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 · 2026
Read UDC-SNN: An Uncertainty-Aware Dynamic Cascading Framework with Spiking Neural Network for Balancing Performance and Energy in Multimodal Emotion Recognition by Guihao Ran, Shengzhe Li, Zhiwen Jiang, Han Zhang, Xinyuan Long, Dakun Lai (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13165955.txt.
Description
Guihao Ran, Shengzhe Li, Zhiwen Jiang, and a wider team wrote this machine learning paper, published in 2026. It presents an emotion recognition system that reads brain and heart signals together, but only wakes the costly brain-signal branch when the cheap heart branch is unsure.
The system uses spiking neural networks, which fire in pulses and sip energy. A heart-signal branch first makes a quick call and rates its own doubt. Only then does the brain-signal branch join in. A weighting scheme blends the two branches while damping the noise of either one alone. On a standard dataset of twenty-three people, the system scored about ninety-one percent accuracy across three emotion dimensions. Its energy use stayed tiny. The authors aim it at live monitoring on devices with little power to spare.
Catalog record
| CREATOR | Guihao Ran, Shengzhe Li, Zhiwen Jiang, Han Zhang, Xinyuan Long, Dakun Lai |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 46 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |