Search Publications

Displaying 51 - 59 of 59

Evaluating Multiple Video Understanding and Retrieval Tasks at TRECVID 2021

June 15, 2022

Author(s)

George Awad, Asad Butt, Keith Curtis, Jonathan G. Fiscus, Afzal A. Godil, Yooyoung Lee, Andrew Delgado, Eliot Godard, Baptiste Chocot, Lukas Diduch, Jeffrey Liu, Yvette Graham, Gareth Jones, Georges Quenot

A Fundamental Assessment of the Concept of Mean Beam Length for Application for Multi-dimensional Non-Gray Radiative Heat Transfer

May 9, 2022

Author(s)

Walter W. Yuen, Wai Cheong Tam

The traditional concept of mean beam length (MBL) and its recommended empirical expression is demonstrated to be inaccurate for general application for the evaluation of multi-dimensional non-gray radiative heat transfer. A new concept, namely Point Mean

Real-time Forecast of Compartment Fire and Flashover based on Deep Learning

April 6, 2022

Author(s)

Tianhang Zhang, Zilong Wang, Ho Yin Wong, Wai Cheong Tam, Xinyan Huang, Fu Xiao

Forecasting building fire development and critical fire events in real-time is of great significance for firefighting and rescue operations. This work proposes an artificial intelligence (AI) system to fast forecast the compartment fire development and

VECTOR: Very Deep Convolutional Autoencoders for Non-Resonant Background Removal in Broadband Coherent Anti-Stokes Raman Scattering

March 14, 2022

Author(s)

Zhengwei Wang, Kevin O'Dwyer, Ryan Muddiman, Tomas Ward, Charles Camp, Bryan Hennelly

Rapid label-free spectroscopy of biological and chemical specimen via molecular vibration through means of Broadband Coherent Anti-Stokes Raman Scattering (B-CARS) could serve as a basis for a robust diagnostic platform for a wide range of applications. A

A Generic Flashover Prediction Model for Residential Buildings Using Graph Neural Network

November 11, 2021

Author(s)

Wai Cheong Tam, Eugene Yujun Fu, Paul A. Reneke, Richard D. Peacock, Thomas Cleary

A generic graph neural network-based model is developed to predict the potential occurrence of flashover for different building structures. The proposed model transforms multivariate temperature data into graph-structure data. Utilizing graph convolution

ANALYZING REMELTING CONDITIONS BASED ON IN-SITU MELT POOL DATA FUSION FOR OVERHANG BUILDING IN POWDER BED FUSION PROCESS

November 1, 2021

Author(s)

Yan Lu, Brandon Lane, Zhuo Yang, Jaehyuk Kim, Yande Ndiaye

Coaxial melt pool monitoring (MPM) images provide in-depth insights into the building process of laser powder bed fusion additive manufacturing. An in-situ MPM image captures the independent melting condition at a specific scanning position. However, it is

Open Media Forensics Challenge (OpenMFC) 2020-2021: Past, Present, and Future

September 29, 2021

Author(s)

Haiying Guan, Yooyoung Lee, Lukas Diduch, Jesse Zhang, Ilia Ghorbanian Bajgiran, Timothee Kheyrkhah, Peter Fontana, Jonathan G. Fiscus

This document describes the online leaderboard public evaluation program, Open Media Forensics Challenge (OpenMFC) 2021-2022. In the report, first, the introduction, objectives, challenges, contributions, and achievements of the evaluation program are

Towards Absolute Viability Measurements for Bacteria

September 12, 2021

Author(s)

Joy Dunkers, Hariharan Iyer, Brynna H. Jones, Charles Camp, Stephan J. Stranick, Nancy Lin

Quantifying viable, vegetative bacteria is a critical measurand in healthcare diagnostics, food safety, and antimicrobial development. Viability determination has traditionally relied on such techniques as plate counting, colorimetric or fluorescent

Comparison of dissimilarity measures for cluster analysis of X-ray diffraction data from combinatorial libraries

February 3, 2017

Author(s)

Aaron Gilad Kusne, Ichiro Takeuchi, Yuma Iwasaki

Machine learning techniques have proven invaluable to manage the ever growing volume of materials research data produced as developments continue in high-throughput materials simulation, fabrication, and characterization. In particular, machine learning