MIMO Signal Multiplexing and Detection Based on Compressive Sensing and Deep Learning

Liu, Chanzi; Zhou, Qingfeng; Wang, Xindi; Chen, Kaiping

doi:10.1109/access.2019.2937490

Cited by 2 publications

(2 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Artificial intelligence techniques have recently been vigorously considered for signal processing and communications. For instance, deep learning is a powerful tool to extract key features of communication systems, e.g., signals, channels, modulation/demodulation schemes and hence it can be effectively employed to address many problems in large-scale wireless communication systems [200]- [202], [206]. Deep learning approaches to address the challenge of CSI sensing and recovery in large dimensional WPN-BCs need further investigations.…”

Section: Artificial Intelligence Based Approachesmentioning

confidence: 99%

Large-Scale Wireless-Powered Networks With Backscatter Communications—A Comprehensive Survey

Rezaei

Tellambura

Herath

2020

IEEE Open J. Commun. Soc.

View full text Add to dashboard Cite

Massive and ubiquitous deployment of devices in networks of fifth generation (5G) and beyond wireless has necessitated the development of ultra-low-power wireless communication paradigms. Recently, wireless-powered networks with backscatter communications (WPN-BCs) has been emerged as a most prominent technology for enabling large-scale selfsustainable wireless networks with the capabilities of RF energy harvesting (EH) and of extreme low power consumption. Therefore, we provide a comprehensive literature review on the fundamentals, challenges and the on-going research efforts in the domain of WPN-BCs. Our emphasis is on large-scale networks. In particular, we discuss signal processing aspects, network design issues and efficient communication techniques. Moreover, we review emerging technologies for WPN-BCs to bring about the best use of resources. Some applications of this innovative technology are also highlighted. Finally, we address some open research problems and future research directions.

show abstract

Section: Artificial Intelligence Based Approachesmentioning

confidence: 99%

Large-Scale Wireless-Powered Networks With Backscatter Communications—A Comprehensive Survey

Rezaei

Tellambura

Herath

2020

IEEE Open J. Commun. Soc.

View full text Add to dashboard Cite

show abstract

“…In the subject of communication, deep reinforcement learning is a potential method to use [123]. Deep learning could be applied to modulation and demodulation phenomena to enhance performance [124], [125]. Many devices get high capacity in multiple access schemes simultaneously with handled interference.…”

Section: ) Machine and Deep Learningmentioning

confidence: 99%

NOMA-Based Backscatter Communications: Fundamentals, Applications, and Advancements

Ahmed,

Shahwar,

Khan

et al. 2024

IEEE Internet Things J.

View full text Add to dashboard Cite

Developing wireless communication technologies is an ongoing process to satisfy the requirements of new applications and the increasing proliferation of interconnected devices. Using non-orthogonal multiple access (NOMA) and backscatter communication (BC) has surfaced as an advantageous approach for enhancing energy efficiency (EE), maximizing sum rates, ensuring security, and optimizing resource allocation. NOMA permits multiple users to share time and frequency resources even without the requirement of antenna arrays, whereas BC employs ambient RF signals for low-power communication. By integrating the advantages of NOMA and BC, NOMA-based BC provides a solution for future energyefficient and low-power networks. Despite its potential, there is a lack of a comprehensive overview of NOMA-BC, necessitating a systematic survey that covers its principles, applications, challenges, and future directions. This survey aims to bridge the gap by exploring NOMA-BC within B5G and 6G networks. We delve into its technical aspects, performance optimization techniques, and real-world applications to enhance understanding and knowledge. First, we cover topics such as enhancing EE, maximizing the sum rates, ensuring security, and optimizing resource allocation. Our primary goal is to provide researchers and practitioners with valuable insights that enable them to grasp the capabilities and benefits of NOMA-BC. To achieve this, we comprehensively analyze various schemes' performance by presenting detailed summary tables. These analyses cover a range of scenarios, methods, and objectives, focusing on emerging B5G technologies such as reconfigurable intelligent surfaces (RIS), visible light communication (VLC), and unmanned aerial vehicle (UAV) communication. By examining NOMA-BC's effectiveness within these contexts, we aim to provide a holistic view of its potential and applicability in diverse technological domains. Moreover, our survey identifies and discusses open research challenges and proposes future directions to guide researchers toward unexplored areas and facilitate advancements in NOMA-BC.

show abstract

MIMO Signal Multiplexing and Detection Based on Compressive Sensing and Deep Learning

Cited by 2 publications

References 36 publications

Large-Scale Wireless-Powered Networks With Backscatter Communications—A Comprehensive Survey

Large-Scale Wireless-Powered Networks With Backscatter Communications—A Comprehensive Survey

NOMA-Based Backscatter Communications: Fundamentals, Applications, and Advancements

Contact Info

Product

Resources

About