Publications by authors named "Rong-guang Zhu"
Hyperspectral Imaging Detection of Total Viable Count from Vacuum Packing Cooling Mutton Based on GA and CARS Algorithms.
Guang Pu Xue Yu Guang Pu Fen Xi
March 2017
In the process of spectral modeling, spectral extraction of characteristic bands with different variable screening algorithms is an important step for improving the model effects. Total viable count of cooling mutton under vacuum packing condition was chosen as the research index in this paper, while the influence of 2 variable screening algorithms on its hyperspectral PLS model effects was compared. Mutton muscle spectra of Regions of interest (ROIs) were extracted and preprocessed.
View Article and Find Full Text PDF[Study on Characteristic Bands Selection of Lamb pH Value Based on Hyperspectral Imaging and Partial Least Squares(PLS)].
Guang Pu Xue Yu Guang Pu Fen Xi
September 2016
Article Synopsis
- The selection of characteristic bands in hyperspectral imaging significantly impacts the performance of models used to detect mutton pH values.
- The study evaluated two band-selection methods—synergy interval partial least square (siPLS) and a combination of siPLS with genetic algorithms (siPLS-GA)—on mutton muscle spectra preprocessed with techniques like second derivative and multiplicative scatter correction.
- Results showed that the siPLS-GA-PLS model outperformed the full-band model, achieving high correlation coefficients and low error rates, indicating improved accuracy in lamb pH detection using fewer spectral variables.
[Study on the Rapid Evaluation of Total Volatile Basic Nitrogen (TVB-N) of Mutton by Hyperspectral Imaging Technique].
Guang Pu Xue Yu Guang Pu Fen Xi
March 2016
Article Synopsis
- * 71 mutton samples were scanned in the Visible-Near Infrared range (400-1000 nm) while their TVB-N content was measured using established chemical methods, allowing for the extraction of relevant spectral data.
- * The study developed calibration models using different statistical approaches, showing that techniques like Partial Least Squares Regression (PLSR) combined with specific spectral preprocessing could accurately quantify mutton freshness, with high correlation coefficients indicating strong predictive capability.
[Effects of Regions of Interest (ROIs) on Detection Models of Mutton pH Based on Hyperspectral Imaging].
Guang Pu Xue Yu Guang Pu Fen Xi
April 2016
Selection of Regions of interest (ROIs) and subsequent spectral extraction was a key step of non-destructive detection and analysis based on hyperspectral imaging (HSI). For the rapid and accurate detection of mutton pH, the study on the effects of 2 different ROIs on mutton pH models was carried out in the visible-near infrared region of 473～1 000 nm. 2 ROIs methods of Rectangle Regions (RR) and Image Segmentation (IS) were adopted to extract 122 corresponding representative spectra respectively.
View Article and Find Full Text PDF