Application of Hyper-Spectral Imaging Technique for the Detection of Total Viable Bacteria Count in Pork
The total viable count (TVC) of bacteria is an important indicator of meat spoilage. Therefore the objective of the present study was to explore the potential of the hyper-spectral imaging technique in connection with the least square support vector machines (LS-SVMs) for predicting the TVC of pork. In order to simplify the TVC prediction model, stepwise discrimination method was used for the original spectrum, 1-st order and 2-nd derivative spectrum respectively to select the optimal wavelengths which can characterize the gross change trend of TVC, and some key characteristics such as the (overlap) peak and turning points of those spectrum were considered also. Then we got eight optimal wavelengths (477, 509, 540, 552, 560, 609, 720 and 772 nm) and then we used the corresponding reflective spectrum data at those optimal wavelengths to construct the TVC prediction model. The ultimate model was able to predict the TVC with R2=0.9236, RMSEV=0.3279, which indicates the feasibility of using the hyperspectral imaging technique for the detection of total viable bacteria count in pork.
Total Viable Count of Bacteria (TVC) Hyper-Spectral Imaging Technique Optimal Wavelength Least Square Support Vector Machines (LS-SVMs) Pork
Wei Wang Yankun Peng Hui Huang Jianhu Wu
College of Engineering, China Agricultural University, Beijing, 100083, P. R. China
国际会议
南昌
英文
1024-1030
2010-10-22（万方平台首次上网日期，不代表论文的发表时间）