Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2020 Dec;10(12):e01721.
doi: 10.1002/brb3.1721. Epub 2020 Oct 30.

A study on EEG feature extraction and classification in autistic children based on singular spectrum analysis method

Jie Zhao  1   2 , Jiajia Song  1   2 , Xiaoli Li  3 , Jiannan Kang  1   2
Affiliations

A study on EEG feature extraction and classification in autistic children based on singular spectrum analysis method

Jie Zhao et al. Brain Behav. 2020 Dec.

Abstract

Introduction: The clinical diagnosis of Autism spectrum disorder (ASD) depends on rating scale evaluation, which introduces subjectivity. Thus, objective indicators of ASD are of great interest to clinicians. In this study, we sought biomarkers from resting-state electroencephalography (EEG) data that could be used to accurately distinguish children with ASD and typically developing (TD) children.

Methods: We recorded resting-state EEG from 46 children with ASD and 63 age-matched TD children aged 3 to 5 years. We applied singular spectrum analysis (SSA) to the EEG sequences to eliminate noise components and accurately extract the alpha rhythm.

Results: When we used individualized alpha peak frequency (iAPF) and individualized alpha absolute power (iABP) as features for a linear support vector machine, ASD versus TD classification accuracy was 92.7%.

Conclusion: This study suggested that our methods have potential to assist in clinical diagnosis.

Keywords: alpha peak frequency (APF); autism; classification; electroencephalography; singular spectrum analysis (SSA).

PubMed Disclaimer

Conflict of interest statement

All authors declared that they have no conflicts of interest to this work.

Figures

Figure 1
Figure 1
a) Contaminated EEG, corrected EEG, and extracted artifacts; b) Spectrum of EEG processed by SSA, removing low frequency EOG signals, showing the desired alpha rhythm
Figure 2
Figure 2
Alpha peak frequency at electrodes O1, O2 in TD and ASD children. Alpha peak frequency of TD children was significantly higher than that of children with ASD. formula image TD; formula image ASD
Figure 3
Figure 3
Alpha rhythm in children with ASD and TD children: power spectra of the extracted alpha rhythm from the electrode at a) O1 and b) O2. formula image TD; formula image ASD
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

See all "Cited by" articles

References

    1. Akin, M. (2002). Comparison of wavelet transform and FFT methods in the analysis of EEG signals. Journal of Medical System, 26, 241–247. - PubMed
    1. Azami, H. , & Sanei, S. Automatic signal segmentation based on singular spectrum analysis and imperialist competitive algorithm. pp. 50–55, 2012.
    1. Basu, M. , & Xavier Savarimuthu, S. (2002). Machine Learning Methods in the Environmental Sciences.
    1. Bazanova, O. M. (2011). [Individual alpha peak frequency variability and reproducibility in various experimental conditions]. Zhurnal Vysshei Nervnoi Deiatelnosti Imeni I. P. Pavlova, 61, 102–111. - PubMed
    1. Berger, H. (1929). Über das Elektrenkephalogramm des Menschen. Archiv Für Psychiatrie Und Nervenkrankheiten, 87, 527–570. 10.1007/BF01797193 - DOI

Publication types