Comparing the placement of two arm-worn devices for recognizing dynamic hand gestures

Dynamic hand gestures become increasingly popular as touch-free input modality for interactive systems. There exists a variety of arm-worn devices for recognition of hand gestures, which differ not only in their capabilities, but also in their positioning on users' arms. These differences in positioning might influence how well gestures are recognized, leading to different gesture recognition accuracies. In this paper we therefore investigate the effect of device placement on dynamic hand gesture recognition accuracy. We consider devices being strapped to the forearm on two positions: the wrist and below the elbow. These positions represent smart watches being worn on the wrist and devices with EMG sensors for the detection of static hand gestures (e.g spreading the fingers) being worn right below the elbow. Our initial hypothesis is that wrist-worn devices will have better recognition accuracy, caused by higher acceleration values of a bigger action radius with dynamic hand gestures on the wrist. We conduct a comparative study using an LG G Watch and Thalmic Labs' Myo armband, for which we record a total of 12960 gesture samples of eight simple dynamic gestures in three different variants with eight participants. We evaluate a potential difference in gesture recognition accuracies using different feature sets and classifiers. Although recognition accuracies for wrist-worn devices seem higher, the difference is not statistically significant due to substantial variations in accuracy across participants. We thus cannot conclude that different positions of gesture recording devices on the lower arm have significant influence or correctly recognizing arm gestures.