Using the Kohonen Clustering Algorithm for Rough Peak Detection during Mass Spectrum Preprocessingстатья
Информация о цитировании статьи получена из
Scopus
Статья опубликована в журнале из списка Web of Science и/или Scopus
Дата последнего поиска статьи во внешних источниках: 1 мая 2024 г.
Аннотация:The paper explores the applicability of the Kohonen clustering algorithm for peak detection during the preprocessing of mass spectra. Various modifications made to the algorithm’s classical version during its implementation in the program code are described. The results of peak detection carried out in four mass spectra of inorganic compounds using the Kohonen algorithm are presented. A brief study is conducted on how the algorithm’s output is affected by various parameter values. The Kohonen algorithm and two other approaches are compared in terms of their peak detection quality. The findings suggest that the Kohonen clustering algorithm can be used for the initial detection of mass spectrum peaks; however, certain peculiarities of the algorithm’s functioning need to be considered.