Wireless Sensing With Deep Spectrogram Network and Primitive Based Autoregressive Hybrid Channel Model
This work addresses the problem of high data collection costs and limited performance in wireless sensing for human motion recognition, offering an incremental improvement with a new channel model and network architecture.
The paper tackled human motion recognition using wireless sensing by proposing a deep spectrogram network (DSN) to improve performance and a primitive-based autoregressive hybrid (PBAH) channel model to generate training data efficiently. The results showed that the PBAH model closely matched real data and the DSN achieved significantly smaller recognition error compared to CNNs.
Human motion recognition (HMR) based on wireless sensing is a low-cost technique for scene understanding. Current HMR systems adopt support vector machines (SVMs) and convolutional neural networks (CNNs) to classify radar signals. However, whether a deeper learning model could improve the system performance is currently not known. On the other hand, training a machine learning model requires a large dataset, but data gathering from experiment is cost-expensive and time-consuming. Although wireless channel models can be adopted for dataset generation, current channel models are mostly designed for communication rather than sensing. To address the above problems, this paper proposes a deep spectrogram network (DSN) by leveraging the residual mapping technique to enhance the HMR performance. Furthermore, a primitive based autoregressive hybrid (PBAH) channel model is developed, which facilitates efficient training and testing dataset generation for HMR in a virtual environment. Experimental results demonstrate that the proposed PBAH channel model matches the actual experimental data very well and the proposed DSN achieves significantly smaller recognition error than that of CNN.