A new study developed a snore-source classification model that uses STFT spectrograms, pretrained CNN features, and an L2-regularized SVM to identify where snoring originates in the upper airway.

Severe class imbalance: failures (pos) are ~1.7% of the data. Heavy missing values (the raw data uses na markers). Train / validation / test split — the training data is split 80/20 (stratified) ...