Pareto filter in the process of multi-label classifier synthesis in medical diagnostics support algorithms
Journal Title: Computer Science and Mathematical Modelling - Year 2015, Vol 0, Issue 1
Abstract
The paper presents the possibility of using multi-criteria optimization methods for simple classifiers fusion in a more precise and reliable classifiers complex. There are defined simple classifiers (one label) in the form of classifier committees and sample the synthesis relations of classifiers allow to obtain classifiers field with improved properties.
Authors and Affiliations
Andrzej Ameljańczyk
Keywords
Related Articles
- EP ID EP77433
- DOI 10.5604/15084183.1197401
- Views 118
- Downloads 0
Evolutionary algorithms for Map of Attributes optimization
Rank thresholds in classifier ensembles in medical diagnosis
Classification methods have multiple applications, with medical diagnosis being one of the most common. A powerful way to improve classification quality is to combine single classifiers into an ensemble. One of the appro...
Web services hybrid composition, grouping and execution platform
The paper describes a software platform that implements the concept of hybrid composition, grounding and execution. The described platform allows to use different methods to build, ground and execute service composition...
Thing about some assuring interoperability of information and information technology systems conditions
In this article, starting from some popular descriptions of interoperability, was presented short discussion of this term according to proprieties of information and information technology systems. In the next step was d...
Transformacja modelu z pełną informacją o sieci użytkowników do modelu z niekompletną informacją Podejście wykorzystujące narzędzia teorii gier
W tym artykule zajmiemy się modelowaniem sieci skierowanych, to znaczy przedstawionych za pomocą grafów skierowanych. Przez „informację” (w raczej ogólnym użyciu tego słowa) będziemy rozumieć dobro, którego przepływ nast...