Skeleton-Based Fall Detection with Multiple Inertial Sensors Using Spatial-Temporal Graph Convolutional Networks
Open accessAbstract
The application of wearable devices for fall detection has been the focus of much research over the past few years. One of the most common problems in established fall detection systems is the large number of false positives in the recognition schemes. In this paper, to make full use of the dependence between human joints and improve the accuracy and reliability of fall detection, a fall-recognition method based on the skeleton and spatial-temporal graph convolutional networks (ST-GCN) was proposed, using the human motion data of body joints acquired by inertial measurement units (IMUs). Firstly, the motion data of five inertial sensors were extracted from the UP-Fall dataset and a human skeleton model for fall detection was established through the natural connection relationship of body joints; after that, the ST-GCN-based fall-detection model was established to extract the motion features of human falls and the activities of daily living (ADLs) at the spatial and temporal scales for fall detection; then, the influence of two hyperparameters and window size on the algorithm performance was discussed; finally, the recognition results of ST-GCN were also compared with those of MLP, CNN, RNN, LSTM, TCN, TST, and MiniRocket. The experimental results showed that the ST-GCN fall-detection model outperformed the other seven algorithms in terms of accuracy, precision, recall, and F1-score. This study provides a new method for IMU-based fall detection, which has the reference significance for improving the accuracy and robustness of fall detection.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
ST-GCN exploits the natural topology of the skeleton, learning spatial dependencies and temporal dynamics simultaneously, a method that has shown state-of-the-art performance in recent skeleton-based fall detection benchmarks.
“This architecture exploits the natural topology of the skeleton extracted by MMPose, learning spatial dependencies (e.g., knee-hip coordination) and temporal dynamics simultaneously, a method that has shown state-of-the-art performance in recent skeleton-based fall detection benchmarks [19].”
From Safe Fall: Use of Predictive Modeling and Machine Vision Techniques for Fall Analysis and Fall Quality (2026) · cites this paper as [19]
Methods §3.2 says ST-GCN models natural connections between joints and extracts spatial and temporal features. Discussion §5.3 reports superior fall-detection performance on the UP-Fall dataset, but the paper uses inertial sensors, not MMPose-extracted skeletons, and does not establish state-of-the-art performance across multiple recent benchmarks. (LLM, conf=0.86)
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Graph neural networks: A review of methods and applications
Zhou, J., Cui, G., Hu, S., Zhang, Z., Yang, C., Liu, Z., Wang, L., Li, C., & Sun, M. (2020) · AI Open · doi:10.1016/j.aiopen.2021.01.001 · Cited by 6,880 · see citing works
Self-citationSpatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition
Yan, S., Xiong, Y., & Lin, D. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.12328 · Cited by 5,410 · cited 3× · see citing works
“To evaluate the performance of the skeleton-based ST-GCN classification model for fall detection, the UP-Fall dataset containing multiple inertial sensors data was used as the experimental dataset.”
InfluentialSpectral Networks and Locally Connected Networks on Graphs
Bruna, J., Zaremba, W., Szlam, A., & LeCun, Y. (2013) · arXiv · doi:10.48550/arxiv.1312.6203 · Cited by 3,983 · see citing works
A Transformer-based Framework for Multivariate Time Series Representation Learning
Zerveas, G., Jayaraman, S., Patel, D., Bhamidipaty, A., & Eickhoff, C. (2021) · Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining · doi:10.1145/3447548.3467401 · Cited by 1,278 · see citing works
Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action RecognitionPreprint
Yan, S., Xiong, Y., & Lin, D. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1801.07455 · Cited by 599 · see citing works
Dempster, A., Schmidt, D. F., & Webb, G. I. (2021) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3447548.3467231 · Cited by 526 · see citing works
