{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T22:39:53Z","timestamp":1773268793782,"version":"3.50.1"},"reference-count":45,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T00:00:00Z","timestamp":1773187200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:p>According to data provided by the World Health Organization (WHO), falls are one of the major reasons for unintentional deaths or injuries in older adults. Although many fall detection methods and algorithms exist, there is no efficient artificial intelligence strategy for fall detection. Various studies have stated that Fall Detection among Elderly Persons (FDEP) provides the possibility of developing an efficient and cost-effective way to tackle this problem. This study generated a signal-based image dataset, SimgFall, from the existing accelerometer or gyroscope-based sensor data of the SiSFall dataset for the early detection of falls to accelerate the medical assistance process. The SimgFall dataset was used to train and evaluate the FallCNN model, a novel deep Convolutional Neural Network (CNN) architecture comprising multiple CNN folds to effectively learn discriminative features from the transformed signal representations. These models utilize depth-wise convolution with varying dilation rates to efficiently extract diversified features from the SimgFall dataset. The dataset contained 1992 signal-based images, of which 498 were samples collected for fall, jump, stumble, and walk for the 4 classes. The initial architecture, referred to as FallCNN_1, with two basic convolutional layers and max-pooling, which is simple and efficient in feature extraction and dimensionality reduction, resulted in 94% accuracy for detecting the 4 classes. The incorporation of the average pooling and dropout layers in FallCNN_2 reduced overfitting and improved feature extraction, thereby enhancing the accuracy to 95%. Expanding the feature dimensions in FallCNN_3 further refined the capacity of the model to capture intricate patterns, achieving a notable accuracy of 97%. Finally, FallCNN_4 with three convolutional blocks and additional intermediate layers achieved the highest accuracy of 98%, demonstrating cumulative performance improvements through architectural enhancements. Furthermore, the performance of the generated dataset using different pretrained and custom models was evaluated based on the loss and accuracy curves. The experimental results showed that the highest classification accuracy was 98%, with a loss of 0.0833, using categorical cross-entropy as the loss function.<\/jats:p>","DOI":"10.3389\/frai.2026.1734096","type":"journal-article","created":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T06:52:21Z","timestamp":1773211941000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Fall detection among elderly persons using FallCNN and transfer learning models"],"prefix":"10.3389","volume":"9","author":[{"given":"K.","family":"Jishnuraj","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Vellore Institute of Technology","place":["Chennai, India"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"M.","family":"Vergin Raja Sarobin","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Vellore Institute of Technology","place":["Chennai, India"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jani","family":"Anbarasi","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Vellore Institute of Technology","place":["Chennai, India"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Graceline","family":"Jasmine","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Vellore Institute of Technology","place":["Chennai, India"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rukmani","family":"Panjanathan","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Vellore Institute of Technology","place":["Chennai, India"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2026,3,11]]},"reference":[{"key":"ref1","first-page":"81","article-title":"Activity recognition for indoor fall detection using convolutional neural network","author":"Adhikari","year":"2017"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"6916","DOI":"10.3390\/app13126916","article-title":"A robust and automated vision-based human fall detection system using 3D multi-stream CNNs with an image fusion technique","volume":"13","author":"Alanazi","year":"2023","journal-title":"Appl. Sci."},{"key":"ref3","doi-asserted-by":"publisher","first-page":"3060","DOI":"10.3390\/diagnostics12123060","article-title":"Human fall detection using 3D multi-stream convolutional neural networks with fusion","volume":"12","author":"Alanazi","year":"2022","journal-title":"Diagnostics"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"108942","DOI":"10.1016\/j.bspc.2025.108942","article-title":"A lightweight and efficient deep learning model for real-time fall detection on edge device","volume":"113","author":"Bach","year":"2026","journal-title":"Biomed. Signal Proces. Control"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"23799","DOI":"10.1007\/s11042-023-16476-6","article-title":"Design of inception with deep convolutional neural network based fall detection and classification model","volume":"83","author":"Durga Bhavani","year":"2024","journal-title":"Multimed. Tools Appl."