22 March 2013 Classification of Raman spectra of bacteria using rank order kernels
Author Affiliations +
The range of applications of Raman-based classification has expanded significantly, including applications in bacterial identification. In this paper, we propose the use of Rank Order Kernels to classify bacterial samples. Rank Order Kernels are two-dimensional image functions which operate on two-dimensional images. The first step in the classification therefore, is to transform the Raman spectra to two-dimensional images. This is achieved by splitting the spectra into segments and calculating the ratio between the mean value of each and every other segment. This creates a two-dimensional matrix of ratios for each Raman spectrum. A similarity metric based on rank order kernels operating on the two-dimensional matrices is then used with a nearest neighbor algorithm for classification. Our results show that this method is comparable in accuracy to other methods which were used previously for the same data set.
© (2013) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Alexandros Kyriakides, Alexandros Kyriakides, Evdokia Kastanos, Evdokia Kastanos, Katerina Hadjigeorgiou, Katerina Hadjigeorgiou, Costas Pitris, Costas Pitris, } "Classification of Raman spectra of bacteria using rank order kernels", Proc. SPIE 8572, Advanced Biomedical and Clinical Diagnostic Systems XI, 85720Y (22 March 2013); doi: 10.1117/12.2003714; https://doi.org/10.1117/12.2003714

Back to Top