M. Kubat et al., TOWARDS AUTOMATED SLEEP CLASSIFICATION IN INFANTS USING SYMBOLIC AND SUBSYMBOLIC APPROACHES, Biomedizinische Technik, 38(4), 1993, pp. 73-80
The paper addresses the problem of automatic sleep classification. A s
pecial effort is made to find a method of extracting reasonable descri
ptions of the individual sleep stages from sample measurements of EGG,
EMG, EOG, etc., and from a classification of these measurements provi
ded by an expert. The method should satisfy three requirements: classi
fication accuracy, interpretability of the results, and the ability to
select the relevant and discard the irrelevant variables. The solutio
n suggested in this paper consists of a combination of the subsymbolic
algorithm LVQ with the symbolic decision tree generator ID3. Results
demonstrating the feasibility and utility of our approach are also pre
sented.