Online Learning of Wearable Sensing for Human Activity Recognition

This article presents a novel semisupervised learning method for wearable sensors to recognize human activities. The proposed method is termed a tri-very fast decision tree (VFDT). The proposed method is a more efficient version of the Hoeffding tree and three VFDTs are generated from the original labeled example set and refined using unlabeled examples. Based on the heuristic growth characteristics of VFDT, a tri-training framework is proposed which uses unlabeled data to update the model without labeled data. This significantly reduces the computational time and storage of the data processing. In addition, the proposed method is embedded into wearable devices for online learning, while the test data flow is regarded as the unlabeled data to update the model. The experiment collects data stream of 16 min with motion state switching frequently while the wearable devices recognize motions in real time. An experimental comparison has also been undertaken for performance evaluation between the wearable and computation using a desktop computer. The obtained results show that only minor difference in terms of the f 1-score rendered by the proposed method online or offline. This is a prominent characteristic for wearable computing within the Internet of Things (IoT). Data set can be linked as https://faculty.uestc.edu.cn/gaobin/zh_CN/lwcg/153392/list/index. htm.

Automated summary

This article presents a novel semisupervised learning method, VFDT, for wearable sensors to recognize human activities. The method efficiently reduces computational time and storage by generating three VFDTs and using unlabeled examples. The method is embedded into wearable devices for online learning and shows similar performance as offline learning.