|
人工智能论文:贝叶斯元分类器和软混淆矩阵分类器在多标签分类的任务中(Bayes metaclassifier and Soft-confusion-matrix classifier in the task of multi-label classification)本文的目的是在多标签分类框架下比较软混淆矩阵方法和Bayesmetaclassifier。尽管在多标签分类框架下成功应用了方法,但到目前为止尚未对它们进行直接比较。这种比较是至关重要的,因为两种方法都非常相似,因为它们都是基于随机参考分类器的概念。由于两种算法都设计用于处理单标签问题,因此将它们与问题转换方法结合起来进行多标签分类。目前的研究包括29个基准数据集和4个不同的基本分类器。根据11个质量标准和我们进行统计分析的结果对算法进行了比较。
The aim of this paper was to compare soft confusion matrix approach and Bayesmetaclassifier under the multi-label classification framework.Although themethods were successfully applied under the multi-label classificationframework, they have not been compared directly thus far.Such comparison is ofvital importance because both methods are quite similar as they are both basedon the concept of randomized reference classifier.Since both algorithms weredesigned to deal with single-label problems, they are combined with theproblem-transformation approach to multi-label classification.Present studyincluded 29 benchmark datasets and four different base classifiers.Thealgorithms were compared in terms of 11 quality criteria and the results weresubjected to statistical analysis.人工智能论文:贝叶斯元分类器和软混淆矩阵分类器在多标签分类的任务中(Bayes metaclassifier and Soft-confusion-matrix classifier in the task of multi-label classification)
URL地址:https://arxiv.org/abs/1901.08827 ----pdf下载地址:https://arxiv.org/pdf/1901.08827 ----人工智能论文:贝叶斯元分类器和软混淆矩阵分类器在多标签分类的任务中(Bayes metaclassifier and Soft-confusion-matrix classifier in the task of multi-label classification) |
|