This is a Demo Server. Data inside this system is only for test purpose.

Scopus

Permanent URI for this collectionhttps://tuit-demo.gcris.com/handle/123456789/23

Browse

Browsing Scopus by Author "Department of System and Applied Programming"

Filter results by typing the first few letters
Now showing 1 - 2 of 2
  • Thumbnail Image
    Conference Object
    Citation Count: 0
    Classification Algorithms With a Complex Structure in Pattern Recognition
    (IEEE Computer Society, 2024) Nishanov, A.Kh.; Allamov, O.; Rakhmanov, A.T.; Yusupova, J.; Ruzibaev, O.B.; Department of System and Applied Programming
    The article considers in the intellectual processing of information, moving from a large unit of measurement to a smaller, more important unit of measurement, selecting sets of informative symbols and classifying symbols, developing modern recognition systems that help specialists in the field, as well as evaluating the states of objects to be classified, developing a classification algorithm for multi-class cases of educational samples. The development of a multi-class algorithm for symbol classification serves to develop the theory of symbol recognition. It deals with the construction of a decision rule construction algorithm. Its main purpose is to determine which of the given classes the recognized object belongs to. The complexity or simplicity of the proposed algorithm depends on the number of classes participating in the study sample. If the number of classes is two, then the formulation of decision rules is simple. That is why the classification algorithms proposed by most authors are solved for cases where the number of classes is three or more, the decisive rule in the matter of classification of objects is solved by making two classes. The construction of a multi-class decision rule for classification, which takes into account all classes at the same time, is a complex and urgent issue. In the article, in the classification of objects, a multi-level complex structured decision rule was developed based on special inequalities, and two-, three- and multi-class classification algorithms were developed. © 2024 IEEE.
  • Thumbnail Image
    Article
    Citation Count: 0
    Clustering Algorithm Based on Object Similarity
    (al-Farabi Kazakh State National University, 2024) Nishanov, A.Kh.; Akbarova, M.Kh.; Tursunov, A.T.; Ollamberganov, F.F.; Rashidova, D.E.; Department of System and Applied Programming
    The article examines the issue of drug clustering. Initially, k classes are arbitrarily formed and the resulting training sample is pre-processed, then the similarities between the objects of each class are evaluated based on the proximity function and the criterion for evaluating the contribution of objects to the formation of their own class. Usually, it is in percentage and is the degree of mutual similarity of objects of each class. In the next steps of the algorithm, first, one object is taken from the first class, and by adding it to all k classes, the contribution of this object to this class is measured. The object will be left in the class which has the most contribution. This process is repeated several times in a row for all objects of the class. The process is stopped when the location of objects does not change and the degree of similarity exceeds the required percentage. As a result, the required clusters are formed. © 2024 Al-Farabi Kazakh National University.