Application of various Pre-processing techniques on Infrared (IR) Spectroscopy data for rapid classification of different ghee samples

Downloads

Downloads per month over past year

Kumar, N and Kiranmaye, AH and Panchariya, PC (2018) Application of various Pre-processing techniques on Infrared (IR) Spectroscopy data for rapid classification of different ghee samples. In: 4th International Conference on Computing, Communications &Maharashtra Automation, August 16-18, 2018, Pune, Maharashtra. (Submitted)

[img]
Preview
PDF - Submitted Version
Download (5Mb) | Preview

Abstract

Abstract- When dealing with IR spectroscopy, the pre­ processing of spectral data is considered to be one of the most important parts of chemometrics modeling. Due to any uncontrollable physical variations may lead to an additive, multiplicative and wavelength-dependent scattering effects in the recorded spectra. Pre-processing techniques basically are required to remove these scattering effects from the spectra and subsequently improve further quantitative and qualitative analysis. popular pre-processing techniques are; baseline correction, smoothing of the spectra, normalization, scattering correction, and spectral derivatives. This paper begins with the theoretical and mathematical foundation of various pre-processing techniques used for IR spectroscopy. Then a qualitative analysis is performed by applying these techniques on the spectral data collected using various samples of ghee. The comparison of various pre-processing is obtained by modeling the data using Principle Component Analysis (PCA) and then the k­ means clustering algorithm.

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: Keywords-chemmometrics; normalization; scattering correction; spectral derivatives; PCA
Subjects: Electronic Systems > Embedded Systems
Divisions: Electronic Systems
Depositing User: Mr. Rabin Chatterjee
Date Deposited: 27 Jul 2021 09:52
Last Modified: 27 Jul 2021 09:52
URI: http://ceeri.csircentral.net/id/eprint/384

Actions (login required)

View Item View Item