Machine learning models for predicting the residual value of heavy construction equipment: An evaluation of modified decision tree, LightGBM, and XGBoost regression

Shehadeh, Ali; Alshboul, Odey; Mamlook, Rabia Emhamed Al; Hamedat, Ola

doi:10.1016/j.autcon.2021.103827

Cited by 194 publications

(78 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For the SMOTE-set , again, the XGBoost model possesses the highest

, and the lowest values of RMSE and MAPE. This result is in agreement with the literature [ 44 , 52 , 53 , 54 ] and shows that the decision-tree models perform better than neural network models to learn hidden features on relatively midsize datasets. However, performing well on the test set still does not guarantee the accuracy of decision-tree-based regression models when inferred on blind datasets generated outside the scope of training set or interpolated within the training sets (see Section 4.4 ).…”

Section: Results and Discussionsupporting

confidence: 92%

A Meta-Model to Predict the Drag Coefficient of a Particle Translating in Viscoelastic Fluids: A Machine Learning Approach

2022

View full text Add to dashboard Cite

This study presents a framework based on Machine Learning (ML) models to predict the drag coefficient of a spherical particle translating in viscoelastic fluids. For the purpose of training and testing the ML models, two datasets were generated using direct numerical simulations (DNSs) for the viscoelastic unbounded flow of Oldroyd-B (OB-set containing 12,120 data points) and Giesekus (GI-set containing 4950 data points) fluids past a spherical particle. The kinematic input features were selected to be Reynolds number, 0<Re≤50, Weissenberg number, 0≤Wi≤10, polymeric retardation ratio, 0<ζ<1, and shear thinning mobility parameter, 0<α<1. The ML models, specifically Random Forest (RF), Deep Neural Network (DNN) and Extreme Gradient Boosting (XGBoost), were all trained, validated, and tested, and their best architecture was obtained using a 10-Fold cross-validation method. All the ML models presented remarkable accuracy on these datasets; however the XGBoost model resulted in the highest R2 and the lowest root mean square error (RMSE) and mean absolute percentage error (MAPE) measures. Additionally, a blind dataset was generated using DNSs, where the input feature coverage was outside the scope of the training set or interpolated within the training sets. The ML models were tested against this blind dataset, to further assess their generalization capability. The DNN model achieved the highest R2 and the lowest RMSE and MAPE measures when inferred on this blind dataset. Finally, we developed a meta-model using stacking technique to ensemble RF, XGBoost and DNN models and output a prediction based on the individual learner’s predictions and a DNN meta-regressor. The meta-model consistently outperformed the individual models on all datasets.

show abstract

“…For the SMOTE-set , again, the XGBoost model possesses the highest

Section: Results and Discussionsupporting

confidence: 92%

A Meta-Model to Predict the Drag Coefficient of a Particle Translating in Viscoelastic Fluids: A Machine Learning Approach

2022

View full text Add to dashboard Cite

show abstract

“…However, when the computer is used to sort out the data and present the 3D image, the impact experience for the students is more intuitive. It can promote their enthusiasm and learning motivation for building architecture and stimulate the students' ability of hands-on operation [ 25 ], as shown in Figure 11 .…”

Section: Methodsmentioning

confidence: 99%

Design of Online Ideological and Political Teaching of Building Architecture from the Perspective of Machine Learning

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Under the background of the rapid progress of machine learning (ML) and information technology, the traditional classroom model is gradually replaced by the self-media classroom. This thesis aims to solve the problems of understanding abstract content and limited teaching in practical teaching. Based on the ideological and political integration teaching of building architecture, the online classroom design principle reflects the classroom optimization and design principle of building architecture from the perspective of ML. The data advantage is utilized, and the classroom application model is established using the deep learning algorithm through information input. The scene of field survey and building construction is presented from the perspective of mechanization. The simulated results are displayed in the classroom through online teaching combined with ideological education and political teaching mode. The research shows that ML combined with online classroom design breaks through the book face-to-face teaching mode of the traditional classroom through the dynamic demonstration of actual construction, the virtual building structure, and the innovative design of building material entity. It stimulates students’ interest in architecture courses, improves the overall learning efficiency, and promotes the ideological and political integration of building architecture courses. Besides, it is conducive to cultivating comprehensive architectural talents in the new era.

show abstract

“…Extreme Gradient Boosting (XGBoost), proposed by Chen and Guestrin 49 , is an efficient and scalable ensemble algorithm based on gradient boosted trees 16 , 50 . XGBoost has been used in a wide range of engineering fields, resulting in outstanding performance due to the advantages of parallel tree boosting and using various regularization techniques 13 , 51 , 52 . XGBoost is a stable algorithm with low bias and variance, handling outliers 24 , 53 .…”

Section: Methodsmentioning

confidence: 99%

Modeling of energy consumption factors for an industrial cement vertical roller mill by SHAP-XGBoost: a "conscious lab" approach

Fatahi

Nasiri

Dadfar

et al. 2022

Sci Rep

View full text Add to dashboard Cite

Cement production is one of the most energy-intensive manufacturing industries, and the milling circuit of cement plants consumes around 4% of a year's global electrical energy production. It is well understood that modeling and digitalizing industrial-scale processes would help control production circuits better, improve efficiency, enhance personal training systems, and decrease plants' energy consumption. This tactical approach could be integrated using conscious lab (CL) as an innovative concept in the internet age. Surprisingly, no CL has been reported for the milling circuit of a cement plant. A robust CL interconnect datasets originated from monitoring operational variables in the plants and translating them to human basis information using explainable artificial intelligence (EAI) models. By initiating a CL for an industrial cement vertical roller mill (VRM), this study conducted a novel strategy to explore relationships between VRM monitored operational variables and their representative energy consumption factors (output temperature and motor power). Using SHapley Additive exPlanations (SHAP) as one of the most recent EAI models accurately helped fill the lack of information about correlations within VRM variables. SHAP analyses highlighted that working pressure and input gas rate with positive relationships are the key factors influencing energy consumption. eXtreme Gradient Boosting (XGBoost) as a powerful predictive tool could accurately model energy representative factors by R-square ever 0.80 in the testing phase. Comparison assessments indicated that SHAP-XGBoost could provide higher accuracy for VRM-CL structure than conventional modeling tools (Pearson correlation, Random Forest, and Support vector regression.

show abstract

Machine learning models for predicting the residual value of heavy construction equipment: An evaluation of modified decision tree, LightGBM, and XGBoost regression

Cited by 194 publications

References 19 publications

A Meta-Model to Predict the Drag Coefficient of a Particle Translating in Viscoelastic Fluids: A Machine Learning Approach

A Meta-Model to Predict the Drag Coefficient of a Particle Translating in Viscoelastic Fluids: A Machine Learning Approach

Design of Online Ideological and Political Teaching of Building Architecture from the Perspective of Machine Learning

Modeling of energy consumption factors for an industrial cement vertical roller mill by SHAP-XGBoost: a "conscious lab" approach

Contact Info

Product

Resources

About