Pavement Roughness Modeling Using Back‐Propagation Neural Networks

Choi, Jaeho; Adams, Teresa M.; Bahia, Hussain U.

doi:10.1111/j.1467-8667.2004.00356.x

Cited by 89 publications

(36 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Bailey and Thomson 1990, Lefteri and Robert 1997, Meier and Tutumluer 1998. One of the common results from these studies is that one hidden layer with sufficient nodes is capable of representing any mapping (Choi et al 2004). …”

Section: Ann Modelmentioning

confidence: 98%

“…Fwa and Chen 1993, Attoh-Okine 1994, 2001, Eldin and Senouci 1995, Huang and Moore 1997, Alsugair and Al-Qudrah 1998, Owusu-Ababio 1998, Shekharan 2000, Sundin and Braban-Ledoux 2001, Bayrak et al 2004, Choi et al 2004, Mei et al 2004, Loizos and Karlaftis 2006, Terzi 2007 have been used to predict pavement condition. The ANN helps to illustrate effect of each individual variable on pavement condition and effect of interactions between the variables.…”

Section: Ann Modelmentioning

confidence: 99%

“…In modelling pavement performance, Anderson et al (1990) mentioned that the challenge is to find the best method to relate material and construction variables with performance based on traffic levels and pavement structure. Deriving such relationships is too complex, poorly understood and very resource intensive to develop using traditional computational methods (Choi et al 2004). Researchers have developed several methods including regression models (e.g.…”

Section: Pavement Performance Modelsmentioning

confidence: 99%

See 2 more Smart Citations

Prediction of IRI in short and long terms for flexible pavements: ANN and GMDH methods

Ziari

Sobhani²,

Ayoubinejad

et al. 2015

International Journal of Pavement Engineering

123

View full text Add to dashboard Cite

Prediction of pavement condition is one of the most important issues in pavement management systems. In this paper, capabilities of artificial neural networks (ANNs) and group method of data handling (GMDH) methods in predicting flexible pavement conditions were analysed in three levels: in 1 year, in 2 years (short term) and in the pavement life cycle (long term). For this purpose, three effective groups on pavement condition including traffic conditions, environmental changes and pavement structures were studied and nine effective variables were selected as input variables. International roughness index (IRI) was also used as the indicator of pavement performance. Various ANN structures and GMDH models in partial description configurations of 1st, 2nd, 3rd and 4th polynomials were formed and examined. Results indicate that while ANN models predict future condition of pavement with high accuracy in the short and long terms, GMDH models do not have accepted accuracy.

show abstract

Section: Ann Modelmentioning

confidence: 98%

Section: Ann Modelmentioning

confidence: 99%

Section: Pavement Performance Modelsmentioning

confidence: 99%

See 1 more Smart Citation

Prediction of IRI in short and long terms for flexible pavements: ANN and GMDH methods

Ziari

Sobhani²,

Ayoubinejad

et al. 2015

International Journal of Pavement Engineering

123

View full text Add to dashboard Cite

show abstract

“…Çalışmalarda, bağımsız değişken sayısının çok olması bazı değişkenlerin sayısal değerlerle ifade edilememesi gibi sebeplerle yapay zeka tekniklerinin sıklıkla tercih edildiği görülmektedir. Araştırmacılar tarafından, sayısal ve sözel verilerin bir arada değerlendirilmesinde oldukça kolaylıklar sağlayan bulanık mantık [10][11][12] ve YSA [13][14][15][16] yaklaşımları ile her iki yöntemin bir arada kullanıldığı ANFIS yaklaşımının [17] [3]. IRI ölçümleri ve değerlendirmeleri ASTM E 950 standardında tanımlanan profilometre cihazı ile çeyrek araç sisteminin (Quarter Car System -QCS) simüle edilmesi ile sağlanmaktadır [18].…”

Section: Ayrıcaunclassified

Bitümlü Sıcak Karışım Üstyapılarda Görülen Yüzey Bozulmaları ile Düzgünsüzlük Arasındaki İlişkilerin Modellenmesinde Bazı Yaklaşımlar

