Clustering of Non-stationary Time Series
M. A. Kalmykov · 2024
This article is devoted to the study of clustering methods for non-stationary time series containing human pulse data. The paper considers K-Means, DBSCAN, Agglomerative Clustering, and Random Forest methods for clustering such time series. This type of data is characterized by changing statistical characteristics over time and is of great importance in medical analysis. The main focus is on investigating the effectiveness of these methods in practice and analyzing their applicability in medical diagnostics. The obtained results are important for the development of methods for analyzing medical data and forecasting based on human pulse data.