no code implementations • 27 Mar 2024 • Megan A. Witherow, Norou Diawara, Janice Keener, John W. Harrington, Khan M. Iftekharuddin
Results: We identify one candidate ET biomarker (percentage gaze duration to the face while mimicking static 'disgust' expression) and 14 additional DVs of interest for future study, including 4 ET DVs, 5 DVs related to VT AU activation, and 4 DVs related to AU asymmetry in VT. Based on a power analysis, we provide sample size recommendations for future studies.
no code implementations • 12 Mar 2024 • Megan A. Witherow, Crystal Butler, Winston J. Shields, Furkan Ilgin, Norou Diawara, Janice Keener, John W. Harrington, Khan M. Iftekharuddin
To measure subjects' AUs in response to CADyFACE, we propose a novel Beta-guided Correlation and Multi-task Expression learning neural network (BeCoME-Net) for multi-label AU detection.
no code implementations • 28 Jun 2023 • Walia Farzana, Mustafa M Basree, Norou Diawara, Zeina A. Shboul, Sagel Dubey, Marie M Lockhart, Mohamed Hamza, Joshua D. Palmer, Khan M. Iftekharuddin
To our knowledge, this study is the first to investigate the potential of conventional ra-diomics, sophisticated multi-resolution fractal texture features, and different molecular features (MGMT, IDH mutations) as a diagnostic and prognostic tool for prediction of REP from non-REP cases using computational and statistical modeling methods.
no code implementations • 18 Sep 2022 • Megan A. Witherow, Manar D. Samad, Norou Diawara, Haim Y. Bar, Khan M. Iftekharuddin
We propose domain adaptation to concurrently align distributions of adult and child expressions in a shared latent space for robust classification of either domain.
no code implementations • 28 Feb 2022 • Manar D Samad, Sakib Abrar, Norou Diawara
Our extensive analyses involving six tabular data sets, up to 80% missingness, and three missingness types (missing completely at random, missing at random, missing not at random) reveal that ensemble or deep learning within MICE is superior to the baseline MICE (b-MICE), both of which are consistently outperformed by CISCL.