{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T05:05:32Z","timestamp":1789967132302,"version":"4.0.1"},"reference-count":26,"publisher":"MDPI AG","issue":"18","license":[{"start":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T00:00:00Z","timestamp":1789516800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100014809","name":"Technology Agency of the Czech Republic","doi-asserted-by":"publisher","award":["TQ15000052"],"award-info":[{"award-number":["TQ15000052"]}],"id":[{"id":"10.13039\/100014809","id-type":"DOI","asserted-by":"publisher"}]},{"award":["TQ15000052"],"award-info":[{"award-number":["TQ15000052"]}],"id":[{"id":"https:\/\/ror.org\/04v0fk911","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Falls in older adults are a leading cause of injury, and the time spent on the floor afterwards is the stronger predictor of outcome. We present a low-cost system that detects the sustained lying posture following a fall. An FLIR Lepton 3.1R (160 \u00d7 120 px) and an int8-quantized FOMO detector run fully on an OpenMV RT1062 board; no image data leaves the node. Ten healthy adults, none in the training data, followed a structured posture protocol, yielding 3034 labelled frames. No fall, real or simulated, was recorded: lying is a proxy for a post-fall state, and claims are restricted accordingly. The detector produced an output on only 66.3% of labelled frames, with a strong class dependence (75.6% lying, 51.7% standing). End-to-end, binary lying-posture recognition reached a sensitivity of 0.723 (95% CI 0.637\u20130.812) and an F1 of 0.801. Every sustained lying bout of at least 20 s was flagged, but the deployed alert rule also produced roughly one hundred false alerts per hour of non-lying activity. Low-resolution thermal sensing is therefore a workable basis for long-lie detection; the limiting factors are the detector\u2019s class-dependent miss rate and the alert logic, not the posture classifier.<\/jats:p>","DOI":"10.3390\/s26185868","type":"journal-article","created":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T13:50:27Z","timestamp":1789566627000},"page":"5868","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Privacy-Preserving Detection of Post-Fall Lying Posture Using a Low-Resolution Infrared Sensor and an Edge FOMO Neural Network"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-4522-4533","authenticated-orcid":false,"given":"Michaela","family":"Mrazkova","sequence":"first","affiliation":[{"name":"University Centre for Energy Efficient Buildings, Czech Technical University in Prague, 273 43 Bustehrad, Czech Republic"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7687-4594","authenticated-orcid":false,"given":"Jakub","family":"Vanek","sequence":"additional","affiliation":[{"name":"University Centre for Energy Efficient Buildings, Czech Technical University in Prague, 273 43 Bustehrad, Czech Republic"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7388-4983","authenticated-orcid":false,"given":"Martin","family":"Faltus","sequence":"additional","affiliation":[{"name":"University Centre for Energy Efficient Buildings, Czech Technical University in Prague, 273 43 Bustehrad, Czech Republic"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5332-1666","authenticated-orcid":false,"given":"Vit","family":"Janovsky","sequence":"additional","affiliation":[{"name":"University Centre for Energy Efficient Buildings, Czech Technical University in Prague, 273 43 Bustehrad, Czech Republic"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,9,16]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"a2227","DOI":"10.1136\/bmj.a2227","article-title":"Inability to Get up after Falling, Subsequent Time on Floor, and Summoning Help: Prospective Cohort Study in People over 90","volume":"337","author":"Fleming","year":"2008","journal-title":"BMJ"},{"key":"ref_2","unstructured":"World Health Organization (2026, April 24). Falls. Available online: https:\/\/www.who.int\/news-room\/fact-sheets\/detail\/falls."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"993","DOI":"10.15585\/mmwr.mm6537a2","article-title":"Falls and Fall Injuries Among Adults Aged \u226565 Years\u2014United States, 2014","volume":"65","author":"Bergen","year":"2016","journal-title":"MMWR Morb. Mortal. Wkly. Rep."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Bagal\u00e0, F., Becker, C., Cappello, A., Chiari, L., Aminian, K., Hausdorff, J.M., Zijlstra, W., and Klenk, J. (2012). Evaluation of Accelerometer-Based Fall Detection Algorithms on Real-World Falls. PLoS ONE, 7.","DOI":"10.1371\/journal.pone.0037062"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"2415","DOI":"10.1111\/jgs.13804","article-title":"Real-World Accuracy and Use of a Wearable Fall Detection Device by Older Adults","volume":"63","author":"Chaudhuri","year":"2015","journal-title":"J. Am. Geriatr. Soc."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Casilari, E., Santoyo-Ram\u00f3n, J.-A., and Cano-Garc\u00eda, J.-M. (2017). Analysis of Public Datasets for Wearable Fall Detection Systems. Sensors, 17.","DOI":"10.3390\/s17071513"},{"key":"ref_7","first-page":"9474806","article-title":"Vision-Based Fall Detection with Convolutional Neural Networks","volume":"2017","author":"Azkune","year":"2017","journal-title":"Wirel. Commun. Mob. Comput."