Інформаційна технологія кластеризації даних у часовому періоді спостережень
Cluster analysis is an important task of data mining. The use of clustering techniques allows to understand the structure of multidimensional data; to simplify further processing using different methods of analysis for each cluster; reduce the original sample data, leaving the most typical represent...
Збережено в:
| Дата: | 2013 |
|---|---|
| Автори: | , |
| Формат: | Стаття |
| Мова: | Ukrainian |
| Опубліковано: |
The National Technical University of Ukraine "Igor Sikorsky Kyiv Polytechnic Institute"
2013
|
| Онлайн доступ: | http://journal.iasa.kpi.ua/article/view/33941 |
| Теги: |
Додати тег
Немає тегів, Будьте першим, хто поставить тег для цього запису!
|
| Назва журналу: | System research and information technologies |
Репозитарії
System research and information technologies| Резюме: | Cluster analysis is an important task of data mining. The use of clustering techniques allows to understand the structure of multidimensional data; to simplify further processing using different methods of analysis for each cluster; reduce the original sample data, leaving the most typical representatives of each group; detect novelty, atypical objects that can not be attached to any of the classes; formulate or test hypotheses based on the results. In this article а new approach to the selection of groups of objects that are similar to each other on a set of features that changing over time has been proposed. Information technology of quality assessment and improvement of the stability of clustering has been developed. The results of practical implementation of the proposed technology to data of hydrochemical monitoring of ater objects in the area with high technological load have been presented. |
|---|