Evaluation of influence of pavement data on measurement of deflection on asphalt surfaced pavements utilizing traffic speed deflection device

Jia, Xiaoyang; Woods, Mark; Gong, Haiqing; Zhu, Di; Hu, Wei; Huang, Baoshan

doi:10.1016/j.conbuildmat.2020.121842

Cited by 12 publications

(7 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Equipment certification and standard data collection process are being developed. Meanwhile, efforts are being made to develop deflection-based indices to be used in pavement evaluation ( 10 ).…”

Section: Discussionmentioning

confidence: 99%

“…For regression models, the importance of a predictor on a dependent variable was estimated by ''increase in node purity, (IncNodePurity),'' which is calculated based on the decrease in accuracy for a given variable across every tree in the forest. The higher the increase in node purity value, the more important the predictor is in the model (10).…”

Section: Random Forest Regressionmentioning

confidence: 99%

See 1 more Smart Citation

Incorporation of National Pavement Performance Measures Into Decision-Making Process

Jia

Woods

Zhu

et al. 2022

Transportation Research Record: Journal of the Transportation R

Self Cite

View full text Add to dashboard Cite

State highway agencies (SHAs) are required by Federal Highway Administration (FHWA) to develop Transportation Asset Management Plans (TAMP) in which the performance targets for roadway assets are determined. FHWA also developed national performance metrics to use in determining performance targets for pavements. However, for pavement assets, most SHAs employ their own performance metrics for pavement condition data reporting and performing maintenance and rehabilitation (M&R) analysis. Therefore, there is a need to incorporate national performance measures into SHAs’ pavement management system to support the development of TAMP. In this study, new pavement performance metrics were proposed to assist SHAs in conducting M&R analysis. The relationships between the new metrics and existing pavement metrics used in the State of Tennessee were investigated. Comparison between the new metrics and the State’s metrics was made with reference to network-level condition summary and performance prediction models. Results indicated that the new performance metrics appeared to be stable and less sensitive to sectioning method. Similar time-series patterns of network-level performance deterioration were found between the State’s metrics and the new metrics. It is recommended that performance models be established based on the new metrics, as the deterioration rates from the two metrics were not well correlated.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Random Forest Regressionmentioning

confidence: 99%

Incorporation of National Pavement Performance Measures Into Decision-Making Process

Jia

Woods

Zhu

et al. 2022

Transportation Research Record: Journal of the Transportation R

Self Cite

View full text Add to dashboard Cite

show abstract

“…In fact, some unseen capability loss has already existed before distresses appear, which cannot be measured [24]. That is why the traditional methods can explain the reasons well but cannot predict the results accurately for potential damage [25,26]. Therefore, ML models can be the perfect complementary to traditional methods.…”

Section: Machine Learning and Random Forestmentioning

confidence: 99%

Using a Random Forest Model to Predict the Location of Potential Damage on Asphalt Pavement

Guo

Hao

2021

Applied Sciences

View full text Add to dashboard Cite

Potential damage, eventually demonstrated as moisture damage on inner and in-situ road structures, is the most complex problem to predict, which costs lots of money, time, and natural resources for maintenance and even leads to safety problems. Traditional linear regression analysis cannot fit well with this multi-factor task in such in-field circumstances. Random Forest (RF) is a progressive nonlinear algorithm, which can combine all relative factors to gain accurate prediction and good explanation. In this study, an RF model is constructed for the prediction of potential damage. In addition, relative variable importance is analyzed to obtain the correlations between factors and potential damage separately. The results show that, through the optimization, the model achieved a good average accuracy of 83.33%. Finally, the controlling method for moisture damage is provided by combining the traditional analysis method and the RF model. In a word, RF is a prospective method in predictions and data mining for highway engineering. Trained with effective data, it can be multifunctional and powerful to solve hard problems.

show abstract

“…The main challenge [ 11 , 12 , 13 , 14 , 15 ] in detecting road cracks arises from the diverse types of cracks caused by severe weather and long-term vehicle use. Traditional manual detection methods are inefficient and often miss cracks, while machine learning (ML) [ 16 , 17 , 18 , 19 , 20 ] models require manually designed features for crack detection. According to the Federal Highway Administration (FHWA), there are various crack types like fatigue, longitudinal, and transverse, making it difficult to design a universal feature extraction model for effective automatic detection using machine learning.…”

Section: Introductionmentioning

confidence: 99%

Visual Detection of Road Cracks for Autonomous Vehicles Based on Deep Learning

Meftah,

Hu,

Asham

et al. 2024

Sensors

View full text Add to dashboard Cite

Detecting road cracks is essential for inspecting and assessing the integrity of concrete pavement structures. Traditional image-based methods often require complex preprocessing to extract crack features, making them challenging when dealing with noisy concrete surfaces in diverse real-world scenarios, such as autonomous vehicle road detection. This study introduces an image-based crack detection approach that combines a Random Forest machine learning classifier with a deep convolutional neural network (CNN) to address these challenges. Three state-of-the-art models, namely MobileNet, InceptionV3, and Xception, were employed and trained using a dataset of 30,000 images to build an effective CNN. A systematic comparison of validation accuracy across various base learning rates identified a base learning rate of 0.001 as optimal, achieving a maximum validation accuracy of 99.97%. This optimal learning rate was then applied in the subsequent testing phase. The robustness and flexibility of the trained models were evaluated using 6,000 test photos, each with a resolution of 224 × 224 pixels, which were not part of the training or validation sets. The outstanding results, boasting a remarkable 99.95% accuracy, 99.95% precision, 99.94% recall, and a matching 99.94% F1 Score, unequivocally affirm the efficacy of the proposed technique in precisely identifying road fractures in photographs taken on real concrete surfaces.

show abstract

Evaluation of influence of pavement data on measurement of deflection on asphalt surfaced pavements utilizing traffic speed deflection device

Cited by 12 publications

References 12 publications

Incorporation of National Pavement Performance Measures Into Decision-Making Process

Incorporation of National Pavement Performance Measures Into Decision-Making Process

Using a Random Forest Model to Predict the Location of Potential Damage on Asphalt Pavement

Visual Detection of Road Cracks for Autonomous Vehicles Based on Deep Learning

Contact Info

Product

Resources

About