Granule Vectors and Granular Convolutional Classifiers
Granule Vectors and Granular Convolutional Classifiers
复制标题
颗粒向量和颗粒卷积分类器
DOI：
10.1109/access.2019.2959126
复制
发表时间：
2020
期刊：
影响因子：
3.9
通讯作者：
Shunzhi Zhu
中科院分区：
文献类型：
--
作者：
Yumin Chen;Xiao Zhang;Wei Li;Shunzhi Zhu
卷积运算可以提取有效的特征，在深度学习领域得到了广泛的应用。针对卷积算法主要处理数值数据的不足，提出了一种集合形式的粒卷积算子，并在其上构造了一个分类器。首先，通过引入邻域粗糙集，在分类系统的每个特征上构造特征粒。同时，在样本的标签上生成决策粒。然后，利用这些粒构造特征粒向量和加权粒向量，并对特征粒向量和加权粒向量进行卷积运算，得到预测粒。将预测粒度与决策粒度进行比较，并将其残差反向传播到加权粒度向量以调整其值。在粒度卷积运算和反向传播校正的多次迭代之后，粒度向量的权重收敛并优化。此外，基于卷积运算设计了一个粒度分类器。在UCI数据集上测试了粒卷积的收敛性和粒分类器的分类性能。理论分析和实验结果表明，粒卷积具有收敛速度快的特点，粒卷积分类器具有较好的分类性能。
Convolutional operations can extract effective features and have been widely used in the field of deep learning. For the deficiency of convolution mainly dealing with numerical data, we propose a novel convolutional operator on granules with a set form, further we build a classifier on it. Firstly, feature granules are constructed on each single feature of a classification system by introducing neighborhood rough sets. Synchronously, decision granules are generated on the labels of samples. Secondly, feature granule vectors and weighted granule vectors are constructed from these granules, and a convolutional operation is proposed on feature granule vectors and weighted granule vectors, then a predicted granule is produced as a result of the convolutional operation. The predicted granule is compared with the decision granule, and their residual error is back propagated to the weighted granule vector for tuning its value. After multiple iterations of the granular convolutional operations and back propagation corrections, the weight of the granular vector is convergent and optimized. Furthermore, a granular classifier is designed based on the convolutional operation. The constringency of the granular convolution and the classification performance of the granular classifier are tested on some UCI datasets. Theoretical analysis and experimental results show that the granular convolution has a characteristic of fast convergence, and the granular convolutional classifier has a better classification performance.
登录
查看更多内容
DOI：
10.1016/j.eswa.2017.10.052
发表时间：
2018-03
期刊：
Expert Syst. Appl.
影响因子：
--
作者：
M. D. Ferreira;D. C. Corrêa;L. G. Nonato;R. Mello
通讯作者：
M. D. Ferreira;D. C. Corrêa;L. G. Nonato;R. Mello
DOI：
10.1007/978-3-319-99368-3
发表时间：
2018-10
期刊：
--
影响因子：
--
作者：
R. Efendi;Voni Apriana Dewi;Rahmadeni;Sri Basriati;Dadang Syarif
通讯作者：
R. Efendi;Voni Apriana Dewi;Rahmadeni;Sri Basriati;Dadang Syarif
DOI：
10.1016/j.ins.2013.06.012
发表时间：
2013-11
期刊：
Inf. Sci.
影响因子：
--
作者：
Peng Fei Zhu;Q. Hu
通讯作者：
Peng Fei Zhu;Q. Hu
DOI：
10.1109/tnnls.2019.2905261
发表时间：
2020-02
影响因子：
10.4
作者：
Rui Wang;N. Xiu;Chao Zhang
通讯作者：
Rui Wang;N. Xiu;Chao Zhang
影响因子：
8.6
作者：
Xie, Tian;Grossman, Jeffrey C.
通讯作者：
Grossman, Jeffrey C.