CardioXNet: A Novel Lightweight Deep Learning Framework for Cardiovascular Disease Classification Using Heart Sound Recordings
Citations
20 citations
16 citations
14 citations
14 citations
13 citations
References
72,897 citations
"CardioXNet: A Novel Lightweight Dee..." refers background in this paper
...Here, sigmoid and tanh are the activation functions which map the non-linearity of the features [46]....
[...]
30,843 citations
"CardioXNet: A Novel Lightweight Dee..." refers background in this paper
...Batch normalization layers helps to stabilize and speed up the training process [49] while abstract feature maps generated from the initial convolutional layers are then passed to the squeeze-expansion layers which results in lowering of parameter count by manifolds(see Figure 6)....
[...]
17,184 citations
9,381 citations
8,807 citations
"CardioXNet: A Novel Lightweight Dee..." refers background in this paper
...A handful of cross-domain studies have investigated the issue and introduced a few advanced strategies such as lightweight networks [29], [30], weight quantization [31] and low precision computation techniques [32]....
[...]