Evaluation of AI-based Smart-Sensor Deployment at the Extreme Edge of a Software- Defined Network

Abstract

The introduction of AI-based smart-sensors on the network might suppose stringent requirements for the network edge, including the necessity to process real-time video feeds. Moreover, the introduction of vehicular communications allows the multiple location placement of necessary computational processes. To this end, we have proposed an AI-based smartsensor solution that is able to be deployed at the extreme edge of the network (i.e., on the vehicle). The architecture for the connected vehicle is presented and accuracy results are provided for the proposed smart-sensor.