[1]徐伟华,张崇泽.基于多尺度注意力的模糊概念认知学习[J].智能系统学报,2026,21(3):783-791.[doi:10.11992/tis.202510039]
XU Weihua,ZHANG Chongze.Fuzzy concept cognitive learning based on multi-scale attention[J].CAAI Transactions on Intelligent Systems,2026,21(3):783-791.[doi:10.11992/tis.202510039]
点击复制
XU Weihua,ZHANG Chongze.Fuzzy concept cognitive learning based on multi-scale attention[J].CAAI Transactions on Intelligent Systems,2026,21(3):783-791.[doi:10.11992/tis.202510039]
基于多尺度注意力的模糊概念认知学习
《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷:
21
期数:
2026年第3期
页码:
783-791
栏目:
学术论文—人工智能基础
出版日期:
2026-05-05
- Title:
- Fuzzy concept cognitive learning based on multi-scale attention
- Keywords:
- concept-cognitive learning; multi-scale; attention mechanism; granular computing; object classification; formal context; knowledge discovery; concept clustering
- 分类号:
- TP18
- 文献标志码:
- 2026-3-14
- 摘要:
- 概念认知学习(conceptual cognitive learning，CCL)以概念为知识载体，研究事物的认知学习过程，广泛应用于知识发现与对象分类。现有模糊CCL模型多基于单一尺度构建，未能充分利用多尺度信息，且忽视了注意力机制在人类认知中的作用。为此，本文提出一种基于多尺度注意力的模糊概念认知学习模型(multi-scale attention-based fuzzy conceptual cognitive learning model，MSA-CCL)。该方法首先构建多尺度模糊形式背景，并通过一致性判定选择最优尺度用于模糊概念学习；随后为各条件属性引入注意力机制，构建模糊概念注意力空间，突出关键属性的重要性；进一步生成伪模糊概念注意力空间，通过计算新对象与伪概念的相似度，实现对象分类与概念识别。在UCI的9个数据集上验证了该方法的有效性和可行性。
- Abstract:
- Concept-cognitive learning (CCL) treats concepts as the fundamental carriers of knowledge and examines the cognitive learning process of objects. It has been widely applied to knowledge discovery and object classification. However, existing fuzzy CCL models are mostly constructed at a single scale, which limits their ability to exploit multi-scale information and overlooks the role of attention mechanisms in human cognition. To address these issues, this paper proposes a multi-scale attention-based fuzzy concept-cognitive learning (MSA-CCL) model. The proposed method first constructs multi-scale fuzzy formal contexts and selects the optimal scale through consistency evaluation for fuzzy concept learning. Next, an attention mechanism is introduced for each conditional attribute to build a fuzzy concept attention space, which highlights the importance of key attributes. Finally, a pseudo-fuzzy concept attention space is generated to perform object classification and concept recognition based on the similarity between new objects and pseudo-concepts. Experiments on nine UCI machine learning repository datasets demonstrate the effectiveness and feasibility of the proposed method.
- 参考文献/References:
-
[1] 窦万春, 刘茜萍, 蔡士杰. 面向认知协作的知识流分析与研究[J]. 计算机研究与发展, 2006, 43(6): 1109-1114 DOU Wanchun, LIU Xiping, CAI Shijie. Cognitive-cooperation-oriented knowledge flow research[J]. Journal of computer research and development, 2006, 43(6): 1109-1114
[2] ZHU Xiubin, PEDRYCZ W, LI Zhiwu. Construction and evaluation of information granules: from the perspective of clustering[J]. IEEE transactions on systems, man, and cybernetics: systems, 2022, 52(3): 2024-2037
[3] YUAN Kehua, MIAO Duoqian, PEDRYCZ W, et al. Multigranularity data analysis with zentropy uncertainty measure for efficient and robust feature selection[J]. IEEE transactions on cybernetics, 2025, 55(2): 740-752
[4] 徐怡, 姚一豫. 划分序乘积空间: 基于划分的粒计算模型[J]. 计算机研究与发展, 2019, 56(4): 836-843 XU Yi, YAO Yiyu. Partition order product space: partition based granular computing model[J]. Journal of computer research and development, 2019, 56(4): 836-843
[5] 张文修, 吴伟志, 梁吉业, 等. 粗糙集理论与方法[M]. 北京: 科学出版社, 2001.
