Food Safety Assurance: Crystal Strcture Algorithm with Extreme Learning Machine for Early Detection of Contaminated Products

The incidents of food safety series directly affect the safety as well as endanger to people’s health. To ensure food safety, the significant model is to detect the food quality. An actual food inspection risk prediction procedure is complex because the food protection monitoring data contains nonlinear properties, discreteness and high-dimension. For that reason, this paper present a novel crystal structure algorithm with Extreme Learning Machine (CS-ELM) for early discovery of contaminated products. The characteristic data is effectively received by utilizing proposed CS–ELM model. For the given input data, an optimal solution are predicted to develop the food process optimization model along with ELM. The comparative study executes the direct comparison among each characteristic information process. For emerging food safety issues identification, huge reliable food information are provided to obtain the prediction value as well as characteristic information. The better and energetic proposed detection model demonstrates food circulation efficiency with labor cost and storage reduction. Compared to the conventional techniques, proposed minimizes the food safety risk and ensuring quality products.