Sign in Subscribe
Machine learning

Breakthrough in Machine Learning: SPR-based Refractive Index Sensor for Dengue Detection

Strategic Insights

— 1 min read

Research conducted by the Indian Institute of Technology (IIT) Indian School of Mines has led to the development of a Surface Plasmon Resonance (SPR) fiber optic refractive index sensor that utilizes machine learning techniques for enhanced detection capabilities. The sensor is capable of detecting the dengue virus with high sensitivity, and its design incorporates a bi-metallic nanostructure with Gold (Au) and Zinc Sulphide (ZnS) as the plasmonic sensing layer. This innovative technology has the potential to improve biological applications and disease detection.

Key Takeaways:

  • The SPR-based refractive index sensor has achieved a maximum wavelength sensitivity (WS) of 18,000 nm/RIU and is capable of detecting the dengue virus with a highest WS of 14,285.71 nm/RIU for the infected haemoglobin.
  • The incorporation of machine learning (ML) techniques has significantly improved the sensor's design, with a minimal mean square error (MSE) of 0.2828 and an R value of 0.9998.
  • The neural network (NN) model exhibited the best performance, offering flexible adaptation and derivation of insights based on data.
  • The sensor's effectiveness in forecasting resonance wavelength (RW) for various analytes, as well as errors, classification metrics like accuracy, precision, F1_score, and computation duration were enhanced through ML techniques.
  • Performance metrics such as Detection Accuracy (DA), Figure of Merit (FOM), signal-to-noise ratio (SNR), and quality factor (QF) were determined to have maximum values of 14.285 mm, 158.73 RIU, 5.55, and 79365.055 nm/RIU respectively.
  • The recommended biosensor, which uses the NN model, performed better than all other models and may be used in biological applications.

Statistics:

  • Maximum wavelength sensitivity (WS): 18,000 nm/RIU
  • Highest WS for dengue virus detection: 14,285.71 nm/RIU
  • Minimal mean square error (MSE): 0.2828
  • R value: 0.9998
  • Detection Accuracy (DA): 14.285 mm
  • Figure of Merit (FOM): 158.73 RIU
  • Signal-to-noise ratio (SNR): 5.55
  • Quality factor (QF): 79365.055 nm/RIU

Sources:

  • Spectrochimica Acta Part A. "SPR-based refractive index sensor design with grated Au-ZnS for dengue detection using machine learning." 2025;339:126276.
  • Indian Institute of Technology (IIT) Indian School of Mines. Department of Electronics Engineering. Ananya Banerjee. Dhanbad, 826004 Jharkhand, India.
  • Pergamon-elsevier Science Ltd. The Boulevard, Langford Lane, Kidlington, Oxford OX5 1GB, England.

Read more