EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Parkinson's disease detection from EEG signal employing autoencoder and RBFNN-based hybrid deep learning framework utilizing power spectral density

Ferdaus Anam Jibon, Alif Tasbir, Md Alamin Talukder iD, Md Ashraf Uddin, Fazla Rabbi, Md Salam Uddin, Fars K Alanazi, Mohsin Kazi

DIGITAL HEALTH · 2024-01 · 10

DOI: 10.1177/20552076241297355 ↗

Kurz gefasst

Fachartikel in der Zeitschrift DIGITAL HEALTH, online erschienen am 12.11.2024. Verfasst von Ferdaus Anam Jibon und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science and Engineering, International University of Business Agriculture and Technology, Dhaka, Bangladesh. Die Arbeit wurde bisher 24-mal zitiert (Crossref) und nennt 55 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Deanship of Scientific Research, King Saud University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective

Early detection of Parkinson's disease (PD) is essential for halting its progression, yet challenges remain in leveraging deep learning for accurate identification. This study aims to overcome these obstacles by introducing a hybrid deep learning approach that enhances PD detection through a combination of autoencoder (AE) and radial basis function neural network (RBFNN).

Methods

The proposed method analyzes the power spectral density (PSD) of preprocessed electroencephalography (EEG) signals, with artifacts removed, to assess energy distribution across EEG sub-bands. AEs are employed to extract features from reconstructed signals, which are subsequently classified by an RBFNN. The approach is validated on UC SanDiego's EEG dataset, consisting of 31 subjects and 93 minutes of recordings.

Results

The hybrid model demonstrates promising performance, achieving a classification accuracy of 99%. The improved accuracy is attributed to advanced feature selection techniques, robust data preprocessing, and the integration of AEs with RBFNN, setting a new benchmark in PD detection frameworks.

Conclusion

This study highlights the efficacy of the hybrid deep learning framework in detecting PD, particularly emphasizing the importance of using multiple EEG channels and advanced preprocessing techniques. The results underscore the potential of this approach for practical clinical applications, offering a reliable solution for early and accurate PD detection.

Schlagwörter

Stichwörter der Autor:innen

EEG signalParkinson's diseaseRBFNNautoencoderbrainclassification

Autor:innen und Institutionen

  • Department of Computer Science and Engineering, International University of Business Agriculture and Technology, Dhaka, Bangladesh.
  • Department of Computer Science and Engineering, University of Information Technology and Sciences, Dhaka, Bangladesh.
  • School of Information Technology, Crown Institute of Higher Education, North Sydney, NSW, Australia.
  • Department of Pharmaceutics, College of Pharmacy, King Saud University, Riyadh, Saudi Arabia.

ORCID-Profile: Md Alamin Talukder

Förderung

  • Deanship of Scientific Research, King Saud University

Zitieren

APA

Jibon, F. A., Tasbir, A., Talukder, M. A., Uddin, M. A., Rabbi, F., Uddin, M. S., Alanazi, F. K., & Kazi, M. (2024). Parkinson's disease detection from EEG signal employing autoencoder and RBFNN-based hybrid deep learning framework utilizing power spectral density. DIGITAL HEALTH, 10. https://doi.org/10.1177/20552076241297355

Vancouver

Jibon FA, Tasbir A, Talukder MA, Uddin MA, Rabbi F, Uddin MS, et al. Parkinson's disease detection from EEG signal employing autoencoder and RBFNN-based hybrid deep learning framework utilizing power spectral density. DIGITAL HEALTH. 2024;10. doi:10.1177/20552076241297355

BibTeX
@article{Jibon2024,
  author = {Jibon, Ferdaus Anam and Tasbir, Alif and Talukder, Md Alamin and Uddin, Md Ashraf and Rabbi, Fazla and Uddin, Md Salam and Alanazi, Fars K and Kazi, Mohsin},
  title = {Parkinson's disease detection from EEG signal employing autoencoder and RBFNN-based hybrid deep learning framework utilizing power spectral density},
  journal = {DIGITAL HEALTH},
  year = {2024},
  volume = {10},
  doi = {10.1177/20552076241297355}
}
Kostenlos starten →