认知不确定性问题的边界思维

张清华; 洪承鑫; 赵凡; 高满; 程云龙; 王国胤

doi:10.12263/DZXB.20250577

您当前的位置：

首页 >

文章列表页 >

认知不确定性问题的边界思维

学术论文 | 更新时间：2026-02-05

- 认知不确定性问题的边界思维
- Boundary Thinking for Cognitive Uncertainty Problems
- 电子学报 2025年53卷第10期页码：3622-3639
- 作者机构：
  
  1.重庆邮电大学计算机科学与技术学院，重庆 400065
  2.重庆邮电大学计算智能重庆市重点实验室，重庆 400065
  3.网络空间大数据智能安全教育部重点实验室，重庆 400065
  4.旅游多源数据感知与决策技术文化和旅游部重点实验室，重庆 400065
  5.山西师范大学数学科学学院，山西太原 030031
  6.川渝共建数字经济智能与安全重点实验室，重庆 400065
  7.类脑认知计算与特殊儿童教育康复重庆市重点实验室（重庆师范大学），重庆 401331
- 作者简介：
  
  [ "张清华男，1974年11月出生于重庆市.教授、博士生导师.现为重庆邮电大学副校长.主要研究方向为粒计算、不确定性信息处理、大数据智能.E-mail: zhangqh@cqupt.edu.cn" ]
  [ "洪承鑫男，1997年1月出生于安徽省安庆市.重庆邮电大学计算机科学与技术学院博士研究生.主要研究方向为粒计算、三支决策、不确定性信息处理.E-mail: hongchengxinaq@163.com" ]
  [ "赵凡女，1996年8月出生于山西省忻州市.现为陕西师范大学数学科学学院讲师.主要研究方向为粒计算、不确定信息处理与度量.E-mail: 837062256@qq.com" ]
  [ "高满男，1994年11月出生于河南省南阳市.重庆邮电大学计算机科学与技术学院博士研究生.主要研究方向为粒计算、阴影集、三支决策.E-mail: d200201005@stu.cqupt.edu.cn" ]
  [ "程云龙男，1978年3月出生于湖北省利川市.副教授、硕士生导师.主要研究方向为粒计算、不确定性信息处理、数据挖掘.E-mail: chengyl@cqupt.edu.cn" ]
  [ "王国胤男，1970年3月出生于重庆市.教授、博士生导师.现为重庆师范大学校长.主要研究方向为粒计算、认知计算、人工智能.E-mail: wanggy@cqnu.edu.cn" ]
- 基金信息：
  
  国家自然科学基金(62276038;62221005);重庆市教委重点合作项目(HZ2021008);重庆市自然科学基金创新发展联合基金(CSTB2023NSCQ-LZX0164);重庆英才计划(cstc2022ycjh-bgzxm0089);重庆邮电大学博士人才培养计划(BYJS202407)
- DOI：10.12263/DZXB.20250577
  中图分类号： TP39
- 收稿：2025-06-30，
  
  录用：2025-10-13，
  
  纸质出版：2025-10-25
- 稿件说明：
移动端阅览
张清华, 洪承鑫, 赵凡, 等. 认知不确定性问题的边界思维[J]. 电子学报, 2025, 53(10): 3622-3639.

ZHANG Qing-hua, HONG Cheng-xin, ZHAO Fan, et al. Boundary Thinking for Cognitive Uncertainty Problems[J]. Acta Electronica Sinica, 2025, 53(10): 3622-3639.
张清华, 洪承鑫, 赵凡, 等. 认知不确定性问题的边界思维[J]. 电子学报, 2025, 53(10): 3622-3639. DOI：10.12263/DZXB.20250577

ZHANG Qing-hua, HONG Cheng-xin, ZHAO Fan, et al. Boundary Thinking for Cognitive Uncertainty Problems[J]. Acta Electronica Sinica, 2025, 53(10): 3622-3639. DOI：10.12263/DZXB.20250577

