Вы здесь ▸ Обсуждение ▸
Мои публикации
Публикации: статьи в журналах и сборниках конференций, доклады, презентации, отчеты, авторские свидетельства.
Иванов В.К., Думина Д.С., Семенов Н.А.
К вопросу о реализации генетического алгоритма для решения задач поиска тематической информации в интернете Proceedings Article
In: Международный научно-технический конгресс «Интеллектуальные системы и информационные технологии - 2020». «IS&IT’20». Труды конгресса. Секция 1 «Эволюционное моделирование», pp. 17-28, Таганрог, 2020, ISBN: 978-56-0436-899-2.
Abstract | Links | BibTeX | Метки: additive function, fitness function, genetic algorithm, relevance, search query, weight factor, аддитивный критерий, весовой коэффициент, генетический алгоритм, поисковый запрос, релевантность, фитнес-функция
@inproceedings{V.K.Ivanov13,
title = {К вопросу о реализации генетического алгоритма для решения задач поиска тематической информации в интернете},
author = {Иванов В.К. and Думина Д.С. and Семенов Н.А.},
url = {https://disk.yandex.ru/i/wYjDcfkpmMg4Zw},
isbn = {978-56-0436-899-2},
year = {2020},
date = {2020-00-01},
urldate = {2020-00-01},
booktitle = {Международный научно-технический конгресс «Интеллектуальные системы и информационные технологии - 2020». «IS&IT’20». Труды конгресса. Секция 1 «Эволюционное моделирование»},
volume = {1},
pages = {17-28},
publisher = {Таганрог},
abstract = {В статье представлено возможное решение задачи выбора способа аналитического определения весовых коэффициентов для аддитивной фитнес-функции генетического алгоритма. Этот генетический алгоритм является основой эволюционного процесса, формирующего в поисковой системе устойчивую и эффективную популяцию запросов для получения высоко релевантных результатов. Приведено формальное описание фитнес-функции алгоритма, которая представляет собой взвешенную сумму трех неоднородных критериев.
V.K. Ivanov, D.S. Dumina, N.A. Semenov. On the Impletmentation of a Genetic Algorithm for Solving Problems of Searching for Thematic Information on the Internet
A possible solution to the problem of choosing a method for the weight factors analytical determination for the genetic algorithm additive fitness function is presented. This genetic algorithm is the evolutionary process basis, which forms a stable and effective queries population in the search engine to obtain highly relevant results. A fitness function formal description, which is a weighted sum of three heterogeneous criteria is given.},
keywords = {additive function, fitness function, genetic algorithm, relevance, search query, weight factor, аддитивный критерий, весовой коэффициент, генетический алгоритм, поисковый запрос, релевантность, фитнес-функция},
pubstate = {published},
tppubtype = {inproceedings}
}
В статье представлено возможное решение задачи выбора способа аналитического определения весовых коэффициентов для аддитивной фитнес-функции генетического алгоритма. Этот генетический алгоритм является основой эволюционного процесса, формирующего в поисковой системе устойчивую и эффективную популяцию запросов для получения высоко релевантных результатов. Приведено формальное описание фитнес-функции алгоритма, которая представляет собой взвешенную сумму трех неоднородных критериев.
V.K. Ivanov, D.S. Dumina, N.A. Semenov. On the Impletmentation of a Genetic Algorithm for Solving Problems of Searching for Thematic Information on the Internet
A possible solution to the problem of choosing a method for the weight factors analytical determination for the genetic algorithm additive fitness function is presented. This genetic algorithm is the evolutionary process basis, which forms a stable and effective queries population in the search engine to obtain highly relevant results. A fitness function formal description, which is a weighted sum of three heterogeneous criteria is given.
V.K. Ivanov, D.S. Dumina, N.A. Semenov. On the Impletmentation of a Genetic Algorithm for Solving Problems of Searching for Thematic Information on the Internet
A possible solution to the problem of choosing a method for the weight factors analytical determination for the genetic algorithm additive fitness function is presented. This genetic algorithm is the evolutionary process basis, which forms a stable and effective queries population in the search engine to obtain highly relevant results. A fitness function formal description, which is a weighted sum of three heterogeneous criteria is given.
Ivanov V.K., Palyukh B.V., Sotnikov A.N.
