Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386714095> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W4386714095 abstract "Abstract The determination of physicochemical properties of crude oils is a very important and time‐intensive process that needs elaborate laboratory procedures. Over the last few decades, several correlations have been developed to estimate these properties, but they have been very limited in their scope and range. In recent years, methods based on spectral data analysis have been shown to be very promising in characterizing petroleum crude. In this work, the physicochemical properties of crude oils using Fourier transform infrared (FTIR) spectrums are predicted. A total of 107 samples of FTIR spectral data consisting of 6840 wavenumbers is used. One dimensional convolutional neural networks (CNNs) were used employing FTIR spectral data as the one‐dimensional input and Keras and TensorFlow were used for model building. The Root Mean Square Error decreased from 160 to around 60 for viscosity when compared to previous machine learning methods like partial least squares (PLS), principal component regression (PCR), and partial least squares regression with genetic algorithm (PLS‐GA) on the same data. The important hyper‐parameters of the CNN were optimized. In addition, a comparison of results obtained with different neural network architectures is presented. Some common preprocessing techniques were also tested on the spectral data to determine their impact on model performance. To increase interpretability, the intermediate neural network layers were analyzed to reveal what the convolutions represented, and sensitivity analysis was done to gather key insights about the wavenumbers that were the most important for prediction of the crude oil properties using the neural network." @default.
- W4386714095 created "2023-09-14" @default.
- W4386714095 creator A5000957204 @default.
- W4386714095 creator A5012535479 @default.
- W4386714095 creator A5046392850 @default.
- W4386714095 creator A5062755316 @default.
- W4386714095 date "2023-09-12" @default.
- W4386714095 modified "2023-10-18" @default.
- W4386714095 title "Deep chemometrics using one‐dimensional convolutional neural networks for predicting crude oil properties from FTIR spectral data" @default.
- W4386714095 cites W2038108991 @default.
- W4386714095 cites W2124290836 @default.
- W4386714095 cites W2556345765 @default.
- W4386714095 cites W2744790985 @default.
- W4386714095 cites W2763417926 @default.
- W4386714095 cites W2807567209 @default.
- W4386714095 cites W2945339512 @default.
- W4386714095 cites W2951230751 @default.
- W4386714095 cites W2999337073 @default.
- W4386714095 cites W3006522969 @default.
- W4386714095 cites W3100777112 @default.
- W4386714095 cites W3153636879 @default.
- W4386714095 cites W3169096570 @default.
- W4386714095 cites W3185419059 @default.
- W4386714095 cites W3206048862 @default.
- W4386714095 cites W4289878225 @default.
- W4386714095 doi "https://doi.org/10.1002/cjce.25076" @default.
- W4386714095 hasPublicationYear "2023" @default.
- W4386714095 type Work @default.
- W4386714095 citedByCount "0" @default.
- W4386714095 crossrefType "journal-article" @default.
- W4386714095 hasAuthorship W4386714095A5000957204 @default.
- W4386714095 hasAuthorship W4386714095A5012535479 @default.
- W4386714095 hasAuthorship W4386714095A5046392850 @default.
- W4386714095 hasAuthorship W4386714095A5062755316 @default.
- W4386714095 hasBestOaLocation W43867140951 @default.
- W4386714095 hasConcept C102519508 @default.
- W4386714095 hasConcept C105795698 @default.
- W4386714095 hasConcept C119857082 @default.
- W4386714095 hasConcept C120665830 @default.
- W4386714095 hasConcept C121332964 @default.
- W4386714095 hasConcept C134306372 @default.
- W4386714095 hasConcept C139945424 @default.
- W4386714095 hasConcept C151304367 @default.
- W4386714095 hasConcept C153180895 @default.
- W4386714095 hasConcept C154945302 @default.
- W4386714095 hasConcept C160892712 @default.
- W4386714095 hasConcept C186060115 @default.
- W4386714095 hasConcept C22354355 @default.
- W4386714095 hasConcept C27438332 @default.
- W4386714095 hasConcept C2781067378 @default.
- W4386714095 hasConcept C33923547 @default.
- W4386714095 hasConcept C34736171 @default.
- W4386714095 hasConcept C41008148 @default.
- W4386714095 hasConcept C50644808 @default.
- W4386714095 hasConcept C74887250 @default.
- W4386714095 hasConcept C81363708 @default.
- W4386714095 hasConcept C86803240 @default.
- W4386714095 hasConceptScore W4386714095C102519508 @default.
- W4386714095 hasConceptScore W4386714095C105795698 @default.
- W4386714095 hasConceptScore W4386714095C119857082 @default.
- W4386714095 hasConceptScore W4386714095C120665830 @default.
- W4386714095 hasConceptScore W4386714095C121332964 @default.
- W4386714095 hasConceptScore W4386714095C134306372 @default.
- W4386714095 hasConceptScore W4386714095C139945424 @default.
- W4386714095 hasConceptScore W4386714095C151304367 @default.
- W4386714095 hasConceptScore W4386714095C153180895 @default.
- W4386714095 hasConceptScore W4386714095C154945302 @default.
- W4386714095 hasConceptScore W4386714095C160892712 @default.
- W4386714095 hasConceptScore W4386714095C186060115 @default.
- W4386714095 hasConceptScore W4386714095C22354355 @default.
- W4386714095 hasConceptScore W4386714095C27438332 @default.
- W4386714095 hasConceptScore W4386714095C2781067378 @default.
- W4386714095 hasConceptScore W4386714095C33923547 @default.
- W4386714095 hasConceptScore W4386714095C34736171 @default.
- W4386714095 hasConceptScore W4386714095C41008148 @default.
- W4386714095 hasConceptScore W4386714095C50644808 @default.
- W4386714095 hasConceptScore W4386714095C74887250 @default.
- W4386714095 hasConceptScore W4386714095C81363708 @default.
- W4386714095 hasConceptScore W4386714095C86803240 @default.
- W4386714095 hasFunder F4320334593 @default.
- W4386714095 hasLocation W43867140951 @default.
- W4386714095 hasOpenAccess W4386714095 @default.
- W4386714095 hasPrimaryLocation W43867140951 @default.
- W4386714095 hasRelatedWork W1496127902 @default.
- W4386714095 hasRelatedWork W2037349157 @default.
- W4386714095 hasRelatedWork W2380927352 @default.
- W4386714095 hasRelatedWork W2413915177 @default.
- W4386714095 hasRelatedWork W2952177900 @default.
- W4386714095 hasRelatedWork W3021554815 @default.
- W4386714095 hasRelatedWork W4211209597 @default.
- W4386714095 hasRelatedWork W4366522197 @default.
- W4386714095 hasRelatedWork W64720297 @default.
- W4386714095 hasRelatedWork W2954124481 @default.
- W4386714095 isParatext "false" @default.
- W4386714095 isRetracted "false" @default.
- W4386714095 workType "article" @default.