ECG classification using three-level fusion of different feature descriptors

作者：

Highlights：

• Novel combination of hand-crafted and CNN-based features.

• Performing information fusion in feature-level, score-level and decision-level.

• Extracting multi-stage learned features from different layers of a CNN for fusion

• Achieving superior classification results comparing to state-of-the-art.

摘要

•Novel combination of hand-crafted and CNN-based features.•Performing information fusion in feature-level, score-level and decision-level.•Extracting multi-stage learned features from different layers of a CNN for fusion•Achieving superior classification results comparing to state-of-the-art.

论文关键词：Electrocardiogram,Morphological feature,Statistical feature,Ttemporal features,Multi-stage CNN-based features,Convolutional neural networks,Feature-level fusion,Score-level fusion,Decision-level fusion

论文评审过程：Received 16 April 2018, Revised 26 June 2018, Accepted 12 July 2018, Available online 25 July 2018, Version of Record 25 July 2018.

论文官网地址：https://doi.org/10.1016/j.eswa.2018.07.030