摘要

不确定性问题在现实世界中普遍存在，对人类理解认知世界和决策行为产生重大影响，也是不确定性人工智能研究的重要课题之一.尽管人工智能在处理不确定性问题方面取得一定进展，但仍难以有效认知处理不确定性问题.不确定性主要来源于概念边界的不确定性及刻画概念边界信息不足导致的不确定性.因此，如何准确识别不确定性问题的边界并有效处理边界成为人工智能领域的重要科学问题.本文首先总结归纳了认知处理不确定性问题的理论模型和方法，揭示了认知不确定性问题本质上是研究两个对立状态（确定状态）之间转变的过渡状态（边界），即识别和处理边界问题.随后从认知不确定性问题边界的角度，按照“点、线、面”的精确边界到“区间、区域、空间”的模糊边界等不同维度，分析了不确定性问题的边界呈现形式.最后，对处理不确定性问题的边界理论进行了讨论和总结，并对未来研究问题和方向进行了展望.本文研究为认知不确定性问题提供了一个新的视角，旨在推动不确定性问题的边界理论的发展和完善.

Abstract

Uncertainty problems are ubiquitous in the real world and have a significant impact on human understanding

cognition

and decision-making

making them an important topic in uncertain artificial intelligence research. Despite the fact that some progress has been made in artificial intelligence in dealing with uncertainty problems

it remains a challenging task to effectively address cognitive uncertainty. Uncertainty arises primarily from the conceptual boundary and from insufficient information to characterize it. Therefore

how to accurately identify the boundary for uncertainty and effectively deal with the boundary has become an important scientific problem in the field of artificial intelligence. This paper first summarizes the theoretical models and methods for dealing with uncertainty

revealing that the cognitive uncertainty is essentially the study of the transition state (boundary) between two opposing states (certainty)

that is

the problem of identifying and dealing with the boundary. Secondly

the presentation forms of uncertainty in different dimensions are analyzed from the perspective of cognitive uncertainty boundary

such as the precise boundary of “point

line

and surface”and the fuzzy boundary of “interval

region

and space”. Finally

the boundary theory for uncertainty is discussed and summarized

and future research questions and directions are prospected. This study provides a new perspective on cognitive uncertainty and aims to promote the development and refinement of the boundary theory for uncertainty.

关键词

Keywords

references

王国胤 , 张清华 , 马希骜 , 等 . 知识不确定性问题的粒计算模型 [J ] . 软件学报 , 2011 , 22 ( 4 ): 676 - 694 .

WANG G Y , ZHANG Q H , MA X A , et al . Granular computing models for knowledge uncertainty [J ] . Journal of Software , 2011 , 22 ( 4 ): 676 - 694 . (in Chinese)

李德毅 , 刘常昱 , 杜鹢 , 等 . 不确定性人工智能 [J ] . 软件学报 , 2004 , 15 ( 11 ): 1583 - 1594 .

LI D Y , LIU C Y , DU Y , et al . Artificial intelligence with uncertainty [J ] . Journal of Software , 2004 , 15 ( 11 ): 1583 - 1594 . (in Chinese)

智慧来 , 张丽 , 李金海 . 旁观者视角下粒的多层次描述 [J ] . 电子学报 , 2022 , 50 ( 11 ): 2568 - 2574 .

ZHI H L , ZHANG L , LI J H . Multi-level description of granules from an outsider's perspective [J ] . Acta Electronica Sinica , 2022 , 50 ( 11 ): 2568 - 2574 . (in Chinese)

张清华 , 王宇泰 , 赵凡 , 等 . 复杂问题求解的多粒度计算框架 [J ] . 中国科学: 信息科学 , 2025 , 55 ( 5 ): 1122 - 1139 .

ZHANG Q H , WANG Y T , ZHAO F , et al . Multi-granularity computing framework for complex problem solving [J ] . Scientia Sinica Informationis , 2025 , 55 ( 5 ): 1122 - 1139 . (in Chinese)

艾萨克·牛顿 . 自然哲学的数学原理 [M ] . 范明, 译. 上海 : 上海译文出版社 , 2021 .

