Use of correspondence analysis partial least squares on linear and unimodal data

Frisvad, Jens Christian; Norsker, Merete

doi:10.1002/(sici)1099-128x(199609)10:5/6<677::aid-cem468>3.3.co;2-j

Cited by 2 publications

(3 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…10) shows a distinctive arch. Initially, it was thought that this is indicative of the horsehoe effect because of the distortion of the data as a result of nonlinearity in spectral regions when using absorbances covering large regions of contiguous wavenumbers [34,35]. Analysing these plots without knowledge of this effect could lead one to believe there is a connection between the high and low viscous samples because of their scoring on LV2.…”

Section: Partial Least Squares Modelmentioning

confidence: 99%

Use of inline near‐infrared spectroscopy to predict the viscosity of shampoo using multivariate analysis

Haroon

Arafeh

Martin

et al. 2019

Intern J of Cosmetic Sci

View full text Add to dashboard Cite

ObjectiveIn the personal care industry, viscosity is a critical quality attribute that influences product quality and process economics. Like many industrial liquids, personal care liquids are complex non‐Newtonian liquids made up of aqueous surfactant systems whose viscosity depends on the build‐up of micellar networks. Measuring the viscosity of complex liquids offline is easily done using benchtop rheometers and viscometers. The challenge lies in measuring the viscosity of personal care liquids online during manufacturing. Being able to track the viscosity of such products through their manufacturing cycle will not only allow for better process control but also more enhanced quality control. Therefore, the aim of this work was to investigate how proxy measurements using inline near‐infrared (NIR) spectroscopy in transmission mode can be used to predict the viscosity of shampoo. NIR spectroscopy has not, to the best our knowledge, been used to predict the viscosity of complex surfactant systems like shampoo and could significantly affect the way quality is monitored in a manufacturing environment.MethodThis work focuses on viscosity changes because of differences in chloride content as salt is often used to adjust viscosity. The relationship between salt content and the viscosity of shampoo is well known following the salt curve. From an industrial perspective the region of interest for the formulation studied in this work only covers a small section of this curve. Therefore, two predictive models were developed: one covering the full range of the salt curve and another focusing on the industrially applicable region.ResultModels were produced using partial least squares (PLS) where both datasets showed some predictive ability with the concentrated region of interest showing enhanced performance [root mean square error of prediction (RMSEP) – 2.32 Pa s] compared with the larger range (RMSEP – 4.44 Pa s).ConclusionThis work provides a good starting point for developing robust predictive models for in situ viscosity measurements for shampoo manufacturing, where further work into different sources of variation and the extent of the modelling capability with regards to different formulations should be studied.

show abstract

Section: Partial Least Squares Modelmentioning

confidence: 99%

Use of inline near‐infrared spectroscopy to predict the viscosity of shampoo using multivariate analysis

Haroon

Arafeh

Martin

et al. 2019

Intern J of Cosmetic Sci

View full text Add to dashboard Cite

show abstract

“…This method works to predict the beetle community from the variables on the vegetation structure or the environment but not to predict the beetle community from the plant community data. The reasons are twofold: (1) canonical correspondence analysis breaks down when the number of predictor variables, the individual plant species in our case, is larger than the number of sites, and (2) the method uses linear combinations-weighted sums (Jongman et al 1995)-of the predictor variables, which does not work well when the community data in the predictor role show a unimodal structure, a strong qualitative nature and/or are sum constrained, i.e., when the predictor community is better analyzed by a correspondence analysis technique than by a linear technique such as principal components analysis , Frisvad and Norsker 1996.…”

Section: Introductionmentioning

confidence: 99%

“…WA-PLS is popular in palaeoecology for reconstructing palaeoenvironments from fossil assemblages (Birks 1998). WA-PLS is called correspondence analysis partial least squares by Frisvad and Norsker (1996). The community data take the role of response variables in CCA-PLS and the role of predictor variables in WA-PLS (Table 1).…”

Section: Introductionmentioning

confidence: 99%

Co-Correspondence Analysis: A New Ordination Method to Relate Two Community Compositions

Braak

Schaffers

2004

Ecology

150

127

View full text Add to dashboard Cite

A new ordination method, called co‐correspondence analysis, is developed to relate two types of communities (e.g., a plant community and an animal community) sampled at a common set of sites in a direct way. The method improves the simple, indirect approach of applying correspondence analysis (reciprocal averaging) to the separate species data sets and correlating the resulting ordination axes. Co‐correspondence analysis maximizes the weighted covariance between weighted averaged species scores of one community and weighted averaged species scores of the other community. It thus attempts to identify the patterns that are common to both communities. Both a symmetric descriptive and an asymmetric predictive form are developed. The symmetric form relates to co‐inertia analysis and the asymmetric, predictive form to partial least‐squares regression. In two examples the predictive power of co‐correspondence analysis is compared with that of canonical correspondence analyses on syntaxonomic and environmental data. In the first example, carabid beetles in roadside verges are shown to be more closely related to plant species composition than to vegetation structure (biomass, height, roughness, among others), and, in the second example, bryophytes in spring meadows are shown to be more closely related to the species composition of the vascular plants than to the measured water chemistry.

show abstract

Use of correspondence analysis partial least squares on linear and unimodal data

Cited by 2 publications

References 1 publication

Use of inline near‐infrared spectroscopy to predict the viscosity of shampoo using multivariate analysis

Use of inline near‐infrared spectroscopy to predict the viscosity of shampoo using multivariate analysis

Co-Correspondence Analysis: A New Ordination Method to Relate Two Community Compositions

Contact Info

Product

Resources

About