面向可解释性人工智能与大数据的模糊系统发展展望

doi:10.11959/j.issn.2096-6652.201937

智能科学与技术学报 ›› 2019, Vol. 1 ›› Issue (4): 327-334.doi: 10.11959/j.issn.2096-6652.201937

面向可解释性人工智能与大数据的模糊系统发展展望

陈德旺^1,²(),蔡际杰^1,²,黄允浒^1,²

¹ 福州大学数学与计算机科学学院，福建福州 350108
² 福州大学智慧地铁福建省高校重点实验室，福建福州 350108

修回日期:2019-11-28 出版日期:2019-12-20 发布日期:2020-02-29
作者简介:陈德旺（1976- ），男，博士，福州大学数学与计算机科学学院教授、博士生导师，福建省“闽江学者特聘教授”，美国加州大学伯克利分校访问学者，中国自动化协会混合智能专委会副主任，中国自动化协会粒计算专委会秘书长，IEEE 高级会员，IEEE Transaction on ITS编委，主要研究方向为人工智能、大数据、最优化、智慧地铁和智慧新能源等|蔡际杰（1997- ），男，福州大学数学与计算机科学学院硕士生，主要研究方向为智能计算和大数据|黄允浒（1990- ），男，福州大学数学与计算机科学学院博士生，主要研究方向为智能计算、大数据与最优化
基金资助:
国家自然科学基金资助项目(61976055);智慧地铁福建省高校重点实验室建设基金资助项目(53001703);智慧地铁福建省高校重点实验室建设基金资助项目(50013203)

Development prospect of fuzzy system oriented to interpretable artificial intelligence and big data

Dewang CHEN^1,²(),Jijie CAI^1,²,Yunhu HUANG^1,²

¹ College of Mathematics and Computer Science,Fuzhou University,Fuzhou 350108,China
² Key Laboratory of Intelligent Metro of Universities in Fujian Province,Fuzhou University,Fuzhou 350108,China

Revised:2019-11-28 Online:2019-12-20 Published:2020-02-29
Supported by:
The National Natural Science Foundation of China(61976055);The Construction of Key Laboratory of Intelligent Metro of Universities in Fujian Province(53001703);The Construction of Key Laboratory of Intelligent Metro of Universities in Fujian Province(50013203)

摘要/Abstract

摘要：

模糊系统作为一种万能逼近器具有很强的可解释性，已被广泛应用在各个领域。尽管目前模糊系统的理论研究不够成熟，仍然存在诸如规则太多、优化困难、维度诅咒等问题，难以处理高维大数据。尽管深度神经网络取得了突出进展，能很好处理图像和语音等大数据，但其可解释性不好，难以用于安全相关的重要场合。因此，非常有必要研究一种基于模糊系统的可解释性强的人工智能算法。结合深度神经网络和模糊系统两者的优点，研究深度模糊系统及其算法，将有可能解决高维大数据问题。主要对模糊系统的发展历程与研究进展分别进行详细阐述，并根据其现有的问题指出其未来的发展方向，对进一步的研究问题进行展望。

关键词: 模糊系统, 可解释AI, 高维大数据, 深度模糊系统, 神经模糊系统

Abstract:

As a universal approximator with strong interpretability,fuzzy system has been widely used in various fields.Although the current theoretical research on fuzzy system is not mature enough,there are still many problems such as too many rules,optimization difficulties,dimension curse,which make it difficult to deal with high-dimensional large data.Although deep neural network has made remarkable progress and can process large data such as image and voice very well,its interpretability is not good and it is difficult to be used in important security-related occasions.Therefore,it is necessary to study an interpretable artificial intelligence algorithm based on fuzzy system.Combining the advantages of deep neural network and fuzzy system,it is possible to solve the problem of high dimensional and large data by studying the deep fuzzy system and its algorithm.The development history and research progress of fuzzy system separately was mainly reviews,and its future development direction according to its existing problems was pointed out,and the summary of this article and the prospect for further research about the problems were given.

