News for hackers. Stuff that matters.
Re:Finding UX in the Trash by madeofpalk on Sunday September 17, 2017 @09:53AM (#15269592)
> perhaps using machine learning.

What? You can't just say 'machine learning' about every (perceived) problem you hear.

Re:Finding UX in the Trash by jstimpfle on Sunday September 17, 2017 @10:03AM (#15269641)
To be honest, this sounds like a perfect application for ML. Especially if you look at how people separate their trash. And it might well be how it's actually done (i don't know anything about recycling)

It might be a good idea to separate paper/dry stuff from wet stuff and glass from the start, though. Just the way it's done in many countries.

(I heard that in one of the poorer regions of the city I live in, the trash is thrown into a single "bin" after collection, and possibly separated from there. Don't know if that's true though).

Re:Finding UX in the Trash by ekianjo on Sunday September 17, 2017 @10:19AM (#15269698)
Machine learning excels at classification, and trash sorting is at heart a classification problem.

Applying ML to non-classification problems is when it is NOT appropriate, but this is a good pick.

Re:Finding UX in the Trash by dom0 on Sunday September 17, 2017 @10:32AM (#15269770)
> Machine learning excels at classification, and trash sorting is at heart a classification problem.

Classifying by physical properties is even easier by simply classifying by physical properties. Want to pull all ferrous metals out of a pile of stuff? Just use a magnet. Want to sort tin from plastic? Blower and conveyor bins by flight distance.

Incidentally, those elements not easily covered by this kind of sorting (which has been used for many years) is also not easy to cover by magical do-all machine learning, which will have a hard time sorting plastic-coated paper from paper from plastics, just like the processes above.

Re:Finding UX in the Trash by ekianjo on Sunday September 17, 2017 @10:37AM (#15269792)
> Want to sort tin from plastic? Blower and conveyor bins by flight distance.

ML is useful when you cannot make a clear difference using physical properties only. For example, if you treat different types of plastic garbage, you will probably want to separate bottles from other types of plastics, and you can do that with visual sorting and pattern matching.

> which will have a hard time sorting plastic-coated paper from paper from plastics, just like the processes above.

Certainly, but then this is when you still need some manual work at some point of the chain. But physical filtering + ML could reduce the human part of the work to exceptions.

Re:Finding UX in the Trash by catnaroek on Sunday September 17, 2017 @10:44AM (#15269830)
Just separate your trash yourself.

(0) It isn't hard.

(1) If the trash bins are aligned in a predictable manner, then you can even do it without thinking.

Re:Finding UX in the Trash by ekianjo on Tuesday September 19, 2017 @01:59AM (#15282131)
I am, but that does not mean further sorting is not needed at the recycling plant anyway. It is.
Re:Finding UX in the Trash by amelius on Sunday September 17, 2017 @10:46AM (#15269847)
I think physical properties are already being used in the sorting process.
Re:Finding UX in the Trash by dom0 on Sunday September 17, 2017 @10:59AM (#15269909)
> (which has been used for many years)