A spatio-temporal graph neural network for fall prediction with inertial sensors
Abstract
Falls are the leading cause of unintentional human injury , having become a public health event of strong social concern. The fall prediction technology based on wearable inertial sensors is a relatively reliable solution in human activity monitoring, a user scenario with mobility and high information privacy sensitivity, and has the advantages of low cost, small size, and high precision. However, a key challenge in sensor-based fall prediction is the fact that a fall event can often occur in various configurations of fall poses together with their own spatio-temporal dependencies. This leads us to define a spatio-temporal model to explicitly characterize these internal configurations of poses. In particular, we introduce a graph neural network with spatio-temporal topological structure to encode such latent relations among poses by capturing representative patterns in fall events. Moreover, a human body orientation estimator is devised to represent human low limbs information and as a result, separate pose dependencies are globally consistent. Empirical evaluations on two benchmark datasets and one in-house dataset suggest our approach significantly outperforms the state-of-the-art methods.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
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?
GNN models sensor topological relationships via graph structures, provides explicit spatial correlation inference, and is used for whole-body motion intent network analysis.
“| GNN | Model sensor topological relationships via graph | Explicit spatial correlation inference | Whole-body motion intent network analysis 270-272 |”
From Recent advances in intelligent wearable systems: from multiscale biomechanical features towards human motion intent prediction (2026) · cites this paper as [271]
Cites
Neural Message Passing for Quantum ChemistryPreprint
Gilmer, J., Schoenholz, S. S., Riley, P. F., Vinyals, O., & Dahl, G. E. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1704.01212 · Cited by 5,414 · see citing works
Estimation of IMU and MARG orientation using a gradient descent algorithm
Madgwick, S., Harrison, A. J., & Vaidyanathan, R. (2011) · International Conference on Rehabilitation Robotics · doi:10.1109/icorr.2011.5975346 · Cited by 2,108 · see citing works
Ye, L., & Keogh, E. (2009) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/1557019.1557122 · Cited by 992 · see citing works
Moreland, B. L., Kakara, R. S., & Henry, A. (2020) · MMWR Morbidity and Mortality Weekly Report · doi:10.15585/mmwr.mm6927a5 · Cited by 650 · see citing works
SisFall: A Fall and Movement Dataset
Sucerquia, A., López, J., & Vargas-Bonilla, J. (2017) · Sensors · doi:10.3390/s17010198 · Cited by 530 · see citing works
Dynamic Multiscale Graph Neural Networks for 3D Skeleton Based Human Motion Prediction
Li, M., Chen, S.-H., Zhao, Y., Zhang, Y., Wang, Y.-F., & Tian, Q. (2020) · Computer Vision and Pattern Recognition · doi:10.1109/cvpr42600.2020.00029 · Cited by 382 · see citing works
The MobiAct Dataset: Recognition of Activities of Daily Living using Smartphones
Vavoulas, G., Chatzaki, C., Malliotakis, T., Pediaditis, M., & Tsiknakis, M. (2016) · ICT4AgeingWell · doi:10.5220/0005792401430151 · Cited by 316 · see citing works
Falls and Fall-Related Injuries among Community-Dwelling Adults in the United States
Verma, S. K., Willetts, J. L., Corns, H. L., Marucci‐Wellman, H., Lombardi, D. A., & Courtney, T. K. (2016) · PLoS ONE · doi:10.1371/journal.pone.0150939 · Cited by 305 · see citing works
