NOTICE: Due to a lapse in annual appropriations, most of this website is not being updated. Learn more.
Form submissions will still be accepted but will not receive responses at this time. Sections of this site for programs using non-appropriated funds (such as NVLAP) or those that are excepted from the shutdown (such as CHIPS and NVD) will continue to be updated.
An official website of the United States government
Here’s how you know
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.
Andrew Maizel, Andre Thompson, Benjamin Place, Alix Rodowa, Jessica Reiner, Audrey Tombaugh, Halen Solomon, Brittany Stinger, Michelle Donnelly, Rick Davis
Firefighter turnout gear provides protection from exposure to flame, heat, and liquids, but has also been found to contain numerous per- and polyfluoroalkyl substances (PFAS). Previous examinations of PFAS in firefighter turnout gear have predominantly
This document serves as the documentation for the Fire Data Generator (FD-Gen), an automated tool designed to streamline the creation of multiple Fire Dynamics Simulator (FDS) input files. By employing Monte Carlo methods to sample relevant fire parameters
This paper presents gFlashNet, a generic flashover prediction model, designed to address the limitations of existing models that are restricted to specific residential building layouts. The aim of this research is to improve the scalability and
Wai Cheong Tam, Fan Linhao, Qi Tong, Fang Hongqiang
This present work utilizes an interpretability model to understand and explain the decisions of deep learning models. The use of DeepLIFT is proposed and attributions of a study case are obtained. Benchmarking against two other interpretability models
A multi-input and multi-output (MIMO) machine learning model is developed to simultaneously detect firefighter's thermal risks across a commercial building structure. A total of 2000 numerical experiments with a wide range of fire and ventilation scenarios
Deep learning model has been a viable approach to forecast critical events in fire development. However, prior to its implementation in real-life firefighting, it is imperative to further understand the black box and assess its rationale. In this paper, an
Dillon Dzikowicz, Sankalp Saoji, Wai Cheong Tam, Wendy Brunner, Mary Carey
Background: Cardiovascular events are known to be the leading cause of death among on-duty firefighters. Implementing fitness standards may help reduce the incidence of cardiovascular deaths; however, standards vary between firefighter type and states. We
Eugene Yujun Fu, Wai Cheong Tam, Tianhang Zhang, Xinyan Huang
The lack of information on the fire ground has always been the leading factor in making wrong decisions . Wrong decisions can be made by individual firefighters, their local chiefs, and/or the incident commander. Any wrong decision at any level (scale)
Jiajia Li, Christopher U. Brown, Dillon Dzikowicz, Mary Carey, Wai Cheong Tam, Michael Xuelin Huang
A machine learning-based heart health monitoring model, named H2M, was developed. 24-hour electrocardiogram (ECG) data from 112 professional firefighters was used to train the proposed model. The model used carefully designed multi-layer convolution neural
This paper presents the development of an explainable machine learning based flashover prediction model, named xFlashNet. Synthetic temperature data from more than 17 000 fire cases are used for model development. The effect of missing data due from heat
Wai Cheong Tam, Eugene Yujun Fu, Jiajia Li, Richard D. Peacock, Paul A. Reneke, Thomas Cleary, Grace Ngai, Hong Va Leong, Michael Xuelin Huang
This paper presents the development of an attention based bi-directional gated recurrent unit model, P-Flashv2, for the prediction of potential occurrence of flashover in a traditional 111 m2 single story ranch-style family home. Synthetic temperature data
Christopher U. Brown, Gregory W. Vogl, Wai Cheong Tam
A wireless sensor network was created to measure water-flow rate in a fire hose. An integrated electronic piezoelectric (IEPE) accelerometer was chosen as the sensor to measure the flow rate based on the vibrations generated by water flowing through a fire
This report documents real-time and time-averaged temperature, global and local equivalence ratios, and oxygen, carbon dioxide, and carbon monoxide concentration measurements made at various positions in an isolated 2/5th scale compartment prior to a
Wai Cheong Tam, Eugene Yujun Fu, Jiajia Li, Xinyan Huang, Jian Chen, Michael Xuelin Huang
Rapid fire progression, such as flashover, has been one of the leading causes for firefighter deaths and injuries in residential building environments. Due to long computational time of and the required prior knowledge about the fire scene, existing models
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
Wai Cheong Tam, Jun Wang, Richard D. Peacock, Paul A. Reneke, Eugene Yujun Fu, Thomas Cleary
This report provides additional technical details to an article entitled P-Flash – A Machine Learning-based Model for Flashover Prediction using Recovered Temperature Data. Research was conducted to examine the use of Support Vector Regression (SVR) to
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
Jun Wang, Andy Tam, Youwei Jia, Richard Peacock, Paul A. Reneke, Eugene Yujun Fu, Thomas Cleary
Research was conducted to examine the use of Support Vector Regression (SVR) to build a model to forecast the potential occurrence of flashover in a single-floor, multi-room compartment fire. Synthetic temperature data for heat detectors in different rooms
Andy Tam, Eugene Yujun Fu, Richard Peacock, Paul A. Reneke, Jun Wang, Grace Ngai, Hong Va Leong, Thomas Cleary
Fire fighter fatalities and injuries in the U.S. remain too high and fire fighting too hazardous. Until now, fire fighters rely only on their experience to avoid life-threatening fire events, such as flashover. In this paper, we describe the development of
A wireless sensor network was created to measure water-flow rate in a fire hose. An integrated electronic piezoelectric accelerometer was chosen as the sensor to measure the flow rate based on the vibrations generated by water flowing through a fire hose
Jun Wang, Andy Tam, Paul A. Reneke, Richard Peacock, Thomas Cleary, Eugene Yujun Fu, Grace Ngai, Hong Va Leong
This paper presents a study to examine the potential use of machine learning algorithms to build a model to forecast the likelihood of flashover occurrence for a single-floor multi-room compartment. Synthetic temperature data for heat detectors from
Jun Wang, Youwei Jia, Eugene Yujun Fu, Jiajia Li, Andy Tam
This paper aims to facilitate the use of machine learning to carry out supervised classification/regression tasks for time series data in fire research. Specifically, a feature engineering tool, FAST (Feature extrAction and Selection for Time-series), is
Wai Cheong Tam, Eugene Yujun Fu, Richard D. Peacock, Paul A. Reneke, Jun Wang, Jiajia Li, Thomas G. Cleary
This paper presents a learning-by-synthesis approach to facilitate the utilization of a machine learning paradigm to enhance situational awareness for fire fighting in buildings. An automated Fire Data Generator (FD-Gen) is developed. The overview of FD
Wai Cheong Tam, Eugene Yujun Fu, Amy E. Mensch, Anthony P. Hamins, Christina Yu, Grace Ngai, Hong va Leong
This paper presents a study to examine the potential use of machine learning models to build a real-time detection algorithm for prevention of unattended cooking fires. 16 sets of time- dependent sensor signals were obtained from 60 normal/ignition cooking