Scholarlink

<p>Underwater acoustic communication (UAC) is a fundamental component of various applications, including marine exploration, underwater robotics, and environmental monitoring. However, the dynamic conditions of underwater environments pose significant challenges to the development of high-performance communication systems. This study introduces a novel dynamic adaptive modulation approach that enables smooth switching between several communication approaches using machine learning methods such as decision trees (DT) and random forests (RF). Through continuous monitoring of environmental parameters, such as temperature, salinity, depth, and acoustic noise levels, the system gathers real-time information to serve as input features for the machine learning model. The model is trained and evaluated to identify the most suitable modulation approach for the prevailing underwater conditions. The DT model achieved an accuracy of 97%, whereas the RF model performed slightly better, reaching 98% accuracy. In addition, the switching delay for the DT model was 2.75&#xa0;ms, whereas that for RF was 0.97&#xa0;ms. The approach improves effective data transmission by reducing error rates, enhancing system robustness, and dynamically adjusting to changing underwater conditions, thereby ensuring optimal communication efficiency in challenging environments.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

AI-powered cognitive modulation adaptation for energy-efficient underwater acoustic communication

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年10月28日

查看全文
  • Lakshmi Kadali,
  • Ashraf Hossain,
  • Nanda Kishore Billa,
  • Kavicharan Mummaneni

摘要

Underwater acoustic communication (UAC) is a fundamental component of various applications, including marine exploration, underwater robotics, and environmental monitoring. However, the dynamic conditions of underwater environments pose significant challenges to the development of high-performance communication systems. This study introduces a novel dynamic adaptive modulation approach that enables smooth switching between several communication approaches using machine learning methods such as decision trees (DT) and random forests (RF). Through continuous monitoring of environmental parameters, such as temperature, salinity, depth, and acoustic noise levels, the system gathers real-time information to serve as input features for the machine learning model. The model is trained and evaluated to identify the most suitable modulation approach for the prevailing underwater conditions. The DT model achieved an accuracy of 97%, whereas the RF model performed slightly better, reaching 98% accuracy. In addition, the switching delay for the DT model was 2.75 ms, whereas that for RF was 0.97 ms. The approach improves effective data transmission by reducing error rates, enhancing system robustness, and dynamically adjusting to changing underwater conditions, thereby ensuring optimal communication efficiency in challenging environments.