Scholarlink

<p>This study presents an advanced annular photonic crystal biosensor designed for the detection and classification of bacterial cells through spectral analysis. The biosensor is analysed for its response to ten different bacterial species, focusing on shifts in peak resonant wavelength and amplitude. Each bacteria produced unique spectral signatures, with significant variations in peak wavelengths. To enhance detection capabilities, we integrated machine learning models, specifically Random Forest and Support Vector Machine (SVM). The Random Forest model, evaluated using Leave-One-Out Cross-Validation (LOOCV), achieved a high accuracy of 90%, effectively interpreting the spectral data. Conversely, the SVM model showed lower accuracy at 30%. This combination of photonic crystal bio sensing and machine learning offers a robust approach for rapid, non-invasive bacterial detection, advancing diagnostic techniques in healthcare and environmental monitoring.</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

Design and analysis of machine learning enhanced photonic crystal biosensor for bacterial detection

  • 期刊论文

  • 发表日期：

    2025年2月1日

查看全文
  • Sheethal Raj T G,
  • Nirmala Hiremani

摘要

This study presents an advanced annular photonic crystal biosensor designed for the detection and classification of bacterial cells through spectral analysis. The biosensor is analysed for its response to ten different bacterial species, focusing on shifts in peak resonant wavelength and amplitude. Each bacteria produced unique spectral signatures, with significant variations in peak wavelengths. To enhance detection capabilities, we integrated machine learning models, specifically Random Forest and Support Vector Machine (SVM). The Random Forest model, evaluated using Leave-One-Out Cross-Validation (LOOCV), achieved a high accuracy of 90%, effectively interpreting the spectral data. Conversely, the SVM model showed lower accuracy at 30%. This combination of photonic crystal bio sensing and machine learning offers a robust approach for rapid, non-invasive bacterial detection, advancing diagnostic techniques in healthcare and environmental monitoring.