Transformer-based 1D CNN with MFCC features classifies pediatric heart sounds at 93.69 percent accuracy on 5-second segments, identifying minimum effective length and RMSSD/ZCR quality threshold of 0.4.
๐เฏ เฏเฏ(๐) =๐๐ แเท ๐(๐) เฏเฌฟเฌต เฏเญเฌด โ๐ปเฏ (๐)แ , 0 โค๐ โค ๐ (12) where ๐(๐) is the power spectrum and ๐ปเฏ (๐) is the filter bank, and ๐ is the number of filter banks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2024 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Classification of Short Segment Pediatric Heart Sounds Based on a Transformer-Based Convolutional Neural Network
Transformer-based 1D CNN with MFCC features classifies pediatric heart sounds at 93.69 percent accuracy on 5-second segments, identifying minimum effective length and RMSSD/ZCR quality threshold of 0.4.