UP-Fall Detection Dataset: A Multimodal Approach
Martínez-Villaseñor, L., Ponce-Espinosa, H., Brieva, J., Moya-Albor, E., Núñez-Martínez, J., & Penafort-Asturiano, C. J. (2019) · Sensors · doi:10.3390/s19091988 · Cited by 404 · see citing works
Home Camera-Based Fall Detection System for the Elderly
Miguel, K. D., Brunete, A., Hernando, M., & Gambao, E. (2017) · Sensors · doi:10.3390/s17122864 · Cited by 273 · see citing works
Development of a Wearable-Sensor-Based Fall Detection System
Wu, F., Zhao, H., Zhao, Y., & Zhong, H. (2015) · International Journal of Telemedicine and Applications · doi:10.1155/2015/576364 · Cited by 235 · see citing works
Mrozek, D., Koczur, A., & Mrozek, D. (2020) · Information Sciences · doi:10.1016/j.ins.2020.05.070 · Cited by 146 · see citing works
A multimodal approach using deep learning for fall detection
Galvão, Y. M., Ferreira, J., Albuquerque, V. A., Barros, P. V. A., & Fernandes, B. (2020) · Expert Systems with Applications · doi:10.1016/j.eswa.2020.114226 · Cited by 109 · see citing works
A Footwear-Based Methodology for Fall Detection
Montanini, L., Campo, A. D., Perla, D., Spinsante, S., & Gambi, E. (2017) · IEEE Sensors Journal · doi:10.1109/jsen.2017.2778742 · Cited by 85 · see citing works
Alarifi, A., & Alwadain, A. S. (2020) · Measurement · doi:10.1016/j.measurement.2020.108258 · Cited by 84 · see citing works
Novel Hierarchical Fall Detection Algorithm Using a Multiphase Fall Model
Hsieh, C.-Y., Liu, K.-C., Huang, C.-N., Chu, W., & Chan, C.-T. (2017) · Sensors · doi:10.3390/s17020307 · Cited by 71 · see citing works
A cross-dataset deep learning-based classifier for people fall detection and identification
Delgado-Escaño, R., Castro, F. M., Cózar, J. R., Marín-Jiménez, M. J., Guil, N., & Casilari, E. (2019) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2019.105265 · Cited by 57 · see citing works
Fall Detection and Personnel Tracking System Using Infrared Array Sensors
Liu, Z., Yang, M., Yuan, Y., & Chan, K. Y. (2020) · IEEE Sensors Journal · doi:10.1109/jsen.2020.2988070 · Cited by 56 · see citing works
Hashim, H. A., Mohammed, S. L., & Gharghan, S. K. (2020) · Measurement · doi:10.1016/j.measurement.2020.107573 · Cited by 51 · see citing works
Towards effective detection of elderly falls with CNN-LSTM neural networks
González, E. G., Villar, M. A., Fáñez, M., Villar, J. R., de la Cal, E., & Cho, S. (2022) · Neurocomputing · doi:10.1016/j.neucom.2021.06.102 · Cited by 50 · see citing works
An Image-Based Fall Detection System for the Elderly
Lu, K.-L., & Chu, E. T.-H. (2018) · Applied Sciences · doi:10.3390/app8101995 · Cited by 49 · see citing works
Li, Y., Zuo, Z., & Pan, J. (2022) · Future Generation Computer Systems · doi:10.1016/j.future.2022.09.011 · Cited by 48 · see citing works
Embedding Recurrent Neural Networks in Wearable Systems for Real-Time Fall Detection
Torti, E., Fontanella, A., Musci, M., Blago, N., Pau, D. P., Leporati, F., & Piastra, M. (2019) · Microprocessors and Microsystems · doi:10.1016/j.micpro.2019.102895 · Cited by 47 · see citing works
Nho, Y., Ryu, S., & Kwon, D. (2021) · IEEE Sensors Journal · doi:10.1109/jsen.2021.3054394 · Cited by 47 · see citing works
A Low-Power Fall Detector Balancing Sensitivity and False Alarm Rate
Wang, C., Lü, W., Redmond, S. J., Stevens, M. C., Lord, S. R., & Lovell, N. H. (2017) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2017.2778271 · Cited by 43 · see citing works
Yousuf, S., & Jilani, M. T. (2021) · Journal of Ambient Intelligence and Humanized Computing · doi:10.1007/s12652-021-03279-6 · Cited by 39 · see citing works
Wang, G., Li, Q., Wang, L., Zhang, Y., & Liu, Z. (2020) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2020.3000338 · Cited by 33 · see citing works
Smart walking assistant (SWA) for elderly care using an intelligent realtime hybrid model
Bhattacharjee, P., & Biswas, S. (2021) · Evolving Systems · doi:10.1007/s12530-021-09382-5 · Cited by 26 · see citing works
An IoT-based framework for remote fall monitoring
Al‐Kababji, A., Amira, A., Bensaali, F., Jarouf, A., Shidqi, L., & Djelouat, H. (2021) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2021.102532 · Cited by 21 · see citing works
Falling motion detection algorithm based on deep learning
