Differences

This shows you the differences between the selected revision and the current version of the page.

projects:mlma 2012/04/22 19:13 projects:mlma 2012/09/06 16:40 current
Line 11: Line 11:
}} }}
-===== Project Description ===== 
-This project explores the use of different Artificial Neural Network architectures in analysis of motion capture data, towards understanding performer gesture. +===== Project Description =====
 +Current and previous work at the IDMIL includes the creation of databases of MoCap data from performances of various instruments (violin, viola, cello, clarinet, drums) recorded by student and professional musicians. Motion capture is a very useful tool for conducting movement analysis. An advantage is that it provides highly accurate information about subject's movements. A disadvantage is that in providing such detailed information the quantity of data is large enough that analysis is challenging. There are many different approaches for dealing with this issue.  Examples include the use of functional data analysis (Vines et al 2006), and sonification of movement data (Verfaille et al 2006). One possible solution is to use machine learning. In particular, this project explores the use of different artificial neural network architectures in analysis of motion capture data, towards understanding performer gesture.
---- ----
{{tag>Machine_Learning Movement_Analysis}} {{tag>Machine_Learning Movement_Analysis}}