A Balanced big dataset for Sensor-Based Fall Detection: Enhancing Model Accuracy and Robustness
Keywords:
fall detection, big dataset, sensor-based fall detection, Activities of Daily Living, machine learning, dataset balancing, healthcare, elderly care, multi-modal dataAbstract
Falls represent a critical challenge in healthcare, particularly for the elderly and those with limited mobility. They can cause severe injuries or deaths if not detected and addressed. Existing falldetection systems often struggle with lacking large, diverse, and balanced datasets; this limitation hinders the development of accurate and generalizable machine-learning (ML) solutions. This paper introduces a complete big dataset designed explicitly for video- and sensor-based fall detection, featuring 8,953 recorded activities, including 2,791 falls and 6,162 activities of daily living (ADL), collected from 29 diverse subjects. The dataset encompasses various fall scenarios—left, right, front, back, and complex cases such as attempting to sit on a chair or falling from elevated positions—along with ADL tasks such as walking, running, standing up from the ground, and driving. Each activity is recorded for 8 s at 100 Hz, yielding 800 data points per file. Including barometer-derived altitude-delta data significantly improves the performance of transformer-based models, raising accuracy from 97–98 % to more than 99.5 %. All 3,000 fall recordings were individually processed and non-matching patterns removed to confirm data quality, producing a clean and consistent corpus. Comparative experiments with existing datasets demonstrate superior detection accuracy and reduced false-positive rates, underscoring the robustness and reliability of our contribution. Overall, the proposed dataset provides the research community with a vital resource for advancing fall-detection systems and promotes the development of robust, deployable ML solutions for real-world healthcare applications.
References
I. Ursul and J. H. Muzamal, "A dynamic blurring approach with efficientnet and lstm to enhance privacy in video-based elderly fall detection," 2024.
R. Vaishya and A. Vaish, "Falls in older adults are serious," Indian journal of orthopaedics, vol. 54, pp. 69-74, 2020. https://doi.org/10.1007/s43465-019-00037-x
S. Z. Fadem, Understanding and Preventing Falls: A Guide to Reducing Your Risks. Springer Nature, 2023. https://doi.org/10.1007/978-3-031-39155-2
N. M. Peel, "Epidemiology of falls in older age," Canadian Journal on Aging/La Revue canadienne du vieillissement, vol. 30, no. 1, pp. 7-19, 2011. https://doi.org/10.1017/S071498081000070X
A. Singh, S. U. Rehman, S. Yongchareon, and P. H. J. Chong, "Sensor technologies for fall detection systems: A review," IEEE Sensors Journal, vol. 20, no. 13, pp. 6889-6919, 2020. https://doi.org/10.1109/JSEN.2020.2976554
I. Singh, "Assessment and management of older people in the general hospital setting," Challenges in Elder Care, vol. 37, pp. 10-5772, 2016. https://doi.org/10.5772/64294
N. H. Rasmussen, J. Dal, J. V. den Bergh, F. de Vries, M. H. Jensen, and P. Vestergaard, "Increased risk of falls, fall-related injuries and fractures in people with type 1 and type 2 diabetes-a nationwide cohort study," Current drug safety, vol. 16, no. 1, pp. 52-61, 2021. https://doi.org/10.2174/1574886315666200908110058
S. Ness, V. Eswarakrishnan, H. Sridharan, V. Shinde, N. Venkata Prasad Janapareddy, and V. Dhanawat, "Anomaly detection in network traffic using advanced machine learning techniques," IEEE Access, vol. 13, pp. 16 133-16 149, 2025. https://doi.org/10.1109/ACCESS.2025.3526988
O. Benichou and S. R. Lord, "Rationale for strengthening muscle to prevent falls and fractures: a review of the evidence," Calcified tissue international, vol. 98, no. 6, pp. 531-545, 2016. https://doi.org/10.1007/s00223-016-0107-9
P. Vallabh and R. Malekian, "Fall detection monitoring systems: a comprehensive review," Journal of Ambient Intelligence and Humanized Computing, vol. 9, no. 6, pp. 1809-1833, 2018. https://doi.org/10.1007/s12652-017-0592-3
G. Diraco, A. Leone, and P. Siciliano, "A radar-based smart sensor for unobtrusive elderly monitoring in ambient assisted living applications," Biosensors, vol. 7, no. 4, p. 55, 2017. https://doi.org/10.3390/bios7040055
S. Rastogi and J. Singh, "Human fall detection and activity monitoring: a comparative analysis of vision-based methods for classification and detection techniques," Soft Computing, vol. 26, no. 8, pp. 3679-3701, 2022. https://doi.org/10.1007/s00500-021-06717-x