Etiology and prevention of age-related hip fractures
Hayes, W. C., Myers, E. R., Robinovitch, S. N., van den Kroonenberg, A. J., Courtney, A., & McMahon, T. A. (1996) · Bone · doi:10.1016/8756-3282(95)00383-5 · Cited by 293 · see citing works
Bi-LSTM Network for Multimodal Continuous Human Activity Recognition and Fall Detection
Li, H., Shrestha, A., Heidari, H., Kernec, J. L., & Fioranelli, F. (2019) · IEEE Sensors Journal · doi:10.1109/jsen.2019.2946095 · Cited by 282 · see citing works
2011 IEEE International Conference on Rehabilitation Robotics
(2011) · doi:10.1109/icorr16527.2011 · Cited by 260 · see citing works
SmartFall: A Smartwatch-Based Fall Detection System Using Deep Learning
Mauldin, T. R., Canby, M. E., Metsis, V., Ngu, A., & Rivera, C. (2018) · Italian National Conference on Sensors · doi:10.3390/s18103363 · Cited by 236 · see citing works
1991 IEEE International Conference on Consumer Electronics
(1991) · doi:10.1109/icce.1991 · Cited by 212 · see citing works
Shimada, S., Golyanik, V., Xu, W., & Theobalt, C. (2020) · ACM Transactions on Graphics · doi:10.1145/3414685.3417877 · Cited by 179 · see citing works
Event Prediction in the Big Data Era: A Systematic Survey
Zhao, L. (2022) · ACM Computing Surveys · doi:10.1145/3450287 · Cited by 135 · see citing works
Yu, X., Jang, J., & Xiong, S. (2021) · Frontiers in Aging Neuroscience · doi:10.3389/fnagi.2021.692865 · Cited by 134 · see citing works
Jain, R., & Semwal, V. B. (2022) · IEEE Sensors Journal · doi:10.1109/jsen.2022.3213814 · Cited by 118 · see citing works
Karar, M. E., Shehata, H. I., & Reyad, O. (2022) · Applied Sciences · doi:10.3390/app12073276 · Cited by 94 · see citing works
Yu, X., Qiu, H., & Xiong, S. (2020) · Frontiers in Bioengineering and Biotechnology · doi:10.3389/fbioe.2020.00063 · Cited by 88 · see citing works
Time2Graph: Revisiting Time Series Modeling with Dynamic Shapelets
Cheng, Z., Yang, Y., Wang, W., Hu, W., Zhuang, Y., & Song, G. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i04.5769 · Cited by 76 · see citing works
Ashry, S., Ogawa, T., & Gomaa, W. E. (2020) · IEEE Sensors Journal · doi:10.1109/jsen.2020.2985374 · Cited by 69 · see citing works
Applying deep learning technology for automatic fall detection using mobile sensors
Wu, X., Zheng, Y., Chu, C., Cheng, L., & Kim, J. (2021) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2021.103355 · Cited by 60 · see citing works
A practical wearable fall detection system based on tiny convolutional neural networks
Yu, X., Park, S., Kim, D., Kim, E., Kim, J., Kim, W., An, Y., & Xiong, S. (2023) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2023.105325 · Cited by 58 · see citing works
On the analysis of background subtraction techniques using Gaussian Mixture Models
Bouttefroy, P. L. M., Bouzerdoum, A., Phung, S. L., & Beghdadi, A. (2010) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2010.5495760 · Cited by 53 · see citing works
A Hybrid Temporal Reasoning Framework for Fall Monitoring
Pannurat, N., Thiemjarus, S., & Nantajeewarawat, E. (2017) · IEEE Sensors Journal · doi:10.1109/jsen.2017.2649542 · Cited by 44 · see citing works
Enhanced Algorithm for the Detection of Preimpact Fall for Wearable Airbags
Jung, H., Koo, B., Kim, J., Kim, T., Nam, Y., & Kim, Y. (2020) · Sensors · doi:10.3390/s20051277 · Cited by 44 · see citing works
Pre-Impact Fall Detection with CNN-Based Class Activation Mapping Method
Shi, J., Chen, D., & Wang, M. (2020) · Sensors · doi:10.3390/s20174750 · Cited by 44 · see citing works
