Adaptive three-way KNN classifier using density-based granular balls DOI
Jie Yang,

Juncheng Kuang,

Guoyin Wang

et al.

Information Sciences, Journal Year: 2024, Volume and Issue: 678, P. 120858 - 120858

Published: June 3, 2024

Language: Английский

Anomaly detection based on weighted fuzzy-rough density DOI
Zhong Yuan, Baiyang Chen, Jia Liu

et al.

Applied Soft Computing, Journal Year: 2023, Volume and Issue: 134, P. 109995 - 109995

Published: Jan. 7, 2023

Language: Английский

Citations

50
A sequential three-way decision-based group consensus method under probabilistic linguistic term sets DOI
Xinru Han, Jianming Zhan

Information Sciences, Journal Year: 2023, Volume and Issue: 624, P. 567 - 589

Published: Jan. 4, 2023

Language: Английский

Citations

42
3WC-GBNRS++: A novel three-way classifier with granular-ball neighborhood rough sets based on uncertainty DOI
Jie Yang, Zhuangzhuang Liu, Shuyin Xia

et al.

IEEE Transactions on Fuzzy Systems, Journal Year: 2024, Volume and Issue: 32(8), P. 4376 - 4387

Published: May 7, 2024

Three-way decision with neighborhood rough sets (3WDNRS) is adept at addressing uncertain problems involving continuous data by configuring the radius. However, on one hand, inputs of 3WDNRS are individual granules, which reduce efficiency and generality; other thresholds require prior knowledge to be approximately set in advance, making it difficult apply cases where such unavailable. To address these issues, we introduce granular-ball computing (GBC) into from perspective uncertainty. Firstly, propose an enhanced generation method based DBSCAN called DBGBC. Subsequently, present improved model (GBNRS++) combining DBGBC a quality index. Furthermore, construct three-way classifier (3WC-GBNRS++) principle minimum fuzziness loss. This approach provides objective efficient way determine thresholds. further enhance classification accuracy, design adaptive within subsequent process 3WC-GBNRS++. Finally, experimental results demonstrate that, 3WC-GBNRS++ almost outperformed comparison methods terms effectiveness robustness, including 4 state-of-the-art granular-balls-based classifiers 5 classical machine learning 12 public benchmark datasets. Moreover, discuss limitations our work outlook for future research.

Language: Английский

Citations

22
Three-way decisions based multi-attribute decision-making with utility and loss functions DOI
Garima Bisht, Arun Kumar

European Journal of Operational Research, Journal Year: 2024, Volume and Issue: 316(1), P. 268 - 281

Published: Feb. 2, 2024

Language: Английский

Citations

18
The multi-criteria ranking method for criterion-oriented regret three-way decision DOI
Weixing Wan, Kai Zhang, Ligang Zhou

et al.

International Journal of Approximate Reasoning, Journal Year: 2025, Volume and Issue: unknown, P. 109374 - 109374

Published: Jan. 1, 2025

Language: Английский

Citations

2
Reimagining multi-criterion decision making by data-driven methods based on machine learning: A literature review DOI
Huchang Liao,

Yangpeipei He,

Xueyao Wu

et al.

Information Fusion, Journal Year: 2023, Volume and Issue: 100, P. 101970 - 101970

Published: Aug. 3, 2023

Language: Английский

Citations

39
Threat assessment of aerial targets based on improved GRA-TOPSIS method and three-way decisions DOI Creative Commons
Yongfeng Yin,

Routing Zhang,

Qingran Su

et al.

Mathematical Biosciences & Engineering, Journal Year: 2023, Volume and Issue: 20(7), P. 13250 - 13266

Published: Jan. 1, 2023

<abstract><p>Target threat assessment is a critical aspect of information warfare and can offer valuable auxiliary support to combat command decision-making. Aiming address the shortcomings three decision-making methods in air target assessment, such as inability effectively handle uncertain situation quantitatively rank targets according their importance, dynamic intuitionistic fuzzy decision model based on improved GRA-TOPSIS method three-way decisions proposed. First, attribute weight obtained by cosine entropy algorithm; then, novel distance measure introduced, grey incidence analysis TOPSIS are used build conditional probability for that fully utilize existing reflect consistency change trend; finally, comprehensive loss function matrix constructed classification results using rules. The example shows proposed not only complex battlefield situations information, but it also classify targets, improving effectiveness rationality providing reference basis scientific decision-making.</p></abstract>

Language: Английский

Citations

31
Three-way conflict analysis based on hybrid situation tables DOI
Hai-Long Yang, Ye Wang,

Zhi-Lian Guo

et al.

Information Sciences, Journal Year: 2023, Volume and Issue: 628, P. 522 - 541

Published: Feb. 6, 2023

Language: Английский

Citations

27
A preference-approval structure-based non-additive three-way group consensus decision-making approach for medical diagnosis DOI
Jin Ye, Bingzhen Sun, Juncheng Bai

et al.

Information Fusion, Journal Year: 2023, Volume and Issue: 101, P. 102008 - 102008

Published: Sept. 9, 2023

Language: Английский

Citations

27
Three-way multi-attribute decision-making under the double hierarchy hesitant fuzzy linguistic information system DOI
Nanfang Luo, Qinghua Zhang, Longjun Yin

et al.

Applied Soft Computing, Journal Year: 2024, Volume and Issue: 154, P. 111315 - 111315

Published: Feb. 2, 2024

Language: Английский

Citations

13