论文信息 - Threshold choice for automatic spindle detection

Threshold choice for automatic spindle detection

In this paper five choices are presented to determine the threshold for sleep spindle automatic detection. The proposed methods are based on performance measures. The different threshold values are compared using a Wave Morphology for Spindle Detection algorithm. For the presented algorithm, sensitivity ranges from 47.9% to 94.7%, while specificity ranges inversely from 98.7% to 89.0% for the threshold values used; the maximum accuracy reached is 96.6%.

[1] E. Wolpert. A Manual of Standardized Terminology, Techniques and Scoring System for Sleep Stages of Human Subjects. , 1969 .

[2] E. G. Jones,et al. Thalamic oscillations and signaling , 1990 .

[3] P. Achermann,et al. Spindle frequency activity in the sleep EEG: individual differences and topographic distribution. , 1997, Electroencephalography and clinical neurophysiology.

[4] M. Ferrara,et al. Sleep spindles: an overview. , 2003, Sleep medicine reviews.

[5] T. Dutoit,et al. Automatic Sleep Spindle Detection in Patients with Sleep Disorders , 2006, 2006 International Conference of the IEEE Engineering in Medicine and Biology Society.

[6] Günther J. L. Gerhardt,et al. Benchmarking matching pursuit to find sleep spindles , 2006, Journal of Neuroscience Methods.

[7] M. Zervakis,et al. Time–frequency analysis methods to quantify the time-varying microstructure of sleep EEG spindles: Possibility for dementia biomarkers? , 2009, Journal of Neuroscience Methods.

[8] János Körmendi,et al. The individual adjustment method of sleep spindle analysis: Methodological improvements and roots in the fingerprint paradigm , 2009, Journal of Neuroscience Methods.

[9] Laura B Ray,et al. Validating an automated sleep spindle detection algorithm using an individualized approach , 2010, Journal of sleep research.