NEWTON I . Mathematical Principles of Natural Philosophy and its System of the World [M ] . FAN M, Trans. Shanghai : Shanghai Translation Publishing House , 2021 . (in Chinese)

STRIEN M V . On the origins and foundations of Laplacian determinism [J ] . Studies in History and Philosophy of Science Part A , 2014 , 45 : 24 - 31 .

BUSCH P , HEINONEN T , LAHTI P . Heisenberg's uncertainty principle [J ] . Physics Reports , 2007 , 452 ( 6 ): 155 - 176 .

SMULLYAN R M . Gödel's Incompleteness Theorems [M ] . New York : Oxford University Press , 1992 .

KLINE M . 数学: 确定性的丧失 [M ] . 李宏魁, 译. 长沙 : 湖南科学技术出版社 , 1997 .

KLINE M . Mathematics: The Loss of Certainty [M ] . LI H K, Trans. Changsha : Hunan Science and Technology Press , 1997 . (in Chinese)

KUNDA Z . The case for motivated reasoning [J ] . Psychological Bulletin , 1990 , 108 ( 3 ): 480 - 498 .

SOX H C , HIGGINS M C , OWENS D K , et al . Medical Decision Making [M ] . New York : Wiley , 2024 .

NGUYEN A T , TANIGUCHI T , ECIOLAZA L , et al . Fuzzy control systems: Past, present and future [J ] . IEEE Computational Intelligence Magazine , 2019 , 14 ( 1 ): 56 - 68 .

KULKARNI V G . Modeling and Analysis of Stochastic Systems [M ] . London : Chapman & Hall , 1995 .

FIELD H . Indeterminacy, degree of belief, and excluded middle [J ] . Noûs , 2000 , 34 ( 1 ): 1 - 30 .

ZADEH L A . Fuzzy sets [J ] . Information and Control , 1965 , 8 ( 3 ): 338 - 353 .

PAWLAK Z . Rough sets [J ] . International Journal of Computer & Information Sciences , 1982 , 11 ( 5 ): 341 - 356 .

LEIBNIZ G W . The Monadology: 1714 [M ] . Berlin : Springer , 1989 .

SHANNON C E . A mathematical theory of communicat-ion [J ] . The Bell System Technical Journal , 1948 , 27 ( 3 ): 379 - 423 .

KAPUR J N , SAHOO P K , WONG A K C . A new method for gray-level picture thresholding using the entropy of the histogram [J ] . Computer Vision, Graphics, and Image Processing , 1985 , 29 ( 3 ): 273 - 285 .

邹耀斌 , 邓世成 , 孟祥丹 , 等 . 多向加权Tsallis熵最大化导向的自动阈值分割方法 [J ] . 电子学报 , 2024 , 52 ( 1 ): 129 - 143 .

ZOU Y B , DENG S C , MENG X D , et al . Automatic thresholding segmentation method guided by maximizing multi-directional weighted tsallis entropy [J ] . Acta Electronica Sinica , 2024 , 52 ( 1 ): 129 - 143 . (in Chinese)

ROSENBLATT F . The perceptron: A probabilistic model for information storage and organization in the brain [J ] . Psychological Review , 1958 , 65 ( 6 ): 386 - 408 .

PARE S , KUMAR A , SINGH G K , et al . Image segmentation using multilevel thresholding: A research review [J ] . Iranian Journal of Science and Technology, Transactions of Electrical Engineering , 2020 , 44 ( 1 ): 1 - 29 .

OTSU N . A threshold selection method from gray-level histograms [J ] . IEEE Transactions on Systems, Man, and Cybernetics , 1979 , 9 ( 1 ): 62 - 66 .

NIBLACK W . An Introduction to Digital Image Processing [M ] . Englewood Cliffs : Prentice-Hall International , 1986 .

BERNSE J . Dynamic thresholding of grey-level images [C ] // Proceedings of the 8th International Conference on Pattern Recognition . Paris : AFCET , 1986 : 1251 - 1255 .

QUINLAN J R . Induction of decision trees [J ] . Machine Learning , 1986 , 1 ( 1 ): 81 - 106 .

QUINLAN J R . C4 . 5 : Programs for Machine Learning [M ] . San Mateo : Morgan Kaufmann Publishers , 1993.

