Research on Ensemble Learning

Huang, Faliang; Xie, Guangqiang; Xiao, Ruliang

doi:10.1109/aici.2009.235

Cited by 103 publications

(59 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Compared to the individual LHF products, the R 2 of the ML methods was 3.7–46.4% higher and the bias decreased by approximately 15 W m −2 . Our results also show that some minor differences existed among the four ML methods, which are mainly affected by the structure of different fusion algorithms [ 69 , 70 ]. Sagi and Rokach [ 71 ] showed that the differences in structure of the ensemble methods may significantly affect the predictions, and the best ensemble method for a given problem needs to consider other factors (such as suitability to a given setting).…”

Section: Discussionmentioning

confidence: 75%

ANN-Based Estimation of Low-Latitude Monthly Ocean Latent Heat Flux by Ensemble Satellite and Reanalysis Products

Chen

Yao

Li³

et al. 2020

Sensors

View full text Add to dashboard Cite

Ocean latent heat flux (LHF) is an essential variable for air–sea interactions, which establishes the link between energy balance, water and carbon cycle. The low-latitude ocean is the main heat source of the global ocean and has a great influence on global climate change and energy transmission. Thus, an accuracy estimation of high-resolution ocean LHF over low-latitude area is vital to the understanding of energy and water cycle, and it remains a challenge. To reduce the uncertainties of individual LHF products over low-latitude areas, four machine learning (ML) methods (Artificial Neutral Network (ANN), Random forest (RF), Bayesian Ridge regression and Random Sample Consensus (RANSAC) regression) were applied to estimate low-latitude monthly ocean LHF by using two satellite products (JOFURO-3 and GSSTF-3) and two reanalysis products (MERRA-2 and ERA-I). We validated the estimated ocean LHF using 115 widely distributed buoy sites from three buoy site arrays (TAO, PIRATA and RAMA). The validation results demonstrate that the performance of LHF estimations derived from the ML methods (including ANN, RF, BR and RANSAC) were significantly better than individual LHF products, indicated by R2 increasing by 3.7–46.4%. Among them, the LHF estimation using the ANN method increased the R2 of the four-individual ocean LHF products (ranging from 0.56 to 0.79) to 0.88 and decreased the RMSE (ranging from 19.1 to 37.5) to 11 W m-2. Compared to three other ML methods (RF, BR and RANSAC), ANN method exhibited the best performance according to the validation results. The results of relative uncertainty analysis using the triangle cornered hat (TCH) method show that the ensemble LHF product using ML methods has lower relative uncertainty than individual LHF product in most area. The ANN was employed to implement the mapping of annual average ocean LHF over low-latitude at a spatial resolution of 0.25° during 2003–2007. The ocean LHF fusion products estimated from ANN methods were 10–30 W m−2 lower than those of the four original ocean products (MERRA-2, JOFURO-3, ERA-I and GSSTF-3) and were more similar to observations.

show abstract

Section: Discussionmentioning

confidence: 75%

ANN-Based Estimation of Low-Latitude Monthly Ocean Latent Heat Flux by Ensemble Satellite and Reanalysis Products

Chen

Yao

Li³

et al. 2020

Sensors

View full text Add to dashboard Cite

show abstract

“…Here we use a learner to combine the output from different learners, which leads to the decrease in either bias or variance error, depending on the combining learner we use. Compared with other commonly-used ensemble learning techniques, such as bagging and boosting, stacking can transfer the ensemble features to a simple model and does not require too many parameter tunings and feature selections [13,14]. In order to improve prediction precision while avoiding overfitting, a two-layer stacking method is applied to build the ensemble model, as illustrated in Figure 7, including a hidden layer and an output layer.…”

Section: Ensemble Model With Two-layer Stackingmentioning

confidence: 99%

An Accurate and Efficient Timing Prediction Framework for Wide Supply Voltage Design Based on Learning Method

