Abstract
Approaches to Human Activity Recognition are typically data driven, classifying activities performed by humans based on low level sensor data from ambient and/or wearable sensors. Collecting this data is a challenging task, being time consuming to collect and label the data, whilst also being expensive to deploy the acquisition systems. The use of synthetic data offers a potential solution to these challenges. This research is based on generating synthetic data, with the aim of improving the performance of HAR. The data used in this study is generated based on a well-known open dataset, Mobile Health (mHealth) dataset, which was collected with wearable sensors for 12 activities. Firstly, the real data was pre- processed and classification methods such as Decision Tree, Gaussian Naïve Bayes, and Support Vector Machine were applied. Three different synthetic generation techniques Synthetic Data Vault Probabilistic Autoregressive (SDV-PAR), Time-series Generative Adversarial Network (TGAN), and Conditional Tabular Generative Adversarial Network (CTGAN) were subsequently used. In comparison to real data, which achieves an accuracy score of 0.9725, the synthetic data generated by CTGAN achieved an accuracy score of 0.8373.
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
Notes
- 1.
This research has been partially funded by the ARC (Advanced Research and Engineering Centre) project, funded by PwC and Invest Northern Ireland.
References
Pires, I.M., Hussain, F., Marques, G., Garcia, N.M.: Comparison of machine learning techniques for the identification of human activities from inertial sensors available in a mobile device after the application of data imputation techniques. Comput. Biol. Med. 135, 104638 (2021)
Murtaza, H., Ahmed, M., Khan, N.F., Murtaza, G., Zafar, S., Bano, A.: Synthetic data generation: state of the art in health care domain. Comput. Sci. Rev. 48, 100546 (2023)
DeOliveira, J., Gerych, W., Koshkarova, A., Rundensteiner, E., Agu, E.: HAR-CTGAN: a mobile sensor data generation tool for human activity recognition. In: IEEE International Conference on Big Data (Big Data), pp. 5233–5242 (2022)
Dahmen, J., Cook, D.: SynSys: a synthetic data generation system for healthcare applications. Sensors (Basel), 19(5). 1181 (2019)
Rajendran, M., Tan, C.T., Atmosukarto, I., Ng, A.B., See, S.: SynDa: a novel synthetic data generation pipeline for activity recognition. In: IEEE International Symposium on Mixed and Augmented Reality Adjunct (ISMAR-Adjunct), pp. 373–377 (2022)
Qu, L., Wang, Y., Yang, T., Sun, Y.: Human activity recognition based on WRGAN-GP-synthesized micro-doppler spectrograms. IEEE Sens. J. 22(9), 8960–8973 (2022)
Jimale, A.O., Mohd Noor, M.H.: Fully connected generative adversarial network for human activity recognition. IEEE Access. 10, 100257–100266 (2022)
Anjum, F., Alam, S., Bahadur, E.H., Muhammad Masum, A.K., Rahman, M.Z.: Deep learning for depression symptomatic activity recognition. In: 2022 International Conference on Innovations in Science, Engineering and Technology (ICISET), pp. 510–515 (2022)
Anowar, F., Sadaoui, S., Selim, B.: Conceptual and empirical comparison of dimensionality reduction algorithms (PCA, KPCA, LDA, MDS, SVD, LLE, ISOMAP, LE, ICA, t-SNE). Comput. Sci. Rev. 40(100378), 100378 (2021)
Banos, O., et al.: mHealthDroid: a novel framework for agile development of mobile health applications. In: Pecchia, L., Chen, L.L., Nugent, C., Bravo, J. (eds.) Ambient Assisted Living and Daily Activities. IWAAL 2014. LNCS, vol. 8868, 91–98. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-13105-4_14
Banos, O., et al.: Design, implementation and validation of a novel open framework for agile development of mobile health applications. Biomed. Eng. Online, 14(Suppl 2), p. S6 (2015)
UCI Machine Learning Repository: MHEALTH Dataset Data Set. http://archive.ics.uci.edu/ml/datasets/mhealth+dataset
sklearn.feature_selection.mutual_info_classif. https://scikit-learn.org/stable/modules/generated/sklearn.feature_selection.mutual_info_classif.html
Zhang, K., Patki, N., Veeramachaneni, K.: Sequential models in the synthetic data vault. arXiv preprint arXiv:2207.14406 (2022)
Yoon, J., Jarrett, D., van der Schaar, M.: Time-series Generative Adversarial Networks. In: Advances in neural information processing systems, vol. 32 (2019)
Kalyan, V., Xu, L., Skoularidou, M., Cuesta-Infante, A.: Modeling tabular data using conditional GAN. In: Advances in neural information processing systems, vol. 32 (2019)
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Liaquat, M., Nugent, C., Cleland, I. (2023). Using Synthetic Data to Improve the Accuracy of Human Activity Recognition. In: Bravo, J., Urzáiz, G. (eds) Proceedings of the 15th International Conference on Ubiquitous Computing & Ambient Intelligence (UCAmI 2023). UCAmI 2023. Lecture Notes in Networks and Systems, vol 842. Springer, Cham. https://doi.org/10.1007/978-3-031-48642-5_16
Download citation
DOI: https://doi.org/10.1007/978-3-031-48642-5_16
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-48641-8
Online ISBN: 978-3-031-48642-5
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)