Real-Time Hand Gesture Tracking for Human–Computer Interface Based on Multi-Sensor Data Fusion
Li, J., Liu, X., Wang, Z., Zhang, T., Qiu, S., Zhao, H., Zhou, X., Cai, H., Ni, R., & Cangelosi, A. (2021) · IEEE Sensors Journal · doi:10.1109/jsen.2021.3122236 · Cited by 44 · see citing works
Human Falling Detection Algorithm Based on Multisensor Data Fusion with SVM
Pan, D., Liu, H., Qu, D., & Zhang, Z. (2020) · Mobile Information Systems · doi:10.1155/2020/8826088 · Cited by 42 · see citing works
Cotechini, V., Belli, A., Palma, L., Morettini, M., Burattini, L., & Pierleoni, P. (2019) · Data in Brief · doi:10.1016/j.dib.2019.103839 · Cited by 38 · see citing works
Prefallkd: Pre-Impact Fall Detection Via CNN-ViT Knowledge Distillation
Chi, T.-H., Liu, K.-C., Hsieh, C.-Y., Tsao, Y., & Chan, C.-T. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10094979 · Cited by 36 · see citing works
Pre-Impact Fall Detection Based on Wearable Device Using Dynamic Threshold Model
Otanasap, N. (2016) · International Conference on Parallel and Distributed Computing, Applications and Technologies (PDCAT) · doi:10.1109/pdcat.2016.083 · Cited by 35 · 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
Traffic prediction based on GCN-LSTM model
Wu, Z., Huang, M., Zhao, A., & Lan, Z. (2021) · Journal of Physics Conference Series · doi:10.1088/1742-6596/1972/1/012107 · Cited by 30 · see citing works
Tabular Learning-Based Traffic Event Prediction for Intelligent Social Transportation System
Sun, C., Li, S., Cao, D., Wang, F., & Khajepour, A. (2022) · IEEE Transactions on Computational Social Systems · doi:10.1109/tcss.2022.3170934 · Cited by 24 · see citing works
A Comprehensive Survey of Various Approaches on Human Fall Detection for Elderly People
Parmar, R., & Trapasiya, S. (2022) · Wireless Personal Communications · doi:10.1007/s11277-022-09816-6 · Cited by 17 · see citing works
MCTN: A Multi-Channel Temporal Network for Wearable Fall Prediction
Liu, J., Li, X., Liao, G., Wang, S., & Liu, L. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-43427-3_24 · Cited by 3 · see citing works
Self-citationApplication of KNN for Fall Detection on Qualcomm SoCs
Nandi, P., Bajaj, A., & Anupama, K. R. (2023) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-031-28663-6_12 · Cited by 3 · see citing works
Feasibility of Tracking Human Kinematics with Simultaneous Localization and Mapping (SLAM)
Laal, S., Vasilyev, P., Pearson, S., Aboy, M., & McNames, J. (2022) · Sensors · doi:10.3390/s22239378 · Cited by 1 · see citing works
Flagged first, then by citations
1 of the 43 references couldn’t be matched to a known paper.
Cited by
Sorted by citations
Multimodal Social Sensing for the Spatio-Temporal Evolution and Assessment of Nature Disasters
Chen, Y., & Wang, Z. (2024) · Sensors · doi:10.3390/s24185889 · Cited by 18 · see citing works
Chen, S., Peng, C., Yang, B., Lin, J., Zhou, L., Jiang, Z., Liu, Z., Liu, Y., & Tang, L. (2026) · npj Artificial Intelligence · doi:10.1038/s44387-026-00083-5 · Cited by 9 · see citing works
Liu, L., Xie, H., Li, X., Liao, G., Wang, S., Liao, C., Miao, S., Wu, H., Li, H., Liao, J., et al. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.127549 · Cited by 5 · see citing works
Self-citationA federated learning framework for arbitrary spatio-temporal graph neural networks
Yoon, H., Chon, K.-W., & Kim, M. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.112801 · Cited by 4 · see citing works
