Structure Analysis of a Probabilistic Network in an Information Geometric Framework

Author(s):  
T. Zheng ◽  
C. Guest
Author(s):  
M. Iwatsuki ◽  
Y. Kokubo ◽  
Y. Harada ◽  
J. Lehman

In recent years, the electron microscope has been significantly improved in resolution and we can obtain routinely atomic-level high resolution images without any special skill. With this improvement, the structure analysis of organic materials has become one of the interesting targets in the biological and polymer crystal fields.Up to now, X-ray structure analysis has been mainly used for such materials. With this method, however, great effort and a long time are required for specimen preparation because of the need for larger crystals. This method can analyze average crystal structure but is insufficient for interpreting it on the atomic or molecular level. The electron microscopic method for organic materials has not only the advantage of specimen preparation but also the capability of providing various information from extremely small specimen regions, using strong interactions between electrons and the substance. On the other hand, however, this strong interaction has a big disadvantage in high radiation damage.


1997 ◽  
Vol 36 (04/05) ◽  
pp. 41-46
Author(s):  
A. Kjaer ◽  
W. Jensen ◽  
T. Dyrby ◽  
L. Andreasen ◽  
J. Andersen ◽  
...  

Abstract.A new method for sleep-stage classification using a causal probabilistic network as automatic classifier has been implemented and validated. The system uses features from the primary sleep signals from the brain (EEG) and the eyes (AOG) as input. From the EEG, features are derived containing spectral information which is used to classify power in the classical spectral bands, sleep spindles and K-complexes. From AOG, information on rapid eye movements is derived. Features are extracted every 2 seconds. The CPN-based sleep classifier was implemented using the HUGIN system, an application tool to handle causal probabilistic networks. The results obtained using different training approaches show agreements ranging from 68.7 to 70.7% between the system and the two experts when a pooled agreement is computed over the six subjects. As a comparison, the interrater agreement between the two experts was found to be 71.4%, measured also over the six subjects.


2009 ◽  
Vol 2009 (30) ◽  
pp. 209-214 ◽  
Author(s):  
P. S. Dubinin ◽  
I. S. Yakimov ◽  
O. E. Piksina ◽  
Y. I. Yakimov ◽  
A. N. Zaloga
Keyword(s):  

Sign in / Sign up

Export Citation Format

Share Document