Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Machine learning in construction and demolition waste management: Progress, challenges, and future directions
Abstract The application of machine learning contributes to intelligent and efficient management of construction and demolition waste, leading to a reduction in waste generation and an increased emphasis on recycling. This research conducts a comprehensive analysis of 98 journals related to the application of machine learning in construction waste management from 2012 to 2023 to identify current hot topics and emerging trends. The results reveal that machine learning is applied in four main areas and 15 subfields, specifically focusing on construction and demolition waste generation, on-site handling, transportation, and disposal. Various models, such as artificial neural networks, deep learning, convolutional neural networks, and support vector machines, demonstrate their effectiveness in different processes of construction and demolition waste management. The findings of this research will aid researchers in gaining a comprehensive understanding of the current state and future directions of machine learning in construction waste management.
Graphical abstract Display Omitted
Highlights A critical analysis of ninety-eight articles is conducted. Four main areas and fifteen subfields are identified. Machine learning algorithms and workflow utilization are analyzed. Five research challenges and five future directions are identified.
Machine learning in construction and demolition waste management: Progress, challenges, and future directions
Abstract The application of machine learning contributes to intelligent and efficient management of construction and demolition waste, leading to a reduction in waste generation and an increased emphasis on recycling. This research conducts a comprehensive analysis of 98 journals related to the application of machine learning in construction waste management from 2012 to 2023 to identify current hot topics and emerging trends. The results reveal that machine learning is applied in four main areas and 15 subfields, specifically focusing on construction and demolition waste generation, on-site handling, transportation, and disposal. Various models, such as artificial neural networks, deep learning, convolutional neural networks, and support vector machines, demonstrate their effectiveness in different processes of construction and demolition waste management. The findings of this research will aid researchers in gaining a comprehensive understanding of the current state and future directions of machine learning in construction waste management.
Graphical abstract Display Omitted
Highlights A critical analysis of ninety-eight articles is conducted. Four main areas and fifteen subfields are identified. Machine learning algorithms and workflow utilization are analyzed. Five research challenges and five future directions are identified.
Machine learning in construction and demolition waste management: Progress, challenges, and future directions
Gao, Yu (Autor:in) / Wang, Jiayuan (Autor:in) / Xu, Xiaoxiao (Autor:in)
09.03.2024
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
Machine learning , Construction and demolition waste management , Literature review , Deep learning , Adaboost , Adaptive Boosting , ANN , Artificial Neural Network , ANO , Ant Colony Optimization , AP , Average Precision , CATPCA , Categorical Principal Component Analysis , CBAM , Convolutional Block Attention Module , C&DW , Construction and Demolition Waste , CNN , Convolutional Neural Network , DCNN , Deep Convolutional Neural Network , DL , Deep Learning , DT , Decision Tree , DW , Demolition Waste , ELM , Extreme Learning Machines , FA , Firefly Algorithm , GB , Gradient Boosting , GBDT , Gradient Boosting Decision Tree , GBM , Gradient Boosting Machines , GDP , Gross Domestic Product , GEP , Gene Expression Programming , GGBFS , Ground Granulated Blast Furnace Slag , GWO , Gray Wolf Optimizer , IoU , Intersection over Union , K-NN , K-Nearest Neighbors , LSTM , Long Short-Term Memory , LR , Linear Regression , MAE , Mean Absolute Error , ML , Machine Learning , MLP , Multi-Layer Perceptron , MLR , Multiple Linear Regression , mAP , mean Average Precision , mIoU , mean Intersection over Union , PCA , Principal Component Analysis , PSO , Particle Swarm Optimization , R , Correlation coefficient , R<sup>2</sup> , Coefficient of determination , RA , Recycled Aggregates , RAC , Recycled Aggregate Concrete , R-CNN , Region-based Convolutional Neural Network , RF , Random Forest , RGB , Red, Green, and Blue , RMSE , Root Mean Square Error , RNN , Recurrent Neural Networks , SVM , Support Vector Machine , SVMR , Support Vector Machine Regression , SVR , Support Vector Regression , VGG , Visual Geometry Group , XGB , Extreme Gradient Boost , YOLO , You Only Look Once
Construction Demolition Waste Management in Lebanon
| ASCE | 2012
Management of construction & demolition waste streams
| British Library Conference Proceedings | 1998