Abstract
Elderly activity detection is one of the major issues in modern civilizations. Due to the increase in workload, people are not able to watch over their elderly ones and leave them into old homes for care and cure. In some countries, most elderly people like to live independently instead of living in old homes, which may leave them alone and helpless in any emergency. This study proposes a Machine Learning (ML) based activity detection system which helps to classify the activities of elderly people includes falling down, lying down, sitting down, walking, lying, sitting, standing up, being on all fours, sitting on the ground, standing up from sitting, and standing up from sitting on the ground. The dataset contains the records of five elderly people's activities are used in this research. The data is collected via a wearable sensor accelerometer, which is in the form of time-series data, associated with the timestamp in each reading. To choose the best classifier for the system, we have applied five ML classifiers including Random Forest, k-Nearest Neighbor (k-NN), BernoulliNB, Decision Tree and XGBClassifier. The k-NN classifier achieved a performance accuracy of 99.50%. The proposed elderly fall detection method performs very accurate at identifying activities such as standing up from the lying posture in order to determine whether a fall was happened by a protracted lay, which cause small to serious health issues.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
World Population Ageing 2019. Homepage: https://www.un.org/en/development/desa/population/publications/pdf/ageing/WorldPopulationAgeing2019-Highlights.pdf. Accessed 02 Sep 2021
World Population Ageing: 1950–2050. Homepage: http://globalag.igc.org/ruralaging/world/ageingo.htm. Accessed 02 Sep 2021
Nahian, M.J.A., et al.: Towards an accelerometer-based elderly fall detection system using cross-disciplinary time series features. IEEE Access 9, 39413–39431 (2021)
Thakur, N., Han, C.Y.: An improved approach for complex activity recognition in smart homes. In: Peng, X., Ampatzoglou, A., Bhowmik, T. (eds.) ICSR 2019. LNCS, vol. 11602, pp. 220–231. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-22888-0_15
Tinetti, M.E.: Clinical practice. Preventing falls in elderly persons. N. Engl. J. Med. 348, 42–49 (2003)
Wang, X., Ellul, J., Azzopardi, G.: Elderly fall detection systems: a literature survey. Front. Robot. AI 7, 71 (2020)
Lezzar, F., Benmerzoug, D., Kitouni, I.: Camera-based fall detection system for the elderly with occlusion recognition. Appl. Med. Inform. 42, 169–179 (2020)
CDC.: Keep on Your Feet Preventing Older Adult Falls. Homepage: https://www.cdc.gov/injury/features/older-adult-falls/index.html. Accessed 02 Sept 2021
The National Council on Aging. Homepage: https://www.ncoa.org/news/resources-for-reporters/get-the-facts/falls-prevention-facts. Accessed 03 Sept 2021
CDC Important Facts about Falls. Homepage: https://www.cdc.gov/homeandrecreationalsafety/falls/adultfalls.html. Accessed 03 Sept 2021
Cost of Older Adult Falls. https://www.cdc.gov/homeandrecreationalsafety/falls/data/fallcost.html. Accessed 04 Sept 2021
Thakur, N., Han, C.Y.: A study of fall detection in assisted living: identifying and improving the optimal machine learning method. J. Sens. Actuator Netw. 10 (2021). https://doi.org/10.3390/jsan10030039
Fu, Z., Delbruck, T., Lichtsteiner, P., Culurciello, E.: An address-event fall detector for assisted living applications. IEEE Trans. Biomed Circ. Syst. 2, 88–96 (2008)
Willems, J., Debard, G., Vanrumste, B., Goedemé, T.: A video-based algorithm for elderly fall detection. In: Dössel, O., Schlegel, W.C. (eds.) World Congress on Medical Physics and Biomedical Engineering, vol. 25(5), pp. 312–315. Springer, Heidelberg (2009). https://doi.org/10.1007/978-3-642-03904-1_87
Rafferty, J., Synnott, J., Nugent, C., Morrison, G., Tamburini, E.: Fall detection through thermal vision sensing. In: García, C., Caballero-Gil, P., Burmester, M., Quesada-Arencibia, A. (eds.) Ubiquitous Computing and Ambient Intelligence, vol. 10070, pp. 84–90. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-48799-1_10
Castillo, J.C., Carneiro, D., Serrano-Cuerda, J., Novais, P., Fernández-Caballero, A., Neves, J.: A multi-modal approach for activity classification and fall detection. Int. J. Syst. Sci. 45, 810–824 (2014)
Liu, C.L., Lee, C.H., Lin, P.M.: A fall detection system using k-nearest neighbor classifier. Expert Syst. Appl. 37, 7174–7181 (2010)
Kaluža, B., Mirchevska, V., Dovgan, E., Luštrek, M., Gams, M.: An agent-based approach to care in independent living. In: de Ruyter, B., et al. (eds.) Ambient Intelligence. LNCS, vol. 6439, pp. 177–186. Springer, Heidelberg (2010). https://doi.org/10.1007/978-3-642-16917-5_18
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), 1–23 (2021). https://doi.org/10.3390/s21155134
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Ali, M., Mushtaq, M.F., Shahroz, M., Majeed, R., Samad, A., Akram, U. (2022). Elderly Fall Activity Detection Using Supervised Machine Learning Models. In: Ghazali, R., Mohd Nawi, N., Deris, M.M., Abawajy, J.H., Arbaiy, N. (eds) Recent Advances in Soft Computing and Data Mining. SCDM 2022. Lecture Notes in Networks and Systems, vol 457. Springer, Cham. https://doi.org/10.1007/978-3-031-00828-3_33
Download citation
DOI: https://doi.org/10.1007/978-3-031-00828-3_33
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-00827-6
Online ISBN: 978-3-031-00828-3
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)