{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T16:23:18Z","timestamp":1778084598536,"version":"3.51.4"},"reference-count":28,"publisher":"MDPI AG","issue":"16","license":[{"start":{"date-parts":[[2022,8,16]],"date-time":"2022-08-16T00:00:00Z","timestamp":1660608000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Korea Institute of Machinery and Materials","award":["NK238F"],"award-info":[{"award-number":["NK238F"]}]},{"name":"Korea Institute of Machinery and Materials","award":["20006386"],"award-info":[{"award-number":["20006386"]}]},{"DOI":"10.13039\/501100003052","name":"Technology Innovation Program","doi-asserted-by":"publisher","award":["NK238F"],"award-info":[{"award-number":["NK238F"]}],"id":[{"id":"10.13039\/501100003052","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003052","name":"Technology Innovation Program","doi-asserted-by":"publisher","award":["20006386"],"award-info":[{"award-number":["20006386"]}],"id":[{"id":"10.13039\/501100003052","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Workers at construction sites are prone to fall-from-height (FFH) accidents. The severity of injury can be represented by the acceleration peak value. In the study, a risk prediction against FFH was made using IMU sensor data for accident prevention at construction sites. Fifteen general working movements (NF: non-fall), five low-hazard-fall movements, (LF), and five high-hazard-FFH movements (HF) were performed by twenty male subjects and a dummy. An IMU sensor was attached to the T7 position of the subject to measure the three-axis acceleration and angular velocity. The peak acceleration value, calculated from the IMU data, was 4 g or less in general work movements and 9 g or more in FFHs. Regression analysis was performed by applying various deep learning models, including 1D-CNN, 2D-CNN, LSTM, and Conv-LSTM, to the risk prediction, and then comparing them in terms of their mean absolute error (MAE) and mean squared error (MSE). The FFH risk level was estimated based on the predicted peak acceleration. The Conv-LSTM model trained by MAE showed the smallest error (MAE: 1.36 g), and the classification with the predicted peak acceleration showed the best accuracy (97.6%). This study successfully predicted the FFH risk levels and could be helpful to reduce fatal injuries at construction sites.<\/jats:p>","DOI":"10.3390\/s22166107","type":"journal-article","created":{"date-parts":[[2022,8,16]],"date-time":"2022-08-16T03:40:32Z","timestamp":1660621232000},"page":"6107","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":26,"title":["Fall-from-Height Detection Using Deep Learning Based on IMU Sensor Data for Accident Prevention at Construction Sites"],"prefix":"10.3390","volume":"22","author":[{"given":"Seunghee","family":"Lee","sequence":"first","affiliation":[{"name":"Department of Biomedical Engineering, Yonsei University, Wonju 26493, Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4681-6318","authenticated-orcid":false,"given":"Bummo","family":"Koo","sequence":"additional","affiliation":[{"name":"Department of Biomedical Engineering, Yonsei University, Wonju 26493, Korea"}]},{"given":"Sumin","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Biomedical Engineering, Yonsei University, Wonju 26493, Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2053-8994","authenticated-orcid":false,"given":"Jongman","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Biomedical Engineering, Yonsei University, Wonju 26493, Korea"}]},{"given":"Yejin","family":"Nam","sequence":"additional","affiliation":[{"name":"Department of Biomedical Engineering, Yonsei University, Wonju 26493, Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7531-802X","authenticated-orcid":false,"given":"Youngho","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Biomedical Engineering, Yonsei University, Wonju 26493, Korea"}]}],"member":"1968","published-online":{"date-parts":[[2022,8,16]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1016\/j.ergon.2019.02.011","article-title":"Comparison of fatal occupational injuries in construction industry in the United States, South Korea, and China","volume":"71","author":"Choi","year":"2019","journal-title":"Int. J. Ind. Ergon."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"194","DOI":"10.1016\/j.autcon.2016.04.007","article-title":"Semi-supervised near-miss fall detection for ironworkers with a wearable inertial measurement unit","volume":"68","author":"Yang","year":"2016","journal-title":"Automat. Constr."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Liu, D., Sommerich, C.M., Sanders, E.B.-N., and Lavender, S.A. Application of a participatory methodology for investigating Personal Fall Arrest System (PFAS) usage in the construction industry. In Proceedings of the Human Factors and Ergonomics Society Annual Meeting, San Antonio, TX, USA, 19\u201323 October 2009; Volume 53.","DOI":"10.1177\/154193120905301415"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Pomares, J.C., Carri\u00f3n, E.\u00c1., Gonz\u00e1lez, A., and Saez, P.I. (2020). Optimization on Personal Fall Arrest Systems. Experimental Dynamic Studies on Lanyard Prototypes. Int. J. Environ. Res. Public Health, 17.","DOI":"10.3390\/ijerph17031107"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"04014059","DOI":"10.1061\/(ASCE)CO.1943-7862.0000910","article-title":"Empirical investigation of the average deployment force of personal fall-arrest energy absorbers","volume":"141","author":"Goh","year":"2015","journal-title":"J. Constr. Eng. Manag."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1136\/emj.2007.046391","article-title":"Suspension trauma","volume":"24","author":"Lee","year":"2007","journal-title":"Emerg. Med. J."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"136","DOI":"10.1016\/j.aap.2017.02.028","article-title":"Fatal falls and PFAS use in the construction industry: Findings from the NIOSH FACE reports","volume":"102","author":"Dong","year":"2017","journal-title":"Accid. Anal. Prev."