Abstract
In the digital era, time-series data is pervasive to various applications and domains such as robotics, healthcare, finance, sport, etc. The inertial measurement unit (IMU) sensor is one of the popular devices collecting time-series data. Together with deep neural network implementation, this results in facilitating advancement in time series data analysis. However, the classical problem for the deep neural network is that it requires a vast amount of data which causes difficulty in the development and analysis process. Thus, we hypothesize that this problem can be avoided by combining data from many subjects that perform the same common tasks to get a larger amount of data. The consequence problem is that this decreases the overall classification accuracy. To tackle this, optimization-based meta-learning algorithms were selected, which are Reptile and model-agnostic meta-learning (MAML). The differences between Reptile and MAML are they use different rules for update gradient descent and differentiating through the optimization process. Leveraging their pre-existing meta-parameter weight before fine-tuning results in preferable accuracy for the existing amount of data, the figure is 89.65% for MAML and 78.38% for Reptile. To our knowledge, this is the first time comparing joint training with the meta-learning model, specifically, Reptile, and MAML for human activity classification from IMU sensors data. Experiment results show the superiority of classification accuracy from METAHACI proposed compare to joint training and simple CNNs.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Chen, T., et al.: Unsupervised anomaly detection of industrial robots using sliding-window convolutional variational autoencoder. IEEE Access 8, 47072–47081 (2020)
Kaushik, S., et al.: AI in healthcare: time-series forecasting using statistical, neural, and ensemble architectures. Front. Big Data 3, 4 (2020)
Xu, Z., et al.: Prediction research of financial time series based on deep learning. Soft Comput. 1–18 (2020)
Rantalainen, T., et al.: Jump height from inertial recordings: a tutorial for a sports scientist. Scand. J. Med. Sci. Sports 30(1), 38–45 (2020)
Mukhopadhyay, S.C.: Wearable sensors for human activity monitoring: a review. IEEE Sens. J. 15(3), 1321–1330 (2014)
Hou, C.: A study on IMU-based human activity recognition using deep learning and traditional machine learning. In: 5th International Conference on Computer and Communication Systems (ICCCS) 2020, Shanghai, pp. 225–234. IEEE (2020)
Vanschoren, J.: Meta-learning: a survey. arXiv preprint arXiv:1810.03548 (2018)
Nichol, A., et al.: On first-order meta-learning algorithms. arXiv preprint arXiv:1803.02999 (2018)
Finn, C., at al.: Model-agnostic meta-learning for fast adaptation of deep networks. arXiv preprint arXiv:1703.03400 (2017)
Wang, J., et al.: Deep learning for sensor-based activity recognition: a survey. Pattern Recogn. Lett. 119, 3–11 (2019)
Jatoba, L.C., et al.: Context-aware mobile health monitoring: evaluation of different pattern recognition methods for classification of physical activity. In: 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society 2008, Vancouver, pp. 5250–5253. IEEE (2008)
Walse, K.H., Dharaskar, R.V., Thakare, V.M.: PCA based optimal ANN classifiers for human activity recognition using mobile sensors data. In: Satapathy, S.C.C., Das, S. (eds.) Proceedings of First International Conference on Information and Communication Technology for Intelligent Systems: Volume 1. SIST, vol. 50, pp. 429–436. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-30933-0_43
Ha, S., et al.: Multi-modal convolutional neural networks for activity recognition. In: IEEE International Conference on Systems, Man, and Cybernetics 2015, Kowloon, pp. 3017–3022. IEEE (2015)
Almaslukh, B., et al.: An effective deep autoencoder approach for online smartphone-based human activity recognition. Int. J. Comput. Sci. Netw. Secur. 17(4), 160–165 (2017)
Inoue, M., et al.: Deep recurrent neural network for mobile human activity recognition with high throughput. Artif. Life Robot. 23(2), 173–185 (2018)
Wang, Q., et al.: MetaSearch: incremental product search via deep meta-learning. IEEE Trans. Image Process. 29, 7549–7564 (2020)
Reiss, A., et al.: Introducing a new benchmarked dataset for activity monitoring. In: 16th International Symposium on Wearable Computers 2012, Newcastle, pp. 108–109. IEEE (2012)
Reiss, A., et al.: Creating and benchmarking a new dataset for physical activity monitoring. In: Proceedings of the 5th International Conference on PErvasive Technologies Related to Assistive Environments 2012, Heraklion, pp. 1–8. PETRA (2012)
Anguita, D., et al.: A public domain dataset for human activity recognition using smartphones. In: ESANN 2013 Proceedings, European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning 2013, Belgium, p. 3. ESANN (2013)
Shoaib, M., et al.: Fusion of smartphone motion sensors for physical activity recognition. Sensors 16(4), 10146–10176 (2014)
Acknowledgement
Thank you Vidyasirimedhi Institute of Science and Technology (VISTEC) for supporting. Thank you very much to the anonymous faculty member of VISTEC for supervision and intellectual discussions. Thank you very much to Dr. Stephen John Turner from the School of Information Science and Technology at VISTEC for professional-suggestions. Thank you very much to Mr. Pichayoot Ouppaphan for technical help. Also, thank you very much to Dr. Chotiluck Leelakittisin for the intellectual suggestions.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Leelakittisin, B., Sun, F. (2021). METAHACI: Meta-learning for Human Activity Classification from IMU Data. In: Sun, F., Liu, H., Fang, B. (eds) Cognitive Systems and Signal Processing. ICCSIP 2020. Communications in Computer and Information Science, vol 1397. Springer, Singapore. https://doi.org/10.1007/978-981-16-2336-3_9
Download citation
DOI: https://doi.org/10.1007/978-981-16-2336-3_9
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-2335-6
Online ISBN: 978-981-16-2336-3
eBook Packages: Computer ScienceComputer Science (R0)