离子液体
萃取(化学)
超声波传感器
产量(工程)
色谱法
灵芝
人工神经网络
均方误差
相关系数
材料科学
化学
高效液相色谱法
生物系统
分析化学(期刊)
计算机科学
数学
人工智能
机器学习
声学
有机化学
物理
食品科学
统计
冶金
生物
催化作用
作者
Changqin Li,Yiping Cui,Lü Jie,Cunyu Liu,Sitan Chen,Changyang Ma,Zhenhua Liu,Jinmei Wang,Wenyi Kang
出处
期刊:Molecules
[Multidisciplinary Digital Publishing Institute]
日期:2020-03-13
卷期号:25 (6): 1309-1309
被引量:24
标识
DOI:10.3390/molecules25061309
摘要
Ganoderma lucidum is widely used in traditional Chinese medicine (TCM). Ganoderic acid A and D are the main bioactive components with anticancer effects in G. lucidum. To obtain the maximum content of two compounds from G. lucidum, a novel extraction method, an ionic liquid-based ultrasonic-assisted method (ILUAE) was established. Ionic liquids (ILs) of different types and parameters, including the concentration of ILs, ultrasonic power, ultrasonic time, rotational speed, solid–liquid ratio, were optimized by the orthogonal experiment and variance analysis. Under these optimal conditions, the total extraction yield of the two compounds in G. lucidum was 3.31 mg/g, which is 36.21% higher than that of the traditional solvent extraction method. Subsequently, an artificial neural network (ANN) was developed to model the performance of the total extraction yield. The Levenberg–Marquardt back propagation algorithm with the sigmoid transfer function (logsig) at the hidden layer and a linear transfer function (purelin) at the output layer were used. Results showed that single hidden layer with 9 neurons presented the best values for the mean squared error (MSE) and the correlation coefficient (R), with respectively corresponding values of 0.09622 and 0.93332.
科研通智能强力驱动
Strongly Powered by AbleSci AI