Abstract
With the development of Internet of Things (IoT), all kinds of sensors appear everywhere in our lives. Sensor-based Human Activity recognition (HAR) as the most common application of IoT system, has attracted attentions from both academia and industry due to the popularity of IoT. In most real-life scenarios, HAR is dynamic. For instance, in the process of classifying the activities, a new class is often encountered. To effectively recognize new activities, we propose a three-stage class incremental temporal-spatial model based on wireless sensor networks for activity recognition. In the first stage, when the new class arrives, rather than using the traditional method to train all the old class data, we design a method based on the recognition score to select part of the old class data as a sample for training, which represents the data distribution of the old class data. In the second stage, we analyze the temporal and spatial characteristics of activity data in combination with physical knowledge, the model extract temporal-spatial features, which further enhances the recognition effect. In the third stage, we avoid the phenomenon of ‘catastrophic forgetting’ of a network by finetuning distillation loss and classification loss. To demonstrate the effectiveness of our proposed model, we conducted comparative experiments using different models on different public datasets. The results showed our proposed model can not only recognize new classes, but also maintain the recognition ability of old classes.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Anguita, D., Ghio, A., Oneto, L., Parra, X., Reyes-Ortiz, J.L.: A public domain dataset for human activity recognition using smartphones. In: 21th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2013, 24–26 April 2013, Bruges, Belgium (2013)
Wannenburg, J., Malekian, R.: Physical activity recognition from smartphone accelerometer data for user context awareness sensing. Syst. Man Cybern. 47(12), 3142–3149 (2017)
Wang, J., Chen, Y., Hao, S., et al.: Deep learning for sensor-based activity recognition: a survey. Pattern Recogn. Lett. 119, 3–11 (2018). S016786551830045X
Plotz, T., Guan, Y.: Deep learning for human activity recognition in mobile computing. Computer 51(5), 50–59 (2018)
Ploetz, T., Hammerla, N., Olivier, P.: Feature learning for activity recognition in ubiquitous computing. In: Proceedings 22nd International Joint Conference Artificial Intelligence (IJCAI 2011), pp. 1729–1734 (2011)
Yang, Q.: Activity recognition: linking low-level sensors to high-level intelligence. In: IJCAI, pp. 20–25 (2009)
Krizhevsky, A., Sutskever, L., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Neural Information Processing Systems (2012)
Cai, Z., Duan, Z., Li, W.: Exploiting multi-dimensional task diversity in distributed auctions for mobile crowdsensing. IEEE Trans. Mobile Comput. 1 (2020)
Yu, L., Chen, L., Cai, Z., et al.: Stochastic load balancing for virtual resource management in datacenters. IEEE Trans. Cloud Comput. 8, 1, (2016)
Duan, Z., Li, W., Cai, Z.: Distributed auctions for task assignment and scheduling in mobile crowdsensing systems. In: 2017 IEEE 37th International Conference on Distributed Computing Systems (ICDCS). IEEE (2017)
Cheng, S., Li, Y., Tian, Z., et al.: A model for integrating heterogeneous sensory data in IoT systems. Comput. Netw. 150, 1–14 (2019)
Cheng, S., Cai, Z., Li, J., et al. Drawing dominant dataset from big sensory data in wireless sensor networks. In: 2015 IEEE Conference on Computer Communications (INFOCOM). IEEE (2015)
Cheng, S., Cai, Z., Li, J., et al.: Extracting kernel dataset from big sensory data in wireless sensor networks. IEEE Trans. Knowl. Data Eng. 29, 1 (2017)
