DEVELOPMENT OF A DATABASE STRUCTURE FOR STORING MODELS FOR DETERMINATED ALPHABETES CLASSES RECOGNITION BASED ON THE SET OF HETEROGENEOUS CHARACTERISTIC
Abstract
The objects and situations recognition is important problem in such areas as the definition of the types of air objects according to various sources of information, diagnosis of patients on the results of the survey and analysis, diagnostics of different equipment or technic types. Under the recognition refers to the process of obtaining the initial information about the affiliation of each studied element to a class based on analyze of the incoming information about studied elements of the environment, using methods to transform input data environment into output. The paper presents a model of the recognition process, which is characterized by the decision making of the class object based on the analysis of a set of quantitative and qualitative characteristics of which information can be obtained from various sources. The article presents a formalized set-theoretic model of the recognition process. According to the model, to attribute an object or situation to a certain class, it is necessary to define a set of feature groups of different types that allow to identify objects (situations) of a particular class. To perform recognition process experts based on experience or on the basis of statistical data must define a fuzzy affiliation function of the object of observation to each class with a set of values [0,1]. In the article shown representation of such function for quantitative characteristic in the form of a histogram. For qualitative attributes determined own values for each value. The new result of researches is a data structure for storing of the recognition process model, which allows to store together diverse characteristics and affiliation functions of different types at the same database tables. The proposed structure can be used in the process of the development of recognition systems software. It should be noted that will provide increased reliability of data storage by reducing the components of the database structure but also increased the complexity of the procedures and algorithms for saving and selecting the data.
Keywords
