Epileptic seizure prediction using relative spectral power features. Issue 2 (February 2015)

• Record Type: Journal Article
• Authors: Bandarabadi, Mojtaba; Teixeira, César A.; Rasekhi, Jalil; Dourado, António
• Is Part Of: Clinical neurophysiology. Volume 126:Issue 2(2015:Feb.)
• Page Start: 237
• Page End: 248
• Publication Date: 2015-02
• Subjects: Neurophysiology -- Periodicals; Electroencephalography -- Periodicals; Electromyography -- Periodicals; Neurology -- Periodicals; 612.8
• DOI: 10.1016/j.clinph.2014.05.022
• Languages: English
• ISSNs: 1388-2457

Abstract

<abstract xml:lang="en" abstract-type="author-highlights" id="ab005"> <title id="st140">Highlights</title> <sec> <p id="sp0005"> <list id="l0005"> <list-item id="o0005"> <label></label> <p id="p0235">The proposed relative spectral power features resulted in an improved performance for seizure prediction.</p> </list-item> <list-item id="o0010"> <label></label> <p id="p0240">The number of selected features was 9.9 in average showing the efficiency of the introduced relative bivariate features.</p> </list-item> <list-item id="o0015"> <label></label> <p id="p0245">In average 75.8% of the test seizures (out-of-sample) were predicted across 1537 h of data with an average FPR of 0.1 h⁻¹.</p> </list-item> </list> </p> </sec> </abstract>