Scholarlink

<p>Air quality monitoring in hazardous environments is crucial for protecting public health and the environment. Traditional stationary systems often fail to cover large, dynamic areas, making real-time detection challenging. Manual monitoring with handheld devices, though common, exposes personnel to hazardous conditions, posing significant health risks due to toxic substances and chemicals. Existing mobile robotic systems for environmental monitoring typically rely on basic sensors and lack advanced data analysis capabilities. This research addresses these gaps by introducing a novel framework using the Recurrent Intelligent Data Archive (RIDA), which combines Recurrent Neural Networks (RNNs) with relational database management systems (RDBMS). RIDA enhances prediction accuracy by efficiently processing, integrating, and managing data, overcoming the limitations of standard RNNs. The mobile robot in this system is equipped with sensors and telemetry to remotely transmit data to a base station, allowing real-time data analysis in hazardous environments and predicting the necessity for personnel presence. The framework demonstrates improved accuracy, with training and testing accuracies of 85% and 88%, respectively, offering a scalable solution for real-time monitoring in hazardous environments and significantly enhancing safety and environmental management.</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

Deep Learning-Based analysis of air quality in hazardous environments using mobile robot

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年7月18日

查看全文
  • Abbas Abdullahi,
  • Gregory Onwodi,
  • Amina Sambo Magaji,
  • Ameer Mohammed,
  • Abdussalam El-Suleiman,
  • Rabiu B. Ahmad

摘要

Air quality monitoring in hazardous environments is crucial for protecting public health and the environment. Traditional stationary systems often fail to cover large, dynamic areas, making real-time detection challenging. Manual monitoring with handheld devices, though common, exposes personnel to hazardous conditions, posing significant health risks due to toxic substances and chemicals. Existing mobile robotic systems for environmental monitoring typically rely on basic sensors and lack advanced data analysis capabilities. This research addresses these gaps by introducing a novel framework using the Recurrent Intelligent Data Archive (RIDA), which combines Recurrent Neural Networks (RNNs) with relational database management systems (RDBMS). RIDA enhances prediction accuracy by efficiently processing, integrating, and managing data, overcoming the limitations of standard RNNs. The mobile robot in this system is equipped with sensors and telemetry to remotely transmit data to a base station, allowing real-time data analysis in hazardous environments and predicting the necessity for personnel presence. The framework demonstrates improved accuracy, with training and testing accuracies of 85% and 88%, respectively, offering a scalable solution for real-time monitoring in hazardous environments and significantly enhancing safety and environmental management.