collaborators

6 papers

eess.SP2025

Quantifying the Generalization Gap in Seizure Detection: A Large-Scale Empirical Benchmark via the SzCORE Challenge

Jonathan Dan, Amirhossein Shahbazinia, Christodoulos Kechris +1

Reliable automatic seizure detection from long-term electroencephalography (EEG) remains an unsolved challenge, as current models often fail to generalize across patients or clinic…

cs.LG2025

Time series saliency maps: explaining models across multiple domains

Christodoulos Kechris, Jonathan Dan, David Atienza

Traditional saliency map methods, popularized in computer vision, highlight individual points (pixels) of the input that contribute the most to the model's output. However, in time…

cs.LG2024

Don't Think It Twice: Exploit Shift Invariance for Efficient Online Streaming Inference of CNNs

Christodoulos Kechris, Jonathan Dan, Jose Miranda +1

Deep learning time-series processing often relies on convolutional neural networks with overlapping windows. This overlap allows the network to produce an output faster than the wi…

cs.LG2024

DC is all you need: describing ReLU from a signal processing standpoint

Christodoulos Kechris, Jonathan Dan, Jose Miranda +1

Non-linear activation functions are crucial in Convolutional Neural Networks. However, until now they have not been well described in the frequency domain. In this work, we study t…

eess.SP2024

Acoustical Features as Knee Health Biomarkers: A Critical Analysis

Christodoulos Kechris, Jerome Thevenot, Tomas Teijeiro +3

Acoustical knee health assessment has long promised an alternative to clinically available medical imaging tools, but this modality has yet to be adopted in medical practice. The f…

eess.SP2024

KID-PPG: Knowledge Informed Deep Learning for Extracting Heart Rate from a Smartwatch

Christodoulos Kechris, Jonathan Dan, Jose Miranda +1

Accurate extraction of heart rate from photoplethysmography (PPG) signals remains challenging due to motion artifacts and signal degradation. Although deep learning methods trained…