Zhu, N., Zhao, G., Zhang, X., & Jin, Z. (2021) · IET Image Processing · doi:10.1049/ipr2.12208 · Cited by 20 · see citing works
A low-power fall detection method based on optimized TBM and RNN
Xu, T., & Liu, J. (2022) · Digital Signal Processing · doi:10.1016/j.dsp.2022.103525 · Cited by 8 · see citing works
Fall Detection in Elderly Care System Based on Group of Pictures
Sowmyayani, S., Murugan, V., & Kavitha, J. (2020) · Vietnam Journal of Computer Science · doi:10.1142/s2196888821500081 · Cited by 7 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Gharghan, S. K., & Hashim, H. A. (2024) · Measurement · doi:10.1016/j.measurement.2024.114186 · Cited by 64 · see citing works
Transformer-based fall detection in videos
Núñez-Marcos, A., & Arganda‐Carreras, I. (2024) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2024.107937 · Cited by 55 · see citing works
Deep Learning for Abnormal Human Behavior Detection in Surveillance Videos—A Survey
Wastupranata, L. M., Kong, S. G., & Wang, L. (2024) · Electronics · doi:10.3390/electronics13132579 · Cited by 49 · see citing works
Tang, J., He, B., Xu, J., Tan, T., Wang, Z., Zhou, Y., & Jiang, S. (2024) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2024.3370396 · Cited by 32 · see citing works
Rehman, S. U., Yasin, A. U., Haq, E. U., Ali, M., Kim, J., & Mehmood, A. (2024) · Sensors · doi:10.3390/s24144646 · Cited by 27 · see citing works
Vuong, T. H., Doan, T., & Takasu, A. (2023) · Sensors · doi:10.3390/s23249721 · Cited by 26 · see citing works
MSMFT: Multi-Stream Multimodal Factorized Transformer for Human Activity Recognition
Zhou, X., Yuan, J., Fan, L., Niu, X., Zha, K., & Liu, X. (2025) · IEEE Sensors Journal · doi:10.1109/jsen.2025.3529889 · Cited by 15 · see citing works
Band, S. S., Biyari, M., Hsu, C.-C., Ruga, T., Zumpano, E., Caroprese, L., Vocaturo, E., Dehzangi, A., Rawal, B. S., & Liang, H. (2025) · Cognitive Computation · doi:10.1007/s12559-025-10532-z · Cited by 10 · see citing works
Reduction of Vision-Based Models for Fall Detection
Garmendia-Orbegozo, A., Anton, M. A., & Núñez-González, J. D. (2024) · Sensors · doi:10.3390/s24227256 · Cited by 9 · see citing works
An AI-Based Approach for Accurate Fall Detection and Prediction Using Wearable Sensors
Sarwar, M. A., Chea, B., Widjaja, M., & Saadeh, W. (2024) · IEEE International Midwest Symposium on Circuits and Systems (MWSCAS) · doi:10.1109/mwscas60917.2024.10658849 · Cited by 8 · see citing works
Sepahvand, M., Meqdad, M. N., & Abdali-Mohammadi, F. (2024) · International Journal of Computers and Applications · doi:10.1080/1206212x.2024.2426501 · Cited by 7 · see citing works
Multi-Target Pose Estimation and Behavior Analysis Based on Symmetric Cascaded AdderNet
Jia, X., Xu, Q., Zhu, A., & Kuang, X. (2025) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2025.3557614 · Cited by 7 · see citing works
Nawaz, A., Ali, N. A., & Ahmad, A. (2025) · Applied Soft Computing · doi:10.1016/j.asoc.2025.113931 · Cited by 6 · see citing works
Research of Fall Detection and Fall Prevention Technologies: A Review
Hrubý, D., Hrubá, E., & Černý, M. (2026) · Sensors · doi:10.3390/s26041192 · Cited by 5 · see citing works
Guendoul, O., Abdelali, H. A., Tabii, Y., Thami, R. O. H., & Bourja, O. (2024) · IEEE Access · doi:10.1109/access.2024.3486077 · Cited by 5 · see citing works
Cao, X., Li, C., & Zhai, H. (2025) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2025.061823 · Cited by 5 · see citing works
Houssein, E. H., Ibrahim, I. A., Mahdy, M. A., Kayed, M., Albarrak, A. M., & Mohamed, W. M. (2025) · Journal Of Big Data · doi:10.1186/s40537-025-01293-5 · Cited by 3 · see citing works
Guendoul, O., Zobi, M., Abdelali, H. A., Tabii, Y., Thami, R. O. H., & Bourja, O. (2025) · Applied Intelligence · doi:10.1007/s10489-025-06316-5 · Cited by 2 · see citing works
DelCastillo-Andrés, O., Fernández-García, R., Pastor-Vicedo, J. C., Lira, M. A., Campos-Mesa, M. C., Castañeda-Vázquez, C., Genovesi, E., Krstulović, S., Kuvačić, G., Morvay-Sey, K., et al. (2026) · Sensors · doi:10.3390/s26082491 · Cited by 1 · see citing works
“This architecture exploits the natural topology of the skeleton extracted by MMPose, learning spatial dependencies (e.g., knee-hip coordination) and temporal dynamics simultaneously, a method that has shown state-of-the-art performance in recent skeleton-based fall detection benchmarks [19].”
