EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Noncontact Neuromorphic Emotion Inference via Gaze Interaction

Jonghyeon Ko, Minho Jin, Siwoo Jeong, Dongwon Lee, Hyeonu Jeong, Zhihao Xu, Sangin Park, Bo-In Park, Eunsoo Park, Abdul Rehman, Yaeeun Han, Mincheol Whang und 3 weitere

ACS Nano · 17.11.2026

DOI: 10.1021/acsnano.6c14473 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACS Nano, online erschienen am 17.11.2026. Verfasst von Jonghyeon Ko und 14 weiteren Autor:innen. Die Arbeit nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: National Research Foundation of Korea.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Understanding social emotion through physiological signals remains highly challenging, as it requires bulky devices and computer systems, limiting its practicality in real-world applications. Here, we propose a neuromorphic approach that decodes affective states from pupillary responses by integrating physiological feature extraction, spiking neural computation, and memristive hardware simulation. Pupil dynamics provide a noncontact physiological signal for studying social-interaction and attentional demands. We derived individual and dyadic features from infrared pupil-diameter recordings from 108 participants and encoded them as spikes for classification by a spiking neural network (SNN). The framework was evaluated in four independent binary tasks defined by the experimental protocol. These tasks examined familiarity and an empathy-related contrast, as well as competition versus cooperation and low versus high attentional demands. With solid spike encoding and a spike-event loss, the SNN trained on combined individual and interactive features achieved performance comparable to the strongest conventional machine learning baselines with an accuracy of 95.4%. We also fabricated h-BN/WSe2 memristors and used their measured conductance characteristics to calibrate a model of RRAM weight mapping and variability. Software-based inference with this model linked the measured device behavior to network performance. A variation-aware training (VAT) strategy that incorporates device-inspired noise during software training improved simulated postmapping accuracy by up to approximately 9 percentage points across the evaluated tasks. Operation-based calculations provided highly efficient estimates of arithmetic and RRAM array-core read energy, achieving approximately 11.28–11.30 fJ per synaptic operation. These results support the use of dyadic pupil features for classification of the studied conditions and demonstrate the benefit of accounting for measured device variability during software training.

Förderung

  • National Research Foundation of Korea

Zitieren

APA

Ko, J., Jin, M., Jeong, S., Lee, D., Jeong, H., Xu, Z., Park, S., Park, B., Park, E., Rehman, A., Han, Y., Whang, M., Kang, J., Bae, S., & Mun, S. (2026). Noncontact Neuromorphic Emotion Inference via Gaze Interaction. ACS Nano. https://doi.org/10.1021/acsnano.6c14473

Vancouver

Ko J, Jin M, Jeong S, Lee D, Jeong H, Xu Z, et al. Noncontact Neuromorphic Emotion Inference via Gaze Interaction. ACS Nano. 2026. doi:10.1021/acsnano.6c14473

BibTeX
@article{Ko2026,
  author = {Ko, Jonghyeon and Jin, Minho and Jeong, Siwoo and Lee, Dongwon and Jeong, Hyeonu and Xu, Zhihao and Park, Sangin and Park, Bo-In and Park, Eunsoo and Rehman, Abdul and Han, Yaeeun and Whang, Mincheol and Kang, Ji-Hoon and Bae, Sang-Hoon and Mun, Sungchul},
  title = {Noncontact Neuromorphic Emotion Inference via Gaze Interaction},
  journal = {ACS Nano},
  year = {2026},
  doi = {10.1021/acsnano.6c14473}
}
Kostenlos starten →