Comparison of Master Sigmoidal Curve and Markov Chain Techniques for Pavement Performance Prediction

El-Khawaga, Mohamed; El-Badawy, Sherif M.; Gabr, Alaa R.

doi:10.1007/s13369-019-04321-8

Cited by 10 publications

(2 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Khaled et al [11] proposed a discrete-time Markov model based on inverse calculation, achieving a prediction model for cost reduction. Khawaga et al [12] developed Markov chain-based and sigmoidal curve-based models to predict IRI. The results show that the Markov chain-based model is better than the sigmoidal curve-based model across comprehensive factors.…”

Section: Literature Reviewmentioning

confidence: 99%

Novel Instance-Based Transfer Learning for Asphalt Pavement Performance Prediction

Li,

Guo,

et al. 2024

Buildings

View full text Add to dashboard Cite

The deep learning method has been widely used in the engineering field. The availability of the training dataset is one of the most important limitations of the deep learning method. Accurate prediction of pavement performance plays a vital role in road preventive maintenance (PM) and decision-making. Pavement performance prediction based on deep learning has been widely used around the world for its accuracy, robustness, and automation. However, most of the countries in the world have not built their pavement performance historical database, which prevents preventive maintenance using the deep learning method. This study presents an innovative particle swarm optimization (PSO) algorithm-enhanced two-stage TrAdaBoost.R2 transfer learning algorithm, which could significantly increase the pavement performance prediction database. The Long-Term Pavement Performance (LTPP) database is used as the source domain data, and one of the highways in China is chosen as the target domain to predict pavement performance. The results show that the proposed PSO-Two-stage TrAdaBoost.R2 model has the highest accuracy compared with AdaBoost.R2 model and traditional regression decision tree model. The validation case study shows significant consistency between the predicted International Roughness Index (IRI) and the whole-year measurement data with an R2 of 0.7. This study demonstrates the great potential of the innovative instance-based transfer learning method in pavement performance prediction of a region’s lack of data. This study also contributes to other engineering fields that could greatly increase the universality of deep learning.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Novel Instance-Based Transfer Learning for Asphalt Pavement Performance Prediction

Li,

Guo,

et al. 2024

Buildings

View full text Add to dashboard Cite

show abstract

“…The development of a logistic function requires some statistical operations which may be complicated to some extents, therefore adoption of existing function with some calibrations to suit the peculiarities of the concerned system is acceptable (El-Khawaga et al, 2019). Previous studies have used sigmoid functions for performance prediction of pavement as stated in Sotil and Kaloush (2004), Nassiri et al (2013), Chen andMastin (2015) and Ayed (2016).…”

Section: Pavement Performance Functionmentioning

confidence: 99%

Calibration of Sigmoid Function for Performance Prediction of Flexible Road Pavement in Nigeria

Olowosulu

Kaura

Adeke³

2021

FUOYEJET

View full text Add to dashboard Cite

The performance prediction of road pavement for optimum maintenance decision to attain sustainable infrastructural development in Nigeria has been a challenge to highway engineers over time. This study attempted to calibrate a sigmoid function using historic dataset on performance variables of flexible road pavement for efficient and reliable pavement management decision in Nigeria. The curve fitting of three sigmoid functions I, II and III using OriginPro software based on historic dataset obtained from the Federal Ministry of Power, Works and Housing Nigeria showed a better fit for Sigmoid Function I with coefficient of determination value of 0.54. Though there were somewhat high margin of Root Mean Square Error (RMSE) of 51.49 for the estimated statistical parameters of the relatively best fit model, the poor performance of the fitted function was attributed to poor dataset characterized by missing and outlier or noisy elements. The relatively best fit sigmoid function was therefore recommended for use by highway management agencies with further calibrations using more recent, accurate and sufficient dataset that defines the present pavement condition in Nigeria. Keywords— Nigeria, road transport, flexible pavement, Sigmoid function, Pavement Management System.

show abstract

Prediction of Decay of Pavement Quality or Performance Index Based on Light Gradient Boost Machine

Pei

et al. 2021

Advances in Intelligent Automation and Soft Computing

View full text Add to dashboard Cite

Comparison of Master Sigmoidal Curve and Markov Chain Techniques for Pavement Performance Prediction

Cited by 10 publications

References 15 publications

Novel Instance-Based Transfer Learning for Asphalt Pavement Performance Prediction

Novel Instance-Based Transfer Learning for Asphalt Pavement Performance Prediction

Calibration of Sigmoid Function for Performance Prediction of Flexible Road Pavement in Nigeria

Prediction of Decay of Pavement Quality or Performance Index Based on Light Gradient Boost Machine

Contact Info

Product

Resources

About