Correction of Temperature-Induced Spectral Variations by Loading Space Standardization

Chen, Zengping; Morris, Julian; Martin, E.B.

doi:10.1021/ac040119g

Cited by 39 publications

(39 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One of the main issues with CPDS, as identified by Chen et al [24], is the need to determine a number of tuning parameters. Apart from the number of latent variables to include in the PLS calibration model for the reference temperature, there are three additional parameters to be determined: the width of the band in ) ( k t Q (2w+1); the number of latent variables in the PLS model to obtain ) ( k t Q ; and the order of the polynomial.…”

Section: Continuous Piecewise Direct Standardizationmentioning

confidence: 99%

“…It was proposed that these tuning parameters are determined by using cross-validation [23] [27]. Although the polynomial is typically taken to be second order by appealing to the established findings in the literature [24][28] [29], the application of cross-validation to attain the other tuning parameters is a time-consuming process.…”

Section: Continuous Piecewise Direct Standardizationmentioning

confidence: 99%

“…The main idea behind the loading space standardization (LSS) approach [24] is to perform standardization on the loading space, as opposed to the original data space. The philosophy being that the loading space may be a more sparse and robust representation of the original data, and hence may provide more reliable standardization results.…”

Section: Loading Space Standardizationmentioning

confidence: 99%

“…For example, there are three tuning factors in CPDS to be determined: the width of the band in ) ( k t Q (2w+1), the number of latent variables in the PLS modelling algorithm to obtain ) ( k t Q , and the order of the polynomial function, whilst in LSS, the number of latent factors retained in the SVD algorithm and the order of the polynomial function require to be determined. Although the polynomial function is typically taken to be second order by appealing to the established findings in the literature [24][28] [29], the cross-validation of the other tuning parameters is still a time-consuming process.…”

Section: Implementation Complexitymentioning

confidence: 99%

“…To extend the concept of PDS to continuous external factors, such as temperature as observed in an online or at-line industrial application, the continuous piecewise direct standardization (CPDS) algorithm was proposed [23]. More recently, loading space standardization (LSS) [24] was proposed where the standardization is implemented in the loading space derived from the data, as opposed to the original data space. These approaches are explored in more detail in § 2.3 and § 2.4.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

The impact of temperature variations on spectroscopic calibration modelling: a comparative study

Chen

Martin

2007

Journal of Chemometrics

Self Cite

View full text Add to dashboard Cite

Abstract:Temperature fluctuations can have a significant impact on the repeatability of spectral measurements and as a consequence can adversely affect the resulting calibration model. More specifically, when test samples measured at temperatures unseen in the training data set are presented to the model, degraded predictive performance can materialize. Current methods for addressing the temperature variations in a calibration model can be categorized into two classescalibration model based approaches, and spectra standardization methodologies. This paper presents a comparative study on a number of strategies reported in the literature including partial least squares (PLS), continuous piecewise direct standardization (CPDS) and loading space standardization (LSS), in terms of the practical applicability of the algorithms, their implementation complexity, and their predictive performance. It was observed from the study that the global modelling approach, where latent variables are initially extracted from the spectra using PLS, and then augmented with temperature as the independent variable, achieved the best predictive performance. In addition, the two spectra standardization methods, CPDS and LSS, did not provide consistently enhanced performance over the conventional global modelling approach, despite the additional effort in terms of standardizing the spectra across different temperatures. Considering the algorithmic complexity and resulting calibration accuracy, it is concluded that the global modelling (with temperature) approach should be first considered for the development of a calibration model where temperature variations are known to affect the fundamental data, prior to investigating the more powerful spectra standardization approaches.

show abstract

Section: Continuous Piecewise Direct Standardizationmentioning

confidence: 99%

Section: Continuous Piecewise Direct Standardizationmentioning

confidence: 99%

Section: Loading Space Standardizationmentioning

confidence: 99%

Section: Implementation Complexitymentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

The impact of temperature variations on spectroscopic calibration modelling: a comparative study

Chen

Martin

2007

Journal of Chemometrics

Self Cite

View full text Add to dashboard Cite

show abstract

Continuous Crystallisation

Brown

McGlone

Florence

2017

Continuous Manufacturing of Pharmaceuticals

View full text Add to dashboard Cite

Mixing 2) Nucleation 3) Growth 4) Filter/wash/dry Required to:  Produce consistent composition  Control crystallisation driving force  Influence flow rate, shear-kinetic effects  Consistent suspension of seed and product Controlled via:  Supersaturation  High shear  External fields, e.g. ultrasound, nonphotochemical laser induced nucleation  Seed. Seeds produced via dry milling, wet media milling, precipitation, recycle, dissolution, spray drying or secondary nucleation Controlled to avoid:  Fouling  Agglomeration  Dissolution  Crystalline form transformation(s) Controlled via:  Supersaturation (typically low) via cooling, anti-solvent, evaporation  Effective heat/mass transfer Ensures:  Efficient desupersaturation Controlled to avoid:  Fouling  Agglomeration  Attrition (particle breakage)  Dissolution  Crystalline form transformation(s) Required to:  Create filter cake  Remove mother liquor and impurities  Maintain particle attributes Controlled to avoid:  Agglomeration  Attrition (particle breakage)Continuous crystallisation has been implemented for many decades in other manufacturing sectors, typically for large volume commodity chemicals, and offers a range of potential advantages [16,17] including lower operating and capital costs, reduced down time and more efficient use of energy and materials. Cooling and anti-solvent crystallisation are commonly used in industrial applications and can be readily implemented in continuous. The aim is to follow a controlled trajectory through the solubility phase diagram (section 1.2).

show abstract

Process analytical technology and compensating for nonlinear effects in process spectroscopic data for improved process monitoring and control

Chen¹,

Morris²

2009

Biotechnology Journal

Self Cite

View full text Add to dashboard Cite

Robust fit-for-purpose multivariate calibration models are of critical importance to on-line/in-line quantitative monitoring of bio-chemicals and pharmaceuticals using spectroscopic instruments. Unlike in off-line assays, the spectroscopic measurements in on-line/in-line real-time applications are almost inevitably subjected to variations in measurement conditions (e.g. temperature) and samples' physical properties (e.g. cell density, particle size, sample compactness), which can invalidate the assumption of a linear relationship between the spectroscopic measurements and the concentrations of the target chemical components. This Biotech Highlight discusses the effects of such variations on spectroscopic measurements, and presents an overview of recent work on modelling and correcting of the detrimental effects of variations in measurement conditions and samples' physical properties.A number of application studies to complex datasets and an industrial plant demonstrate the methodologies and algorithms discussed.

show abstract

Correction of Temperature-Induced Spectral Variations by Loading Space Standardization

Cited by 39 publications

References 27 publications

The impact of temperature variations on spectroscopic calibration modelling: a comparative study

The impact of temperature variations on spectroscopic calibration modelling: a comparative study

Continuous Crystallisation

Process analytical technology and compensating for nonlinear effects in process spectroscopic data for improved process monitoring and control

Contact Info

Product

Resources

About