Application of artificial neural network ensembles for city ecology forecasting using air chemical composition information : доклад, тезисы доклада | Научно-инновационный портал СФУ

Application of artificial neural network ensembles for city ecology forecasting using air chemical composition information : доклад, тезисы доклада

Тип публикации: доклад, тезисы доклада, статья из сборника материалов конференций

Конференция: International Conference on Environmental Engineering and Computer Application, ICEECA 2014; Kowloon; Kowloon

Год издания: 2015

Аннотация: The constant growth of the population, the growth of the number of cars, the huge amount of harmful products, technogenic factors—these are some of the reasons for the bad ecological situation in modern megalopolis. The high level of harmful substances in the air makes the average lifetime shorter in cities and as a consequence damages the economy and city development. In this article, solving the problem of predicting the ecological condition of a city based on the air chemical composition is considered. The procedure of solving the problem with artificial neural networks, designed automatically with an evolutionary algorithm, is described. A set of modifications, which allow an increase in the accuracy of the solution of the data analysis problem, are presented and tested. A comparison with analogues is fulfilled. The analysis of the presented results shows the efficiency of the proposed approach when solving test problems. The application of this algorithm for predicting the ecological state of the city shows competitive efficiency compared with other algorithms.

Ссылки на полный текст

Издание

Журнал: Environmental Engineering and Computer Application - Proceedings of the International Conference on Environmental Engineering and Computer Application, ICEECA 2014

Номера страниц: 45-50

Авторы

  • Khritonenko D.I. (Siberian State Aerospace University)
  • Semenkin E.S. (Siberian State Aerospace University)

Вхождение в базы данных

Информация о публикациях загружается с сайта службы поддержки публикационной активности СФУ. Сообщите, если заметили неточности.

Вы можете отметить интересные фрагменты текста, которые будут доступны по уникальной ссылке в адресной строке браузера.