.png){kind=icon}
.png){kind=icon}
Return
Feature selection by utilizing kernel-based fuzzy rough set and entropy-based non-dominated sorting genetic algorithm in multi-label data
.png){kind=icon}
PRE
AI
DOI：10.1007/s10115-025-02341-5.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Multi-label learning, which involves assigning multiple class labels to each instance, becomes increasingly complex when dealing with large-scale mixed datasets featuring high-dimensional feature spaces. These mixed datasets often involve a combination of numerical and categorical features, which exacerbate the challenges of multi-label learning by introducing additional layers of uncertainty and variability. Traditional classification methods, although effective in simpler scenarios, often fail to address these complexities resulting in significant errors. To overcome this, we have developed an entropy-based objective function that captures the intricate interplay between features and classes, while accounting for the inherent uncertainty of mixed data. This objective function explicitly accounts for the heterogeneous nature of mixed datasets, ensuring robust feature selection across diverse attribute types. To tackle these challenges, we propose a memetic algorithm that integrates fuzzy rough sets with enhancements from kernel fuzzy rough sets (KFRS), and the Non-dominated Sorting Genetic Algorithm II. This synergy enables the extraction of optimal feature subsets that significantly improve classification performance. By leveraging kernel-based similarity measures, KFRS refines the partitions formed by fuzzy set memberships for distinct classes, ensuring precise alignment of data samples with multiple labels, while effectively handling the complexities of mixed-data representation. A key strength of our approach lies in its ability to preserve valuable information through KFRS-driven feature selection. Empirical evaluations on three benchmark datasets highlight the effectiveness of the proposed methodology. The results validate the superiority of our feature selection strategy, grounded in kernel-modulated neighborhoods; furthermore, the implementation demonstrates a notable improvement in both solution quality and search efficiency, establishing it as a highly promising method for multi-label learning tasks.
Keywords:
Feature selection
Kernel fuzzy rough set
Mixed data
Multi-label learning
Journal
IF:
3.1
Papers:
535
Citations:
5.2K