Kırbaş¹,

Karaşahin²,

Demir³

et al. 2018

SDÜ Fen Bil Enst Der

View full text Add to dashboard Cite

Anahtar KelimelerÜstyapı performansı, Yüzey bozulmaları, IRI Özet: Esnek üstyapılarda görülen yüzey bozulmaları ile düzgünsüzlük arasında ilişkilerin araştırıldığı çalışmalar incelendiğinde sınırlı sayıda yüzey bozulma türünün dikkate alındığı görülmektedir. Literatüre katkı sağlamak amacıyla bu çalışmada, 13 adet yüzey bozulma türü ve bozulma şiddetleri ile birlikte toplam 32 adet üstyapı bozulması ile IRI arasındaki ilişkilerin matematiksel modelleme analizi yapılmıştır. Modelleme çalışmalarında doğrusal regresyon, değişkenli uyarlamalı regresyon eğrileri (MARS) ve yapay sinir ağları (YSA) yaklaşımları kullanılmıştır. Oluşturulan modellerin tahmin yetenekleri ortalama mutlak hata (OMH), kök ortalama karesel hata (KOKH), ortalama mutlak göreceli hata (OMGH) ve regresyon katsayısı (R 2 ) istatistiksel karşılaştırma yöntemleri kullanılarak değerlendirilmiştir. Tahmin yeteneği en yüksek olan modelin YSA yaklaşımı kullanılarak oluşturulan model olduğu tespit edilmiştir. Ayrıca, YSA yaklaşımında girdi değişkenlerinin çıktı değişkeni üzerindeki etkileri bağlantı ağırlıklarına göre değerlendirilmiştir. Bu değerlendirmeye göre, üstyapı bozulmaları oluşma nedenlerine (mekanizmalarına) göre incelendiğinde, IRI üzerinde % 43.8 yük kaynaklı, % 39 diğer sebepler kaynaklı ve % 17.2 iklim kaynaklı bozulmaların etkili olduğu sonucuna ulaşılmıştır. Some Approaches to the Modeling of Relationships between Surface Distresses and Roughness in Hot-Mixed Asphalts Keywords Pavement performance, Surface distresses, IRIAbstract: When studies investigating the relationship between pavement roughness and surface distresses seen in flexible pavements are examined, a limited number of surface distress types are considered to be taken into account. In order to contribute to the literature, in this study, mathematical modeling analysis of relations between IRI and a total of 32 pavement distresses with 13 types of surface distress types and severities were carried out. Linear regression, multivariate adaptive regression splines (MARS) and artificial neural networks (ANN) approaches are used in modeling studies. Estimating capabilities of the analyzed mathematical models were evaluated using statistical comparison methods such as mean absolute error (MAE), root mean squared error (RMSE), mean absolute relative error (MARE) and regression coefficient (R 2 ). The model constructed using the ANN approach was ascertained to be the model with the highest prediction accuracy. In addition, in the ANN approach, the effects on the output variable of the input variables are evaluated according to the connection weights. According to this evaluation, when pavement distresses are examined according to the cause of distress, it is concluded that 43.8 % of IRI is caused by load, 39 % is caused by other causes and 17.2 % is caused by climate.

show abstract

“…is model combined with the establishment of ε r trigger values is deemed useful for analyzing, ranking, and prioritizing sections with reduced asphalt layers' fatigue life that urges for maintenance and rehabilitation treatments [11]. Further, with regard to the pavement functional condition assessment, it has been demonstrated that an ANN model can be an effective and accurate way to predict surface roughness based on the backpropagation learning method and by exploiting experimental measurements obtained from the pavement surfaces [12][13][14][15][16]. In addition, the support vector machine (SVM) method appeared as a promising soft computing technique derived from statistical learning theory that is not often used to solve pavement engineering problems [17].…”

Section: Background and Objectivesmentioning

confidence: 99%

Soft Computing Models to Predict Pavement Roughness: A Comparative Study

Georgiou

Plati

Loizos

2018

Advances in Civil Engineering

View full text Add to dashboard Cite

Pavement roughness as a critical determinant of public satisfaction can potentially play a major role in road or highway resource allocation to competing pavement resurfacing projects. With this in mind, the aim of the present paper is to develop an accurate model for the prediction of pavement roughness in terms of the International Roughness Index (IRI) using artificial neural networks (ANNs) and support vector machines (SVMs). e modeling is based on pavement roughness data collected periodically for a highvolume motorway during a seven-year period, on a yearly basis. e comparative study of the developed models concludes that the performance of the ANN model is slightly better compared to the SVM in terms of prediction accuracy. Further, the analysis results produce evidence in support of the statement that both models are capable to predict accurately pavement roughness; hence, they are deemed useful for supporting decision making of pavement maintenance and rehabilitation strategies. Background and ObjectivesRoad pavements deteriorate under the combined effect of traffic loading and environmental conditions. Performance is a general term describing the way pavements' conditions change or satisfy their intended function offering an at least acceptable level of service to the road users over their design life. Over the past few decades, road agencies have established performance indicators to assess the effectiveness and efficiency of their service provision. Amongst others, an important indicator of pavement performance is ride quality. is is a rather subjective measure of performance that depends on (i) the physical properties of the pavement surface, (ii) the mechanical characteristics of the ride vehicle, and (iii) the standards of the road users concerning the acceptability of the perceived ride quality. Due to the subjectivity of the ride quality assessment, a lot of researchers had worked in the past to establish an objective indicator of pavement performance. Starting at the early 1960's with the development of present serviceability index (PSI) [1,2], nowadays the International Roughness Index (IRI) seems to have the broadest application for the assessment of ride quality [3][4][5].IRI is considered to be a good indicator of pavement performance in respect to road roughness. It is developed in order to be linear, portable, and stable with time. It is portable since it can be measured with a wide range of equipment giving the same results, and stable with time since it is defined as a mathematical transform of a measured profile; thus, it is not affected by the measurement procedure nor the characteristics of the vehicle used for profile measurement [6]. IRI is based on the concept of a true longitudinal profile, rather than the physical properties of a particular type of instrument [7].Following the identification and quantification of ride quality through IRI, several studies have been performed to identify the variables affecting roughness development in time, especially when a pavement management s...

show abstract

Pavement Roughness Modeling Using Back‐Propagation Neural Networks

Cited by 89 publications

References 2 publications

Prediction of IRI in short and long terms for flexible pavements: ANN and GMDH methods

Prediction of IRI in short and long terms for flexible pavements: ANN and GMDH methods

Bitümlü Sıcak Karışım Üstyapılarda Görülen Yüzey Bozulmaları ile Düzgünsüzlük Arasındaki İlişkilerin Modellenmesinde Bazı Yaklaşımlar

Soft Computing Models to Predict Pavement Roughness: A Comparative Study

Contact Info

Product

Resources

About