BREIMAN L , FRIEDMAN J , STONE C J , et al . Classification and Regression Trees [M ] . New York : Chapman and Hall/CRC , 1984 .

POLANSKY M G , HERRMANN C , HUR J , et al . Boundary attention: Learning to find faint boundaries at any resoluti-on [EB/OL ] . ( 2024-05-14 )[ 2025-06-30 ] . https://arxiv.org/html/2401.00935v1 https://arxiv.org/html/2401.00935v1 .

ZHONG Z H , CAO M D , JI X , et al . Blur interpolation transformer for real-world motion from blur [C ] // 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2023 : 5713 - 5723 .

XU Y , SHANG L , YE J X , et al . Dash: Semi-supervised learning with dynamic thresholding [C ] // Proceedings of the 38th International Conference on Machine Learning . New York : ACM , 2021 , 139 : 11525 - 11536 .

HUANG S Y , MA J W , HAN G X , et al . Task-adaptive negative envision for few-shot open-set recognition [C ] // 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2022 : 7161 - 7170 .

LEI Q , ZHONG J , WANG C , et al . Adaptive thresholding based on multi-task learning for refining binary medical image segmentation [C ] // 2023 IEEE International Conference on Bioinformatics and Biomedicine . Piscataway : IEEE , 2024 : 3059 - 3066 .

ZHOU C X , HUANG Y P , PU M Y , et al . The treasure beneath multiple annotations: An uncertainty-aware edge detector [C ] // 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2023 : 15507 - 15517 .

WANG Y D , CHEN H , HENG Q , et al . FreeMatch: Self-adaptive thresholding for semi-supervised learning [EB/OL ] . ( 2023-01-31 )[ 2025-07-15 ] . https://arXiv.org/abs/2205. 07246 https://arXiv.org/abs/2205.07246 .

孔告化 , 石爱菊 . 概率论与数理统计 [M ] . 北京 : 人民邮电出版社 , 2022 .

KONG G H , SHI A J . Probability and Statistics [M ] . Beijing : Posts & Telecom Press , 2022 . (in Chinese)

HE S F , WANG Y M , PAN X H , et al . A novel behavioral three-way decision model with application to the treatment of mild symptoms of COVID-19 [J ] . Applied Soft Computing , 2022 , 124 : 109055 .

ABDAR M , SAMAMI M , DEHGHANI MAHMOODABAD S , et al . Uncertainty quantification in skin cancer classification using three-way decision-based Bayesian deep learn-ing [J ] . Computers in Biology and Medicine , 2021 , 135 : 104418 .

JIANG C M , DUAN Y . A novel three-way deep learning approach for multigranularity fuzzy association analysis of time series data [J ] . IEEE Transactions on Fuzzy Systems , 2024 , 32 ( 9 ): 4835 - 4845 .

LI D , XIONG W M , LUO T , et al . 3WAUS: A novel three-way adaptive uncertainty-suppressing model for facial expression recognition [J ] . Information Sciences , 2024 , 677 : 120962 .

PAN X H , WANG Y M , HE S F , et al . An interval type-2 fuzzy ORESTE method for waste-to-energy plant site selection: A case study in China [J ] . Applied Soft Computing , 2023 , 136 : 110092 .

MICHAEL LINCOFF A , BROWN-FRANDSEN K , COL-HOUN H M , et al . Semaglutide and cardiovascular outcomes in obesity without diabetes [J ] . The New England Journal of Medicine , 2023 , 389 ( 24 ): 2221 - 2232 .

WANG X H , WANG B , LI T T , et al . Multi-criteria fuzzy portfolio selection based on three-way decisions and cumulative prospect theory [J ] . Applied Soft Computing , 2023 , 134 : 110033 .

COX D R . The regression analysis of binary sequences [J ] . Journal of the Royal Statistical Society Series B: Statistical Methodology , 1958 , 20 ( 2 ): 215 - 242 .

李航 . 统计学习方法 [M ] . 北京 : 清华大学出版社 , 2012 .

