Comparison of Random Forest and Gradient Boosting Machine Models for Predicting Demolition Waste Based on Small Datasets and Categorical Variables

Cha, Gi-Wook; Moon, Hyeun-Jun; Kim, Young-Chan

doi:10.3390/ijerph18168530

Cited by 57 publications

(40 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The GBM is a forward learning ensemble methodology, under the rationale that good predictive results can be obtained through increasingly re ned approximations, and it builds regression trees on all factors assuming that each tree is built in parallel. Like ours, some studies have shown the excellent predictive performance of the GBM as compared with other models [33,34]. Besides the identi cation of best machine learning model, the key nding of this survey was the selection of a minimal number of factors according to their important contributions, including age of children, eating speed, number of relatives with obesity, sweet drinking, and paternal education.…”

Section: Discussionmentioning

confidence: 85%

Machine/Deep Learning-based Approaches to Predict Overweight or Obesity in Chinese Preschool-Aged Children

Wang

Yang

Pang

et al. 2022

Preprint

View full text Add to dashboard Cite

Objectives: We adopted the machine learning and deep learning algorithms to explore risk profiling for overweight and obesity in Chinese preschool-aged children.Methods: This is a cross-sectional survey, and was conducted between September and December in 2020 at Beijing and Tangshan. Using a stratified cluster random sampling strategy, children 3-6 years of age from 30 kindergartens were enrolled. Data were analyzed using community PyCharm.Results: A total of 9478 children were eligible for inclusion, 1250 children with overweight or obesity, and they were randomly divided into the training group and testing group in a 6:4 ratio. After the training and testing process, the SVM (accuracy: 0.9457) was ranked as the best algorithm, followed by the GBM (accuracy: 0.9454) as reflected by model accuracy. As reflected by other performance indexes, the GBM had the highest F1 score (0.7748), followed by the SVM with the F1 score at 0.7731. After importance ranking, the top five factors seemed sufficient to obtain descent performance under the GBM algorithm, including age of children, eating speed, number of relatives with obesity, sweet drinking, and paternal education, which was further reinforced by a classical deep learning sequential model. Conclusions: We identified five factors relating to children and parents that can help differentiate children with overweight or obesity from general children. Further validations are necessary.

show abstract

Section: Discussionmentioning

confidence: 85%

Machine/Deep Learning-based Approaches to Predict Overweight or Obesity in Chinese Preschool-Aged Children

Wang

Yang

Pang

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…To verify model performance, we applied leave-one-out cross-validation, a special case of k -fold cross-validation; this method can achieve more stable results than k -fold cross-validation for small datasets because it uses all samples for testing and training to ensure sufficient sample sizes [ 50 , 51 , 52 , 53 , 54 , 55 ].…”

Section: Methodsmentioning

confidence: 99%

Developing a Prediction Model of Demolition-Waste Generation-Rate via Principal Component Analysis

Cha

Choi

Hong

et al. 2023

IJERPH

Self Cite

View full text Add to dashboard Cite

Construction and demolition waste accounts for a sizable proportion of global waste and is harmful to the environment. Its management is therefore a key challenge in the construction industry. Many researchers have utilized waste generation data for waste management, and more accurate and efficient waste management plans have recently been prepared using artificial intelligence models. Here, we developed a hybrid model to forecast the demolition-waste-generation rate in redevelopment areas in South Korea by combining principal component analysis (PCA) with decision tree, k-nearest neighbors, and linear regression algorithms. Without PCA, the decision tree model exhibited the highest predictive performance (R2 = 0.872) and the k-nearest neighbors (Chebyshev distance) model exhibited the lowest (R2 = 0.627). The hybrid PCA–k-nearest neighbors (Euclidean uniform) model exhibited significantly better predictive performance (R2 = 0.897) than the non-hybrid k-nearest neighbors (Euclidean uniform) model (R2 = 0.664) and the decision tree model. The mean of the observed values, k-nearest neighbors (Euclidean uniform) and PCA–k-nearest neighbors (Euclidean uniform) models were 987.06 (kg·m−2), 993.54 (kg·m−2) and 991.80 (kg·m−2), respectively. Based on these findings, we propose the k-nearest neighbors (Euclidean uniform) model using PCA as a machine-learning model for demolition-waste-generation rate predictions.

show abstract

“…Consequently, the risk of selecting misclassified samples for the training set rises, and a greater proportion of instances are correctly classified [40], [41]. However, boosting is a continual process of constructing classifiers enhanced by the weights of weak classifiers from previous rounds, which contributes to reducing dataset volatility and variability.…”

Section: Figure 2 Workflows Of Boosting and Bagging Techniquementioning

confidence: 99%

Day-Ahead Electricity Price Forecasting Based on Hybrid Regression Model

et al. 2022

View full text Add to dashboard Cite

Since the deregulation of the power markets, accurate short term Electricity Price Forecasting (EPF) has become crucial in maximizing economic benefits and mitigating power market risks. Due to the challenging characteristics of electricity price, which comprise high volatility, rapid spike, and seasonality, developing robust machine learning prediction tools becomes cumbersome. This work proposes a new hybrid machine learning method for a day-ahead EPF, which involves linear regression Automatic Relevance Determination (ARD) and ensemble bagging Extra Tree Regression (ETR) models. Considering that each model of EPF has its own strengths and weaknesses, combining several models gives more accurate predictions and overcomes the limitations of an individual model. Therefore, the linear ARD model is applied because it can efficiently deal with trend and seasonality variations; on the other hand, the ensemble ETR model is employed to learn from interactions, and thus combining ARD with ETR produces robust forecasting outcomes. The effectiveness of the proposed method was validated using a data set from the Nord Pool electricity market. The proposed model is compared with other models to demonstrate its superiority using performance matrices, such as Mean Absolute Error (MAE) and Root Mean Square Error (RMSE). Experiment results show that the proposed method achieves lower forecasting errors than other individual and hybrid models. Additionally, a comparative study has been performed against previous works, where forecasting measurement of the proposed method outperforms previous works' accuracy in forecasting electricity price.INDEX TERMS Electricity price forecasting, electricity market, hybrid regression models, short-term dayahead prediction, time series analysis.

show abstract

Comparison of Random Forest and Gradient Boosting Machine Models for Predicting Demolition Waste Based on Small Datasets and Categorical Variables

Cited by 57 publications

References 40 publications

Machine/Deep Learning-based Approaches to Predict Overweight or Obesity in Chinese Preschool-Aged Children

Machine/Deep Learning-based Approaches to Predict Overweight or Obesity in Chinese Preschool-Aged Children

Developing a Prediction Model of Demolition-Waste Generation-Rate via Principal Component Analysis

Day-Ahead Electricity Price Forecasting Based on Hybrid Regression Model

Contact Info

Product

Resources

About