The article discusses the problem of drug clustering. Initially, k classes are randomly formed and the resulting training sample is preprocessed, then the similarity between objects of each class is assessed based on the proximity function and the criterion for assessing the contribution of objects to the formation of their own class. It is usually expressed as a percentage and represents 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 remains in the class that contributed the most. This process is repeated several times in a row for all objects of the class. The process stops when the location of objects does not change and the degree of similarity exceeds the required percentage. As a result, the necessary clusters are formed.
| Mualliflar | Akhram Khasanovich Nishanov, Alisher Tursunov, Fayzullo Farhod o'g'li Ollamberganov |
|---|---|
| Jurnal | Кимёвий технология. Назорат ва бошқарув |
| Nashr sanasi | 2024-08-30 |
| Jild | 2024 |
| Son | 4 |
| Betlar | 11-21 |
| Til | en |
| DOI | 10.59048/2181-1105.1586 |
DOI: 10.59048/2181-1105.1586 · Maqolaning asl sahifasi
In the modern world, decision-making often takes place in an environment of uncertainty and under the significant influence of emotional factors, which requires the use of special methods for analyzing information. This…
This article discusses methods of low capacitance measurement of capacitive sensors. The results of the study of the amplitude-frequency (AF) and phase-frequency (PF) response of measurement circuits of capacitive…
The article is devoted to the solution of the scientific issue of decision-making support for the prevention and elimination of the consequences of emergency situations. The relevance of this issue is related to the…
Agricultural products provide significant growth in export earnings for many countries and provide food globally. Fruits and vegetables are perishable foods due to their high moisture content. Therefore, most…
The paper presents methods and algorithms for automatic control based on predictive models of dynamic objects in continuous and semi-continuous industrial production. The approach under consideration allows further…
The paper considers the issues of synthesizing a predictor controller as part of a control system for a non-stationary dynamic plant with a predictive model. Technological processes in industry, in essence, have…
This paper presents a major challenge in fault diagnosis for electronic computing equipment is developing an object model tailored to support diagnostic tasks. Effective fault localization requires establishing a link…
In-depth scientific research is being conducted around the world aimed at developing the scientific and methodological foundations of energy-saving extractors, processing medicinal plants, increasing the efficiency of…
This scientific work analyzes the research on data collection and transmission technologies for automatic control of high-frequency ozonators in water disinfection. The purpose of the study is to improve disinfection…
This paper presents the results of a study of the parameters of a new technological scheme for the extraction of uranium from technogenic uranium ores. The results of the analytical determination of the concentration of…