Building Classification Using Random Forest to Develop a Geodatabase for Probabilistic Hazard Information

Kim, Jooho; Hatzis, Joshua J.; Klockow, Kim; Campbell, Patrick A.

doi:10.1061/(asce)nh.1527-6996.0000561

Cited by 4 publications

(1 citation statement)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, among different measures of proximity (e.g., Euclidean Distance, Cosine Similarity, and Jaccard Similarity), Euclidean Distance is the most commonly used in the case of numeric predictors (Melhem and Cheng 2003). RF algorithm is an ensemble machine learning technique whose outcome is based on the majority voting of multiple decision tree models (Breiman 1996;Cutler et al 2007;Kim et al 2022). RF is very tolerant to outliers and noise, unlikely to overfitting, and has a good prediction accuracy (Sun et al 2020).…”

Section: Predictive Modelsmentioning

confidence: 99%

Hybrid feature selection framework for predicting bridge deck conditions

Omar¹,

Moselhi²

2022

ITcon

View full text Add to dashboard Cite

Bridge decks’ maintenance funding requirements are influenced by bridge decks' current and predicted future conditions. Additionally, the serviceability of bridges may be negatively impacted by the degradation of bridge decks. Bridge inspections require considerable effort, time, cost, and resources; besides, such inspections may introduce hazards and safety concerns. This paper introduces a data-driven hybrid feature selection framework for predicting bridge deck deterioration conditions and applying it to a bridge deck in Iowa State, USA. Firstly, the Boruta algorithm, stepwise regression, and multi-layer perceptron are employed to find the best subset of features that contribute to bridge deck deterioration. Then, four classification models were developed using the best feature subset of features, namely k-nearest neighbours, random forest, artificial neural networks, and deep neural networks. The hyperparameters of the models were optimized to get their best performance. The developed models showed comparable performance, and the random forest model outperformed the other models in prediction accuracy with fewer misclassifications. The developed models are thought to reduce field inspections and give insights into the most influential factors in bridge deck deterioration conditions.

show abstract