DeepWiSim

Abstract

Deep learning (DL) has been used for wireless signal analysis in many applications, e.g., indoor localization. By collecting measurement data of wireless signals from the environment, DL models can be trained to accurately predict the change of signal characteristics. However, constructing high-quality DL training data from a real experiment environment is often labor-intensive and time-consuming, which is the biggest obstacle to applying the newest DL model to wireless network research. To address such issues, we present DeepWiSim, a ray-tracing-based wireless signal simulator that automates the DL process from data generation to model training and evaluation. The demonstration shows that DeepWiSim can efficiently generate high-quality simulated wireless signal measurement data and simultaneously train and evaluate the DL model.