The discrimination of fluorescence spectra of phytoplankton for environment protection based on the PCA and SVM

Issues of environmental protection and sustainable development are gaining an increasing importance in everyday life, and nowhere is this more than in the field of Materials Science and Engineering. The alga is the most common phytoplankton, identifying them can estimate the community structure and distribute status of ecosystem in the sea area and realize the inspecting and comprehensive father of sea. In this paper, the three dimension fluorescence spectra and principal component analysis method is combined to identify the ocean phytoplankton. Aiming at the east China sea, adopt the selection of common seaweed three-dimensional fluorescenCe spectrum of first principal component scores spectrum as bacillariophyta and pyrrophyta identification features diatoms and spectrum, established the phytoplankton fluorescence features spectrum library. On this basis, the SVM classifier is used to identify the kinds of the phytoplankton. The accuracy of the experimental results recognition is for 95%.