1. IEEE Signal Processing Magazine
2. Signal Processing Digital Library*
3. Inside Signal Processing Newsletter
4. SPS Resource Center
5. Career advancement & recognition
6. Discounts on conferences and publications
7. Professional networking
8. Communities for students, young professionals, and women
9. Volunteer opportunities
10. Coming soon! PDH/CEU credits
Click here to learn more.
Researchers in an almost endless number of fields are embracing artificial intelligence (AI) and machine learning (ML) to develop tools and systems that can predict and adapt to a wide range of changing situations, optimize system performance, and intelligently filter signals. In areas as diverse as firefighter protection, solar power optimization, and exoplanet discovery, researchers are turning to AI, ML, and signal processing to help them achieve breakthroughs that were unimaginable only a few years ago.
Flashover is every firefighter’s biggest enemy—and worst nightmare. That’s because structure fires can turn from scary to lethal in an instant with little, if any, advance warning. Looking to enhance firefighter safety, researchers at the U.S. National Institute of Standards and Technology (NIST) have developed the Prediction Model for Flashover (P-Flash), an AI/ML-powered technology designed to predict and warn firefighters that a flashover may be imminent.
Wai Cheong Tam, a NIST mechanical engineer and P-Flash’s lead developer, describes the tool as an AI-driven, ML learning-based model that’s designed to predict flashover conditions inside a multicompartment building structure. A flashover occurs the instant a structure fire transitions from individual objects burning inside a room to the ignition of all combustible objects and surfaces. A typical indication that a flashover may be imminent is upper-compartment temperatures exceeding 600 °C.
P-Flash is designed to work in real-world situations. The model uses temperature signals transmitted by conventional building heat detectors to tell firefighters which rooms in a structure have already flashed over or will likely reach a flashover state within the next 60 s. “The model is extremely efficient, and it can provide a flashover-state prediction faster than the 1-Hz temperature sampling frequency,” Tam says.