Linear Regression, Neural Network and Induction Analysis to Determine Harvesting and Processing Effects on Surimi Quality

Abstract

ABSTRACT Harvesting and processing input combinations and product quality attributes for the Pacific whiting surimi industry were collected and analyzed. Multiple linear regression, neural networks, and M5‐induction were used to determine significant variables in the industry. Significant factors included variables intrinsic to the fish (moisture content, salinity, pH, length, weight) and processing variables (processing time, storage temperature, harvest date, wash time, wash ratios). Most variables were highly interactive and nonlinear. Information derived from these models have implications for production and management decisions.