AI & ML
ENACT-Heart -- ENsemble-based Assessment Using CNN and Transformer on Heart Sounds
arXiv cs.SD0 views
arXiv:2502.16914v2 Announce Type: replace Abstract: ENACT-Heart is a two-branch ensemble for heart-sound classification. A Vision Transformer (ViT) processes spectrogram images, while a convolutional neural network (CNN) processes visualizations of waveforms and spectral centroids derived from the same recordings. The branch predictions are combined by a weighted average with fixed, input-independent weights. On the PASCAL heart-sound dataset, the ensemble achieved an accuracy of 97.52%, compared with 93.88% for the ViT and 95.45% for the CNN. The ensemble achieved a macro-F1 of 0.94 and recall of 0.74 for extra heart sounds. On this dataset, late fusion improved accuracy and macro-F1 relative to both individual branches.
Source：https://arxiv.org/abs/2502.16914PreviousCRESiST: Self-Enhancing Explorative Policy Learning for Simultaneous Speech TranslationNextSame Words, Different Judgments: How Preferences Vary Across Modalities
Related posts
Rate-Fidelity Control for Wide-Area Quantum Links
0arXiv cs.NI
Who Needs DRAM? We Have Fiber
0arXiv cs.NI
The Multipath Reliable Connection (MRC) Transport
0arXiv cs.NI
From Network Experience to Subscriber Retention: An Explainable AI Framework for Mobile Operators
0arXiv cs.NI
Spatial Path Superposition: A No-Cloning Perspective on MIMO-Inspired Spatial Diversity
0arXiv cs.NI
Optimization of Joint Beamforming in RIS-aided Multi-carrier and Multi-user MIMO Systems
0arXiv cs.NI