},{"key":"ref6","doi-asserted-by":"publisher","first-page":"103520","DOI":"10.1016\/j.compbiomed.2019.103520","article-title":"A vision-based approach for fall detection using multiple cameras and convolutional neural networks: a case study using the UP-fall detection dataset","volume":"115","author":"Espinosa","year":"2019","journal-title":"Comput. Biol. Med."},{"key":"ref7","doi-asserted-by":"publisher","first-page":"114226","DOI":"10.1016\/j.eswa.2020.114226","article-title":"A multimodal approach using deep learning for fall detection","volume":"168","author":"Galv\u00e3o","year":"2021","journal-title":"Expert Syst. Appl."},{"key":"ref8","doi-asserted-by":"publisher","first-page":"8831","DOI":"10.1109\/TITS.2022.3219474","article-title":"CAMRL: a joint method of channel attention and multidimensional regression loss for 3D object detection in automated vehicles","volume":"24","author":"Gao","year":"","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref9","doi-asserted-by":"publisher","first-page":"2978","DOI":"10.1109\/TNSE.2022.3163144","article-title":"TSMAE: a novel anomaly detection approach for internet of things time series data using memory-augmented autoencoder","volume":"10","author":"Gao","year":"","journal-title":"IEEE Trans Netw Sci Eng"},{"key":"ref10","doi-asserted-by":"crossref","DOI":"10.1109\/TVT.2024.3372940","article-title":"CFPC: the curbed fake point collector to Pseudo-LiDAR-based 3D object detection for autonomous vehicles","author":"Gao","year":"2025"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"3475","DOI":"10.1109\/TCE.2024.3353530","article-title":"MonoLI: precise monocular 3-D object detection for next-generation consumer electronics for autonomous electric vehicles","volume":"70","author":"Gao","year":"2024","journal-title":"IEEE Trans. Consum. Electron."},{"key":"ref12","first-page":"47","article-title":"Accelerometer placement for posture recognition and fall detection","author":"Gjoreski","year":"2011"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"18091","DOI":"10.1007\/s11042-023-16214-y","article-title":"Fall detection using mixtures of convolutional neural networks","volume":"83","author":"Ha","year":"2024","journal-title":"Multimed. Tools Appl."},{"key":"ref14","doi-asserted-by":"publisher","first-page":"320","DOI":"10.1016\/j.bspc.2018.03.005","article-title":"Prospective elderly fall prediction by older-adult fall-risk modeling with feature selection","volume":"43","author":"Howcroft","year":"2018","journal-title":"Biomed. Signal Process. Control"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/1475-925X-12-66","article-title":"Challenges, issues and trends in fall detection systems","volume":"12","author":"Igual","year":"2013","journal-title":"Biomed. Eng. Online"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"5763","DOI":"10.1007\/s13369-024-09478-5","article-title":"Enhancing elderly care with wearable technology: development of a dataset for fall detection and ADL classification during Muslim prayer activities","volume":"50","author":"Jarrah","year":"2025","journal-title":"Arab. J. Sci. Eng."},{"key":"ref17","doi-asserted-by":"crossref","DOI":"10.1109\/AIIoT58432.2024.10574542","article-title":"Computer vision based algorithms for detecting and classification of activities for fall recognition on real time video","author":"Kandukuru","year":"2024"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1109\/JBHI.2014.2328593","article-title":"A smart phone-based pocket fall accident detection, positioning, and rescue system","volume":"19","author":"Kau","year":"2015","journal-title":"IEEE J. Biomed. Health Informat."},{"key":"ref19","doi-asserted-by":"publisher","first-page":"106216","DOI":"10.1016\/j.autcon.2025.106216","article-title":"Robust skeleton-based AI for automatic multi-person fall detection on construction sites with occlusions","volume":"175","author":"Kim","year":"2025","journal-title":"Autom. Constr."},{"key":"ref20","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"ref21","first-page":"1","article-title":"Grammar-based, posture- and context-cognitive detection for falls with different activity levels","author":"Li","year":"2011"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"569","DOI":"10.1016\/j.cger.2010.06.002","article-title":"Vision and falls in older people: risk factors and intervention strategies","volume":"26","author":"Lord","year":"2010","journal-title":"Clin. Geriatric Med."},{"key":"ref23","doi-asserted-by":"publisher","first-page":"314","DOI":"10.1109\/JBHI.2018.2808281","article-title":"Deep learning for fall detection: three-dimensional CNN combined with LSTM on video kinematic data","volume":"23","author":"Lu","year":"2018","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref24","doi-asserted-by":"publisher","first-page":"e94811","DOI":"10.1371\/journal.pone.0094811","article-title":"Detecting falls as novelties in acceleration patterns acquired with smartphones","volume":"9","author":"Medrano","year":"2014","journal-title":"PLoS One"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"573","DOI":"10.1109\/TNSRE.2017.2771383","article-title":"Wearable inertial sensors for fall risk assessment and prediction in older adults: a systematic review and meta-analysis","volume":"26","author":"Montesinos","year":"2018","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref26","doi-asserted-by":"publisher","first-page":"144","DOI":"10.1016\/j.neucom.2011.09.037","article-title":"A survey on fall detection: principles and approaches","volume":"100","author":"Mubashir","year":"2013","journal-title":"Neurocomputing"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"9474806","DOI":"10.1155\/2017\/9474806","article-title":"Vision-based fall detection with convolutional neural networks","author":"Nunez-Marcos","year":"2017","journal-title":"Wirel. Commun. Mob. Comput."