Feature-based detection of the K-complex wave in the human electroencephalogram using neural networks
- 1 January 1992
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Biomedical Engineering
- Vol. 39 (12) , 1305-1310
- https://doi.org/10.1109/10.184707
Abstract
The main difficulties in reliable automated detection of the K-complex wave in EEG are its close similarity to other waves and the lack of specific characterization criteria. We present a feature-based detection approach using neural networks that provides good agreement with visual K-complex recognition: a sensitivity of 90% is obtained with about 8% false positives. The respective contribution of the features and that of the neural network is demonstrated by comparing the results to those obtained with i) raw EEG data presented to neural networks, and ii) features presented to Fisher's linear discriminant.Keywords
This publication has 5 references indexed in Scilit:
- Artificial neural nets for K-complex detectionIEEE Engineering in Medicine and Biology Magazine, 1990
- Sleep staging automaton based on the theory of evidenceIEEE Transactions on Biomedical Engineering, 1989
- Knowledge-based approach to sleep EEG analysis-a feasibility studyIEEE Transactions on Biomedical Engineering, 1989
- Principles of automatic analysis of sleep records with a hybrid systemComputers and Biomedical Research, 1973
- Automatic Detection of the K-Complex in Sleep ElectroencephalogramsIEEE Transactions on Biomedical Engineering, 1970