Scholarlink

<p>Tuberculosis (TB) remains a global health crisis, particularly in low- and middle-income countries. Traditional diagnostic methods, while reliable, are time-consuming and resource-intensive. This paper presents an advanced biosensor for TB detection, leveraging advancements in nanotechnology, metamaterials, and artificial intelligence. The design is simulated using COMSOL Multiphysics, with key parameters such as graphene chemical potential, incident angle, and resonator dimensions optimized to enhance sensitivity and performance. The sensor demonstrates high sensitivity (up to 1000 GHzRIU<sup>−1</sup>) and a strong linear relationship between resonance frequency and refractive index (R<sup>2</sup> = 98.825%). Machine learning algorithms, essentially XGBoost, are employed to further optimize sensor performance, achieving 100% accuracy in predicting absorption values under various conditions. The proposed sensor offers a promising solution for rapid, non-invasive TB detection, with potential applications in resource-limited settings.</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

Graphene-Enhanced Terahertz Metamaterial Biosensor for Tuberculosis Detection with XGBoost-Based Machine Learning Optimization

  • 期刊论文

  • 发表日期：

    2025年2月20日

查看全文
  • Jacob Wekalao

摘要

Tuberculosis (TB) remains a global health crisis, particularly in low- and middle-income countries. Traditional diagnostic methods, while reliable, are time-consuming and resource-intensive. This paper presents an advanced biosensor for TB detection, leveraging advancements in nanotechnology, metamaterials, and artificial intelligence. The design is simulated using COMSOL Multiphysics, with key parameters such as graphene chemical potential, incident angle, and resonator dimensions optimized to enhance sensitivity and performance. The sensor demonstrates high sensitivity (up to 1000 GHzRIU−1) and a strong linear relationship between resonance frequency and refractive index (R2 = 98.825%). Machine learning algorithms, essentially XGBoost, are employed to further optimize sensor performance, achieving 100% accuracy in predicting absorption values under various conditions. The proposed sensor offers a promising solution for rapid, non-invasive TB detection, with potential applications in resource-limited settings.