Showing 2024Show all
3 papers · 1 filter
eess.SP2024
An Efficient and Flexible Deep Learning Method for Signal Delineation via Keypoints Estimation
Adrian Atienza, Jakob Bardram, Sadasivan Puthusserypady
Deep Learning (DL) methods have been used for electrocardiogram (ECG) processing in a wide variety of tasks, demonstrating good performance compared with traditional signal process…
cs.LG2024
Contrastive Learning Is Not Optimal for Quasiperiodic Time Series
Adrian Atienza, Jakob Bardram, Sadasivan Puthusserypady
Despite recent advancements in Self-Supervised Learning (SSL) for time series analysis, a noticeable gap persists between the anticipated achievements and actual performance. While…
eess.SP2024
NERULA: A Dual-Pathway Self-Supervised Learning Framework for Electrocardiogram Signal Analysis
Gouthamaan Manimaran, Sadasivan Puthusserypady, Helena Domínguez +2
Electrocardiogram (ECG) signals are critical for diagnosing heart conditions and capturing detailed cardiac patterns. As wearable single-lead ECG devices become more common, effici…