ISSN 2071-8594

Российская академия наук

Главный редактор

Академик С. В. Емельянов

R.V. Isachenko, I.N. Zharikov, A.M. Bochkarev, V.V. Strijov "Feature Generation for Physical Activity Classification"

Abstract.

The paper investigates human physical activity classification problem. Time series obtained from accelerometer of a wearable device produce a dataset. Due to the high dimension of object description and low computational resources one has to state a feature generation problem. The authors propose to use the parameters of the local approximation models as informative features. The experiment is conducted on two datasets for human activity recognition using accelerometer: WISDM and USC-HAD. It compares several superpositions of various generation methods and classification models.

Keywords:

wearable devices, accelerometer, time series, local approximation, classification.

Стр. 20-27.

DOI 10.14357/20718594180312

References

1. Bao, L., Intille, S.S.: Activity recognition from userannotated acceleration data. In: International Conference on Pervasive Computing. pp. 1–17. Springer (2004)
2. Budnik, M., Gutierrez-Gomez, E.L., Safadi, B., Pellerin, D., Quénot, G.: Learned features versus engineered features for multimedia indexing. Multimedia Tools and Applications 76(9), 11941–11958 (2017)
3. De Boor, C.: A practical guide to splines, vol. 27. Springer-Verlag (1978)
4. Geurts, P.: Pattern extraction for time series classification. In: European Conference on Principles of Data Mining and Knowledge Discovery. pp. 115–127. Springer (2001)
5. Golub, G.H., Reinsch, C.: Singular value decomposition and least squares solutions. Numerische mathematik 14(5), 403–420 (1970)
6. Hammerla, N.Y., Halloran, S., Ploetz, T.: Deep, convolutional, and recurrent models for human activity recognition using wearables. arXiv preprint arXiv:1604.08880 (2016)
7. Hassani, H.: Singular spectrum analysis: methodology and comparison. Journal of Data Science 5(2), 239–257 (2007)
8. Ignatov, A.D., Strijov, V.V.: Human activity recognition using quasiperiodic time series collected from a single triaxial accelerometer. Multimedia tools and applications 75(12), 7257–7270 (2016)
9. Incel, O.D., Kose, M., Ersoy, C.: A review and taxonomy of activity recognition on mobile phones. BioNanoScience 3(2), 145–171 (2013)
10. Jones, E., Oliphant, T., Peterson, P.: SciPy: Open source scientific tools for Python (2001), http://www.scipy.org/, [Online; accessed today]
11. Karasikov, M., Strijov, V.: Feature-based time-series classification. Intelligence 24(1), 164–181 (2016)
12. Kuznetsov, M., Ivkin, N.: Time series classification algorithm using combined feature description. Machine Learning and Data Analysis 1(11), 1471–1483 (2015)
13. Kwapisz, J.R., Weiss, G.M., Moore, S.A.: Activity recognition using cell phone accelerometers. ACM SigKDD Explorations Newsletter 12(2), 74–82 (2011)
14. Lu, L., Qing-ling, C., Yi-Ju, Z.: Activity recognition in smart homes. Multimedia Tools and Applications pp. 1–18 (2016)
15. Lu, Y., Wei, Y., Liu, L., Zhong, J., Sun, L., Liu, Y.: Towards unsupervised physical activity recognition using smartphone accelerometers. Multimedia Tools and Applications 76(8)
16. Lukashin, Y.P.: Adaptive methods of short-term forecasting of time series. M.: Finance and statistics (2003)
17. Motrenko, A., Strijov, V.: Extracting fundamental periods to segment biomedical signals. IEEE journal of biomedical and health informatics 20(6), 1466–1476 (2016)
18. Umeda, Y.: Time series classification via topological data analysis. Transactions of the Japanese Society for Artificial Intelligence 32(3), D–G72_1 (2017)
19. The usc human activity dataset. http://wwwscf.usc.edu/~mizhang/datasets.html
20. Wang, W., Liu, H., Yu, L., Sun, F.: Human activity recognition using smart phone embedded sensors: A linear dynamical systems method. In: Neural Networks (IJCNN), 2014 International Joint Conference on. pp. 1185–1190. IEEE (2014)
21. The wisdm dataset. http://www.cis.fordham.edu/wisdm/dataset.php