Variable step dynamic threshold local binary pattern for classification of atrial fibrillation

作者：

Highlights：

• Tested on MIT-BIH Atrial Fibrillation Database and MIT-BIH Arrhythmia Database.

• One of the best published results for detection of atrial fibrillation from ECG signal.

• Use only addition, division and compare operations for feature extraction.

• Does not need filtering, wavelet transform, up/down-sampling, or beat detection.

摘要

•Tested on MIT-BIH Atrial Fibrillation Database and MIT-BIH Arrhythmia Database.•One of the best published results for detection of atrial fibrillation from ECG signal.•Use only addition, division and compare operations for feature extraction.•Does not need filtering, wavelet transform, up/down-sampling, or beat detection.

论文关键词：Local binary pattern,Dynamic threshold,Variable step,Atrial fibrillation,AFDB,MITDB

论文评审过程：Received 31 July 2019, Revised 7 July 2020, Accepted 13 July 2020, Available online 15 July 2020, Version of Record 24 July 2020.

论文官网地址：https://doi.org/10.1016/j.artmed.2020.101932