Key words: fuzzy system, interpretable artificial intelligence, high-dimensional big data, deep fuzzy system, neuro fuzzy system

中图分类号:

TP391.41，TP273

陈德旺,蔡际杰,黄允浒. 面向可解释性人工智能与大数据的模糊系统发展展望[J]. 智能科学与技术学报, 2019, 1(4): 327-334.

Dewang CHEN,Jijie CAI,Yunhu HUANG. Development prospect of fuzzy system oriented to interpretable artificial intelligence and big data[J]. Chinese Journal of Intelligent Science and Technology, 2019, 1(4): 327-334.

图/表 3

表1

图1

图2

参考文献 51

[1]	ZADEH L A . Fuzzy sets[J]. Information and Control, 1965,8(3): 338-353.
[2]	ZADEH L A . The concept of a linguistic variable and its application to approximate reasoning-I[J]. Information Sciences, 1975,8(3): 199-249.
[3]	ZADEH L A . Fuzzy algorithms[J]. Information and Control, 1968,12(2): 94-102.
[4]	BELLMAN R E , ZADEH L A . Decision-making in a fuzzy environment[J]. Management Science, 1970,17(4): B141-B164.
[5]	ZADEH L A . Similarity relations and fuzzy ordering[J]. Information Sciences, 1971,3(2): 177-200.
[6]	DRIANKOV D , HELLENDOORNN H , REINFRANK M . An introduction to fuzzy control \|\| stability of fuzzy control systems[M]. Berlin: Springer-VerlagPress, 1993:316.
[7]	BERKAN R C , TRUBATCH S . Fuzzy system design principles[M]. Wiley-IEEE Press, 1997:514.
[8]	王立新 . 模糊系统:挑战与机遇并存—— 十年研究之感悟[J]. 自动化学报, 2001,27(4): 585-590.
	WANG L X . Fuzzy systems:challenges and chance,my experiences and perspectives[J]. Acta Automatica Sinica, 2001,27(4): 585-590.
[9]	阎岭, 郑洪涛, 蒋静坪 . 基于进化策略生成可解释性模糊系统[J]. 电子学报, 2005,33(1): 70-73.
	YAN L , ZHENG H T , JIANG J P . Generation of interpretable fuzzy system based on evolution strategy[J]. Acta Electronica Sinica, 2005,33(1): 70-73.
[10]	晏勇, 杜继宏, 冯元琨 . 模糊控制[J]. 计算机测量与控制, 1999,7(1): 55-57.
	YAN Y , DU J H , FENG Y K . Fuzzy control[J]. Computer Measure-ment and Control, 1999,7(1): 55-57.
[11]	雷英杰, 路艳丽, 王毅 . 模糊逻辑与智能系统[M]. 西安: 电子科技大学出版社, 2016.
	LEI Y J , LU Y L , WANG Y . Fuzzy logic and intelligent system[M]. Xi’an: University of Electronic Science and Technology of China PressPress, 2016.
[12]	WANG L X , MENDEL J M . Fuzzy basis functions,universal approximation,and orthogonal least-squares learning[J]. IEEE Transactions on Neural Networks, 1992,3(5): 807-814.
[13]	WANG L X , MENDEL J M . Generating fuzzy rules by learning from examples[J]. IEEE Transactions on Systems,Man and Cybernetics, 1992,22(6): 1414-1427.
[14]	WANG L X . Stable adaptive fuzzy control of nonlinear systems[J]. IEEE Transactions on Fuzzy Systems, 1993(12): 146-155.
[15]	MOUZOURIS G C , MENDEL J M . Nonsingleton fuzzy logic systems:theory and application[J]. IEEE Transactions on Fuzzy Systems, 1997,5(1): 56-71.
[16]	KARNIK N N , MENDEL J M . Operations on type-2 fuzzy sets[J]. Fuzzy Sets and Systems, 2001,122(2): 327-348.
[17]	LIANG Q L , MENDEL J M . Modeling MPEG VBR video traffic using type-2 fuzzy logic systems[C]// Granular Computing:An Emerging Paradigm,January 1,2001,Berlin,Germany. Berlin:Springer-Verlag, 2001: 367-383.
[18]	WU H W , MENDEL J M . Uncertainty bounds and their use in the design of interval type-2 fuzzy logic systems[J]. IEEE Transactions on Fuzzy Systems, 2002,10(5): 622-639.
