13 October 2005 Classification of urea data from a novel near-infrared spectrometer
Author Affiliations +
Near-infrared (NIR) spectroscopy is being applied to the solution of problems in many areas of biomedical and pharmaceutical research. The need for modern medical diagnostics to develop small portable instruments that enable fast and effective monitoring of the biological properties of the human body is apparent. We have developed a portable and robust spectrometer that consists of a two beam interferometer operating in the near-infrared wavelength range for real-time measurements. The device has limited spectral resolution and so methods of computational intelligence and advanced signal processing have been applied to the NIR data to produce more precise and informative diagnostic information. Our target application concerns blood and tissue status in a form that can be interpreted directly by the user, without special knowledge of spectral analysis. More specifically, theories and methods from the field of machine intelligence (learning algorithms, neural networks, etc.) were first applied to classify in vitro urea samples of different concentrations. The results are encouraging, with overall mean squared prediction errors of less than 10-4, and in vivo trials will follow to further develop the device. Non-intrusive diagnostics of this kind are suitable for point-of-care screening.
© (2005) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Dimitrios Kalamatianos, Dimitrios Kalamatianos, Panos Liatis, Panos Liatis, Peter E. Wellstead, Peter E. Wellstead, "Classification of urea data from a novel near-infrared spectrometer", Proc. SPIE 5969, Photonic Applications in Biosensing and Imaging, 59691N (13 October 2005); doi: 10.1117/12.629890; https://doi.org/10.1117/12.629890

Back to Top