A1 Journal article (refereed)
Ensemble deep clustering analysis for time window determination of event-related potentials (2023)


Mahini, R., Li, F., Zarei, M., Nandi, A. K., Hämäläinen, T., & Cong, F. (2023). Ensemble deep clustering analysis for time window determination of event-related potentials. Biomedical Signal Processing and Control, 86, B, Article 105202. https://doi.org/10.1016/j.bspc.2023.105202


JYU authors or editors


Publication details

All authors or editorsMahini, Reza; Li, Fan; Zarei, Mahdi; Nandi, Asoke K.; Hämäläinen, Timo; Cong, Fengyu

Journal or seriesBiomedical Signal Processing and Control

ISSN1746-8094

eISSN1746-8108

Publication year2023

Publication date02/07/2023

Volume86, B

Article number105202

PublisherElsevier

Publication countryUnited Kingdom

Publication languageEnglish

DOIhttps://doi.org/10.1016/j.bspc.2023.105202

Publication open accessOpenly available

Publication channel open accessPartially open access channel

Publication is parallel published (JYX)https://jyx.jyu.fi/handle/123456789/88313


Abstract

Objective
Cluster analysis of spatio-temporal event-related potential (ERP) data is a promising tool for exploring the measurement time window of ERPs. However, even after preprocessing, the remaining noise can result in uncertain cluster maps followed by unreliable time windows while clustering via conventional clustering methods.

Methods
We designed an ensemble deep clustering pipeline to determine a reliable time window for the ERP of interest from temporal concatenated grand average ERP data. The proposed pipeline includes semi-supervised deep clustering methods initialized by consensus clustering and unsupervised deep clustering methods with end-to-end architectures. Ensemble clustering from those deep clusterings was used by the designed adaptive time window determination to estimate the time window.

Results
After applying simulated and real ERP data, our method successfully obtained the time window for identifying the P3 components (as the interest of both ERP studies) while additional noise (e.g., adding 20 dB to −5 dB white Gaussian noise) was added to the prepared data.

Conclusion
Compared to the state-of-the-art clustering methods, a superior clustering performance was yielded from both ERP data. Furthermore, more stable and precise time windows were elicited as the noise increased.

Significance
Our study provides a complementary understanding of identifying the cognitive process using deep clustering analysis to the existing studies. Our finding suggests that deep clustering can be used to identify the ERP of interest when the data is imperfect after preprocessing.


Keywordsclustersanalysiscognitive processesresearch methods

Free keywordsevent-related potentials; time window; deep clustering; ensemble learning; consensus clustering; ERP microstates


Contributing organizations


Ministry reportingYes

Reporting Year2023

Preliminary JUFO rating1


Last updated on 2024-18-02 at 18:26