The Real Deal Behind the Artificial Appeal: Inferential Utility of Tabular Synthetic Data

1 code implementation • 13 Dec 2023 • Alexander Decruyenaere, Heidelinde Dehaene, Paloma Rabaey, Christiaan Polet, Johan Decruyenaere, Stijn Vansteelandt, Thomas Demeester

Recent advances in generative models facilitate the creation of synthetic data to be made available for research in privacy-sensitive contexts.

Overly Optimistic Prediction Results on Imbalanced Data: a Case Study of Flaws and Benefits when Applying Over-sampling

2 code implementations • 15 Jan 2020 • Gilles Vandewiele, Isabelle Dehaene, György Kovács, Lucas Sterckx, Olivier Janssens, Femke Ongenae, Femke De Backere, Filip De Turck, Kristien Roelens, Johan Decruyenaere, Sofie Van Hoecke, Thomas Demeester

Information extracted from electrohysterography recordings could potentially prove to be an interesting additional source of information to estimate the risk on preterm birth.

Positive blood culture detection in time series data using a BiLSTM network

no code implementations • 3 Dec 2016 • Leen De Baets, Joeri Ruyssinck, Thomas Peiffer, Johan Decruyenaere, Filip De Turck, Femke Ongenae, Tom Dhaene

The presence of bacteria or fungi in the bloodstream of patients is abnormal and can lead to life-threatening conditions.

Cultural Vocal Bursts Intensity Prediction Time Series +1