C. H. Antink

Label-Aware Federated Learning Improves ECG Classification in Heterogeneous Hospital Settings

DNN-Based Frequency-Dependent Estimation of Speech, Music, and Noise Power in Acoustic Mixtures for Hearing-Aid Scene Analysis

This work estimates time- and frequency-dependent power proportions by a causal low-complexity Deep Neural Network, from which multiple downstream acoustic scene analysis measures can in principle be derived by simple post-processing.

Multimodal Contrastive Learning with ECG and Echocardiography for Ejection Fraction Estimation

Multimodal pretraining improved frozen DINO models over the uni-modal baseline, but its benefits diminished after fine-tuning, suggesting that encoder initialization and down-stream adaptation were more influential than increasingly complex echocardiographic supervision.