Accuracy and diversity-aware multi-objective approach for random forest construction

Karabadji, Nour El Islem; Korba, Abdelaziz Amara; Assi, Ali; Séridi, Hamid; Aridhi, Sabeur; Dhifli, Wajdi

doi:10.1016/j.eswa.2023.120138

Cited by 44 publications

(8 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This helps measure the similarities between the data points based on the supervised task. Overall, the Random Forest classification was used to find similarities between data points by comparing them to each other using a grouping of decision trees (Karabadji et al, 2023).…”

Section: Discussionmentioning

confidence: 99%

Climate change and topographic differences influence grassland vegetation greening across environmental gradients

Xun,

An,

2024

Front. Environ. Sci.

View full text Add to dashboard Cite

Despite the research on the responses of grassland vegetation to climate change and topography has advance worldwide, the large-scale importance of these parameters to grassland vegetation greening in arid regions across environmental gradients is unclear. To address this, in this study, we applied MODIS Normalized Difference Vegetation Index (NDVI) data and trend analysis methods to measure the spatial–temporal variation in grassland vegetation greening in central Eurasia. Multiple regression models and hierarchical partitioning were used to quantify the importance of climate [annual precipitation (AP), annual mean temperature (AMT), relative humidity (RH)] and topography [elevation (ELE), aspect (ASP), topographic position index (TPI)] to the NDVI. The results showed that there was a significant increasing trend in the NDVI of meadows, but not other grassland types, from 2000 to 2021 (3.3 × 10−3/year, p < 0.05). Additionally, the responses of the NDVI to climate and topography in deserts were positively correlated with RH, AP, and ELE. Meanwhile, the dependence of NDVI on climate and topography decreased with increasing RH. Under conditions of escalating AMT and AP, RH and ELE independently contributed to explaining the NDVI. However, RH may be the key determinant of long-term NDVI stabilization in arid grassland. These findings underscore the significance of vegetation–climate–topography feedback and can inform the development of more comprehensive and effective climate mitigation and adaptation strategies.

show abstract

Section: Discussionmentioning

confidence: 99%

Climate change and topographic differences influence grassland vegetation greening across environmental gradients

Xun,

An,

2024

Front. Environ. Sci.

View full text Add to dashboard Cite

show abstract

“…Random forests have good noise resistance and are not easily overfitting. 33 KNN is considered one of the simplest algorithms in machine learning, and it has a wide range of applications, high accuracy, and is not sensitive to outliers. 34 2.7.…”

Section: Chromatographic Conditions and Methods Validationmentioning

confidence: 99%

“…Its basic idea is to construct a large number of decision trees separately to vote on the classification results and finally combine the results of all decision trees to determine the category of the sample. Random forests have good noise resistance and are not easily overfitting . KNN is considered one of the simplest algorithms in machine learning, and it has a wide range of applications, high accuracy, and is not sensitive to outliers …”

Section: Methodsmentioning

confidence: 99%

Fast Discrimination and Quantification Analysis of Atractylodis rhizoma Using NIR Spectroscopy Coupled with Chemometrics Tools

Peng,

He,

Wang

et al. 2024

J. Agric. Food Chem.

View full text Add to dashboard Cite

In this study, near-infrared (NIR) spectroscopy and high-performance liquid chromatography (HPLC) combined with chemometrics tools were applied for quick discrimination and quantitative analysis of different varieties and origins of Atractylodis rhizoma samples. Based on NIR data, orthogonal partial least squares discriminant analysis (OPLS-DA) and K-nearest neighbor (KNN) models achieved greater than 90% discriminant accuracy of the three species and two origins of Atractylodis rhizoma. Moreover, the contents of three active ingredients (atractyloxin, atractylone, and β-eudesmol) in Atractylodis rhizoma were simultaneously determined by HPLC. There are significant differences in the content of the three components in the samples of Atractylodis rhizoma from different varieties and origins. Then, partial least squares regression (PLSR) models for the prediction of atractyloxin, atractylone, and β-eudesmol content were successfully established. The complete Atractylodis rhizoma spectra gave rise to good predictions of atractyloxin, atractylone, and β-eudesmol content with R 2 values of 0.9642, 0.9588, and 0.9812, respectively. Based on the results of this present research, it can be concluded that NIR is a great nondestructive alternative to be applied as a rapid classification system by the drug industry.

show abstract

“…The required steps to design an RF paradigm are as follows 54 : Step 1: The RF topology is developed with different sampling methods and considering the bootstrapping for employed replacement. On the other hand, it is necessary to generate n training sets after getting the experienced sample n times with n times.…”

Section: Machine Learning Methodsmentioning

confidence: 99%

Applying feature selection and machine learning techniques to estimate the biomass higher heating value

Abdollahi,

Ranjbar,

Razeghi Jahromi

2023

Sci Rep

View full text Add to dashboard Cite

The biomass higher heating value (HHV) is an important thermal property that determines the amount of recoverable energy from agriculture byproducts. Precise laboratory measurement or accurate prediction of the HHV is essential for designing biomass conversion equipment. The current study combines feature selection scenarios and machine learning tools to establish a general model for estimating biomass HHV. Multiple linear regression and Pearson’s correlation coefficients justified that volatile matter, nitrogen, and oxygen content of biomass samples have a slight effect on the HHV and it is better to ignore them during the HHV modeling. Then, the prediction performance of random forest, multilayer and cascade feedforward neural networks, group method of data handling, and least-squares support vector regressor are compared to determine the intelligent estimator with the highest accuracy toward biomass HHV prediction. The ranking test shows that the multilayer perceptron neural network better predicts the HHV of 532 biomass samples than the other intelligent models. This model presents the outstanding absolute average relative error of 2.75% and 3.12% and regression coefficients of 0.9500 and 0.9418 in the learning and testing stages. The model performance is also superior to a recurrent neural network which was recently developed in the literature using the same databank.

show abstract

Accuracy and diversity-aware multi-objective approach for random forest construction

Cited by 44 publications

References 22 publications

Climate change and topographic differences influence grassland vegetation greening across environmental gradients

Climate change and topographic differences influence grassland vegetation greening across environmental gradients

Fast Discrimination and Quantification Analysis of Atractylodis rhizoma Using NIR Spectroscopy Coupled with Chemometrics Tools

Applying feature selection and machine learning techniques to estimate the biomass higher heating value

Contact Info

Product

Resources

About