Prediction of Compressive Strength of Concrete and Rock Using an Elementary Instance-Based Learning Algorithm

Table 4

Correlation matrices of rock datasets.

Dataset 4	UW	VP	SHH	SSH	BTS	Is	CS
UW	1	0.866	0.801	0.647	0.629	0.545	0.589
VP	—	1	0.799	0.609	0.702	0.614	0.702
SHH	—	—	1	0.818	0.785	0.728	0.781
SSH	—	—	—	1	0.784	0.812	0.807
BTS	—	—	—	—	1	0.884	0.947
Is	—	—	—	—	—	1	0.896
CS	—	—	—	—	—	—	1
Dataset 5	Is	VP	Rn	n	E	CS
Is	1	0.622	0.629	−0.728	0.617	0.814
VP	—	1	0.615	−0.663	0.673	0.789
Rn	—	—	1	−0.631	0.696	0.701
n	—	—	—	1	−0.562	−0.885
E	—	—	—	—	1	0.739
CS	—	—	—	—	—	1
Dataset 6	VP	SHN	Is	BPI	CS
VP	1	0.697	0.629	0.693	0.819
SHN	—	1	0.812	0.813	0.872
Is	—	—	1	0.822	0.873
BPI	—	—	—	1	0.873
CS	—	—	—	—	1

The parameters listed in the first row of datasets 4 to 6 are defined in Table 2.