Krishna Kumari R.; Padma V.

A Graph Learning Framework for Analyzing Smart Assistive Sensor Data in Elderly Fall Prediction

PDF (979KB), PP.117-131

Views: 0 Downloads: 0

Author(s)

1. Department of Mathematics, College of Engineering and Technology, SRM Institute of Science and Technology, Kattankulathur, Chennai-603203, Tamilnadu, India

* Corresponding author.

DOI: https://doi.org/10.5815/ijem.2026.04.09

Received: 22 Apr. 2026 / Revised: 27 May 2026 / Accepted: 17 Jun. 2026 / Published: 8 Aug. 2026

Index Terms

Bipartite Graphs, Graph based Machine Learning, Feature Distribution, Pairplot, Kernel density estimation (KDE) plots

Abstract

Falls among older adults represent a critical public health challenge, with approximately 37.3 million fall-related incidents reported globally each year. Early and accurate prediction of falls is essential to enable timely, proactive interventions and to reduce associated injuries and fatalities. This work introduces a graph-based machine learning framework that leverages data from the cStick, a smart assistive Internet of Medical Things (IoMT) device. Bipartite graphs are constructed to model static correlations between multivariate sensor inputs— including heart rate variability (HRV), pressure, distance, SpO2, blood sugar levels, and accelerometer readings— and fall outcomes encoded as no fall, predicted fall, or definite fall. SHAP (SHapley Additive exPlanations) values are further integrated to enhance model interpretability and to identify the most influential sensor features through feature-only graph projections. Kernel Density Estimation (KDE) plots and pairplots are used to visualize feature distributions across fall categories. The proposed framework demonstrates that Pressure and Distance exhibit the strongest correlations with fall decisions (1.000 and −0.946, respectively), providing actionable insights for risk stratification. The integration of graph-based analysis with SHAP interpretability improves both predictive accuracy and transparency, facilitating proactive interventions and enhancing the safety, autonomy, and well-being of elderly individuals in real-world assistive care settings.

Cite This Paper

Krishna Kumari R., Padma V., "A Graph Learning Framework for Analyzing Smart Assistive Sensor Data in Elderly Fall Prediction", International Journal of Engineering and Manufacturing (IJEM), Vol.16, No.4, pp.117-131, 2026. DOI:10.5815/ijem.2026.04.09

