Comparative Study of Gesture Recognition Based on Accelerometer and Photoplethysmography Sensor for Gesture Interactions in Wearable Devices

With the goal of implementing gesture interaction applications on wearable devices, this paper presents a comparative study on hand gesture recognition based on accelerometer (ACC) and photoplethysmography (PPG) sensors. Research is conducted on 14 hand gestures involving wrist and finger movements under four motion scenarios: sitting, walking, jogging, and running. When the participants perform the hand gestures, four channels of PPG signals and 3D ACC signals are collected. To effectively extract gesture repetitions from the continuous movements, a segmentation method based on PPG signal and motion noise is employed. The experimental results verify that the PPG signal is more suitable for implementing gesture interactions on wearable devices. At first, the signal-to-noise ratio analysis demonstrates that the ACC signals are much more affected by motion noise than the PPG signals. Then, the hand gesture recognition results in the four different motion scenarios demonstrate that the accuracies of both the ACC and PPG signals decrease with the intensity of body movement; however, the decrease of the PPG signals is significantly lower than that of the ACC signals, especially for finger-related gestures. A hand gesture recognition experiment with ratios of the samples between the training set and test set from 1:9 to 8:2 demonstrates that the PPG signal also has advantages in regards to reducing user's training burden. Moreover, this research verifies that the green PPG signal is not the best choice for the implementation of gesture interactions. The research results provide a reliable foundation for promoting the development of gesture-based interactions in wearable devices.