Neural network for sleep EEG K-complex detection.

C Strungaru; M S Popescu

doi:10.1515/bmte.1998.43.s3.113

Home/Archive/PubMed

PubMed · 11776208

Neural network for sleep EEG K-complex detection.

C Strungaru·M S Popescu

View original source ↗Export metadata ↓

Abstract

The paper presents the development and application of an automatic system used to detect and classify the K-complexes aperiodic, waveforms found in electroencephalograms of patients during stage two sleep. The slow-wave transient K-complex is evoked by auditory or somatosensory stimulation being an event related potential. The analysis of this transitory waveform contributes to the assessment of sleep stages used by controlled learning during sleep. In our work we used a TMS320C30 DSP to implement an automatic detection procedure based on features extraction and classification using a feed-forward neural network.

Explore related subjects

Analog-Digital Conversion Cerebral Cortex Electroencephalography Humans Neural Networks, Computer Polysomnography Signal Processing, Computer-Assisted Sleep Stages Journal Article

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

C Strungaru, M S Popescu. 1998. Neural network for sleep EEG K-complex detection.. https://doi.org/10.1515/bmte.1998.43.s3.113

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related citations

PubMed2006

[Present and future of analog image and digital image on mammography in closing the symposium].

Explore the source record for details and available documents.

Analog-Digital Conversion↗

PubMed2006

A user-friendly PC-based data acquisition and analysis system for respirometric investigations.

We have developed an easy-to-use computer-based system for recording, displaying, storing and analyzing signals generated by Clark-type oxygen electrodes. A user-friendly interface of Windows-based program BioMed significantly increases the productivity of investigations. It allows to process, control, present and archive the experimental data in real time. A 12-bit analog-to-digital-converter, analog and digital filters, a possibility to zoom the obtained respiratory curves and calculation of the respiration rates by a linear regression method increase the resolution of the estimated oxygen consumption rates. The new system enables to register even small changes, such as 3-5 ngatoms O/min, in respiration rates of biological objects -- enzymes, mitochondria and permeabilized muscle fibers. The system has been developed and is regularly used for the respirometric investigations at the Laboratory of Biochemistry, Institute for Biomedical Research, Kaunas University of Medicine.

Analog-Digital Conversion↗

PubMed2006

Elimination of depth degeneracy in optical frequency-domain imaging through polarization-based optical demodulation.

A novel optical frequency-domain imaging system is demonstrated that employs a passive optical demodulation circuit and a chirped digital acquisition clock derived from a voltage-controlled oscillator. The demodulation circuit allows the separation of signals from positive and negative depths to better than 50 dB, thereby eliminating depth degeneracy and doubling the imaging depth range. Our system design is compatible with dual-balanced and polarization-diverse detection, important techniques in the practical biomedical application of optical frequency-domain imaging.

Analog-Digital Conversion↗