A CNN-based Fog Node Data Processing Method and Application in Wearable Heart Detection Equipment

Abstract

Abstract. With the amount increase of sensors and collection data, a large number of low-value data will be directly uploaded to the cloud server without screening in the application process of the Internet of Things, which will waste a lot of network resources. This paper proposes an intelligent processing method of Internet of Things data based on fog computing. Firstly, fog nodes are introduced into the sensor network in the edge of the Internet of Things, and then deep neural network is used as the data processing method in the fog nodes to conduct preliminary classification and screening of the sensor data collected in the edge network. Finally, the processed data is sent to the cloud according to the demand. By comparison, using fog nodes to screen data can greatly reduce the amount of data transmission and meet the needs of data analysis, which is conducive to reducing the cost of the Internet of Things.