PMID- 19228565
OWN - NLM
STAT- MEDLINE
DCOM- 20090902
LR  - 20090623
IS  - 1558-0210 (Electronic)
IS  - 1534-4320 (Linking)
VI  - 17
IP  - 3
DP  - 2009 Jun
TI  - Conjugate-prior-penalized learning of Gaussian mixture models for multifunction 
      myoelectric hand control.
PG  - 287-97
LID - 10.1109/TNSRE.2009.2015177 [doi]
AB  - This paper presents a new learning method for Gaussian mixture models (GMMs) to 
      improve their generalization ability. A traditional maximum a posterior (MAP) 
      parameter estimate is used to achieve regularization based on conjugate priors. 
      Plus, a model order selection criterion is derived from Bayesian-Laplace 
      approaches, using the conjugate priors to measure the uncertainty of the 
      estimated parameters. As a result, the proposed learning method avoids the 
      possibility of convergence toward the boundary of the parameter space, and is 
      also capable of selecting the optimal order for a GMM with more enhanced 
      stability than conventional methods using a flat prior. When applying the 
      proposed learning method to construct a GMM classifier for electromyogram (EMG) 
      pattern recognition, the proposed GMM classifier achieves a high generalization 
      ability and outperforms conventional classifiers in terms of recognition 
      accuracy.
FAU - Chu, Jun-Uk
AU  - Chu JU
AD  - School of Electrical Engineering and Computer Science, Kyungpook National 
      University, Daegu 702-701, Korea. juchu@ee.knu.ac.kr
FAU - Lee, Yun-Jung
AU  - Lee YJ
LA  - eng
PT  - Journal Article
DEP - 20090218
PL  - United States
TA  - IEEE Trans Neural Syst Rehabil Eng
JT  - IEEE transactions on neural systems and rehabilitation engineering : a 
      publication of the IEEE Engineering in Medicine and Biology Society
JID - 101097023
SB  - IM
MH  - Algorithms
MH  - Computer Simulation
MH  - Data Interpretation, Statistical
MH  - Electromyography/*methods
MH  - Hand/*physiology
MH  - Humans
MH  - *Models, Neurological
MH  - Models, Statistical
MH  - Muscle Contraction/*physiology
MH  - Normal Distribution
MH  - Pattern Recognition, Automated/*methods
MH  - Robotics/*methods
MH  - Therapy, Computer-Assisted/*methods
MH  - User-Computer Interface
EDAT- 2009/02/21 09:00
MHDA- 2009/09/03 06:00
CRDT- 2009/02/21 09:00
PHST- 2009/02/21 09:00 [entrez]
PHST- 2009/02/21 09:00 [pubmed]
PHST- 2009/09/03 06:00 [medline]
AID - 10.1109/TNSRE.2009.2015177 [doi]
PST - ppublish
SO  - IEEE Trans Neural Syst Rehabil Eng. 2009 Jun;17(3):287-97. doi: 
      10.1109/TNSRE.2009.2015177. Epub 2009 Feb 18.