> Well, that might be an idea to use both accelerometers. Currently
more is usually better than less ;-) I haven't yet looked at the machine
learning part of the recognition you do (I know that you described it in
your MS thesis I think), but doubling the number of features for
classification/detection should have only positive effects here -- those
features are not bogus and well correlated with each other, thus I would
expect significant boost in performance.
And taking the fact that recognition works quite well already with just
a single accelerometer is great news -- it means that with 2 it should
be just better ;-)
--
.-.
=------------------------------ /v\ ----------------------------=
Keep in touch // \\ (yoh@|www.)onerussian.com
Yaroslav Halchenko /( )\ ICQ#: 60653192
Linux User ^^-^^ [175555]
_______________________________________________
Openmoko community mailing list
community@lists.openmoko.orghttp://lists.openmoko.org/mailman/listinfo/community