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"635","DOI":"10.1061\/(ASCE)CP.1943-5487.0000279","article-title":"Vision-based detection of unsafe actions of a construction worker: Case study of ladder climbing","volume":"27","author":"Han","year":"2013","journal-title":"J. Comput. Civ. Eng."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"170","DOI":"10.1016\/j.aei.2018.12.005","article-title":"A deep lea rning-based approach for mitigating falls from height with computer vision: Convolutional neural network","volume":"39","author":"Fang","year":"2019","journal-title":"Adv. Eng. Inform."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"101400","DOI":"10.1016\/j.aei.2021.101400","article-title":"Computer vision and long short-term memory: Learning to predict unsafe behaviour in construction","volume":"50","author":"Kong","year":"2021","journal-title":"Adv. Eng. Inform."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Jung, H., Koo, B., Kim, J., Kim, T., Nam, Y., and Kim, Y. (2020). Enhanced algorithm for the detection of preimpact fall for wearable airbags. Sensors, 20.","DOI":"10.3390\/s20051277"},{"key":"ref_12","first-page":"1743","article-title":"Optimization of a pre-impact fall detection algorithm and development of hip protection airbag system","volume":"30","author":"Ahn","year":"2018","journal-title":"Sens. Mater."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Koo, B., Kim, J., Nam, Y., and Kim, Y. (2021). The Performance of Post-Fall Detection Using the Cross-Dataset: Feature Vectors, Classifiers and Processing Conditions. Sensors, 21.","DOI":"10.3390\/s21144638"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Dogan, O., and Akcamete, A. (2019). Detecting falls-from-height with wearable sensors and reducing consequences of occupational fall accidents leveraging IoT. Advances in Informatics and Computing in Civil and Construction Engineering, Springer.","DOI":"10.1007\/978-3-030-00220-6_25"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Kim, Y., Jung, H., Koo, B., Kim, J., Kim, T., and Nam, Y. (2020). Detection of pre-impact falls from heights using an inertial measurement unit sensor. Sensors, 20.","DOI":"10.3390\/s20185388"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"411","DOI":"10.1007\/s00068-017-0799-1","article-title":"Fall from heights: Does height really matter?","volume":"44","author":"Alizo","year":"2018","journal-title":"Eur. J. Trauma Emerg. Surg."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Arena, S., Davis, J., Grant, J., and Madigan, M. (2016). Tripping elicits earlier and larger deviations in linear head acceleration compared to slipping. PLoS ONE, 11.","DOI":"10.1371\/journal.pone.0165670"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"2143","DOI":"10.1007\/s10439-015-1255-1","article-title":"Measurement of Head Impact Due to Standing Fall in Adults Using Anthropomorphic Test Dummies","volume":"43","author":"Hajiaghamemar","year":"2015","journal-title":"Ann. Biomed. Eng."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Kim, T., Choi, A., Heo, H., Kim, H., and Mun, J. (2020). Acceleration Magnitude at Impact Following Loss of Balance Can Be Estimated Using Deep Learning Model. Sensors, 20.","DOI":"10.3390\/s20216126"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"259","DOI":"10.3795\/KSME-A.2022.46.3.259","article-title":"Multi-class Classification of Industrial Fall from Height based on Machine Learning Algorithm","volume":"46","author":"Koo","year":"2022","journal-title":"Trans. Korean Soc. Mech. Eng. A"},{"key":"ref_21","unstructured":"Occupational Safety and Health Adminstraion, U.S. (2022, August 02). Department of Labor, Directorate of Technical Support and Emergency Management, OSHA Technical Manual (OTM)\u2014Section V: Chapter 4, Available online: https:\/\/www.osha.gov\/otm\/section-5-construction-operations\/chapter-4#fall_arrest."},{"key":"ref_22","unstructured":"Albers, J.T., and Estill, C.F. (2007). Simple Solutions: Ergonomics for Construction Workers, National Institute for Occupational Safety and Health."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Huang, S., Tang, J., Dai, J., and Wang, Y. (2019). Signal Status Recognition Based on 1DCNN and Its Feature Extraction Mechanism Analysis. Sensors, 19.","DOI":"10.3390\/s19092018"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1016\/j.imavis.2018.09.011","article-title":"Enhancing convolutional neural networks for face recognition with occlusion maps and batch triplet loss","volume":"79","author":"Trigueros","year":"2018","journal-title":"Image Vis. Comput."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"63","DOI":"10.3389\/fbioe.2020.00063","article-title":"A novel hybrid deep neural network to predict pre-impact fall for older people based on wearable inertial sensors","volume":"8","author":"Yu","year":"2020","journal-title":"Front. Bioeng. Biotechnol."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"6622927","DOI":"10.1155\/2020\/6622927","article-title":"A CNN-LSTM-based model to forecast stock prices","volume":"2020","author":"Lu","year":"2020","journal-title":"Complexity"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1016\/j.patcog.2017.10.013","article-title":"Recent advances in convolutional neural networks","volume":"77","author":"Gu","year":"2018","journal-title":"Pattern Recognit."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/16\/6107\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T00:09:12Z","timestamp":1760141352000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/16\/6107"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,16]]},"references-count":28,"journal-issue":{"issue":"16","published-online":{"date-parts":[[2022,8]]}},"alternative-id":["s22166107"],"URL":"https:\/\/doi.org\/10.3390\/s22166107","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,8,16]]}}}