Table 5.

ANN algorithm for temporal layer stacked image.

ANN results for temporal layer stacked image
Training 70							Testing 30
No of training		Fields_ training	Forest_ training	Shrubs_ training	Urban_ training	Overall. accuracy	Fields_ testing	Forest_ testing	Shrubs_ testing	Urban_ testing	Overall. accuracy
50	Overall accuracy = 97.07%, kappa coefficient = 0.954						Overall accuracy = 97.29%, kappa coefficient = 0.957
	Unclassified	0	0	0	0		0	0	0	0
	Fields	16,499	252	267	105	96.48%	15,922	791	1019	304	93.11%
	Forest	165	32,607	464	21	98.68%	207	31,004	1149	17	93.83%
	Shrubs	44	87	4759	2	86.45%	284	1135	3337	10	60.62%
	Urban	393	98	15	9414	98.66%	688	114	0	9211	96.53%
100	Overall accuracy = 97.73%, kappa coefficient = 0.964						Overall accuracy = 97.43%, kappa coefficient = 0.959
	Unclassified	0	0	0	0		0	0	0	0
	Fields	16,412	171	75	101	95.97%	7046	30	47	46	95.51%
	Forest	291	32,653	196	19	98.82%	131	13,992	129	7	98.91%
	Shrubs	114	121	5229	3	94.99%	33	99	1882	1	91.45%
	Urban	284	99	5	9419	98.71%	167	25	0	4137	98.71%
200	Overall accuracy = 98.07%, kappa coefficient = 0.970						Overall accuracy = 97.75%, kappa coefficient = 0.965
	Unclassified	0	0	0	0		0	0	0	0
	Fields	16,720	229	68	132	97.77%	7179	56	62	44	97.32%
	Forest	69	32,514	124	18	98.4%	43	13,898	5	66	98.25%
	Shrubs	120	210	5313	4	96.51%	113	20	4123	0	98.38%
	Urban	192	91	0	9388	98.39%	42	172	1	1948	94.66%
300	Overall accuracy = 97.69%, kappa coefficient = 0.964						Overall accuracy = 97.44%, kappa coefficient = 0.960
	Unclassified	0	0	0	0		0	0	0	0
	Fields	16,959	396	225	346	99.17%	7293	119	181	87	98.86%
	Forest	28	32,550	272	20	98.5%	29	13,985	7	188	98.86%
	Shrubs	21	51	5008	3	90.97%	40	9	4001	0	95.47%
	Urban	93	48	0	9173	96.13%	15	33	2	1783	86.64%