This AI could save a firefighter's life

Computer scientists have built an algorithm to predict deadly explosions within blazes before they occur in the hope it can one day serve as a warning system for firefighters tackling burning buildings. Furniture and other stuff that's made out of combustible materials can, in the heat of a fire, suddenly erupt into balls of …

[Pascal Monett]

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.

[JulieM]

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.

[Korev]

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?

[Version 1.0]

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?

[amanfromMars 1]

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?

[IanRS]

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.

[wolfetone]

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.

[Anonymous Coward]

Bad training yields bad results

To paraphrase Mike Tyson “Everyone has a simulation ’till they get punched in the mouth.”

Training an AI on simulated data enables it to predict the simulated world, not the real one. What is sad about this extremely worthwhile effort is that real data for training the AI was available. Fire departments train firefighters in specially constructed buildings with real fires involving real furnishings, appliances, etc. This real world data should have been used as input rather than just as verification.

[katrinab]

Do real-world buildings have these heat sensors that can be used to provide the required information? And do they work outside normal room-temperature ranges?