Mkrtchyan F.A. The problem of statistical learning decision-making for the small sample size in geoinformation monitoring. American Journal of Mathematics and Statistics , 2013 (6). С. 346-348. ISSN p-ISSN: 2162-948X e-ISSN: 2162-8475
Полный текст не доступен из этого репозитория. (Заказать копию)Аннотация
The application of geoinformation monitoring means often involves statistical decision making about the presence of one or other phenomenon on a surveyed part of the Earth surface. One of the features of information acquisition conditions for such a decision is that it is impossible to obtain large statistical samples. Therefore, the development and research of optimal algorithms for distinguishing between random signals with samples of limited size under conditions of parametric a priori uncertainty is a topical problem. In the present work, a generalized adaptive learning algorithm is developed for statistical decision making concerning exponential families of distributions under conditions of a priori parametric uncertainty for small sample sizes. Numerical examples are presented. The efficiency of the optimal procedure developed is demonstrated in the case of small samples. “The reported study was partially supported by RFBR, research project No.13-07-00146”. Keywords: Statistical Decision, Small Samples, Exponential Classes, Geoinformation Monitoring, Spottiness Cite this paper: F. A. Mkrtchyan, The Problem of Statistical Learning Decision-Making for the Small Sample Size in Geoinformation Monitoring, American Journal of Mathematics and Statistics, Vol. 3 No. 6, 2013, pp. 346-348. doi: 10.5923/j.ajms.20130306.07.
| Тип объекта: | Статья |
|---|---|
| Авторы на русском. ОБЯЗАТЕЛЬНО ДЛЯ АНГЛОЯЗЫЧНЫХ ПУБЛИКАЦИЙ!: | Мкртчян Ферденант Анушаванович |
| Подразделения (можно выбрать несколько, удерживая Ctrl): | 209 лаб. вычислительная |
| URI: | http://cplire.ru:8080/id/eprint/267 |
 |
Изменить объект |