D. Roy, V. Komini, and S. Girdzijauskas, "Classifying falls using out-ofdistribution detection in human activity recognition," AI Communications, no. Preprint, pp. 1-17, 2023. https://doi.org/10.3233/AIC-220205
S. Mobsite, N. Alaoui, M. Boulmalf, and M. Ghogho, "Activity classification and fall detection using monocular depth and motion analysis," IEEE Access, 2023. https://doi.org/10.1109/ACCESS.2023.3348413
R. Keramati Hatkeposhti, M. Yadollahzadeh-Tabari, and M. Golsorkhtabariamiri, "Providing an approach for early prediction of fall in human activities based on wearable sensor data and the use of deep learning algorithms," The Computer Journal, vol. 67, no. 2, pp. 658-673, 2024. https://doi.org/10.1093/comjnl/bxad008
N. I. M. Amir, R. A. Dziyauddin, N. Mohamed, N. S. N. Ismail, H. M. Kaidi, N. Ahmad, and M. A. M. Izhar, "Fall detection system using wearable sensor devices and machine learning: A review," Authorea Preprints, 2024. https://doi.org/10.36227/techrxiv.171084921.16728034/v1
K. Misaghian, J. E. Lugo, and J. Faubert, "Immediate fall prevention: the missing key to a comprehensive solution for falling hazard in older adults," Frontiers in aging neuroscience, vol. 16, p. 1348712, 2024. https://doi.org/10.3389/fnagi.2024.1348712
E. Strelcenia and S. Prakoonwit, "Improving classification performance in credit card fraud detection by using new data augmentation," AI, vol. 4, no. 1, 2023. https://doi.org/10.3390/ai4010008
D. Twomey, "Novel algorithm-level approaches for class-imbalanced machine learning," Ph.D. dissertation, UCL (University College London), 2023.
V. Dhanawat, V. Shinde, V. Karande, and K. Singhal, "Enhancing financial risk management with federated ai," in 2024 8th SLAAI International Conference on Artificial Intelligence (SLAAI-ICAI), 2024, pp. 1-6. https://doi.org/10.1109/SLAAI-ICAI63667.2024.10844982
Z. Sun, W. Ying, W. Zhang, and S. Gong, "Undersampling method based on minority class density for imbalanced data," Expert Systems with Applications, vol. 249, p. 123328, 2024. https://doi.org/10.1016/j.eswa.2024.123328
D. Dablain, K. N. Jacobson, C. Bellinger, M. Roberts, and N. V. Chawla, "Understanding cnn fragility when learning with imbalanced data," Machine Learning, vol. 113, no. 7, pp. 4785-4810, 2024. https://doi.org/10.1007/s10994-023-06326-9
V. M. Di Mucci, A. Cardellicchio, S. Ruggieri, A. Nettis, V. Renò, and G. Uva, "Artificial intelligence in structural health management of existing bridges," Automation in Construction, vol. 167, p. 105719, 2024. https://doi.org/10.1016/j.autcon.2024.105719
G. Vavoulas, M. Pediaditis, E. G. Spanakis, and M. Tsiknakis, "The mobifall dataset: An initial evaluation of fall detection algorithms using smartphones," in 13th IEEE International Conference on BioInformatics and BioEngineering. IEEE, 2013, pp. 1-4. https://doi.org/10.1109/BIBE.2013.6701629
A. Sucerquia, J. D. López, and J. F. Vargas-Bonilla, "Sisfall: A fall and movement dataset," Sensors, vol. 17, no. 1, p. 198, 2017. https://doi.org/10.3390/s17010198
J. Klenk, L. Schwickert, L. Palmerini, S. Mellone, A. Bourke, E. A. Ihlen, N. Kerse, K. Hauer, M. Pijnappels, M. Synofzik et al., "The farseeing realworld fall repository: a large-scale collaborative database to collect and share sensor signals from real-world falls," European review of aging and physical activity, vol. 13, pp. 1-7, 2016. https://doi.org/10.1186/s11556-016-0168-9
L. Martínez-Villaseñor, H. Ponce, J. Brieva, E. Moya-Albor, J. NúñezMartínez, and C. Peñafort-Asturiano, "Up-fall detection dataset: A multimodal approach," Sensors, vol. 19, no. 9, p. 1988, 2019. https://doi.org/10.3390/s19091988
X. Yu, J. Jang, and S. Xiong, "A large-scale open motion dataset (kfall) and benchmark algorithms for detecting pre-impact fall of the elderly using wearable inertial sensors," Frontiers in Aging Neuroscience, vol. 13, p. 692865, 2021.
https://doi.org/10.3389/fnagi.2021.692865
A. Shahroudy, J. Liu, T.-T. Ng, and G. Wang, "Ntu rgb+ d: A large scale dataset for 3d human activity analysis," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 1010- 1019.
https://doi.org/10.1109/CVPR.2016.115
O. Keskes and R. Noumeir, "Vision-based fall detection using st-gcn," IEEE Access, vol. 9, pp. 28 224-28 236, 2021.
Downloads
Published
How to Cite
Issue
Section
License
International Journal of Computing is an open access journal. Authors who publish with this journal agree to the following terms:• Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
• Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
• Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.