This AI could save a firefighter's life
- Reference: 1622719514
- News link: https://www.theregister.co.uk/2021/06/03/ai_firefighter_app/
- Source link:
Furniture and other stuff that's made out of combustible materials can, in the heat of a fire, suddenly erupt into balls of flames that spread quickly across a closed space, such as a room or floor of a building. These incidents, known as flashovers, can break windows and knock down walls, and are one of the most dangerous risks for firefighters.
Researchers led by the US government's NIST are trying to develop technology capable of alerting firefighters to flashovers before they happen. At the heart of the tech is a neural network trained to predict these explosions from the building's temperature sensors. And yes, it's supposed to be a little more sophisticated than an algorithm that just raises the alarm when the temperature goes over a certain level as these situations are usually more complex than that.
[1]
“I don't think the fire service has many tools technology-wise that predict flashover at the scene,” [2]said NIST researcher Christopher Brown, who was not directly involved with the research and is a volunteer firefighter.
[3]
[4]
“Our biggest tool is just observation, and that can be very deceiving. Things look one way on the outside, and when you get inside, it could be quite different.”
[5]Apple sued in nightmare case involving teen wrongly accused of shoplifting, driver's permit used by impostor, and unreliable facial-rec tech
[6]America to get world's 'most powerful' AI supercomputer to create the most detailed 3D map of the universe yet
[7]Insurance startup backtracks on running videos of claimants through AI lie detector
[8]Amazon continues its ban on allowing police to use its facial-recognition software
The team created computer simulations of fires to not only teach the neural net to predict an imminent flashover but also evaluate its abilities, generating 4,033 training examples, and 504 test cases. The system, nicknamed P-Flash, was at least 80 per cent accurate with these simulations, according to a paper detailing the research that was [9]published in the Proceedings of the AAAI Conference on Artificial Intelligence. Most of the errors were false positives, the researchers said.
However, the accuracy dropped to as low as 25 per cent when the algorithm was given temperature sensor data taken from real fires in 13 experiments conducted by the UL Firefighter Safety Research Institute, depending on what room the fire started in.
P-Flash was better at predicting flashovers 30 seconds in advance in areas that were more open, such as kitchens and living rooms, and it struggled with smaller spaces, such as bedrooms. Temperature readings in flashovers in confined areas shoot up more quickly. Since P-Flash wasn’t trained on data that fluctuated as wildly, its performance was less precise in those situations.
Our ability to accurately simulate fire conditions in buildings places a limit on model accuracy in predicting real fires
“Our ability to accurately simulate fire conditions in buildings places a limit on model accuracy in predicting real fires,” Wai Cheong Tam, a co-author of the paper and a NIST mechanical engineer, told The Register . “Improvement in fire models would help [improve the model].”
To get their model tested and working in real-world conditions, the team has to figure out a way to gather data in real time from a building's heat sensors and feed that information into devices running the machine-learning software. Such a device would need to be able to make predictions on the fly, and alert firefighters on the scene.
[10]
“The exact mechanism is not decided,” Thomas Cleary, a chemical engineer at NIST and a co-author of the study, told us. “The fire service will ultimately decide how to use this information. One could imagine a head-up display with various data streams.”
