.png){kind=icon}
返回
Fuzzy support vector machine with graph for classifying imbalanced datasets
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2022.09.139.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Since support vector machine (SVM) considers all the training samples equally, it suffers from the problems of noise/outliers and class imbalance. Although many fuzzy support vector machines (FSVMs) have been proposed to suppress the effect of noise/outliers and class imbalance, most of them ignore the impact of the curse of dimensionality on the discriminative performance of fuzzy membership function and do not give the fuzzy membership function corresponding to the kernel space, which seriously reduces the performance of FSVM. To solve these problems, we propose the fuzzy support vector machine with graph (GraphFSVM) in this paper. Specifically, we first design a graph-based fuzzy membership function to accurately assess the importance of samples in original feature space and prove that the function can mine discriminative information between samples in high-dimensional data. Additionally, since the data distribution in kernel space is different from those in the original feature space, a method is provided to calculate the fuzzy membership function in the kernel space. Finally, the GraphFSVM model analyzes samples of each class independently, this suppresses the effect of class imbalance. Following the above principles, we design the graph-based fuzzy support vector machine and propose a detailed optimization method. Experimental results on UCI, gene expression, and image datasets show that the GraphFSVM has better generalization and robustness than other state-of-the-art methods.(c) 2022 Elsevier B.V. All rights reserved.
Keyword:
Fuzzy support vector machines
Class imbalance
The curse of dimensionality
Kernel space
Graph
期刊
IF:
6.5
论文数:
2.5W
被引数:
6.5W
机构
引用论文
Ability of troponin I to predict cardiac events in patients admitted from the emergency department
PREAI
分享收藏Joint Learning of Spectral Clustering Structure and Fuzzy Similarity Matrix of Data数据的谱聚类结构与模糊相似矩阵的联合学习
PREAI
分享收藏Using unsupervised clustering approach to train the Support Vector Machine for text classification使用无监督聚类方法训练支持向量机进行文本分类.png)
NEUROCOMPUTING
NEUROCOMPUTINGIF6.5
PREAI
分享收藏Robust and efficient multiclass SVM models for phrase pattern recognitionPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏A robust loss function for classification with imbalanced datasets不平衡数据集分类的鲁棒损失函数NEUROCOMPUTING
NEUROCOMPUTINGIF6.5
PREAI
分享收藏分享收藏
查看更多内容