A Diversity-Accuracy Measure for Homogenous Ensemble Selection

Zouggar, Souad Taleb; Adla, Abdelkader

doi:10.9781/ijimai.2018.06.005

Cited by 8 publications

(4 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this study, the base learner of the ensemble algorithms was the regression tree model, and thus, the ensemble was homogeneous. Since the diversity of the base learners has a great effect on the performance of an ensemble algorithm, heterogeneous ensemble algorithms (e.g., stacking) that integrate different base learners could further improve the accuracy of estimated AGB, and this technique will be considered in future studies [104][105][106].…”

Section: Discussionmentioning

confidence: 99%

An Evaluation of Eight Machine Learning Regression Algorithms for Forest Aboveground Biomass Estimation from Multiple Satellite Data Products

Zhang

Liang

et al. 2020

Remote Sensing

View full text Add to dashboard Cite

This study provided a comprehensive evaluation of eight machine learning regression algorithms for forest aboveground biomass (AGB) estimation from satellite data based on leaf area index, canopy height, net primary production, and tree cover data, as well as climatic and topographical data. Some of these algorithms have not been commonly used for forest AGB estimation such as the extremely randomized trees, stochastic gradient boosting, and categorical boosting (CatBoost) regression. For each algorithm, its hyperparameters were optimized using grid search with cross-validation, and the optimal AGB model was developed using the training dataset (80%) and AGB was predicted on the test dataset (20%). Performance metrics, feature importance as well as overestimation and underestimation were considered as indicators for evaluating the performance of an algorithm. To reduce the impacts of the random training-test data split and sampling method on the performance, the above procedures were repeated 50 times for each algorithm under the random sampling, the stratified sampling, and separate modeling scenarios. The results showed that five tree-based ensemble algorithms performed better than the three nonensemble algorithms (multivariate adaptive regression splines, support vector regression, and multilayer perceptron), and the CatBoost algorithm outperformed the other algorithms for AGB estimation. Compared with the random sampling scenario, the stratified sampling scenario and separate modeling did not significantly improve the AGB estimates, but modeling AGB for each forest type separately provided stable results in terms of the contributions of the predictor variables to the AGB estimates. All the algorithms showed forest AGB were underestimated when the AGB values were larger than 210 Mg/ha and overestimated when the AGB values were less than 120 Mg/ha. This study highlighted the capability of ensemble algorithms to improve AGB estimates and the necessity of improving AGB estimates for high and low AGB levels in future studies.

show abstract

Section: Discussionmentioning

confidence: 99%

An Evaluation of Eight Machine Learning Regression Algorithms for Forest Aboveground Biomass Estimation from Multiple Satellite Data Products

Zhang

Liang

et al. 2020

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…The RFR method uses an ensemble of decision trees, which usually vote or are averaged to obtain the final result (Zouggar and Adla, 2019;Rastgou et al, 2020). RFR does not easily fall into overfitting and is more robust than other methods in terms of noise due to the introduction of randomness.…”

Section: Rfr Methods For Estimating Winter Wheat Yieldmentioning

confidence: 99%

Analysis of Influencing Factors on Winter Wheat Yield Estimations Based on a Multisource Remote Sensing Data Fusion

Li¹,

Ren²,

Gao³

et al. 2021

Applied Engineering in Agriculture

View full text Add to dashboard Cite

HighlightsThe potential of fusing GF-1 WFV and MODIS data by the ESTARFM algorithm was demonstrated.A better time window selection method for estimating yields was provided.A better vegetation index suitable for yield estimation based on spatiotemporally fused data was identified.The effect of the spatial resolution of remote sensing data on yield estimations was visualized.Abstract. The accurate estimation of crop yields is very important for crop management and food security. Although many methods have been developed based on single remote sensing data sources, advances are still needed to exploit multisource remote sensing data with higher spatial and temporal resolution. More suitable time window selection methods and vegetation indexes, both of which are critical for yield estimations, have not been fully considered. In this article, the Chinese GaoFen-1 Wide Field View (GF-1 WFV) and Terra Moderate Resolution Imaging Spectroradiometer (MODIS) data were fused by the Enhanced Spatial and Temporal Adaptive Reflectance Fusion Model (ESTARFM) to generate time-series data with a high spatial resolution. Then, two time window selection methods involving distinguishing or not distinguishing the growth stages during the monitoring period, and three vegetation indexes, the normalized difference vegetation index (NDVI), two-band enhanced vegetation index (EVI2) and wide dynamic range vegetation index (WDRVI), were intercompared. Furthermore, the yield estimations obtained from two different spatial resolutions of fused data and MODIS data were analyzed. The results indicate that taking the growth stage as the time window unit division basis can allow a better estimation of winter wheat yield; and that WDRVI is more suitable for yield estimations than NDVI or EVI2. This study demonstrates that the spatial resolution has a great influence on yield estimations; further, this study identifies a better time window selection method and vegetation index for improving the accuracy of yield estimations based on a multisource remote sensing data fusion. Keywords: Remote sensing, Spatiotemporal data fusion, Winter wheat, Yield estimation.

show abstract

“…The decision tree is the most popular machine-learning based classification algorithm, which was first introduced by Quinlan in 1993 (Quinlan, 1993). It is a tree data structure in which each non-leaf/internal node symbolises a test on the variables, each external/leaf node contains the label for class, and each branch shows the result of the test (Kaur and Gosain, 2018;Zouggar and Adla, 2019). As shown in Figure 3, the decision tree divides the whole dataset into mutually exclusive spaces.…”

Section: Decision Treementioning

confidence: 99%

Statistical analysis of machine learning techniques for predicting powdery mildew disease in tomato plants

Chug¹,

Bhatia²,

Singh³

2021

IJIEI

View full text Add to dashboard Cite

Powdery mildew is a dangerous disease that reduces the quality and the yield of tomato fruit rapidly. Its early prediction is a prior requirement for obtaining good quality fruit. Therefore, in this study, the best classifier amongst various classifiers has been discovered using different machine learning algorithms. This classifier can precisely classify whether the meteorological conditions of a particular day are conducive to the development of powdery mildew disease or not. Tomato powdery mildew disease dataset has been tested using various performance measures and the results computed for all the classifiers are promising. Friedman test has been used to rank multiple classifiers and post hoc analysis has also been done using the Nemenyi test. It has been observed in comparison that 62.05% of the total pairs of classifiers perform significantly different from each other, and medium Gaussian support vector machine (MGSVM) is the best classifier with 94.74% accuracy.

show abstract

A Diversity-Accuracy Measure for Homogenous Ensemble Selection

Cited by 8 publications

References 29 publications

An Evaluation of Eight Machine Learning Regression Algorithms for Forest Aboveground Biomass Estimation from Multiple Satellite Data Products

An Evaluation of Eight Machine Learning Regression Algorithms for Forest Aboveground Biomass Estimation from Multiple Satellite Data Products

Analysis of Influencing Factors on Winter Wheat Yield Estimations Based on a Multisource Remote Sensing Data Fusion

Statistical analysis of machine learning techniques for predicting powdery mildew disease in tomato plants

Contact Info

Product

Resources

About