GTSNet: Flexible architecture under budget constraint for real-time human activity recognition from wearable sensor

Abstract

Human activity recognition is an essential task for human-centered intelligent systems such as healthcare and smart vehicles, which can be accomplished by analyzing time-series signals collected from sensors in wearable devices. In these applications, real-time response is vital because prompt action is necessary for urgent events such as an elderly person falling or driving while drowsy. Although recurrent neural networks have been widely used owing to their temporal modeling capabilities, recent studies have focused on convolutional neural networks (CNNs) that are suitable for real-time responses because they incur lower computational costs. However, CNNs with a manual design may fail to achieve optimal accuracy due to varying computational budgets with applications or devices. In this paper, we propose a novel design framework that uses a mathematical approach to derive a CNN architecture suitable for a given computational budget. As a result, we introduce a grouped temporal shift network (GTSNet) with the network architecture to be flexibly modified by predefining the theoretical computation cost. We demonstrate the effectiveness of our framework in experiments, achieving the best performance for well-known public benchmark datasets under limited computational budgets. The source codes of the GTSNet are publicly available at https://github.com/jgpark92/GTSNet.