Expanding the Horizons of 1-D Tasks: Leveraging 2-D Convolutional Neural Networks Pretrained by ImageNet

Sensor-based human activity recognition (HAR) plays a pivotal role in the Internet of Things (IoT). Due to the low cost, low power consumption, and broad applicability of sensor devices, the integration of HAR with IoT has become increasingly imminent. Deep learning (DL)-based HAR methods, with their capability for the automatic feature extraction, are applied in our daily lives. However, obtaining a substantial amount of the labeled data for the HAR tasks remains a challenge. Although transfer learning (TL) offers a viable solution in the HAR domain, we lack the large-source domain data sets akin to ImageNet. In response to this challenge, our study introduces an innovative cross-modal TL strategy. By compressing the ImageNet parameters, which has allowed us to transfer the robust capabilities of the 2-D models into the 1-D domain. This was achieved by employing various DL architectures, thereby validating the robustness of our method. Furthermore, by introducing the hyperparameter $\alpha $ and compressing the weight magnitude in TL, we further investigated our proposed method to enhance its universality. This is evidenced by the positive results obtained from the HAR benchmark data sets. We also expanded our analysis to include results from different sensor types, affirming the adaptability and effectiveness of our TL strategy across diverse contexts. These experiments have not only reinforced our initial findings but have also widened the understanding of how our approach can be applied to a vast array of the IoT-based scenarios and sensor data, opening up new avenues for research and application in the field.