2.845

2023影响因子

(CJCR)

  • 中文核心
  • EI
  • 中国科技核心
  • Scopus
  • CSCD
  • 英国科学文摘

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

深度神经模糊系统算法及其回归应用

赵文迪 陈德旺 卓永强 黄允浒

赵文迪, 陈德旺, 卓永强, 黄允浒. 深度神经模糊系统算法及其回归应用. 自动化学报, 2020, 46(11): 2350−2358 doi: 10.16383/j.aas.c200100
引用本文: 赵文迪, 陈德旺, 卓永强, 黄允浒. 深度神经模糊系统算法及其回归应用. 自动化学报, 2020, 46(11): 2350−2358 doi: 10.16383/j.aas.c200100
Zhao Wen-Di, Chen De-Wang, Zhuo Yong-Qiang, Huang Yun-Hu. Deep neural fuzzy system algorithm and its regression application. Acta Automatica Sinica, 2020, 46(11): 2350−2358 doi: 10.16383/j.aas.c200100
Citation: Zhao Wen-Di, Chen De-Wang, Zhuo Yong-Qiang, Huang Yun-Hu. Deep neural fuzzy system algorithm and its regression application. Acta Automatica Sinica, 2020, 46(11): 2350−2358 doi: 10.16383/j.aas.c200100

深度神经模糊系统算法及其回归应用

doi: 10.16383/j.aas.c200100
基金项目: 国家自然科学基金面上项目(61976055), 智慧地铁福建省高校重点实验室(53001703, 50013203)资助
详细信息
    作者简介:

    赵文迪:福州大学数学与计算机科学学院, 智慧地铁福建省高校重点实验室科研助理. 主要研究方向为深度学习, 模糊系统.E-mail: wdzhao@aliyun.com

    陈德旺:福建省“闽江学者”特聘教授, 福州大学数学与计算机学院教授. 主要研究方向为深度学习, 模糊系统和智能交通系统. 本文通信作者.E-mail: dwchen@fzu.edu.cn

    卓永强:广州海航学院海运学院教授. 主要研究方向为船舶运动智能控制, 海上交通系统工程和模糊系统.E-mail: zhuoyq@aliyun.com

    黄允浒:福州大学数学与计算机科学学院博士研究生. 主要研究方向为机器学习, 模糊系统与智能交通系统.E-mail: N190310001@fzu.edu.cn

Deep Neural Fuzzy System Algorithm and Its Regression Application

Funds: Supported by General Program of National Natural Science Foundation of China (61976055), Key laboratory of Intelligent Metro of Universities in Fujian Province (53001703, 50013203)
  • 摘要: 深度神经网络是人工智能的热点, 可以很好处理高维大数据, 却有可解释性差的不足. 通过IF-THEN规则构建的模糊系统, 具有可解释性强的优点, 但在处理高维大数据时会遇到“维数灾难”问题. 本文提出一种基于ANFIS (Adaptive network based fuzzy inference system)的深度神经模糊系统(Deep neural fuzzy system, DNFS)及两种基于分块和分层的启发式实现算法: DNFS1和DNFS2. 通过四个面向回归应用的数据集的测试, 我们发现: 1)采用分块、分层学习的DNFS在准确度与可解释性上优于BP、RBF、GRNN等传统浅层神经网络算法, 也优于LSTM和DBN等深度神经网络算法; 2)在低维问题中, DNFS1具有一定优势; 3)在面对高维问题时, DNFS2表现更为突出. 本文的研究结果表明DNFS是一种新型深度学习方法, 不仅可解释性好, 而且能有效解决处理高维数据时模糊规则数目爆炸的问题, 具有很好的发展前景.
  • 图  1  DNFS1基本结构

