Subject: | |
From: | |
Reply To: | |
Date: | Fri, 17 Oct 2008 09:47:05 +0100 |
Content-Type: | text/plain |
Parts/Attachments: |
|
|
Hi Peter
> when you get a match or near match, what you'll
> end up with is a probability that some hypothesis is true, not a guarantee.
Obtaining the matches would only be a starting point for further
checking, I am not expecting perfection and would always prefer 'real
data', but where data is not existing or is expensive to gather there
may be room for a synthetic approach.
> Computing or estimating the probabilities could be tricky.
The modelling would have to be based on what we already know.
What I am suggesting does not synthesize 'answers' only large quantities
of arbitrary sets of data, once a match is found, a human must interpret
the data to establish the answers.
--
Regards & Best 73s, Dave Cushman, G8MZY
http://melliferabees.net Email: [log in to unmask]
Short FallBack M/c, Build 7.21/2.01
Son of ORAC M/c, Build 5.o1/2.o1
****************************************************
* General Information About BEE-L is available at: *
* http://www.honeybeeworld.com/bee-l/default.htm *
****************************************************
|
|
|