Is Combining Classifiers with Stacking Better than Selecting the Best One?

Džeroski, Sašo; Ženko, Bernard

doi:10.1023/b:mach.0000015881.36452.6e

Cited by 706 publications

(370 citation statements)

References 20 publications

Supporting

Mentioning

350

Contrasting

Unclassified

Order By: Relevance

“…The problem with these rules is that is if difficult to estimate different weights for the scores belonging to each class. Therefore, in our work we stack the output of the different classifiers into a single vector and the train a Support Vector Machine (SVM) to make a combined decision [8]. …”

Section: B Fusionmentioning

confidence: 99%

Changes in Facial Expression as Biometric: A Database and Benchmarks of Identification

Haamer

Kulkarni

Imanpour

et al. 2018

2018 13th IEEE International Conference on Automatic Face &Amp; Gesture Recognition (FG 2018)

View full text Add to dashboard Cite

Abstract-Facial dynamics can be considered as unique signatures for discrimination between people. These have started to become important topic since many devices have the possibility of unlocking using face recognition or verification. In this work, we evaluate the efficacy of the transition frames of video in emotion as compared to the peak emotion frames for identification. For experiments with transition frames we extract features from each frame of the video from a fine-tuned VGG-Face Convolutional Neural Network (CNN) and geometric features from facial landmark points. To model the temporal context of the transition frames we train a Long-Short Term Memory (LSTM) on the geometric and the CNN features. Furthermore, we employ two fusion strategies: first, an early fusion, in which the geometric and the CNN features are stacked and fed to the LSTM. Second, a late fusion, in which the prediction of the LSTMs, trained independently on the two features, are stacked and used with a Support Vector Machine (SVM). Experimental results show that the late fusion strategy gives the best results and the transition frames give better identification results as compared to the peak emotion frames.

show abstract

Section: B Fusionmentioning

confidence: 99%

Changes in Facial Expression as Biometric: A Database and Benchmarks of Identification

Haamer

Kulkarni

Imanpour

et al. 2018

2018 13th IEEE International Conference on Automatic Face &Amp; Gesture Recognition (FG 2018)

View full text Add to dashboard Cite

show abstract

“…A Model Tree predictor was chosen as a metaregressor not only because it achieved good results in the initial experiments, but also because it is a state-of-the-art regression method and it has already been successfully used as a meta-classifier for stacking (Dzeroski & Zenko, 2004), outperforming all the other combining methods tested. In order to determine which subset of algorithms can provide the best ensemble, we built four models by stacking: one containing the square-root SPKFs and EKF, and the others leaving one of them out.…”

Section: Stacking Of Sigma-point Kalman Filtersmentioning

confidence: 99%

Applying REC Analysis to Ensembles of Sigma-Point Kalman Filters

Pina

Zaverucha

2006

Artificial Neural Networks – ICANN 2006

View full text Add to dashboard Cite

The Sigma-Point Kalman Filters (SPKF) is a family of filters that achieve very good performance when applied to time series. Currently most researches involving time series forecasting use the Sigma-Point Kalman Filters, however they do not use an ensemble of them, which could achieve a better performance. The REC analysis is a powerful technique for visualization and comparison of regression models. The objective of this work is to advocate the use of REC curves in order to compare the SPKF and ensembles of them and select the best model to be used.

show abstract

“…For example [13] generate ensembles of heterogeneous classifiers using stacking. [11] proposed a framework for generating hundreds of thousands of classifiers in parallel in a distributed environment using small subsamples of the dataset.…”

Section: Introductionmentioning

confidence: 99%

Random Prism: An Alternative to Random Forests

Stahl

Bramer

2011

Research and Development in Intelligent Systems XXVIII

View full text Add to dashboard Cite

Ensemble learning techniques generate multiple classifiers, so called base classifiers, whose combined classification results are used in order to increase the overall classification accuracy. In most ensemble classifiers the base classifiers are based on the Top Down Induction of Decision Trees (TDIDT) approach. However, an alternative approach for the induction of rule based classifiers is the Prism family of algorithms. Prism algorithms produce modular classification rules that do not necessarily fit into a decision tree structure. Prism classification rulesets achieve a comparable and sometimes higher classification accuracy compared with decision tree classifiers, if the data is noisy and large. Yet Prism still suffers from overfitting on noisy and large datasets. In practice ensemble techniques tend to reduce the overfitting, however there exists no ensemble learner for modular classification rule inducers such as the Prism family of algorithms. This article describes the first development of an ensemble learner based on the Prism family of algorithms in order to enhance Prism's classification accuracy by reducing overfitting.

show abstract

Is Combining Classifiers with Stacking Better than Selecting the Best One?

Cited by 706 publications

References 20 publications

Changes in Facial Expression as Biometric: A Database and Benchmarks of Identification

Changes in Facial Expression as Biometric: A Database and Benchmarks of Identification

Applying REC Analysis to Ensembles of Sigma-Point Kalman Filters

Random Prism: An Alternative to Random Forests

Contact Info

Product

Resources

About