A Comparative Study of Land Cover Classification by Using Multispectral and Texture Data

Table 10

Classification table for multispectral data using artificial neural network (ANN: -class).

Multispectral data iteration (80-20)	Training dataset	Training data classification accuracy %	Test dataset	Misclassified data	Test data classification accuracy %
1-fold	200	100%	50	6/50	88%
2-fold	200	100%	50	2/50	96%
3-fold	200	100%	50	0/50	100%
4-fold	200	100%	50	1/50	98%
5-fold	200	100%	50	0/50	100%
Average multispectral training data classification accuracy: (100 + 100 + 100 + 100 + 100)/5 = 100%
Average multispectral test data classification accuracy: (88 + 96 + 100 + 98 + 100)/5 = 96.40%