Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Videos

A dynamically adjusted mixed emphasis method for building boosting ensembles.

Vanessa Gomez-Verdejo¹, Jerónimo Arenas-Garcia, Aníbal R Figueiras-Vidal

¹Department of Signal Theory and Communications, Universidad Carlos III de Madrid, Spain. vanessa@tsc.uc3m.es

IEEE Transactions on Neural Networks

|February 14, 2008

Summary

This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

A systematic review of machine learning on clinical MALDI-TOF MS.

Briefings in bioinformatics·2026

Same author

Addressing wide-data studies of gene expression microarrays with the Relevance Feature and Vector Machine.

Computers in biology and medicine·2025

Same author

Automated web-based typing of Clostridioides difficile ribotypes via MALDI-TOF MS.

BMC bioinformatics·2025

Same author

Bayesian learning of feature spaces for multitask regression.

Neural networks : the official journal of the International Neural Network Society·2024

Same author

Adaptive Sparse Gaussian Process.

IEEE transactions on neural networks and learning systems·2023

Same author

Multidimensional analysis of immune cells from COVID-19 patients identified cell subsets associated with the severity at hospital admission.

PLoS pathogens·2023

Same journal

Universal perceptron and DNA-like learning algorithm for binary neural networks: LSBF and PBF implementations.

IEEE transactions on neural networks·2013

Same journal

Guest editorial: special section on white box nonlinear prediction models.

IEEE transactions on neural networks·2011

Same journal

Data-based fault-tolerant control of high-speed trains with traction/braking notch nonlinearities and actuator failures.

IEEE transactions on neural networks·2011

Same journal

Guest editorial: special section on data-based control, modeling, and optimization.

IEEE transactions on neural networks·2011

Same journal

Neural network-based multiple robot simultaneous localization and mapping.

IEEE transactions on neural networks·2011

Same journal

Data-driven model-free adaptive control for a class of MIMO nonlinear discrete-time systems.

IEEE transactions on neural networks·2011

See all related articles

Real Adaboost (RA) ensembles improve performance by emphasizing hard-to-classify samples. The new dynamically adapted weighted emphasis RA (DW-RA) method optimizes this emphasis dynamically for better results.

Area of Science:

Machine Learning
Ensemble Methods
Classification Algorithms

Background:

Real Adaboost (RA) ensembles achieve high performance by progressively emphasizing misclassified samples.
The emphasis function in RA combines quadratic error and proximity to the classification border.
Adjustable combinations of these factors offer potential for performance enhancement.

Purpose of the Study:

To introduce a principled procedure for optimizing the combination of emphasis factors in RA ensembles.
To develop a novel method, dynamically adapted weighted emphasis RA (DW-RA), for improved classification.
To enhance the performance of RA ensembles through dynamic parameter selection.

Main Methods:

A principled procedure for selecting the combination parameter is introduced.

Related Experiment Videos

The parameter is selected by maximizing the associated edge parameter at each step of adding a new learner.

The resulting method is termed dynamically adapted weighted emphasis RA (DW-RA).

Main Results:

The DW-RA method demonstrates performance improvements in application examples.
Dynamic adaptation of emphasis factors leads to enhanced classification accuracy.
The proposed method effectively optimizes the ensemble learning process.

Conclusions:

DW-RA offers a principled and effective approach to enhance RA ensemble performance.
Dynamic adjustment of emphasis factors is crucial for maximizing classification performance.
The DW-RA method represents a significant advancement in ensemble learning techniques.