Click on “Download PDF” for the PDF version or on the title for the HTML version.

If you are not an ASABE member or if your employer has not arranged for access to the full-text, Click here for options.

Food Process Control Based on Sensory Evaluations

Published by the American Society of Agricultural and Biological Engineers, St. Joseph, Michigan

Citation:  Paper number  036166,  2003 ASAE Annual Meeting . (doi: 10.13031/2013.15417)
Authors:   Sasikan Kupongsak, Jinglu Tan
Keywords:   Food process control, neural network, sensory evaluation, set point determination

Sensory evaluation is the ultimate measure of quality for many food products, but automated process control relies on instrumental measurements. The objective of this study was to develop strategies for food process control based on sensory evaluations. Multi-input and multi-output (MIMO) neural networks were used to convert sensory quality targets into process control set points. The MIMO neural networks successfully predicted the instrumental process set points (including manipulatable process variables and instrumentally measured variables) from sensory quality attributes of a rice cake product with an average error less than 2%. The technique was validated by using the predicted set points for manipulatable process variables to produce new rice cake products. The sensory measurements of the new rice cakes from the validation process were close to those defined as the original targets. The results demonstrated the effectiveness of the method.

(Download PDF)    (Export to EndNotes)