Classification and Prediction of Bee Honey Indirect Adulteration Using Physiochemical Properties Coupled with K-Means Clustering and Simulated Annealing-Artificial Neural Networks (SA-ANNs)

Table 4

K-means clustering classification of honey adulteration using sugar profile and pH values.

Input variable	% correct classification	F value ( ≤ value)
Maltose	85	940 ( ≤ 0.01)
Fructose	95	934 ( ≤ 0.01)
Sucrose	95	6740 ( ≤ 0.01)
Total sugar	100	9067 ( ≤ 0.01)
Glucose	100	10344 ( ≤ 0.01)
pH	52	2789 ( ≤ 0.01)