11–20 of 71 posts
With 90 minutes of data, they could pick out one driver out of a sample size of 15 . How meaningful is that, really?
Honestly it seems like everyone reading these kinds of papers/articles does a ctrl-f "sample size" before anything else. Bit cynical.
With 90 minutes of data, they could pick out one driver out of a sample size of 15 . How meaningful is that, really?
Not sure it's as trivial as you seem to be implying, but extending this to more drivers would certainly be a logical next step. Honestly it seems like everyone reading these kinds of papers/articles does a ctrl-f "sample size" before anything else. Bit cynical.
It's been easy to do face identification for a very small population for a while. But scaling that to thousands of people has proven quite difficult.
With 90 minutes of data, they could pick out one driver out of a sample size of 15 . How meaningful is that, really?
I think they meant 15/15 drivers which is a little better, but yeah.
So, the claim is 90% accuracy in determining which one of the fifteen drivers they are looking at. So, they were correct on 13.5 drivers.
Um, what?
Earlier quoted context omitted.
I think they meant 15/15 drivers which is a little better, but yeah.
"...could let them correctly distinguish the correct driver out of 15 individuals about nine times out of ten, after just 15 minutes of driving." So, the claim is 90% accuracy in determining which one of the fifteen drivers they are looking at. So, they were correct on 13.5 drivers. Um, what?
Earlier quoted context omitted.
"...could let them correctly distinguish the correct driver out of 15 individuals about nine times out of ten, after just 15 minutes of driving." So, the claim is 90% accuracy in determining which one of the fifteen drivers they are looking at. So, they were correct on 13.5 drivers. Um, what?
Try parsing it as "90% of drives ", not of drivers .
Earlier quoted context omitted.
Try parsing it as "90% of drives ", not of drivers .
That doesn't make sense to me. The constraint is 15 minutes total. If drives vs drivers give different data, that could only imply that (a) each driver's 15 minutes spans multiple vehicles, or (b) they make conflicting conclusions for the same driver across multiple trips.
I don't see where you're coming up with only 15 minutes total driving. That isn't implied anywhere in The Fine Article. But even leaving that detail aside, it would actually be more impressive than the reported finding if they were correctly identifying people that well after only 15 minutes total!
"In a study they plan to present at the Privacy Enhancing Technology Symposium in Germany this July" How would this enhance privacy? It seems like it would do the opposite?
This is exactly the reason they would never consider lock-picking techniques at lock symposium.