RGC: Reliable Gesture Classification via Wearables Using GANs-Based Data Augmentation
Han Zhou, Ji Zhao, Yi Cong Gao, Wei Dong · 2021
Gesture-related human-computer interaction systems have been developed with different purposes. Wearable-based gesture recognition is well studied and considered to be effective. However, unexpected body movement of a user, such as walking and turning, is one issue that affects the robustness of classification. Collecting a sufficient dataset for every unexpected movement would be time-consuming and labor-intensive. To reduce the burden on users and address the lack of training data, we proposed RGC, which is a framework for IMU data augmentation. RGC adopts Generative-Adversarial-Networks-based and rotation-based augmentation to enhance the diversity of the dataset, which helps the classifier learn more effective representations for gesture recognition. We collected a dataset of 21120 arm gesture samples under different kinds of unexpected movements to evaluate RGC. The experiments showed that our method provides an 8.8% to 1.1% accuracy improvement for different SOTA classifiers with different original dataset sizes.