Volume- 10
Issue- 1
Year- 2023
DOI: 10.55524/ijirem.2023.10.1.12 | DOI URL: https://doi.org/10.55524/ijirem.2023.10.1.12
Crossref
This is an Open Access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0) (http://creativecommons.org/licenses/by/4.0)
Article Tools: Print the Abstract | Indexing metadata | How to cite item | Email this article | Post a Comment
The main aim of the bridge maintenance strategy is to evaluate the performance based on their past conditions and taking appropriate actions for future decisions. Further, taking the appropriate actions at right time reduces the maintenance cost of the bridges. Earlier, man-power-based methods are used for bridge maintenance strategy. However, this method is time consuming, human error while predicting the conditions, and more cost demandable. To overcome these issues, machine learning models-based bridge maintenance strategy are designed in which machine learning models are trained with past conditions of the bridges and future conditions are predict. Thus, this paper proposes a concrete deck performance model based on the hybridization of machine learning algorithm. The main contribution of this work is to enhance the performance of the model by hybrid the prediction of machine learning algorithms. This is achieved by ensemble learning and artificial neural network algorithm. Besides that, feature selection algorithm is applied in the pre-processing of the model. To validate the performance of the proposed model, standard national bridge inventory (NBI) database was taken under consideration and various performance metrics are measured for it. The result shows the proposed model achieves high value of these performance metrics such as accuracy (≅0.90207
), recall (≅0.9363
), precision (≅0.8855)
, and F-score (≅0.92935
) and performance superior over autoencoder and random forest algorithm.
No. of Downloads: 20 | No. of Views: 1088
