Proposed framework for applying data mining techniques to detect key performance indicators for food deterioration

Abstract

One of the most prosperous domains that Data mining accomplished a great progress is Food Security and safety. Some of Data mining techniques studies applied several machine learning algorithms to enhance and traceability of food supply chain safety procedures and some of them applying machine learning methodologies with several feature selection methods for detecting and predicting the most significant key performance indicators affect food safety. In this research we proposed an adaptive data mining model applying nine machine learning algorithms (Naive Bayes, Bayes Net Key -Nearest Neighbor (KNN), Multilayer Perceptron (MLP), Random Forest (RF), Support Vector Machine (SVM), J48, Hoeffding tree, Logistic Model Tree) with feature selection wrapper methods (forward and backward techniques) for detecting food deterioration’s key performance indicators. Therefore, results before and after applying wrapper feature selection methods have been compared, analyzed, and interpreted. In conclusion the proposed model applied effectively and successfully detected the most significant indicators for meat safety and quality with the aim of helping farmers and suppliers for being sure of delivering safety meat for consumer and diminishing the cost of monitoring meat safety.