Derives explicit discriminant gain as a function of precoding coefficients in ISCC networks and proposes a precoding algorithm that improves sensing accuracy by up to 15% on synthetic data and 10% on real data in low-SNR simulations.
Progressive feature transmission for split classification at the wireless edge,
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
eess.SP 3representative citing papers
Derives closed-form DG-optimal and MSE-optimal transceiver designs for ISAC under compress-and-estimate framework, with numerical results showing DG-optimal design is more power-efficient at low SNR by selective feature allocation.
citing papers explorer
-
Edge AI Inference in ISCC Networks: Sensing Accuracy Analysis and Precoding Design
Derives explicit discriminant gain as a function of precoding coefficients in ISCC networks and proposes a precoding algorithm that improves sensing accuracy by up to 15% on synthetic data and 10% on real data in low-SNR simulations.
-
Inference-Optimal ISAC via Task-Oriented Feature Transmission and Power Allocation
Derives closed-form DG-optimal and MSE-optimal transceiver designs for ISAC under compress-and-estimate framework, with numerical results showing DG-optimal design is more power-efficient at low SNR by selective feature allocation.
- Distributed Integrated Sensing and Edge AI Exploiting Prior Information