[19]	LIU F L . An efficient centroid type-reduction strategy for general type-2 fuzzy logic system[J]. Information Sciences, 2008,178(9): 2224-2236.
[20]	WU D R , MENDEL J M . Enhanced Karnik-Mendel algorithms[J]. IEEE Transactions on Fuzzy Systems, 2009,17(4): 923-934.
[21]	FERNANDEZ , ALBERTO CARMONA ,et al. A view on fuzzy systems for big data:progress and opportunities[J]. International Journal of Computational Intelligence Systems, 2016,9(S1): 69-80.
[22]	FERRANTI A , MARCELLONI F , SEGATORI A . A multi-objective evolutionary fuzzy system for big data[C]// 2016 IEEE International Conference on Fuzzy Systems,July 24-29,2016,Vancouver,Canada. Piscataway:IEEE Press, 2016: 1562-1569.
[23]	MARQUEZ A A , MARQUEZ F A , PEREFRIN A . A scalable evolutionary linguistic fuzzy system with adaptive defuzzification in big data[C]// 2017 IEEE International Conference on Fuzzy Systems,July 9-12,2017,Naples,Italy. Piscataway:IEEE Press, 2017: 1-6.
[24]	王飞跃 . 关于模糊系统研究的认识和评价以及其他[J]. 自动化学报, 2002,28(4): 663-669.
	WANG F Y . A note on research in fuzzy systems[J]. Acta Automatica Sinica, 2002,28(4): 663-669.
[25]	CHEN S M . Erratum to:fuzzy system reliability analysis using fuzzy number arithmetic operations[J]. Fuzzy Sets and Systems, 1994,64(1): 31-38.
[26]	姚敏, 黄燕君 . 模糊决策方法研究[J]. 系统工程理论与实践, 1999(11): 61-64.
	YAO M , HUANG Y J . Research on methodology of fuzzy decision making[J]. Systems Engineering-Theory ＆ Practice, 1999(11): 61-64.
[27]	王立新 . 模糊系统与模糊控制教程[M]. 北京: 清华大学出版社, 2003.
	WANG L X . Fuzzy system and fuzzy control[M]. Beijing: Tsinghua University PressPress, 2003.
[28]	邹开其, 徐扬 . 模糊系统与专家系统[M]. 成都: 西南交通大学出版社, 1989.
	ZOU K Q , XU Y . Fuzzy system and expert system[M]. Chengdu: Southwest Jiaotong University PressPress, 1989.
[29]	崔晨, 邓赵红, 王士同 . 面向单调分类的简洁单调TSK模糊系统[J]. 南京大学学报(自然科学版), 2018,54(1): 124-133.
	CUI C , DENG Z H , WANG S T . Concise monotonic TSK fuzzy sys-tem for monotonic classification[J]. Journal of Nanjing University (Natural Sciences), 2018,54(1): 124-133.
[30]	薛梅 . 基于新模糊系统与T-S模糊系统的比较与研究[J]. 计算机工程与应用, 2009,45(22): 44-46.
	XUE M . Comparison of new fuzzy systems and T-S and Mamdani fuzzy system[J]. Computer Engineering and Applications, 2009,45(22): 44-46.
[31]	WANG L X . The WM method completed:a flexible fuzzy system approach to data mining[J]. IEEE Transactions on Fuzzy Systems, 2003,11(6): 768-782.
[32]	JANG J S R . ANFIS:adaptive-network-based fuzzy inference system[J]. IEEE Transactions on Systems,Man and Cybernetics, 1993,23(3): 665-685.
[33]	KOSKO B . Fuzzy systems as universal approximators[J]. IEEE Transactions on Computers, 1994,43(11): 1329-1333.
[34]	NILESH N K , MENDEL J M , LIANG Q L . Type-2 fuzzy logic systems[J]. IEEE Transactions on Fuzzy Systems, 1999,7(6): 643-658.
[35]	丁永生, 应浩, 邵世煌 . 模糊系统逼近理论:现状与展望[J]. 信息与控制, 2000,29(2): 157-163.
	DING Y S , YING H , SHAO S H . Approximation theory of fuzzy sys-tems:current state and future directions[J]. Information and Control, 2000,29(2): 157-163.
[36]	陈龙, 王飞跃 . 一种新的神经模糊系统及其学习算法[J]. 模式识别与人工智能, 2003,16(2): 178-184.
	CHEN L , WANG F Y . A new neuro-fuzzy system and its learning al-gorithm[J]. Pattern Recognition and Artificial Intelligence, 2003,16(2): 178-184.
