Performance Evaluation of Biomedical Time Series Transformation Methods for Classification Tasks DOI Open Access
Carlos Alejandro Ku-Maldonado, Erik Molino Minero

Revista Mexicana de Ingeniería Biomédica, Год журнала: 2023, Номер 44(4), С. 105 - 116

Опубликована: Авг. 17, 2023

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 extracting pertinent information that can significantly enhance classification performance. Among these are those translate into different domains. This study investigates three distinct transformation approaches for addressing challenges within biomedical data. first method involves response vector transformation, while the other two employ image techniques: RandOm Convolutional KErnel Transform (ROCKET), Gramian Angular Fields, and Markov Transition Fields. These were applied five datasets, exploring format configurations ascertain optimal representation technique configuration input, which in turn improves Evaluations conducted on effectiveness conjunction with algorithms. outcomes underscore significance techniques as facilitators enhanced algorithms documented current literature.

Язык: Английский

Performance Evaluation of Biomedical Time Series Transformation Methods for Classification Tasks DOI Open Access
Carlos Alejandro Ku-Maldonado, Erik Molino Minero

Revista Mexicana de Ingeniería Biomédica, Год журнала: 2023, Номер 44(4), С. 105 - 116

Опубликована: Авг. 17, 2023

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 extracting pertinent information that can significantly enhance classification performance. Among these are those translate into different domains. This study investigates three distinct transformation approaches for addressing challenges within biomedical data. first method involves response vector transformation, while the other two employ image techniques: RandOm Convolutional KErnel Transform (ROCKET), Gramian Angular Fields, and Markov Transition Fields. These were applied five datasets, exploring format configurations ascertain optimal representation technique configuration input, which in turn improves Evaluations conducted on effectiveness conjunction with algorithms. outcomes underscore significance techniques as facilitators enhanced algorithms documented current literature.

Язык: Английский

Процитировано

0