Detection of Spray-Dried Porcine Plasma (SDPP) based on Electronic Nose and Near-Infrared Spectroscopy Data
| Autor: | Guangjun Qiu, Xiaoteng Han, Fanguo Zeng, Huazhong Lu, Min Zhang, Enli Lü, Qiaodong Yu |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
electronic nose
02 engineering and technology lcsh:Technology 01 natural sciences regression analysis lcsh:Chemistry continuum regression Partial least squares regression Feature (machine learning) General Materials Science lcsh:QH301-705.5 Instrumentation Mathematics Fluid Flow and Transfer Processes Electronic nose lcsh:T business.industry Process Chemistry and Technology 010401 analytical chemistry Near-infrared spectroscopy General Engineering Regression analysis Pattern recognition discriminant analysis 021001 nanoscience & nanotechnology Linear discriminant analysis lcsh:QC1-999 Regression 0104 chemical sciences Computer Science Applications lcsh:Biology (General) lcsh:QD1-999 Fourier transform near-infrared spectroscopy lcsh:TA1-2040 Principal component analysis Artificial intelligence lcsh:Engineering (General). Civil engineering (General) 0210 nano-technology business spray-dried porcine plasma lcsh:Physics |
| Zdroj: | Applied Sciences Volume 10 Issue 8 Applied Sciences, Vol 10, Iss 2967, p 2967 (2020) |
| ISSN: | 2076-3417 |
| Popis: | Recent studies have indicated that spray-dried porcine plasma (SDPP) is a potential transmission route for African swine fever (ASF). Therefore, it is essential to develop rapid, high-efficiency analytical methods to detect SDPP, aiming to both restrict the abuse of SDPP and block the spread of ASF through feed additive. The feasibility of detecting SDPP using an electronic nose and near-infrared spectroscopy (NIRS) is explored and validated by a principal component analysis (PCA). Both discrimination experiments and prediction experiments were implemented to compare the detect feature of the two techniques. On this basis, partial least squares discriminant analysis (PLS&ndash DA) under various preprocessing methods was used to develop a qualitative discriminant model for estimating the prediction performance. Before selecting a specific regression model for the quantitative analysis of SDPP, a continuum regression (CR) model was employed to explore and choose the potential most appropriate regression model for these two different types of datasets. The results showed that the optimal regression model adopted partial least squares regression (PLSR) with the Savitzky&ndash Golay first derivative and mean-center preprocessing for the NIRS dataset (Rp2 = 0.999, RMSEP = 0.1905). Overall, combining the NIRS technique with multivariate data analysis methods shows more possibilities than an electronic nose for rapidly detecting the usage of SDPP in mixed feed samples, which could provide an effective way to control the spread of ASF. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|