An Instance- and Label-Based Feature Selection Method in Classification Tasks
Feature selection is crucial in classification tasks as it helps to extract relevant information while reducing redundancy. This paper presents a novel method that considers both instance and label correlation. By employing the least squares method, we calculate the linear relationship between each...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-09-01
|
| Series: | Information |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2078-2489/14/10/532 |
| _version_ | 1797573559896244224 |
|---|---|
| author | Qingcheng Fan Sicong Liu Chunjiang Zhao Shuqin Li |
| author_facet | Qingcheng Fan Sicong Liu Chunjiang Zhao Shuqin Li |
| author_sort | Qingcheng Fan |
| collection | DOAJ |
| description | Feature selection is crucial in classification tasks as it helps to extract relevant information while reducing redundancy. This paper presents a novel method that considers both instance and label correlation. By employing the least squares method, we calculate the linear relationship between each feature and the target variable, resulting in correlation coefficients. Features with high correlation coefficients are selected. Compared to traditional methods, our approach offers two advantages. Firstly, it effectively selects features highly correlated with the target variable from a large feature set, reducing data dimensionality and improving analysis and modeling efficiency. Secondly, our method considers label correlation between features, enhancing the accuracy of selected features and subsequent model performance. Experimental results on three datasets demonstrate the effectiveness of our method in selecting features with high correlation coefficients, leading to superior model performance. Notably, our approach achieves a minimum accuracy improvement of 3.2% for the advanced classifier, lightGBM, surpassing other feature selection methods. In summary, our proposed method, based on instance and label correlation, presents a suitable solution for classification problems. |
| first_indexed | 2024-03-10T21:10:48Z |
| format | Article |
| id | doaj.art-6a2f707dde3f4f09a367fd0c9c0e0757 |
| institution | Directory Open Access Journal |
| issn | 2078-2489 |
| language | English |
| last_indexed | 2024-03-10T21:10:48Z |
| publishDate | 2023-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Information |
| spelling | doaj.art-6a2f707dde3f4f09a367fd0c9c0e07572023-11-19T16:47:48ZengMDPI AGInformation2078-24892023-09-01141053210.3390/info14100532An Instance- and Label-Based Feature Selection Method in Classification TasksQingcheng Fan0Sicong Liu1Chunjiang Zhao2Shuqin Li3College of Information Engineering, Northwest A&F University, 3 Taicheng Road, Yangling, Xianyang 712100, ChinaCollege of Information Engineering, Northwest A&F University, 3 Taicheng Road, Yangling, Xianyang 712100, ChinaCollege of Information Engineering, Northwest A&F University, 3 Taicheng Road, Yangling, Xianyang 712100, ChinaCollege of Information Engineering, Northwest A&F University, 3 Taicheng Road, Yangling, Xianyang 712100, ChinaFeature selection is crucial in classification tasks as it helps to extract relevant information while reducing redundancy. This paper presents a novel method that considers both instance and label correlation. By employing the least squares method, we calculate the linear relationship between each feature and the target variable, resulting in correlation coefficients. Features with high correlation coefficients are selected. Compared to traditional methods, our approach offers two advantages. Firstly, it effectively selects features highly correlated with the target variable from a large feature set, reducing data dimensionality and improving analysis and modeling efficiency. Secondly, our method considers label correlation between features, enhancing the accuracy of selected features and subsequent model performance. Experimental results on three datasets demonstrate the effectiveness of our method in selecting features with high correlation coefficients, leading to superior model performance. Notably, our approach achieves a minimum accuracy improvement of 3.2% for the advanced classifier, lightGBM, surpassing other feature selection methods. In summary, our proposed method, based on instance and label correlation, presents a suitable solution for classification problems.https://www.mdpi.com/2078-2489/14/10/532feature selectionmanifold learningclassification |
| spellingShingle | Qingcheng Fan Sicong Liu Chunjiang Zhao Shuqin Li An Instance- and Label-Based Feature Selection Method in Classification Tasks Information feature selection manifold learning classification |
| title | An Instance- and Label-Based Feature Selection Method in Classification Tasks |
| title_full | An Instance- and Label-Based Feature Selection Method in Classification Tasks |
| title_fullStr | An Instance- and Label-Based Feature Selection Method in Classification Tasks |
| title_full_unstemmed | An Instance- and Label-Based Feature Selection Method in Classification Tasks |
| title_short | An Instance- and Label-Based Feature Selection Method in Classification Tasks |
| title_sort | instance and label based feature selection method in classification tasks |
| topic | feature selection manifold learning classification |
| url | https://www.mdpi.com/2078-2489/14/10/532 |
| work_keys_str_mv | AT qingchengfan aninstanceandlabelbasedfeatureselectionmethodinclassificationtasks AT sicongliu aninstanceandlabelbasedfeatureselectionmethodinclassificationtasks AT chunjiangzhao aninstanceandlabelbasedfeatureselectionmethodinclassificationtasks AT shuqinli aninstanceandlabelbasedfeatureselectionmethodinclassificationtasks AT qingchengfan instanceandlabelbasedfeatureselectionmethodinclassificationtasks AT sicongliu instanceandlabelbasedfeatureselectionmethodinclassificationtasks AT chunjiangzhao instanceandlabelbasedfeatureselectionmethodinclassificationtasks AT shuqinli instanceandlabelbasedfeatureselectionmethodinclassificationtasks |