User profiles for M. Fiterau
Madalina FiterauAssistant Professor, University of Massachusetts, Amherst Verified email at cs.stanford.edu Cited by 1693 |
Machine learning in human movement biomechanics: Best practices, common pitfalls, and new opportunities
… rate) = n u m b e r o f t r u e p o s i t i v e s n u m b e r o f t r u e … rate) = n u m b e r o f t r u e n
e g a t i v e s n u m b e r o f t r u … value) = n u m b e r o f t r u e p o s i t i v e s n u m b e r o f t r u e …
e g a t i v e s n u m b e r o f t r u … value) = n u m b e r o f t r u e p o s i t i v e s n u m b e r o f t r u e …
Deep neural decision forests
P Kontschieder, M Fiterau… - Proceedings of the …, 2015 - openaccess.thecvf.com
… node m … m. Detailed derivations of (9) can be found in Section 2 of the supplementary
document. Moreover, in Section 4 we describe how Am can be efficiently computed for all nodes m …
document. Moreover, in Section 4 we describe how Am can be efficiently computed for all nodes m …
[HTML][HTML] Weakly supervised classification of aortic valve malformations using unlabeled cardiac MRI sequences
… Patient MRIs are represented as a collection of m frames X = {x 1 , …, x m }, where each
frame x i is a 32 × 32 image with MAG, CINE, and VENC encodings mapped to color channels. …
frame x i is a 32 × 32 image with MAG, CINE, and VENC encodings mapped to color channels. …
Pedestrian detection in thermal images using saliency maps
…, D Chakraborty, M Fiterau… - Proceedings of the …, 2019 - openaccess.thecvf.com
Thermal images are mainly used to detect the presence of people at night or in bad lighting
conditions, but perform poorly at daytime. To solve this problem, most state-of-the-art …
conditions, but perform poorly at daytime. To solve this problem, most state-of-the-art …
Using supervised machine learning to classify real alerts and artifact in online multisignal vital sign monitoring data
…, D Wang, M Fiterau, M Guillame-Bert… - Critical care …, 2016 - journals.lww.com
Objective: The use of machine-learning algorithms to classify alerts as real or artifacts in
online noninvasive vital sign data streams to reduce alarm fatigue and missed true instability. …
online noninvasive vital sign data streams to reduce alarm fatigue and missed true instability. …
Trends and focus of machine learning applications for health research
Importance The use of machine learning applications related to health is rapidly increasing
and may have the potential to profoundly affect the field of health care. Objective To analyze …
and may have the potential to profoundly affect the field of health care. Objective To analyze …
[PDF][PDF] Predicting in-hospital mortality by combining clinical notes with time-series data
In intensive care units (ICUs), patient health is monitored through (1) continuous vital signals
from various medical devices, and (2) clinical notes consisting of opinions and summaries …
from various medical devices, and (2) clinical notes consisting of opinions and summaries …
Constrained offline policy optimization
In this work we introduce Constrained Offline Policy Optimization (COPO), an offline policy
optimization algorithm for learning in MDPs with cost constraints. COPO is built upon a novel …
optimization algorithm for learning in MDPs with cost constraints. COPO is built upon a novel …
Alzheimer's disease brain mri classification: Challenges and insights
In recent years, many papers have reported state-of-the-art performance on Alzheimer's
Disease classification with MRI scans from the Alzheimer's Disease Neuroimaging Initiative (…
Disease classification with MRI scans from the Alzheimer's Disease Neuroimaging Initiative (…
Direct inference of effect of treatment (diet) for a cookieless world
… Let us assume that this number is M. Note that with high probability (whp) M > Nε, as anytime
a user loses a cookie, there is a chance to get another history; and if a user doesn’t lose a …
a user loses a cookie, there is a chance to get another history; and if a user doesn’t lose a …