Abstract
In the era of scarce spectrum resources, the integration of communication and sensing will become a trend. The combination of radar and communication enables the synchronous transmission of integrated waveform information and radar detection function in the system, eliminating spectrum waste and maximizing equipment efficiency. In this article, we propose a radar sensing algorithm, Beta process factor analysis augmented classifier (BPFAaC), for the 6G integrated sensing and communications (ISAC) scenes. The integrated waveform's adaptive adjustment is guided by the detection sensing algorithm's outcomes. The BPFAaC model, which we propose, takes advantage of the later variable support vector machine (LVSVM) to learn a discriminative subspace with max-margin constraint. To enhance the performance of the prediction, it jointly learns the feature space and the augmented variable classifier in one framework. In this way, BPFAaC combines the advantages of Bayesian model to capture the latent feature of data, Bayesian nonparametrics to determine the number of factors, and LVSVM to induct label information. Moreover, it is natural for BPFAaC to handle outlier rejection problem, which benefits from the data description ability of BPFA. The proposed approach is validated through experiments with the measured HRRP datasets. The experimental results demonstrate that the proposed BPFAaC model outperforms baseline models and achieves more than 91.5% prediction accuracy.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.