TinyCSI: A Rapid Development Framework for CSI-based Sensing Applications

Abstract

Channel State Information (CSI)-based wireless sensing has recently attracted extensive attention from both academia and industry. However, it is still challenging and time-consuming to develop a CSI-based sensing application due to the use of complex signal processing algorithms and the requirements of accuracy and responsiveness. In this paper, we present TinyCSI, a rapid development framework for CSI-based sensing applications. With TinyCSI, developers only need to write a main script to determine the CSI collection settings and a callback function to process the collected CSI signals using the well-abstracted Matlab/C-based library, without dealing with the connection/transmission details of the sensing nodes. To achieve fast performance tuning, TinyCSI also provides three working modes for different deployment requirements: a remote mode for fast iteration of the sensing algorithms and their parameters, an efficient mode for making full use of computing resources and improving sensing responsiveness, and a standalone mode for offline running sensing systems on individual nodes. We implement three representative demos and conduct real-world user studies to show the workflows and benefits of TinyCSI. Experimental results show that TinyCSI helps reduce the lines of code significantly compared to the original implementation. More importantly, the efficient mode can generate an optimal computing resource allocation solution and significantly improve the sensing responsiveness.