Granule Vectors and Granular Convolutional Classifiers
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,...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8931552/ |
| _version_ | 1818444362604871680 |
|---|---|
| author | Yumin Chen Xiao Zhang Wei Li Shunzhi Zhu |
| author_facet | Yumin Chen Xiao Zhang Wei Li Shunzhi Zhu |
| author_sort | Yumin Chen |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-12-14T19:14:44Z |
| format | Article |
| id | doaj.art-53bd18df16e84af0aec09f5573fdf15e |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-14T19:14:44Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-53bd18df16e84af0aec09f5573fdf15e2022-12-21T22:50:39ZengIEEEIEEE Access2169-35362020-01-0182042205110.1109/ACCESS.2019.29591268931552Granule Vectors and Granular Convolutional ClassifiersYumin Chen0https://orcid.org/0000-0003-1981-5827Xiao Zhang1https://orcid.org/0000-0001-9935-0219Wei Li2https://orcid.org/0000-0002-4308-4385Shunzhi Zhu3https://orcid.org/0000-0001-8321-1169College of Computer and Information Engineering, Xiamen University of Technology, Xiamen, ChinaCollege of Computer and Information Engineering, Xiamen University of Technology, Xiamen, ChinaCollege of Computer and Information Engineering, Xiamen University of Technology, Xiamen, ChinaCollege of Computer and Information Engineering, Xiamen University of Technology, Xiamen, ChinaConvolutional 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.https://ieeexplore.ieee.org/document/8931552/Granular computingneighborhood rough setsconvolutional networkgranular classifierrough sets |
| spellingShingle | Yumin Chen Xiao Zhang Wei Li Shunzhi Zhu Granule Vectors and Granular Convolutional Classifiers IEEE Access Granular computing neighborhood rough sets convolutional network granular classifier rough sets |
| title | Granule Vectors and Granular Convolutional Classifiers |
| title_full | Granule Vectors and Granular Convolutional Classifiers |
| title_fullStr | Granule Vectors and Granular Convolutional Classifiers |
| title_full_unstemmed | Granule Vectors and Granular Convolutional Classifiers |
| title_short | Granule Vectors and Granular Convolutional Classifiers |
| title_sort | granule vectors and granular convolutional classifiers |
| topic | Granular computing neighborhood rough sets convolutional network granular classifier rough sets |
| url | https://ieeexplore.ieee.org/document/8931552/ |
| work_keys_str_mv | AT yuminchen granulevectorsandgranularconvolutionalclassifiers AT xiaozhang granulevectorsandgranularconvolutionalclassifiers AT weili granulevectorsandgranularconvolutionalclassifiers AT shunzhizhu granulevectorsandgranularconvolutionalclassifiers |