TY - JOUR
T1 - Arrhythmia detection model using modified DenseNet for comprehensible Grad-CAM visualization
AU - Kim, Jin Kook
AU - Jung, Sunghoon
AU - Park, Jinwon
AU - Han, Sung Won
N1 - Funding Information:
This work was supported by Korea University Grant (K1915041, K1920081). This research was also supported by National Research Foundation of Korea (NRF-2019R1F1A1060250).
Publisher Copyright:
© 2021
PY - 2022/3
Y1 - 2022/3
N2 - Diagnosing arrhythmia is difficult, requires significant efforts. Because arrhythmia can be associated with serious diseases, it is important to classify arrhythmia patients with high accuracy, and the basis for the classification model's judgment should be properly demonstrated. Traditional algorithm methods are less accurate, and simply using a high-accuracy image classification deep learning model yields incomprehensible results when the model is visualized with gradient-weighted class activation mapping (Grad-CAM). We want to achieve high-performance deep learning models can also comprehensible visualization. To obtain this, two hypotheses about Grad-CAM were established and the experiment was conducted. As a result, a method that could clearly visualize the response area using Grad-CAM with a higher classification performance of 0.98 accuracy is created.
AB - Diagnosing arrhythmia is difficult, requires significant efforts. Because arrhythmia can be associated with serious diseases, it is important to classify arrhythmia patients with high accuracy, and the basis for the classification model's judgment should be properly demonstrated. Traditional algorithm methods are less accurate, and simply using a high-accuracy image classification deep learning model yields incomprehensible results when the model is visualized with gradient-weighted class activation mapping (Grad-CAM). We want to achieve high-performance deep learning models can also comprehensible visualization. To obtain this, two hypotheses about Grad-CAM were established and the experiment was conducted. As a result, a method that could clearly visualize the response area using Grad-CAM with a higher classification performance of 0.98 accuracy is created.
KW - Arrhythmia classification
KW - Class activation mapping
KW - Convolutional neural network
KW - Electrocardiogram
UR - http://www.scopus.com/inward/record.url?scp=85121129981&partnerID=8YFLogxK
U2 - 10.1016/j.bspc.2021.103408
DO - 10.1016/j.bspc.2021.103408
M3 - Article
AN - SCOPUS:85121129981
VL - 73
JO - Biomedical Signal Processing and Control
JF - Biomedical Signal Processing and Control
SN - 1746-8094
M1 - 103408
ER -