A Visual Variability and Visuo‐Tactile Coordination Inspired Child Adaptation Mechanism for Wearable Age Group Recognition and Activity Recognition

Not all wearable fitness devices are suitable for children. Due to the decay of activity recognition accuracy and exercise requirement variety caused by the physical differences between adults and children, devices developed for adults cannot provide appropriate exercise guidance to children. Considering the complexity and time-consuming nature of developing a new children-specific model, this article proposes a child adaptation mechanism that can be integrated into current adult wearable devices. Two algorithms using unlabeled children's data for age group recognition and activity recognition inspired by the visual variability in cognitive process and visuo-tactile coordination phenomenon in cortical plasticity are proposed. During an experiment on 30 adults and children, the age group recognition algorithm achieves 93.33% recognition accuracy, and the activity recognition algorithm achieves 88.57% recognition accuracy. This is an 11.16% improvement compared with the baseline and 2.87-4.1% improvement compared with the state-of-the-art transfer learning or self-adaptation algorithms. The proposed mechanism ameliorates current wearable devices with minimum cost to make them suitable for children and can serve as an alternative to help children learn healthy exercise habits. It is hoped that the work can draw the attention of academia to vulnerable groups, including children, to build a friendlier artificial intelligence network.