Arslan Muhammad, Zareef Muhammad, Elrasheid Tahir Haroon, Xiaodong Zhai, Rakha Allah, Ali Shujat, Shi Jiyong, Xiaobo Zou
Agricultural Product Processing and Storage Lab, School of Food and Biological Engineering, Jiangsu University, 301 Xuefu Rd., 212013 Zhenjiang, Jiangsu, China; Yixing Institute of Food and Biotechnology, Yixing, Jiangsu, China.
Agricultural Product Processing and Storage Lab, School of Food and Biological Engineering, Jiangsu University, 301 Xuefu Rd., 212013 Zhenjiang, Jiangsu, China.
Spectrochim Acta A Mol Biomol Spectrosc. 2023 May 5;292:122359. doi: 10.1016/j.saa.2023.122359. Epub 2023 Jan 18.
This study evaluated the feasibility of colorimetric sensor array (CSA), near-infrared (NIR) and mid-infrared (MIR) spectroscopy for quantitation of free fatty acids in rice using data fusion. Purposely, different data sets of low-level (CSA-NIR, CSA-MIR, and NIR-MIR) and mid-level (CSA-NIR, CSA-MIR, and NIR-MIR) fusion were adopted to enhance the statistical parameters. The model performance was evaluated using coefficient of determination for prediction, (Rp), root mean square error of prediction (RMSEP) and residual predictive deviation (RPD). Synergetic low-level and mid-level fusion model yielded 0.7707 ≤ Rp ≤ 0.8275, 14.4 ≤ RMSEP ≤ 16.3 and 2.19 ≤ RPD ≤ 2.48; and 0.7788 ≤ Rp ≤ 0.8571, 12.4 ≤ RMSEP ≤ 16.8 and 2.12 ≤ RPD ≤ 2.88, respectively. The CSA-NIR model delivered an optimal performance for prediction of free fatty acid. The integration of CSA, NIR and MIR was feasible and could improve the prediction accuracy of free fatty acids in rice.
本研究评估了比色传感器阵列（CSA）、近红外（NIR）和中红外（MIR）光谱法通过数据融合对大米中游离脂肪酸进行定量分析的可行性。特意采用了低水平（CSA-NIR、CSA-MIR和NIR-MIR）和中水平（CSA-NIR、CSA-MIR和NIR-MIR）融合的不同数据集来提高统计参数。使用预测决定系数（Rp）、预测均方根误差（RMSEP）和剩余预测偏差（RPD）对模型性能进行评估。协同低水平和中水平融合模型分别得到0.7707≤Rp≤0.8275、14.4≤RMSEP≤16.3和2.19≤RPD≤2.48；以及0.7788≤Rp≤0.8571、12.4≤RMSEP≤16.8和2.12≤RPD≤2.88。CSA-NIR模型在游离脂肪酸预测方面表现出最佳性能。CSA、NIR和MIR的整合是可行的，并且可以提高大米中游离脂肪酸的预测准确性。
