PubAg

Main content area

You searched for: Author "Sarathjith, M.C." Remove constraint Author: "Sarathjith, M.C." Subject models Remove constraint Subject: models Subject algorithms Remove constraint Subject: algorithms
Start Over

Search

2  Search Results

1 - 2 of 2
Number of results to display per page

Search Results

1. Optimizing wavelength selection by using informative vectors for parsimonious infrared spectra modelling

Author:
Sarathjith, M.C.,   et al.   ; Ng, Wartini; Minasny, Budiman; Malone, Brendan P.; Das, Bhabani S.;     Show all 5 Authors
Source:
Computers and electronics in agriculture 2019 v.158 pp. 201-210
ISSN:
0168-1699
Subject:
algorithms; carbon; cation exchange capacity; clay; covariance; data collection; infrared spectroscopy; least squares; models; pH; prediction; sand fraction; wavelengths
Abstract:
... Infrared spectroscopy has been widely adopted by various agricultural research. The typical spectra variables contain thousands of wavelengths. These large number of spectra variables often contribute to collinearity, and redundancies rather than relevant information. Variable selection of the predictors is an important step to create a robust calibration model from these spectra data. This paper ...
DOI:
10.1016/j.compag.2019.02.003

2. Variable indicators for optimum wavelength selection in diffuse reflectance spectroscopy of soils

Author:
Sarathjith, M.C.,   et al.   ; Das, Bhabani Sankar; Wani, Suhas P.; Sahrawat, Kanwar L.;     Show all 4 Authors
Source:
Geoderma 2016 v.267 pp. 1-9
ISSN:
0016-7061
Subject:
Alfisols; Vertisols; algorithms; clay fraction; covariance; geometry; iron; least squares; model validation; models; organic carbon; pH; prediction; reflectance; reflectance spectroscopy; sand; wavelengths
Abstract:
... Diffuse reflectance spectroscopy (DRS) operating in 350–2500nm wavelength range is fast emerging as a rapid and non-invasive technique for analyzing multiple soil attributes. Because the spectral reflectance values in this range of wavelengths are highly co-linear, it is important to select relevant spectral information from the reflectance spectra to build a robust spectral algorithm. The objecti ...
DOI:
10.1016/j.geoderma.2015.12.031