The freshness on four selected types of fish (Red Snapper

Gurnard

Tarakihi and Trevally) which are the most common fish in the New Zealand market was investigated. A portable Cyranose 320 Enose was used in our experiments under the same laboratory condition. It converted the odour of four selected types of fish to smell prints over days 1

2

5

6

7

8

9

and 10 after catching the fish (no data was collected on days 3 and 4). Approximately 2 000 samples were collected by each sensor during each process. About 2 048 000 data samples ［4 (fish) × 8 (days) ×32 (sensors) ×2 000 (samples) =2 048 000］ were obtained. Extracted features from the Enose sensors and artificial neural network （ANN）were used to assess the freshness of the fish by classifying the smell print data according to the day of data collection. The proposed system has been successful in identifying the number of days after catching the fish with an accuracy of up to 91%. The result showed that the proposed network architecture proved very suitable for fish freshness assessment.