Feature selection based on artificial bee colony and gradient boosting decision tree

Rao, Haidi; Shi, Xianzhang; Rodrigue, Ahoussou Kouassi; Feng, Juanjuan; Xia, Yingchun; Elhoseny, Mohamed; Yuan, Xiaohui; Gu, Lichuan

doi:10.1016/j.asoc.2018.10.036

Cited by 440 publications

(166 citation statements)

References 25 publications

Supporting

Mentioning

133

Contrasting

Order By: Relevance

“…GBDT models can handle mixed types of data for both classification and regression tasks. These techniques often perform feature selection and are robust against outliers [68]. GBDT models, however, have not been widely applied to mangrove AGB retrieval.…”

Section: Gradient Boosting Decision Tree (Gbdt) Algorithmsmentioning

confidence: 99%

Comparison of Machine Learning Methods for Estimating Mangrove Above-Ground Biomass Using Multiple Source Remote Sensing Data in the Red River Delta Biosphere Reserve, Vietnam

et al. 2020

View full text Add to dashboard Cite

This study proposes a hybrid intelligence approach based on an extreme gradient boosting regression and genetic algorithm, namely, the XGBR-GA model, incorporating Sentinel-2, Sentinel-1, and ALOS-2 PALSAR-2 data to estimate the mangrove above-ground biomass (AGB), including small and shrub mangrove patches in the Red River Delta biosphere reserve across the northern coast of Vietnam. We used the novel extreme gradient boosting decision tree (XGBR) technique together with genetic algorithm (GA) optimization for feature selection to construct and verify a mangrove AGB model using data from a field survey of 105 sampling plots conducted in November and December of 2018 and incorporated the dual polarimetric (HH and HV) data of the ALOS-2 PALSAR-2 L-band and the Sentinel-2 multispectral data combined with Sentinel-1 (C-band VV and VH) data. We employed the root-mean-square error (RMSE) and coefficient of determination (R 2 ) to evaluate the performance of the proposed model. The capability of the XGBR-GA model was assessed via a comparison with other machine-learning (ML) techniques, i.e., the CatBoost regression (CBR), gradient boosted regression tree (GBRT), support vector regression (SVR), and random forest regression (RFR) models. The XGBR-GA model yielded a promising result (R 2 = 0.683, RMSE = 25.08 Mg·ha −1 ) and outperformed the four other ML models. The XGBR-GA model retrieved a mangrove AGB ranging from 17 Mg·ha −1 to 142 Mg·ha −1 (with an average of 72.47 Mg·ha −1 ). Therefore, multisource optical and synthetic aperture radar (SAR) combined with the XGBR-GA model can be used to estimate the mangrove AGB in North Vietnam. The effectiveness of the proposed method needs to be further tested and compared to other mangrove ecosystems in the tropics.

show abstract

Section: Gradient Boosting Decision Tree (Gbdt) Algorithmsmentioning

confidence: 99%

Comparison of Machine Learning Methods for Estimating Mangrove Above-Ground Biomass Using Multiple Source Remote Sensing Data in the Red River Delta Biosphere Reserve, Vietnam

et al. 2020

View full text Add to dashboard Cite

show abstract

“…The notion of dropping one or more variables within the dataset in the quest to help reduce dimensionality is certain. Therefore, the removal of 66.66% of the variables is acceptable since the 60% ratio of feature reduction is suitable, as orchestrated by the work of [35].…”

Section: A Variable Minimization Resultsmentioning

confidence: 99%

An Enhanced K-Nearest Neighbor Predictive Model through Metaheuristic Optimization

Delima¹

2020

IJACSA

View full text Add to dashboard Cite

The K-Nearest Neighbor (KNN) algorithm is vulnerable to noise, which is rooted in the dataset and has negative effects on its accuracy. Hence, various researchers employed variable minimization techniques before predicting the KNN in the quest so as to improve its predictive capability. The Genetic Algorithm (GA) is the most widely used metaheuristics for such purpose; however, the GA suffers a problem, which is its mating scheme bounded on its crossover operator. Thus, the use of the novel Inversed Bi-segmented Average Crossover (IBAX) was observed. In the present work, the crossover improved genetic algorithm (CIGAL) was instrumental in the enhancement of KNN's prediction accuracy. The use of the unmodified genetic algorithm had removed 13 variables; while the CIGAL then further removed 20 variables from the 30 total variables in the faculty evaluation dataset. Consequently, the integration of the CIGAL to the KNN (CIGAL-KNN) prediction model improved the KNN prediction accuracy to 95.53%. In contrast to the model of having the unmodified genetic algorithm (GA-KNN); the use of the lone KNN algorithm, the prediction accuracy is only at 89.94% and 87.15%, respectively. To validate the accuracy of the models, the use of the 10-folds cross-validation technique revealed a 93.13%, 89.27%, and 87.77% prediction accuracy of the CIGAL-KNN, GA-KNN, and KNN prediction models, respectively. The above results show that the CIGAL carried out an optimized GA performance and increased the accuracy of the KNN algorithm as a prediction model.

show abstract

“…Clearly, a much more detailed study is needed to understand trade-offs between all other design possibilities, other mechanical properties of brick-and-mortar, or mechanical behavior under different loading conditions. The presented RVE draws inspiration from previous analytical and numerical studies for the micromechanical modeling of composite materials 29,37,[48][49][50] . For reference, the FEA model predictions are compared to the measured properties of the nacre-inspired synthetic Al 2 O 3 /PMMA (poly(methyl methacrylate)) composite 28 , and an analytical model presented in ref.…”

Section: Discussionmentioning

confidence: 99%

Designing bioinspired brick-and-mortar composites using machine learning and statistical learning

2020

View full text Add to dashboard Cite

The brick-and-mortar structure inspired by nature, such as in nacre, is considered one of the most optimal designs for structural composites. Given the large number of design possibilities, extensive computational work is required to guide their manufacturing. Here, we propose a computational framework that combines statistical analysis and machine learning with finite element analysis to establish structure-property design strategies for brick-andmortar composites. Approximately 20,000 models with different geometrical designs were categorized into good and bad based on their failure modes, with statistical analysis of the results used to find the importance of each feature. Aspect ratio of the bricks and horizontal mortar thickness were identified as the main influencing features. A decision tree machine learning model was then established to draw the boundaries of good design space. This approach might be used for the design of brick-and-mortar composites with improved mechanical properties.

show abstract

Feature selection based on artificial bee colony and gradient boosting decision tree

Cited by 440 publications

References 25 publications

Comparison of Machine Learning Methods for Estimating Mangrove Above-Ground Biomass Using Multiple Source Remote Sensing Data in the Red River Delta Biosphere Reserve, Vietnam

Comparison of Machine Learning Methods for Estimating Mangrove Above-Ground Biomass Using Multiple Source Remote Sensing Data in the Red River Delta Biosphere Reserve, Vietnam

An Enhanced K-Nearest Neighbor Predictive Model through Metaheuristic Optimization

Designing bioinspired brick-and-mortar composites using machine learning and statistical learning

Contact Info

Product

Resources

About