Generative Adversarial Networks Based on Edge Computing With Blockchain Architecture for Security System

Abstract

This paper proposes a face recognition for security system based on artificial intelligence and edge computing with a limited dataset. Generative adversarial networks (GANs) are used to manipulate the dataset in order to overcome the accuracy issue of the limited dataset. The average accuracy of GANs outperforms the limited dataset up to 92.79%. Edge computing is used to overcome a high latency of cloud computing with Jetson Nano board, which produces an average of 8.8 frame-per-second. Furthermore, the detected face will make a payment using a smart contract to the blockchain network with low static difficulty to open a gate or door's lock. In comparison, a low static difficulty outperforms the Proof-of- Work consensus algorithm in terms of transaction time around 33-39 milliseconds.