Concept cognition over knowledge graphs: A perspective from mining multi-granularity attribute characteristics of concepts DOI
Xin Hu,

Deju Huang,

Jiangli Duan

и другие.

Information Processing & Management, Год журнала: 2025, Номер 62(4), С. 104095 - 104095

Опубликована: Фев. 11, 2025

Язык: Английский

Concept-cognitive learning survey: Mining and fusing knowledge from data DOI
Doudou Guo, Weihua Xu, Weiping Ding

и другие.

Information Fusion, Год журнала: 2024, Номер 109, С. 102426 - 102426

Опубликована: Апрель 16, 2024

Язык: Английский

Процитировано

28

Three-way multi-label classification: A review, a framework, and new challenges DOI

Yuanjian Zhang,

Tianna Zhao, Duoqian Miao

и другие.

Applied Soft Computing, Год журнала: 2025, Номер unknown, С. 112757 - 112757

Опубликована: Янв. 1, 2025

Язык: Английский

Процитировано

2

Fuzzy-Granular Concept-Cognitive Learning via Three-Way Decision: Performance Evaluation on Dynamic Knowledge Discovery DOI
Doudou Guo, Weihua Xu, Yuhua Qian

и другие.

IEEE Transactions on Fuzzy Systems, Год журнала: 2023, Номер 32(3), С. 1409 - 1423

Опубликована: Окт. 19, 2023

Concept-cognitive learning (CCL) and three-way decision (3WD) models provide powerful techniques for knowledge discovery. Some early attempts in the field have successfully combined CCL 3WD, i.e., concept learning. However, only a few were made to combine with 3WD dynamic fuzzy context due two challenges: 1) Three-way incapability; 2) The current incremental mechanism is insufficient model real-time updating cognitive procedure. Hence, this article first shows some new standpoints on improving fuzzy-based accuracy then proposes fuzzy-granular concept-cognitive (F3WG-CCL) modeling Specifically, we define F3WG-concept characterize embedded data. Furthermore, big priority principle an update are borrowed recognition cognition. Finally, show that F3WG-CCL can be implemented simultaneously via theoretical guarantee sufficient experimental, including achieving state-of-the-art learning; demonstrating effective context; 3) discovering valuable recognition. Our work will approach research

Язык: Английский

Процитировано

42

Feature Selection Using Zentropy-Based Uncertainty Measure DOI
Kehua Yuan, Duoqian Miao, Yiyu Yao

и другие.

IEEE Transactions on Fuzzy Systems, Год журнала: 2023, Номер 32(4), С. 2246 - 2260

Опубликована: Дек. 28, 2023

Feature selection and entropy theory are two efficacious data analysis tools for investigating uncertainty information processing in artificial intelligence. The fruitful marriage of the has been an active research topic knowledge discovery. Currently, most feature methods via mainly focus on measures at a single granular level. However, it ignores interaction between levels, which leads to poor stability accuracy related methods. Hence, this article proposes novel zentropy-based measure design method by exploiting level structure space. Subsequently, analyzing decision data, its properties designed analyzed depict from whole internal. Moreover, importance defined evaluate features based measure, then corresponding algorithm is developed. Finally, some experiments carried out public datasets demonstrate that proposed can achieve state-of-the-art performance among methods, especially regarding classification accuracy.

Язык: Английский

Процитировано

24

A local rough set method for feature selection by variable precision composite measure DOI
Kehua Yuan, Weihua Xu, Duoqian Miao

и другие.

Applied Soft Computing, Год журнала: 2024, Номер 155, С. 111450 - 111450

Опубликована: Март 4, 2024

Язык: Английский

Процитировано

17

Ze-HFS: Zentropy-Based Uncertainty Measure for Heterogeneous Feature Selection and Knowledge Discovery DOI
Kehua Yuan, Duoqian Miao, Witold Pedrycz

и другие.

IEEE Transactions on Knowledge and Data Engineering, Год журнала: 2024, Номер 36(11), С. 7326 - 7339

Опубликована: Июнь 26, 2024

Язык: Английский

Процитировано

17

Semi-supervised feature selection by minimum neighborhood redundancy and maximum neighborhood relevancy DOI

Damo Qian,

Keyu Liu, Shiming Zhang

и другие.

Applied Intelligence, Год журнала: 2024, Номер 54(17-18), С. 7750 - 7764

Опубликована: Июнь 13, 2024

Язык: Английский

Процитировано

15

Correlation concept-cognitive learning model for multi-label classification DOI
Jiaming Wu, Eric C.C. Tsang, Weihua Xu

и другие.

Knowledge-Based Systems, Год журнала: 2024, Номер 290, С. 111566 - 111566

Опубликована: Фев. 24, 2024

Язык: Английский

Процитировано

10

Zoom method for association rules in multi-granularity formal context DOI

Lihui Niu,

Ju‐Sheng Mi,

Yuzhang Bai

и другие.

Soft Computing, Год журнала: 2025, Номер unknown

Опубликована: Фев. 8, 2025

Язык: Английский

Процитировано

1

An Emerging Incremental Fuzzy Concept-Cognitive Learning Model Based on Granular Computing and Conceptual Knowledge Clustering DOI
X. Deng, Jinhai Li, Yuhua Qian

и другие.

IEEE Transactions on Emerging Topics in Computational Intelligence, Год журнала: 2024, Номер 8(3), С. 2417 - 2432

Опубликована: Фев. 14, 2024

Fuzzy granular concepts are fundamental units in developing computational intelligence approaches based on fuzzy concept-cognitive learning. However, existing models this field merely focus the information provided by induced objects, ignoring that of those attributes. Consequently, these underutilize and weaken classification ability. To solve problem, we propose an effective learning model, which incorporates attribute basis object concepts. be concrete, firstly introduce notion a concept construct space. Secondly, obtain clustering space optimizing threshold is used to fuse similar concepts, then form lower upper approximation spaces through set approximation. In addition, explain mechanism new incremental model for label prediction integrating spaces. Finally, show performance proposed 28 datasets comparing it with 10 classical machine algorithms 17 similarity-based algorithms, evaluate ability our model. The experimental results demonstrate feasibility effectiveness method.

Язык: Английский

Процитировано

9