English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

The acquisition of high-quality asphalt pavement inspection data is a key factor for road maintenance and management throughout the pavement’s life cycle. This paper establishes a data cleaning framework that is based on data mining and deep learning to eliminate abnormal data points and interpolate missing points to improve the accuracy of the original road inspection dataset. The first process in the proposed framework is to analyse the influential factors that are used to evaluate data quality and calculate the abnormality of the data through the confidence interval used in Gaussian fitting. Then, a deep artificial neural network is established to learn the mapping between the inspection data and data abnormality. The abnormal points are removed according to their abnormality level. Next, a second deep artificial neural network predicts the missing point values. Finally, by defining the overall cleanliness index of the dataset as the optimisation target, the steps are repeated until the cleanliness threshold is met. In this study, the proposed framework was applied to rut depth data cleaning for a highway maintenance project in Jiangsu Province, China. The cleanliness of the rut depth data increased by 6–95.75% after one cleaning cycle.

Data cleaning framework for highway asphalt pavement inspection data based on artificial neural networks