[6] DING Juanjuan, ZHANG Chao, LI Deyu, et al. Three-way decisions in generalized intuitionistic fuzzy environments: survey and challenges[J]. Artificial intelligence review, 2024, 57(2): 38
[7] WILLE R. Concept lattices and conceptual knowledge systems[J]. Computers & mathematics with applications, 1992, 23(6/7/8/9): 493-515
[8] ZHANG Wenxiu, XU Weihua. Cognitive model based on granular computing[J]. Chin J Eng Math, 2007, 24(6): 957-971
[9] KANG Xiangping, LI Deyu, WANG Suge, et al. Formal concept analysis based on fuzzy granularity base for different granulations[J]. Fuzzy sets and systems, 2012, 203: 33-48
[10] HUANG Chenchen, LI Jinhai, MEI Changlin, et al. Three-way concept learning based on cognitive operators: an information fusion viewpoint[J]. International journal of approximate reasoning, 2017, 83: 218-242
[11] XU Weihua, GUO Doudou, QIAN Yuhua, et al. Two-way concept-cognitive learning method: a fuzzy-based progressive learning[J]. IEEE transactions on fuzzy systems, 2023, 31(6): 1885-1899
[12] ZHANG Xiaoyan, GUO Doudou, XU Weihua. Two-way concept-cognitive learning with multi-source fuzzy context[J]. Cognitive computation, 2023, 15(5): 1526-1548
[13] YAO Yiyu. Interpreting concept learning in cognitive informatics and granular computing[J]. IEEE transactions on systems, man, and cybernetics, part B (cybernetics), 2009, 39(4): 855-866
[14] SHI Yong, MI Yunlong, LI Jinhai, et al. Concurrent concept-cognitive learning model for classification[J]. Information sciences, 2019, 496: 65-81
[15] MI Yunlong, SHI Yong, LI Jinhai, et al. Fuzzy-based concept learning method: exploiting data with fuzzy conceptual clustering[J]. IEEE transactions on cybernetics, 2022, 52(1): 582-593
[16] LIU Zhiming, LI Jinhai, ZHANG Xiao, et al. Incremental incomplete concept-cognitive learning model: a stochastic strategy[J]. IEEE transactions on neural networks and learning systems, 2025, 36(1): 393-406
[17] WANG Jinbo, XU Weihua, DING Weiping, et al. Multiview fuzzy concept-cognitive learning with high-order information fusion of fuzzy attributes[J]. IEEE transactions on fuzzy systems, 2024, 32(12): 6965-6978
[18] GUO Doudou, XU Weihua, QIAN Yuhua, et al. Fuzzy-granular concept-cognitive learning via three-way decision: performance evaluation on dynamic knowledge discovery[J]. IEEE transactions on fuzzy systems, 2024, 32(3): 1409-1423
[19] WU Jiaming, TSANG E C C, XU Weihua, et al. Correlation concept-cognitive learning model for multi-label classification[J]. Knowledge-based systems, 2024, 290: 111566
[20] ZHOU Yinfeng, YANG Hailong, LI Jinjin, et al. Skill assessment method: a perspective from concept-cognitive learning[J]. Fuzzy sets and systems, 2025, 508: 109331
[21] YAHIA S B, AROUR K, SLIMANI A, et al. Discovery of compact rules in relational databases[J]. Information Science Journal, 2000, 4(3): 497-511
[22] WU Weizhi, LEUNG Y. Theory and applications of granular labelled partitions in multi-scale decision tables[J]. Information sciences, 2011, 181(18): 3878-3897
[23] 郭豆豆, 徐伟华. R-FCCL: 一种面向高维数据的稳健模糊概念认知学习方法[J]. 计算机研究与发展, 2025, 62(2): 383-396 GUO Doudou, XU Weihua. R-FCCL: an approach of fuzzy-based concept-cognitive learning with robustness for high-dimensional data[J]. Journal of computer research and development, 2025, 62(2): 383-396
[24] LI Feng, HU Bao qing. A new approach of optimal scale selection to multi-scale decision tables[J]. Information sciences, 2017, 381: 193-208
[25] COVER T, HART P. Nearest neighbor pattern classification[J]. IEEE transactions on information theory, 1967, 13(1): 21-27
[26] SONG Yanyan, LU Ying. Decision tree methods: applications for classification and prediction[J]. Shanghai archives of psychiatry, 2015, 27(2): 130-135
[27] MURPHY K P. Naive bayes classifiers[J]. University of British Columbia, 2006, 18(60): 1-8
[28] ZHANG Chengling, TSANG E C C, XU Weihua, et al. Incremental concept-cognitive learning approach for concept classification oriented to weighted fuzzy concepts[J]. Knowledge-based systems, 2023, 260: 110093
