Building Interpretable and Parsimonious Fuzzy Models using a Multi-Objective Approach

被引:2
|
作者
Fuchs, Caro [1 ,3 ]
Kaymak, Uzay [1 ]
Nobile, Marco S. [2 ,3 ,4 ]
机构
[1] Eindhoven Univ Technol, Jheronimus Acad Data Sci, Shertogenbosch, Netherlands
[2] Ca Foscari Univ Venice, Dept Environm Sci Informat & Stat, Venice, Italy
[3] Eindhoven Univ Technol, Dept Ind Engn & Innovat Sci, Eindhoven, Netherlands
[4] Interdisciplinary Res Ctr, Bicocca Bioinformat Biostat & Bioimaging B4, Milan, Italy
关键词
Fuzzy model; Feature selection; Model parameter estimation; Explainable AI (XAI); Multi-objective optimization; SYSTEMS; IDENTIFICATION; ALGORITHMS; REDUCTION; SELECTION; RULES;
D O I
10.1109/FUZZ-IEEE55066.2022.9882755
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Nowadays, the growing amounts of collected data enable the training of machine learning models that can be used to extract insights from the data and make better-informed decisions. Among the possible models that can be learned from data are fuzzy rule-based models, which are transparent and enable when properly designed- interpretable artificial intelligence. One of the requirements of interpretability is a simple model structure, which can be achieved by performing feature selection and by limiting the number of rules in the model. However, the chosen feature set and the number of rules may interact and strongly affect the model's accuracy. In this study, we employ techniques from the field of evolutionary computation to perform feature and rule number selection simultaneously. To ensure the developed models do not only perform well but are also interpretable and have good generalization capabilities, we adopt a multi-objective approach in which we train the models focusing on three objectives: performance, complexity, and model stability. In this way, we strive to develop simple, well-performing parsimonious fuzzy models. We show the effectiveness of our approach on three benchmark data sets.
引用
收藏
页数:8
相关论文
共 50 条
  • [41] Fuzzy arithmetic DEA approach for fuzzy multi-objective transportation problem
    Bagheri, M.
    Ebrahimnejad, A.
    Razavyan, S.
    Lotfi, F. Hosseinzadeh
    Malekmohammadi, N.
    OPERATIONAL RESEARCH, 2022, 22 (02) : 1479 - 1509
  • [42] Fuzzy arithmetic DEA approach for fuzzy multi-objective transportation problem
    M. Bagheri
    A. Ebrahimnejad
    S. Razavyan
    F. Hosseinzadeh Lotfi
    N. Malekmohammadi
    Operational Research, 2022, 22 : 1479 - 1509
  • [43] An interpretable model for sepsis prediction using multi-objective rule extraction
    Chen, Mingzhou
    Huo, Jiazhen
    Duan, Yongrui
    JOURNAL OF INTELLIGENT INFORMATION SYSTEMS, 2024, 62 (5) : 1403 - 1429
  • [44] Surrogate Models for Efficient Multi-Objective Optimization of Building Performance
    Araujo, Goncalo Roque
    Gomes, Ricardo
    Gomes, Maria Gloria
    Guedes, Manuel Correia
    Ferrao, Paulo
    ENERGIES, 2023, 16 (10)
  • [45] An Analysis of Multi-objective Fuzzy Stochastic Nonlinear Programming Models
    Beaula, Thangaraj
    Seetha, R.
    COMMUNICATIONS IN MATHEMATICS AND APPLICATIONS, 2022, 13 (04): : 1287 - 1294
  • [46] Multi-objective optimization using statistical models
    Tsionas, Mike G.
    EUROPEAN JOURNAL OF OPERATIONAL RESEARCH, 2019, 276 (01) : 364 - 378
  • [47] Multi-objective approach to deriving QSAR models.
    Nicolotti, O
    Gillet, VJ
    Fleming, PJ
    Green, D
    ABSTRACTS OF PAPERS OF THE AMERICAN CHEMICAL SOCIETY, 2004, 227 : U1027 - U1027
  • [48] Local models—an approach to distributed multi-objective optimization
    Lam T. Bui
    Hussein A. Abbass
    Daryl Essam
    Computational Optimization and Applications, 2009, 42 : 105 - 139
  • [49] Multi-Objective Hybrid PSO Using ε-Fuzzy Dominance
    Koduru, Praveen
    Das, Sanjoy
    Welch, Stephen M.
    GECCO 2007: GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE, VOL 1 AND 2, 2007, : 853 - +
  • [50] Using a staged multi-objective optimization approach to find selective pharmacophore models
    Robert D. Clark
    Edmond Abrahamian
    Journal of Computer-Aided Molecular Design, 2009, 23 : 765 - 771