Reference | Material(s) | Input(s) | Model(s) | R2 | Study Site(s) |
---|---|---|---|---|---|
Lee et al. [15] | Waterborne paint, thermoplastic, polyester, tape | Time | Simple linear regression | 0.14 – 0.18 | MI |
Abboud and Bowman [16] | Waterborne paint, thermoplastic | Traffic | Exponential regression | 0.31 –0.58 | AL |
Sarasua et al. [19] | Thermoplastic, epoxy | Time | Simple linear regression | 0.21 – 0.47 | SC |
Hollingsworth [17] | Waterborne paint, thermoplastic | Time, traffic, bead type, color, initial retroreflectivity, lateral line location, and time | Logarithmic | 0.53 | NC |
Sitzabee et al. [18] | Thermoplastic, waterborne paint | Time, initial retroreflectivity, traffic, line lateral location, line color | Multiple linear regression | 0.60 – 0.75 | NC |
Karwa and Donnell [25] | Thermoplastic | Initial retroreflectivity, time, traffic, marking type, marking location | Artificial Neural Network (ANN) | - | NC |
Robertson et al. [20] | Waterborne paint | Time, traffic, lane width, shoulder width | Multiple linear regression | 0.24 – 0.34 | SC |
Ozelim and Turochy [9] | Thermoplastic | Time, traffic, initial retroreflectivity | Multiple linear regression | 0.49 | AL |
Malyuta [21] | Waterborne paint, thermoplastic | Time, traffic | Multiple linear regression | 0.33 – 0.46 | TN |
Mousa et al. [11] | Waterborne paint | Initial retroreflectivity, manufacturer, surface type, color, thickness, bead types, time, air temperature, rainfall, snowfall, traffic, surface age | Categorical Boosting | 0.83 – 0.98 | FL, PA, MN, MS |
Idris et al. [26] | Thermoplastic | Initial retroreflectivity, surface type, color, thickness, bead types, rainfall, traffic | Genetic Algorithm | 0.64 – 0.93 | FL |