Cluster channel equalization using adaptive sensing and reinforcement learning for UAV communication DOI Creative Commons
Xin Liu, Shanghong Zhao, Yanxia Liang

и другие.

PeerJ Computer Science, Год журнала: 2024, Номер 10, С. e2557 - e2557

Опубликована: Дек. 13, 2024

Aiming to address the need for dynamic sensing and channel equalization in UAV cluster communication environments, this article introduces an algorithm based on a U-Net model fuzzy reinforcement Q-learning (U-FRQL-EA). This is designed enhance capabilities of systems. Initially, we develop U-Net-based signal processing that effectively reduces acoustic noise channels enables real-time, accurate perception states by automatically learning features. Subsequently, incorporating neural network approximate Q-values integrating approach with allocation strategy wireless nodes. enhancement not only improves accuracy Q-value approximation but also increases algorithm's adaptability decision-making ability complex environments. Finally, construct U-FRQL-EA combining improved Q-learning. leverages sense real time intelligently adjusts data forwarding strategies values generated Simulation results demonstrate system's bit error rate, enhances quality, optimizes resource utilization, offering novel solution improving performance uncrewed aerial vehicle

Язык: Английский

A Comprehensive Review of Deep Learning: Architectures, Recent Advances, and Applications DOI Creative Commons
Ibomoiye Domor Mienye, Theo G. Swart

Information, Год журнала: 2024, Номер 15(12), С. 755 - 755

Опубликована: Ноя. 27, 2024

Deep learning (DL) has become a core component of modern artificial intelligence (AI), driving significant advancements across diverse fields by facilitating the analysis complex systems, from protein folding in biology to molecular discovery chemistry and particle interactions physics. However, field deep is constantly evolving, with recent innovations both architectures applications. Therefore, this paper provides comprehensive review DL advances, covering evolution applications foundational models like convolutional neural networks (CNNs) Recurrent Neural Networks (RNNs), as well such transformers, generative adversarial (GANs), capsule networks, graph (GNNs). Additionally, discusses novel training techniques, including self-supervised learning, federated reinforcement which further enhance capabilities models. By synthesizing developments identifying current challenges, insights into state art future directions research, offering valuable guidance for researchers industry experts.

Язык: Английский

Процитировано

15
Graph embedding dimensionality reduction combined with improved APO optimized kELM for pneumonia recognition DOI
Wenhao Lai,

Duoduo Liu,

Jialong Yang

и другие.

Biomedical Signal Processing and Control, Год журнала: 2025, Номер 108, С. 107909 - 107909

Опубликована: Апрель 22, 2025

Язык: Английский

Процитировано

0
Cluster channel equalization using adaptive sensing and reinforcement learning for UAV communication DOI Creative Commons
Xin Liu, Shanghong Zhao, Yanxia Liang

и другие.

PeerJ Computer Science, Год журнала: 2024, Номер 10, С. e2557 - e2557

Опубликована: Дек. 13, 2024

Aiming to address the need for dynamic sensing and channel equalization in UAV cluster communication environments, this article introduces an algorithm based on a U-Net model fuzzy reinforcement Q-learning (U-FRQL-EA). This is designed enhance capabilities of systems. Initially, we develop U-Net-based signal processing that effectively reduces acoustic noise channels enables real-time, accurate perception states by automatically learning features. Subsequently, incorporating neural network approximate Q-values integrating approach with allocation strategy wireless nodes. enhancement not only improves accuracy Q-value approximation but also increases algorithm's adaptability decision-making ability complex environments. Finally, construct U-FRQL-EA combining improved Q-learning. leverages sense real time intelligently adjusts data forwarding strategies values generated Simulation results demonstrate system's bit error rate, enhances quality, optimizes resource utilization, offering novel solution improving performance uncrewed aerial vehicle

Язык: Английский

Процитировано

0