Determination of Informative Features Based on the Criteria of Positive Type
Narzillo Mamatov1, Abdurashid Samijonov2, Nilufar Niyozmatova3, Erkin Rahmonov4, Bakhromjon Abdurakhmonov5
1Mamatov Narzillo*, Tashkent University Information Technologies, Al-Kharezmi, Tashkent, Uzbekistan.
2Niyozmatova Nilufar, Tashkent University Information Technologies Al-Kharezmi, Tashkent, Uzbekistan.
3Samijonov Abdurashid, Bauman Moscow State Technical University, Moscow, Russia Federation.
4Rahmonov Erkin, Tashkent Pharmaceutical Institute, Tashkent, Uzbekistan.
5Abdurakhmonov Bakhromjon, Tashkent Pharmaceutical Institute, Tashkent, Uzbekistan.
Manuscript received on December 15, 2019. | Revised Manuscript received on December 20, 2019. | Manuscript published on January 10, 2020. | PP: 2860-2862 | Volume-9 Issue-3, January 2020. | Retrieval Number: B6369129219/2020©BEIESP | DOI: 10.35940/ijitee.B6369.019320
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Currently, pattern recognition systems are widely used to solve practical problems. The choice of criterion in pattern recognition problems is fundamental. The choice of informative features depends on the criterion of informativeness. A single criterion has not been developed to select a set of informative features. Therefore, the criterion is selected from the formulation of a practical problem. For each selected criterion, it is necessary to develop special methods and algorithms. For homogeneous criteria, there is no single method.A new method and algorithm for determining sets of informative features based on generalized criteria of a positive order is proposed in this work.
Keywords: Feature, Positive-Types Criteria, Informative Feature, Vector, Functional, Gradient, Operator.
Scope of the Article: Logic, Functional programming and Microcontrollers for IoT