A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf
.
Filters
3-level Confidence Voting Strategy for Dynamic Fusion-Selection of Classifier Ensembles
2009
Acta Cybernetica
This is a dynamic, half fusion-half selection type method for ensemble member combination, which is midway between the extremes of fusion and selection. ...
In this paper, we propose a novel procedure for building the meta-classifier stage of MCSs, using an oracle of three-level voting strategy. ...
Beyond the usage of implicit measures, the application of two explicit indices is one of the most important difference between our 3-level technique and dynamic classifier selection of Giacinto et al. ...
doi:10.14232/actacyb.19.1.2009.4
fatcat:h7nestm5krauzjjv7yrwvpopbi
A dynamic overproduce-and-choose strategy for the selection of classifier ensembles
2008
Pattern Recognition
The optimization level is intended to generate a population of highly accurate candidate classifier ensembles, while the dynamic selection level applies measures of confidence to reveal the candidate ensemble ...
In this paper, we propose a dynamic overproduce-and-choose strategy which combines optimization and dynamic selection in a two-level selection phase to allow the selection of the most confident subset ...
Two main approaches for the design of classifier ensembles are defined in the literature: (1) classifier fusion; and (2) classifier selection [1--3] . ...
doi:10.1016/j.patcog.2008.03.027
fatcat:wuglpp5ojfbbnkukd2zalbx7ku
Dynamic classifier ensemble using classification confidence
2013
Neurocomputing
It dynamically selects a subset of classifiers for test samples according to classification confidence. ...
How to combine the outputs from base classifiers is a key issue in ensemble learning. This paper presents a dynamic classifier ensemble method termed as DCE-CC. ...
Acknowledgments This work is supported by National Natural Science Foundation of China under Grant 61222210, 61170107, 60873140, 61073125 and 61071179, the Program for New Century Excellent Talents in ...
doi:10.1016/j.neucom.2012.07.026
fatcat:6ygpuinbpvbbpo26wvuvphky2u
Music genre recognition based on visual features with dynamic ensemble of classifiers selection
2013
2013 20th International Conference on Systems, Signals and Image Processing (IWSSIP)
This paper introduces the use of a dynamic ensemble of classifiers selection scheme with a pool of classifiers created to perform automatic music genre classification. ...
The results obtained on the Latin Music Database showed that local feature extraction and the k-nearest oracle (KNORA) for dynamic ensemble of classifiers selection can reach a recognition rate of 83%, ...
the dynamic ensemble of classifiers selection approach. ...
doi:10.1109/iwssip.2013.6623448
fatcat:izqx4inj7rfstlwbole4vt3f4i
Review on the Architecture, Algorithm and Fusion Strategies in Ensemble Learning
2014
International Journal of Computer Applications
model and the algorithms for implementing the Ensemble Learning. ...
In the last part an analysis of ensemble learning algorithms on the basis on Bias and Variance is included. ...
FUSION STRATEGIES IN ENSEMBLE LEARNING Fusion unit forms an important component in the ensemble of classifier. ...
doi:10.5120/18932-0337
fatcat:ienitsbogrevlll2rd7jlfr6ry
MNIST-NET10: A heterogeneous deep networks fusion based on the degree of certainty to reach 0.1 error rate. Ensembles overview and proposal
[article]
2020
arXiv
pre-print
Ensemble methods have been widely used for improving the results of the best single classificationmodel. ...
However, very few works have explored complex fusion schemes using het-erogeneous ensembles with new aggregation strategies. ...
The final prediction is obtained using the most voted strategy. • The top-3 model [3] used a two-level ensemble which achieves an average test error of 0.19% (i.e., 19 misclassified images) . ...
arXiv:2001.11486v2
fatcat:ji7ovh6mwvdjzgb3dwhpuqmike
A dynamic optimization approach for adaptive incremental learning
2011
International Journal of Intelligent Systems
Selection and Fusion of Solutions into Ensembles We now turn our attention to dynamic ensemble selection. ...
The method generates classifiers from optimum regions of the parameter search space, and then dynamically selects ensembles based on the classifiers' confidence levels to improve the overall results. ...
doi:10.1002/int.20501
fatcat:7kq2ytpnwrcelhvluk5ype3u3q
A Study of Ensemble of Hybrid Networks with Strong Regularization
[chapter]
2003
Lecture Notes in Computer Science
We study various ensemble methods for hybrid neural networks. ...
Thus, there is no random selection of the initial (and final) parameters as in other training algorithms. ...
