Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2404.10235 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916208381526016 |
|---|---|
| author | Jin, Xibin Li, Guoliang Wang, Shuai Wen, Miaowen Xu, Chengzhong Poor, H. Vincent |
| author_facet | Jin, Xibin Li, Guoliang Wang, Shuai Wen, Miaowen Xu, Chengzhong Poor, H. Vincent |
| contents | Integrated sensing and communication (ISAC) is a promising solution to accelerate edge inference via the dual use of wireless signals. However, this paradigm needs to minimize the inference error and latency under ISAC co-functionality interference, for which the existing ISAC or edge resource allocation algorithms become inefficient, as they ignore the inter-dependency between low-level ISAC designs and high-level inference services. This letter proposes an inference-oriented ISAC (IO-ISAC) scheme, which minimizes upper bounds on end-to-end inference error and latency using multi-objective optimization. The key to our approach is to derive a multi-view inference model that accounts for both the number of observations and the angles of observations, by integrating a half-voting fusion rule and an angle-aware sensing model. Simulation results show that the proposed IO-ISAC outperforms other benchmarks in terms of both accuracy and latency. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_10235 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Integrated Sensing and Communication for Edge Inference with End-to-End Multi-View Fusion Jin, Xibin Li, Guoliang Wang, Shuai Wen, Miaowen Xu, Chengzhong Poor, H. Vincent Signal Processing Integrated sensing and communication (ISAC) is a promising solution to accelerate edge inference via the dual use of wireless signals. However, this paradigm needs to minimize the inference error and latency under ISAC co-functionality interference, for which the existing ISAC or edge resource allocation algorithms become inefficient, as they ignore the inter-dependency between low-level ISAC designs and high-level inference services. This letter proposes an inference-oriented ISAC (IO-ISAC) scheme, which minimizes upper bounds on end-to-end inference error and latency using multi-objective optimization. The key to our approach is to derive a multi-view inference model that accounts for both the number of observations and the angles of observations, by integrating a half-voting fusion rule and an angle-aware sensing model. Simulation results show that the proposed IO-ISAC outperforms other benchmarks in terms of both accuracy and latency. |
| title | Integrated Sensing and Communication for Edge Inference with End-to-End Multi-View Fusion |
| topic | Signal Processing |
| url | https://arxiv.org/abs/2404.10235 |