Information-extremе machine learning for object identification on the terrain
Journal Title: Журнал інженерних наук - Year 2016, Vol 3, Issue 1
Abstract
The article deals with the usage of a SURF local descriptor of key fragments to create a global descriptor BoF for objects of interest on terrain within task of recognition of armored technique in the controlled territory using images of air reconnaissance. The method of optimization of the input mathematical description of the information-extreme classifier trained on dataset, which consist of global descriptors BoF, is proposed. The optimal in information understanding dimensionality of a global descriptor is determined by iterative procedure, which includes k-means clustering of key fragment's SURF-vectors, training dataset creation and information-extreme machine learning of the classifier. The offered algorithm of information-extreme machine learning implements the adaptive coding of values of primary features using multilevel system of control permits, and creation of hyperspherical containers of classes in binary space of secondary features with sequential optimization procedures. It was suggested to use the rated modification of S. Kulbak's information measure, which is a function of false omission rate and positive predictive value of decision-making and it also allows machine learning on imbalanced dataset.
Authors and Affiliations
V. Moskalenko, A. Korobov
Keywords
Related Articles
- EP ID EP241741
- DOI -
- Views 66
- Downloads 0
Increased Wear Coatings due Intrastructural Self-Correction
A mechanism for blocking and subsequent annihilation of endogenous microcracks due to their intrastructural self-correction has been proposed. It has been established that during tribomechanical processes of friction int...
Improvement of the Vacuum Cooling System for Biodiesel Production
The article deals with the actual problem of improving the vacuum cooling efficiency systems during the biodiesel production by using vacuum devices account for the liquid-vapor ejector, which operates on the principle o...
Research of Working Process of Vortex Expansion Machine with Side Channel
At gas distribution stations, a large amount of energy of compressed gases is lost. In such cases, the useful power is obtained with the aid of a turboexpander. The problem is that there is a great need for turboexpander...
The hypothesis of formation of the structure of surfaced metal at the surfacing based on the application of the prognostic algorithm of control the electrode wire speed
The growth of a drop in the process of surfacing by a consumable electrode is characterized by a linear dependence of the current change on time. A hypothesis has been put forward, according to which a reduction in the f...
Solving the Nonstationary Problem of the Disperse Phase Concentration during the Pneumoclassification Process of Mechanical Mixtures
The article dials with studying of the gas-dispersed systems classification process in gravitation pneumoclassifiers of prismatic shape. The aim of the research is to determine operating parameters of the investigated pr...