Near-infrared spectroscopy moves into warehouses to check incoming drug substances, excipients, and packaging materials, and onto the production floor to monitor characteristics such as blend uniformity, moisture content, and dissolution rate.
Deep Learning Advances Gas Quantification Analysis in Near-Infrared Dual-Comb Spectroscopy
May 15th 2024Researchers from Tsinghua University and Beihang University in Beijing have developed a deep-learning-based data processing framework that significantly improves the accuracy of dual-comb absorption spectroscopy (DCAS) in gas quantification analysis. By using a U-net model for etalon removal and a modified U-net combined with traditional methods for baseline extraction, their framework achieves high-fidelity absorbance spectra, even in challenging conditions with complex baselines and etalon effects.
New Near-Infrared Machine Learning Technique Identifies Dangerous Blood for Transfusion Safety
May 6th 2024Researchers in China have developed a cutting-edge machine learning approach that can detect chylous blood in blood intended for transfusion with more than 90% accuracy. This development promises to significantly reduce the risks associated with blood transfusions and improve the efficiency of blood donation centers.