Dynamic Selection: The forth strategy involves dynamic selection of the best classifier for prediction of the output value when a novel pattern is given [11] . ...
doi:10.1007/3-540-44938-8_23
fatcat:c2gxpxrlxvhmnmsw2pmbmfrmpq
The Use of Artificial-Intelligence-Based Ensembles for Intrusion Detection: A Review
2012
Applied Computational Intelligence and Soft Computing
; (3) other measures used to evaluate classification performance of the ensembles. ...
The paper also presents the updated review of various AI-based ensembles for ID (in particular) during last decade. ...
Optimization level
Ensemble learning phase Ensemble level
Strategy adopted
Method employed
Decision optimization Ensemble integration Combination level
Fusion
Majority voting method
Table 2 ...
doi:10.1155/2012/850160
fatcat:rxi5t7appjgl3pn2l7bbb5ru3q
Investigating the influence of the choice of the ensemble members in accuracy and diversity of selection-based and fusion-based methods for ensembles
2007
Pattern Recognition Letters
This paper presents an extensive evaluation of how the choice of the components (classifiers) can affect the performance of several combination methods (selection-based and fusion-based methods). ...
One of the most important steps in the design of a multi-classifier system (MCS), also known as ensemble, is the choice of the components (classifiers). ...
a confidence level of 95%, is performed. ...
doi:10.1016/j.patrec.2006.09.001
fatcat:cmjypmogjbcefb3gemkotok4ii
Adaptive Incremental Learning with an Ensemble of Support Vector Machines
2010
2010 20th International Conference on Pattern Recognition
The key idea is to track, evolve, and combine optimum hypotheses over time, based on dynamic optimization processes and ensemble selection. ...
In this paper, we propose an approach for performing incremental learning in an adaptive fashion with an ensemble of support vector machines. ...
Acknowledgments This research was supported by grant OGP0106456 to Robert Sabourin from NSERC of Canada. ...
doi:10.1109/icpr.2010.984
dblp:conf/icpr/KappSM10
fatcat:7pbkqozu3rc7blkjmlcys73ow4
Multiple Classifier System for Remote Sensing Image Classification: A Review
2012
Sensors
the design of remote sensing classifier ensemble. ...
Over the last two decades, multiple classifier system (MCS) or classifier ensemble has shown great potential to improve the accuracy and reliability of remote sensing image classification. ...
Acknowledgements The authors would like to thank the anonymous reviewers for their valuable comments. ...
doi:10.3390/s120404764
pmid:22666057
pmcid:PMC3355439
fatcat:xeu6ougwsrhfpfoyvl4llqxw2m
Active classifier selection for RGB-D object categorization using a Markov random field ensemble method
2017
Ninth International Conference on Machine Vision (ICMV 2016)
By exploiting its specific characteristics, the MRF ensemble method can also be executed as a Dynamic Classifier Selection (DCS) system. ...
Despite reduced computational costs and using less information, our strategy performs on the same level as common ensemble approaches. ...
Rudolph Triebel for helpful discussions. ...
doi:10.1117/12.2268551
dblp:conf/icmv/DurnerMHAK16
fatcat:sit7rosvlrde7bq5uahesozlxa
Using a classifier ensemble for proactive quality monitoring and control: The impact of the choice of classifiers types, selection criterion, and fusion process
2018
Computers in industry (Print)
Using a classifier ensemble for proactive quality monitoring and control: the impact of the choice of classifiers types, selection criterion, and fusion process. ...
In this study, we focus and analyze the impact of the choice of classifier types on the accuracy of the classifier ensemble; in addition, we explore the effects of the selection criterion and fusion process ...
Another advantage of the classifier ensemble is that the vote used for fusion may be used as a confidence interval on the classification. ...
doi:10.1016/j.compind.2018.03.038
fatcat:ier4gykvlnfkflu5eplbvbrtoy
Dynamic integration of classifiers for handling concept drift
2008
Information Fusion
To improve the treatment of local concept drifts, dynamic integration of classifiers can be used, which integrates base classifiers at an instance level. ...
paper we present the dynamic integration approach in the level of detail necessary for 4 possible implementation. ...
Besides the straightforward use of local accuracies for dynamic classifier selection (DS) as in [10] and [33], we also consider two other integration strategies, which are based on dynamic voting (namely ...
doi:10.1016/j.inffus.2006.11.002
fatcat:hruij4647bgo7gmxt34togcv4m
« Previous
Showing results 1 — 15 out of 1,705 results