Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

How many flies are in my apartment?

saml98.github.io

Post reply on HN
Print view View original

51–60 of 158 posts

Re: How many flies are in my apartment?

#51

Post by pelasaco »

mkreis wrote: post #46
m12k wrote: post #40

In my statistics class we were taught a technique for estimating the number of flies in a barn. You capture a fixed size sample of flies, e.g. 100, and give them each a little white dot on the back, then release them all back in the barn. Leave them to mingle for a while, then capture another fixed number of flies, e.g. 100. If 5 of them have a white dot on them, then you estimate that the 100 flies you captured orig…

Reminds me of how the Allies estimated the production capacity of German tanks during WW2: https://medium.com/dataseries/how-data-science-gave-the-alli...

Thank you! Great read, indeed!

Re: How many flies are in my apartment?

#52

Post by ramanan »

m12k wrote: post #40

In my statistics class we were taught a technique for estimating the number of flies in a barn. You capture a fixed size sample of flies, e.g. 100, and give them each a little white dot on the back, then release them all back in the barn. Leave them to mingle for a while, then capture another fixed number of flies, e.g. 100. If 5 of them have a white dot on them, then you estimate that the 100 flies you captured orig…

This catch and release pattern is quite common in many wildlife surveys.

For example, when estimating tiger populations, instead of painting a white dot, rangers set up camera traps to take photos. Then they can use stripe patterns as a signature for subsequent re-appearances. Quite an interesting intersection for image AI with statistical counting methods.

Re: How many flies are in my apartment?

#53

Post by canadianfella »

ramanan wrote: post #52
m12k wrote: post #40

In my statistics class we were taught a technique for estimating the number of flies in a barn. You capture a fixed size sample of flies, e.g. 100, and give them each a little white dot on the back, then release them all back in the barn. Leave them to mingle for a while, then capture another fixed number of flies, e.g. 100. If 5 of them have a white dot on them, then you estimate that the 100 flies you captured orig…

This catch and release pattern is quite common in many wildlife surveys. For example, when estimating tiger populations, instead of painting a white dot, rangers set up camera traps to take photos. Then they can use stripe patterns as a signature for subsequent re-appearances. Quite an interesting intersection for image AI with statistical counting methods.

Why would AI be needed?

Re: How many flies are in my apartment?

#54

Post by m12k »

rozab wrote: post #47
m12k wrote: post #40

In my statistics class we were taught a technique for estimating the number of flies in a barn. You capture a fixed size sample of flies, e.g. 100, and give them each a little white dot on the back, then release them all back in the barn. Leave them to mingle for a while, then capture another fixed number of flies, e.g. 100. If 5 of them have a white dot on them, then you estimate that the 100 flies you captured orig…

Fun idea, but presumably there is a big bias in that some flies will be easier to catch for various reasons. I suppose lots of population studies on birds, cetaceans or whatever have this bias, since you can't just slap a quadrat down and catch everything. In fact with these more advanced animals, perhaps they're harder to observe a second time since they've learned to be wary of humans.

Right, if you're measuring long enough that predators eating some of the flies could be an issue, then you'd want to mark them with something only visible under a blacklight, or similarly "neutral", so it doesn't introduce a bias.

Re: How many flies are in my apartment?

#55

Post by MereInterest »

ramanan wrote: post #52
m12k wrote: post #40

In my statistics class we were taught a technique for estimating the number of flies in a barn. You capture a fixed size sample of flies, e.g. 100, and give them each a little white dot on the back, then release them all back in the barn. Leave them to mingle for a while, then capture another fixed number of flies, e.g. 100. If 5 of them have a white dot on them, then you estimate that the 100 flies you captured orig…

This catch and release pattern is quite common in many wildlife surveys. For example, when estimating tiger populations, instead of painting a white dot, rangers set up camera traps to take photos. Then they can use stripe patterns as a signature for subsequent re-appearances. Quite an interesting intersection for image AI with statistical counting methods.

Are there adjustments that need to be made for non-random sampling in that case? I'd imagine that with any territorial animal, a stationary camera is most likely to see the same animal multiple times.

Re: How many flies are in my apartment?

#56

Post by josefresco »

btbuildem wrote: post #39
lolc wrote: post #34

All these models ignore how insects actually zero in on a smell. For a fly outside, the source of the smell is the gap in the window. What looks like random direction changes is actually a search pattern for that source.

Very good point -- and that's why they find their way inside so easily, but look really dumb trying to find their way out. Same principle behind a DIY fruit fly trap (glass of juice with a plastic cover with a few holes poked in it).

Then why only two?

Re: How many flies are in my apartment?

#57

Post by ramanan »

MereInterest wrote: post #55
ramanan wrote: post #52

Earlier quoted context omitted.

This catch and release pattern is quite common in many wildlife surveys. For example, when estimating tiger populations, instead of painting a white dot, rangers set up camera traps to take photos. Then they can use stripe patterns as a signature for subsequent re-appearances. Quite an interesting intersection for image AI with statistical counting methods.

Are there adjustments that need to be made for non-random sampling in that case? I'd imagine that with any territorial animal, a stationary camera is most likely to see the same animal multiple times.

True. I’m no expert in this area, but there are a lot more factors too - including territorial range and even different camera locations.

Re: How many flies are in my apartment?

#58

Post by madethemcry »

This reminds me of the flocking boids algorithm by Craig Reynolds [0] which is based on three principles:

  + separation: steer to avoid crowding local flockmates
  + alignment: steer towards the average heading of local flockmates
  + cohesion: steer to move towards the average position (center of mass) of local flockmates
The algorithm was used to animate the bat swarms in Batman Returns (1992) [1].

I love this algorithm, it's easy to develop and experiment with and the results feel beautiful & natural.

  [0]: https://www.red3d.com/cwr/boids/
  [1]: https://en.wikipedia.org/wiki/Boids

Re: How many flies are in my apartment?

#59

Post by minitoar »

morelisp wrote: post #27
jbb_hn wrote: post #25

Earlier quoted context omitted.

This sounds like a potentially lucrative business opportunity!

They are for sale, for cheap, in every drug store.

The number of presumably Europeans in here citing screens blocking light as a reason for not installing screens makes me think maybe those screens are pretty low quality?

Re: How many flies are in my apartment?

#60

Post by OJFord »

only_as_i_fall wrote: post #45
pvaldes wrote: post #33

Earlier quoted context omitted.

Not in south of Europe unless is a mosquito disco location. One of the main purposes of windows is to see out. The more transparent, the better. Another factor is the light level. If you have a lot of days with rain or low light, like UK or many other places have, nets reduce even more the level of light entering in the house. Lacking of a lot of the dangerous mosquito borne diseases than tropical places have, the co…

Idk I've just never even considered losing light because of the screens, it's so little. Maybe I'm just used to it. Also it's not only like a cultural thing, I legally had to put screens in every window of my house before it was able to be occupied. Just an anecdote... It's weird how we never question things like that.

FWIW that applies to a lot of your 'codes'. Obviously we have regulations too, but it's bizarre (from an outsider perspective) how much it comes up in US television, or online, and (and in part it seems due to) the extent of it.

Regarding light - leaving aside however much it blocks light for illumination purposes, what about seeing out? I want to look out of the window, not look at a mesh all but completely obscuring the view.

Post reply on HN