Conformance Evaluation of Genetic Algorithm for Evolutionary Area Search of Canonical Model Journal Article
In: Lobachevskii Journal of Mathematics, vol. 40, no. 11, pp. 1799–1808, 2019, ISSN: 1995-0802.
Abstract | Links | BibTeX | Altmetric | Метки: coding, crossover, defining length, fitness function, genetic algorithm, genotype, Holland’s schema theorem, innovation index, order, query, scheme, subject search
@article{nokey,
title = {Conformance Evaluation of Genetic Algorithm for Evolutionary Area Search of Canonical Model},
author = {Ivanov V.K. and Palyukh B.V. and Sotnikov A.N.},
url = {https://disk.yandex.ru/i/Q42TFMNFM5XGlg},
doi = {10.1134/S1995080219110155},
issn = {1995-0802},
year = {2019},
date = {2019-11-30},
urldate = {2019-11-30},
journal = {Lobachevskii Journal of Mathematics},
volume = {40},
number = {11},
pages = {1799–1808},
publisher = {Pleiades Publishing, Ltd.},
abstract = {The theory and practice of genetic algorithms is largely based on the Schema Theorem. It was formulated for a canonical genetic algorithm and proves its ability to generate a sufficient number of effective schemata of individuals. Genetic algorithms to solve specific problems and to be different from canonical ones have to be checked to find out whether the Schema Theorem evaluates the algorithm fitness. The article validates the way of testing the algorithm developed as a technique of an area search. The methodology and research results are stated consistently. Coding specifics of the search queries are noted, a criterion of the coding method applicability is substantiated. A variant of the genotype geometric coding is proposed. In comparison with other methods of binary search coding, it provides a short code length and uniqueness as well as conforms the formulated criterion of applicability. Supporting experimental results are given. The Schema Theorem is shown to hold with the iterative execution of the genetic algorithm being tested.
},
keywords = {coding, crossover, defining length, fitness function, genetic algorithm, genotype, Holland’s schema theorem, innovation index, order, query, scheme, subject search},
pubstate = {published},
tppubtype = {article}
}
The theory and practice of genetic algorithms is largely based on the Schema Theorem. It was formulated for a canonical genetic algorithm and proves its ability to generate a sufficient number of effective schemata of individuals. Genetic algorithms to solve specific problems and to be different from canonical ones have to be checked to find out whether the Schema Theorem evaluates the algorithm fitness. The article validates the way of testing the algorithm developed as a technique of an area search. The methodology and research results are stated consistently. Coding specifics of the search queries are noted, a criterion of the coding method applicability is substantiated. A variant of the genotype geometric coding is proposed. In comparison with other methods of binary search coding, it provides a short code length and uniqueness as well as conforms the formulated criterion of applicability. Supporting experimental results are given. The Schema Theorem is shown to hold with the iterative execution of the genetic algorithm being tested.
Иванов В.К.
Обоснование и постановка задачи прогнозирования результатов генетического алгоритма Journal Article
In: vol. 8, no. 57, pp. 5-13, 2016.
Abstract | Links | BibTeX | Метки: crossover, data centre, defining length, fitness function, genetic algorithm, genotype, Holland’s schema theorem, order, query, representation, scheme, subject search, генетический алгоритм, генотип, кодирование, кроссинговер, определяющая длина, поисковый запрос, порядок, схема, тематический поиск, теорема Холланда, фитнес-функция
@article{nokey,
title = {Обоснование и постановка задачи прогнозирования результатов генетического алгоритма},
author = {Иванов В.К.},
url = {https://disk.yandex.ru/i/I6iQWk2vOm4p8A
https://cyberleninka.ru/article/n/obosnovanie-i-postanovka-zadachi-prognozirovaniya-rezultatov-geneticheskogo-algoritma/viewer},
year = {2016},
date = {2016-12-31},
urldate = {2016-12-31},
volume = {8},
number = {57},
pages = {5-13},
publisher = {СибАК},
abstract = {В статье обосновывается и формулируется постановка задачи прогнозирования результатов генетического алгоритма, разработанного для выполнения документного тематического поиска. Утверждается необходимость и полезность проверки выполнения теоремы схем Холланда для указанного алгоритма. Отмечены условия корректной проверки, в частности требования к кодированию генотипа запросов и сглаживанию фитнес-функции. Предложен метод кодирования генотипа, который использует расстояние между векторами, представ-ляющими запросы.
