Application of Artificial Intelligence to the Prediction of the Antimicrobial Activity of Essential Oils

Table 2

Prediction by an artificial neural network (FANN) of the inhibition diameter in disk diffusion assays for a specific microorganism (1 output) using the small data input set (). Accuracy is expressed in the percentage of predictions within the given error margin. In parenthesis, total of validating sets correctly predicted within the corresponding error margin.

Strains	Accuracy %
	ΔID ≤ 5 mm	ΔID ≤ 10 mm	ΔID ≤ 15 mm	ΔID > 15 mm
S. aureus ATCC 25923	61.1 (11)	83.3 (15)	100 (18)	0 (0)
E. coli ATCC 25922	47.6 (10)	71.4 (15)	81.0 (17)	19.0 (4)
C. perfringens KT	38.9 (7)	61.1 (11)	81.0 (17)	19 (4)
C. albicans ATCC 10239	26.7 (4)	66.7 (10)	86.7 (13)	13.3 (2)