EUVIMEDEUVIMED entdecken
Crossref

An improved multi-source domain adaptation network for inter-subject mental fatigue detection based on DANN

Kun Chen iD, Zhiyong Liu, Zhilei Li, Quan Liu, Qingsong Ai, Li Ma

Biomedical Engineering / Biomedizinische Technik · 27.06.2023 · 68 (3) · 317-327

DOI: 10.1515/bmt-2022-0354 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Biomedical Engineering / Biomedizinische Technik, online erschienen am 17.02.2023. Verfasst von Kun Chen und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Information Engineering, Wuhan University of Technology, Wuhan, China. Hauptthemen laut MEDLINE: Electroencephalography, Mental Fatigue. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 33 Literaturangaben. Gefördert von: Natural Science Foundation of Hubei Province, National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objectives

Electroencephalogram (EEG) is often used to detect mental fatigue because of its real-time characteristic and objective nature. However, because of the individual variability of EEG among different individuals, tedious and time-consuming calibration sessions are needed.

Methods

Therefore, we propose a multi-source domain adaptation network for inter-subject mental fatigue detection named FLDANN, which is short for focal loss based domain-adversarial training of neural network. As for mental state feature extraction, power spectrum density is extracted based on the Welch method from four sub-bands of EEG signals. The features of the source domain and target domain are fed into the FLDANN network. The contributions of FLDANN include: (1) It uses the idea of adversarial to reduce feature differences between the source and target domain. (2) A loss function named focal loss is used to assign weights to source and target domain samples Results The experiment result shows that when the number of the source domains increases, the classification accuracy of domain-adversarial training of neural network (DANN) gradually decreases and finally tends to be stable. The proposed method achieves an accuracy of 84.10% ± 8.75% on the SEED-VIG dataset and 65.42% ± 7.47% on the self-designed dataset. In addition, the proposed method is compared with other domain adaptation methods and the results show that the proposed method outperforms those state-of-the-art methods.

Conclusions

The result proves that the proposed method is able to solve the problem of individual differences across subjects and to solve the problem of low classification performance of multi-source domain transfer learning.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ElectroencephalographyMental FatigueHumansCalibrationNeural Networks, Computer

Stichwörter der Autor:innen

EEGFLDANNdomain adaptationinter-subjectmental fatiguemulti-source domain

Autor:innen und Institutionen

  • School of Information Engineering, Wuhan University of Technology, Wuhan, China.
  • School of Computer Science and Information Engineering, Hubei University, Wuhan, China.

ORCID-Profile: Kun Chen

Förderung

  • Natural Science Foundation of Hubei Province
  • National Natural Science Foundation of China

Zitieren

APA

Chen, K., Liu, Z., Li, Z., Liu, Q., Ai, Q., & Ma, L. (2023). An improved multi-source domain adaptation network for inter-subject mental fatigue detection based on DANN. Biomedical Engineering / Biomedizinische Technik, 68(3), 317-327. https://doi.org/10.1515/bmt-2022-0354

Vancouver

Chen K, Liu Z, Li Z, Liu Q, Ai Q, Ma L. An improved multi-source domain adaptation network for inter-subject mental fatigue detection based on DANN. Biomedical Engineering / Biomedizinische Technik. 2023;68(3):317-327. doi:10.1515/bmt-2022-0354

BibTeX
@article{Chen2023,
  author = {Chen, Kun and Liu, Zhiyong and Li, Zhilei and Liu, Quan and Ai, Qingsong and Ma, Li},
  title = {An improved multi-source domain adaptation network for inter-subject mental fatigue detection based on DANN},
  journal = {Biomedical Engineering / Biomedizinische Technik},
  year = {2023},
  volume = {68},
  number = {3},
  pages = {317--327},
  doi = {10.1515/bmt-2022-0354}
}
Kostenlos starten →