Vladimir Ivanov
Rationale Of The Problem With Prediction Of Genetic Algorithm Results
This article presents and explains the problem with prediction of the genetic algorithm results developed to perform a subject document search. The article alleges the necessity and usefulness of the verification Holland's scheme theorem for a specified algorithm. The correct test conditions and requirements including the query genotype representation and smoothing of the fitness function are described. The genotype representation method that uses the distance between vectors is offered.},
keywords = {crossover, data centre, defining length, fitness function, genetic algorithm, genotype, Holland’s schema theorem, order, query, representation, scheme, subject search, генетический алгоритм, генотип, кодирование, кроссинговер, определяющая длина, поисковый запрос, порядок, схема, тематический поиск, теорема Холланда, фитнес-функция},
pubstate = {published},
tppubtype = {article}
}
В статье обосновывается и формулируется постановка задачи прогнозирования результатов генетического алгоритма, разработанного для выполнения документного тематического поиска. Утверждается необходимость и полезность проверки выполнения теоремы схем Холланда для указанного алгоритма. Отмечены условия корректной проверки, в частности требования к кодированию генотипа запросов и сглаживанию фитнес-функции. Предложен метод кодирования генотипа, который использует расстояние между векторами, представ-ляющими запросы.
Vladimir Ivanov
Rationale Of The Problem With Prediction Of Genetic Algorithm Results
This article presents and explains the problem with prediction of the genetic algorithm results developed to perform a subject document search. The article alleges the necessity and usefulness of the verification Holland's scheme theorem for a specified algorithm. The correct test conditions and requirements including the query genotype representation and smoothing of the fitness function are described. The genotype representation method that uses the distance between vectors is offered.
Vladimir Ivanov
Rationale Of The Problem With Prediction Of Genetic Algorithm Results
This article presents and explains the problem with prediction of the genetic algorithm results developed to perform a subject document search. The article alleges the necessity and usefulness of the verification Holland's scheme theorem for a specified algorithm. The correct test conditions and requirements including the query genotype representation and smoothing of the fitness function are described. The genotype representation method that uses the distance between vectors is offered.
Ivanov V.K., Palyukh B.V., Sotnikov A.N.
Efficiency of genetic algorithm for subject search queries Journal Article
In: Lobachevskii Journal of Mathematics, vol. 37, no. 3, pp. 244–254, 2016, ISSN: 1995-0802.
Abstract | Links | BibTeX | Altmetric | Метки: convergence, data centre, fitness function, genetic algorithm, population, ranking, relevance, search precision, search query
@article{nokey,
title = {Efficiency of genetic algorithm for subject search queries},
author = {Ivanov V.K. and Palyukh B.V. and Sotnikov A.N.},
url = {https://disk.yandex.ru/i/5AegVA7CNqPk_Q},
doi = {10.1134/S1995080216030124},
issn = {1995-0802},
year = {2016},
date = {2016-03-31},
urldate = {2022-09-28},
journal = {Lobachevskii Journal of Mathematics},
volume = {37},
number = {3},
pages = {244–254},
publisher = {Pleiades Publishing, Ltd.},
abstract = {The article presents and generalizes the results on some performance indicators of genetic algorithm developed by authors and applied to effective search queries and selection of relevant results after document subject search. It is shown that the developed technology expands opportunities of semantic search and increases the number of the found relevant results. In particular, we made an effort to show the ability of the developed algorithm to achieve the neighborhood of the fitness function in a finite number of steps, to provide higher precision of search in comparison with the well-known search engines of the Internet as well as to provide the acceptable semantic relevance of the found documents.
},
keywords = {convergence, data centre, fitness function, genetic algorithm, population, ranking, relevance, search precision, search query},
pubstate = {published},
tppubtype = {article}
}
The article presents and generalizes the results on some performance indicators of genetic algorithm developed by authors and applied to effective search queries and selection of relevant results after document subject search. It is shown that the developed technology expands opportunities of semantic search and increases the number of the found relevant results. In particular, we made an effort to show the ability of the developed algorithm to achieve the neighborhood of the fitness function in a finite number of steps, to provide higher precision of search in comparison with the well-known search engines of the Internet as well as to provide the acceptable semantic relevance of the found documents.