Sarwar, S.S., Ankit, A., Roy, K., et al.: Incremental learning in deep convolutional neural networks using partial network sharing. arXiv: Computer Vision and Pattern Recognition (2017)
Rosenfeld, A.: Incremental learning through deep adaptation. IEEE Trans. Pattern Anal. Mach. Intell. 42, 1 (2018)
Lampert, C.H., Nickisch, H., Harmeling, S., et al.: Learning to detect unseen object classes by between-class attribute transfer. In: Computer Vision and Pattern Recognition, pp. 951–958 (2009)
Feifei, L., Fergus, R., Perona, P., et al.: One-shot learning of object categories. IEEE Trans. Pattern Anal. Mach. Intell. 28(4), 594–611 (2006)
Luo, J., Wu, J., Lin, W., et al.: ThiNet: a filter level pruning method for deep neural network compression. In: International Conference on Computer Vision, pp. 5068–5076 (2017)
Liu, Z., Li, J., Shen, Z., et al.: Learning efficient convolutional networks through network slimming. In: International Conference on Computer Vision, pp. 2755–2763 (2017)
Chen, Z., Chen, Y., Hu, L., et al.: ContextSense: unobtrusive discovery of incremental social context using dynamic bluetooth data. In: Ubiquitous Computing, pp. 23–26 (2014)
Castro, F.M., Marinjimenez, M.J., Guil, N., et al.: End-to-end incremental learning. In: European Conference on Computer Vision, pp. 241–257 (2018)
Li, Y., Li, Z., Ding, L., et al.: SupportNet: solving catastrophic forgetting in class incremental learning with support data. arXiv: Neural and Evolutionary Computing (2018)
Lee, K., Lee, K., Shin, J., et al.: Incremental learning with unlabeled data in the wild. arXiv: Computer Vision and Pattern Recognition (2019)
Kirkpatrick, J., Pascanu, R., Rabinowitz, N.C., et al.: Overcoming catastrophic forgetting in neural networks. Proc. Natl. Acad. Sci. U.S.A. 114(13), 3521–3526 (2017)
Aljundi, R., Babiloni, F., Elhoseiny, M., et al.: Memory aware synapses: learning what (not) to forget. In: European Conference on Computer Vision, pp. 144–161 (2018)
Rebuffi, S., Kolesnikov, A., Sperl, G., et al.: iCaRL: incremental classifier and representation learning. In: Computer Vision and Pattern Recognition, pp. 5533–5542 (2017)
Hu, C., Chen, Y., Peng, X., et al.: A novel feature incremental learning method for sensor-based activity recognition. IEEE Trans. Knowl. Data Eng. 31(6), 1038–1050 (2019)
Chinghu, L., Yuchen, H., Yihan, C., Lichen, F.: Hybrid user-assisted incremental model adaptation for activity recognition in a dynamic smart-home environment. IEEE Trans. Hum. Mach. Syst. 43(5), 421–436 (2013)
Zhelong, W., Ming, J., Yaohua, H., Hongyi, L.: An incremental learning method based on probabilistic neural networks and adjustable fuzzy clustering for human activity recognition by using wearable sensors. IEEE Trans. Inf. Technol. Biomed. Publ. IEEE Eng. Med. Biol. Soc. 16(4) 691–699 (2012)
Li, Y., Li, Z., Ding, L., et al.: SupportNet: solving catastrophic forgetting in class incremental learning with support data. In: Neural and Evolutionary Computing (2018)
Li, X., et al.: Understanding and improving deep neural network for activity recognition. In: MOBIMEDIA (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Ethics declarations
This work was supported by the National Key R&D Program of China under Grant 2018YFB1703403.
Appendix
Appendix
.
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Li, X., Nie, L., Si, X., Zhan, D. (2020). A Class Incremental Temporal-Spatial Model Based on Wireless Sensor Networks for Activity Recognition. In: Yu, D., Dressler, F., Yu, J. (eds) Wireless Algorithms, Systems, and Applications. WASA 2020. Lecture Notes in Computer Science(), vol 12384. Springer, Cham. https://doi.org/10.1007/978-3-030-59016-1_22
Download citation
DOI: https://doi.org/10.1007/978-3-030-59016-1_22
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-59015-4
Online ISBN: 978-3-030-59016-1
eBook Packages: Computer ScienceComputer Science (R0)