Survey on deep learning-based integrated sensing and communication systems
With the deep integration of wireless communication and radar sensing technologies, integrated sensing and communication (ISAC) shares hardware platforms and spectrum resources. It has demonstrated significant potential for enhancing system efficiency. However, traditional ISAC relying on prior mode...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | Chinese |
| Published: |
Editorial Department of Journal on Communications
2025-06-01
|
| Series: | Tongxin xuebao |
| Subjects: | |
| Online Access: | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2025103/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1839638042701201408 |
|---|---|
| author | RAN Xinyi CHEN Qianbin XU Yongjun ZUO Wenke ZHAO Yun CHEN Li |
| author_facet | RAN Xinyi CHEN Qianbin XU Yongjun ZUO Wenke ZHAO Yun CHEN Li |
| author_sort | RAN Xinyi |
| collection | DOAJ |
| description | With the deep integration of wireless communication and radar sensing technologies, integrated sensing and communication (ISAC) shares hardware platforms and spectrum resources. It has demonstrated significant potential for enhancing system efficiency. However, traditional ISAC relying on prior models and expert knowledge has struggled to address real-time communication and sensing demands in dynamic environments. The rapid development of deep learning recently provided a novel paradigm to resolve these limitations, enabling systems to process massive data more effectively, achieve adaptive learning, and make intelligent decisions in complex environments, thereby optimizing system performance. A comprehensive review was conducted on deep learning-based ISAC. Firstly, the principles, the system model, the network architecture, and the types of technical solutions of ISAC were introduced. Then, the mainly adopted deep learning model architectures in ISAC were analyzed. Furthermore, the research situation of deep learning in typical scenarios such as channel estimation, channel coding, resource allocation, human detection, and target recognition and tracking was systematically investigated. Finally, key technical challenges and future directions in deep learning-driven ISAC were discussed. The research contributed to the deep integration of communication and sensing in 6G networks and facilitated the coordinated development of intelligent networks, holding important theoretical and practical value. |
| format | Article |
| id | doaj-art-614d1bc4054a43fda2b5b7593f3e8e15 |
| institution | Matheson Library |
| issn | 1000-436X |
| language | zho |
| publishDate | 2025-06-01 |
| publisher | Editorial Department of Journal on Communications |
| record_format | Article |
| series | Tongxin xuebao |
| spelling | doaj-art-614d1bc4054a43fda2b5b7593f3e8e152025-07-05T19:00:12ZzhoEditorial Department of Journal on CommunicationsTongxin xuebao1000-436X2025-06-0146233250114256712Survey on deep learning-based integrated sensing and communication systemsRAN XinyiCHEN QianbinXU YongjunZUO WenkeZHAO YunCHEN LiWith the deep integration of wireless communication and radar sensing technologies, integrated sensing and communication (ISAC) shares hardware platforms and spectrum resources. It has demonstrated significant potential for enhancing system efficiency. However, traditional ISAC relying on prior models and expert knowledge has struggled to address real-time communication and sensing demands in dynamic environments. The rapid development of deep learning recently provided a novel paradigm to resolve these limitations, enabling systems to process massive data more effectively, achieve adaptive learning, and make intelligent decisions in complex environments, thereby optimizing system performance. A comprehensive review was conducted on deep learning-based ISAC. Firstly, the principles, the system model, the network architecture, and the types of technical solutions of ISAC were introduced. Then, the mainly adopted deep learning model architectures in ISAC were analyzed. Furthermore, the research situation of deep learning in typical scenarios such as channel estimation, channel coding, resource allocation, human detection, and target recognition and tracking was systematically investigated. Finally, key technical challenges and future directions in deep learning-driven ISAC were discussed. The research contributed to the deep integration of communication and sensing in 6G networks and facilitated the coordinated development of intelligent networks, holding important theoretical and practical value.http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2025103/ISACdeep learningchannel estimationchannel codingresource allocationhuman detectiontarget recognition and tracking |
| spellingShingle | RAN Xinyi CHEN Qianbin XU Yongjun ZUO Wenke ZHAO Yun CHEN Li Survey on deep learning-based integrated sensing and communication systems Tongxin xuebao ISAC deep learning channel estimation channel coding resource allocation human detection target recognition and tracking |
| title | Survey on deep learning-based integrated sensing and communication systems |
| title_full | Survey on deep learning-based integrated sensing and communication systems |
| title_fullStr | Survey on deep learning-based integrated sensing and communication systems |
| title_full_unstemmed | Survey on deep learning-based integrated sensing and communication systems |
| title_short | Survey on deep learning-based integrated sensing and communication systems |
| title_sort | survey on deep learning based integrated sensing and communication systems |
| topic | ISAC deep learning channel estimation channel coding resource allocation human detection target recognition and tracking |
| url | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2025103/ |
| work_keys_str_mv | AT ranxinyi surveyondeeplearningbasedintegratedsensingandcommunicationsystems AT chenqianbin surveyondeeplearningbasedintegratedsensingandcommunicationsystems AT xuyongjun surveyondeeplearningbasedintegratedsensingandcommunicationsystems AT zuowenke surveyondeeplearningbasedintegratedsensingandcommunicationsystems AT zhaoyun surveyondeeplearningbasedintegratedsensingandcommunicationsystems AT chenli surveyondeeplearningbasedintegratedsensingandcommunicationsystems |