Publicaties
Unsupervised Neighborhood Propagation Kernel Layers for Semi-supervised Node Classification KU Leuven
Contact Resistance Sensing for Touch and Squeeze Interactions KU Leuven
This study investigates accessible and sensitive electrode solutions for detecting touches and squeezes on soft interfaces based on commercially available conductive polyurethane foam. Various electrode materials and configurations are explored, and for electrodes made of conductive threads, the static and dynamic electrical behaviors are studied in depth. In contrast to existing approaches that aim to minimize or stabilize contact resistance, ...
Squeezable Interface for Emotion Regulation in Work Environments KU Leuven
Squeezing objects has been proven to be effective in helping people release negative emotions. This work-in-progress study revolves around the design and development of a proof-of-concept system to facilitate conversations on how to design squeezable interfaces for emotion regulation in the workplace. In this paper, we describe the design and development of EmoSkweezee, an interactive desktop wallpaper controlled by a squeezable ball to support ...
Compressing Features for Learning With Noisy Labels KU Leuven
Supervised learning can be viewed as distilling relevant information from input data into feature representations. This process becomes difficult when supervision is noisy as the distilled information might not be relevant. In fact, recent research shows that networks can easily overfit all labels including those that are corrupted, and hence can hardly generalize to clean datasets. In this article, we focus on the problem of learning with noisy ...
Deep kernel principal component analysis for multi-level feature learning KU Leuven
Principal Component Analysis (PCA) and its nonlinear extension Kernel PCA (KPCA) are widely used across science and industry for data analysis and dimensionality reduction. Modern deep learning tools have achieved great empirical success, but a framework for deep principal component analysis is still lacking. Here we develop a deep kernel PCA methodology (DKPCA) to extract multiple levels of the most informative components of the data. Our ...
CoRe-Sleep: A Multimodal Fusion Framework for Time Series Robust to Imperfect Modalities. KU Leuven
Sleep abnormalities can have severe health consequences. Automated sleep staging, i.e. labelling the sequence of sleep stages from the patient's physiological recordings, could simplify the diagnostic process. Previous work on automated sleep staging has achieved great results, mainly relying on the EEG signal. However, often multiple sources of information are available beyond EEG. This can be particularly beneficial when the EEG recordings are ...