English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Open

We study model-based end-to-end learning in the context of integrated sensingand communication (ISAC) under hardware impairments. Hardware impairments areusually addressed by means of array calibration with a focus on communicationperformance. However, residual impairments may exist that affect sensingperformance. This paper proposes a data-driven framework for mitigating suchimpairments. A monostatic orthogonal frequency-division multiplexing (OFDM)sensing and multiple-input single-output (MISO) communication scenario isconsidered, incorporating hardware imperfections at the ISAC transceiverantenna array. We propose a novel differentiable version of the orthogonalmatching pursuit (OMP) algorithm that is suitable for multi-target sensing andallows for efficient end-to-end learning of the hardware impairments. Based onthe differentiable OMP, we devise two model-based parameterization strategiesof the ISAC beamformer and sensing receiver to account for hardwareimpairments: (i) learning a dictionary of steering vectors for different anglesand (ii) learning the parameterized hardware impairments. We carry out acomprehensive performance analysis of the proposed model-based learningapproaches and a strong baseline consisting of least-squares beamforming,conventional OMP, and maximum-likelihood symbol detection for communication.Results show that by parameterizing the hardware impairments, learningapproaches offer gains in terms of higher detection probability, positionestimation accuracy, and lower symbol error rate (SER) compared to thebaseline. We demonstrate that learning the parameterized hardware impairmentsoutperforms learning a dictionary of steering vectors, also exhibiting thelowest complexity.

Model-Based End-to-End Learning for Multi-Target Integrated Sensing and Communication under Hardware Impairments