Encyclopedia of Analytical Chemistry 2000
DOI: 10.1002/9780470027318.a6002
|View full text |Cite
|
Sign up to set email alerts
|

Artificial Intelligence and Expert Systems in Mass Spectrometry

Abstract: This article provides a brief introduction to aspects of mass spectrometry (MS) that employ artificial intelligence (AI) and expert system (ES) technology. These areas have grown rapidly with the development of computer software and hardware capabilities. In many cases, they have become fundamental parts of modern mass spectrometers. Specific attention is paid to applications that demonstrate how important features of MS are now dependent on AI and ESs. The following topics are specifically covered: … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
13
0

Year Published

2002
2002
2018
2018

Publication Types

Select...
6
2

Relationship

5
3

Authors

Journals

citations
Cited by 13 publications
(13 citation statements)
references
References 185 publications
0
13
0
Order By: Relevance
“…The unsupervised learning algorithm principal components analysis (PCA) 26,29,30 was used to visualized any natural variations within the data set.…”
Section: Discussionmentioning
confidence: 99%
“…The unsupervised learning algorithm principal components analysis (PCA) 26,29,30 was used to visualized any natural variations within the data set.…”
Section: Discussionmentioning
confidence: 99%
“…Furthermore, the spectra are complex and multidimensional in nature, so they do not easily lend themselves to simple visual interpretation; this is compounded by the fact that the data set for all three experiments is substantial, with a total of 450 spectra, each containing 441 wave numbers. However, with the advent of modern machine learning approaches, the opportunity now exists to analyze such complex high-dimensional spectral patterns (7,46) and to extract an answer to a question of biological interest with much lower dimensionality, i.e., "What is the bacterial load on the meat surface?" Therefore, as described above, the supervised-learning method of PLS regression was calibrated and cross validated with the FT-IR spectral data and the known log 10 (TVC) values from experiments 1 and 2 ( Table 2 shows the details and TVC levels) before being challenged by the independent and "unseen" test set of data from experiment 3.…”
Section: Cfu Gmentioning
confidence: 99%
“…This dimensionality reduction occurs broadly in one of two ways; either using an unsupervised algorithm to summarise the natural variance in the data, or by using supervised learning via partial least squares (PLS) regression or artificial neural networks which is targeted based upon the experimenters a priori knowledge of the samples being studied. [27][28][29][30] In the first case, variance due to experimental error may mask the interesting differerences relating to the hypothesis being studied. If this is the case, then supervised methods, which need to be used with suitable model validation steps, can offer a targeted approach to studying spectral variance which correlates with the patterns expected from the data.…”
Section: Multiplexingmentioning
confidence: 99%