2 April 2020 in IEEE Transactions on Fuzzy Systems
Granular structure is a mathematical expression of knowledge in granular computing and a direct determinant of the data processing efficiency. To improve the efficiency of data processing, many scholars have studied the reduction of granular structure. The attribute reduction and the granular reduction are two types of reduction on different layers of a granular structure, with the latter being both an essential step for granular structure reduction and the foundation of the attribute reduction. Yet compared with the attribute reduction, the granular reduction has received less attention from scholars. Therefore, a fuzzy granular reduction theory and a granular matrix based on the fuzzy $\beta$ -coverings is proposed in this work. The insufficiency of the existing granular reduction theory for fuzzy $\beta$ -coverings is pointed out, and proper sufficient and necessary conditions for two fuzzy $\beta$ -coverings generating the same upper and lower approximations are also given in this work. In addition, to reduce and evaluate a fuzzy $\beta$ -covering, a novel reduction algorithm based on granular matrix is proposed for the first time. Also, since fuzzy covering reduction is NP-hard, a heuristic greedy algorithm is designed to obtain a reduct. Numerical experiments have shown that the redundancy rates of neighborhood granule sets induced by some big scale data sets exceed 99%, which indicates that the existing neighborhood granulation methods need to be urgently improved. Based on this, concise granular structures and much more efficient feature selection algorithms will be proposed in the future.
12 May 2023 in IEEE Transactions on Fuzzy Systems
Large-scale data processing based on limited computing resources has always been a difficult problem in data mining, where feature selection is often used as an effective data compressing mechanism. For granular computing of big data, discernibility matrix and dependency degree are the most representative methods for matrix-based and feature importance degree-based feature selection, respectively. However, their temporal and space complexities are high and often lead to poor performance. In this paper, a novel feature selection framework for large scale data processing with linear complexities was proposed for the first time. Firstly, a much more concise fuzzy granule set, called fuzzy arithmetic covering, was introduced to reduce computational costs. Then a new matrix-based feature selection framework, namely consistent matrix, was proposed for general rough set models. As a result, a heuristic attribute reduction algorithm, i.e., HARCM, was designed accordingly. Compared with six state-of-the-art algorithms for feature selection, the average running time of the newly proposed algorithm was reduced up to 2913 times, with a comparable or even better classification performance.
1 November 2016 in Journal of Alloys and Compounds
29 October 2024 in IEEE Transactions on Knowledge and Data Engineering
Monotonic classification is a special ordinal classification task that involves monotonicity constraints between features and the decision. Monotonic feature selection can reduce dimensionality while preserving the monotonicity constraints, ultimately improving the efficiency and performance of monotonic classifiers. However, existing feature selection algorithms cannot handle large-scale monotonic data sets due to their lack of consideration for monotonic constraints or their high computational complexities. To address these issues, building on our team's previous research, we define the monotonic related family method with lower time complexity to select informative features and obtain multi-reducts carrying complementary information from multi-view for raw feature space. Using bi-directional rank mutual information, we build two trees for each feature subset and fuse all trees using the corresponding decision support level (BFMDT). Compared with six representative algorithms for monotonic feature selection, BFMDT's average classification accuracy increased by 4.06% (FFREMT), 6.77% (FCMT), 5.61% (FPRS_up), 6.05% (FPRS_down), 5.86%(FPRS_global), 4.41% (Bagging), 7.65% (REMT) and 21.89% (FMKNN), the average execution time compared to tree-based algorithms decreased by 83.41% (FFREMT), 96.96% (FCMT), 75.64% (FPRS_up), 59.43% (FPRS_down), 84.65%(FPRS_global), 81.50% (Bagging) and 63.41% (REMT), while most of comparing algorithms were unable to complete computation on six high-dimensional datasets.
5 March 2025 in IEEE Transactions on Fuzzy Systems
Biselection (feature and sample selection) enhances the efficiency and accuracy of machine learning models when handling large-scale data. Fuzzy rough sets, an uncertainty mathematics model known for its excellent interpretability, are widely used in machine learning, particularly for feature selection. While the consistent matrix has significantly improved the computational efficiency and scalability of feature selection, like most fuzzy rough set-based methods, it focuses only on feature selection and seldom incorporates sample selection. This feature-centric approach can limit classification performance, particularly in noisy and large-scale datasets where both features and samples require judicious selection. To overcome these limitations, this article explores the integration of sample selection with feature selection. First, we introduce a $\beta$-consistent granulation method to generate more accurate and concise fuzzy information granules, reducing the impact of noisy samples. In addition, a novel membership function is employed to distinguish noise while simultaneously evaluating both features and samples. As a result, a biselection algorithm with linear computation complexity is proposed to select high-quality features and samples. Numerical experiments demonstrate that, compared to eleven representative algorithms, our proposed method achieves an average accuracy improvement of 9.66% and a 933-fold increase in efficiency.
19 December 2025 in IEEE Transactions on Fuzzy Systems
Density-based clustering algorithms are widely used for discovering clusters of arbitrary shapes without prior knowledge, yet they encounter major challenges when dealing with fuzzy boundaries and ensuring scalability on complex datasets. To address these issues, we propose a novel density-based fuzzy rough clustering algorithm (DFR). First, a new definition of core points is introduced by incorporating fuzzy dominance relations, enabling more accurate identification of dense regions. Second, DFR decomposes the clustering process into independent expansion and clustering stages, with hyperparameters that enhance the flexibility and adaptability of the algorithm. Third, by integrating fuzzy rough set theory with Euclidean distance, the algorithm effectively handles boundary fuzziness and simultaneously improves stability and outlier detection. Experimental results on a wide range of synthetic and real-world datasets demonstrate that DFR consistently outperforms stateof- the-art clustering methods, particularly excelling in scenarios with fuzzy boundaries and high-dimensional data. Through these innovations, DFR achieves superior clustering accuracy, robustness, and interpretability, offering an efficient and reliable solution for complex data analysis.