The Optimization of Multi-classifier Ensemble Method Based on Dynamic Weighted Voting

Abstract Generally, on the same data set, different deep learning classification models will achieve different performances. The existing weighted voting method can combine the results of models, which can improve the performance of classification. On the other side, its classification accuracy is a...

Full description

Saved in:
Bibliographic Details
Published inJournal of physics. Conference series Vol. 2185; no. 1; pp. 12030 - 12037
Main Authors Yang, Ping, Fang, Jian, Xu, Junting, Jin, Guanghao, Song, Qingzeng
Format Journal Article
LanguageEnglish
Published Bristol IOP Publishing 01.01.2022
Subjects
Accuracy
Classification
Datasets
Machine learning
Model accuracy
Optimization
Physics
Regulatory reform
Voting
Online AccessGet full text

Cover

More Information
Summary:Abstract Generally, on the same data set, different deep learning classification models will achieve different performances. The existing weighted voting method can combine the results of models, which can improve the performance of classification. On the other side, its classification accuracy is affected by the accuracy of all models. In this paper, we proposed a dynamic weighted voting method. Our method dynamically selects models on different data sets, and integrates them according to their weights, thereby improving the classification accuracy. We evaluated the methods on three data sets of CIFAR10, CIFAR100 and Existing, which increased the accuracy about 0.65%, 0.91%, and 0.78% respectively compared with the existing weighted voting method.
ISSN:1742-6588
1742-6596
DOI:10.1088/1742-6596/2185/1/012030