Predicting pavement condition index using artificial neural networks approach

Issa, Amjad; Samaneh, Haya; Ghanim, Mohammad

doi:10.1016/j.asej.2021.04.033

Cited by 41 publications

(19 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Training data: This data is employed to train the machine learning algorithm [31]; scientists feed data into the algorithm, which correlates to the desired outcomes. The model analyses the data regularly to learn more about its function and then adapts itself to achieve its intended function.…”

Section: B Ann Modelingmentioning

confidence: 99%

“…Validation data: During training, validation data is beamformed into the model that it has not previously analyzed [31]. Validation data is used as the first test against previously unknown data, allowing data scientists to assess how well the model predicts based on the new data.…”

Section: B Ann Modelingmentioning

confidence: 99%

“…Tests data: After the model has been constructed, testing data confirms that it can generate correct predictions [31]. The testing data should remain unlabeled if the training and validation data contain labels to monitor the model's performance metrics.…”

Section: B Ann Modelingmentioning

confidence: 99%

“…A value of "0" indicates no prediction error, whereas a value of "100" represents the most significant number of errors. Equations 1 and 2 [31] provide the mathematical formulas for MSE and percent E based on observed values or target vector (t) and forecast values vector (y) at the total number of samples (N).…”

Section: B Ann Modelingmentioning

confidence: 99%

See 3 more Smart Citations

Modeling of Pavement Maintenance Decisions Using Artificial Intelligence Based on Maintenance Unit.

Faheem

Mahmoud

Hashem

et al. 2022

MEJ. Mansoura Engineering Journal

View full text Add to dashboard Cite

Recently, all efforts have been directed toward keeping the network functional at a high level by determining the appropriate maintenance or rehabilitation (M & R) treatment. Determining the appropriate M & R strategies for flexible pavements is a complex process and is considered a key component of the Pavement Maintenance Management System (PMMS). Since such a decision system is complex, automated implementation using a pretrained model via an artificial neural network (ANN) approach is a critical tool for decision-makers. Many studies have been conducted on modeling pavement condition index using ANN to determine the maintenance decision. The Egyptian Code of Practice has recently relied on the maintenance unit (MU) concept for maintenance decision prediction. A few researchers have investigated maintenance decision (MD) predications using the MU modeling by ANN but have not adequately studied Egyptian Code consideration. Therefore, this paper addresses the application of the latest machine learning technique for forecasting the current pavement maintenance decisions based on the MU system according to the Egyptian code considerations to develop a one-step enhanced decisionmaking tool. A pattern-recognition algorithm (neural network) was applied to 54.3 km of surveyed roads in Minia governorate, Egypt. The results indicated that the ANN model is capable of predicting the MD with a high level of reliability, with a mean square error (MSE) value of 0.02993, 0.03046, and 0.03018, and a percentage error (% E) value of 13.29693, 14.11734, and 13.83215 for the training, validation, and testing datasets, respectively.

show abstract

Section: B Ann Modelingmentioning

confidence: 99%

Section: B Ann Modelingmentioning

confidence: 99%

Section: B Ann Modelingmentioning

confidence: 99%

Section: B Ann Modelingmentioning

confidence: 99%

See 2 more Smart Citations

Modeling of Pavement Maintenance Decisions Using Artificial Intelligence Based on Maintenance Unit.

Faheem

Mahmoud

Hashem

et al. 2022

MEJ. Mansoura Engineering Journal

View full text Add to dashboard Cite

show abstract

“…Moreover, poor pavements condition cause delay as it interrupts the traffic movement and reduces the speed of the vehicles and consequently it results in additional money losses due to fuel consumption, vehicles' parts exhausting and lost in time [19][20][21]. Furthermore, poor pavements condition cause inconvenience driving which make the road users nervous and annoyed [22,23]. Over that, maintaining such pavements require a huge amounts of materials, efforts, energy, and money [24].…”

Section: Introductionmentioning

confidence: 99%

Evaluation of structural properties of Baghdad-Baquba road pavements

Kadeem¹,

Joni²,

Waheed³

2022

PEN

View full text Add to dashboard Cite

Structural evaluation of the road pavements is an essential concept to ensure their efficiency to carry traffic loads and to archive the data for future usage especially in major highways. Baghdad-Baquba is an important interstate highway as it connects the capital of Iraq with Diyala governorate which is one of the biggest governorates in Iraq. In addition, this highway connects Baghdad city with several governorates in the north of Iraq. However, this highway exhibits low serviceability due to poor condition of its pavements. Therefore, the structure of the pavements must be evaluated to specify the causes those lead to the decrease in its serviceability and to propose the suitable rehabilitation methods. This study aims to adopt a field survey to extract a number of samples from selected section in this highway to evaluate the structural properties of the pavements based on laboratory testing. Four cores and one pit with 1×1 m dimensions were extracted from the pavements in the field. Several tests were implemented on these tests based on standard methods. The results of the tests were adopted to evaluate the capacity of the pavement based on AASHTO 1993 method. The results exhibited that the estimated applied traffic load exceeded the calculated allowable traffic load by more than 12 times which reflect the disastrous situation. Therefore, the study proposed to rehabilitate the pavements by reconstruction. The study proposed to construct three layers: asphaltic layer with thickness of 240 mm, granular base with thickness of 250 mm, and granular subbase with a thickness of 250 mm. The study stated that all layers must have superior quality with high elastic modulus to resist the predicated traffic load.

show abstract

Assessment of Present Pavement Condition Using Machine Learning Techniques

Sharma

Kumar

2022

Lecture Notes in Civil Engineering

View full text Add to dashboard Cite

Predicting pavement condition index using artificial neural networks approach

Cited by 41 publications

References 13 publications

Modeling of Pavement Maintenance Decisions Using Artificial Intelligence Based on Maintenance Unit.

Modeling of Pavement Maintenance Decisions Using Artificial Intelligence Based on Maintenance Unit.

Evaluation of structural properties of Baghdad-Baquba road pavements

Assessment of Present Pavement Condition Using Machine Learning Techniques

Contact Info

Product

Resources

About