基于遗传算法和间隔偏最小二乘的苹果硬度特征波长分析研究

Analysis of NIR Characteristic Wavelengths for Apple Flesh Firmness Based on GA and iPLS

利用傅里叶近红外光谱(FT-NIRS)测定了苹果的硬度。通过使用几种基于遗传算法和间隔偏最小二乘法的特征波长选取方法,包括动态向后间隔偏最小二乘(dynamic backward version of interval PLS,dynamic biPLS)、动态向后间隔偏最小二乘结合遗传算法(dynamic biPLS & GA-PLS)和反复的遗传算法(iterative GA-PLS),分析了苹果硬度的特征波长。结果表明,运用遗传算法和间隔偏最小二乘选择特征波长后,不但可以降低模型的复杂度,同时能够达到提高模型预测精度的效果。在此基础上,研究分析了苹果硬度特征波长的物理化学意义。由于果胶是在苹果成熟过程中一种和硬度有很大关联的物质,通过比较苹果硬度的特征波长和果胶的特征吸收峰,发现两者具有有很好的一致性。因此,采用遗传算法和间隔偏最小二乘法得到的苹果硬度的特征波长能够反映果胶的吸收信息,从而解释了近红外技术检测苹果硬度的机理。

In the present study, the fruit flesh firmness of apple was analyzed by near infrared （NIR） spectroscopy using an FTNIR spectrometer. The sensitive spectral regions that provide the lowest prediction error were analyzed by different well-known variable selection methods, including dynamic backward interval partial least-squares （dynamic biPLS）, sequential application of backward interval partial least-squares and genetic algorithm（dynamic biPLS ＆ GA-PLS）, and iterative genetic algorithm partial least-squares （iterative GA-PLS）. Iterative GA-PLS, dynamic biPLS ＆ GA-PLS led to a distinct reduction in the number of spectral data points with better predictive quality. Furthermore, the majority of selected wavelengths were content with the characteristic of the sorption bands of fruit flesh firmness. Pectin constituents, complex non-starch polysaceharides, which are related to texture change in apple, play an important role in their harvest maturity, ripening and storage. Comparing NIR characteristic wavelengths of apple flesh firmness and typical absorption bands for pectin, it was found that characteristic wavelengths of apple flesh firmness were consistent with the pectins relevant spectral regions. Therefore, the NIR characteristic wavelengths of apple firmness based on GA and iPLS reflected the chemical component of apple and the results were reasonable.