Variable selection using Mean Decrease Accuracy and Mean Decrease Gini based on Random Forest

Han, Hong; Guo, Xuerang; Yu, Hua

doi:10.1109/icsess.2016.7883053

Cited by 141 publications

(83 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In studies characterized by very high dimensionality, it is crucial to estimate the importance of each predictive variable in classifying the data in order to determine the variables performance. In order to detect the predictive power of the input variables within the RF algorithm, the Mean Decrease in Accuracy (MDA) and Mean Decreased Gini (MDG) for individual vegetation indices across all RF trees was analysed (Han et al, 2016). The Gini index is a measure of the homogeneity and purity of nodes and leaves.…”

Section: Validation Classification Accuracy Assessment and Comparisomentioning

confidence: 99%

Fine scale plant community assessment in coastal meadows using UAV based multispectral data

Villoslada

Bergamo

Ward

et al. 2020

Ecological Indicators

View full text Add to dashboard Cite

Highlights:-Plant communities in coastal wetlands are at risk due to the impacts of global change-Knowing the distribution of plant communities is essential for nature conservation-Communities distribution maps were produced using a UAV-based multispectral sensor-The Random Forest classifier yielded the highest classification accuracy-Species diversity and aboveground biomass affect the classification performance ABSTRACT Coastal meadows worldwide are subjected to habitat degradation due to abandonment, intensification and the impacts of global change. In order to protect and restore these habitats and ensure the supply of valuable ecosystem services, it is necessary to know the extent and location of plant communities in coastal meadows. In this study, five plant communities were mapped at very high resolution in three different study sites in West Estonia. A fixed wing UAV was used to obtain multispectral images and derive a set of vegetation indices. Two different image classification techniques were used to cluster the vegetation indices maps and produce plant community distribution maps. The highest classification accuracy was obtained using a Random Forest classifier and 13 vegetation indices. Additionally, the spectral characteristics of the training samples were correlated with aboveground biomass and species diversity. Both biomass and species diversity were positively correlated with the spectral diversity of training samples and are thus likely to have an effect on the classification accuracy. The results of this study highlight the need to utilize a wide array of vegetation indices and assess the spectral characteristics of training samples in order to obtain high classification accuracies and understand the nature of misclassification errors. The resulting maps provide a solid foundation for global change impact assessment and habitat management and restoration in coastal meadows.

show abstract

Section: Validation Classification Accuracy Assessment and Comparisomentioning

confidence: 99%

Fine scale plant community assessment in coastal meadows using UAV based multispectral data

Villoslada

Bergamo

Ward

et al. 2020

Ecological Indicators

View full text Add to dashboard Cite

show abstract

“…The Gini impurity metric accounts for how often a randomly selected component from a training set would be incorrectly labelled if it was randomly labelled according to the class distribution in a subset [61]. The mean decrease in the Gini, also known as Gini importance, is the total decrease in node impurities from splitting on the variable, averaged over all trees [62]. This is essentially a measure of how important a variable is for estimating the value of the target variable across all tress in the forest.…”

Section: Random Forestmentioning

confidence: 99%

Developing infrared spectroscopic detection for stratifying brain tumour patients: glioblastoma multiforme vs. lymphoma

Cameron

Butler

Smith

et al. 2019

Analyst

View full text Add to dashboard Cite

show abstract

“…To assess the relative importance of all available input variables (Table 2) aggregated to the ground as in Sect. 3.3 and to choose the most pertinent ones, an approach from Han et al (2016) has been adapted for regression. Assuming as before that M is the number of available input features, the method is described in Algorithm 1.…”

Section: Choice Of Input Featuresmentioning

confidence: 99%

RainForest: a random forest algorithm for quantitative precipitation estimation over Switzerland

et al. 2021

View full text Add to dashboard Cite

Abstract. Quantitative precipitation estimation (QPE) is a difficult task, particularly in complex topography, and requires the adjustment of empirical relations between radar observables and precipitation quantities, as well as methods to transform observations aloft to estimations at the ground level. In this work, we tackle this classical problem with a new twist, by training a random forest (RF) regression to learn a QPE model directly from a large database comprising 4 years of combined gauge and polarimetric radar observations. This algorithm is carefully fine-tuned by optimizing its hyperparameters and then compared with MeteoSwiss' current operational non-polarimetric QPE method. The evaluation shows that the RF algorithm is able to significantly reduce the error and the bias of the predicted precipitation intensities, especially for large and solid or mixed precipitation. In weak precipitation, however, and despite a posteriori bias correction, the RF method has a tendency to overestimate. The trained RF is then adapted to run in a quasi-operational setup providing 5 min QPE estimates on a Cartesian grid, using a simple temporal disaggregation scheme. A series of six case studies reveal that the RF method creates realistic precipitation fields, with no visible radar artifacts, that appear less smooth than the original non-polarimetric QPE and offers an improved performance for five out of six events.

show abstract

Variable selection using Mean Decrease Accuracy and Mean Decrease Gini based on Random Forest

Cited by 141 publications

References 2 publications

Fine scale plant community assessment in coastal meadows using UAV based multispectral data

Fine scale plant community assessment in coastal meadows using UAV based multispectral data

Developing infrared spectroscopic detection for stratifying brain tumour patients: glioblastoma multiforme vs. lymphoma

RainForest: a random forest algorithm for quantitative precipitation estimation over Switzerland

Contact Info

Product

Resources

About