Abstract
This paper analyses the periodic signals in the time series to recognize human activity by using a mobile accelerometer. Each point in the timeline corresponds to a segment of historical time series. This segments form a phase trajectory in phase space of human activity. The principal components of segments of the phase trajectory are treated as feature descriptions at the point in the timeline. The paper introduces a new distance function between the points in new feature space. To reval changes of types of the human activity the paper proposes an algorithm. This algorithm clusters points of the timeline by using a pairwise distances matrix. The algorithm was tested on synthetic and real data. This real data were obtained from a mobile accelerometer.
Similar content being viewed by others
REFERENCES
J. R. Kwapisz, G. M. Weiss, and S. A. Moore, ‘‘Activity recognition using cell phone accelerometers,’’ in Proceedings of the 4th International Workshop on Knowledge Discovery from Sensor Data (2010), Vol. 12, pp. 74–82.
W. Wang, H. Liu, L. Yu, and F. Sun, ‘‘Human activity recognition using smart phone embedded sensors: a linear dynamical systems method. In: Neural Networks (IJCNN),’’ in Proceedings of the International Joint Conference on Neural Networks, 2014, pp. 1185–1190.
A. D. Ignatov and V. V. Strijov, ‘‘Human activity recognition using quasiperiodic time series collected from a single tri-axial accelerometer,’’ Multimedial Tools Appl. 75, 7257–7270 (2016).
A. Olivares, J. Ramirez, J. M. Gorris, G. Olivares, and M. Damas, ‘‘Detection of (in)activity periods in human body motion using inertial sensors: a comparative study,’’ Sensors (Basel) 12, 7257–7270 (2012).
Y. G. Cinar and H. Mirisaee, ‘‘Period-aware content attention RNNs for time series forecasting with missing values,’’ Neurocomputing 312, 177–186 (2018).
A. P. Motrenko and V. V. Strijov, ‘‘Extracting fundamental periods to segment biomedical signals,’’ J. Biomed. Health Inform. 20, 1466–1476 (2015).
Y. P. Lukashin, Adaptive Methods for Short-Term Forecasting (Finansy Statistika, Moscow, 2003) [in Russian].
M. P. Kuznetsov and N. P. Ivkin, ‘‘Time series classification algorithm using combined feature description,’’ Machine Learning Data Anal. 11, 1471–1483 (2015).
A. M. Katrutsa and V. V. Strijov, ‘‘Stress test procedures for features selection algorithms,’’ Chemometr. Intell. Labor. Syst. 142, 172–183 (2015).
I. Borg and P. J. F. Groenen, Modern Multidimensional Scaling (Springer, New York, 2005).
D. L. Danilov and A. A. Zhiglovsky, Main Components of Time Series: Method ‘‘Gusenitsa’’ (SPb. Gos. Univ., St. Petersburg, 1997) [in Russian].
Funding
The research was supported by the Russian Foundation for Basic Research (projects 19-07-01155, 19-07-00875) and by the Government of the Russian Federation (agreement 05.Y09.21.0018).
Author information
Authors and Affiliations
Corresponding authors
Additional information
(Submitted by F. G. Avkhadiev)
Rights and permissions
About this article
Cite this article
Grabovoy, A.V., Strijov, V.V. Quasi-Periodic Time Series Clustering for Human Activity Recognition. Lobachevskii J Math 41, 333–339 (2020). https://doi.org/10.1134/S1995080220030075
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1134/S1995080220030075