Abstract
Fall Detection (FD) and ADL (Activity of Daily Living) identification is one the main challenges in a lot of real-world problems like work monitoring, healthcare systems, etc. Up to our knowledge, there are a lot of proposals in the literature for both problems separately, but few of them pose both problems at a time. A possible solution relies on-wrist wearable devices including tri-axial accelerometers performing ADL and Fall identification autonomously. Since the dynamics of both kind of activities (FALL and ADL) are quite similar and not easy to identify, mainly in FALL and high ADLs like Running, Jogging, GoUpstairs, etc, a technique considering peaks is suitable. Thus, in this study, an ensemble between KMEANS and KNN (stands for EKMEANS) taking as input a 19 features dataset calculated from a time window whenever a peak is detected. As peak detection algorithm is used, the MAX-PEAKS algorithm presented in [15].
The proposal is evaluated using the UMA Fall, one of the publicly available simulated fall detection data sets, and compared to two classical well-known algorithms: the KNN and a Feed Forward Neural Network (NN) [15].
The results show that our proposal outperforms the NN results.
Future work includes a further analysis of the dynamics of the ensemble EKMEANS and a study of this problem using Deep-Learning.
This research has been funded by the Spanish Ministry of Science and Innovation, under project MINECO-TIN2017-84804-R, and by the Grant FC-GRUPIN-IDI/2018/000226 project from the Asturias Regional Government.
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
Notes
- 1.
The default implementation of the R platform “kmeans” function has been used.
References
Abbate, S., Avvenuti, M., Bonatesta, F., Cola, G., Corsini, P.: AlessioVecchio: a smartphone-based fall detection system. Pervasive Mob. Comput. 8(6), 883–899 (2012)
Bourke, A., O’Brien, J., Lyons, G.: Evaluation of a threshold-based triaxial accelerometer fall detection algorithm. Gait Posture 26, 194–199 (2007)
Casilari, E., Santoyo-Ramón, J.A., Cano-García, J.M.: Umafall: a multisensor dataset for the research on automatic fall detection. Procedia Comput. Sci. 110(Supplement C), 32–39 (2017). https://doi.org/10.1016/j.procs.2017.06.110
Hartigan, J.A., Wong, M.A.: Algorithm as 136: a k-means clustering algorithm. J. Roy. Stat. Soc. Ser. C (Appl. Stat.) 28(1), 100–108 (1979). http://www.jstor.org/stable/2346830
Huynh, Q.T., Nguyen, U.D., Irazabal, L.B., Ghassemian, N., Tran, B.Q.: Optimization of an acc. and gyro.-based fall det. algorithm. J. Sens. (2015)
Kangas, M., Konttila, A., Lindgren, P., Winblad, I., Jämsaä, T.: Comparison of low-complexity fall detection algorithms for body attached accelerometers. Gait Posture 28, 285–291 (2008)
Khojasteh, S.B., Villar, J.R., de la Cal, E., González, V.M., Sedano, J., Yazgan, H.R.: Evaluation of a wrist-based wearable fall detection method. In: de Cos Juez, F., et al. (eds.) 13th International Conference on Soft Computing Models in Industrial and Environmental Applications. HAIS 2018. LNCS, vol. 10870, pp. 377–386. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-92639-1_31
Khojasteh, S.B., Villar, J.R., Chira, C., González, V.M., de la Cal, E.: Improving fall detection using an on-wrist wearable accelerometer. Sensors 18(5), 1350 (2018)
Lin, W.Y., Verma, V.K., Lee, M.Y., Lai, C.S.: Activity monitoring with a wrist-worn, accelerometer-based device. Micromachines 9(9), 450 (2018)
Lu, J., Tong, K.Y.: Robust single accelerometer-based activity recognition using modified recurrence plot. IEEE Sens. J. 19(15), 6317–6324 (2019)
Palshikar, G.K.: Simple algorithms for peak detection in time-series. Technical report, Tata Research Development and Design Centre (2009)
Sukor, A.A., Zakaria, A., Rahim, N.A.: Activity recognition using accelerometer sensor and machine learning classifiers. In: 2018 IEEE 14th International Colloquium on Signal Processing and Its Applications (CSPA), pp. 233–238. IEEE (2018)
Venables, W.N., Ripley, B.D.: Modern Applied Statistics with S. Springer, Cham (2002)
Villar, J.R., de la Cal, E., Fañez, M., González, V.M., Sedano, J.: User-centered fall detection using supervised, on-line learning and transfer learning. Progress Artif. Intell. 2019, 1–22 (2019). https://doi.org/10.1007/s13748-019-00190-2
Villar, M., Villar, J.R.: Peak detection enhancement in autonomous wearable fall detection. In: Abraham, A., Siarry, P., Ma, K., Kaklauskas, A. (eds.) ISDA 2019. AISC, vol. 1181, pp. 48–58. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-49342-4_5
Wu, F., Zhao, H., Zhao, Y., Zhong, H.: Development of a wearable-sensor-based fall detection system. Int. J. Telemed. Appl. 2015, 11 (2015). https://doi.org/10.1155/2015/576364
Yacchirema, D., de Puga, J.S., Palau, C., Esteve, M.: Fall detection system for elderly people using IoT and big data. Procedia Comput. Sci. 130, 603–610 (2018). The 9th International Conference on Ambient Systems, Networks and Technologies (ANT 2018)/The 8th International Conference on Sustainable Energy Information Technology (SEIT-2018)/Affiliated Workshops
Zhang, T., Wang, J., Xu, L., Liu, P.: Fall detection by wearable sensor and one-class SVM algorithm. In: Huang, D.S., Li, K.I.G. (eds.) Intelligent Computing in Signal Processing and Pattern Recognition. LNCS, vol. 345, pp. 858–863. Springer, Heidelberg (2006). https://doi.org/10.1007/978-3-540-37258-5_104
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
de la Cal, E.A., Fáñez, M., Villar, M., Villar, J.R., Suárez, V. (2020). A Simple Classification Ensemble for ADL and Falls. In: de la Cal, E.A., Villar Flecha, J.R., Quintián, H., Corchado, E. (eds) Hybrid Artificial Intelligent Systems. HAIS 2020. Lecture Notes in Computer Science(), vol 12344. Springer, Cham. https://doi.org/10.1007/978-3-030-61705-9_9
Download citation
DOI: https://doi.org/10.1007/978-3-030-61705-9_9
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-61704-2
Online ISBN: 978-3-030-61705-9
eBook Packages: Computer ScienceComputer Science (R0)