Monitoring of straw solid-state fermentation based on NIR and one-class support vector machine

作者：Jiang Hui; Liu Guohai^*; Mei Congli; Xiao Xiahong; Yu Shuang; Ding Yuhan

来源：Transactions of the Chinese Society for Agricultural Machinery, 2012, 43(10): 114-117+166.

DOI：10.6041/j.issn.1000-1298.2012.10.021

• Chemical change
• Cross validation
• Discrimination rates
• Identification model
• Input vector
• One-class support vector machine
• Solid-state fermentation
• SVM model
• Target class
• Training sets
• Wavelength ranges

Near infrared (NIR) spectroscopy coupled with one-class support vector machine (OC-SVM) were used to rapidly and accurately monitor physical and chemical changes in solid-state fermentation (SSF) of crop straws without the need for chemical analysis. Raw spectra of fermented samples were acquired with wavelength range of 10000-4000 cm-1. Then the top seven PCs as input vectors were extracted by principal component analysis (PCA). OC-SVM algorithm was implemented to develop identification model, and some parameters of OC-SVM model were optimized by cross-validation in calibrating model. Experimental results showed that OC-SVM model revealed its incomparable superiority than SVM model in handling imbalance training sets under the same condition. The discrimination rate of OC-SVM model was 85% in the validation set when the ratio of samples from target class to those from non-target class was one to eight in the training set.

• 出版日期2012