Application of evolutionary deep learning algorithm in construction engineering management system

The application of construction project management system is crucial for improving work efficiency and operational convenience. However, in order to further improve the application level and efficiency of the system, this study aims to optimize deep learning algorithms and apply them to the construc...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Systems and soft computing Jg. 7; S. 200317
1. Verfasser: Yang, Zhe
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier B.V 01.12.2025
Elsevier
Schlagworte:
Construction engineering
Deep learning algorithm
Evolutionary
Management System
Office Automation
Office Automation
Management System
Evolutionary
Construction engineering
Deep learning algorithm
ISSN:2772-9419, 2772-9419
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The application of construction project management system is crucial for improving work efficiency and operational convenience. However, in order to further improve the application level and efficiency of the system, this study aims to optimize deep learning algorithms and apply them to the construction project management system. The goal of this work is to develop a construction project management platform based on optimized evolutionary deep learning algorithms. Evolutionary computation strategy has been introduced in learning network models. Compared with other classic deep learning models, the optimized evolutionary deep learning algorithm model has significantly higher classification training accuracy and testing accuracy. The optimized evolutionary deep learning algorithm model can be applied to the field of construction project management. Based on this model, the development platform can be regarded as the "neurons" in the neural network structure, and through the collaboration of various components, a personalized management information system that meets user needs can be formed. Designed the structure, logical structure, and functional modules of the management system. The design process can provide experience for the design of similar management systems. This study optimized deep learning algorithms and introduced evolutionary computation strategies. By comparing with other classic deep learning models, we found that the optimized evolutionary deep learning algorithm model significantly improved the accuracy of classification training and testing. Through the collaboration of various components, a personalized management information system that meets user needs can be formed. We have designed the structure, logical structure, and functional modules of the management system, and verified its effectiveness through actual testing.
ISSN:2772-9419
2772-9419
DOI:10.1016/j.sasc.2025.200317