Title :
Poster abstract: Gesture recognition via continuous maximum entropy training on accelerometer data
Author :
Liu, Alan L. ; Yang, Jun ; Boda, P?©ter P??l
Author_Institution :
Univ. of Washington, Seattle, WA, USA
Abstract :
This work presents a gesture recognition system via continuous maximum entropy (MaxEnt) training on accelerometer data. MaxEnt models are commonly learned using generalized iterative scaling (GIS), which is an iterative algorithm for most convex optimization problems.
Keywords :
gesture recognition; iterative methods; maximum entropy methods; MaxEnt; accelerometer; generalized iterative scaling; gesture recognition; iterative algorithm; maximum entropy training; Accelerometers; Computer vision; Entropy; Geographic Information Systems; Iterative algorithms; Mobile computing; Natural language processing; Permission; Predictive models; Web pages;
Conference_Titel :
Information Processing in Sensor Networks, 2009. IPSN 2009. International Conference on
Print_ISBN :
978-1-4244-5108-1
Electronic_ISBN :
978-1-60558-371-6
