Skip to main content

Research Repository

Advanced Search

A Lightweight FCNN-Driven Approach to Concrete Composition Extraction in a Distributed Environment

Lu, Hui; Kamoto, Kondwani Michael; Liu, Qi; Zhang, Yiming; Liu, Xiaodong; Xu, Xiaolong; Qi, Lianyong


Hui Lu

Kondwani Michael Kamoto

Qi Liu

Yiming Zhang

Xiaolong Xu

Lianyong Qi


It is of great significance to study the positive characteristics of concrete bearing cracks, fire and other adverse environment for the safety of human life and property and the protection of environmental resources. However, there are still some challenges in traditional concrete composition evaluation methods. On the one hand, the traditional method needs a lot of experimental work, which is time-consuming and laborious; On the other hand, the cost of new technology is high, and its applicability needs further study. Therefore, this paper proposes an improved lightweight model based on fully connected neural network (FCNN) to discover the relationship between the performance of different concrete mixtures and the visual (image) performance of the final synthesis process, so as to realize the prediction of concrete composition. The model is built in a distributed environment, and it can achieve lightweight and convenient effect through remote call learning model. The experimental results show that the method greatly improves the accuracy of concrete composition prediction.

Presentation Conference Type Conference Paper (Published)
Conference Name 11th EAI International Conference, CloudComp 2021
Start Date Dec 9, 2021
End Date Dec 10, 2021
Acceptance Date Oct 6, 2021
Online Publication Date Mar 23, 2022
Publication Date 2022
Deposit Date Oct 17, 2022
Publisher Springer
Pages 40-46
Series Title Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering
Series Number 430
Book Title Cloud Computing: 11th EAI International Conference, CloudComp 2021, Virtual Event, December 9–10, 2021, Proceedings
ISBN 978-3-030-99190-6
Keywords Concrete, Lightweight FCNN, Distributed
Public URL