The effect of multiscale PCA de-noising in epileptic seizure detection - PubMed (original) (raw)

The effect of multiscale PCA de-noising in epileptic seizure detection

Jasmin Kevric et al. J Med Syst. 2014 Oct.

Abstract

In this paper we describe the effect of Multiscale Principal Component Analysis (MSPCA) de-noising method in terms of epileptic seizure detection. In addition, we developed a patient-independent seizure detection algorithm using Freiburg EEG database. Each patient contains datasets called "ictal" and "interictal". Window length of 16 s was applied to extract EEG segments from datasets of each patient. Furthermore, Power Spectral Density (PSD) of each EEG segment was estimated using different spectral analysis methods. Afterwards, these values were fed as input to different machine learning methods that were responsible for seizure detection. We also applied MSPCA de-noising method to EEG segments prior to PSD estimation to determine if MSPCA can further enhance the classifiers' performance. The MSPCA drastically improved both the sensitivity and the specificity, increasing the overall accuracy of all three classifiers up to 20%. The best overall detection accuracy (99.59%) was achieved when Eigenvector analysis was used for frequency estimation, and C4.5 as a classifier. The experiment results show that MSPCA is an effective de-noising method for improving the classification performance in epileptic seizure detection.

PubMed Disclaimer

References

    1. J Med Syst. 2004 Dec;28(6):511-22 -PubMed
    1. J Clin Neurophysiol. 2002 Apr;19(2):113-24 -PubMed
    1. J Neurosci Methods. 2006 Dec 15;158(2):300-12 -PubMed
    1. Comput Methods Programs Biomed. 2008 Aug;91(2):100-9 -PubMed
    1. IEEE Trans Inf Technol Biomed. 2006 Jul;10(3):458-67 -PubMed

MeSH terms

LinkOut - more resources