The National Institute of Advanced Industrial Science and Technology (AIST) and the Hokkaido Industrial Technology Center have developed a sensing technology that determines the freshness of fish meat from its odor, using yellowtail as a model.
It is a non-destructive test that does not require the collection of fish meat because it targets fish odors. Analyze the odors of fish meat for each freshness level, and create a simulated freshness index gas based on the results. The measurement results of the indicator gas were used as learning data, and machine learning was used to determine the freshness from the actual odor of the fish meat.
In order to expand the export volume of Japanese marine products, it is necessary to have indicators that objectively guarantee quality and methods of measuring them. Currently, the K value is proposed as a freshness index for fresh marine products. However, the K value requires the collection of fish meat. Also, chemical measurements for deriving the K value require special skills and a certain amount of time.
Therefore, the development of a new sensing technology that can easily determine the freshness has been demanded.