“In the next year we are planning to conduct experiments to demonstrate and test the algorithm [in real-time] in building fire tests with heat detectors,” he added. ®
Get our [11]Tech Resources
[1] https://pubads.g.doubleclick.net/gampad/jump?co=1&iu=/6978/reg_software/aiml&sz=300x50%7C300x100%7C300x250%7C300x251%7C300x252%7C300x600%7C300x601&tile=2&c=2YLj8nT27JFrQLS7nY5u4uQAAAJA&t=ct%3Dns%26unitnum%3D2%26raptor%3Dcondor%26pos%3Dtop%26test%3D0
[2] https://www.nist.gov/news-events/news/2021/06/how-ai-could-alert-firefighters-imminent-danger
[3] https://pubads.g.doubleclick.net/gampad/jump?co=1&iu=/6978/reg_software/aiml&sz=300x50%7C300x100%7C300x250%7C300x251%7C300x252%7C300x600%7C300x601&tile=4&c=44YLj8nT27JFrQLS7nY5u4uQAAAJA&t=ct%3Dns%26unitnum%3D4%26raptor%3Dfalcon%26pos%3Dmid%26test%3D0
[4] https://pubads.g.doubleclick.net/gampad/jump?co=1&iu=/6978/reg_software/aiml&sz=300x50%7C300x100%7C300x250%7C300x251%7C300x252%7C300x600%7C300x601&tile=3&c=33YLj8nT27JFrQLS7nY5u4uQAAAJA&t=ct%3Dns%26unitnum%3D3%26raptor%3Deagle%26pos%3Dmid%26test%3D0
[5] https://www.theregister.com/2021/05/29/apple_sis_lawsuit/
[6] https://www.theregister.com/2021/05/27/most_powerful_ai/
[7] https://www.theregister.com/2021/05/26/ai_insurance_lemonade/
[8] https://www.theregister.com/2021/05/24/in_brief_ai/
[9] https://ojs.aaai.org/index.php/AAAI/article/view/17736
[10] https://pubads.g.doubleclick.net/gampad/jump?co=1&iu=/6978/reg_software/aiml&sz=300x50%7C300x100%7C300x250%7C300x251%7C300x252%7C300x600%7C300x601&tile=4&c=44YLj8nT27JFrQLS7nY5u4uQAAAJA&t=ct%3Dns%26unitnum%3D4%26raptor%3Dfalcon%26pos%3Dmid%26test%3D0
[11] https://whitepapers.theregister.com/
Re: The eternal problem with thermodynamics
You are probably thinking of the n+1th Law of Thermodynamics; which states that for any energy calculation in which simplifying assumptions have been made, there will be a scientist questioning those simplifying assumptions.
However, the accuracy dropped to as low as 25 per cent when the algorithm was given temperature sensor data taken from real fires in 13 experiments
What accuracy do the actual Fire Brigade putting the fire out have?
Most of the time they put out 100% of all fires but the most significant factor is the ability to get to the fire quickly. Research like this is good but maybe it will work or maybe not, it will be a while before we know. A better solution might be to create a fire risk monitoring system that could be installed in buildings and accessed when the Fire Brigade arrives at the site?
Meanwhile, in Other Live Operational Virtual Environments ...... Applications in the Discovery.
Most of the errors were false positives, the researchers said.
Is that fail-safe in action providing future possibilities to be aware of ‽ .
Such probably creates valuable hindsight and fabulous fabless foresight ....... in Great AI Sees ..... NEUKlearer HyperRadioProACTive ProgramMING ...... Sourcing Almighty Mined IntelAIgent Networking Games for Work, REST and Play.
There a lot going on in NeoGeoPolitical Spheres which directly impacts each and every one of you.
The Very Best of it is so Good it is Able to be Real Bad and Perform Virtual Miracles Fantastically Well.
And to tell y'all the truth, such is impossible to resist ..... and why ever anything sane would fight against it would be answered with a diagnosis of certifiably mad and subject to depressing fits of unwarranted badness.
Is that Symptomatic of Extreme Manic Depression ? In AI, HyperRadioProACTive IT Servering and Servicing?
Simulation accuracy
This shows an example of how little match there is between many simulations and reality. Having written a number of simulators for various parts of my academic research (a long time ago) I could tweak parameters until there was a good match between the simulator and previous observations under known conditions. However, take one step outside the boundary of those known conditions and I could guarantee the simulator would be useless.
Climate model simulations are the obvious exception to this. They have perfect predictive abilities for up to a century ahead.
It's all well and good, but when you have people using illegal materials - or materials rated incorrectly - all of this goes out of the window.
It'd be great if we could trust people to do their jobs, from the people living/working there through to the people selling the materials to the builders, but at some point in the chain the ball is dropped - or something is changed for "value engineering" - that starts hacking away at the trust you can have in a location.
The eternal problem with thermodynamics
I'm not by any stretch a physicist, but I've often read that if you think you understand thermodynamics, you're wrong.
Anything that can help those brave firefighters is a good thing in my book. I hope this will pan out and become reliable.
People who put their lives in harm's way to go save other people deserve every bit of help they can get.