Abstract
In this work we present a new algorithm for multivariate time-series classification. On multivariate time-series of features we train multi-class, multi-channel CNNs to model sequential data. The multi-channel CNNs are trained on time-series drawn with replacement from a pool of augmented time-series. The features extracted by such bagging meta-estimators are used to train SVM classifiers focusing on hard samples that are close to the decision boundary and multi-class logistic regression classifiers returning well calibrated predictions by default. The recognition is done by a soft voting-based ensemble, built on SVM and logistic regression classifiers. We demonstrate that despite limited amount of training data, it is possible to learn sequential features with highly discriminative power. The time-series were extracted in tasks including classification of human actions on depth maps only. The experimental results demonstrate that on MSR-Action3D dataset the proposed algorithm outperforms state-of-the-art depth-based algorithms and attains promising results on UTD-MHAD dataset.
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
Liang, B., Zheng, L.: A survey on human action recognition using depth sensors (2015)
Guo, K., Ishwar, P., Konrad, J.: Action recognition from video using feature covariance matrices. IEEE Trans. Image Process. 22(6), 2479–2494 (2013)
Li, W., Zhang, Z., Liu, Z.: Action recognition based on a bag of 3D points (2010)
Chen, C., Jafari, R., Kehtarnavaz, N.: UTD-MHAD: a multimodal dataset for human action recognition utilizing a depth camera and a wearable inertial sensor, September 2015
Shotton, J., et al.: Real-time human pose recognition in parts from single depth images. Commun. ACM 56(1), 116–124 (2013)
Wu, H., Ma, X., Li, Y.: Hierarchical dynamic depth projected difference images-based action recognition in videos with convolutional neural networks. Int. J. Adv. Robot. Syst. 16(1) (2019)
Yang, X., Zhang, C., Tian, Y.L.: Recognizing actions using depth motion maps-based histograms of oriented gradients (2012)
Xia, L., Aggarwal, J.: Spatio-temporal depth cuboid similarity feature for activity recognition using depth camera (2013)
Zheng, Y., Liu, Q., Chen, E., Ge, Y., Zhao, J.L.: Time series classification using multi-channels deep convolutional neural networks. In: Li, F., Li, G., Hwang, S., Yao, B., Zhang, Z. (eds.) WAIM 2014. LNCS, vol. 8485, pp. 298–310. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-08010-9_33
Zheng, Y., Liu, Q., Chen, E., Ge, Y., Zhao, J.L.: Exploiting multi-channels deep convolutional neural networks for multivariate time series classification. Front. Comput. Sci. 10(1), 96–112 (2016)
Breiman, L.: Bagging predictors. Mach. Learn. 24(2), 123–140 (1996)
Ho, T.K.: The random subspace method for constructing decision forests. IEEE Trans. Pattern Anal. Mach. Intell. 20(8), 832–844 (1998)
Panov, P., Džeroski, S.: Combining bagging and random subspaces to create better ensembles. In: R. Berthold, M., Shawe-Taylor, J., Lavrač, N. (eds.) IDA 2007. LNCS, vol. 4723, pp. 118–129. Springer, Heidelberg (2007). https://doi.org/10.1007/978-3-540-74825-0_11
Wang, P., Li, W., Gao, Z., Zhang, J., Tang, C., Ogunbona, P.: Action recognition from depth maps using deep convolutional neural networks. IEEE Trans. Hum.-Mach. Syst. 46(4), 498–509 (2016)
Xia, L., Chen, C.C., Aggarwal, J.: View invariant human action recognition using histograms of 3D joints (2012)
Kamel, A., Sheng, B., Yang, P., Li, P., Shen, R., Feng, D.: Deep convolutional neural networks for human action recognition using depth maps and postures. IEEE Trans. Syst. Man Cybern.: Syst. 49(9), 1806–1819 (2019)
Wang, P., Li, W., Li, C., Hou, Y.: Action recognition based on joint trajectory maps with convolutional neural networks. Knowl.-Based Syst. 158, 43–53 (2018)
Hou, Y., Li, Z., Wang, P., Li, W.: Skeleton optical spectra-based action recognition using convolutional neural networks. IEEE Trans. Circuits Syst. Video Technol. 28(3), 807–811 (2018)
Wang, P., Wang, S., Gao, Z., Hou, Y., Li, W.: Structured images for RGB-D action recognition (2017)
Wu, Y.: Mining actionlet ensemble for action recognition with depth cameras (2012)
Acknowledgment
This work was supported by Polish National Science Center (NCN) under a research grant 2017/27/B/ST6/01743.
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
Treliński, J., Kwolek, B. (2020). Ensemble of Multi-channel CNNs for Multi-class Time-Series Classification. Depth-Based Human Activity Recognition. In: Nguyen, N., Jearanaitanakij, K., Selamat, A., Trawiński, B., Chittayasothorn, S. (eds) Intelligent Information and Database Systems. ACIIDS 2020. Lecture Notes in Computer Science(), vol 12033. Springer, Cham. https://doi.org/10.1007/978-3-030-41964-6_39
Download citation
DOI: https://doi.org/10.1007/978-3-030-41964-6_39
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-41963-9
Online ISBN: 978-3-030-41964-6
eBook Packages: Computer ScienceComputer Science (R0)