Application of Principal Component Analysis in Organic Chemistry

Zalewski, Romuald I.

doi:10.1002/9780470171974.ch3

Cited by 8 publications

(2 citation statements)

References 129 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is particularly crucial because approximately one quarter of the food produced and supplied is lost within the food supply chain (Kummu et al, 2012). Food production, distribution, and consumption are the key segments within the agribusiness chains (Gurnell & Grabowski, 2016), where Zalewski et al (1991) ranked the food sector as the foremost vital and complex of the economy. It capitalizes on value creation, collaboration, and integration of business processes (Ho et al, 2002) and optimizes profits from integration among shareholders (Chopra & Sodhi, 2004).…”

Section: Introductionmentioning

confidence: 99%

Economic dynamics of agri‐food supply chains at a macrolevel

Gildas

2024

World Food Policy

View full text Add to dashboard Cite

This paper employs a comprehensive methodology that integrates demand and supply elasticities, performance metrics, and data envelopment analysis to analyze agri‐food supply chains at a macroeconomic level. It utilizes data from a global sample of 53 countries spanning the years 2000 to 2019. The findings from various levels of analysis reveal several key insights: first, Australia or Cameroon should allocate all their food resources to enhance the capacity utilization of their Food Supply Chains (FSC). Second, Ghana or New Zealand may concentrate 100% of their resources on improving the Responsiveness of their FSC. Third, Switzerland, Turkey, and the United States should allocate 100% of their food resources to adjust resource allocation within their FSC. Fourth, for countries like Costa Rica and Canada, the allocation should be 19% to capacity utilization and 81% to resource allocation. Fifth, countries such as Cyprus, the Dominican Republic, Ecuador, and El Salvador should prioritize 12% of inputs for resilience and allocate the remaining 88% to resource allocation. Sixth, for countries like Nicaragua, Niger, Nigeria, Russia, South Korea, Serbia, Senegal, and Singapore, the allocation should be 28% of inputs to responsiveness, with the majority, 72%, directed to resource allocation. Sixth, Nigeria, Ethiopia, and Ghana have better performance across critical variables. This study introduces an innovative framework that facilitates the interaction of agri‐food supply chains with various macroeconomic variables, including GDP, inflation, corruption, food security, and nutrition, opening new avenues for a holistic understanding of these systems.

show abstract

Section: Introductionmentioning

confidence: 99%

Economic dynamics of agri‐food supply chains at a macrolevel

Gildas

2024

World Food Policy

View full text Add to dashboard Cite

show abstract

“…Unfortunately, a small number of samples and the large dimension of inputs construct the typical dilemma for the real data sets. In analytical chemistry, principal component analysis (PCA), as a traditional method, is regularly applied for the dimension-reduction of data [13]. Although PCA has a wide range of application areas such as data compression to eliminate redundancy and data noise cancellation.…”

Section: Introductionmentioning

confidence: 99%

Multiple Compounds Recognition from The Tandem Mass Spectral Data Using Convolutional Neural Network

Jian

Wang

et al. 2019

Molecules

View full text Add to dashboard Cite

Mixtures analysis can provide more information than individual components. It is important to detect the different compounds in the real complex samples. However, mixtures are often disturbed by impurities and noise to influence the accuracy. Purification and denoising will cost a lot of algorithm time. In this paper, we propose a model based on convolutional neural network (CNN) which can analyze the chemical peak information in the tandem mass spectrometry (MS/MS) data. Compared with traditional analyzing methods, CNN can reduce steps in data preprocessing. This model can extract features of different compounds and classify multi-label mass spectral data. When dealing with MS data of mixtures based on the Human Metabolome Database (HMDB), the accuracy can reach at 98%. In 600 MS test data, 451 MS data were fully detected (true positive), 142 MS data were partially found (false positive), and 7 MS data were falsely predicted (true negative). In comparison, the number of true positive test data for support vector machine (SVM) with principal component analysis (PCA), deep neural network (DNN), long short-term memory (LSTM), and XGBoost respectively are 282, 293, 270, and 402; the number of false positive test data for four models are 318, 284, 198, and 168; the number of true negative test data for four models are 0, 23, 7, 132, and 30. Compared with the model proposed in other literature, the accuracy and model performance of CNN improved considerably by separating the different compounds independent MS/MS data through three-channel architecture input. By inputting MS data from different instruments, adding more offset MS data will make CNN models have stronger universality in the future.

show abstract

References

2010

Solvents and Solvent Effects in Organic Chemistry

View full text Add to dashboard Cite

Application of Principal Component Analysis in Organic Chemistry

Cited by 8 publications

References 129 publications

Economic dynamics of agri‐food supply chains at a macrolevel

Economic dynamics of agri‐food supply chains at a macrolevel

Multiple Compounds Recognition from The Tandem Mass Spectral Data Using Convolutional Neural Network

References

Contact Info

Product

Resources

About