Dong, L., Xu, X., He, G., Xu, Y., Rasol, J., Tao, C., & Zhang, Z. (2025) · Alexandria Engineering Journal · doi:10.1016/j.aej.2025.04.019 · Cited by 1 · see citing works
A Review on Sensor-based HAR Models Using GNN: AI in Healthcare
Dangol, N., & Mahfuz, S. (2025) · Procedia Computer Science · doi:10.1016/j.procs.2025.10.217 · Cited by 1 · see citing works
Wastupranata, L. M. (2024) · doi:10.36227/techrxiv.170473723.30823862/v1
Dual-branch fall detection algorithm based on multi-scale temporal difference
Cai, X., Chen, Y., Fan, M., & Han, G. (2025) · Signal Image and Video Processing · doi:10.1007/s11760-025-04863-5
Triviño, J. M., Lassó, A., Paredes, C. M., & Peñeñory, V. M. (2025) · Research Square · doi:10.21203/rs.3.rs-8273858/v1
lu, Y., cui, Y., Lu, Y., Lu, X., Zhang, X., & Zhang, X. (2025) · Sensors · doi:10.3390/s25237394
Shen, J., Zhang, Y., Li, X., Zhou, M., Wang, W., & Zhang, D. (2026) · IET Image Processing · doi:10.1049/ipr2.70262
Ibe, B. C., Orifama, D. G., Erics, G., Ali, D. I., Enumah, I. N., & Ogbuagu, D. C. (2026) · Artificial Intelligence and Applications · doi:10.47852/bonviewaia62028461
Edge-Deployable Multimodal Fall Detection with INT8 Quantization on Rockchip RK3568Preprint
Zhang, T., Xiong, L., Zhou, H., Feng, Y., He, Z., & Zhang, X. (2026) · Research Square · doi:10.21203/rs.3.rs-9395963/v1
Fall Detection for the Elderly in Low-Light Environments Based on Improved YOLO11-Pose
Wang, L. (2026) · International Conference on Image, Signal Processing and Pattern Recognition (ISPP) · doi:10.1109/ispp69262.2026.11543093
FLASH: Efficient Impact Fall Detection with Unified Hypergraph State-Space Model
Koffi, T. Y., Mourchid, Y., & Dupuis, Y. (2026) · Proceedings - International Conference on Image Processing · doi:10.1109/icip61757.2026.11630266
- Authors
- Yan, J., Wang, X., Shi, J., & Hu, S.
- Affiliations
- East China University of Science and Technology (CN)
- Corresponding author
- Yan, Jianjun
- Venue
- Sensors
- Publisher
- MDPI AG
- Published
- 2023-02-14
- Volume
- 23
- Issue
- 4
- Pages
- 2153
- ISSN
- 1424-8220 (ISSN-L)
- PMC
- PMC9962182
- OpenAlex
- W4320920821
- Cited by
- 28
- References
- 28
- Citations by year
- 2026: 5 · 2025: 12 · 2024: 10 · 2023: 1
- FWCI
- 2.53
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Sensors (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- National Natural Science Foundation of China (91748110)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
- Health Sciences › Health Professions › Physical Therapy, Sports Therapy and Rehabilitation › Balance, Gait, and Falls Prevention
- Physical Sciences › Engineering › Biomedical Engineering › Gait Recognition and Analysis
- Keywords
- fall detection, inertial measurement unit, spatio-temporal graph convolutional network, wearable sensors, activities of daily living, false positive reduction
- MeSH terms
- Accidental Falls, Activities of Daily Living, Humans, Musculoskeletal System, Skeleton, Reproducibility of Results
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
