Integration of results from recognition algorithms and its realization at the uranium production process

Polina Gritsenko, S. Iskakov, R. Muhamediyev, K. Yakinin

2014

Closed access Metadata (CSL-JSON)
DOI 10.1109/icaict.2014.7035940
Data confidence 70 medium
How this score is calculated

It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.

Abstract

Taught systems such as artificial neural network (ANN) can be used for data interpretation of electric logging. Using only the ANN algorithm gives the result of coincidence between interpretable data and experimental results in certain samplings from 66% to 73%. But using additional algorithms of recognition and integrating the results of recognition could enhance quality of recognition by 1-3%. The problem of integration of classification algorithms results was formulated and realization as pseudocode was shown.