- Home
- Research
- Photonic Data Science
- Publications
- Recursive feature elimination in Raman spectra with support vector machines
Recursive feature elimination in Raman spectra with support vector machines
in: Frontiers of Optoelectronics (2017)
The presence of irrelevant and correlated data points in a Raman spectrum can lead to a decline in classifier performance. We introduce support vector machine-based recursive feature elimination into the field of Raman spectroscopy and demonstrate its performance on a dataset of spectra of clinically relevant microorganisms in urine samples, along with patient samples. As the original technique is only suitable for two-class problems, we adapt it to the multi-class setting. It is shown that a large amount of spectral points can be removed without degrading the prediction accuracy of the resulting model notably.