Skip to main content

Table 9 Example results for models ANN-A through ANN-F

From: Modeling retroreflectivity degradation of pavement markings across the US with advanced machine learning algorithms

Variable type

Variables

Reported values

ANN-A

ANN-B

ANN-C

ANN-D

ANN-E

ANN-F

Input

E (month)

0

1

2

3

11

12

S

Asphalt

Asphalt

Asphalt

Asphalt

Asphalt

Asphalt

T

Polyurea

Polyurea

Polyurea

Polyurea

Polyurea

Polyurea

C

White

White

White

White

White

White

M

M-29

M-29

M-29

M-29

M-29

M-29

TH (mil)

20.7

20.7

20.7

20.7

20.7

20.7

b

N/A

N/A

N/A

N/A

N/A

N/A

B

Premium optics “Utah blend”

Premium optics “Utah blend”

Premium optics “Utah blend”

Premium optics “Utah blend”

Premium optics “Utah blend”

Premium optics “Utah blend”

TR (no. of vehicles)

222,000

740,000

1,776,000

2,812,000

12,617,000

13,394,000

SN (in.)

1.6

1.6

1.6

1.6

3.9

3.9

Input RS (mcd/m2/lux)

329

369

343

299

160

130

Prediction horizon (month)

1

2

3

11

12

15

Output

PRS (mcd/m2/lux)

369

343

299

160

130

87

Actual

Actual RS (mcd/m2/lux)

344

329

355

168

125

54