Metrika članka

  • citati u SCindeksu: 0
  • citati u CrossRef-u:0
  • citati u Google Scholaru:[=>]
  • posete u poslednjih 30 dana:2
  • preuzimanja u poslednjih 30 dana:0
članak: 4 od 9  
Back povratak na rezultate
Yugoslav Journal of Operations Research
2019, vol. 29, br. 1, str. 51-67
jezik rada: engleski
vrsta rada: neklasifikovan
objavljeno: 28/02/2019
doi: 10.2298/YJOR171107030K
Algorithms with greedy heuristic procedures for mixture probability distribution separation
(naslov ne postoji na srpskom)
aReshetnev University, Department of Systems Analysis and Operations Research, Krasnoyarsk, Russian Federation
bITMO University, Department of Computer Educational Technologies, Petersburg, Russian Federation

e-adresa: levklevk@gmail.com, stashkov@ngs.ru, darfai04@gmai

Projekat

Results were obtained in the framework of the state task 2.5527.2017/8.9 of the Ministry of Education and Science of the Russian Federation.

Sažetak

(ne postoji na srpskom)
For clustering problems based on the model of mixture probability distribution separation, we propose new Variable Neighborhood Search algorithms (VNS) and evolutionary genetic algorithms (GA) with greedy agglomerative heuristic procedures and compare them with known algorithms. New genetic algorithms implement a global search strategy with the use of a special crossover operator based on greedy agglomerative heuristic procedures in combination with the EM algorithm (Expectation Maximization). In our new VNS algorithms, this combination is used for forming randomized neighborhoods to search for better solutions. The results of computational experiments made on classical data sets and the testings of production batches of semiconductor devices shipped for the space industry demonstrate that new algorithms allow us to obtain better results, higher values of the log likelihood objective function, in comparison with the EM algorithm and its modifications.

Ključne reči

Clustering; Variable Neighborhood Search; Genetic Algorithm; Greedy Heuristic; Agglomerative Heuristic; Expectation Maximization