Abstract
Human Activity Recognition and particularly detection of abnormal activities such as falls have become a point of interest to many researchers worldwide since falls are considered to be one of the leading causes of injury and death, especially in the elderly population. The prompt intervention of caregivers in critical situations can significantly improve the autonomy and well-being of individuals living alone and those who require remote monitoring. This paper presents a study of accelerometer and gyroscope data retrieved from smartphone embedded sensors, using iOS-based devices. In the project framework there was developed a mobile application for data collection with the following fall type and fall-like activities: Falling Right, Falling Left, Falling Forward, Falling Backward, Sitting Fast, and Jumping. The collected dataset has passed the preprocessing phase and afterward was classified using different Machine Learning algorithms, namely, by Decision Trees, Random Forest, Logistic Regression, k-Nearest Neighbour, XGBoost, LightGBM, and Pytorch Neural Network. Unlike other similar studies, during the experimental setting, volunteers were asked to have smartphones freely in their pockets without tightening and fixing them on the body. This natural way of keeping a mobile device is quite challenging in terms of noisiness however it is more comfortable to wearers and causes fewer constraints. The obtained results are promising that encourages us to continue working with the aim to reach sufficient accuracy along with building a real-time application for potential users.
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
References
Aggarwal, C.C.: Data classification. Data Mining, pp. 285–344. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-14142-8_10
Alasadi, S.A., Bhaya, W.S.: Review of data preprocessing techniques in data mining. Eng. Appl. Sci. 12(16), 4102–4107 (2017)
Ali, S., Khusro, S., Rauf, A., Mahfooz, S.: Sensors and mobile phones: evolution and state-of-the-art. Pak. J. Sci. 66(4), 386–400 (2014)
Attal, F., Mohammed, S., Dedabrishvili, M., Chamroukhi, F., Oukhellou, L., Amirat, Y.: Physical human activity recognition using wearable sensors. Sensors (Basel Switz.) 15, 31314–31338 (2015)
Chen, T., Guestrin, C.: Xgboost: a scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 785–794 (2016)
Dedabrishvili, M.: Effective ways to overcome classification limitations for activities of daily livings (ADLS). In: 2020 IEEE 2nd International Conference on System Analysis and Intelligent Computing (SAIC), pp. 1–7 (2020)
GarcÃa, S., RamÃrez-Gallego, S., Luengo, J., BenÃtez, J.M., Herrera, F.: Big data preprocessing: methods and prospects. Big Data Anal. 1(1), 9 (2016)
Gent, I.P., et al.: Learning when to use lazy learning in constraint solving. In: ECAI, pp. 873–878 (2010)
Han, J., Pei, J., Kamber, M.: Data Mining: Concepts and Techniques. Elsevier (2011)
Kambria: Logistic Regression For Machine Learning and Classification (2019). https://kambria.io/blog/logistic-regression-for-machine-learning/. Accessed 28 December 2020
Ke, G., et al.: Lightgbm: a highly efficient gradient boosting decision tree. In: NIPS (2017)
Motoda, H., Liu, H.: Feature selection extraction and construction. Commun. IICM Inst. Inf. Comput. Mach. 5(2), 67–72 (2002)
Müller, A.C., Guido, S. et al.: Introduction to Machine Learning with Python: a Guide for Data Scientists. O’Reilly Media, Inc. (2016)
Paszke, A., et al.:. Automatic differentiation in pytorch. In: NIPS-W (2017)
Phyu,T.N.: Survey of classification techniques in data mining. In: Proceedings of the International MultiConference of Engineers and Computer Scientists Vol I IMECS 2009, Hong Kong (2009)
Pyle, D.: Data Preparation for Data Mining. Morgan Kaufmann (1999)
Raschka, S., Mirjalili, V.: Python machine learning: machine learning and deep learning with python. In: scikit-learn, and TensorFlow. Packt Publishing (2019)
Schmidhuber, J.: Deep learning in neural networks: an overview. Neural Netw. 61, 85–117 (2015)
Yuan, G., Wang, Z., Meng, F., Yan, Q., Xia, S.: An overview of human activity recognition based on smartphone. Sensor Rev. 39(2), 288–306 (2019)
Acknowledgments
This work was supported by Shota Rustaveli National Science Foundation of Georgia (SRNSFG) under the grant YS-19-1633.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Dedabrishvili, M., Dundua, B., Mamaiashvili, N. (2021). Smartphone Sensor-Based Fall Detection Using Machine Learning Algorithms. In: Fujita, H., Selamat, A., Lin, J.CW., Ali, M. (eds) Advances and Trends in Artificial Intelligence. Artificial Intelligence Practices. IEA/AIE 2021. Lecture Notes in Computer Science(), vol 12798. Springer, Cham. https://doi.org/10.1007/978-3-030-79457-6_52
Download citation
DOI: https://doi.org/10.1007/978-3-030-79457-6_52
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-79456-9
Online ISBN: 978-3-030-79457-6
eBook Packages: Computer ScienceComputer Science (R0)