U.S. flag

An official website of the United States government

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you’ve safely connected to the .gov website. Share sensitive information only on official, secure websites.

Search Publications by: Michael Paul Majurski (Fed)

Search Title, Abstract, Conference, Citation, Keyword or Author
Displaying 1 - 25 of 52

Detection limits of AI-based SEM dimensional metrology

March 14, 2025
Author(s)
Peter Bajcsy, Brycie Wiseman, Michael Paul Majurski, Andras Vladar
The speed of in-line scanning electron microscope (SEM) measurements of linewidth, contact hole, and overlay is critically important for identifying the measurement area and generating indispensable process control information. Sample charging and damage

Measuring Dimensionality of Cell-Scaffold Contacts of Primary Human Bone Marrow Stromal Cells Cultured on Electrospun Fiber Scaffolds

January 1, 2023
Author(s)
Carl Simon Jr., Peter Bajcsy, Joe Chalfoun, Michael Paul Majurski, Mary C. Brady, Mylene Simon, Nathan Hotaling, Nick Schaub, Allison Horenberg, Piotr Szczypinski, Dongbo Wang, Veronica DeFelice, Soweon Yoon, Stephanie Florczyk
The properties and structure of the cellular microenvironment can influence cell behavior. Sites of cell adhesion to the extracellular matrix (ECM) initiate intracellular signaling that direct cell functions such as proliferation, differentiation and

Characterization of AI Model Configurations For Model Reuse

October 24, 2022
Author(s)
Peter Bajcsy, Daniel Gao, Michael Paul Majurski, Thomas Cleveland, Manuel Carrasco, Michael Buschmann, Walid Keyrouz
With the widespread creation of artificial intelligence (AI) models in biosciences, bio-medical researchers are reusing trained AI models from other applications. This work is motivated by the need to characterize trained AI models for reuse based on

Exact Tile-Based Segmentation Inference for Images Larger than GPU Memory

June 3, 2021
Author(s)
Michael P. Majurski, Peter Bajcsy
We address the problem of performing exact (tiling-error free) out-of-core semantic segmentation inference of arbitrarily large images using fully convolutional neural networks (FCN). FCN models have the property that once a model is trained, it can be

Baseline Pruning-Based Approach to Trojan Detection in Neural Networks

May 7, 2021
Author(s)
Peter Bajcsy, Michael Paul Majurski
This paper addresses the problem of detecting trojans in neural networks (NNs) by analyzing how NN accuracy responds to systematic pruning. This study leverages the NN models generated for the TrojAI challenges. Our pruning-based approach (1) detects any

Designing Trojan Detectors in Neural Networks Using Interactive Simulations

February 20, 2021
Author(s)
Peter Bajcsy, Nicholas J. Schaub, Michael P. Majurski
This paper addresses the problem of designing trojan detectors in neural networks (NNs) using interactive simulations. Trojans in NNs are defined as triggers in inputs that cause misclassification of such inputs into a class (or classes) unintended by the

Trojan Detection Evaluation: Finding Hidden Behavior in AI Models

October 10, 2020
Author(s)
Michael Paul Majurski, Derek Juba, Timothy Blattner, Peter Bajcsy, Walid Keyrouz
Neural Networks are trained on data, learn relationships in that data, and then are deployed to the world to operate on new data. For example, a traffic sign classification AI can differentiate stop signs and speed limit signs. One potential problem is

Detection of Dense, Overlapping, Geometric Objects

July 1, 2020
Author(s)
Adele P. Peskin, Boris Wilthan, Michael P. Majurski
Using a unique data collection, we are able to study the detection of dense geometric objects in image data where object density, clarity, and size vary. The data is a large set of black and white images of scatterplots, taken from journals reporting

Approaches to Training Multi-Class Semantic Image Segmentation of Damage in Concrete

May 14, 2020
Author(s)
Peter Bajcsy, Steven B. Feldman, Michael P. Majurski, Kenneth A. Snyder, Mary C. Brady
This paper addresses the problem of creating a large quantity of high-quality training image segmentation masks from scanning electron microscopy (SEM) images of concrete samples that exhibit progressive amounts of degradation resulting from alkali-silica

Summary: Workshop on Machine Learning for Optical Communication Systems

March 26, 2020
Author(s)
Joshua A. Gordon, Abdella Battou, Michael P. Majurski, Dan Kilper, Uiara Celine, Massimo Tonatore, Joao Pedro, Jesse Simsarian, Jim Westdorp, Darko Zibar
Optical communication systems are expected to find use in new applications that require more intelligent and automated functionality. Optical networks are needed to address the high speeds and low latency of 5G wireless networks. The analog nature of