Abstract: Abstract: In recent years, many sensor models based on LoRa devices have verified the long-distance sensing potential of LoRa devices, but the use of feature-blurred LoRa wireless signals to identify human activities still requires further research. This paper analyzes the propagation law of LoRa signals affected by human activities, and proposes a LoRa signal processing method to extract signal change features. Subsequently, data are collected to create two LoRa datasets that record human activities, and the proposed method is tested through advanced deep learning models.  The accuracy of recognizing activity types, activity roles in a room, activity roles, and activity rooms in four rooms reaches over 90%. Compared to the method of using convolutional recurrent neural networks for direct training, it is also more time-saving and spatial resource-saving.

Key words: wireless sensing, long distance sensing, human activity recognition, lora signal feature extraction, deep learning