A Machine Learning-Based Anomaly Detection Method and Blockchain-Based Secure Protection Technology in Collaborative Food Supply Chain

Abstract

The complexity of the collaborative food supply chain has resulted in the frequent occurrence of food safety incidents, which harm people's health and life. Therefore, the maintenance of food safety has become a key value. This study expects to solve the food safety problem and bring more benefits to people using intelligent systems. To meet the safety needs of the collaborative food supply chain, this study designed a food safety protection system architecture which collects the supply and sales data of various suppliers, as well as the data of equipment used in production. The architecture can carry out anomaly detections with machine learning to make a preliminary judgement on whether a problem has occurred in this batch of food during the transaction, and then implement in-depth anomaly detections with the supplier's equipment to determine the stage at which this problem occurred. The proposed system can help food operators achieve effective food monitoring, prediction, prevention, and improvement, thereby improving food safety.