KECA for Identifying the Habitats of Chinese Mitten Crab (Eriocheir Sinensis) Based on Aroma Analysis

Abstract

Chinese mitten crabs (Eriocheir Sinensis) are rich in resources, wide varieties, and extensive origins. Crabs in Yangcheng Lake are most famous. However, some businessmen are driven by profits to subvert the market. In this paper, the aroma of 12 crabs of three producer areas was described by using electronic nose, and the difference in crabs' flavor profile between different producing areas was explored. 7 sensors, response data of the electronic nose were analyzed by using kernel entropy component analysis (KECA), principal component analysis (PCA), and linear discriminant analysis (LDA). Results showed that KECA had a better accuracy than PCA and LDA in locality identification. The distinguish effect of electronic nose on the crabs from different areas was overlapped, such as weeping Tai Lake and Gucheng Lake, but Yangcheng Lake crab could be distinguished dramatically from other localities in KECA. Therefore, electronic nose can be used as an important method to identify the crab habitat based on the different flavor profile of crabs.