Reference

[1]Andriopoulou, F., Dagiuklas, T., & Orphanoudakis, T., Integrating IoT and fog computing for healthcare service delivery. In Components and services for IoT platforms: Paving the way for IoT standards, Cham: Springer International Publishing,pp.213-232,(2016). https://doi.org/10.1007/978-3-319-42304-3_11
[2]Alrashdi, Ibrahim, Ali Alqazzaz, Raed Alharthi, Esam Aloufi, Mohamed A. Zohdy, and Hua Ming. "FBAD: Fog-based attack detection for IoT healthcare in smart cities." In 2019 IEEE 10th Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON), IEEE, pp. 0515-0522, (2019). https://doi.org/10.1109/UEMCON47517.2019.8992963
[3]Ambrose, A. F., Paul, G., Hausdorff, J. M., “Risk factors for falls among older adults: a review of the literature”, Maturitas, 75(1), pp.51-61, (2013). https://doi.org/10.1016/j.maturitas.2013.02.009
[4]Apple Inc. Apple Watch: Fall Detection and Emergency Services (2022). Retrieved from https://www. apple.com/apple-watch/features/
[5]Azimi, I., Rahmani, A. M., Liljeberg, P., & Tenhunen, H., Internet of things for remote elderly monitoring: a study from user-centered perspective. Journal of ambient intelligence and humanized computing, 8(2), pp.273-289, (2017). https://doi.org/10.1007/s12652-016-0387-y
[6]Baig, M. M., Afifi, S., GholamHosseini, H., Mirza, F. A systematic review of wearable sensors and IoT-based monitoring applications for older adults–a focus on ageing population and independent living. Journal of medical systems, 43(8), 233, (2019). https://doi.org/10.1007/s10916-019-1365-7
[7]Bhattacharyya, Tamonash, Prasun Ghosal., “Healthier aging: A systematic review of different fall detection techniques in home and outdoor environments”, In 2023 4th International Conference on Computing and Communication Systems (I3CS), IEEE, pp. 1-6, (2023). https://doi.org/10.1109/I3CS58314.2023.10127548
[8]Burns, E. (2018). Deaths from falls among persons aged≥ 65 years-United States, 2007-2016. MMWR. Morbidity and mortality weekly report, 67. https://doi.org/10.15585/mmwr.mm6718a1
[9]Centers for Disease Control and Prevention (CDC). Falls among older adults: An overview. CDC Injury Center (2022).
[10]Centers for Disease Control and Prevention (CDC). Injury prevention and control: Falls. CDC Injury Center (2017).
[11]Cocuzzo, B., Wrench, A., O’Malley, C., O’Malley, C. B., “ Effects of COVID-19 on older adults: physical, mental, emotional, social, and financial problems seen and unseen”, Cureus, 14(9), (2022). https://doi.org/10.7759/cureus.29493
[12]cStick. cStick: A smart assistive device for fall detection in the elderly. cStick Technology (2022).
[13]Debenham, M. I., Smuin, J. N., Grantham, T. D., Ainslie, P. N., Dalton, B. H. “Hypoxia and standing balance”, European Journal of Applied Physiology, 121 pp.993-1008, (2021). https://doi.org/10.1007/s00421-020-04581-5
[14]Fournier, Hélène, Irina Kondratova, and Keiko Katsuragawa., “Smart technologies and internet of things designed for aging in place”, In International Conference on Human-Computer Interaction, Cham: Springer International Publishing, pp.158–176, (2021). https://doi.org/10.1007/978-3-030-77392-2_11
[15]Hip-Hope, “Fall detection with Hip-Hope: A smart wearable solution”, Hip-Hope Technologies (2019).
[16]Kejani, M. T., Dornaika, F., & Talebi, H., Graph convolution networks with manifold regularization for semi-supervised learning. Neural Networks, 127, pp.160-167, (2020). https://doi.org/10.1016/j.neunet.2020.04.016
[17]Krishna Kumari, R.: Revolutionizing Education: Harnessing Graph Machine Learning for Enhanced Problem-Solving in Environmental Science and Pollution Technology. Nature Environment and Pollution Technology. 23(4), 2247–2254, (2024). https://doi.org/10.46488/NEPT.2024.v23i04.038
[18]Krishna Kumari, R., Krishnan, S.B., Subramanian, S.S., Chakrabarti, P.: Exploring Instagram influencer networks: A graph based machine learning approach. Mathematical Modelling of Engineering Problems. 11(8), 2048–2059, (2024). https://doi.org/10.18280/mmep.110806
[19]Krishna Kumari, R., Krishnan, S.B., Chakrabarti, P., Subramanian, S.S.: Securing online transactions: Un- veiling anomalies through graph-based machine learning in fraud detection. MESA. 15(3), 961–979, (2024).
[20]Krishna Kumari, R., Janaki, K., Jeyanthi Lakshminarayanan, and Mahimairaj Pathinathan.: Enhancing algo- rithmic reasoning and critical thinking through game-based learning: A graph theory approach. Multidisci- plinary Reviews, 7(10), pp.2024233–2024233, (2024). https://doi.org/10.31893/multirev.2024233
