The role of decision tree representation in regression problems – An evolutionary perspective

Czajkowski, Marcin; Krȩtowski, Marek

doi:10.1016/j.asoc.2016.07.007

Cited by 75 publications

(19 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…SGB is one of the ensemble techniques proposed by Friedman [41]. Based on decision tree algorithm [42,43], SGB was improved by using boosting learning and editing error of decision trees. Like RF technique, SGB can solve all classification, as well as regression issues.…”

Section: Stochastic Gradient Boostingmentioning

confidence: 99%

A Comparative Study of Different Machine Learning Algorithms in Predicting the Content of Ilmenite in Titanium Placer

Bui

et al. 2020

Applied Sciences

View full text Add to dashboard Cite

In this study, the ilmenite content in beach placer sand was estimated using seven soft computing techniques, namely random forest (RF), artificial neural network (ANN), k-nearest neighbors (kNN), cubist, support vector machine (SVM), stochastic gradient boosting (SGB), and classification and regression tree (CART). The 405 beach placer borehole samples were collected from Southern Suoi Nhum deposit, Binh Thuan province, Vietnam, to test the feasibility of these soft computing techniques in estimating ilmenite content. Heavy mineral analysis indicated that valuable minerals in the placer sand are zircon, ilmenite, leucoxene, rutile, anatase, and monazite. In this study, five materials, namely rutile, anatase, leucoxene, zircon, and monazite, were used as the input variables to estimate ilmenite content based on the above mentioned soft computing models. Of the whole dataset, 325 samples were used to build the regarded soft computing models; 80 remaining samples were used for the models’ verification. Root-mean-squared error (RMSE), determination coefficient (R2), a simple ranking method, and residuals analysis technique were used as the statistical criteria for assessing the model performances. The numerical experiments revealed that soft computing techniques are capable of estimating the content of ilmenite with high accuracy. The residuals analysis also indicated that the SGB model was the most suitable for determining the ilmenite content in the context of this research.

show abstract

Section: Stochastic Gradient Boostingmentioning

confidence: 99%

A Comparative Study of Different Machine Learning Algorithms in Predicting the Content of Ilmenite in Titanium Placer

Bui

et al. 2020

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…Then, a regression model is generated for each leaf. After that, the RT is pruning the leaves for decreasing the error up to the optimum model [38].…”

Section: Regression Treesmentioning

confidence: 99%

Elliot and Symmetric Elliot Extreme Learning Machines for Gaussian Noisy Industrial Thermal Modelling

Salmeron

Ruiz-Celma

2018

Energies

View full text Add to dashboard Cite

This research proposes an Elliot-based Extreme Learning Machine approach for industrial thermal processes regression. The main contribution of this paper is to propose an Extreme Learning Machine model with Elliot and Symmetric Elliot activation functions that will look for the fittest number of neurons in the hidden layer. The methodological proposal is tested on an industrial thermal drying process. The thermal drying process is relevant in many industrial processes such as the food industry, biofuels production, detergents and dyes in powder production, pharmaceutical industry, reprography applications, textile industries and others. The methodological proposal of this paper outperforms the following techniques: Linear Regression, k-Nearest Neighbours regression, Regression Trees, Random Forest and Support Vector Regression. In addition, all the experiments have been benchmarked using four error measurements (MAE, MSE, MEADE, R 2 ).

show abstract

“…Much data is used in the regression when doing this. The aim of regression analysis is to estimate the output variables from new samples [3]- [6]. In literature, linear regression, support vector regression, multilayer perception (MLP), K-nearest neighbour (KNN) and the decision tree methodologies are usually employed for regression analysis.…”

Section: Introductionmentioning

confidence: 99%

“…It is an efficient nonparametric method, which can be used both for classification and regression [3]. Although regression trees are not as popular as classification trees, they are highly competitive with different machine learning algorithms and are often applied to many real-life problems [6]. Regression tree is a type of the machine learning tools that can satisfy both good prediction accuracy and easy interpretation, and therefore, have received extensive attention in the literature.…”

Section: Introductionmentioning

confidence: 99%

Estimating California Bearing Ratio Using Decision Tree Regression Analysis Using Soil Index and Compaction Parameters

Günaydın¹,

Özbeyaz²,

Söylemez³

2019

ijisae

View full text Add to dashboard Cite

California Bearing Ratio is used as an index of soil strength and bearing capacity. In the machine learning theory, a decision tree algorithm can help us to define preferences, risks, benefits and targets. In this study, the decision tree algorithm was employed for estimating California Bearing Ratio from the soil index and compaction parameters. There were seven inputs and one output in the study. In the analysis, we employed gravel, sand, fine grain, liquid limit, plastic limit, maximum dry unit weight and optimum water as inputs and California Bearing Ratio as output. The number of data was 124. In the decision tree algorithm, data were divided two for train and test groups. In addition, 10-fold cross validation process was applied to data in the analysis. Consequently, fine grain values used as input in the study were carried out to be very determinative for regression analysis. Decision tree regression analysis estimation indicated strong correlation (R = 0.89) between the output and target. It has been shown that the correlation equations obtained as a result of regression analysis are in satisfactory agreement with the test results.

show abstract

The role of decision tree representation in regression problems – An evolutionary perspective

Cited by 75 publications

References 25 publications

A Comparative Study of Different Machine Learning Algorithms in Predicting the Content of Ilmenite in Titanium Placer

A Comparative Study of Different Machine Learning Algorithms in Predicting the Content of Ilmenite in Titanium Placer

Elliot and Symmetric Elliot Extreme Learning Machines for Gaussian Noisy Industrial Thermal Modelling

Estimating California Bearing Ratio Using Decision Tree Regression Analysis Using Soil Index and Compaction Parameters

Contact Info

Product

Resources

About