Genetic programming hyperheuristic parameter configuration using fitness landscape analysis

被引：3

作者：

Coric, Rebeka ^{[1
]}

Dumic, Mateja ^{[1
]}

Jakobovic, Domagoj ^{[2
]}

机构：

[1] JJ Strossmayer Univ Osijek, Dept Math, Gajev Trg 6, Osijek 31000, Croatia

[2] Fac Elect Engn & Comp, Unska 3, Zagreb 10000, Croatia

来源：

APPLIED INTELLIGENCE | 2021年 / 51卷 / 10期

关键词：

Fitness landscape analysis; Genetic programming; Scheduling; Tree operators; Clustering; Parameter configuration; DISPATCHING RULES; OPTIMIZATION; ALGORITHM; MODEL;

D O I：

10.1007/s10489-021-02227-3

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Fitness landscape analysis is a tool that can help us gain insight into a problem, determine how hard it is to solve a problem using a given algorithm, choose an algorithm for solving a given problem, or choose good algorithm parameters for solving the problem. In this paper, fitness landscape analysis of hyperheuristics is used for clustering instances of three scheduling problems. After that, good parameters for tree-based genetic programming that can solve a given scheduling problem are calculated automatically for every cluster. Additionally, we introduce tree editing operators which help in the calculation of fitness landscape features in tree based genetic programming. A heuristic is proposed based on introduced operators, and it calculates the distance between any two trees. The results show that the proposed approach can obtain parameters that offer better performance compared to manual parameter selection.

引用

页码：7402 / 7426

页数：25

共 56 条

[1] A novel fitness function in genetic programming to handle unbalanced emotion recognition data [J].

Acharya, Divya ;

Goel, Shivani ;

Asthana, Rishi ;

Bhardwaj, Arpit .

PATTERN RECOGNITION LETTERS, 2020, 133 :272-279

[2]

Artigues C., 2008, Resource-constrained project scheduling: models, algorithms, extensions and applications

[3] Genetic programming performance prediction and its application for symbolic regression problems [J].

Astarabadi, Samaneh Sadat Mousavi ;

Ebadzadeh, Mohammad Mehdi .

INFORMATION SCIENCES, 2019, 502 :418-433

[4] Greedy randomized adaptive search for dynamic flexible job-shop scheduling [J].

Baykasoglu, Adil ;

Madenoglu, Fatma S. ;

Hamzadayi, Alper .

JOURNAL OF MANUFACTURING SYSTEMS, 2020, 56 :425-451

[5]

Bogon T, 2013, AGENTS ARTIFICIAL IN, P72

[6] The k-coloring fitness landscape [J].

Bouziri, Hend ;

Mellouli, Khaled ;

Talbi, El-Ghazali .

JOURNAL OF COMBINATORIAL OPTIMIZATION, 2011, 21 (03) :306-329

[7]

Calinski T., 1974, COMMUN STAT, V3, P1, DOI DOI 10.1080/03610927408827101

[8] Neuro-genetic programming for multigenre classification of music content [J].

Campobello, G. ;

Dell'Aquila, D. ;

Russo, M. ;

Segreto, A. .

APPLIED SOFT COMPUTING, 2020, 94

[9] Predicting customer satisfaction based on online reviews and hybrid ensemble genetic programming algorithms [J].

Chan, Kit Yan ;

Kwong, C. K. ;

Kremer, Gul E. .

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2020, 95

[10] A genetic programming approach based on Levy flight applied to nonlinear identification of a poppet valve [J].

Coelho, Leandro dos Santos ;

Bora, Teodoro Cardoso ;

Klein, Carlos Eduardo .

APPLIED MATHEMATICAL MODELLING, 2014, 38 (5-6) :1729-1736

← 1 2 3 4 5 6 →