{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T19:02:17Z","timestamp":1780081337808,"version":"3.54.0"},"reference-count":34,"publisher":"MDPI AG","issue":"19","license":[{"start":{"date-parts":[[2024,9,26]],"date-time":"2024-09-26T00:00:00Z","timestamp":1727308800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Science Foundation","award":["21223749"],"award-info":[{"award-number":["21223749"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Falls are the second leading cause of unintentional injury deaths worldwide. While numerous wearable fall detection devices incorporating AI models have been developed, none of them are used successfully in a fall detection application running on commodity-based smartwatches in real time. The system misses some falls, and generates an annoying amount of False Positives for practical use. We have investigated and experimented with an LSTM model for fall detection on a smartwatch. Even though the LSTM model has high accuracy during offline testing, the good performance of offline LSTM models cannot be translated to the equivalence of real-time performance. Transformers, on the other hand, can learn long-sequence data and patterns intrinsic to the data due to their self-attention mechanism. This paper compares three variants of LSTM and two variants of Transformer models for learning fall patterns. We trained all models using fall and activity data from three datasets, and the real-time testing of the model was performed using the SmartFall App. Our findings showed that in the offline training, the CNN-LSTM model was better than the Transformer model for all the datasets. However, the Transformer is a preferable choice for deployment in real-time fall detection applications.<\/jats:p>","DOI":"10.3390\/s24196235","type":"journal-article","created":{"date-parts":[[2024,9,26]],"date-time":"2024-09-26T09:46:20Z","timestamp":1727343980000},"page":"6235","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["Experimental Study of Long Short-Term Memory and Transformer Models for Fall Detection on Smartwatches"],"prefix":"10.3390","volume":"24","author":[{"given":"Syed Tousiful","family":"Haque","sequence":"first","affiliation":[{"name":"Department of Computer Science, Texas State University, San Marcos, TX 78666, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2777-2437","authenticated-orcid":false,"given":"Minakshi","family":"Debnath","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Texas State University, San Marcos, TX 78666, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0599-6568","authenticated-orcid":false,"given":"Awatif","family":"Yasmin","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Texas State University, San Marcos, TX 78666, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1238-9397","authenticated-orcid":false,"given":"Tarek","family":"Mahmud","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Texas State University, San Marcos, TX 78666, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anne Hee Hiong","family":"Ngu","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Texas State University, San Marcos, TX 78666, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2024,9,26]]},"reference":[{"key":"ref_1","unstructured":"(2023, June 13). Falls. World Health Organization. Available online: www.who.int\/news-room\/fact-sheets\/detail\/falls."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Tacconi, C., Mellone, S., and Chiari, L. (2011, January 23\u201326). Smartphone-based applications for investigating falls and mobility. Proceedings of the 2011 5th International Conference on Pervasive Computing Technologies for Healthcare (PervasiveHealth) and Workshops, Dublin, Ireland.","DOI":"10.4108\/icst.pervasivehealth.2011.246060"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1016\/j.measurement.2019.03.079","article-title":"Intelligent fall detection method based on accelerometer data from a wrist-worn smart watch","volume":"140","author":"Chen","year":"2019","journal-title":"Measurement"},{"key":"ref_4","unstructured":"(2023, June 13). Medical Life Alert Systems. Available online: http:\/\/www.lifealert.com."},{"key":"ref_5","unstructured":"(2019, November 18). Mobilehelp Smart. Available online: https:\/\/www.mobilehelp.com\/pages\/smart."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3428666","article-title":"Ensemble Deep Learning on Wearables Using Small Datasets","volume":"2","author":"Mauldin","year":"2021","journal-title":"ACM Trans. Comput. Healthc."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Mauldin, T.R., Canby, M.E., Metsis, V., Ngu, A.H., and Rivera, C.C. (2018). SmartFall: A Smartwatch-Based Fall Detection System Using Deep Learning. Sensors, 18.","DOI":"10.3390\/s18103363"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"2250048","DOI":"10.1142\/S0129065722500484","article-title":"Personalized Watch-Based Fall Detection Using a Collaborative Edge-Cloud Framework","volume":"32","author":"Ngu","year":"2022","journal-title":"Int. J. Neural Syst."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Guan, Y., and Pl\u00f6tz, T. (2017). Ensembles of Deep LSTM Learners for Activity Recognition Using Wearables. Proc. ACM Interact. Mob. Wearable Ubiquitous Technol., 1.","DOI":"10.1145\/3090076"},{"key":"ref_10","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., and Polosukhin, I. (2017, January 4\u20139). Attention is all you need. Proceedings of the NIPS, Long Beach, CA, USA."