Work

Quantitative analysis of millet mixtures based on terahertz time-domain spectroscopy and improved coati optimization algorithm

Year: 2023

Type: article

Abstract: The significant difference in economic and nutritional value between new and old cereals has led to a plethora of grain mix-ups on the market, and it seriously damages the rights and interests of consumers. The study primarily focuses on millet, which has a higher economic and nutritional value among cereals, Terahertz time-domain spectroscopy (THz-TDS) combined with chemometrics is used to quantitatively detect millet mixtures with different gradient ratios. First of all, the spectral data in the 0.2-2.5 THz range was chosen for pre-processing. Standard normal variate transformation, Savitzky-Golay smoothing, multiplicative scatter correction (MSC), and normalizing techniques were employed to reduce noise and interference while enhancing valuable data. The sample set was then divided using the Spectral-Physical Value Coexistence Distance (SPXY) technique after principal component analysis (PCA) had chosen more representative characteristics. Finally, support vector regression (SVR) was utilized for quantitative analysis of millet mixtures with different gradient ratios. In order to further improve the prediction accuracy of SVR model, an improved Coati optimization algorithm (LASCCOA) was proposed. The quality and diversity of the initial population are improved by introducing chaotic mapping, tent mapping, and reverse learning mechanisms, followed by the introduction of adaptive weights and Wright flight mechanisms, which enhance the flexibility and convergence speed of the algorithm, and lastly, the introduction of the sine-cosine algorithm to improve the search range. The experimental results indicate a significant improvement in prediction accuracy over traditional and original algorithms, further enhancing model performance. This research provides technical support and a reference for rapid no n-destructive quantitative detection of cereals mixtures while opening up new possibilities for subsequent cereal quantitative detection.

Source: Spectroscopy Letters

DOI: 10.1080/00387010.2023.2285510

Authors: Xianhua Yin, Hao Tian, Fuqiang Zhang, An Li

Institutions: Guangxi Key Laboratory of Automatic Detecting Technology and Instruments, Guilin University of Electronic Technology

Language: English

Topic: Spectroscopy and Chemometric Analyses

Subfield: Analytical Chemistry

Field: Chemistry

Domain: Physical Sciences

SDG: Zero hunger

Open Access status: green

Funder: National Natural Science Foundation of China