[37]	武妍, 施鸿宝 . 神经网络、模糊系统和遗传算法相结合的研究概述[C]// 中国智能自动化学术会议,5月1日,1998年,上海，中国. [出版地不详]:[出版者不详], 1998: 84-90.
	WU Y , SHI H B . Overview of research on the combination of neural networks,fuzzy systems and genetic algorithms[C]// Chinese Aca-demic Conference on Intelligent Automation,May 1,1998,Shanghai,China.[S.l.:s.n]. 1998: 84-90.
[38]	张凯, 钱锋, 刘漫丹 . 模糊神经网络技术综述[J]. 信息与控制, 2003,32(5): 431-435.
	ZHANG K , QIAN F , LIU M D . Overview of fuzzy neural network technology[J]. Information and Control, 2003,32(5): 431-435.
[39]	王素芬 . 模糊系统与神经网络结合的现状[J]. 网络与信息, 2007(5):71.
	WANG S F . Status of combination of fuzzy system and neural net-work[J]. Network and Information, 2007(5):71.
[40]	SHOKROLLAHI A , MAVBODI M N . An energy-efficient clustering algorithm using fuzzy c-means and genetic fuzzy stem for wireless sensor network[J]. Journal of Circuits,Systems and Computers, 2017,26(1): 393-422.
[41]	MAHMOUDI A , SHAVANDI H , VAKILI M R . Modeling dual-channel supply chain based on fuzzy system and genetic algorithm[J]. International Journal of Uncertainty,Fuzziness and Knowledge-Based Systems, 2017,25(4): 573-598.
[42]	ANTHONY Z . A critique of pure learning and what artificial neural networks can learn from animal brains[J]. Nature Communications, 2019:3770.
[43]	JIN S Z , PENG J , XIE D . Towards MapReduce approach with dynamic fuzzy inference/interpolation for big data classification problems[C]// 2017 IEEE 16th International Conference on Cognitive In formatics ＆ Cognitive Computing,July 26-28,2007,Oxford,UK. Piscataway:IEEE Press, 2017: 407-413.
[44]	WU J , WANG C Z . Privacy preserving for big data based on fuzzy set[C]// The 4th International Conference on Cloud Computing and Security,June 8-10,2018,Haikou,China.[S.l.:s.n]. 2018: 651-659.
[45]	WANG Y Y . Type-2 fuzzy event parallel computing system:overcoming computer int index limitation in big data[J]. Applied Soft Computing, 2016,38: 1076-1087.
[46]	STATHOPOULOS A , DIMITRIOU L , TSEKERIS T . Fuzzy modeling approach for combined forecasting of urban traffic flow[J]. Computer-Aided Civil and Infrastructure Engineering, 2008,23(7): 521-535.
[47]	NAIR B B , DHARINI N M , MOHANDS V P . A stock market trend prediction system using a hybrid decision tree-neuro-fuzzy system[C]// International Conference on Advances in Recent Technologies in Communication ＆ Computing,October 16-17,2010,Kottayam,India. Piscataway:IEEE Press, 2010: 381-385.
[48]	SILVIA A , ROBERTSON R , WARFIELD S K ,et al. A fuzzy system for helping medical diagnosis of malformations of cortical development[J]. Journal of Biomedical Informatics, 2007,40(3): 221-235.
[49]	WANG H , XU Z S , PEDRYCZ W . An overview on the roles of fuzzy set techniques in big data processing:trends,challenges and opportunities[J]. Knowledge-Based Systems, 2016,S0950705116304452.
[50]	WANG L X , MENDEL J M . Back-propagation fuzzy system as nonlinear dynamic system identifiers[C]// IEEE International Conference on Fuzzy Systems,March 8-12,San Diego,USA.[S.l.:s.n]. 1992: 1409-1418.
[51]	LIU P Y , LI X H . Fuzzy neural network theory and application[M]. Singapore: World Scientific Publishing CompanyPress, 2004.

