利用低频核磁共振（LF-NMR）弛豫技术对鱼类水分、脂肪及脂肪酸组成进行人工智能预测
Artificial intelligence predictability of moisture, fats and fatty acids composition of fish using low frequency Nuclear Magnetic Resonance (LF-NMR) relaxation.
作者信息
Al-Habsi Nasser, Al-Julandani Ruqaya, Al-Hadhrami Afrah, Al-Ruqaishi Houda, Al-Sabahi Jamal, Al-Attabi Zaher, Rahman Mohammad Shafiur
机构信息
Department of Food Science and Nutrition, College of Agricultural and Marine Sciences, Sultan Qaboos University, P. O. Box 34-123, Seeb, Oman.
Central Laboratory, College of Agricultural and Marine Sciences, Sultan Qaboos University, P. O. Box 34-123, Seeb, Oman.
出版信息
J Food Sci Technol. 2024 Nov;61(11):2071-2081. doi: 10.1007/s13197-024-05977-3. Epub 2024 Apr 14.
UNLABELLED
Moisture, fats and fatty acids of 14 pelagic and demersal fishes were measured by conventional chemical analysis to relate these with the proton relaxation using Low Frequency Nuclear Magnetic Resonance (LF-NMR). Artificial intelligence was used to assess the predictability of composition using six relaxation parameters of LF-NMR. Multiple linear regression showed significant prediction for moisture (W) (P < 0.00001), total fat (F) (P < 0.0001), ω-6 fatty acid (O6) (P < 0.001), saturated fats (SF), fatty acids (FA), mono-unsaturated fatty acids (MU) and ω-3 fatty acid (O3) (P < 0.01). However, the highest regression coefficient was observed for water (R: 0.490) and the lowest was observed for SF (R: 0.224). The low regression coefficients indicated strong non-linear relationships exited between LF-NMR parameters and composition. However, decision tree showed higher regression coefficients for all compositions considered in this study (R:0.780-0.694). In addition, it provided simple decision rules for the prediction of composition. General Regression Neural Network provided the highest prediction capability (R:0.847-1.000 for training and 0.506-0.924 for validation).
SUPPLEMENTARY INFORMATION
The online version contains supplementary material available at 10.1007/s13197-024-05977-3.
未标注
通过常规化学分析测量了14种中上层和底层鱼类的水分、脂肪和脂肪酸含量，并使用低频核磁共振（LF-NMR）将这些与质子弛豫相关联。利用人工智能，通过LF-NMR的六个弛豫参数评估成分的可预测性。多元线性回归显示，对水分（W）（P < 0.00001）、总脂肪（F）（P < 0.0001）、ω-6脂肪酸（O6）（P < 0.001）、饱和脂肪（SF）、脂肪酸（FA）、单不饱和脂肪酸（MU）和ω-3脂肪酸（O3）（P < 0.01）有显著预测作用。然而，水的回归系数最高（R：0.490），SF的回归系数最低（R：0.224）。低回归系数表明LF-NMR参数与成分之间存在很强的非线性关系。然而，决策树显示本研究中考虑的所有成分的回归系数更高（R：0.780 - 0.694）。此外，它为成分预测提供了简单的决策规则。广义回归神经网络提供了最高的预测能力（训练时R：0.847 - 1.000，验证时R：0.506 - 0.924）。
补充信息
在线版本包含可在10.1007/s13197 - 024 - 05977 - 3获取的补充材料。
Zotero 插件