Performance Evaluation of Biomedical Time Series Transformation Methods for Classification Tasks;
Por:
Ku-Maldonado C.A., Molino-Minero-Re E.
Publicada:
1 ene 2023
Categoría:
Biomedical engineering
Resumen:
The extraction of time series features is essential across various fields, yet it remains a challenging endeavor. Therefore, it's crucial to identify appropriate methods capable of extracting pertinent information that can significantly enhance classification performance. Among these methods are those that translate time series into different domains. This study investigates three distinct time series transformation approaches for addressing time series classification challenges within biomedical data. The first method involves a response vector transformation, while the other two employ image transformation techniques: RandOm Convolutional KErnel Transform (ROCKET), Gramian Angular Fields, and Markov Transition Fields. These transformation methods were applied to five biomedical datasets, exploring various format configurations to ascertain the optimal representation technique and configuration for input, which in turn improves classification performance. Evaluations were conducted on the effectiveness of these methods in conjunction with two classification algorithms. The outcomes underscore the significance of these time series transformation techniques as facilitators for enhanced classification algorithms documented in current literature. © 2023 Sociedad Mexicana de Ingenieria Biomedica. All rights reserved.
Filiaciones:
Ku-Maldonado C.A.:
Universidad Nacional Autónoma de México, Yucatán, Mexico
Molino-Minero-Re E.:
Instituto de Investigaciones en Matemáticas Aplicadas y en Sistemas, UNAM, Unidad Académica, Yucatán, Mexico
All Open Access; Bronze Open Access
|