[29] DING Yi, XU Weihua, DING Weiping, et al. IFCRL: interval-intent fuzzy concept re-cognition learning model[J]. IEEE transactions on fuzzy systems, 2024, 32(6): 3581-3593
[30] KUNCHEVA L. An intuitionistic fuzzy K-nearest neighbors rule[J]. Notes intuit fuzzy sets, 1995, 1: 56-60
[31] ARIF M, AKRAM M U, MINHAS F A. Pruned fuzzy K-nearest neighbor classifier for beat classification[J]. Journal of biomedical science and engineering, 2010, 3(4): 380-389
[32] 李金海, 闫梦宇, 徐伟华, 等. 概念认知学习的若干问题与思考[J]. 西北大学学报(自然科学版), 2020(4): 501-515 LI Jinhai, YAN Mengyu, XU Weihua, et al. Some problems and thoughts on concept-cognitive learning[J]. Journal of Northwest University (natural science edition), 2020(4): 501-515
- 相似文献/References:
-
[1]王成济,罗志明,钟准,等.一种多层特征融合的人脸检测方法[J].智能系统学报,2018,13(1):138.[doi:10.11992/tis.201707018]
WANG Chengji,LUO Zhiming,ZHONG Zhun,et al.Face detection method fusing multi-layer features[J].CAAI Transactions on Intelligent Systems,2018,13():138.[doi:10.11992/tis.201707018]
[2]杨恢先,付宇,曾金芳,等.基于正交Log-Gabor滤波二值模式的人脸识别算法[J].智能系统学报,2019,14(2):330.[doi:10.11992/tis.201708015]
YANG Huixian,FU Yu,ZENG Jinfang,et al.Face recognition based on orthogonal Log-Gabor binary pattern[J].CAAI Transactions on Intelligent Systems,2019,14():330.[doi:10.11992/tis.201708015]
[3]雷芳,熊建斌,张磊,等.金属腐蚀区域图像增强算法研究[J].智能系统学报,2019,14(2):385.[doi:10.11992/tis.201712024]
LEI Fang,XIONG Jianbin,ZHANG Lei,et al.Image enhancement algorithm in metal corrosion area[J].CAAI Transactions on Intelligent Systems,2019,14():385.[doi:10.11992/tis.201712024]
[4]赵文清,周震东,翟永杰.基于反卷积和特征融合的SSD小目标检测算法[J].智能系统学报,2020,15(2):310.[doi:10.11992/tis.201905035]
ZHAO Wenqing,ZHOU Zhendong,ZHAI Yongjie.SSD small target detection algorithm based on deconvolution and feature fusion[J].CAAI Transactions on Intelligent Systems,2020,15():310.[doi:10.11992/tis.201905035]
[5]曹锦纲,李金华,郑顾平.基于生成式对抗网络的道路交通模糊图像增强[J].智能系统学报,2020,15(3):491.[doi:10.11992/tis.201903041]
CAO Jin gang,LI Jinhua,ZHENG Guping.Enhancement of blurred road-traffic images based on generative adversarial network[J].CAAI Transactions on Intelligent Systems,2020,15():491.[doi:10.11992/tis.201903041]
[6]刘万军,佟畅,曲海成.空洞卷积与注意力融合的对抗式图像阴影去除算法[J].智能系统学报,2021,16(6):1081.[doi:10.11992/tis.202011022]
LIU Wanjun,TONG Chang,QU Haicheng.An antagonistic image shadow removal algorithm based on dilated convolution and attention mechanism[J].CAAI Transactions on Intelligent Systems,2021,16():1081.[doi:10.11992/tis.202011022]
[7]周静,胡怡宇,黄心汉.形状补全引导的Transformer点云目标检测方法[J].智能系统学报,2023,18(4):731.[doi:10.11992/tis.202210038]
ZHOU Jing,HU Yiyu,HUANG Xinhan.Shape completion-guided Transformer point cloud object detection method[J].CAAI Transactions on Intelligent Systems,2023,18():731.[doi:10.11992/tis.202210038]
[8]张少乐,雷涛,王营博,等.基于多尺度金字塔Transformer的人群计数方法[J].智能系统学报,2024,19(1):67.[doi:10.11992/tis.202304044]
ZHANG Shaole,LEI Tao,WANG Yingbo,et al.A crowd counting network based on multi-scale pyramid Transformer[J].CAAI Transactions on Intelligent Systems,2024,19():67.[doi:10.11992/tis.202304044]
[9]赵文清,赵振寰,巩佳潇.结合倒残差自注意力机制的遥感图像目标检测[J].智能系统学报,2025,20(1):64.[doi:10.11992/tis.202312001]
ZHAO Wenqing,ZHAO Zhenhuan,GONG Jiaxiao.Remote sensing image object detection based on inverted residual self-attention mechanism[J].CAAI Transactions on Intelligent Systems,2025,20():64.[doi:10.11992/tis.202312001]
[10]牛苗赫,雷飞.面向下肢外骨骼的运动意图识别算法研究[J].智能系统学报,2025,20(2):407.[doi:10.11992/tis.202403025]
NIU Miaohe,LEI Fei.Motion intention recognition algorithms for lower limb exoskeleton[J].CAAI Transactions on Intelligent Systems,2025,20():407.[doi:10.11992/tis.202403025]
备注/Memo
收稿日期:2025-10-30。
基金项目:国家自然科学基金项目(62376229)；重庆市自然科学基金项目(CSTB2023NSCQ-LZX0027).
作者简介:徐伟华，教授，博士生导师，主要研究方向为粒计算、认知计算、数据挖掘和机器学习。主持国家自然科学基金项目4项、省部级项目20余项。出版学术著作5部，发表学术论文260余篇。E-mail：chxuwh@gmail.com。;张崇泽，硕士研究生，主要研究方向为粒计算、概念认知学习。E-mail：a1157260366@163.com。
通讯作者:徐伟华. E-mail：chxuwh@gmail.com
更新日期/Last Update:
1900-01-01