2020
DOI: 10.1016/j.forc.2019.100209
|View full text |Cite
|
Sign up to set email alerts
|

Forensic analysis of red lipsticks using ATR-FTIR spectroscopy and chemometrics

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

1
41
0

Year Published

2020
2020
2024
2024

Publication Types

Select...
8
1

Relationship

1
8

Authors

Journals

citations
Cited by 50 publications
(42 citation statements)
references
References 20 publications
1
41
0
Order By: Relevance
“…This type of algorithm is widely used for spectral data analysis in different methods and elds of application. [56][57][58][59][60][61] This is because of the high dimensionality nature of the spectroscopic data analysed in this work and the ability of LDA to reduce these dimensions to just a few while preserving most of the information, which allows for feature extraction rather than feature selection. Using the Raman spectra of each cell obtained with different wavelengths as input, the LDA algorithm was used to classify the different cells of the combinatorial sample according to the following classi-cation targets: efficiency, V oc and [Zn/Ge] ratio.…”
Section: Machine Learning Approach For Device Performance Analysismentioning
confidence: 99%
“…This type of algorithm is widely used for spectral data analysis in different methods and elds of application. [56][57][58][59][60][61] This is because of the high dimensionality nature of the spectroscopic data analysed in this work and the ability of LDA to reduce these dimensions to just a few while preserving most of the information, which allows for feature extraction rather than feature selection. Using the Raman spectra of each cell obtained with different wavelengths as input, the LDA algorithm was used to classify the different cells of the combinatorial sample according to the following classi-cation targets: efficiency, V oc and [Zn/Ge] ratio.…”
Section: Machine Learning Approach For Device Performance Analysismentioning
confidence: 99%
“…A two dimensional plot was presented as it provided easy visualization. The same method was reported by Chophi et al [19] and Sharma et al [20]. These four PCs were tried in different set of combinations to investigate which PC combination provided better discrimination between vermilion samples.…”
Section: Resultsmentioning
confidence: 99%
“…Such drawbacks can be overlooked by utilizing non-destructive methods of analysis to generate objective results with high accuracy in quick time. For example, spectroscopic techniques like Attenuated Total Reflectance Fourier Transform Infrared Spectroscopy (ATR-FTIR) is proven to be useful in analysis of exhibits from all fields of forensic science like paints [17], inks [18], lipstick [19], kajal [20], body fluids [21][22][23], soil [24], and in the field of questioned document [25].…”
mentioning
confidence: 99%
“…This study shows the ability to classify tire samples using their elemental signature (from LIBS) and the analysis of those signatures using principal component analysis (PCA) combined with linear discriminant analysis (LDA), a relatively simple machine learning technique. PCA has seen use in forensics for many years, [18][19][20] being a technique that uses the variance within the data to reduce the dimensionality of the data to the most relevant variables. PCA tends to be misused due to its simplicity, but it is especially useful in reducing the dimensionality of spectral data where a lot of points are simply contributions of noise.…”
Section: Introductionmentioning
confidence: 99%