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Nahian, M.J.A., Raju, M.H., Tasnim, Z., Mahmud, M., Ahad, M.A.R., and Kaiser, M.S. (2021). Contactless fall detection for the elderly. Contactless Human Activity Analysis, Springer.","DOI":"10.1007\/978-3-030-68590-4_8"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"7181","DOI":"10.3390\/s140407181","article-title":"Smartphone-based solutions for fall detection and prevention: Challenges and open issues","volume":"14","author":"Habib","year":"2014","journal-title":"Sensors"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Liu, S.H., and Cheng, W.C. (2012). Fall Detection with the Support Vector Machine during Scripted and Continuous Unscripted Activities. Sensors, 12.","DOI":"10.3390\/s120912301"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Theodoridis, T., Solachidis, V., Vretos, N., and Daras, P. (2018). Human fall detection from acceleration measurements using a Recurrent Neural Network. Precision Medicine Powered by pHealth and Connected Health, Springer.","DOI":"10.1007\/978-981-10-7419-6_25"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"489","DOI":"10.1016\/j.cmpb.2014.09.005","article-title":"Human fall detection on embedded platform using depth maps and wireless accelerometer","volume":"117","author":"Kwolek","year":"2014","journal-title":"Comput. Methods Programs Biomed."},{"key":"ref_16","unstructured":"Musci, M., De Martini, D., Blago, N., Facchinetti, T., and Piastra, M. (2018). Online Fall Detection using Recurrent Neural Networks. arXiv."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Sucerquia, A., L\u00f3pez, J.D., and Vargas-Bonilla, J.F. (2017). SisFall: A fall and movement dataset. Sensors, 17.","DOI":"10.3390\/s17010198"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Khojasteh, S.B., Villar, J.R., Chira, C., Gonz\u00e1lez, V.M., and de la Cal, E. (2018). Improving Fall Detection Using an On-Wrist Wearable Accelerometer. Sensors, 18.","DOI":"10.3390\/s18051350"},{"key":"ref_19","unstructured":"(2019, April 18). Fall Data Collected Using Microsoft Band Smartwatch. Available online: http:\/\/www.cs.txstate.edu\/~hn12\/data\/SmartFallDataSet."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Yu, X., Qiu, H., and Xiong, S. (2020). A Novel Hybrid Deep Neural Network to Predict Pre-impact Fall for Older People Based on Wearable Inertial Sensors. Front. Bioeng. Biotechnol., 8.","DOI":"10.3389\/fbioe.2020.00063"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Ord\u00f3\u00f1ez, F.J., and Roggen, D. (2016). Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition. Sensors, 16.","DOI":"10.3390\/s16010115"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Mohammed Sharook, K., Premkumar, A., Aishwaryaa, R., Amrutha, J.M., and Deepthi, L.R. (2022). Fall Detection Using Transformer Model. ICT Infrastructure and Computing: Proceedings of ICT4SD 2022, Springer Nature.","DOI":"10.1007\/978-981-19-5331-6_4"},{"key":"ref_23","unstructured":"(2023, August 14). Fall Detection Using a Transformer. Available online: https:\/\/www.edgeimpulse.com\/blog\/save-yourself-a-trip-fall-detect-using-a-transformer-model."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Wang, S., and Wu, J. (2023). Patch-Transformer Network: A Wearable-Sensor-Based Fall Detection Method. Sensors, 23.","DOI":"10.3390\/s23146360"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Katrompas, A., Ntakouris, T., and Metsis, V. (2022, January 14\u201317). Recurrence and self-attention vs the transformer for time-series classification: A comparative study. Proceedings of the International Conference on Artificial Intelligence in Medicine, Halifax, NS, Canada.","DOI":"10.1007\/978-3-031-09342-5_10"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"178","DOI":"10.1519\/JPT.0b013e3182abe779","article-title":"Fall Detection Devices and their use with Older Adults: A Systematic Review","volume":"37","author":"Chaudhuri","year":"2014","journal-title":"J. Geriatr. Phys. Ther."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Gulati, A., Qin, J., Chiu, C.C., Parmar, N., Zhang, Y., Yu, J., Han, W., Wang, S., Zhang, Z., and Wu, Y. (2020). Conformer: Convolution-augmented Transformer for Speech Recognition. arXiv.","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Maray, N., Ngu, A.H., Ni, J., Debnath, M., and Wang, L. (2023). Transfer Learning on Small Datasets for Improved Fall Detection. Sensors, 23.","DOI":"10.3390\/s23031105"},{"key":"ref_29","unstructured":"Lu, Y., Li, Z., He, D., Sun, Z., Dong, B., Qin, T., Wang, L., and Liu, T.Y. (2019). Understanding and improving transformer from a multi-particle dynamic system point of view. arXiv."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Micucci, D., Mobilio, M., and Napoletano, P. (2017). UniMiB SHAR: A Dataset for Human Activity Recognition Using Acceleration Data from Smartphones. Appl. Sci., 7.","DOI":"10.20944\/preprints201706.0033.v1"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Yu, X., Jang, J., and Xiong, S. (2021). A large-scale open motion dataset (KFall) and benchmark algorithms for detecting pre-impact fall of the elderly using wearable inertial sensors. Front. Aging Neurosci., 13.","DOI":"10.3389\/fnagi.2021.692865"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Yasmin, A., Mahmud, T., Debnath, M., and Ngu, A. (2024, January 2\u20134). An Empirical Study on AI-Powered Edge Computing Architectures for Real-Time IoT Applications. Proceedings of the IEEE Computers, Software, and Applications Conference (COMPSAC 2024), Osaka, Japan.","DOI":"10.1109\/COMPSAC61105.2024.00187"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"e30121","DOI":"10.2196\/30121","article-title":"Effectiveness of a Smartwatch App in Detecting Induced Falls: Observational Study","volume":"6","author":"Brew","year":"2022","journal-title":"JMIR Form Res."},{"key":"ref_34","unstructured":"(2023, June 13). Databrary\u2014Videos of Falls in Long Term Care. Available online: https:\/\/www.sfu.ca\/ipml\/research\/data-sharing.html."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/19\/6235\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T16:04:06Z","timestamp":1760112246000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/19\/6235"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,26]]},"references-count":34,"journal-issue":{"issue":"19","published-online":{"date-parts":[[2024,10]]}},"alternative-id":["s24196235"],"URL":"https:\/\/doi.org\/10.3390\/s24196235","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9,26]]}}}