Novel grouped-convolution block and tuning algorithm for precomputed 1D-CNNs enables 95% F1 atrial-fibrillation detection on MIT-BIH ECG using 2844 LUTs on AMD Spartan-7 S15 with zero DSPs or BRAM.
LogicNets: Co-Designed Neural Networks and Circuits for Extreme-Throughput Applications,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Precomputed 1D-CNNs for Atrial Fibrillation Detection on Tiny Smart Sensor Systems
Novel grouped-convolution block and tuning algorithm for precomputed 1D-CNNs enables 95% F1 atrial-fibrillation detection on MIT-BIH ECG using 2844 LUTs on AMD Spartan-7 S15 with zero DSPs or BRAM.