DivePro.me online Decompression Planner

[Alexey Vlasov]

DiveProMe is a decompression planner aimed at calculating a Open Circuit profile and gas consumption for technical and recreational dives. DiveProMe works in any browser for any device compatible with javaScript and HTML5. DiveProMe is an open source software based on machine learning.

The point is to get the safest profile using machine learning. The idea of this method is to analyze most of the popular software products with same parameters (GF, Last Stop, Mix Type etc.) and pick the safest profile. By analyzing and comparing data from different software products in order to select the safest plan we minimize the probability of an error in a particular software. In the process of analyzing DiveProMe finds errors in profiles (zero ascent time, zero stop time, zero time to surface, value converting errors, zero deco stop time, etc.) and ignores these profiles.

There is still a chance that all the software products might have the same error in the same plan which will result in all the data being wrong. But the probability of suchlike result is severely diminished by comparing data from similar plans. If DiveProMe indicates a certain “leap” of errors, it will use calculations from similar plans and get the average values using the safest method.

User part of DiveProMe contains about 2,500 strings of code. It is not that many and only shows data calculated previously using machine learning. Which makes the probability of an error in the code and your plan even less.

Surely, the plan DiveProMe will give you won't be the most effective, but it will definitely be several hundred times safer than a plan calculated with a separate software.

DiveProMe is a donation based freeware with no intention of commercial use. However there are certain restrictions to the use of this product according to CDDL (Common Development and Distribution License). For any detail feel free to contact the developer: all3862000@mail.ru

If you have any questions or you have found any errors please contact the developer all3862000@mail.ru

Direct link to Planner: divepro.me
Direct link to Facebook: divepro.me Decompression Planner Software

Enjoy!

 

[Patoux01]

I don't get it. What data are you using for the training and testing sets?

I understand it as:
- we run the different profiles (depth-time) in the different softwares and algos (various values of GF etc) we found
- threw in some machine learning and see what comes out

Is this what has been done?

 

[doctormike]

View attachment 414339
Surely, the plan DiveProMe will give you won't be the most effective, but it will definitely be several hundred times safer than a plan calculated with a separate software.

A sentence like this makes me doubtful about the whole project.

Is "machine learning" just a buzzword? Or does it actually mean something? To me, machine learning would mean that the system has access to massive data sets of real world dive results to correlate profiles with injuries.

Assuming that the site gets one profile from one "software product" (do you mean algorithm?), and another profile from another one, how does it determine which is safer? Isn't that why decompression science still has controversies with competing theories and algorithms, despite decades of research by very smart people?

 

[stuartv]

Surely, the plan DiveProMe will give you won't be the most effective, but it will definitely be several hundred times safer than a plan calculated with a separate software.

Right. Because a plan from a committee is always several hundred times better than a plan from a single expert that truly knows what he or she is doing.

 

[tursiops]

Right. Because a plan from a committee is always several hundred times better than a plan from a single expert that truly knows what he or she is doing.

Isn't this the theory behind crowd-sourcing? Get enough people providing input and the right answer is bound to be in there somewhere...

Reminds me of an old United Technologies full-page advertisement in a newspaper, many years ago: "If 50,000 people believe in a dumb idea.....it is still a dumb idea."

 

[Patoux01]

Right. Because a plan from a committee is always several hundred times better than a plan from a single expert that truly knows what he or she is doing.

Committees of experts tend to get to the correct answer though.

 

[stuartv]

Committees of experts tend to get to the correct answer though.

What about a committee where you don't actually know who any of the members are?

 

[northernone]

I appreciate the layout, graphics and amount of data presented.

Before I would use it, I need to understand how it uses the various algorithms. I'd be conserved at combining various models without hard research justifying it.

Well done,
Cameron

 

[AlexL]

Get enough people providing input and the right answer is bound to be in there somewhere..."

foul on defensive side during play, logical fallacy, Argument to moderation / fallacy of the golden mean, 10 yard penalty, restart the clock.

as for the OP,
1) online only dive plans are worthless when you're not online. y'know, like on a boat?
2) no way to save / link to a plan
3) there's a very large amount of 'black boxing' going on here. 'mixing' various decompression algorithms does not result in a 'better' plan.

 

[Patoux01]

@stuartv , that's not what you said. In this case, the experts are apparently deco algorithms. Maybe wait for confirmation on that before making claims?