Saumita Kar
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Saumita Kar has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Bipan Tudu
Jadavpur University
2 shared publications - Rajib Bandyopadhyay
Department of Instrumentation and Electronics Engineering, Jadavpur University, Kolkata, India
2 shared publications Anil K. Bag
Heritage Institute of Technology
1 shared publication- Arun Jana
Centre for Development of Advanced Computing (C-DAC), Kolkata, India
1 shared publication Bipan Tudu
Department of Instrumentation and Electronics Engineering, Jadavpur University, Kolkata, India
1 shared publicationRajib Bandyopadhyay
Department of Instrumentation and Electronics Engineering, Jadavpur University, Kolkata, India
1 shared publication
Latest Publications
- 19 March 2024
- Published by Springer Nature in Journal of Food Science and Technology
- Vol. 61 (10) , 1955-1964
Statistical machine learning techniques applied to NIR spectral data for rapid detection of sudan dye-I in turmeric powders with optimized pre-processing and wavelength selection
Machine learning techniques were applied systematically to the spectral data of near-infrared (NIR) spectroscopy to find out the sudan dye I adulterants in turmeric powders. Turmeric powder is one of the most commonly used spice and a simple target for adulteration. Pure turmeric powder was prepared at the laboratory and spiked with sudan dye I adulterants. The spectral data of these adulterated mixtures were obtained by NIR spectrometer and investigated accordingly. The concentrations of the adulterants were 1%, 5%, 10%, 15%, 20%, 25%, 30% (w/w) respectively. Exploratory data analysis was done for the visualization of the adulterant classes by principal component analysis (PCA). Optimization of the pre-processing and wavelength selection was done by cross-validation techniques using a partial least squares regression (PLSR) model. For quantitative analysis four different regression techniques were applied namely ensemble tree regression (ENTR), support vector regression (SVR), principal component regression (PCR), and PLSR, and a comparative analysis was done. The best method was found to be PLSR. The accuracy of the PLSR analysis was determined with the coefficients of determination (R2) of greater than 0.97 and with root mean square error (RMSE) of less than 0.93 respectively. For the verification of the robustness of the model, the Figure of merit (FOM) of the model was derived with the help of the Net analyte signal (NAS) theory. The current study established that the NIR spectroscopy can be applied to detect and quantify the amount of sudan dye I adulterants added to the turmeric powders with satisfactory accuracy.
- 19 March 2024
- Published by Springer Nature in Journal of Food Science and Technology
- Vol. 61 (10) , 1955-1964
Statistical machine learning techniques applied to NIR spectral data for rapid detection of sudan dye-I in turmeric powders with optimized pre-processing and wavelength selection
Machine learning techniques were applied systematically to the spectral data of near-infrared (NIR) spectroscopy to find out the sudan dye I adulterants in turmeric powders. Turmeric powder is one of the most commonly used spice and a simple target for adulteration. Pure turmeric powder was prepared at the laboratory and spiked with sudan dye I adulterants. The spectral data of these adulterated mixtures were obtained by NIR spectrometer and investigated accordingly. The concentrations of the adulterants were 1%, 5%, 10%, 15%, 20%, 25%, 30% (w/w) respectively. Exploratory data analysis was done for the visualization of the adulterant classes by principal component analysis (PCA). Optimization of the pre-processing and wavelength selection was done by cross-validation techniques using a partial least squares regression (PLSR) model. For quantitative analysis four different regression techniques were applied namely ensemble tree regression (ENTR), support vector regression (SVR), principal component regression (PCR), and PLSR, and a comparative analysis was done. The best method was found to be PLSR. The accuracy of the PLSR analysis was determined with the coefficients of determination (R2) of greater than 0.97 and with root mean square error (RMSE) of less than 0.93 respectively. For the verification of the robustness of the model, the Figure of merit (FOM) of the model was derived with the help of the Net analyte signal (NAS) theory. The current study established that the NIR spectroscopy can be applied to detect and quantify the amount of sudan dye I adulterants added to the turmeric powders with satisfactory accuracy.
- 29 April 2019
- Published by Taylor & Francis in Food Additives & Contaminants: Part A
- Vol. 36 (6) , 863-875
FT-NIR spectroscopy coupled with multivariate analysis for detection of starch adulteration in turmeric powder
This paper investigates the feasibility of Fourier transform near-infrared (FT-NIR) spectroscopy, a fast and easy method based on chemometric methods to detect corn starch illegally added to turmeric powder. In this work, the pure turmeric powders were blended with corn starch to generate different concentrations (1–30%)(w/w) of starch-adulterated turmeric samples. The reflectance spectra of total of 224 samples were taken by FT-NIR spectroscopy. The exploratory data analysis was done by principal component analysis (PCA). The starch related peaks were selected by variable importance in projection (VIP) method and were explored by examination of original reflectance spectra, 1st derivative spectra, PCA loadings and β coefficients plot of the partial least square regression (PLSR) model. The coefficient of determination (R2) and root-mean-square error of partial least square regression (PLSR) models were found to be 0.91–0.99 and 0.23–1.3%, respectively, depending on the pre-processing techniques of spectral data. The figure of merit (FOM) of the model was found with the help of net analyte signal (NAS) theory.
- 29 April 2019
- Published by Taylor & Francis in Food Additives & Contaminants: Part A
- Vol. 36 (6) , 863-875
FT-NIR spectroscopy coupled with multivariate analysis for detection of starch adulteration in turmeric powder
This paper investigates the feasibility of Fourier transform near-infrared (FT-NIR) spectroscopy, a fast and easy method based on chemometric methods to detect corn starch illegally added to turmeric powder. In this work, the pure turmeric powders were blended with corn starch to generate different concentrations (1–30%)(w/w) of starch-adulterated turmeric samples. The reflectance spectra of total of 224 samples were taken by FT-NIR spectroscopy. The exploratory data analysis was done by principal component analysis (PCA). The starch related peaks were selected by variable importance in projection (VIP) method and were explored by examination of original reflectance spectra, 1st derivative spectra, PCA loadings and β coefficients plot of the partial least square regression (PLSR) model. The coefficient of determination (R2) and root-mean-square error of partial least square regression (PLSR) models were found to be 0.91–0.99 and 0.23–1.3%, respectively, depending on the pre-processing techniques of spectral data. The figure of merit (FOM) of the model was found with the help of net analyte signal (NAS) theory.
- 25 November 2017
- Published by Springer Nature in Food Analytical Methods
- Vol. 11 (5) , 1291-1302
Application of Near-Infrared Spectroscopy for the Detection of Metanil Yellow in Turmeric Powder
- 25 November 2017
- Published by Springer Nature in Food Analytical Methods
- Vol. 11 (5) , 1291-1302
Application of Near-Infrared Spectroscopy for the Detection of Metanil Yellow in Turmeric Powder