EUVIMEDEUVIMED entdecken
Crossref

Kernel Quaternion Principal Component Analysis of Eye and Head Dynamics for Depression Severity Prediction

Kevin Hung, Gary Man-Tat Man, Kwok-Tai Chui, Daniel Hung-Kay Chow, Bingo Wing-Kuen Ling, Sio-Hang Pun, Tai-Wa Liu, Shuqiang Wang

IEEE Transactions on Consumer Electronics · 2025-11 · 71 (4) · 9904-9919

DOI: 10.1109/tce.2025.3603229 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Consumer Electronics, 2025-11. Verfasst von Kevin Hung und 7 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 73 Literaturangaben. Gefördert von: Research Grants Council of the Hong Kong Special Administrative Region, China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Depression is a global mental health challenge that necessitates accurate and timely diagnosis. Studies have shown that features extracted from eye dynamics and head movements constitute a non-invasive and real-time means of monitoring behavioral biomarkers associated with depression. However, representing and analyzing these high-dimensional, time-varying signals for medical diagnosis poses significant challenges, including computational inefficiency, loss of temporal information, and the inability to capture complex interrelations between movement channels. This paper proposes a novel algorithm that leverages kernel quaternion principal component analysis to extract features from eye and head dynamics, represented as quaternion time series signals, preserving channel-wise interrelations and temporal information. Additionally, a model-based quaternion interpolation method is introduced to address class imbalance by augmenting depression samples. The proposed approach is evaluated on a benchmark depression dataset, demonstrating superior accuracy in predicting depression severity with a root mean square error (RMSE) of 4.84 and a mean absolute error (MAE) of 3.88. When applied to the augmented dataset, the algorithm achieves further improvement, with an RMSE of 4.48 and an MAE of 3.53. These results outperform previous methods based solely on eye and head dynamics, highlighting the potential of quaternion-based signal processing in advancing mental health diagnostics. The proposed framework is particularly promising for integration into consumer systems for healthcare and wellbeing, such as smart eyewear, offering a practical and accessible solution for the early detection and intervention of depression by equipping individuals with tools to manage their mental wellbeing in everyday life.

Förderung

  • Research Grants Council of the Hong Kong Special Administrative Region, China

Zitieren

APA

Hung, K., Man, G. M., Chui, K., Chow, D. H., Ling, B. W., Pun, S., Liu, T., & Wang, S. (2025). Kernel Quaternion Principal Component Analysis of Eye and Head Dynamics for Depression Severity Prediction. IEEE Transactions on Consumer Electronics, 71(4), 9904-9919. https://doi.org/10.1109/tce.2025.3603229

Vancouver

Hung K, Man GM, Chui K, Chow DH, Ling BW, Pun S, et al. Kernel Quaternion Principal Component Analysis of Eye and Head Dynamics for Depression Severity Prediction. IEEE Transactions on Consumer Electronics. 2025;71(4):9904-9919. doi:10.1109/tce.2025.3603229

BibTeX
@article{Hung2025,
  author = {Hung, Kevin and Man, Gary Man-Tat and Chui, Kwok-Tai and Chow, Daniel Hung-Kay and Ling, Bingo Wing-Kuen and Pun, Sio-Hang and Liu, Tai-Wa and Wang, Shuqiang},
  title = {Kernel Quaternion Principal Component Analysis of Eye and Head Dynamics for Depression Severity Prediction},
  journal = {IEEE Transactions on Consumer Electronics},
  year = {2025},
  volume = {71},
  number = {4},
  pages = {9904--9919},
  doi = {10.1109/tce.2025.3603229}
}
Kostenlos starten →