Theoretical Basis for Multidimensional Patterns Recognition in Hamming Space

Krulikovskyy, B.B.; Sydor, Andrij; Zastavnyy, Oleg; Nykolaychuk, Yaroslav

doi:10.15421/40260359

Cited by 2 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Розпізнавання образів (об'єктів, сигналів) -задача ідентифікації об'єкта за зображенням чи набором характеристик [1]. Класифікація об'єктів базується на методиці віднесення елемента до певного образу у просторі метрик, яка передбачає побудову певного правила -класифікатора.…”

Section: аналіз досліджень та публікаційunclassified

“…Класифікація об'єктів базується на методиці віднесення елемента до певного образу у просторі метрик, яка передбачає побудову певного правила -класифікатора. Від вибору представлення образів і реалізації метрики залежить ефективність процесу класифікації [1]. Існують різні евристичні, лінгвістичні та математичні методи розпізнавання зображень, ідентифікації та класифікації об'єктів [2,3]: потенційні функції, байєсівські мережі, марківські мережі, штучні нейронні мережі, генетичні алгоритми, дерева рішень тощо.…”

Section: аналіз досліджень та публікаційunclassified

See 1 more Smart Citation

Meta-Model of Design of Information Technology Prototype of Classification of Objects by Image Shape Using GMDH Neural Networks in the Notation of a Unified Modeling Language

Davydenko¹

2022

Herald KhmNU.TS

View full text Add to dashboard Cite

The article is devoted to the development of intelligent monitoring systems of technological processes based on the use of machine vision systems. The principles of object-oriented formalization of the process of designing information technology of the classification of objects by the geometric shape of the image obtained from the machine vision system are proposed in the article. The proposed information technology is based on the use of machine learning technologies and provides for the selection of the best structure of the classifier model from a set of candidate models. Construction of candidate models is based on the use of the group method of data handling, based on the principles of self-organization of models. The outline of the image of the object obtained from the intelligent monitoring system is the input information. The set of input data contains a set of morphometric parameters that describe the geometric shape of the figure formed by the contour of the image of the object, as well as the label of the class to which the object belongs. The formation of the set of input data is implemented in the block «Image Processing». The decisive rule of classification is built in the block of synthesis of models of information technology of classification. GMDH neural networks were used as an algorithm for model synthesis. The choice of the best structure of the model is performed by a set of criteria. The information technology for constructing the classifier model is implemented by supplementing the block of algorithms for synthesis of MSUA models with the block «Class of models», which implements the process of selecting the class of functions for building models, and the block «Verification of models», which implements the best model structure. Construction of the meta-model of the design process was performed using a unified modeling language. The functional meta-model is represented by a use case diagram.

show abstract

Section: аналіз досліджень та публікаційunclassified

Meta-Model of Design of Information Technology Prototype of Classification of Objects by Image Shape Using GMDH Neural Networks in the Notation of a Unified Modeling Language

Davydenko¹

2022

Herald KhmNU.TS

View full text Add to dashboard Cite

show abstract

Automatic Pilot System for Unmanned of Aircraft in the Absence of Radio Communication

2020

View full text Add to dashboard Cite

One of the most pressing problems of piloting unmanned aerial vehicles (UAV) in the absence of radio communication is considered in the article. Therefore, the aim of the article is to develop an algorithm and method of automatic piloting of UAV in terms of loss of radio control signal using the methods of technical vision. The most effective methods of tracking, identification and detection of landmarks are based on the comparison of reference information (database of known navigation objects) with the observation scene in real time.Working system of automatic piloting of UAVs in the conditions of loss of radio control signal or GPS-navigation developed. The hardware and software of the UAV provides full automatic control. The programming of the system consists of two stages: planning the flight task and calculating the trajectory of the UAV in flight. The planning of the flight task is carried out by setting the topographic landmarks and flight parameters in relation to them. At this stage, the criteria for the generalization of the various components of the landscape are formed and their division by gradations. This work is combined with the recognition of points with altitude marks, and fixing the heights of horizontal surfaces available in the area. All horizontal surfaces are tied with the shortest shooting strokes to at least of three points with elevations. The process of topography-based object selection is directly related to its segmentation, the results of which significantly affect the further process of image analysis and UAV control. The calibration of the starting point of the route occurs during the launch of the UAV. The control system automatically monitors the location of the UAV throughout the trajectory of the movement on a topographic basis relative to the prespecified landmarks. Structured shots of the terrain and topographic bases are compared during the flight. The algorithm is based on the comparison of geometric parameters of landmarks. The parameters of the geometric center O(x, y) and the area S are taken into account by such parameters. The control signal in the three axes OX, OY and OZ is determined for the first time by the method of least squares depending on the values of the calculated coefficients of the original equations.

show abstract

Theoretical Basis for Multidimensional Patterns Recognition in Hamming Space

Cited by 2 publications

References 0 publications

Meta-Model of Design of Information Technology Prototype of Classification of Objects by Image Shape Using GMDH Neural Networks in the Notation of a Unified Modeling Language

Meta-Model of Design of Information Technology Prototype of Classification of Objects by Image Shape Using GMDH Neural Networks in the Notation of a Unified Modeling Language

Automatic Pilot System for Unmanned of Aircraft in the Absence of Radio Communication

Contact Info

Product

Resources

About