Your browser doesn't support javascript.
loading
Tunable Q-factor wavelet transform based identification of diabetic patients using ECG signals.
Jain, Anuja; Verma, Anurag; Verma, Amit Kumar; Bajaj, Varun.
Afiliação
  • Jain A; Teerthanker Mahaveer University, Moradabad, UP, India.
  • Verma A; Teerthanker Mahaveer University, Moradabad, UP, India.
  • Verma AK; Mahatama Jyotiba Phule Rohilkhand University, Bareilly, UP, India.
  • Bajaj V; PDPM Indian Institute of Information Technology, Design & Manufacturing (IIITDM), Jabalpur, India.
Article em En | MEDLINE | ID: mdl-38635476
ABSTRACT
Diabetes is a chronic health condition that is characterized by increased levels of glucose (sugar) in the blood. It can have harmful effects on different parts of the body, such as the retina of the eyes, skin, nervous system, kidneys, and heart. Diabetes affects the structure of electrocardiogram (ECG) impulses by causing cardiovascular autonomic dysfunction. Multi-resolution analysis of the input ECG signal is utilized in this paper to develop a machine learning-based system for the automated detection of diabetic patients. In the first step, the input ECG signal is decomposed into sub-bands utilizing the tunable Q-factor wavelet transform (TQWT) technique. In the second step, four entropy-based characteristics are evaluated from each SB and elected using the K-W test method. To develop an automatic diabetes detection system, selected features are given as input with 10-fold validation to a SVM classifier using various kernel functions. The 3rd sub-band of TQWT with the Coarse Gaussian kernel function kernel of the SVM classifier yields a classification accuracy of 91.5%. In the same dataset, the comparative analysis demonstrates that the proposed method outperforms other existing methods.
Palavras-chave

Texto completo: 1 Base de dados: MEDLINE Idioma: En Ano de publicação: 2024 Tipo de documento: Article

Texto completo: 1 Base de dados: MEDLINE Idioma: En Ano de publicação: 2024 Tipo de documento: Article