MURAL: An Unsupervised Random Forest-Based Embedding for Electronic Health Record Data
Gerasimiuk M, Shung D, Tong A, Stanley A, Schultz M, Ngu J, Laine L, Wolf G, Krishnaswamy S. MURAL: An Unsupervised Random Forest-Based Embedding for Electronic Health Record Data. 2021, 00: 4694-4704. DOI: 10.1109/bigdata52589.2021.9672045.Peer-Reviewed Original ResearchFixing Bias in Reconstruction-based Anomaly Detection with Lipschitz Discriminators
Tong A, Wolf G, Krishnaswamy S. Fixing Bias in Reconstruction-based Anomaly Detection with Lipschitz Discriminators. Journal Of Signal Processing Systems 2021, 94: 229-243. DOI: 10.1007/s11265-021-01715-6.Peer-Reviewed Original ResearchAnomaly detectionTraining dataReconstruction-based anomaly detectionAutoencoder reconstruction errorDeep learning methodsReconstruction-based methodsOriginal data spaceGraph dataLearning methodsData spaceUnseen anomaliesReconstruction errorImproved performanceIrregular graphsTraining setHealth recordsHealth record dataWasserstein distanceLow errorDiscriminatorImagesCIFAR10MNISTUndesirable resultsRecord data