Orthogonal signal correction of near-infrared spectra

The selection of optimal preprocessing is among the main bottlenecks in chemometric data analysis. Preprocessing currently is a burden, since a multitude of different preprocessing methods is available for, e.g., baseline correction, smoothing, and alignment, but it is not clear beforehand which method(s) should be used for which data set. The process of preprocessing selection is often limited to trial-and-error and is therefore considered somewhat subjective. In this paper, we present a novel, simple, and effective approach for preprocessing selection. The defining feature of this approach is a design of experiments. On the basis of the design, model performance of a few well-chosen preprocessing methods, and combinations thereof (called strategies) is evaluated. Interpretation of the main effects and interactions subsequently enables the selection of an optimal preprocessing strategy. The presented approach is applied to eight different spectroscopic data sets, covering both calibration and classification challenges. We show that the approach is able to select a preprocessing strategy which improves model performance by at least 50% compared to the raw data; in most cases, it leads to a strategy very close to the true optimum. Our approach makes preprocessing selection fast, insightful, and objective.

show abstract

“…Finally, Pareto scaling was chosen for the scaling step, because this is one of the more commonly applied scaling methods in infrared data. 27 …”

mentioning

confidence: 99%

Simple and Effective Way for Data Preprocessing Selection Based on Design of Experiments

et al. 2015

View full text Add to dashboard Cite

show abstract

“…Based on the 54 NIR samples three PLS models were built using the three pretreatment methods and compared. When implementing OSC, a direct orthogonal signal correction algorithm [8] …”

Section: Resultsmentioning

confidence: 99%

Comparative Study of NIR-based Prediction Methods for Biomass Weight Loss Profiles

Cho¹,

Liu²

2012

Clean Technology

View full text Add to dashboard Cite

: Biomass has become a major feedstock for bioenergy and other bio-based products because of its renewability and environmental benefits. Various researches have been done in the prediction of crucial characteristics of biomass, including the active utilization of spectroscopy data. Near infrared (NIR) spectroscopy has been widely used because of its attractive features: it's non-destructive and cost-effective producing fast and reliable analysis results. This work developed the multivariate statistical scheme for predicting weight loss profiles based on the utilization of NIR spectra data measured for six lignocellulosic biomass types. Wavelet analysis was used as a compression tool to suppress irrelevant noise and to select features or wavelengths that better explain NIR data. The developed scheme was demonstrated using real NIR data sets, in which different prediction models were evaluated in terms of prediction performance. In addition, the benefits of using right pretreatment of NIR spectra were also given. In our case, it turned out that compression of high-dimensional NIR spectra by wavelet and then PLS modeling yielded more reliable prediction results without handling full set of noisy data. This work showed that the developed scheme can be easily applied for rapid analysis of biomass.

show abstract

“…This procedure is repeated to obtain predictions for all samples. The method of orthogonal signal correction (OSC), described by Wold et al [26], was used to remove irrelevant systematic data, mainly the result of light scattering. In short, the method involves the removal of spectral X data that is unrelated to Y.…”

Section: Reflectance Spectroscopymentioning

confidence: 99%

Screening for efficient cold hardening in a breeding population of Salix using near infrared reflectance spectroscopy

Lennartsson

Ögren

2004

Ann. For. Sci.

View full text Add to dashboard Cite

-The inheritance of cold hardening components -the timing of onset and the inherent rate -was studied in Salix spp. This was achieved by characterising the F 2 population of a cross between an early-and-rapidly hardening clone and a late-and-slowly hardening clone. The cold hardiness of stems was estimated using the infrared reflectance spectra of dried and homogenised samples. This method was first calibrated against the freeze test method. The timing of growth cessation was used to determine the onset of cold hardening. In the F 2 progeny, traits were partly recombined as indicated by the occurrence of clones with early-and-slowly hardening characteristics. The frequency distributions of clones also indicated that the timing of onset and the inherent rate of hardening were independently inherited traits. None of the clones exhibited the desirable late-and-rapidly hardening characteristics, combining a long growing period with effective cold hardening. This is not surprising since few F 2 clones exhibited late hardening. acclimatation au froid / arrêt de croissance / spectroscopie du proche-infrarouge / Salix / amélioration génétique des arbres

show abstract

Orthogonal signal correction of near-infrared spectra

Cited by 983 publications

References 10 publications

Simple and Effective Way for Data Preprocessing Selection Based on Design of Experiments

Simple and Effective Way for Data Preprocessing Selection Based on Design of Experiments

Comparative Study of NIR-based Prediction Methods for Biomass Weight Loss Profiles

Screening for efficient cold hardening in a breeding population of Salix using near infrared reflectance spectroscopy

Contact Info

Product

Resources

About