":"Adam","family":"Wolach","sequence":"additional","affiliation":[{"name":"Department of Aging and Geriatric Research, College of Medicine, University of Florida, Gainesville, FL 32610, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9617-2952","authenticated-orcid":false,"given":"Lisa","family":"Anthony","sequence":"additional","affiliation":[{"name":"Department of Computer and Information Science and Engineering, University of Florida, Gainesville, FL 32611, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5345-8811","authenticated-orcid":false,"given":"Mamoun T.","family":"Mardini","sequence":"additional","affiliation":[{"name":"Department of Health Outcomes and Biomedical Informatics, College of Medicine, University of Florida, Gainesville, FL 32610, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2021,9,30]]},"reference":[{"key":"ref_1","unstructured":"(2021, August 13). CDC How to Prevent the Spread of Respiratory Illnesses in Disaster Evacuation Centers, Available online: https:\/\/www.cdc.gov\/disasters\/disease\/respiratoryic.html."},{"key":"ref_2","first-page":"1","article-title":"A survey of knowledge, attitudes and practices towards avian influenza in an adult population of Italy","volume":"8","author":"Abbate","year":"2008","journal-title":"BMC Infect. Dis."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"347","DOI":"10.1080\/15459620802003896","article-title":"A study quantifying the hand-to-face contact rate and its potential application to predicting respiratory tract infection","volume":"5","author":"Nicas","year":"2008","journal-title":"J. Occup. Environ. Hyg."},{"key":"ref_4","first-page":"85","article-title":"Biofeedback in medicine: Who, when, why and how?","volume":"7","author":"Frank","year":"2010","journal-title":"Ment. Health Fam. Med."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"112","DOI":"10.1016\/j.ajic.2014.10.015","article-title":"Face touching: A frequent habit that has implications for hand hygiene","volume":"43","author":"Kwok","year":"2015","journal-title":"Am. J. Infect. Control"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1002\/pbc.28593","article-title":"Frequency of face touching with and without a mask in pediatric hematology\/oncology health care professionals","volume":"67","author":"Lucas","year":"2020","journal-title":"Pediatr. Blood Cancer"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1016\/j.jocrd.2017.10.007","article-title":"Awareness enhancing and monitoring device plus habit reversal in the treatment of trichotillomania: An open feasibility trial","volume":"16","author":"Himle","year":"2018","journal-title":"J. Obsessive. Compuls. Relat. Disord."},{"key":"ref_8","unstructured":"(2021, August 13). IDC Worldwide Wearables Market Forecast to Maintain Double-Digit Growth in 2020 and Through 2024, According to IDC. Available online: https:\/\/www.idc.com\/getdoc.jsp?containerId=prUS46885820."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Davoudi, A., Wanigatunga, A.A., Kheirkhahan, M., Corbett, D.B., Mendoza, T., Battula, M., Ranka, S., Fillingim, R.B., Manini, T.M., and Rashidi, P. (2019). Accuracy of samsung gear s smartwatch for activity recognition: Validation study. JMIR mHealth uHealth, 7.","DOI":"10.2196\/11270"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"62","DOI":"10.1109\/MPRV.2017.3971131","article-title":"Recognizing detailed human context in the wild from smartphones and smartwatches","volume":"16","author":"Vaizman","year":"2017","journal-title":"IEEE Pervasive Comput."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Channa, A., Popescu, N., Skibinska, J., and Burget, R. (2021). The Rise of Wearable Devices during the COVID-19 Pandemic: A Systematic Review. Sensors, 21.","DOI":"10.3390\/s21175787"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1","DOI":"10.3389\/frobt.2021.612392","article-title":"FaceGuard: A Wearable System To Avoid Face Touching","volume":"8","author":"Michelin","year":"2021","journal-title":"Front. Robot. AI"},{"key":"ref_13","unstructured":"Ye, X., Chen, G., and Cao, Y. (2015, January 14\u201317). Automatic Eating Detection using head-mount and wrist-worn accelerometers. Proceedings of the 2015 17th International Conference on E-health Networking, Application & Services, Boston, MA, USA."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1253","DOI":"10.1109\/JBHI.2013.2282471","article-title":"Detecting periods of eating during free-living by tracking wrist motion","volume":"18","author":"Dong","year":"2014","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Parate, A., Chiu, M.C., Chadowitz, C., Ganesan, D., and Kalogerakis, E. (2014, January 16\u201319). RisQ: Recognizing smoking gestures with inertial sensors on a wristband. Proceedings of the 12th Annual International Conference on Mobile Systems, Applications, and Services, Bretton Woods, NH, USA.","DOI":"10.1145\/2594368.2594379"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Senyurek, V., Imtiaz, M., Belsare, P., Tiffany, S., and Sazonov, E. (2019). Cigarette smoking detection with an inertial sensor and a smart lighter. Sensors, 19.","DOI":"10.3390\/s19030570"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Sudharsan, B., Sundaram, D., Breslin, J.G., and Ali, M.I. (2020, January 6\u20139). Avoid Touching Your Face: A Hand-to-face 3D Motion Dataset (COVID-away) and Trained Models for Smartwatches. Proceedings of the 10th International Conference on the Internet of Things Companion, Malm\u00f6, Sweden.","DOI":"10.1145\/3423423.3423433"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"206","DOI":"10.1249\/JES.0000000000000206","article-title":"A Framework to evaluate devices that assess physical behavior","volume":"47","author":"Keadle","year":"2019","journal-title":"Exerc. Sport Sci. Rev."