NN	FS
第一次兴起代表人物	第一次兴起代表人物
McCulloch、Pitts：1943年提出抽象的神经元模型MP	Zadeh（开创人物）：模糊理论之父，为模糊领域作出许多贡献；1965年提出模糊子集概念
Hebb：1949年提出突触学习的Hebb定律
Rosenblat：1958年提出可以模拟人类感知能力的感知器	Mandami：1974年开创模糊控制
	Sugeno：1980年提出地铁模糊控制
第二次兴起代表人物	第二次兴起代表人物
Hopfield：1982年提出新型神经网络Hopield，该网络结合存储系统和二元系统，提供了模拟人类记忆的模型	Lee：1990年提出了控制模糊逻辑控制器的理论与设计方法
Rumelhart：1986 年和Hinton共同提出反向传播算法	Wang：1992年与Mendel提出WM方法，实现从数据中产生模糊规则；1993 年提出能确保稳定的自适应模糊控制器的方法；1998年发表多层模糊系统的万能逼近定理；1999 年发表多层模糊系统的BP算法
Vapnik：1995年提出支持向量机（SVM）
	Jang：1993年提出ANFIS，使FS拥有了自学习能力
第三次兴起代表人物	DFS（第三次兴起可能会出现的主要技术）
Geofrey Hinton：2005年在Science发表论文提出用神经网络进行维数约简；2012年和他的学生提出AlexNet；其后提出自编码器等算法，使得神经网络可以有效处理高维大数据，获得ImageNet冠军	DCFS：深度卷积模糊系统
	DCANFIS：深度卷积自适应神经模糊推理系统
LeCun：2016年提出基于能量的生成对抗网络模型	RFS：循环模糊系统
?oshua Bengio：2009年提出学习人工智能的深层架构
以上3人2015年在Nature上共同发表深度学习综述，2018共同获得图灵奖，使得深度神经网络一鸣惊人

面向可解释性人工智能与大数据的模糊系统发展展望

Development prospect of fuzzy system oriented to interpretable artificial intelligence and big data

在线阅读

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 3

参考文献 51

相关文章 2

Metrics

推荐阅读 0

[1]	张俊, 许沛东, 陈思远, 高天露, 戴宇欣, 张科, 赵杭, 高杰迈, 白昱阳, 李金星, 张浩然, 李湘, 陈玖香. 物理-数据-知识混合驱动的人机混合增强智能系统管控方法[J]. 智能科学与技术学报, 2022, 4(4): 571-583.
[2]	杜宏庆,陈德旺,黄允浒,朱凤华,李灵犀. 基于改进遗传算法与支持度的模糊系统优化建模方法[J]. 智能科学与技术学报, 2020, 2(2): 179-185.