EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

UDC-SNN: An Uncertainty-Aware Dynamic Cascading Framework with Spiking Neural Network for Balancing Performance and Energy in Multimodal Emotion Recognition

Guihao Ran, Shengzhe Li, Zhiwen Jiang, Han Zhang, Xinyuan Long, Dakun Lai iD

Sensors · 03.05.2026 · 26 (9) · 2859

DOI: 10.3390/s26092859 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 03.05.2026. Verfasst von Guihao Ran und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Electronic Science and Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China. Hauptthemen laut MEDLINE: Neural Networks, Computer, Emotions. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Sichuan Science and Technology Program.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The aim of this study is to propose an uncertainty-aware dynamic cascading framework based on spiking neural network (UDC-SNN) for multimodal emotion recognition, particularly to address the inherent trade-off between recognition performance and energy efficiency. An asymmetric dynamic routing mechanism was proposed to enable demand-driven activation of the high-power electroencephalogram (EEG) branch, coupled with preliminary inference on a low-power electrocardiogram (ECG) branch and uncertainty quantification via Shannon entropy. Meanwhile, a parameter-free log-linear aggregation strategy was developed to transform modality-specific entropy into dynamic Bayesian weights through an exponential decay function, effectively mitigating the negative transfer effects induced by unimodal noise. The UDC-SNN was evaluated on the multimodal affective dataset DREAMER, comprising 23 subjects (170,660 segments). The averaged recognition accuracy and energy consumption across the three dimensions of valence, arousal, and dominance were 90.75% and 4.62 μJ, respectively. The obtained results suggest that the proposed framework could potentially achieve a favorable balance between high emotion recognition and low energy consumption, thereby establishing its applicability for real-time monitoring in resource-constrained scenarios.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Neural Networks, ComputerEmotionsHumansUncertaintyElectroencephalographyAlgorithmsElectrocardiographyBayes TheoremEntropySignal Processing, Computer-Assisted

Stichwörter der Autor:innen

energy efficiencymultimodal emotion recognitionspiking neural networkuncertainty-aware

Autor:innen und Institutionen

  • School of Electronic Science and Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China.
  • Haihe Laboratory for Brain-Computer Interaction and Human-Computer Collaboration, Tianjin 300000, China.

ORCID-Profile: Dakun Lai

Förderung

  • Sichuan Science and Technology Program

Zitieren

APA

Ran, G., Li, S., Jiang, Z., Zhang, H., Long, X., & Lai, D. (2026). UDC-SNN: An Uncertainty-Aware Dynamic Cascading Framework with Spiking Neural Network for Balancing Performance and Energy in Multimodal Emotion Recognition. Sensors, 26(9), 2859. https://doi.org/10.3390/s26092859

Vancouver

Ran G, Li S, Jiang Z, Zhang H, Long X, Lai D. UDC-SNN: An Uncertainty-Aware Dynamic Cascading Framework with Spiking Neural Network for Balancing Performance and Energy in Multimodal Emotion Recognition. Sensors. 2026;26(9):2859. doi:10.3390/s26092859

BibTeX
@article{Ran2026,
  author = {Ran, Guihao and Li, Shengzhe and Jiang, Zhiwen and Zhang, Han and Long, Xinyuan and Lai, Dakun},
  title = {UDC-SNN: An Uncertainty-Aware Dynamic Cascading Framework with Spiking Neural Network for Balancing Performance and Energy in Multimodal Emotion Recognition},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {9},
  pages = {2859},
  doi = {10.3390/s26092859}
}
Kostenlos starten →