Dynamic ensemble selection for quantification tasks
57
TL;DR: Three new quantifier selection criteria particularly devised for quantification problems are devised, where two of them are defined for dynamic ensemble selection and show that performance heavily depends on the combination of the base quantification algorithm and the selection measure.
read more
About: This article is published in Information Fusion. The article was published on 01 Jan 2018. and is currently open access. The article focuses on the topics: Selection (genetic algorithm).
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Figures
Figure 5: MAE scores selecting a different percentage of models using EHDy-DS 
Table 5: MAE results using different selection functions for the ensemble version of the Probabilistic Adjusted Count (PAC) quantifier. The best score for each dataset is in bold 
Table 1: Summary of datasets: n is the number of examples, d is the dimension of the input space, P (N) the number of positive (negative) examples and p the prevalence of the positive class 
Table 4: Mean absolute errors using different selection functions for the ensemble version of the Adjusted Count (AC) quantifier. The best score for each dataset is in bold 
Table 6: Mean absolute errors using different selection functions for the ensemble version of the HDy quantifier. The best score for each dataset is in bold 
Figure 3: MAE scores selecting a different percentage of models using EAC-DS
Citations
A Survey of Ensemble Learning: Concepts, Algorithms, Applications, and Prospects
01 Jan 2022
TL;DR: This article presented a concise overview of ensemble learning, covering the three main ensemble methods: bagging, boosting, and stacking, their early development to the recent state-of-the-art algorithms.
389
A Survey of Ensemble Learning: Concepts, Algorithms, Applications, and Prospects
Ibomoiye Domor Mienye,Yanxia Sun +1 more
TL;DR: An attempt is made to concisely cover the three main ensemble methods: bagging, boosting, and stacking, their early development to the recent state-of-the-art algorithms, and their mathematical and algorithmic representations.
230
A novel dynamic ensemble selection classifier for an imbalanced data set: An application for credit risk assessment
TL;DR: A novel combined DES model is developed for imbalanced learning problems and it is shown that the proposed model improves the performance of seven known and popular DES algorithms in terms of the area under the curve.
78
DyS: A Framework for Mixture Models in Quantification
André Gustavo Maletzke,Denis Moreira dos Reis,Everton Alvares Cherman,Gustavo E. A. P. A. Batista +3 more
- 17 Jul 2019
TL;DR: It is concluded that, when tuned, Topsoe is the histogram distance function that consistently leads to smaller quantification errors and, therefore, is recommended to general use, notwithstanding Hellinger Distance’s popularity.
Exploring Diverse Features for Sentiment Quantification Using Machine Learning Algorithms
TL;DR: The computed results show that the diverse features sets affect the performance of classifiers in sentiment quantification and confirm that the deep learning techniques perform better than the conventional machine learning algorithms.
References
Density estimation for statistics and data analysis
Bernard W. Silverman
- 01 Jan 1986
TL;DR: The Kernel Method for Multivariate Data: Three Important Methods and Density Estimation in Action.
Density Estimation for Statistics and Data Analysis
TL;DR: Density estimation, as discussed in this book, is the construction of an estimate of the density function from the observed data from an unknown probability density function.
14.7K
•Journal Article
LIBLINEAR: A Library for Large Linear Classification
TL;DR: LIBLINEAR is an open source library for large-scale linear classification that supports logistic regression and linear support vector machines and provides easy-to-use command-line tools and library calls for users and developers.
Multivariate Density Estimation, Theory, Practice and Visualization
TL;DR: Representation and Geometry of Multivariate Data.
4.5K
Measures of Diversity in Classifier Ensembles and Their Relationship with the Ensemble Accuracy
TL;DR: Although there are proven connections between diversity and accuracy in some special cases, the results raise some doubts about the usefulness of diversity measures in building classifier ensembles in real-life pattern recognition problems.