LI H . Statistical Learning Method [M ] . Beijing : Tsinghua University Press , 2012 . (in Chinese)

CORTES C , VAPNIK V . Support-vector networks [J ] . Machine Learning , 1995 , 20 ( 3 ): 273 - 297 .

WU Y C , LI X Q , DAI S M , et al . Hierarchical semantic contrast for weakly supervised semantic segmentation [C ] // Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence . New York : ACM , 2023 : 1542 - 1550 .

KANG W T , LIU G W , SHAH M , et al . SegVG: Transferring object bounding box to segmentation for visual ground-ing [M ] // Computer Vision–ECCV 2024 . Cham : Springer , 2025 : 57 - 75 .

LIN Y , ZHANG D , FANG X , et al . Rethinking boundary detection in deep learning models for medical image segmentation [M ] // Information Processing in Medical Imaging . Cham : Springer , 2023 : 730 - 742 .

PU M Y , HUANG Y P , GUAN Q J , et al . RINDNet++: Edge detection for discontinuity in reflectance, illumination, normal, and depth [J ] . InternationalJournalof Computer Vision , 2025 , 133 ( 10 ): 7486 - 7510 .

PU M Y , HUANG Y P , LIU Y M , et al . EDTER: Edge detection with transformer [C ] // 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2022 : 1392 - 1402 .

CHEN G P , LI L , ZHANG J X , et al . Rethinking the unpretentious U-Net for medical ultrasound image segmentat-ion [J ] . Pattern Recognition , 2023 , 142 : 109728 .

ZHANG S X , YANG C , ZHU X B , et al . Arbitrary shape text detection via boundary transformer [J ] . IEEE Transactions on Multimedia , 2024 , 26 : 1747 - 1760 .

YAO Y Y . Decision-theoretic rough set models [C ] // Rough Sets and Knowledge Technology . Berlin : Springer , 2007 : 1 - 12 .

PENG J , CHEN Y . Density-based clustering with boundary samples verification [J ] . Applied Soft Computing , 2024 , 159 : 111685 .

CHU X L , SUN B Z , ZOU H , et al . Multi-modal incomplete label information three-way bidirectional decision-making: Applications of disease assessment [J ] . Information Fusion , 2025 , 113 : 102615 .

LEI M Q , WU H C , LV X H , et al . ConDSeg: A general medical image segmentation framework via contrast-driven feature enhancement [J ] . Proceedings of the AAAI Conference on Artificial Intelligence , 2025 , 39 ( 5 ): 4571 - 4579 .

WANG Y H , LIU S K , LI L , et al . SwinShadow: Shifted window for ambiguous adjacent shadow detection [J ] . ACM Transactions on Multimedia Computing, Communications, and Applications , 2024 , 20 ( 11 ): 1 - 20 .

LIN Y N , WANG Y Y , LYU G Y , et al . Enhance multi-view classification through multi-scale alignment and expanded boundary [C ] // The Thirteenth International Conference on Learning Representations . Washington DC : ICLR , 2025 : 3591 .

LIN Y N , CAI H H , HANG J Y , et al . Mitigating local cohesion and global sparseness in graph contrastive learning with fuzzy boundaries [C ] // Proceedings of the 42nd International Conference on Machine Learning . New York : ACM , 2025 : 37745 - 37761 .

MIN F , LIU F L , WEN L Y , et al . Tri-partition cost-sensitive active learning through kNN [J ] . Soft Computing , 2019 , 23 ( 5 ): 1557 - 1572 .

MA H Y , LIAO Q M , ZHANG J C , et al . An α-matte boundary defocus model-based cascaded network for multi-focus image fusion [J ] . IEEE Transactions on Image Processing , 2020 , 29 : 8668 - 8679 .

WU M Y , DAI H Z , YAO K X , et al . BG-triangle: Bézier Gaussian triangle for 3D vectorization and rendering [C ] // 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2025 : 16197 - 16207 .

LIU H Z , WANG Y L , CHU H Z , et al . Enhancing pseudo label quality for pedestrian and cyclist in weakly supervised 3D object detection [J ] . Neurocomputing , 2024 , 584 : 127531 .

