Matches in SemOpenAlex for { <https://semopenalex.org/work/W4384207906> ?p ?o ?g. }
- W4384207906 endingPage "124946" @default.
- W4384207906 startingPage "124946" @default.
- W4384207906 abstract "Laser-induced breakdown spectroscopy (LIBS) is a well-established industrial tool with emerging relevance in high-stakes applications. To achieve its required analytical performance, LIBS is often coupled with advanced pattern-recognition algorithms, including machine learning models. Namely, artificial neural networks (ANNs) have recently become a frequently applied part of LIBS practitioners’ toolkit. Nevertheless, ANNs are generally applied in spectroscopy as black-box models, without a real insight into their predictions. Here, we apply various post-hoc interpretation techniques with the aim of understanding the decision-making of convolutional neural networks. Namely, we find synthetic spectra that yield perfect expected classification predictions and denote these spectra class-specific prototype spectra. We investigate the simplest possible convolutional neural network (consisting of a single convolutional and fully connected layers) trained to classify the extended calibration dataset collected for the ChemCam laser-induced breakdown spectroscopy instrument of the Curiosity Mars rover. The trained convolutional neural network predominantly learned meaningful spectroscopic features which correspond to the elements comprising the major oxides found in the calibration targets. In addition, the discrete convolution operation with the learnt filters results in a crude baseline correction." @default.
- W4384207906 created "2023-07-14" @default.
- W4384207906 creator A5001632758 @default.
- W4384207906 creator A5031110792 @default.
- W4384207906 creator A5065663908 @default.
- W4384207906 creator A5077439582 @default.
- W4384207906 creator A5077513667 @default.
- W4384207906 creator A5082160514 @default.
- W4384207906 date "2024-01-01" @default.
- W4384207906 modified "2023-10-01" @default.
- W4384207906 title "Interpreting convolutional neural network classifiers applied to laser-induced breakdown optical emission spectra" @default.
- W4384207906 cites W1593822055 @default.
- W4384207906 cites W1632317248 @default.
- W4384207906 cites W1964258422 @default.
- W4384207906 cites W1981639777 @default.
- W4384207906 cites W1987953420 @default.
- W4384207906 cites W1996484899 @default.
- W4384207906 cites W2016999855 @default.
- W4384207906 cites W2017784810 @default.
- W4384207906 cites W2024339761 @default.
- W4384207906 cites W2037431508 @default.
- W4384207906 cites W2054078143 @default.
- W4384207906 cites W2059856562 @default.
- W4384207906 cites W2066556866 @default.
- W4384207906 cites W2074545163 @default.
- W4384207906 cites W2082289296 @default.
- W4384207906 cites W2088567173 @default.
- W4384207906 cites W2091379531 @default.
- W4384207906 cites W2101926813 @default.
- W4384207906 cites W2120620624 @default.
- W4384207906 cites W2163103958 @default.
- W4384207906 cites W2201699903 @default.
- W4384207906 cites W2506133648 @default.
- W4384207906 cites W2514029986 @default.
- W4384207906 cites W2529389662 @default.
- W4384207906 cites W2563285874 @default.
- W4384207906 cites W2604409408 @default.
- W4384207906 cites W2618530766 @default.
- W4384207906 cites W2621344075 @default.
- W4384207906 cites W2744446924 @default.
- W4384207906 cites W2792458396 @default.
- W4384207906 cites W2810174094 @default.
- W4384207906 cites W2899284235 @default.
- W4384207906 cites W2909922240 @default.
- W4384207906 cites W2917664838 @default.
- W4384207906 cites W2919115771 @default.
- W4384207906 cites W2971670346 @default.
- W4384207906 cites W2971885458 @default.
- W4384207906 cites W2981731882 @default.
- W4384207906 cites W2997428643 @default.
- W4384207906 cites W3003808549 @default.
- W4384207906 cites W3006025378 @default.
- W4384207906 cites W3006091360 @default.
- W4384207906 cites W3007750780 @default.
- W4384207906 cites W3008511810 @default.
- W4384207906 cites W3023440774 @default.
- W4384207906 cites W3042243247 @default.
- W4384207906 cites W3043751454 @default.
- W4384207906 cites W3102564565 @default.
- W4384207906 cites W3105148046 @default.
- W4384207906 cites W3109229326 @default.
- W4384207906 cites W3114527129 @default.
- W4384207906 cites W3147012193 @default.
- W4384207906 cites W3150912719 @default.
- W4384207906 cites W3155672759 @default.
- W4384207906 cites W3158711593 @default.
- W4384207906 cites W3180692978 @default.
- W4384207906 cites W4210343698 @default.
- W4384207906 cites W4220744085 @default.
- W4384207906 cites W4294156759 @default.
- W4384207906 cites W605824061 @default.
- W4384207906 cites W893139541 @default.
- W4384207906 doi "https://doi.org/10.1016/j.talanta.2023.124946" @default.
- W4384207906 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37454514" @default.
- W4384207906 hasPublicationYear "2024" @default.
- W4384207906 type Work @default.
- W4384207906 citedByCount "0" @default.
- W4384207906 crossrefType "journal-article" @default.
- W4384207906 hasAuthorship W4384207906A5001632758 @default.
- W4384207906 hasAuthorship W4384207906A5031110792 @default.
- W4384207906 hasAuthorship W4384207906A5065663908 @default.
- W4384207906 hasAuthorship W4384207906A5077439582 @default.
- W4384207906 hasAuthorship W4384207906A5077513667 @default.
- W4384207906 hasAuthorship W4384207906A5082160514 @default.
- W4384207906 hasConcept C105795698 @default.
- W4384207906 hasConcept C119857082 @default.
- W4384207906 hasConcept C120665830 @default.
- W4384207906 hasConcept C121332964 @default.
- W4384207906 hasConcept C153180895 @default.
- W4384207906 hasConcept C154945302 @default.
- W4384207906 hasConcept C165838908 @default.
- W4384207906 hasConcept C185592680 @default.
- W4384207906 hasConcept C32891209 @default.
- W4384207906 hasConcept C33923547 @default.
- W4384207906 hasConcept C41008148 @default.
- W4384207906 hasConcept C45347329 @default.
- W4384207906 hasConcept C50497907 @default.
- W4384207906 hasConcept C50644808 @default.