Nondestructive Testing for Wheat Quality with Sensor Technology Based on Big Data

Table 2

Near-infrared spectroscopy test of wheat.

No.	Data	Conclusion	References
1	400	The correct grading of various varieties of wheat.	[29]
2	4096	Distinguishing the single cell layer near the outer shell of the wheat kernel and the primary roots in the germ.	[30]
3	70	A near-infrared reflection-granulation model was developed and verified.	[31]
4	60	Visible light and near-infrared reflectance spectroscopy technology are used to quickly and nondestructively measure the hardness of bulk wheat grains.	[37]
5	86	A band selection method combining ant colony algorithm and support vector regression is proposed to predict wheat grain hardness.	[39]
6	192	Possibility to detect differences in the quantity and size distribution of wheat polymer protein.	[40]
7	120	The wet and dry gluten content and Zeleny sedimentation of wheat were measured.	[41]
8	140	Near-infrared reflectance spectroscopy and radial basis function (RBF) neural network algorithm can be more convenient for the determination of wheat protein content.	[42]
9	391	Combined with different regression methods, the advantages of nonlinear modeling and multiobjective prediction are obtained.	[43]