1. Rapid prediction of yellow tea free amino acids with hyperspectral images
- Author
-
Hongmin Li, Baohua Yang, Yuan Gao, Xie Shenru, Ye Shengbo, and He Hongxia
- Subjects
Support Vector Machine ,Spectrophotometry, Infrared ,Kernel Functions ,01 natural sciences ,Grayscale ,Machine Learning ,Mathematical and Statistical Techniques ,Medicine and Health Sciences ,Amino Acids ,Operator Theory ,Mathematics ,Principal Component Analysis ,Multidisciplinary ,Applied Mathematics ,Simulation and Modeling ,Optical Imaging ,Statistics ,Hyperspectral imaging ,04 agricultural and veterinary sciences ,Equipment Design ,040401 food science ,Principal component analysis ,Physical Sciences ,Amino Acid Analysis ,Medicine ,Smoothing ,Algorithms ,Research Article ,Computer and Information Sciences ,Imaging Techniques ,Science ,Free amino ,Research and Analysis Methods ,Beverages ,0404 agricultural biotechnology ,Artificial Intelligence ,Support Vector Machines ,Statistical Methods ,Spectral data ,Computer Imaging ,Molecular Biology Techniques ,Molecular Biology ,Nutrition ,Molecular Biology Assays and Analysis Techniques ,Tea ,business.industry ,010401 analytical chemistry ,Biology and Life Sciences ,Pattern recognition ,0104 chemical sciences ,Diet ,Support vector machine ,Artificial intelligence ,business ,Forecasting - Abstract
Free amino acids are an important indicator of the freshness of yellow tea. This study investigated a novel procedure for predicting the free amino acid (FAA) concentration of yellow tea. It was developed based on the combined spectral and textural features from hyperspectral images. For the purposes of exploration and comparison, hyperspectral images of yellow tea (150 samples) were captured and analyzed. The raw spectra were preprocessed with Savitzky-Golay (SG) smoothing. To reduce the dimension of spectral data, five feature wavelengths were extracted using the successive projections algorithm (SPA). Five textural features (angular second moment, entropy, contrast, correlation, and homogeneity) were extracted as textural variables from the characteristic grayscale images of the five characteristic wavelengths using the gray-level co-occurrence matrix (GLCM). The FAA content prediction model with different variables was established by a genetic algorithm-support vector regression (GA-SVR) algorithm. The results showed that better prediction results were obtained by combining the feature wavelengths and textural variables. Compared with other data, this prediction result was still very satisfactory in the GA-SVR model, indicating that data fusion was an effective way to enhance hyperspectral imaging ability for the determination of free amino acid values in yellow tea.
- Published
- 2018