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"3617","DOI":"10.1109\/TAES.2019.2910980","article-title":"Radar Data Cube Processing for Human Activity Recognition Using Multisubspace Learning","volume":"55","author":"Erol","year":"2019","journal-title":"IEEE Trans. Aerosp. Electron. Syst."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1007\/s00138-013-0570-5","article-title":"Thermal Cameras and Applications: A Survey","volume":"25","author":"Gade","year":"2014","journal-title":"Mach. Vis. Appl."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Tateno, S., Meng, F., Qian, R., and Hachiya, Y. (2020). Privacy-Preserved Fall Detection Method with Three-Dimensional Convolutional Neural Network Using Low-Resolution Infrared Array Sensor. Sensors, 20.","DOI":"10.3390\/s20205957"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Kido, S., Miyasaka, T., Tanaka, T., Shimizu, T., and Saga, T. (2009). Fall Detection in Toilet Rooms Using Thermal Imaging Sensors. Proceedings of the 2009 IEEE\/SICE International Symposium on System Integration (SII), Tokyo, Japan, 29 November 2009, IEEE.","DOI":"10.1109\/SI.2009.5384550"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Newaz, N.T., and Hanada, E. (2023). The Methods of Fall Detection: A Literature Review. Sensors, 23.","DOI":"10.3390\/s23115212"},{"key":"ref_13","unstructured":"Hymel, S., Banbury, C., Situnayake, D., Elium, A., Ward, C., Kelcey, M., Baaijens, M., Majchrzycki, M., Plunkett, J., and Tischler, D. (2022). Edge Impulse: An MLOps Platform for Tiny Machine Learning. arXiv."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., and Chen, L.-C. (2019). MobileNetV2: Inverted Residuals and Linear Bottlenecks. arXiv.","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref_15","unstructured":"(2026, September 03). Edge Impulse. FOMO. Available online: https:\/\/docs.edgeimpulse.com\/studio\/projects\/learning-blocks\/blocks\/object-detection\/fomo."},{"key":"ref_16","unstructured":"OpenMV (2026, June 26). OpenMV Cam RT1062. Available online: https:\/\/docs.openmv.io\/v5.0.0\/openmvcam\/quickref\/openmv-rt1062.html."},{"key":"ref_17","unstructured":"Teledyne FLIR (2026, September 03). Lepton Series: High Resolution LWIR Micro Thermal Camera Module. Datasheet. Available online: https:\/\/groupgets-files.s3.amazonaws.com\/lepton\/Resources\/Lepton%20Series%20Datasheet.pdf."},{"key":"ref_18","unstructured":"(2026, September 03). Edge Impulse Documentation. Available online: https:\/\/docs.edgeimpulse.com."},{"key":"ref_19","unstructured":"Banbury, C., Reddi, V.J., Torelli, P., Holleman, J., Jeffries, N., Kiraly, C., Montino, P., Kanter, D., Ahmed, S., and Pau, D. (2021). MLPerf Tiny Benchmark. arXiv."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Lin, Y., and Zhao, Q. (2025). Human Occupancy Monitoring and Positioning with Speed-Responsive Adaptive Sliding Window Using an Infrared Thermal Array Sensor. Sensors, 25.","DOI":"10.3390\/s25010129"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Newaz, N.T., and Hanada, E. (2025). An Approach to Fall Detection Using Statistical Distributions of Thermal Signatures Obtained by a Stand-Alone Low-Resolution IR Array Sensor Device. Sensors, 25.","DOI":"10.3390\/s25020504"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Newaz, N.T., and Hanada, E. (2024). A Low-Resolution Infrared Array for Unobtrusive Human Activity Recognition That Preserves Privacy. Sensors, 24.","DOI":"10.3390\/s24030926"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"611","DOI":"10.1109\/TCSVT.2011.2129370","article-title":"Robust Video Surveillance for Fall Detection Based on Human Shape Deformation","volume":"21","author":"Rougier","year":"2011","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Nguyen, D., Hong, H., Kim, K., and Park, K.K. (2017). Person Recognition System Based on a Combination of Body Images from Visible Light and Thermal Cameras. Sensors, 17.","DOI":"10.3390\/s17030605"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Wu, A., Zheng, W.-S., Yu, H.-X., Gong, S., and Lai, J. (2017). RGB-Infrared Cross-Modality Person Re-Identification. Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy, 22\u201329 October 2017, IEEE.","DOI":"10.1109\/ICCV.2017.575"},{"key":"ref_26","first-page":"541","article-title":"Thermal Imaging Based Elderly Fall Detection","volume":"Volume 10118","author":"Chen","year":"2017","journal-title":"Proceedings of Computer Vision\u2014ACCV 2016 Workshops, Taipei, Taiwan, 20\u201324 November 2016"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/18\/5868\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T04:29:58Z","timestamp":1789964998000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/18\/5868"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,16]]},"references-count":26,"journal-issue":{"issue":"18","published-online":{"date-parts":[[2026,9]]}},"alternative-id":["s26185868"],"URL":"https:\/\/doi.org\/10.3390\/s26185868","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,16]]}}}