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"525","DOI":"10.1111\/cpf.12337","article-title":"Physical activity using wrist-worn accelerometers: Comparison of dominant and non-dominant wrist","volume":"37","author":"Dieu","year":"2017","journal-title":"Clin. Physiol. Funct. Imaging"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1016\/j.jbi.2018.11.003","article-title":"A smartwatch-based framework for real-time and online assessment and mobility monitoring","volume":"89","author":"Kheirkhahan","year":"2019","journal-title":"J. Biomed. Inform."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1007\/s12668-013-0088-3","article-title":"A Review and Taxonomy of Activity Recognition on Mobile Phones","volume":"3","author":"Incel","year":"2013","journal-title":"Bionanoscience"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Krause, A., Smailagic, A., Siewiorek, D.P., and Farringdon, J. (2003). Unsupervised, dynamic identification of physiological and activity context in wearable computing. Proc. Int. Symp. Wearable Comput. ISWC, 88\u201397.","DOI":"10.1109\/ISWC.2003.1241398"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"2193","DOI":"10.1249\/MSS.0b013e31829736d6","article-title":"Activity recognition using a single accelerometer placed at the wrist or ankle","volume":"45","author":"Mannini","year":"2013","journal-title":"Med. Sci. Sports Exerc."},{"key":"ref_24","first-page":"516","article-title":"Feature selection and activity recognition from wearable sensors","volume":"4239","author":"Pirttikangas","year":"2006","journal-title":"Lect. Notes Comput. Sci. Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinform."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Stikic, M., Hu\u1ef3nh, T., Van Laerhoven, K., and Schiele, B. (February, January 30). ADL recognition based on the combination of RFID and aeeelerometer sensing. Proceedings of the 2008 Second International Conference on Pervasive Computing Technologies for Healthcare, Tampere, Finland.","DOI":"10.4108\/ICST.PERVASIVEHEALTH2008.2795"},{"key":"ref_26","first-page":"159","article-title":"Analyzing features for activity recognition","volume":"121","author":"Huynh","year":"2005","journal-title":"ACM Int. Conf. Proc. Ser."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"396","DOI":"10.1152\/japplphysiol.00026.2015","article-title":"Methods to estimate aspects of physical activity and sedentary behavior from high-frequency wrist accelerometer measurements","volume":"119","author":"Staudenmayer","year":"2015","journal-title":"J. Appl. Physiol."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Pires, I.M., Marques, G., Garcia, N.M., Fl\u00f3rez-Revuelta, F., Teixeira, M.C., Zdravevski, E., Spinsante, S., and Coimbra, M. (2020). Pattern recognition techniques for the identification of activities of daily living using a mobile device accelerometer. Electronics, 9.","DOI":"10.3390\/electronics9030509"},{"key":"ref_29","first-page":"2079","article-title":"On over-fitting in model selection and subsequent selection bias in performance evaluation","volume":"11","author":"Cawley","year":"2010","journal-title":"J. Mach. Learn. Res."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Corchado, E., Corchado, J.M., and Abraham, A. (2007). Finding Optimal Model Parameters by Discrete Grid Search. Innovations in Hybrid Intelligent Systems, Springer.","DOI":"10.1007\/978-3-540-74972-1"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random Forest","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn."},{"key":"ref_32","unstructured":"(2021, August 13). Machine Learning Model Codes. Available online: https:\/\/github.com\/ufdsat\/FTCode."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Zaki, Z. (2020). Logistic Regression Based Human Activities Recognition. J. Mech. Contin. Math. Sci., 15.","DOI":"10.26782\/jmcms.2020.04.00018"},{"key":"ref_34","unstructured":"Anguita, D., Ghio, A., Oneto, L., Parra, X., and Reyes-Ortiz, J.L. (2013, January 2\u20134). A Public Domain Dataset for Human Activity Recognition Using Smartphones. Proceedings of the 21th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN, Bruges, Belgium."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Bellinger, C., Sharma, S., and Japkowicz, N. (2012, January 12\u201315). One-class versus binary classification: Which and when?. Proceedings of the 2012 11th International Conference on Machine Learning and Applications, Boca Raton, FL, USA.","DOI":"10.1109\/ICMLA.2012.212"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/19\/6528\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T07:07:39Z","timestamp":1760166459000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/19\/6528"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,30]]},"references-count":35,"journal-issue":{"issue":"19","published-online":{"date-parts":[[2021,10]]}},"alternative-id":["s21196528"],"URL":"https:\/\/doi.org\/10.3390\/s21196528","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,9,30]]}}}