Article: Deep learning-based concrete compressive strength prediction with modified resilient backpropagation training Journal: International Journal of Intelligent Engineering Informatics (IJIEI) 2024 Vol.12 No.3 pp.276 - 301 Abstract: This article proposes a novel approach for predicting concrete compressive strength using deep learning techniques. It overcomes limitations of traditional methods like memory footprint, training time, and computational requirements for predicting concrete compressive strength. Currently various filter pruning techniques are used to compress models by removing irrelevant information, but they cannot decrease memory consumption due to their large parameters. So, the entropy-based filter pruning is suggested to reduce the complexity of the model by decreasing the parameters. Then for training the CNN model, the modified resilient backpropagation technique (MRPROP) is suggested, because the previous backpropagation techniques take more time for training and also it loss the accuracy. This MRPROP improve the efficiency and convergence of CNN training and also it updates the models weight. The proposed approach demonstrated superior performance in mean squared error, root mean squared error, loss function, and regression analysis, as per the experimental results. Inderscience Publishers - linking academia, business and industry through research

Title: Deep learning-based concrete compressive strength prediction with modified resilient backpropagation training

Authors: M. Adams Joe; J. Sahaya Ruben; M. Prem Anand; M. Anand

Addresses: Department of Civil and Mechanical Engineering, Middle East College, Muscat, Sultanate of Oman ' Rohini College of Engineering and Technology, Anjugramam 629401, Tamil Nadu, India ' Department of Civil Engineering, VSVN Polytechnic College, Virudhunagar 626001, Tamil Nadu, India ' Department of Civil Engineering, Annamalai Polytechnic College, Chettinad 630102, Tamil Nadu, India

Abstract: This article proposes a novel approach for predicting concrete compressive strength using deep learning techniques. It overcomes limitations of traditional methods like memory footprint, training time, and computational requirements for predicting concrete compressive strength. Currently various filter pruning techniques are used to compress models by removing irrelevant information, but they cannot decrease memory consumption due to their large parameters. So, the entropy-based filter pruning is suggested to reduce the complexity of the model by decreasing the parameters. Then for training the CNN model, the modified resilient backpropagation technique (MRPROP) is suggested, because the previous backpropagation techniques take more time for training and also it loss the accuracy. This MRPROP improve the efficiency and convergence of CNN training and also it updates the models weight. The proposed approach demonstrated superior performance in mean squared error, root mean squared error, loss function, and regression analysis, as per the experimental results.

Keywords: machine learning; deep learning; convolutional neural network; CNN; pruning technique; backpropagation.

DOI: 10.1504/IJIEI.2024.140164

International Journal of Intelligent Engineering Informatics, 2024 Vol.12 No.3, pp.276 - 301

Received: 30 Oct 2023
Accepted: 19 Mar 2024
Published online: 26 Jul 2024 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article

Title: Deep learning-based concrete compressive strength prediction with modified resilient backpropagation training

Keep up-to-date