A Novel Semi-supervised Deep Learning Method for Human Activity Recognition

Human activity recognition (HAR) based on inertial sensors has been investigated for many industrial informatics applications, such as healthcare and ubiquitous computing. Existing methods mainly rely on supervised learning schemes which require large labeled training data. However, labeled data is sometimes difficult to acquire, while unlabeled data is readily available. Thus, we intend to make use of both labeled and unlabeled data with semi-supervised learning for accurate HAR. In this paper, we propose a semi-supervised deep learning approach, using temporal ensembling of Deep Long Short-Term Memory (DLSTM), to recognize human activities with smartphone inertial sensors. With the deep neural network processing, features are extracted for local dependencies in the recurrent framework. Besides, with an ensemble approach based on both labeled and unlabeled data, we can combine together the supervised and unsupervised losses, so as to make good use of unlabeled data which the supervised learning method cannot leverage. Experimental results indicate the effectiveness of our proposed semi-supervised learning scheme, when compared to several state-of-the-art semi-supervised learning approaches.