Improving time–frequency domain sleep EEG classification via singular spectrum analysis

Tools

Mahvash Mohammadi, S., Kouchaki, S., Ghavami, M. and Sanei, S. ORCID: 0000-0002-3437-2801, 2016. Improving time–frequency domain sleep EEG classification via singular spectrum analysis. Journal of Neuroscience Methods, 273, pp. 96-106. ISSN 0165-0270

Preview

Text
PubSub10176_Sanei.pdf - Post-print
Download (3MB) | Preview

Official URL: http://doi.org/10.1016/j.jneumeth.2016.08.008

Abstract

Background: Manual sleep scoring is deemed to be tedious and time consuming. Even among automatic methods such as Time-Frequency (T-F) representations, there is still room for more improvement.
New method: To optimise the efficiency of T-F domain analysis of sleep electroencephalography (EEG) a novel approach for automatically identifying the brain waves, sleep spindles, and K-complexes from the sleep EEG signals is proposed. The proposed method is based on singular spectrum analysis (SSA). The single-channel EEG signal (C3-A2) is initially decomposed and then the desired components are automatically separated. In addition, the noise is removed to enhance the discrimination ability of features. The obtained T-F features after preprocessing stage are classified using a multi-class support vector machines (SVM) and used for the identification of four sleep stages over three sleep types. Furthermore, to emphasize on the usefulness of the proposed method the automatically-determined spindles are parameterised to discriminate three sleep types.
Result: The four sleep stages are classified through SVM twice: with and without preprocessing stage. The mean accuracy, sensitivity, and specificity for before the preprocessing stage are: 71.5 ± 0.11%, 56.1 ± 0.09% and 86.8 ± 0.04% respectively. However, these values increase significantly to 83.6 ± 0.07%, 70.6 ± 0.14% and 90.8 ± 0.03% after applying SSA.
Comparison with existing method: The new T-F representation has been compared with the existing benchmarks. Our results prove that, the proposed method well outperforms the previous methods in terms of identification and representation of sleep stages.
Conclusion: Experimental results confirm the performance improvement in terms of classification rate and also representative T-F domain.

Item Type:

Journal article

Publication Title:

Journal of Neuroscience Methods

Creators:

Mahvash Mohammadi, S., Kouchaki, S., Ghavami, M. and Sanei, S.

Publisher:

Elsevier

Date:

1 November 2016

Volume:

273