Classification of Raman spectra of bacteria using rank order kernels

Alexandros Kyriakides; Evdokia Kastanos; Katerina Hadjigeorgiou; Costas Pitris

doi:10.1117/12.2003714

22 March 2013 Classification of Raman spectra of bacteria using rank order kernels

Alexandros Kyriakides, Evdokia Kastanos, Katerina Hadjigeorgiou, Costas Pitris

Proceedings Volume 8572, Advanced Biomedical and Clinical Diagnostic Systems XI; 85720Y (2013) https://doi.org/10.1117/12.2003714
Event: SPIE BiOS, 2013, San Francisco, California, United States

Abstract

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.

Citation Download Citation

Alexandros Kyriakides, Evdokia Kastanos, Katerina Hadjigeorgiou, and 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); https://doi.org/10.1117/12.2003714

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available