Reinforcement Learning Based Efficient Underwater Image Communication

Su, Wei; Tao, Jincheng; Pei, Yuehua; You, Xudong; Xiao, Liang; Cheng, En

doi:10.1109/lcomm.2020.3041937

Cited by 16 publications

(5 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As UWA environment is complex and there is no standard channel model for algorithm evaluation, experiment is a persuasive evaluation method. Reinforcement learning has the ability to learn from the interaction of environment and agent without any prior knowledge, so the Q-table can be initialized with all zeros, such as in [24][25][26][27][28][29][30][31][32]. Considering practical implementation, this paper has shown how the pre-training helps to improve the system performance.…”

Section: Discussionmentioning

confidence: 99%

“…Reinforcement learning (RL) has been used to address the problem of maximizing rewards or achieving specific goals by learning strategies during the interaction of an agent with its environment. In UWA communication systems, some researchers have employed RL to solve adaptive problems, such as adaptive data and image transmission [23,24], and adaptive routing [25][26][27]. In terms of relay selection, Jadoon et al [28] firstly proposed QLbased relay selection algorithm (QL-RSA) in wireless sensor networks.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Reinforcement Learning Based Relay Selection for Underwater Acoustic Cooperative Networks

Zhang

Shen

et al. 2022

Remote Sensing

View full text Add to dashboard Cite

In the complex and dynamically varying underwater acoustic (UWA) channel, cooperative communication can improve throughput for UWA sensor networks. In this paper, we design a reasonable relay selection strategy for efficient cooperation with reinforcement learning (RL), considering the characteristics of UWA channel variation and long transmission delay. The proposed scheme establishes effective state and reward expression to better reveal the relationship between RL and UWA environment. Meanwhile, simulated annealing (SA) algorithm is integrated with RL to improve the performance of relay selection, where exploration rate of RL is dynamically adapted by SA optimization through the temperature decline rate. Furthermore, the fast reinforcement learning (FRL) strategy with pre-training process is proposed for practical UWA network implementation. The whole proposed SA-FRL scheme has been evaluated by both simulation and experimental data. The simulation and experimental results show that the proposed relay selection scheme can converge more quickly than classical RL and random selection with the increase of the number of iterations. The reward, access delay and data rate of SA-FRL can converge at the highest value and are close to the ideal optimum value. All in all, the proposed SA-FRL relay selection scheme can improve the communication efficiency through the selection of the relay nodes with high link quality and low access delay.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Reinforcement Learning Based Relay Selection for Underwater Acoustic Cooperative Networks

Zhang

Shen

et al. 2022

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…The paper [33] applies contrastive learning within underwater networks to compress machine-friendly features under low bit-rates, devoted to underwater machine vision. Machine learning is also exploited in paper [34], whose main goal is to optimally set transmission parameters to avoid bandwidth Fig. 1.…”

Section: Related Workmentioning

confidence: 99%

A Semantic-Oriented Federated Learning for Hybrid Ground–Aqua Computing Systems

Picano,

Fantacci

2024

IEEE Internet Things J.

View full text Add to dashboard Cite

Nowadays, an ambitious target of the next generation networks is to develop intelligent overarching spaceair-ground-aqua computing systems, in order to provide a smart ecosystem able to efficiently operate computation in heterogeneous domains. In particular, in such a context, the underwater environment requires a special attention, since it is recognized as the most challenging domain, due to channel impairments and adverse propagation conditions. This paper proposes a self-intelligent system able to efficiently perform underwater environment monitoring or underwater survey of critical infrastructure, by resorting to the use of the semantic communication paradigm to lower the impairments due to the underwater channel propagation conditions. In particular, in our case, images sent by underwater devices are collected by shore small base stations (SSBSs) to form their training dataset to take part in a federated learning process with a ground base station. In particular, the paper considers a semantic communication scheme based on a deep-convolution neural networks encoder-decoder architecture for an efficient exploitation of the data transmission from underwater devices to the linked SSBSs. Performance analysis is provided to show the better behavior of the proposed system in comparison with the conventional alternative that does not involve the use of the semantic communications approach. Finally, a specific performance evaluation analysis is devoted to the investigation of the convergence behavior of the proposed federated learning procedure in reference to the cross groundaqua system considered in order to highlight its advantages with respect to a classical implementation.

show abstract

“…La fibra monomodo, permite la propagación de un único modo de luz, esto se logra reduciendo el diámetro del núcleo de la fibra a un tamaño de 8.3 a 10 micrones, lo que asegura una sola dirección de propagación [23] [24]. Las fibras monomodo permiten alcanzar grandes distancias de propagación de hasta 400 km y transmitir elevadas tasas de información [25] [26] [27] [28].…”

Section: Metodologíaunclassified

Análisis de propagación de las comunicaciones ópticas subacuáticas

Muñoz Zambrano,

Ruiz Jimenez

2023

Perspectivas

View full text Add to dashboard Cite

Este artículo presenta un estudio de la propagación de luz en medios acuáticos. El objetivo principal fue investigar y comprender los fenómenos que causan perdidas de propagación en la transmision de luz en medios líquidos, específicamente agua bajo diferentes condiciones. Para estudiar el comportamiento de estas ondas en un medio liquido se realizó una simulación utilizando una fibra óptica monomodo Corning SMF-28 con una transición de agua utilizando el software FIMMWAVE y realizando un análisis a través de regresión polinomail, relacionando la variacion de la longitud de onda en funcion de la permitividad del agua, con lo cual se obtuvo una ecuación con un comportamiento polinómico de orden 11. Las longitudes de onda analizadas abarcaron un rango de 0.18 a 1.13 μm, considerando agua potable como el medio de transición. En el analisis de resultados se utilizó la herramienta WG Scanner de FIMMWAVE para analizar los modos de propagación en la fibra óptica, observando un comportamiento exponencial más allá de cierto valor de longitud de onda. Este estudio busca avanzar en el conocimiento de las comunicaciones subacuáticas y proporcionar información relevante para el diseño y la optimización de sistemas de transmisión óptica en entornos acuáticos. La comprensión de la propagación de la luz en este contexto es fundamental para mejorar la calidad y la eficiencia de las comunicaciones submarinas.

show abstract

Reinforcement Learning Based Efficient Underwater Image Communication

Cited by 16 publications

References 13 publications

Reinforcement Learning Based Relay Selection for Underwater Acoustic Cooperative Networks

Reinforcement Learning Based Relay Selection for Underwater Acoustic Cooperative Networks

A Semantic-Oriented Federated Learning for Hybrid Ground–Aqua Computing Systems

Análisis de propagación de las comunicaciones ópticas subacuáticas

Contact Info

Product

Resources

About