    Fig.  1  Basic structure of DNFS1

    图  2  DNFS2基本结构

    Fig.  2  Basic structure of DNFS2

    图  3  DNFS算法流程

    Fig.  3  DNFS algorithm flow

    图  4  SMW数据集深度结构

    Fig.  4  The deep structure of SMW data set

    图  5  SMW测试集预测效果

    Fig.  5  Prediction effect of SMW test set

    图  6  ONP数据集深度结构

    Fig.  6  The deep structure of ONP data set

    图  7  ONP测试集预测效果

    Fig.  7  Prediction effect of ONP test set

    图  8  SUP数据集深度结构

    Fig.  8  The deep structure of SUP data set

    图  9  SUP测试集预测效果

    Fig.  9  Prediction effect of SUP test set

    图  10  BF测试集预测效果

    Fig.  10  Prediction effect of BF test set

    表  1  实验数据集

    Table  1  Experimental data set

    项目编号数据集输入维度输出维度样本数DNFS1总层数DNFS2总层数
    1Smartwatch_sens (SMW)121120001530
    2Online News Popularity (ONP)5912000025145
    3Superconductivty (SUP)8111000030200
    4BlogFeedback (BF)27111500040675
    下载: 导出CSV

    表  2  SMW测试集评价指标

    Table  2  Evaluation index of SMW test set

    BPRBFGRNNLSTMDBNANFISDNFS1DNFS2
    STD0.0388690.0385100.0384410.0393850.0385960.0393980.037643 0.040971
    RMSE0.0388650.0385060.0384370.0402190.0385920.0393970.037640 0.040970
    MAE0.0177890.0183550.0170810.0209280.0170880.0179650.016639 0.016834
    SMAPE3.5849 %3.7368 %3.4864 %4.2653 %3.4872 %3.6510 %3.3553 %3.5535 %
    Score161627721113214
    下载: 导出CSV

    表  3  ONP测试集评价指标

    Table  3  Evaluation index of ONP test set

    BPRBFGRNNLSTMDBNANFISDNFS1DNFS2
    STD0.0401480.0175650.0169410.0163210.0162170.2345850.0250120.016195
    RMSE0.0401730.0175670.0169410.0188270.0162160.2639660.0250110.016195
    MAE0.0058240.0053470.0040600.0116390.0041530.1236090.0044000.003975
    SMAPE83.1325 %110.4412 %77.8989 %136.6059 %88.0204 %106.8444 %78.3964 %79.4094 %
    Score121526132461830
    下载: 导出CSV

    表  4  SUP测试集评价指标

    Table  4  Evaluation index of SUP test set

    BPRBFGRNNLSTMDBNANFISDNFS1DNFS2
    STD0.123850.130380.174930.159970.210740.168660.134150.12293
    RMSE0.123840.130380.175270.160040.210760.169720.134180.12293
    MAE0.087860.100380.149560.129580.182450.126570.101650.08735
    SMAPE30.1760 %32.4668 %43.0296 %38.5752 %51.2832 %37.7120 %31.2728 %28.7900 %
    Score28238144142132
    下载: 导出CSV