[21]Lin, Frank R., and Luigi Ferrucci.: Hearing loss and falls among older adults in the United States. Archives of internal medicine. 172(4) pp.369-371, (2012). https://doi.org/10.1001/archinternmed.2011.728
[22]Liu, B. A., Topper, A. K., Reeves, R. A., Gryfe, C., Maki, B. E.: Falls among older people: relationship to medication use and orthostatic hypotension. Journal of the American Geriatrics Society. 43(10), pp.1141– 1145, (1995). https://doi.org/10.1111/j.1532-5415.1995.tb07016.x
[23]Madhubala, J. S., Umamakeswari, A.: A vision based fall detection system for elderly people. Indian Journal of Science and Technology, 8, pp.167–175, (2015). https://doi.org/10.17485/ijst/2015/v8iS9/65545
[24]Madigan, Michael, Noah J. Rosenblatt, and Mark D. Grabiner.: Obesity as a factor contributing to falls by older adults. Current obesity reports 3. pp.348-354, (2014). https://doi.org/10.1007/s13679-014-0106-y
[25]Muir, Susan W., Karen Gopaul, Manuel M. Montero Odasso.: The role of cognitive impairment in fall risk among older adults: a systematic review and meta-analysis. Age and ageing 41(3), pp.299–308, (2012). https://doi.org/10.1093/ageing/afs012
[26]Newaz, N. T., Hanada , E.: The methods of fall detection: A literature review. Sensors. 23(11), pp.5212 (2023). https://doi.org/10.3390/s23115212
[27]Perumal, T.: A review on fall detection systems in bathrooms: challenges and opportunities. Multimedia Tools and Applications, 83(29), pp.73477-73505, (2024). https://doi.org/10.1007/s11042-023-18088-6
[28]Rastogi, S., Singh, J.: A systematic review on machine learning for fall detection system. Computational intelligence 37(2), pp.951–974, (2021). https://doi.org/10.1111/coin.12441
[29]Ren, Lingmei, and Yanjun Peng.: Research of fall detection and fall prevention technologies: A systematic review. IEEE access 7. pp.77702-77722, (2019). https://doi.org/10.1109/ACCESS.2019.2922708
[30]Rakhman, Arkham Zahri, Lukito Edi Nugroho.: Fall detection system using accelerometer and gyroscope based on smartphone. In 2014 The 1st International Conference on Information Technology, Computer, and Electrical Engineering IEEE, pp.99-104, (2014). https://doi.org/10.1109/ICITACEE.2014.7065722
[31]Rubenstein, L. Z., Josephson, K. R.: Falls and their prevention in elderly people: what does the evidence show?. Medical Clinics, 90(5), 807-824, (2006). https://doi.org/10.1016/j.mcna.2006.05.013
[32]Rachakonda, L., Sharma, A., Mohanty, S. P., Kougianos, E.: Good-eye: a combined computer-vision and physiological-sensor based device for full-proof prediction and detection of fall of adults. In Internet of Things. A Confluence of Many Disciplines: Second IFIP International Cross-Domain Conference, IFIPIoT 2019, Tampa, FL, USA, October 31–November 1, 2019, Revised Selected Papers 2. Springer International Publishing , pp.273-288, (2020). https://doi.org/10.1007/978-3-030-43605-6_16
[33]Singh, A., Rehman, S. U., Yongchareon, S., Chong, P. H. J.: Sensor technologies for fall detection systems: A review. IEEE Sensors Journal, 20(13), pp.6889-6919, (2020). https://doi.org/10.1109/JSEN.2020.2976554
[34]Srinivasan, V. P., Pandey, P., Muthumarilakshmi, S., Konidhala, J., Rajmohan, M., Murugan, S.: Smart Aging Technology with IoT and Deep Learning Analytics for Elderly Activity Patterns and Health Outcomes. In 2024 9th International Conference on Communication and Electronics Systems (ICCES) IEEE. pp.585-590, (2024). https://doi.org/10.1109/ICCES63552.2024.10859925
[35]Stavropoulos, T. G., Papastergiou, A., Mpaltadoros, L., Nikolopoulos, S., Kompatsiaris, I.: IoT wearable sensors and devices in elderly care: A literature review. Sensors, 20(10), 2826, (2020). https://doi.org/10.3390/s20102826
[36]Thomas, E., Battaglia, G., Patti, A., Brusa, J., Leonardi, V., Palma, A., Bellafiore, M.: Physical activity programs for balance and fall prevention in elderly: A systematic review. Medicine. 98(27), pp.e16218, (2019). https://doi.org/10.1097/MD.0000000000016218
[37]Usmani, S., Saboor, A., Haris, M., Khan, M. A., Park, H.: Latest research trends in fall detection and prevention using machine learning: A systematic review. Sensors 21(15), pp.5134, (2021). https://doi.org/10.3390/s21155134
[38]Vallabh, P., Malekian, R.: Fall detection monitoring systems: a comprehensive review. Journal of Ambient Intelligence and Humanized Computing 9(6), pp.1809-1833, (2018). https://doi.org/10.1007/s12652-017-0592-3
[39]Wang, X., Ellul, J., Azzopardi, G.: Elderly fall detection systems: A literature survey. Frontiers in Robotics and AI, 7, 71, (2020). https://doi.org/10.3389/frobt.2020.00071

International Journal of Engineering and Manufacturing (IJEM)