Single-shot in-sensor optical spectral AI processing
We demonstrate an analogue frequency-comb-based optical smart sensor with in-memory computing for real-time image classification and blood analysis. Our system successfully predicts early-stage heart-attack samples with 95.1% accuracy with single-pulse latency of 10 ns.
Authors
- Yuan-Fang Li (ORCID: https://orcid.org/0000-0003-4651-2821)
- Kaiwen Xue (ORCID: https://orcid.org/0000-0003-1931-7852)
- Mengjie Yu (ORCID: https://orcid.org/0000-0002-7815-4195)
- Yuanhao Liang
- Wei Wu (ORCID: https://orcid.org/0000-0001-6404-0317)
- Zerui Liu (ORCID: https://orcid.org/0000-0001-9516-7046)
- Zaijun Chen (ORCID: https://orcid.org/0000-0003-1069-3122)
- Lian Zhou (ORCID: https://orcid.org/0000-0001-5740-9083)
- James Z. Wang (ORCID: https://orcid.org/0000-0003-4379-4173)
- Xinyi Ren (ORCID: https://orcid.org/0009-0003-8514-5988)
Publication Details
- Published
- 2025-01-01
- DOI
- https://doi.org/10.1364/cleo_at.2025.jps200_210
- Primary Topic
- Neural Networks and Reservoir Computing
- Type
- article
- Field-Weighted Citation Impact
- 0.00