Table 6.

The results obtained during experiment 1 for various segment sizes and both networks. The chaos class is denoted as Positive and non-chaos as Negative.

Model	Segment	Accuracy	TP	FN	TN	FP
LSTM	50	0.978	107,389	5,651	139,992	8
	100	0.989	55,233	1,287	70,000	0
	200	0.991	27,708	5,52	35,000	0
CNN	50	0.979	108,195	4,845	139,757	243
	100	0.982	54,781	1,713	69,457	543
	200	0.985	27,360	900	34,982	18