    表  5  BF测试集评价指标

    Table  5  Evaluation index of BF test set

    BPRBFGRNNLSTMDBNANFISDNFS1DNFS2
    STD0.109000.042170.043220.033550.044570.096830.044650.03155
    RMSE0.109730.042590.043240.033980.044570.339220.044660.03156
    MAE0.023040.011120.011200.014090.016070.326300.010280.00859
    SMAPE54.675 %76.842 %81.804 %96.684 %102.462 %142.341 %64.263 %54.162 %
    Score122319211351932
    下载: 导出CSV
  • [1] Mcclloch W S, Pitts W. A logical calculus of the ideas immanent in nervous activity. Bulletin of Mathematical Biology, 1943, 10(5): 115−133
    [2] Rosenblatt, F. The perceptron: A probabilistic model for information storage and organization in the brain. Psychological Review, 1958, 65: 386−408 doi: 10.1037/h0042519
    [3] Minsky M L, Papert S A. Perceptrons. American Journal of Psychology, 1969, 84(3): 449−452
    [4] Hopfield J J. Neural networks and physical systems with emergent collective computational abilities. Proceedings of the National Academy of Sciences of the United States of America, 1982, 79(8): 2554−2558 doi: 10.1073/pnas.79.8.2554
    [5] Lv Y S, Chen Y Y, Zhang X Q, Duan Y J, Li N Q. Social media based transportation research: The state of the work and the networking. IEEE/CAA Journal of Automatica Sinica, 2017, 4(1): 19−26 doi: 10.1109/JAS.2017.7510316
    [6] Rumelhart, David E, Hinton, Geoffrey E, Williams, Ronald J. Learning representations by back-propagating errors. Nature, 1986, 323(6088): 533−536 doi: 10.1038/323533a0
    [7] Cortes C, Vapnik V. Support-vector networks. Machine Learning, 1995, 20(3): 273−297
    [8] Hinton, G. E. Reducing the dimensionality of data with neural networks. Science, 2006, 313(5786): 504−507 doi: 10.1126/science.1127647
    [9] Lecun Y, Bengio Y, Hinton G. Deep learning. Nature, 2015, 521(7553): 436−444 doi: 10.1038/nature14539
    [10] Sabour S, Frosst N, Hinton G E. Dynamic routing between capsules. In: Proceedings of the 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA. 2017. 1−11
    [11] Guha A, Ghosh S, Roy A, Chatterjee S. Epileptic seizure recognition using deep neural network. Emerging Technology in Modelling and Graphics. Springer, Singapore, 2020. 21−28
    [12] Kantz E D, Tiwari S, Watrous J D, Cheng S. Deep neural networks for classification of lc-ms spectral peaks. Analytical Chemistry, 2019, 91(19): 12407−12413. DOI: 10.1021/acs.analchem.9b02983
    [13] Liu B S, Chen X M, Han Y H, Li J J, Xu H B, Li X W. Accelerating DNN-based 3D point cloud processing for mobile computing. Science China. Information Sciences, 2019, 32(11): 36−46
    [14] Mercedes E. Paoletti. Deep pyramidal residual networks for spectral–spatial hyperspectral image classification. IEEE Transactions on Geoscience and Remote Sensing, 2019, 57(2): 740−754 doi: 10.1109/TGRS.2018.2860125
    [15] Yang H, Luo L, Chueng L P, Ling D, Chin F. Deep learning and its applications to natural language processing. Deep Learning: Fundamentals, Theory and Applications. Springer, Cham, 2019. 89−109
    [16] Zadeh, L.A. Fuzzy sets. Information & Control, 1965, 8(3): 338−353
    [17] Mamdani E H, Baaklini N. Prescriptive method for deriving control policy in a fuzzy-logic controller. Electronics Letters, 1975, 11(25): 625−626
    [18] Wang L X. Fuzzy systems are universal approximators. In: Proceedings of the 1992 IEEE International Conference on Fuzzy Systems. San Diego, CA, USA: IEEE, 1992.1163−1170
    [19] Wang L X, Mendel J M. Generating fuzzy rules by learning from examples. IEEE Transactions on Systems, Man and Cybernetics, 1992, 22(6): 1414−1427 doi: 10.1109/21.199466
    [20] Jang J S R. ANFIS: Adaptive-network-based fuzzy inference system. IEEE Transactions on Systems Man and Cybernetics, 1993, 23(3): 665−685
    [21] Sun B X, Gao K, Jiang J C, Luo M, He T T, Zheng F D, Guo H Y. Research on discharge peak power prediction of battery based on ANFIS and subtraction clustering. Transactions of China Electrotechnical Society, 2015, 30(4): 272−280
    [22] 陈伟宏, 安吉尧, 李仁发, 李万里. 深度学习认知计算综述. 自动化学报, 2017, 43(11): 1886−1897

    Chen Wei-Hong, An Ji-Yao, Li Ren-Fa, Li Wan-Li. Review on deep-learning-based cognitive computing. Acta Automatica Sinica, 2017, 43(11): 1886−1897
  • 加载中
图(10) / 表(5)
计量
  • 文章访问数:  1998
  • HTML全文浏览量:  356
  • PDF下载量:  449
  • 被引次数: 0
出版历程
  • 收稿日期:  2020-03-02
  • 录用日期:  2020-06-28
  • 刊出日期:  2020-11-24

目录

    /

    返回文章
    返回