Cho, Y., Solak, G., Nocentini, O., Lorenzini, M., Fortuna, A., & Ajoudani, A. (2025) · IEEE RO-MAN · doi:10.1109/ro-man63969.2025.11217598 · Cited by 3 · see citing works
SPATS: a practical system for comparative analysis of spatio-temporal graph neural networks
Yoon, H., Chon, K.-W., & Kim, M. (2025) · Cluster Computing · doi:10.1007/s10586-025-05523-6 · Cited by 2 · see citing works
Liu, L., Wang, X., Huang, S., Deng, Z., Wang, S., Wu, G., Yang, D., Zha, S., Su, G., & Tao, Q. (2026) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2026.114540 · Cited by 2 · see citing works
Self-citationWearable interface for real-time gait phase recognition using sensor networks
Mohamed, S. A., & Martínez-Hernández, U. (2026) · Applied Soft Computing · doi:10.1016/j.asoc.2026.115005 · Cited by 1 · see citing works
Liu, T., Weng, C., Huang, J. G., & Ni, Z. (2024) · Knowledge-Based Systems · doi:10.1016/j.knosys.2024.112717 · Cited by 1 · see citing works
Liu, L., Xu, Y., Huang, S., Wang, L., Wang, S., Yang, X., Liu, M., Su, G., & Tao, Q. (2026) · Expert Systems with Applications · doi:10.1016/j.eswa.2026.133047
Self-citationSmartwatch-Based Semi-Supervised Fall Detection Using Anomaly Detection Techniques
Alshalaan, M., Harrou, F., & Sun, Y. (2025) · IGI Global eBooks · doi:10.4018/979-8-3373-2033-5.ch006
Vision-Based Fall Prediction With Spatial–Temporal Graph Convolutional Networks
Cui, W., Xiao, L., Wei, C., Li, R., & Lin, H. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3649280
Hypergraph-based contrastive embedding and attention fusion for detection of skin cancer
Banerjee, T., Chhabra, P., Kumar, M., Kumar, A., Abhishek, K., & Shafeeq, B. M. A. (2026) · Scientific Reports · doi:10.1038/s41598-026-43351-9
Adaptive Bayesian optimized spatio-temporal network for fall detection
Bansal, A., Sharma, R., & Kathuria, M. (2026) · Pervasive and Mobile Computing · doi:10.1016/j.pmcj.2026.102237
Sang, P., Ding, S., Liu, L. Q., Ding, S. W., Qin, H., Cao, X., Wang, X., Zhuang, Y., & Hu, Y. (2026) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2026.3688555
Self-citationHe, L., Wang, S., Seo, H.-I., Shen, Q., Cao, Y., Hu, M., Zhang, S., Xu, H., Wen, J., & 滚军军 (2026) · Frontiers in Bioengineering and Biotechnology · doi:10.3389/fbioe.2026.1867362
Self-citationKim, J., & Xiong, S. (2026) · Measurement · doi:10.1016/j.measurement.2026.122880
Ye, S., Xia, Z., Li, B., Wu, D., Liu, C., Ma, L., & Shi, S. (2026) · Biosensors · doi:10.3390/bios16100584
- Authors
- Wang, S., Li, X., Liao, G., Liu, J., Liao, C., Liu, M., Liao, J., & Liu, L.
- Affiliations
- Southwest University (CN)
- Chongqing University (CN)
- Northwestern Polytechnical University (CN)
- Corresponding author
- Liu, Li
- Venue
- Knowledge-Based Systems
- Publisher
- Elsevier BV
- Published
- 2024-06
- Volume
- 293
- Pages
- 111709
- ISSN
- 0950-7051 (ISSN-L)
- OpenAlex
- W4393167082
- Semantic Scholar
- 6978b9bdf5abd7d9fe4b756dd9729b387a23b62c
- Cited by
- 18
- References
- 43
- Citations by year
- 2026: 10 · 2025: 6 · 2024: 2
- FWCI
- 2.11
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- Knowledge-Based Systems (publishedVersion)
- Funders
- Natural Science Foundation of Chongqing Municipality (CSTB2022NSCQ-MSX1256)
- Natural Science Foundation Project of Chongqing
- National Natural Science Foundation of China (62207007, 62377040, 61977012, 61977054)
- 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 risk prediction, wearable inertial sensors, spatio-temporal graph neural networks, human activity monitoring, spatiotemporal dependencies, fall detection
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
