检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:刘晓倩 张英俊[1,2,3] 秦家虎 李卓凡[1,2] 梁伟玲 李宗溪 LIU Xiao-Qian;ZHANG Ying-Jun;QIN Jia-Hu;LI Zhuo-Fan;LIANG Wei-Ling;LI Zong-Xi(School of Computer Science and Technology,Beijing Jiaotong University,Beijing 100044;Beijing Key Laboratory of Traffic Data Analysis and Mining,Beijing 100044;Frontiers Science Center for Smart High-Speed Railway System,Beijing 100044;Department of Automation,University of Science and Technology of China,Hefei 230027)
机构地区:[1]北京交通大学计算机科学与技术学院,北京100044 [2]交通数据分析与挖掘北京市重点实验室,北京100044 [3]智慧高铁系统前沿科学中心,北京100044 [4]中国科学技术大学自动化系,合肥230027
出 处:《自动化学报》2024年第3期450-474,共25页Acta Automatica Sinica
基 金:中央高校基本科研业务费专项资金(2022YJS121);国家自然科学基金(51827813);国家自然科学基金委员会-中国国家铁路集团有限公司铁路基础研究联合基金(U2268206);科技部重点研发计划项目(2022YFB2603302)资助。
摘 要:模糊认知图(Fuzzy cognitive map, FCM)是建立在认知图和模糊集理论上的一类代表性的软计算理论,兼具神经网络和模糊决策两者的优势,已成功地应用于复杂系统建模和时间序列分析等众多领域.学习权重矩阵是基于模糊认知图建模的首要任务,是模糊认知图研究领域的焦点.针对这一核心问题,首先,全面综述模糊认知图的基本理论框架,系统地总结近年来模糊认知图的拓展模型.其次,归纳、总结和分析模糊认知图学习算法的最新研究进展,对学习算法进行重新定义和划分,深度阐述各类学习算法的时间复杂度和优缺点.然后,对比分析各类学习算法在不同科学领域的应用特点以及现有的模糊认知图建模软件工具.最后,讨论学习算法未来潜在的研究方向和发展趋势.Fuzzy cognitive maps(FCM)are a representative soft computing theory based on cognitive maps and fuzzy set theory.They combine the advantages of both neural networks and fuzzy decision-making and have been successfully applied in many fields,including complex system modeling and time series analysis.Learning the weight matrix is the primary task of modeling based on fuzzy cognitive maps and is the focus of research in this field.To address this core issue,we first comprehensively review the basic theoretical framework of fuzzy cognitive maps and systematically summarize the extended models developed in recent years.Next,the most recent advancements in fuzzy cognitive map learning algorithms are reviewed,analyzed,and summarized.The algorithms are redefined and categorized,with a detailed exploration of their time complexity,strengths,and weaknesses.Additionally,the application properties of various learning algorithms in various scientific domains are also compared and analyzed in this research,along with the software tools that are now available for creating fuzzy cognitive maps.Finally,potential research directions and development trends for learning algorithms are discussed.
关 键 词:模糊认知图 学习范式 因果推理 软计算 复杂系统建模
分 类 号:TP18[自动化与计算机技术—控制理论与控制工程]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.15