Wyniki wyszukiwania - BazTech

Ograniczanie wyników

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Sortuj według:

Ogranicz wyniki do:

Classification of rocks radionuclide data using machine learning techniques

Khan A. R., Mir A. A., Saeed S., Rafique M., Asim K. M., Iqbal T., Jabbar A., Rahman S. U.

Acta Geophysica

2018

Vol. 66, no. 5

1073--1079

The aim of this study is to assess the performance of linear discriminate analysis, support vector machines (SVMs) with linear and radial basis, classification and regression trees and random forest (RF) in the classification of radionuclide data obtained from three different types of rocks. Radionuclide data were obtained for metamorphic, sedimentary and igneous rocks using gamma spectroscopic method. A P-type high-purity germanium detector was used for the radiometric study. For analysis purpose, we have determined activity concentrations of 232Th, 226Ra and 40K radionuclides, published elsewhere (Rafique et al. in Russ Geol Geophys 55:1073–1082, 2014), in different rock samples and built the classification model after pre-processing the data using three times tenfold cross-validation. Using this model, we have classified the new samples into known categories of sedimentary, igneous and metamorphic. The statistics depicts that RF and SVM with radial kernel outperform as compared to other classification methods in terms of error rate, area under the curve and with respect to other performance measures.

Review of computer codes for modeling corrosion product transport and activity build-up in light water reactors

Rafique M., Mirza N. M., Mirza S. M., Iqbal M. J.

Nukleonika

2010

Vol. 55, No. 3

263-269

The corrosion products are among the leading sources of radiation in primary coolant circuits of pressurized water reactors leading to prolongation of reactor down-time for routine maintenance entailing substantial loss of revenues. These deposits affect adversely coolant flow rates resulting in elevation of fuel and cladding temperature and become activated by high neutron flux in reactor core consequently creating high radiation field by accumulating in the out-of-core reactor components. In the case of light water reactors (LWRs), prevailing corrosion products include 59Fe, 99Mo, 56Mn, 58Co, and 60Co. The 56Mn is the leading corrosion product activity source during operation while cobalt isotopes dominate the activity after reactor shutdown. This paper presents a detailed discussion on some computer codes developed for prediction and transport of corrosion product activity in LWRs.