I need help with the following:
I have a dataset with the positions of fingers on a certain object. We
have the position of a particular point on each finger. For each
finger, we pick the x and y coordinates of that point. Furthermore, we
have 20 subjects and 5 trials per subject. So we have 100 observations
(20*5) and 10 variables ( x and y coordinates of 5 particular points on
each subject's finger).
The objective is to find the number of sensors to put on this
particular object and where to put them in order to maximize the
discrimination between the subjects. In other words, where is the
position of the best discriminating sensor? Where is the postion of the
second best discriminating sensor? etc..., and when to stop adding
sensors? (in other words, when it's not worthwile to add anymore
Any suggestions in how to proceed?
The data looks like:
ID Trial XT YT XI YI XM YM XR YR XP YP
Trial: 1 to 5 (each subject holds the object 5 times)
XT: x coordinate of the thumb
YT: y coordinate of the thumb
XI: x coordinate of the index
YI: y coordinate of the index
XM: x coordinate of the middle finger
YM: y '' '' ''
XR: x coordinate of the ring
YR: y " "
XP: x coordinate of the pinky
YP: y coordiante of the pinky
Thanks in advance.
Sent via Deja.com http://www.deja.com/
Before you buy.