The work establishes two proxies linking AirComp distortion to inference quality and derives threshold-based and dual-decomposition power allocations for TDM and FDM modes in an integrated sensing and edge AI system.
Inference-Optimal ISAC via Task-Oriented Feature Transmission and Power Allocation
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
abstract
This work is concerned with the coordination gain in integrated sensing and communication (ISAC) systems under a compress-and-estimate (CE) framework, wherein inference performance is leveraged as the key metric. To enable tractable transceiver design and resource optimization, we characterize inference performance via an error probability bound as a monotonic function of the discriminant gain (DG). This raises the natural question of whether maximizing DG, rather than minimizing mean squared error (MSE), can yield better inference performance. Closed-form solutions for DG-optimal and MSE-optimal transceiver designs are derived, revealing water-filling-type structures and explicit sensing and communication (S\&C) tradeoff. Numerical experiments confirm that DG-optimal design achieves more power-efficient transmission, especially in the low signal-to-noise ratio (SNR) regime, by selectively allocating power to informative features and thus saving transmit power for sensing.
fields
eess.SP 2years
2025 2verdicts
UNVERDICTED 2representative citing papers
A Bayesian distributed ISEA system uses a Gaussian-mixture prior for an RWB estimator at sensing and derives threshold-based optimal power allocation at communication to gain inference performance.
citing papers explorer
-
Optimized Power Control for Multi-User Integrated Sensing and Edge AI
The work establishes two proxies linking AirComp distortion to inference quality and derives threshold-based and dual-decomposition power allocations for TDM and FDM modes in an integrated sensing and edge AI system.
-
Distributed Integrated Sensing and Edge AI Exploiting Prior Information
A Bayesian distributed ISEA system uses a Gaussian-mixture prior for an RWB estimator at sensing and derives threshold-based optimal power allocation at communication to gain inference performance.