On 16/01/2014 10:15 AM, Michael wrote: > > On 16 January 2014 09:43, Bernard Robertson-Dunn <b...@iimetro.com.au > <mailto:b...@iimetro.com.au>> wrote: > > > To be pedantic (and correct), Ford knows what the car is doing, they > don't know who is driving. It's the same with phone tracking. If there > are two people in the car - who is driving and who is on the > phone? Even > it both phones are being used that does not prove (it only suggests) > both people are on the phone. > > -- > > > Yes, but I can envisage a mechanism for identifying an individual > based on driving habits (like handwriting analysis, or gait > recognition or keystroke dynamics) that could link a driver across trips. > Matching that up to an individual human then becomes much easier. > Especially as most vehicles have a small set of regular drivers. > I suspect I could identify whether it was my mum or dad driving with > better than 95% accuracy if I had access to their acceleration and > breaking data, for example.
Agreed, but you are talking about a) the future and b) more than just data. It would need someone to build model(s) of an individual's behaviour. This is more than just data collection and gets back to where I started a few days ago - model building is an integral part of analysis. -- Regards brd Bernard Robertson-Dunn Sydney Australia email: b...@iimetro.com.au web: www.drbrd.com web: www.problemsfirst.com Blog: www.problemsfirst.com/blog _______________________________________________ Link mailing list Link@mailman.anu.edu.au http://mailman.anu.edu.au/mailman/listinfo/link