2020

View full text Add to dashboard Cite

The wide voltage design methodology has been widely employed in the state-of-the-art circuit design with the advantage of remarkable power reduction and energy efficiency enhancement. However, the timing verification issue for multiple PVT (process–voltage–temperature) corners rises due to unacceptable analysis effort increase for multiple supply voltage nodes. Moreover, the foundry-provided timing libraries in the traditional STA (static timing analysis) approach are only available for the nominal supply voltage with limited voltage scaling, which cannot support timing verification for low voltages down to near- or sub-threshold voltages. In this paper, a learning-based approach for wide voltage design is proposed where feature engineering is performed to enhance the correlation among PVT corners based on a dilated CNN (convolutional neural network) model, and an ensemble model is utilized with two-layer stacking to improve timing prediction accuracy. The proposed method was verified with a commercial RISC (reduced instruction set computer) core under the supply voltage nodes ranging from 0.5 V to 0.9 V. Experimental results demonstrate that the prediction error is limited by 4.9% and 7.9%, respectively, within and across process corners for various working temperatures, which achieves up to 4.4× and 3.9× precision enhancement compared with related learning-based methods.

show abstract

“…In our research, the pharyngeal fricative speech detection task is performed by applying the bagging of the ensemble learning classifier. The idea of ensemble learning is principally based on the theoretical cornerstone that the generalization ability of an ensemble is usually much stronger than that of a single learner [32][33][34]. There are 30 learners in the training process of this classification model.…”

Section: Bagging Of Ensemble Learning Classifiermentioning

confidence: 99%

“…The classificationHe et al BioMed Eng OnLine (2020) 19:36 performance of the model depends on the stability of the base classifiers[32]. All the base classifiers are mutually independent.…”

mentioning

confidence: 99%

Acoustic analysis and detection of pharyngeal fricative in cleft palate speech using correlation of signals in independent frequency bands and octave spectrum prominent peak

Wang

Yin

et al. 2020

BioMed Eng OnLine

View full text Add to dashboard Cite

Background: Pharyngeal fricative is one typical compensatory articulation error of cleft palate speech. It passively influences daily communication for people who suffer from it. The automatic detection of pharyngeal fricatives in cleft palate speech can provide information for clinical doctors and speech-language pathologists to aid in diagnosis. Results: This paper proposes two features (CSIFs: correlation of signals in independent frequency bands; OSPP: octave spectrum prominent peak) to detect pharyngeal fricative speech. CSIFs feature is proposed to detect the distribution characteristics of frequency components in pharyngeal fricative speech caused by the changed place of articulation and movement of articulators. While OSPP is presented to reflect the concentration degree of prominent peak which is closely related to the place of articulation in pharyngeal fricative, both features are investigated to relate to the altered production process of pharyngeal fricative. To evaluate the capability of these two features to detect pharyngeal fricative, we collected a speech database covering all the types of initial consonants in which pharyngeal fricatives occur. In this detection task, the classifier used to discriminate pharyngeal fricative speech and normal speech is based on ensemble learning. Conclusion: The detection accuracy obtained with CSIFs and OSPP features ranges from 83.5 to 84.5% and from 85 to 87%, respectively. When these two features are combined, the detection accuracy for pharyngeal fricative speech ranges from 88 to 89%, with an AUC (area under the receiver operating characteristic curve) value of 93%.

show abstract

Research on Ensemble Learning

Cited by 103 publications

References 5 publications

ANN-Based Estimation of Low-Latitude Monthly Ocean Latent Heat Flux by Ensemble Satellite and Reanalysis Products

ANN-Based Estimation of Low-Latitude Monthly Ocean Latent Heat Flux by Ensemble Satellite and Reanalysis Products

An Accurate and Efficient Timing Prediction Framework for Wide Supply Voltage Design Based on Learning Method

Acoustic analysis and detection of pharyngeal fricative in cleft palate speech using correlation of signals in independent frequency bands and octave spectrum prominent peak

Contact Info

Product

Resources

About