One of the important factors of high accuracy of deep learning is the sufficient amount of training data. A robust and reliable model needs a vast amount of data to precisely capture the underlying pattern of the data. However, data collection in activity recognition is expensive and time-consuming especially from the elderly people. In this research, we propose a unified deep generative model based on the conditional generative adversarial network (CGAN). The proposed model is able to generate verisimilar sensor data of different activities using a single model. The generated data allows for data augmentation in HAR classification problem to improve its recognition accuracy. Interested readers are referred to [1] for more details.
[1] M. H. Chan, M. H. M. Noor, “A Unified Generative Model using Generative Adversarial Network for Activity Recognition”, Journal of Ambient Intelligence and Humanized Computing, 2020, doi,pdf,read