MA D , FANG H Y , WANG N N , et al . A low-cost 3D reconstruction and measurement system based on structure-from-motion (SFM) and multi-view stereo (MVS) for sewer pipelines [J ] . Tunnelling and Underground Space Technology , 2023 , 141 : 105345 .

LI Z W , WU Y , XU T C , et al . A fast 3D lung image reconstruction method based on CT pixel matrices learning with electrical impedance tomography [J ] . Measurement , 2025 , 251 : 117176 .

LI L , ZHOU Z Y , WU S P , et al . Multi-scale edge-guided learning for 3D reconstruction [J ] . ACM Transactions on Multimedia Computing, Communications, and Applications , 2023 , 19 ( 3 ): 1 - 24 .

HUO R T , CHEN J K , ZHANG Y , et al . 3D skeleton aware driver behavior recognition framework for autonomous driving system [J ] . Neurocomputing , 2025 , 613 : 128743 .

CHEN S C , XIE F , CHEN S H , et al . TdDS-UNet: Top-down deeply supervised U-Net for the delineation of 3D colorectal cancer [J ] . Physics in Medicine & Biology , 2024 , 69 ( 5 ): 055018 .

NAM S J , KEHTARNAVAZ N . Flash shadow detection and removal in stereo photography [J ] . IEEE Transactions on Consumer Electronics , 2012 , 58 ( 2 ): 205 - 211 .

SIKANDER G , ANWAR S , HUSNAIN G , et al . An adaptive snake based shadow segmentation for robust driver fatigue detection: A 3D facial feature based photometric stereo perspective [J ] . IEEE Access , 2023 , 11 : 99178 - 99188 .

LI Z X , JI S , FAN D Z , et al . Reconstruction of 3D information of buildings from single-view images based on shadow information [J ] . ISPRS International Journal of Geo-Information , 2024 , 13 ( 3 ): 62 .

YAN H , LIN F , LI J , et al . Shadow based non-line-of-sight pedestrian rushing detection for automated driving [J ] . IEEE Transactions on Mobile Computing , 2024 , 23 ( 12 ): 14754 - 14767 .

YAO Y Y . Three-way decision and granular computing [J ] . International Journal of Approximate Reasoning , 2018 , 103 : 107 - 123 .

DENG X F , YAO Y Y . Decision-theoretic three-way approximations of fuzzy sets [J ] . Information Sciences , 2014 , 279 : 702 - 715 .

YAO Y Y , WANG S , DENG X F . Constructing shadowed sets and three-way approximations of fuzzy sets [J ] . Information Sciences , 2017 , 412/413 : 132 - 153 .

YAO Y Y . Interval-set algebra for qualitative knowledge representation [C ] // Proceedings of ICCI'93: 5th International Conference on Computing and Information . Piscataway : IEEE , 2002 : 370 - 374 .

YAO Y Y . An outline of a theory of three-way decisions [C ] // Rough Sets and Current Trends in Computing . Berlin : Springer , 2012 : 1 - 17 .

YAO Y Y . The geometry of three-way decision [J ] . Applied Intelligence , 2021 , 51 ( 9 ): 6298 - 6325 .

YAO Y Y . The Dao of three-way decision and three-world thinking [J ] . International Journal of Approximate Reasoning , 2023 , 162 : 109032 .

WANG G Y . DGCC: Data-driven granular cognitive computing [J ] . Granular Computing , 2017 , 2 ( 4 ): 343 - 355 .

王国胤 , 傅顺 , 杨洁 , 等 . 基于多粒度认知的智能计算研究 [J ] . 计算机学报 , 2022 , 45 ( 6 ): 1161 - 1175 .

WANG G Y , FU S , YANG J , et al . A review of research on multi-granularity cognition based intelligent computing [J ] . Chinese Journal of Computers , 2022 , 45 ( 6 ): 1161 - 1175 . (in Chinese)

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

模糊知识测度下图像脉冲噪声去除方法

旁观者视角下粒的多层次描述

基于粗糙集的属性约简算法综述

被动传感器网基于模糊综合贴近度的航迹起始

镓铝砷双异质结红光二极管中红外辐射起因的研究