},{"key":"ref28","doi-asserted-by":"publisher","first-page":"6479","DOI":"10.3390\/s20226479","article-title":"Accelerometer-based fall detection using machine learning: training and testing on real-world falls","volume":"20","author":"Palmerini","year":"2020","journal-title":"Sensors"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"12900","DOI":"10.3390\/s140712900","article-title":"Automatic fall monitoring: a review","volume":"14","author":"Pannurat","year":"2014","journal-title":"Sensors"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"e70321","DOI":"10.1002\/ett.70321","article-title":"Human fall detection in SAGIN environment using ultrasonic sensors and hybrid deep learning","volume":"37","author":"Patel","year":"2026","journal-title":"Trans. Emerg. Telecommun. Technol."},{"key":"ref31","doi-asserted-by":"crossref","first-page":"1475","DOI":"10.1109\/TITB.2010.2051956","article-title":"Detection of falls among the elderly by a floor sensor using the electric near field","volume":"14","author":"Rimminen","year":"2010","journal-title":"IEEE Trans. Inf. Technol. Biomed."},{"key":"ref32","doi-asserted-by":"publisher","first-page":"358","DOI":"10.1016\/j.procs.2018.10.189","article-title":"Fall detection system by machine learning framework for public health","volume":"141","author":"Rodrigues","year":"2018","journal-title":"Procedia Computer Sci."},{"key":"ref33","doi-asserted-by":"publisher","first-page":"6842","DOI":"10.1109\/TII.2021.3049342","article-title":"Contactless fall detection using time-frequency analysis and convolutional neural networks","volume":"17","author":"Sadreazami","year":"2021","journal-title":"IEEE Trans. Industr. Inform."},{"key":"ref34","doi-asserted-by":"publisher","first-page":"205","DOI":"10.1016\/j.asoc.2015.04.060","article-title":"A supervised approach to automatically extract a set of rules to support fall detection in an mHealth system","volume":"34","author":"Sannino","year":"2015","journal-title":"Appl. Soft Comput."},{"key":"ref35","doi-asserted-by":"publisher","first-page":"1644","DOI":"10.3390\/s19071644","article-title":"Accelerometer-based human fall detection using convolutional neural networks","volume":"19","author":"Santos","year":"2019","journal-title":"Sensors"},{"key":"ref36","first-page":"223","article-title":"Comparing machine learning approaches for fall risk assessment","author":"Silva","year":"2017"},{"key":"ref37","doi-asserted-by":"publisher","first-page":"290","DOI":"10.1109\/JBHI.2014.2312180","article-title":"Fall detection in homes of older adults using the Microsoft Kinect","volume":"19","author":"Stone","year":"2015","journal-title":"IEEE J. Biomed. Health Informat."},{"key":"ref38","doi-asserted-by":"publisher","first-page":"198","DOI":"10.3390\/s17010198","article-title":"SisFall: a fall and movement dataset","volume":"17","author":"Sucerquia","year":"2017","journal-title":"Sensors"},{"key":"ref39","doi-asserted-by":"crossref","first-page":"191","DOI":"10.1201\/9781003476047-11","article-title":"Preventive care: smart strategies for elderly fall detection and prevention","volume-title":"Deep learning and Blockchain Technology for Smart and Sustainable Cities","author":"Sumathi","year":"2025"},{"key":"ref40","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1080\/20476965.2024.2395574","article-title":"Next-generation fall detection: harnessing human pose estimation and transformer technology","volume":"14","author":"Sykes","year":"2025","journal-title":"Health Systems"},{"key":"ref41","first-page":"131","article-title":"Design of fall detection system with floor pressure and infrared image","author":"Tzeng","year":"2010"},{"key":"ref42","doi-asserted-by":"publisher","first-page":"44","DOI":"10.4018\/ijmstr.2014010103","article-title":"The MobiFall dataset: fall detection and classification with a smartphone","volume":"2","author":"Vavoulas","year":"2014","journal-title":"Int. J. Monit. Surveil. Technol. Res."},{"key":"ref43","volume-title":"WHO global report on falls prevention in older age","year":"2007"},{"key":"ref44","doi-asserted-by":"publisher","first-page":"403","DOI":"10.3390\/info12100403","article-title":"Fall detection with CNN-casual LSTM network","volume":"12","author":"Wu","year":"2021","journal-title":"Information"},{"key":"ref45","doi-asserted-by":"publisher","first-page":"102016","DOI":"10.1016\/j.pmcj.2025.102016","article-title":"A real-time skeleton-based fall detection algorithm based on temporal convolutional networks and transformer encoder","volume":"107","author":"Yu","year":"2025","journal-title":"Pervasive Mobile Comput."}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1734096\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T06:52:22Z","timestamp":1773211942000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1734096\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,11]]},"references-count":45,"alternative-id":["10.3389\/frai.2026.1734096"],"URL":"https:\/\/doi.org\/10.3389\/frai.2026.1734096","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,11]]},"article-number":"1734096"}}