WaveHAR: Learning Wavelet Representation for Wearable Human Activity Recognition

In rapidly evolving the Internet-of-Things (IoT) industry, human activity recognition (HAR) technology based on wearable sensors always plays a pivotal role. Deep learning models, especially convolutional neural networks (CNNs) have achieved remarkable success in the HAR domain. However, the existing research still faces with two major limitations: 1)small-kernel CNNs struggle to establish long-range dependency relationships when extracting motion features and 2)traditional convolutional layers tend to focus on high-frequency information, neglecting the low-frequency component, which nonetheless contains rich feature information. Although some studies have addressed the limitations of small-kernel CNNs by adopting large-kernel CNNs, leading to significant performance improvements, the issues of over-parametrization and performance saturation associated with large-kernel CNNs cannot be ignored. To tackle these challenges, we introduce a novel method that expands the receptive field by cascading wavelet decompositions at multiple levels. This process enhances the model’s ability to capture low-frequency information while complementing traditional convolutional layers that primarily focus on high-frequency features. While the wavelet transform (WT) is a well-established tool in signal processing, how to apply it to extend the receptive field in wearable sensor-based HAR has been rarely explored. Unlike the previous wavelet research, this article mainly targets the expansion of the receptive field in the low-frequency domain of small-kernel convolutional layers, aiming to enhance the activity recognition performance. To thoroughly evaluate the proposed method, we conducted extensive experiments on multiple public datasets and compared it against several competitive state-of-the-art baselines. The experimental results consistently demonstrate that our method exhibits a clear advantage in a variety of activity recognition tasks, validating the effectiveness and efficiency of this approach.