Application of data handling techniques to predict pavement performance

Saride, Sireesh and Peddinti, Pranav R.T. and Basha, B. Munwar (2021) Application of data handling techniques to predict pavement performance. Handbook of Statistics, 44. pp. 105-127. ISSN 01697161

Full text not available from this repository. (Request a copy)

Abstract

The present study discusses the design of pavements and the importance of big data handling in improving their performance. A comprehensive framework based on a simple natural language processing technique is presented to reduce the computational time and error in data handling for pavement applications. The application of the proposed method to automate a graphical user interface (UI) adopted in pavement design is demonstrated. The proposed method was found to reduce the run-time by about 83% as compared to the conventional procedures. The proposed framework is highly flexible and can be adapted to extract data from various file formats and automate UIs at ease. To present the potential of this framework, about 0.2 million data sets representing pavement geometry and material properties were generated using language processing algorithms. Further, robust non-linear regression equations for calculating pavement damage in terms of fatigue and rutting strains were developed by using automated data processing through the pavement design interface.

[error in script]
IITH Creators:
IITH CreatorsORCiD
Saride, SireeshUNSPECIFIED
Peddinti, Pranav R.T.UNSPECIFIED
Basha, B. MunwarUNSPECIFIED
Item Type: Article
Uncontrolled Keywords: Automation; Data handling; Fatigue; Pavement; Regression; Rutting; User interface (UI)
Subjects: Civil Engineering
Divisions: Department of Civil Engineering
Depositing User: . LibTrainee 2021
Date Deposited: 17 Jul 2021 11:39
Last Modified: 17 Jul 2021 11:39
URI: http://raiith.iith.ac.in/id/eprint/8399
Publisher URL: http://doi.org/10.1016/bs.host.2020.07.001
Related URLs:

Actions (login required)

View Item View Item
Statistics for RAIITH ePrint 8399 Statistics for this ePrint Item