Scholarlink

<p>Understanding a smart environment’s location is essential, as traditional GPS systems do not work well indoors. This paper presents AIILS, a novel tracking method that combines Bluetooth Low Energy (BLE) and Received Signal Strength Indicator (RSSI) signals to achieve an effective interior tracking base system. With the addition of filtering the signal, the system will be very effective in handling noisy data and ensure better predictions and scalability. This proposed architecture integrates adaptive pre-processing, a strong client–server model, and online web monitoring, making it fit for different sectors including underground mine as well as industrial facility environments. To improve the overall scalability and accuracy of the system an efficient Machine Learning Algorithm has also been part of the overall system to precisely access the current location of the targeted node. The findings from simulations and statistical analysis are used to evaluate the efficacy of the proposed method. The resultant outcome confirms the supremacy of the proposed framework in terms of a lower average discrepancy, and acceptable Packet Delivery Ratio of 98.4% along with an adequate model having an R2 value equivalent to one and a MAPE of 0.01%. The effectiveness of the AIILS is demonstrated through an extensive evaluation of the suggested framework. A thorough analysis of the proposed system demonstrates the effectiveness of the AIILS offering an extensive way of localization in an interior setting.</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

An AI enhanced IoT driven localization system (AIILS) for underground mine environments through implementation of bluetooth low energy (BLE)

  • 期刊论文

  • 发表日期：

    2025年7月4日

查看全文
  • Pulakesh Roy,
  • Surabhi Solanki,
  • Sachin Kumar,
  • Santu Mondal,
  • Sheuli Chakraborty,
  • Biru Rajak,
  • Rajib Banerjee,
  • Arindam Biswas

摘要

Understanding a smart environment’s location is essential, as traditional GPS systems do not work well indoors. This paper presents AIILS, a novel tracking method that combines Bluetooth Low Energy (BLE) and Received Signal Strength Indicator (RSSI) signals to achieve an effective interior tracking base system. With the addition of filtering the signal, the system will be very effective in handling noisy data and ensure better predictions and scalability. This proposed architecture integrates adaptive pre-processing, a strong client–server model, and online web monitoring, making it fit for different sectors including underground mine as well as industrial facility environments. To improve the overall scalability and accuracy of the system an efficient Machine Learning Algorithm has also been part of the overall system to precisely access the current location of the targeted node. The findings from simulations and statistical analysis are used to evaluate the efficacy of the proposed method. The resultant outcome confirms the supremacy of the proposed framework in terms of a lower average discrepancy, and acceptable Packet Delivery Ratio of 98.4% along with an adequate model having an R2 value equivalent to one and a MAPE of 0.01%. The effectiveness of the AIILS is demonstrated through an extensive evaluation of the suggested framework. A thorough analysis of the proposed system demonstrates the effectiveness of the AIILS offering an extensive way of localization in an interior setting.