Title :
Information processing models for automatic sleep scoring
Author :
Principe, Jose C. ; Chang, Tae G. ; Gala, Sunit K. ; Tome, Ana P.
Author_Institution :
Dept. of Electr. Eng., Florida Univ., Gainesville, FL, USA
Abstract :
Three different methods of information processing are described (a knowledge-based system, an automaton based on the theory of evidence, and a neural network). Their performance is compared and analyzed. One factor that is discussed is the degradation of the man-machine agreement, which is very high in the input tokens, and only high in the final result. The man-machine agreement for five sleep records, from normal subjects spanning the ages from 13 to 70 years, is shown. The records were chosen because they represent the normal sleep patterns of each age group. The token data and the human scoring are the same for all cases, so that the relative performance of the methods can be compared
Keywords :
biology computing; knowledge based systems; modelling; neural nets; 13 to 70 yr; automatic sleep scoring; automaton; information processing models; input tokens; knowledge-based system; man-machine agreement; neural network; normal subjects; theory of evidence; Automata; Electroencephalography; Electromyography; Electrooculography; Information processing; Knowledge based systems; Man machine systems; Neural networks; Signal processing algorithms; Sleep;
Conference_Titel :
Engineering in Medicine and Biology Society, 1989. Images of the Twenty-First Century., Proceedings of the Annual International Conference of the IEEE Engineering in
Conference_Location :
Seattle, WA
DOI :
10.1109/IEMBS.1989.96466
